| 3 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 | // SPDX-License-Identifier: GPL-2.0 /* Copyright 2011-2014 Autronica Fire and Security AS * * Author(s): * 2011-2014 Arvid Brodin, arvid.brodin@alten.se * * Frame handler other utility functions for HSR and PRP. */ #include "hsr_slave.h" #include <linux/etherdevice.h> #include <linux/if_arp.h> #include <linux/if_vlan.h> #include "hsr_main.h" #include "hsr_device.h" #include "hsr_forward.h" #include "hsr_framereg.h" bool hsr_invalid_dan_ingress_frame(__be16 protocol) { return (protocol != htons(ETH_P_PRP) && protocol != htons(ETH_P_HSR)); } static rx_handler_result_t hsr_handle_frame(struct sk_buff **pskb) { struct sk_buff *skb = *pskb; struct hsr_port *port; struct hsr_priv *hsr; __be16 protocol; /* Packets from dev_loopback_xmit() do not have L2 header, bail out */ if (unlikely(skb->pkt_type == PACKET_LOOPBACK)) return RX_HANDLER_PASS; if (!skb_mac_header_was_set(skb)) { WARN_ONCE(1, "%s: skb invalid", __func__); return RX_HANDLER_PASS; } port = hsr_port_get_rcu(skb->dev); if (!port) goto finish_pass; hsr = port->hsr; if (hsr_addr_is_self(port->hsr, eth_hdr(skb)->h_source)) { /* Directly kill frames sent by ourselves */ kfree_skb(skb); goto finish_consume; } /* For HSR, only tagged frames are expected (unless the device offloads * HSR tag removal), but for PRP there could be non tagged frames as * well from Single attached nodes (SANs). */ protocol = eth_hdr(skb)->h_proto; if (!(port->dev->features & NETIF_F_HW_HSR_TAG_RM) && port->type != HSR_PT_INTERLINK && hsr->proto_ops->invalid_dan_ingress_frame && hsr->proto_ops->invalid_dan_ingress_frame(protocol)) goto finish_pass; skb_push(skb, ETH_HLEN); skb_reset_mac_header(skb); if ((!hsr->prot_version && protocol == htons(ETH_P_PRP)) || protocol == htons(ETH_P_HSR)) skb_set_network_header(skb, ETH_HLEN + HSR_HLEN); skb_reset_mac_len(skb); /* Only the frames received over the interlink port will assign a * sequence number and require synchronisation vs other sender. */ if (port->type == HSR_PT_INTERLINK) { spin_lock_bh(&hsr->seqnr_lock); hsr_forward_skb(skb, port); spin_unlock_bh(&hsr->seqnr_lock); } else { hsr_forward_skb(skb, port); } finish_consume: return RX_HANDLER_CONSUMED; finish_pass: return RX_HANDLER_PASS; } bool hsr_port_exists(const struct net_device *dev) { return rcu_access_pointer(dev->rx_handler) == hsr_handle_frame; } static int hsr_check_dev_ok(struct net_device *dev, struct netlink_ext_ack *extack) { /* Don't allow HSR on non-ethernet like devices */ if ((dev->flags & IFF_LOOPBACK) || dev->type != ARPHRD_ETHER || dev->addr_len != ETH_ALEN) { NL_SET_ERR_MSG_MOD(extack, "Cannot use loopback or non-ethernet device as HSR slave."); return -EINVAL; } /* Don't allow enslaving hsr devices */ if (is_hsr_master(dev)) { NL_SET_ERR_MSG_MOD(extack, "Cannot create trees of HSR devices."); return -EINVAL; } if (hsr_port_exists(dev)) { NL_SET_ERR_MSG_MOD(extack, "This device is already a HSR slave."); return -EINVAL; } if (is_vlan_dev(dev)) { NL_SET_ERR_MSG_MOD(extack, "HSR on top of VLAN is not yet supported in this driver."); return -EINVAL; } if (dev->priv_flags & IFF_DONT_BRIDGE) { NL_SET_ERR_MSG_MOD(extack, "This device does not support bridging."); return -EOPNOTSUPP; } /* HSR over bonded devices has not been tested, but I'm not sure it * won't work... */ return 0; } /* Setup device to be added to the HSR bridge. */ static int hsr_portdev_setup(struct hsr_priv *hsr, struct net_device *dev, struct hsr_port *port, struct netlink_ext_ack *extack) { struct net_device *hsr_dev; struct hsr_port *master; int res; /* Don't use promiscuous mode for offload since L2 frame forward * happens at the offloaded hardware. */ if (!port->hsr->fwd_offloaded) { res = dev_set_promiscuity(dev, 1); if (res) return res; } master = hsr_port_get_hsr(hsr, HSR_PT_MASTER); hsr_dev = master->dev; res = netdev_upper_dev_link(dev, hsr_dev, extack); if (res) goto fail_upper_dev_link; res = netdev_rx_handler_register(dev, hsr_handle_frame, port); if (res) goto fail_rx_handler; dev_disable_lro(dev); return 0; fail_rx_handler: netdev_upper_dev_unlink(dev, hsr_dev); fail_upper_dev_link: if (!port->hsr->fwd_offloaded) dev_set_promiscuity(dev, -1); return res; } int hsr_add_port(struct hsr_priv *hsr, struct net_device *dev, enum hsr_port_type type, struct netlink_ext_ack *extack) { struct hsr_port *port, *master; int res; if (type != HSR_PT_MASTER) { res = hsr_check_dev_ok(dev, extack); if (res) return res; } port = hsr_port_get_hsr(hsr, type); if (port) return -EBUSY; /* This port already exists */ port = kzalloc(sizeof(*port), GFP_KERNEL); if (!port) return -ENOMEM; port->hsr = hsr; port->dev = dev; port->type = type; if (type != HSR_PT_MASTER) { res = hsr_portdev_setup(hsr, dev, port, extack); if (res) goto fail_dev_setup; } list_add_tail_rcu(&port->port_list, &hsr->ports); synchronize_rcu(); master = hsr_port_get_hsr(hsr, HSR_PT_MASTER); netdev_update_features(master->dev); dev_set_mtu(master->dev, hsr_get_max_mtu(hsr)); return 0; fail_dev_setup: kfree(port); return res; } void hsr_del_port(struct hsr_port *port) { struct hsr_priv *hsr; struct hsr_port *master; hsr = port->hsr; master = hsr_port_get_hsr(hsr, HSR_PT_MASTER); list_del_rcu(&port->port_list); if (port != master) { netdev_update_features(master->dev); dev_set_mtu(master->dev, hsr_get_max_mtu(hsr)); netdev_rx_handler_unregister(port->dev); if (!port->hsr->fwd_offloaded) dev_set_promiscuity(port->dev, -1); netdev_upper_dev_unlink(port->dev, master->dev); } synchronize_rcu(); kfree(port); } |
| 2 11 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 | /* SPDX-License-Identifier: GPL-2.0-or-later */ /* * Berkeley style UIO structures - Alan Cox 1994. */ #ifndef __LINUX_UIO_H #define __LINUX_UIO_H #include <linux/kernel.h> #include <linux/thread_info.h> #include <linux/mm_types.h> #include <uapi/linux/uio.h> struct page; struct folio_queue; typedef unsigned int __bitwise iov_iter_extraction_t; struct kvec { void *iov_base; /* and that should *never* hold a userland pointer */ size_t iov_len; }; enum iter_type { /* iter types */ ITER_UBUF, ITER_IOVEC, ITER_BVEC, ITER_KVEC, ITER_FOLIOQ, ITER_XARRAY, ITER_DISCARD, }; #define ITER_SOURCE 1 // == WRITE #define ITER_DEST 0 // == READ struct iov_iter_state { size_t iov_offset; size_t count; unsigned long nr_segs; }; struct iov_iter { u8 iter_type; bool nofault; bool data_source; size_t iov_offset; /* * Hack alert: overlay ubuf_iovec with iovec + count, so * that the members resolve correctly regardless of the type * of iterator used. This means that you can use: * * &iter->__ubuf_iovec or iter->__iov * * interchangably for the user_backed cases, hence simplifying * some of the cases that need to deal with both. */ union { /* * This really should be a const, but we cannot do that without * also modifying any of the zero-filling iter init functions. * Leave it non-const for now, but it should be treated as such. */ struct iovec __ubuf_iovec; struct { union { /* use iter_iov() to get the current vec */ const struct iovec *__iov; const struct kvec *kvec; const struct bio_vec *bvec; const struct folio_queue *folioq; struct xarray *xarray; void __user *ubuf; }; size_t count; }; }; union { unsigned long nr_segs; u8 folioq_slot; loff_t xarray_start; }; }; static inline const struct iovec *iter_iov(const struct iov_iter *iter) { if (iter->iter_type == ITER_UBUF) return (const struct iovec *) &iter->__ubuf_iovec; return iter->__iov; } #define iter_iov_addr(iter) (iter_iov(iter)->iov_base + (iter)->iov_offset) #define iter_iov_len(iter) (iter_iov(iter)->iov_len - (iter)->iov_offset) static inline enum iter_type iov_iter_type(const struct iov_iter *i) { return i->iter_type; } static inline void iov_iter_save_state(struct iov_iter *iter, struct iov_iter_state *state) { state->iov_offset = iter->iov_offset; state->count = iter->count; state->nr_segs = iter->nr_segs; } static inline bool iter_is_ubuf(const struct iov_iter *i) { return iov_iter_type(i) == ITER_UBUF; } static inline bool iter_is_iovec(const struct iov_iter *i) { return iov_iter_type(i) == ITER_IOVEC; } static inline bool iov_iter_is_kvec(const struct iov_iter *i) { return iov_iter_type(i) == ITER_KVEC; } static inline bool iov_iter_is_bvec(const struct iov_iter *i) { return iov_iter_type(i) == ITER_BVEC; } static inline bool iov_iter_is_discard(const struct iov_iter *i) { return iov_iter_type(i) == ITER_DISCARD; } static inline bool iov_iter_is_folioq(const struct iov_iter *i) { return iov_iter_type(i) == ITER_FOLIOQ; } static inline bool iov_iter_is_xarray(const struct iov_iter *i) { return iov_iter_type(i) == ITER_XARRAY; } static inline unsigned char iov_iter_rw(const struct iov_iter *i) { return i->data_source ? WRITE : READ; } static inline bool user_backed_iter(const struct iov_iter *i) { return iter_is_ubuf(i) || iter_is_iovec(i); } /* * Total number of bytes covered by an iovec. * * NOTE that it is not safe to use this function until all the iovec's * segment lengths have been validated. Because the individual lengths can * overflow a size_t when added together. */ static inline size_t iov_length(const struct iovec *iov, unsigned long nr_segs) { unsigned long seg; size_t ret = 0; for (seg = 0; seg < nr_segs; seg++) ret += iov[seg].iov_len; return ret; } size_t copy_page_from_iter_atomic(struct page *page, size_t offset, size_t bytes, struct iov_iter *i); void iov_iter_advance(struct iov_iter *i, size_t bytes); void iov_iter_revert(struct iov_iter *i, size_t bytes); size_t fault_in_iov_iter_readable(const struct iov_iter *i, size_t bytes); size_t fault_in_iov_iter_writeable(const struct iov_iter *i, size_t bytes); size_t iov_iter_single_seg_count(const struct iov_iter *i); size_t copy_page_to_iter(struct page *page, size_t offset, size_t bytes, struct iov_iter *i); size_t copy_page_from_iter(struct page *page, size_t offset, size_t bytes, struct iov_iter *i); size_t _copy_to_iter(const void *addr, size_t bytes, struct iov_iter *i); size_t _copy_from_iter(void *addr, size_t bytes, struct iov_iter *i); size_t _copy_from_iter_nocache(void *addr, size_t bytes, struct iov_iter *i); static inline size_t copy_folio_to_iter(struct folio *folio, size_t offset, size_t bytes, struct iov_iter *i) { return copy_page_to_iter(&folio->page, offset, bytes, i); } static inline size_t copy_folio_from_iter(struct folio *folio, size_t offset, size_t bytes, struct iov_iter *i) { return copy_page_from_iter(&folio->page, offset, bytes, i); } static inline size_t copy_folio_from_iter_atomic(struct folio *folio, size_t offset, size_t bytes, struct iov_iter *i) { return copy_page_from_iter_atomic(&folio->page, offset, bytes, i); } size_t copy_page_to_iter_nofault(struct page *page, unsigned offset, size_t bytes, struct iov_iter *i); static __always_inline __must_check size_t copy_to_iter(const void *addr, size_t bytes, struct iov_iter *i) { if (check_copy_size(addr, bytes, true)) return _copy_to_iter(addr, bytes, i); return 0; } static __always_inline __must_check size_t copy_from_iter(void *addr, size_t bytes, struct iov_iter *i) { if (check_copy_size(addr, bytes, false)) return _copy_from_iter(addr, bytes, i); return 0; } static __always_inline __must_check bool copy_to_iter_full(const void *addr, size_t bytes, struct iov_iter *i) { size_t copied = copy_to_iter(addr, bytes, i); if (likely(copied == bytes)) return true; iov_iter_revert(i, copied); return false; } static __always_inline __must_check bool copy_from_iter_full(void *addr, size_t bytes, struct iov_iter *i) { size_t copied = copy_from_iter(addr, bytes, i); if (likely(copied == bytes)) return true; iov_iter_revert(i, copied); return false; } static __always_inline __must_check size_t copy_from_iter_nocache(void *addr, size_t bytes, struct iov_iter *i) { if (check_copy_size(addr, bytes, false)) return _copy_from_iter_nocache(addr, bytes, i); return 0; } static __always_inline __must_check bool copy_from_iter_full_nocache(void *addr, size_t bytes, struct iov_iter *i) { size_t copied = copy_from_iter_nocache(addr, bytes, i); if (likely(copied == bytes)) return true; iov_iter_revert(i, copied); return false; } #ifdef CONFIG_ARCH_HAS_UACCESS_FLUSHCACHE /* * Note, users like pmem that depend on the stricter semantics of * _copy_from_iter_flushcache() than _copy_from_iter_nocache() must check for * IS_ENABLED(CONFIG_ARCH_HAS_UACCESS_FLUSHCACHE) before assuming that the * destination is flushed from the cache on return. */ size_t _copy_from_iter_flushcache(void *addr, size_t bytes, struct iov_iter *i); #else #define _copy_from_iter_flushcache _copy_from_iter_nocache #endif #ifdef CONFIG_ARCH_HAS_COPY_MC size_t _copy_mc_to_iter(const void *addr, size_t bytes, struct iov_iter *i); #else #define _copy_mc_to_iter _copy_to_iter #endif size_t iov_iter_zero(size_t bytes, struct iov_iter *); bool iov_iter_is_aligned(const struct iov_iter *i, unsigned addr_mask, unsigned len_mask); unsigned long iov_iter_alignment(const struct iov_iter *i); unsigned long iov_iter_gap_alignment(const struct iov_iter *i); void iov_iter_init(struct iov_iter *i, unsigned int direction, const struct iovec *iov, unsigned long nr_segs, size_t count); void iov_iter_kvec(struct iov_iter *i, unsigned int direction, const struct kvec *kvec, unsigned long nr_segs, size_t count); void iov_iter_bvec(struct iov_iter *i, unsigned int direction, const struct bio_vec *bvec, unsigned long nr_segs, size_t count); void iov_iter_discard(struct iov_iter *i, unsigned int direction, size_t count); void iov_iter_folio_queue(struct iov_iter *i, unsigned int direction, const struct folio_queue *folioq, unsigned int first_slot, unsigned int offset, size_t count); void iov_iter_xarray(struct iov_iter *i, unsigned int direction, struct xarray *xarray, loff_t start, size_t count); ssize_t iov_iter_get_pages2(struct iov_iter *i, struct page **pages, size_t maxsize, unsigned maxpages, size_t *start); ssize_t iov_iter_get_pages_alloc2(struct iov_iter *i, struct page ***pages, size_t maxsize, size_t *start); int iov_iter_npages(const struct iov_iter *i, int maxpages); void iov_iter_restore(struct iov_iter *i, struct iov_iter_state *state); const void *dup_iter(struct iov_iter *new, struct iov_iter *old, gfp_t flags); static inline size_t iov_iter_count(const struct iov_iter *i) { return i->count; } /* * Cap the iov_iter by given limit; note that the second argument is * *not* the new size - it's upper limit for such. Passing it a value * greater than the amount of data in iov_iter is fine - it'll just do * nothing in that case. */ static inline void iov_iter_truncate(struct iov_iter *i, u64 count) { /* * count doesn't have to fit in size_t - comparison extends both * operands to u64 here and any value that would be truncated by * conversion in assignement is by definition greater than all * values of size_t, including old i->count. */ if (i->count > count) i->count = count; } /* * reexpand a previously truncated iterator; count must be no more than how much * we had shrunk it. */ static inline void iov_iter_reexpand(struct iov_iter *i, size_t count) { i->count = count; } static inline int iov_iter_npages_cap(struct iov_iter *i, int maxpages, size_t max_bytes) { size_t shorted = 0; int npages; if (iov_iter_count(i) > max_bytes) { shorted = iov_iter_count(i) - max_bytes; iov_iter_truncate(i, max_bytes); } npages = iov_iter_npages(i, maxpages); if (shorted) iov_iter_reexpand(i, iov_iter_count(i) + shorted); return npages; } struct iovec *iovec_from_user(const struct iovec __user *uvector, unsigned long nr_segs, unsigned long fast_segs, struct iovec *fast_iov, bool compat); ssize_t import_iovec(int type, const struct iovec __user *uvec, unsigned nr_segs, unsigned fast_segs, struct iovec **iovp, struct iov_iter *i); ssize_t __import_iovec(int type, const struct iovec __user *uvec, unsigned nr_segs, unsigned fast_segs, struct iovec **iovp, struct iov_iter *i, bool compat); int import_ubuf(int type, void __user *buf, size_t len, struct iov_iter *i); static inline void iov_iter_ubuf(struct iov_iter *i, unsigned int direction, void __user *buf, size_t count) { WARN_ON(direction & ~(READ | WRITE)); *i = (struct iov_iter) { .iter_type = ITER_UBUF, .data_source = direction, .ubuf = buf, .count = count, .nr_segs = 1 }; } /* Flags for iov_iter_get/extract_pages*() */ /* Allow P2PDMA on the extracted pages */ #define ITER_ALLOW_P2PDMA ((__force iov_iter_extraction_t)0x01) ssize_t iov_iter_extract_pages(struct iov_iter *i, struct page ***pages, size_t maxsize, unsigned int maxpages, iov_iter_extraction_t extraction_flags, size_t *offset0); /** * iov_iter_extract_will_pin - Indicate how pages from the iterator will be retained * @iter: The iterator * * Examine the iterator and indicate by returning true or false as to how, if * at all, pages extracted from the iterator will be retained by the extraction * function. * * %true indicates that the pages will have a pin placed in them that the * caller must unpin. This is must be done for DMA/async DIO to force fork() * to forcibly copy a page for the child (the parent must retain the original * page). * * %false indicates that no measures are taken and that it's up to the caller * to retain the pages. */ static inline bool iov_iter_extract_will_pin(const struct iov_iter *iter) { return user_backed_iter(iter); } struct sg_table; ssize_t extract_iter_to_sg(struct iov_iter *iter, size_t len, struct sg_table *sgtable, unsigned int sg_max, iov_iter_extraction_t extraction_flags); #endif |
| 90 46 239 96 96 6 90 96 96 95 232 213 232 304 304 196 196 196 120 196 304 355 357 232 46 207 213 231 356 357 46 46 46 46 1 143 143 159 159 159 69 95 267 265 190 191 281 299 191 192 191 192 189 2 191 190 192 191 265 267 265 261 264 267 96 96 95 95 96 96 46 46 46 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 1522 1523 1524 1525 1526 1527 1528 1529 1530 1531 1532 1533 1534 1535 1536 1537 1538 1539 1540 1541 1542 1543 1544 1545 1546 1547 1548 1549 1550 1551 1552 1553 1554 1555 1556 1557 1558 1559 1560 1561 1562 1563 1564 1565 1566 1567 1568 1569 1570 1571 1572 1573 1574 1575 1576 1577 1578 1579 1580 1581 1582 1583 1584 1585 1586 1587 1588 1589 1590 1591 1592 1593 1594 1595 1596 1597 1598 1599 1600 1601 1602 1603 1604 1605 1606 1607 1608 1609 1610 1611 1612 1613 1614 1615 1616 1617 1618 1619 1620 1621 1622 1623 1624 1625 1626 1627 1628 1629 1630 1631 1632 1633 1634 1635 1636 1637 1638 1639 1640 1641 1642 1643 1644 1645 1646 1647 1648 1649 1650 1651 1652 1653 1654 1655 1656 1657 1658 1659 1660 1661 1662 1663 1664 1665 1666 1667 1668 1669 1670 1671 1672 1673 1674 1675 1676 1677 1678 1679 1680 1681 1682 1683 1684 1685 1686 1687 1688 1689 1690 1691 1692 1693 1694 1695 1696 1697 1698 1699 1700 1701 1702 1703 1704 1705 1706 1707 1708 1709 1710 1711 1712 1713 1714 1715 1716 1717 1718 1719 1720 1721 1722 1723 1724 1725 1726 1727 1728 1729 1730 1731 1732 1733 1734 1735 1736 1737 1738 1739 1740 1741 1742 1743 1744 1745 1746 1747 1748 1749 1750 1751 1752 1753 1754 1755 1756 1757 1758 1759 1760 1761 1762 1763 1764 1765 1766 1767 1768 1769 1770 1771 1772 1773 1774 1775 1776 1777 1778 1779 1780 1781 1782 1783 1784 1785 1786 1787 1788 1789 1790 1791 1792 1793 1794 1795 1796 1797 1798 1799 1800 1801 1802 1803 1804 1805 1806 1807 1808 1809 1810 1811 1812 1813 1814 1815 1816 1817 1818 1819 1820 1821 1822 1823 1824 1825 1826 1827 1828 1829 1830 1831 1832 1833 1834 1835 1836 1837 1838 1839 1840 1841 1842 1843 1844 1845 1846 1847 1848 1849 1850 1851 1852 1853 1854 1855 1856 1857 1858 1859 1860 1861 1862 1863 1864 1865 1866 1867 1868 1869 1870 1871 1872 1873 1874 1875 1876 1877 1878 1879 1880 1881 1882 1883 1884 1885 1886 1887 1888 1889 1890 1891 1892 1893 1894 1895 1896 1897 1898 1899 1900 1901 1902 1903 1904 1905 1906 1907 1908 1909 1910 1911 1912 1913 1914 1915 1916 1917 1918 1919 1920 1921 1922 1923 1924 1925 1926 1927 1928 1929 1930 1931 1932 1933 1934 1935 1936 1937 1938 1939 1940 1941 1942 1943 1944 1945 1946 1947 1948 1949 1950 1951 1952 1953 1954 1955 1956 1957 1958 1959 1960 1961 1962 1963 1964 1965 1966 1967 1968 1969 1970 1971 1972 1973 1974 1975 1976 1977 1978 1979 1980 1981 1982 1983 1984 1985 1986 1987 1988 1989 1990 1991 1992 1993 1994 1995 1996 1997 1998 1999 2000 2001 2002 2003 2004 2005 2006 2007 2008 2009 2010 2011 2012 2013 2014 2015 2016 2017 2018 2019 2020 2021 2022 2023 2024 2025 2026 2027 2028 2029 2030 2031 2032 2033 2034 2035 2036 2037 2038 2039 2040 2041 2042 2043 2044 2045 2046 2047 2048 2049 2050 2051 2052 2053 2054 2055 2056 2057 2058 2059 2060 2061 2062 2063 2064 2065 2066 2067 2068 2069 2070 2071 2072 2073 2074 2075 2076 2077 2078 2079 2080 2081 2082 2083 2084 2085 2086 2087 2088 2089 2090 2091 2092 2093 2094 2095 2096 2097 2098 2099 2100 2101 2102 2103 2104 2105 2106 2107 2108 2109 2110 2111 2112 2113 2114 2115 2116 2117 2118 2119 2120 2121 2122 2123 2124 2125 2126 2127 2128 2129 2130 2131 2132 2133 2134 2135 2136 2137 2138 2139 2140 2141 2142 2143 2144 2145 2146 2147 2148 2149 2150 2151 2152 2153 2154 2155 2156 2157 2158 2159 2160 2161 2162 2163 2164 2165 2166 2167 2168 2169 2170 2171 2172 2173 2174 2175 2176 2177 2178 2179 2180 2181 2182 2183 2184 2185 2186 2187 2188 2189 2190 2191 2192 2193 2194 2195 2196 2197 2198 2199 2200 2201 2202 2203 2204 2205 2206 2207 2208 2209 2210 2211 2212 2213 2214 2215 2216 2217 2218 2219 2220 2221 2222 2223 2224 2225 2226 2227 2228 2229 2230 2231 2232 2233 2234 2235 2236 2237 2238 2239 2240 2241 2242 2243 2244 2245 2246 2247 2248 2249 2250 2251 2252 2253 2254 2255 2256 2257 2258 2259 2260 2261 2262 2263 2264 2265 2266 2267 2268 2269 2270 2271 2272 2273 2274 2275 2276 2277 2278 2279 2280 2281 2282 2283 2284 2285 2286 2287 2288 2289 2290 2291 2292 2293 2294 2295 2296 2297 2298 2299 2300 2301 2302 2303 2304 2305 2306 2307 2308 2309 2310 2311 2312 2313 2314 2315 2316 2317 2318 2319 2320 2321 2322 2323 2324 2325 2326 2327 2328 2329 2330 2331 2332 2333 2334 2335 2336 2337 2338 2339 2340 2341 2342 2343 2344 2345 2346 2347 2348 2349 2350 2351 2352 2353 2354 2355 2356 2357 2358 2359 2360 2361 2362 2363 2364 2365 2366 2367 2368 2369 2370 2371 2372 2373 2374 2375 2376 2377 2378 2379 2380 2381 2382 2383 2384 2385 2386 2387 2388 2389 2390 2391 2392 2393 2394 2395 2396 2397 2398 2399 2400 2401 2402 2403 2404 2405 2406 2407 2408 2409 2410 2411 2412 2413 2414 2415 2416 2417 2418 2419 2420 2421 2422 2423 2424 2425 2426 2427 2428 2429 2430 2431 2432 2433 2434 2435 2436 2437 2438 2439 2440 2441 2442 2443 2444 2445 2446 2447 2448 2449 2450 2451 2452 2453 2454 2455 2456 2457 2458 2459 2460 2461 2462 2463 2464 2465 2466 2467 2468 2469 2470 2471 2472 2473 2474 2475 2476 2477 2478 2479 2480 2481 2482 2483 2484 2485 2486 2487 2488 2489 2490 2491 2492 2493 2494 2495 2496 2497 2498 2499 2500 2501 2502 2503 2504 2505 2506 2507 2508 2509 2510 2511 2512 2513 2514 2515 2516 2517 2518 2519 2520 2521 2522 2523 2524 2525 2526 2527 2528 2529 2530 2531 2532 2533 2534 2535 2536 2537 2538 2539 2540 2541 2542 2543 2544 2545 2546 2547 2548 2549 2550 2551 2552 2553 2554 2555 2556 2557 2558 2559 2560 2561 2562 2563 2564 2565 2566 2567 2568 2569 2570 2571 2572 2573 2574 2575 2576 2577 2578 2579 2580 2581 2582 2583 2584 2585 2586 2587 2588 2589 2590 2591 2592 2593 2594 2595 2596 2597 2598 2599 2600 2601 2602 2603 2604 2605 2606 2607 2608 2609 2610 2611 2612 2613 2614 2615 2616 2617 2618 2619 2620 2621 2622 2623 2624 2625 2626 2627 2628 2629 2630 2631 2632 2633 2634 2635 2636 2637 2638 2639 2640 2641 2642 2643 2644 2645 2646 2647 2648 2649 2650 2651 2652 2653 2654 2655 2656 2657 2658 2659 2660 2661 2662 2663 2664 2665 2666 2667 2668 2669 2670 2671 2672 2673 2674 2675 2676 2677 2678 2679 2680 2681 2682 2683 2684 2685 2686 2687 2688 2689 2690 2691 2692 2693 2694 2695 2696 2697 2698 2699 2700 2701 2702 2703 2704 2705 2706 2707 2708 2709 2710 2711 2712 2713 2714 2715 2716 2717 2718 2719 2720 2721 2722 2723 2724 2725 2726 2727 2728 2729 2730 2731 2732 2733 2734 2735 2736 2737 2738 2739 2740 2741 2742 2743 2744 2745 2746 2747 2748 2749 2750 2751 2752 2753 2754 2755 2756 2757 2758 2759 2760 2761 2762 2763 2764 2765 2766 2767 2768 2769 2770 2771 2772 2773 | /* * mm/rmap.c - physical to virtual reverse mappings * * Copyright 2001, Rik van Riel <riel@conectiva.com.br> * Released under the General Public License (GPL). * * Simple, low overhead reverse mapping scheme. * Please try to keep this thing as modular as possible. * * Provides methods for unmapping each kind of mapped page: * the anon methods track anonymous pages, and * the file methods track pages belonging to an inode. * * Original design by Rik van Riel <riel@conectiva.com.br> 2001 * File methods by Dave McCracken <dmccr@us.ibm.com> 2003, 2004 * Anonymous methods by Andrea Arcangeli <andrea@suse.de> 2004 * Contributions by Hugh Dickins 2003, 2004 */ /* * Lock ordering in mm: * * inode->i_rwsem (while writing or truncating, not reading or faulting) * mm->mmap_lock * mapping->invalidate_lock (in filemap_fault) * folio_lock * hugetlbfs_i_mmap_rwsem_key (in huge_pmd_share, see hugetlbfs below) * vma_start_write * mapping->i_mmap_rwsem * anon_vma->rwsem * mm->page_table_lock or pte_lock * swap_lock (in swap_duplicate, swap_info_get) * mmlist_lock (in mmput, drain_mmlist and others) * mapping->private_lock (in block_dirty_folio) * i_pages lock (widely used) * lruvec->lru_lock (in folio_lruvec_lock_irq) * inode->i_lock (in set_page_dirty's __mark_inode_dirty) * bdi.wb->list_lock (in set_page_dirty's __mark_inode_dirty) * sb_lock (within inode_lock in fs/fs-writeback.c) * i_pages lock (widely used, in set_page_dirty, * in arch-dependent flush_dcache_mmap_lock, * within bdi.wb->list_lock in __sync_single_inode) * * anon_vma->rwsem,mapping->i_mmap_rwsem (memory_failure, collect_procs_anon) * ->tasklist_lock * pte map lock * * hugetlbfs PageHuge() take locks in this order: * hugetlb_fault_mutex (hugetlbfs specific page fault mutex) * vma_lock (hugetlb specific lock for pmd_sharing) * mapping->i_mmap_rwsem (also used for hugetlb pmd sharing) * folio_lock */ #include <linux/mm.h> #include <linux/sched/mm.h> #include <linux/sched/task.h> #include <linux/pagemap.h> #include <linux/swap.h> #include <linux/swapops.h> #include <linux/slab.h> #include <linux/init.h> #include <linux/ksm.h> #include <linux/rmap.h> #include <linux/rcupdate.h> #include <linux/export.h> #include <linux/memcontrol.h> #include <linux/mmu_notifier.h> #include <linux/migrate.h> #include <linux/hugetlb.h> #include <linux/huge_mm.h> #include <linux/backing-dev.h> #include <linux/page_idle.h> #include <linux/memremap.h> #include <linux/userfaultfd_k.h> #include <linux/mm_inline.h> #include <linux/oom.h> #include <asm/tlbflush.h> #define CREATE_TRACE_POINTS #include <trace/events/tlb.h> #include <trace/events/migrate.h> #include "internal.h" static struct kmem_cache *anon_vma_cachep; static struct kmem_cache *anon_vma_chain_cachep; static inline struct anon_vma *anon_vma_alloc(void) { struct anon_vma *anon_vma; anon_vma = kmem_cache_alloc(anon_vma_cachep, GFP_KERNEL); if (anon_vma) { atomic_set(&anon_vma->refcount, 1); anon_vma->num_children = 0; anon_vma->num_active_vmas = 0; anon_vma->parent = anon_vma; /* * Initialise the anon_vma root to point to itself. If called * from fork, the root will be reset to the parents anon_vma. */ anon_vma->root = anon_vma; } return anon_vma; } static inline void anon_vma_free(struct anon_vma *anon_vma) { VM_BUG_ON(atomic_read(&anon_vma->refcount)); /* * Synchronize against folio_lock_anon_vma_read() such that * we can safely hold the lock without the anon_vma getting * freed. * * Relies on the full mb implied by the atomic_dec_and_test() from * put_anon_vma() against the acquire barrier implied by * down_read_trylock() from folio_lock_anon_vma_read(). This orders: * * folio_lock_anon_vma_read() VS put_anon_vma() * down_read_trylock() atomic_dec_and_test() * LOCK MB * atomic_read() rwsem_is_locked() * * LOCK should suffice since the actual taking of the lock must * happen _before_ what follows. */ might_sleep(); if (rwsem_is_locked(&anon_vma->root->rwsem)) { anon_vma_lock_write(anon_vma); anon_vma_unlock_write(anon_vma); } kmem_cache_free(anon_vma_cachep, anon_vma); } static inline struct anon_vma_chain *anon_vma_chain_alloc(gfp_t gfp) { return kmem_cache_alloc(anon_vma_chain_cachep, gfp); } static void anon_vma_chain_free(struct anon_vma_chain *anon_vma_chain) { kmem_cache_free(anon_vma_chain_cachep, anon_vma_chain); } static void anon_vma_chain_link(struct vm_area_struct *vma, struct anon_vma_chain *avc, struct anon_vma *anon_vma) { avc->vma = vma; avc->anon_vma = anon_vma; list_add(&avc->same_vma, &vma->anon_vma_chain); anon_vma_interval_tree_insert(avc, &anon_vma->rb_root); } /** * __anon_vma_prepare - attach an anon_vma to a memory region * @vma: the memory region in question * * This makes sure the memory mapping described by 'vma' has * an 'anon_vma' attached to it, so that we can associate the * anonymous pages mapped into it with that anon_vma. * * The common case will be that we already have one, which * is handled inline by anon_vma_prepare(). But if * not we either need to find an adjacent mapping that we * can re-use the anon_vma from (very common when the only * reason for splitting a vma has been mprotect()), or we * allocate a new one. * * Anon-vma allocations are very subtle, because we may have * optimistically looked up an anon_vma in folio_lock_anon_vma_read() * and that may actually touch the rwsem even in the newly * allocated vma (it depends on RCU to make sure that the * anon_vma isn't actually destroyed). * * As a result, we need to do proper anon_vma locking even * for the new allocation. At the same time, we do not want * to do any locking for the common case of already having * an anon_vma. */ int __anon_vma_prepare(struct vm_area_struct *vma) { struct mm_struct *mm = vma->vm_mm; struct anon_vma *anon_vma, *allocated; struct anon_vma_chain *avc; mmap_assert_locked(mm); might_sleep(); avc = anon_vma_chain_alloc(GFP_KERNEL); if (!avc) goto out_enomem; anon_vma = find_mergeable_anon_vma(vma); allocated = NULL; if (!anon_vma) { anon_vma = anon_vma_alloc(); if (unlikely(!anon_vma)) goto out_enomem_free_avc; anon_vma->num_children++; /* self-parent link for new root */ allocated = anon_vma; } anon_vma_lock_write(anon_vma); /* page_table_lock to protect against threads */ spin_lock(&mm->page_table_lock); if (likely(!vma->anon_vma)) { vma->anon_vma = anon_vma; anon_vma_chain_link(vma, avc, anon_vma); anon_vma->num_active_vmas++; allocated = NULL; avc = NULL; } spin_unlock(&mm->page_table_lock); anon_vma_unlock_write(anon_vma); if (unlikely(allocated)) put_anon_vma(allocated); if (unlikely(avc)) anon_vma_chain_free(avc); return 0; out_enomem_free_avc: anon_vma_chain_free(avc); out_enomem: return -ENOMEM; } /* * This is a useful helper function for locking the anon_vma root as * we traverse the vma->anon_vma_chain, looping over anon_vma's that * have the same vma. * * Such anon_vma's should have the same root, so you'd expect to see * just a single mutex_lock for the whole traversal. */ static inline struct anon_vma *lock_anon_vma_root(struct anon_vma *root, struct anon_vma *anon_vma) { struct anon_vma *new_root = anon_vma->root; if (new_root != root) { if (WARN_ON_ONCE(root)) up_write(&root->rwsem); root = new_root; down_write(&root->rwsem); } return root; } static inline void unlock_anon_vma_root(struct anon_vma *root) { if (root) up_write(&root->rwsem); } /* * Attach the anon_vmas from src to dst. * Returns 0 on success, -ENOMEM on failure. * * anon_vma_clone() is called by vma_expand(), vma_merge(), __split_vma(), * copy_vma() and anon_vma_fork(). The first four want an exact copy of src, * while the last one, anon_vma_fork(), may try to reuse an existing anon_vma to * prevent endless growth of anon_vma. Since dst->anon_vma is set to NULL before * call, we can identify this case by checking (!dst->anon_vma && * src->anon_vma). * * If (!dst->anon_vma && src->anon_vma) is true, this function tries to find * and reuse existing anon_vma which has no vmas and only one child anon_vma. * This prevents degradation of anon_vma hierarchy to endless linear chain in * case of constantly forking task. On the other hand, an anon_vma with more * than one child isn't reused even if there was no alive vma, thus rmap * walker has a good chance of avoiding scanning the whole hierarchy when it * searches where page is mapped. */ int anon_vma_clone(struct vm_area_struct *dst, struct vm_area_struct *src) { struct anon_vma_chain *avc, *pavc; struct anon_vma *root = NULL; list_for_each_entry_reverse(pavc, &src->anon_vma_chain, same_vma) { struct anon_vma *anon_vma; avc = anon_vma_chain_alloc(GFP_NOWAIT | __GFP_NOWARN); if (unlikely(!avc)) { unlock_anon_vma_root(root); root = NULL; avc = anon_vma_chain_alloc(GFP_KERNEL); if (!avc) goto enomem_failure; } anon_vma = pavc->anon_vma; root = lock_anon_vma_root(root, anon_vma); anon_vma_chain_link(dst, avc, anon_vma); /* * Reuse existing anon_vma if it has no vma and only one * anon_vma child. * * Root anon_vma is never reused: * it has self-parent reference and at least one child. */ if (!dst->anon_vma && src->anon_vma && anon_vma->num_children < 2 && anon_vma->num_active_vmas == 0) dst->anon_vma = anon_vma; } if (dst->anon_vma) dst->anon_vma->num_active_vmas++; unlock_anon_vma_root(root); return 0; enomem_failure: /* * dst->anon_vma is dropped here otherwise its num_active_vmas can * be incorrectly decremented in unlink_anon_vmas(). * We can safely do this because callers of anon_vma_clone() don't care * about dst->anon_vma if anon_vma_clone() failed. */ dst->anon_vma = NULL; unlink_anon_vmas(dst); return -ENOMEM; } /* * Attach vma to its own anon_vma, as well as to the anon_vmas that * the corresponding VMA in the parent process is attached to. * Returns 0 on success, non-zero on failure. */ int anon_vma_fork(struct vm_area_struct *vma, struct vm_area_struct *pvma) { struct anon_vma_chain *avc; struct anon_vma *anon_vma; int error; /* Don't bother if the parent process has no anon_vma here. */ if (!pvma->anon_vma) return 0; /* Drop inherited anon_vma, we'll reuse existing or allocate new. */ vma->anon_vma = NULL; /* * First, attach the new VMA to the parent VMA's anon_vmas, * so rmap can find non-COWed pages in child processes. */ error = anon_vma_clone(vma, pvma); if (error) return error; /* An existing anon_vma has been reused, all done then. */ if (vma->anon_vma) return 0; /* Then add our own anon_vma. */ anon_vma = anon_vma_alloc(); if (!anon_vma) goto out_error; anon_vma->num_active_vmas++; avc = anon_vma_chain_alloc(GFP_KERNEL); if (!avc) goto out_error_free_anon_vma; /* * The root anon_vma's rwsem is the lock actually used when we * lock any of the anon_vmas in this anon_vma tree. */ anon_vma->root = pvma->anon_vma->root; anon_vma->parent = pvma->anon_vma; /* * With refcounts, an anon_vma can stay around longer than the * process it belongs to. The root anon_vma needs to be pinned until * this anon_vma is freed, because the lock lives in the root. */ get_anon_vma(anon_vma->root); /* Mark this anon_vma as the one where our new (COWed) pages go. */ vma->anon_vma = anon_vma; anon_vma_lock_write(anon_vma); anon_vma_chain_link(vma, avc, anon_vma); anon_vma->parent->num_children++; anon_vma_unlock_write(anon_vma); return 0; out_error_free_anon_vma: put_anon_vma(anon_vma); out_error: unlink_anon_vmas(vma); return -ENOMEM; } void unlink_anon_vmas(struct vm_area_struct *vma) { struct anon_vma_chain *avc, *next; struct anon_vma *root = NULL; /* * Unlink each anon_vma chained to the VMA. This list is ordered * from newest to oldest, ensuring the root anon_vma gets freed last. */ list_for_each_entry_safe(avc, next, &vma->anon_vma_chain, same_vma) { struct anon_vma *anon_vma = avc->anon_vma; root = lock_anon_vma_root(root, anon_vma); anon_vma_interval_tree_remove(avc, &anon_vma->rb_root); /* * Leave empty anon_vmas on the list - we'll need * to free them outside the lock. */ if (RB_EMPTY_ROOT(&anon_vma->rb_root.rb_root)) { anon_vma->parent->num_children--; continue; } list_del(&avc->same_vma); anon_vma_chain_free(avc); } if (vma->anon_vma) { vma->anon_vma->num_active_vmas--; /* * vma would still be needed after unlink, and anon_vma will be prepared * when handle fault. */ vma->anon_vma = NULL; } unlock_anon_vma_root(root); /* * Iterate the list once more, it now only contains empty and unlinked * anon_vmas, destroy them. Could not do before due to __put_anon_vma() * needing to write-acquire the anon_vma->root->rwsem. */ list_for_each_entry_safe(avc, next, &vma->anon_vma_chain, same_vma) { struct anon_vma *anon_vma = avc->anon_vma; VM_WARN_ON(anon_vma->num_children); VM_WARN_ON(anon_vma->num_active_vmas); put_anon_vma(anon_vma); list_del(&avc->same_vma); anon_vma_chain_free(avc); } } static void anon_vma_ctor(void *data) { struct anon_vma *anon_vma = data; init_rwsem(&anon_vma->rwsem); atomic_set(&anon_vma->refcount, 0); anon_vma->rb_root = RB_ROOT_CACHED; } void __init anon_vma_init(void) { anon_vma_cachep = kmem_cache_create("anon_vma", sizeof(struct anon_vma), 0, SLAB_TYPESAFE_BY_RCU|SLAB_PANIC|SLAB_ACCOUNT, anon_vma_ctor); anon_vma_chain_cachep = KMEM_CACHE(anon_vma_chain, SLAB_PANIC|SLAB_ACCOUNT); } /* * Getting a lock on a stable anon_vma from a page off the LRU is tricky! * * Since there is no serialization what so ever against folio_remove_rmap_*() * the best this function can do is return a refcount increased anon_vma * that might have been relevant to this page. * * The page might have been remapped to a different anon_vma or the anon_vma * returned may already be freed (and even reused). * * In case it was remapped to a different anon_vma, the new anon_vma will be a * child of the old anon_vma, and the anon_vma lifetime rules will therefore * ensure that any anon_vma obtained from the page will still be valid for as * long as we observe page_mapped() [ hence all those page_mapped() tests ]. * * All users of this function must be very careful when walking the anon_vma * chain and verify that the page in question is indeed mapped in it * [ something equivalent to page_mapped_in_vma() ]. * * Since anon_vma's slab is SLAB_TYPESAFE_BY_RCU and we know from * folio_remove_rmap_*() that the anon_vma pointer from page->mapping is valid * if there is a mapcount, we can dereference the anon_vma after observing * those. * * NOTE: the caller should normally hold folio lock when calling this. If * not, the caller needs to double check the anon_vma didn't change after * taking the anon_vma lock for either read or write (UFFDIO_MOVE can modify it * concurrently without folio lock protection). See folio_lock_anon_vma_read() * which has already covered that, and comment above remap_pages(). */ struct anon_vma *folio_get_anon_vma(const struct folio *folio) { struct anon_vma *anon_vma = NULL; unsigned long anon_mapping; rcu_read_lock(); anon_mapping = (unsigned long)READ_ONCE(folio->mapping); if ((anon_mapping & PAGE_MAPPING_FLAGS) != PAGE_MAPPING_ANON) goto out; if (!folio_mapped(folio)) goto out; anon_vma = (struct anon_vma *) (anon_mapping - PAGE_MAPPING_ANON); if (!atomic_inc_not_zero(&anon_vma->refcount)) { anon_vma = NULL; goto out; } /* * If this folio is still mapped, then its anon_vma cannot have been * freed. But if it has been unmapped, we have no security against the * anon_vma structure being freed and reused (for another anon_vma: * SLAB_TYPESAFE_BY_RCU guarantees that - so the atomic_inc_not_zero() * above cannot corrupt). */ if (!folio_mapped(folio)) { rcu_read_unlock(); put_anon_vma(anon_vma); return NULL; } out: rcu_read_unlock(); return anon_vma; } /* * Similar to folio_get_anon_vma() except it locks the anon_vma. * * Its a little more complex as it tries to keep the fast path to a single * atomic op -- the trylock. If we fail the trylock, we fall back to getting a * reference like with folio_get_anon_vma() and then block on the mutex * on !rwc->try_lock case. */ struct anon_vma *folio_lock_anon_vma_read(const struct folio *folio, struct rmap_walk_control *rwc) { struct anon_vma *anon_vma = NULL; struct anon_vma *root_anon_vma; unsigned long anon_mapping; retry: rcu_read_lock(); anon_mapping = (unsigned long)READ_ONCE(folio->mapping); if ((anon_mapping & PAGE_MAPPING_FLAGS) != PAGE_MAPPING_ANON) goto out; if (!folio_mapped(folio)) goto out; anon_vma = (struct anon_vma *) (anon_mapping - PAGE_MAPPING_ANON); root_anon_vma = READ_ONCE(anon_vma->root); if (down_read_trylock(&root_anon_vma->rwsem)) { /* * folio_move_anon_rmap() might have changed the anon_vma as we * might not hold the folio lock here. */ if (unlikely((unsigned long)READ_ONCE(folio->mapping) != anon_mapping)) { up_read(&root_anon_vma->rwsem); rcu_read_unlock(); goto retry; } /* * If the folio is still mapped, then this anon_vma is still * its anon_vma, and holding the mutex ensures that it will * not go away, see anon_vma_free(). */ if (!folio_mapped(folio)) { up_read(&root_anon_vma->rwsem); anon_vma = NULL; } goto out; } if (rwc && rwc->try_lock) { anon_vma = NULL; rwc->contended = true; goto out; } /* trylock failed, we got to sleep */ if (!atomic_inc_not_zero(&anon_vma->refcount)) { anon_vma = NULL; goto out; } if (!folio_mapped(folio)) { rcu_read_unlock(); put_anon_vma(anon_vma); return NULL; } /* we pinned the anon_vma, its safe to sleep */ rcu_read_unlock(); anon_vma_lock_read(anon_vma); /* * folio_move_anon_rmap() might have changed the anon_vma as we might * not hold the folio lock here. */ if (unlikely((unsigned long)READ_ONCE(folio->mapping) != anon_mapping)) { anon_vma_unlock_read(anon_vma); put_anon_vma(anon_vma); anon_vma = NULL; goto retry; } if (atomic_dec_and_test(&anon_vma->refcount)) { /* * Oops, we held the last refcount, release the lock * and bail -- can't simply use put_anon_vma() because * we'll deadlock on the anon_vma_lock_write() recursion. */ anon_vma_unlock_read(anon_vma); __put_anon_vma(anon_vma); anon_vma = NULL; } return anon_vma; out: rcu_read_unlock(); return anon_vma; } #ifdef CONFIG_ARCH_WANT_BATCHED_UNMAP_TLB_FLUSH /* * Flush TLB entries for recently unmapped pages from remote CPUs. It is * important if a PTE was dirty when it was unmapped that it's flushed * before any IO is initiated on the page to prevent lost writes. Similarly, * it must be flushed before freeing to prevent data leakage. */ void try_to_unmap_flush(void) { struct tlbflush_unmap_batch *tlb_ubc = ¤t->tlb_ubc; if (!tlb_ubc->flush_required) return; arch_tlbbatch_flush(&tlb_ubc->arch); tlb_ubc->flush_required = false; tlb_ubc->writable = false; } /* Flush iff there are potentially writable TLB entries that can race with IO */ void try_to_unmap_flush_dirty(void) { struct tlbflush_unmap_batch *tlb_ubc = ¤t->tlb_ubc; if (tlb_ubc->writable) try_to_unmap_flush(); } /* * Bits 0-14 of mm->tlb_flush_batched record pending generations. * Bits 16-30 of mm->tlb_flush_batched bit record flushed generations. */ #define TLB_FLUSH_BATCH_FLUSHED_SHIFT 16 #define TLB_FLUSH_BATCH_PENDING_MASK \ ((1 << (TLB_FLUSH_BATCH_FLUSHED_SHIFT - 1)) - 1) #define TLB_FLUSH_BATCH_PENDING_LARGE \ (TLB_FLUSH_BATCH_PENDING_MASK / 2) static void set_tlb_ubc_flush_pending(struct mm_struct *mm, pte_t pteval, unsigned long uaddr) { struct tlbflush_unmap_batch *tlb_ubc = ¤t->tlb_ubc; int batch; bool writable = pte_dirty(pteval); if (!pte_accessible(mm, pteval)) return; arch_tlbbatch_add_pending(&tlb_ubc->arch, mm, uaddr); tlb_ubc->flush_required = true; /* * Ensure compiler does not re-order the setting of tlb_flush_batched * before the PTE is cleared. */ barrier(); batch = atomic_read(&mm->tlb_flush_batched); retry: if ((batch & TLB_FLUSH_BATCH_PENDING_MASK) > TLB_FLUSH_BATCH_PENDING_LARGE) { /* * Prevent `pending' from catching up with `flushed' because of * overflow. Reset `pending' and `flushed' to be 1 and 0 if * `pending' becomes large. */ if (!atomic_try_cmpxchg(&mm->tlb_flush_batched, &batch, 1)) goto retry; } else { atomic_inc(&mm->tlb_flush_batched); } /* * If the PTE was dirty then it's best to assume it's writable. The * caller must use try_to_unmap_flush_dirty() or try_to_unmap_flush() * before the page is queued for IO. */ if (writable) tlb_ubc->writable = true; } /* * Returns true if the TLB flush should be deferred to the end of a batch of * unmap operations to reduce IPIs. */ static bool should_defer_flush(struct mm_struct *mm, enum ttu_flags flags) { if (!(flags & TTU_BATCH_FLUSH)) return false; return arch_tlbbatch_should_defer(mm); } /* * Reclaim unmaps pages under the PTL but do not flush the TLB prior to * releasing the PTL if TLB flushes are batched. It's possible for a parallel * operation such as mprotect or munmap to race between reclaim unmapping * the page and flushing the page. If this race occurs, it potentially allows * access to data via a stale TLB entry. Tracking all mm's that have TLB * batching in flight would be expensive during reclaim so instead track * whether TLB batching occurred in the past and if so then do a flush here * if required. This will cost one additional flush per reclaim cycle paid * by the first operation at risk such as mprotect and mumap. * * This must be called under the PTL so that an access to tlb_flush_batched * that is potentially a "reclaim vs mprotect/munmap/etc" race will synchronise * via the PTL. */ void flush_tlb_batched_pending(struct mm_struct *mm) { int batch = atomic_read(&mm->tlb_flush_batched); int pending = batch & TLB_FLUSH_BATCH_PENDING_MASK; int flushed = batch >> TLB_FLUSH_BATCH_FLUSHED_SHIFT; if (pending != flushed) { arch_flush_tlb_batched_pending(mm); /* * If the new TLB flushing is pending during flushing, leave * mm->tlb_flush_batched as is, to avoid losing flushing. */ atomic_cmpxchg(&mm->tlb_flush_batched, batch, pending | (pending << TLB_FLUSH_BATCH_FLUSHED_SHIFT)); } } #else static void set_tlb_ubc_flush_pending(struct mm_struct *mm, pte_t pteval, unsigned long uaddr) { } static bool should_defer_flush(struct mm_struct *mm, enum ttu_flags flags) { return false; } #endif /* CONFIG_ARCH_WANT_BATCHED_UNMAP_TLB_FLUSH */ /** * page_address_in_vma - The virtual address of a page in this VMA. * @folio: The folio containing the page. * @page: The page within the folio. * @vma: The VMA we need to know the address in. * * Calculates the user virtual address of this page in the specified VMA. * It is the caller's responsibililty to check the page is actually * within the VMA. There may not currently be a PTE pointing at this * page, but if a page fault occurs at this address, this is the page * which will be accessed. * * Context: Caller should hold a reference to the folio. Caller should * hold a lock (eg the i_mmap_lock or the mmap_lock) which keeps the * VMA from being altered. * * Return: The virtual address corresponding to this page in the VMA. */ unsigned long page_address_in_vma(const struct folio *folio, const struct page *page, const struct vm_area_struct *vma) { if (folio_test_anon(folio)) { struct anon_vma *page__anon_vma = folio_anon_vma(folio); /* * Note: swapoff's unuse_vma() is more efficient with this * check, and needs it to match anon_vma when KSM is active. */ if (!vma->anon_vma || !page__anon_vma || vma->anon_vma->root != page__anon_vma->root) return -EFAULT; } else if (!vma->vm_file) { return -EFAULT; } else if (vma->vm_file->f_mapping != folio->mapping) { return -EFAULT; } /* KSM folios don't reach here because of the !page__anon_vma check */ return vma_address(vma, page_pgoff(folio, page), 1); } /* * Returns the actual pmd_t* where we expect 'address' to be mapped from, or * NULL if it doesn't exist. No guarantees / checks on what the pmd_t* * represents. */ pmd_t *mm_find_pmd(struct mm_struct *mm, unsigned long address) { pgd_t *pgd; p4d_t *p4d; pud_t *pud; pmd_t *pmd = NULL; pgd = pgd_offset(mm, address); if (!pgd_present(*pgd)) goto out; p4d = p4d_offset(pgd, address); if (!p4d_present(*p4d)) goto out; pud = pud_offset(p4d, address); if (!pud_present(*pud)) goto out; pmd = pmd_offset(pud, address); out: return pmd; } struct folio_referenced_arg { int mapcount; int referenced; unsigned long vm_flags; struct mem_cgroup *memcg; }; /* * arg: folio_referenced_arg will be passed */ static bool folio_referenced_one(struct folio *folio, struct vm_area_struct *vma, unsigned long address, void *arg) { struct folio_referenced_arg *pra = arg; DEFINE_FOLIO_VMA_WALK(pvmw, folio, vma, address, 0); int referenced = 0; unsigned long start = address, ptes = 0; while (page_vma_mapped_walk(&pvmw)) { address = pvmw.address; if (vma->vm_flags & VM_LOCKED) { if (!folio_test_large(folio) || !pvmw.pte) { /* Restore the mlock which got missed */ mlock_vma_folio(folio, vma); page_vma_mapped_walk_done(&pvmw); pra->vm_flags |= VM_LOCKED; return false; /* To break the loop */ } /* * For large folio fully mapped to VMA, will * be handled after the pvmw loop. * * For large folio cross VMA boundaries, it's * expected to be picked by page reclaim. But * should skip reference of pages which are in * the range of VM_LOCKED vma. As page reclaim * should just count the reference of pages out * the range of VM_LOCKED vma. */ ptes++; pra->mapcount--; continue; } /* * Skip the non-shared swapbacked folio mapped solely by * the exiting or OOM-reaped process. This avoids redundant * swap-out followed by an immediate unmap. */ if ((!atomic_read(&vma->vm_mm->mm_users) || check_stable_address_space(vma->vm_mm)) && folio_test_anon(folio) && folio_test_swapbacked(folio) && !folio_likely_mapped_shared(folio)) { pra->referenced = -1; page_vma_mapped_walk_done(&pvmw); return false; } if (lru_gen_enabled() && pvmw.pte) { if (lru_gen_look_around(&pvmw)) referenced++; } else if (pvmw.pte) { if (ptep_clear_flush_young_notify(vma, address, pvmw.pte)) referenced++; } else if (IS_ENABLED(CONFIG_TRANSPARENT_HUGEPAGE)) { if (pmdp_clear_flush_young_notify(vma, address, pvmw.pmd)) referenced++; } else { /* unexpected pmd-mapped folio? */ WARN_ON_ONCE(1); } pra->mapcount--; } if ((vma->vm_flags & VM_LOCKED) && folio_test_large(folio) && folio_within_vma(folio, vma)) { unsigned long s_align, e_align; s_align = ALIGN_DOWN(start, PMD_SIZE); e_align = ALIGN_DOWN(start + folio_size(folio) - 1, PMD_SIZE); /* folio doesn't cross page table boundary and fully mapped */ if ((s_align == e_align) && (ptes == folio_nr_pages(folio))) { /* Restore the mlock which got missed */ mlock_vma_folio(folio, vma); pra->vm_flags |= VM_LOCKED; return false; /* To break the loop */ } } if (referenced) folio_clear_idle(folio); if (folio_test_clear_young(folio)) referenced++; if (referenced) { pra->referenced++; pra->vm_flags |= vma->vm_flags & ~VM_LOCKED; } if (!pra->mapcount) return false; /* To break the loop */ return true; } static bool invalid_folio_referenced_vma(struct vm_area_struct *vma, void *arg) { struct folio_referenced_arg *pra = arg; struct mem_cgroup *memcg = pra->memcg; /* * Ignore references from this mapping if it has no recency. If the * folio has been used in another mapping, we will catch it; if this * other mapping is already gone, the unmap path will have set the * referenced flag or activated the folio in zap_pte_range(). */ if (!vma_has_recency(vma)) return true; /* * If we are reclaiming on behalf of a cgroup, skip counting on behalf * of references from different cgroups. */ if (memcg && !mm_match_cgroup(vma->vm_mm, memcg)) return true; return false; } /** * folio_referenced() - Test if the folio was referenced. * @folio: The folio to test. * @is_locked: Caller holds lock on the folio. * @memcg: target memory cgroup * @vm_flags: A combination of all the vma->vm_flags which referenced the folio. * * Quick test_and_clear_referenced for all mappings of a folio, * * Return: The number of mappings which referenced the folio. Return -1 if * the function bailed out due to rmap lock contention. */ int folio_referenced(struct folio *folio, int is_locked, struct mem_cgroup *memcg, unsigned long *vm_flags) { bool we_locked = false; struct folio_referenced_arg pra = { .mapcount = folio_mapcount(folio), .memcg = memcg, }; struct rmap_walk_control rwc = { .rmap_one = folio_referenced_one, .arg = (void *)&pra, .anon_lock = folio_lock_anon_vma_read, .try_lock = true, .invalid_vma = invalid_folio_referenced_vma, }; *vm_flags = 0; if (!pra.mapcount) return 0; if (!folio_raw_mapping(folio)) return 0; if (!is_locked && (!folio_test_anon(folio) || folio_test_ksm(folio))) { we_locked = folio_trylock(folio); if (!we_locked) return 1; } rmap_walk(folio, &rwc); *vm_flags = pra.vm_flags; if (we_locked) folio_unlock(folio); return rwc.contended ? -1 : pra.referenced; } static int page_vma_mkclean_one(struct page_vma_mapped_walk *pvmw) { int cleaned = 0; struct vm_area_struct *vma = pvmw->vma; struct mmu_notifier_range range; unsigned long address = pvmw->address; /* * We have to assume the worse case ie pmd for invalidation. Note that * the folio can not be freed from this function. */ mmu_notifier_range_init(&range, MMU_NOTIFY_PROTECTION_PAGE, 0, vma->vm_mm, address, vma_address_end(pvmw)); mmu_notifier_invalidate_range_start(&range); while (page_vma_mapped_walk(pvmw)) { int ret = 0; address = pvmw->address; if (pvmw->pte) { pte_t *pte = pvmw->pte; pte_t entry = ptep_get(pte); if (!pte_dirty(entry) && !pte_write(entry)) continue; flush_cache_page(vma, address, pte_pfn(entry)); entry = ptep_clear_flush(vma, address, pte); entry = pte_wrprotect(entry); entry = pte_mkclean(entry); set_pte_at(vma->vm_mm, address, pte, entry); ret = 1; } else { #ifdef CONFIG_TRANSPARENT_HUGEPAGE pmd_t *pmd = pvmw->pmd; pmd_t entry; if (!pmd_dirty(*pmd) && !pmd_write(*pmd)) continue; flush_cache_range(vma, address, address + HPAGE_PMD_SIZE); entry = pmdp_invalidate(vma, address, pmd); entry = pmd_wrprotect(entry); entry = pmd_mkclean(entry); set_pmd_at(vma->vm_mm, address, pmd, entry); ret = 1; #else /* unexpected pmd-mapped folio? */ WARN_ON_ONCE(1); #endif } if (ret) cleaned++; } mmu_notifier_invalidate_range_end(&range); return cleaned; } static bool page_mkclean_one(struct folio *folio, struct vm_area_struct *vma, unsigned long address, void *arg) { DEFINE_FOLIO_VMA_WALK(pvmw, folio, vma, address, PVMW_SYNC); int *cleaned = arg; *cleaned += page_vma_mkclean_one(&pvmw); return true; } static bool invalid_mkclean_vma(struct vm_area_struct *vma, void *arg) { if (vma->vm_flags & VM_SHARED) return false; return true; } int folio_mkclean(struct folio *folio) { int cleaned = 0; struct address_space *mapping; struct rmap_walk_control rwc = { .arg = (void *)&cleaned, .rmap_one = page_mkclean_one, .invalid_vma = invalid_mkclean_vma, }; BUG_ON(!folio_test_locked(folio)); if (!folio_mapped(folio)) return 0; mapping = folio_mapping(folio); if (!mapping) return 0; rmap_walk(folio, &rwc); return cleaned; } EXPORT_SYMBOL_GPL(folio_mkclean); /** * pfn_mkclean_range - Cleans the PTEs (including PMDs) mapped with range of * [@pfn, @pfn + @nr_pages) at the specific offset (@pgoff) * within the @vma of shared mappings. And since clean PTEs * should also be readonly, write protects them too. * @pfn: start pfn. * @nr_pages: number of physically contiguous pages srarting with @pfn. * @pgoff: page offset that the @pfn mapped with. * @vma: vma that @pfn mapped within. * * Returns the number of cleaned PTEs (including PMDs). */ int pfn_mkclean_range(unsigned long pfn, unsigned long nr_pages, pgoff_t pgoff, struct vm_area_struct *vma) { struct page_vma_mapped_walk pvmw = { .pfn = pfn, .nr_pages = nr_pages, .pgoff = pgoff, .vma = vma, .flags = PVMW_SYNC, }; if (invalid_mkclean_vma(vma, NULL)) return 0; pvmw.address = vma_address(vma, pgoff, nr_pages); VM_BUG_ON_VMA(pvmw.address == -EFAULT, vma); return page_vma_mkclean_one(&pvmw); } static __always_inline unsigned int __folio_add_rmap(struct folio *folio, struct page *page, int nr_pages, enum rmap_level level, int *nr_pmdmapped) { atomic_t *mapped = &folio->_nr_pages_mapped; const int orig_nr_pages = nr_pages; int first = 0, nr = 0; __folio_rmap_sanity_checks(folio, page, nr_pages, level); switch (level) { case RMAP_LEVEL_PTE: if (!folio_test_large(folio)) { nr = atomic_inc_and_test(&folio->_mapcount); break; } do { first += atomic_inc_and_test(&page->_mapcount); } while (page++, --nr_pages > 0); if (first && atomic_add_return_relaxed(first, mapped) < ENTIRELY_MAPPED) nr = first; atomic_add(orig_nr_pages, &folio->_large_mapcount); break; case RMAP_LEVEL_PMD: first = atomic_inc_and_test(&folio->_entire_mapcount); if (first) { nr = atomic_add_return_relaxed(ENTIRELY_MAPPED, mapped); if (likely(nr < ENTIRELY_MAPPED + ENTIRELY_MAPPED)) { *nr_pmdmapped = folio_nr_pages(folio); nr = *nr_pmdmapped - (nr & FOLIO_PAGES_MAPPED); /* Raced ahead of a remove and another add? */ if (unlikely(nr < 0)) nr = 0; } else { /* Raced ahead of a remove of ENTIRELY_MAPPED */ nr = 0; } } atomic_inc(&folio->_large_mapcount); break; } return nr; } /** * folio_move_anon_rmap - move a folio to our anon_vma * @folio: The folio to move to our anon_vma * @vma: The vma the folio belongs to * * When a folio belongs exclusively to one process after a COW event, * that folio can be moved into the anon_vma that belongs to just that * process, so the rmap code will not search the parent or sibling processes. */ void folio_move_anon_rmap(struct folio *folio, struct vm_area_struct *vma) { void *anon_vma = vma->anon_vma; VM_BUG_ON_FOLIO(!folio_test_locked(folio), folio); VM_BUG_ON_VMA(!anon_vma, vma); anon_vma += PAGE_MAPPING_ANON; /* * Ensure that anon_vma and the PAGE_MAPPING_ANON bit are written * simultaneously, so a concurrent reader (eg folio_referenced()'s * folio_test_anon()) will not see one without the other. */ WRITE_ONCE(folio->mapping, anon_vma); } /** * __folio_set_anon - set up a new anonymous rmap for a folio * @folio: The folio to set up the new anonymous rmap for. * @vma: VM area to add the folio to. * @address: User virtual address of the mapping * @exclusive: Whether the folio is exclusive to the process. */ static void __folio_set_anon(struct folio *folio, struct vm_area_struct *vma, unsigned long address, bool exclusive) { struct anon_vma *anon_vma = vma->anon_vma; BUG_ON(!anon_vma); /* * If the folio isn't exclusive to this vma, we must use the _oldest_ * possible anon_vma for the folio mapping! */ if (!exclusive) anon_vma = anon_vma->root; /* * page_idle does a lockless/optimistic rmap scan on folio->mapping. * Make sure the compiler doesn't split the stores of anon_vma and * the PAGE_MAPPING_ANON type identifier, otherwise the rmap code * could mistake the mapping for a struct address_space and crash. */ anon_vma = (void *) anon_vma + PAGE_MAPPING_ANON; WRITE_ONCE(folio->mapping, (struct address_space *) anon_vma); folio->index = linear_page_index(vma, address); } /** * __page_check_anon_rmap - sanity check anonymous rmap addition * @folio: The folio containing @page. * @page: the page to check the mapping of * @vma: the vm area in which the mapping is added * @address: the user virtual address mapped */ static void __page_check_anon_rmap(const struct folio *folio, const struct page *page, struct vm_area_struct *vma, unsigned long address) { /* * The page's anon-rmap details (mapping and index) are guaranteed to * be set up correctly at this point. * * We have exclusion against folio_add_anon_rmap_*() because the caller * always holds the page locked. * * We have exclusion against folio_add_new_anon_rmap because those pages * are initially only visible via the pagetables, and the pte is locked * over the call to folio_add_new_anon_rmap. */ VM_BUG_ON_FOLIO(folio_anon_vma(folio)->root != vma->anon_vma->root, folio); VM_BUG_ON_PAGE(page_pgoff(folio, page) != linear_page_index(vma, address), page); } static void __folio_mod_stat(struct folio *folio, int nr, int nr_pmdmapped) { int idx; if (nr) { idx = folio_test_anon(folio) ? NR_ANON_MAPPED : NR_FILE_MAPPED; __lruvec_stat_mod_folio(folio, idx, nr); } if (nr_pmdmapped) { if (folio_test_anon(folio)) { idx = NR_ANON_THPS; __lruvec_stat_mod_folio(folio, idx, nr_pmdmapped); } else { /* NR_*_PMDMAPPED are not maintained per-memcg */ idx = folio_test_swapbacked(folio) ? NR_SHMEM_PMDMAPPED : NR_FILE_PMDMAPPED; __mod_node_page_state(folio_pgdat(folio), idx, nr_pmdmapped); } } } static __always_inline void __folio_add_anon_rmap(struct folio *folio, struct page *page, int nr_pages, struct vm_area_struct *vma, unsigned long address, rmap_t flags, enum rmap_level level) { int i, nr, nr_pmdmapped = 0; VM_WARN_ON_FOLIO(!folio_test_anon(folio), folio); nr = __folio_add_rmap(folio, page, nr_pages, level, &nr_pmdmapped); if (likely(!folio_test_ksm(folio))) __page_check_anon_rmap(folio, page, vma, address); __folio_mod_stat(folio, nr, nr_pmdmapped); if (flags & RMAP_EXCLUSIVE) { switch (level) { case RMAP_LEVEL_PTE: for (i = 0; i < nr_pages; i++) SetPageAnonExclusive(page + i); break; case RMAP_LEVEL_PMD: SetPageAnonExclusive(page); break; } } for (i = 0; i < nr_pages; i++) { struct page *cur_page = page + i; /* While PTE-mapping a THP we have a PMD and a PTE mapping. */ VM_WARN_ON_FOLIO((atomic_read(&cur_page->_mapcount) > 0 || (folio_test_large(folio) && folio_entire_mapcount(folio) > 1)) && PageAnonExclusive(cur_page), folio); } /* * For large folio, only mlock it if it's fully mapped to VMA. It's * not easy to check whether the large folio is fully mapped to VMA * here. Only mlock normal 4K folio and leave page reclaim to handle * large folio. */ if (!folio_test_large(folio)) mlock_vma_folio(folio, vma); } /** * folio_add_anon_rmap_ptes - add PTE mappings to a page range of an anon folio * @folio: The folio to add the mappings to * @page: The first page to add * @nr_pages: The number of pages which will be mapped * @vma: The vm area in which the mappings are added * @address: The user virtual address of the first page to map * @flags: The rmap flags * * The page range of folio is defined by [first_page, first_page + nr_pages) * * The caller needs to hold the page table lock, and the page must be locked in * the anon_vma case: to serialize mapping,index checking after setting, * and to ensure that an anon folio is not being upgraded racily to a KSM folio * (but KSM folios are never downgraded). */ void folio_add_anon_rmap_ptes(struct folio *folio, struct page *page, int nr_pages, struct vm_area_struct *vma, unsigned long address, rmap_t flags) { __folio_add_anon_rmap(folio, page, nr_pages, vma, address, flags, RMAP_LEVEL_PTE); } /** * folio_add_anon_rmap_pmd - add a PMD mapping to a page range of an anon folio * @folio: The folio to add the mapping to * @page: The first page to add * @vma: The vm area in which the mapping is added * @address: The user virtual address of the first page to map * @flags: The rmap flags * * The page range of folio is defined by [first_page, first_page + HPAGE_PMD_NR) * * The caller needs to hold the page table lock, and the page must be locked in * the anon_vma case: to serialize mapping,index checking after setting. */ void folio_add_anon_rmap_pmd(struct folio *folio, struct page *page, struct vm_area_struct *vma, unsigned long address, rmap_t flags) { #ifdef CONFIG_TRANSPARENT_HUGEPAGE __folio_add_anon_rmap(folio, page, HPAGE_PMD_NR, vma, address, flags, RMAP_LEVEL_PMD); #else WARN_ON_ONCE(true); #endif } /** * folio_add_new_anon_rmap - Add mapping to a new anonymous folio. * @folio: The folio to add the mapping to. * @vma: the vm area in which the mapping is added * @address: the user virtual address mapped * @flags: The rmap flags * * Like folio_add_anon_rmap_*() but must only be called on *new* folios. * This means the inc-and-test can be bypassed. * The folio doesn't necessarily need to be locked while it's exclusive * unless two threads map it concurrently. However, the folio must be * locked if it's shared. * * If the folio is pmd-mappable, it is accounted as a THP. */ void folio_add_new_anon_rmap(struct folio *folio, struct vm_area_struct *vma, unsigned long address, rmap_t flags) { const int nr = folio_nr_pages(folio); const bool exclusive = flags & RMAP_EXCLUSIVE; int nr_pmdmapped = 0; VM_WARN_ON_FOLIO(folio_test_hugetlb(folio), folio); VM_WARN_ON_FOLIO(!exclusive && !folio_test_locked(folio), folio); VM_BUG_ON_VMA(address < vma->vm_start || address + (nr << PAGE_SHIFT) > vma->vm_end, vma); /* * VM_DROPPABLE mappings don't swap; instead they're just dropped when * under memory pressure. */ if (!folio_test_swapbacked(folio) && !(vma->vm_flags & VM_DROPPABLE)) __folio_set_swapbacked(folio); __folio_set_anon(folio, vma, address, exclusive); if (likely(!folio_test_large(folio))) { /* increment count (starts at -1) */ atomic_set(&folio->_mapcount, 0); if (exclusive) SetPageAnonExclusive(&folio->page); } else if (!folio_test_pmd_mappable(folio)) { int i; for (i = 0; i < nr; i++) { struct page *page = folio_page(folio, i); /* increment count (starts at -1) */ atomic_set(&page->_mapcount, 0); if (exclusive) SetPageAnonExclusive(page); } /* increment count (starts at -1) */ atomic_set(&folio->_large_mapcount, nr - 1); atomic_set(&folio->_nr_pages_mapped, nr); } else { /* increment count (starts at -1) */ atomic_set(&folio->_entire_mapcount, 0); /* increment count (starts at -1) */ atomic_set(&folio->_large_mapcount, 0); atomic_set(&folio->_nr_pages_mapped, ENTIRELY_MAPPED); if (exclusive) SetPageAnonExclusive(&folio->page); nr_pmdmapped = nr; } __folio_mod_stat(folio, nr, nr_pmdmapped); mod_mthp_stat(folio_order(folio), MTHP_STAT_NR_ANON, 1); } static __always_inline void __folio_add_file_rmap(struct folio *folio, struct page *page, int nr_pages, struct vm_area_struct *vma, enum rmap_level level) { int nr, nr_pmdmapped = 0; VM_WARN_ON_FOLIO(folio_test_anon(folio), folio); nr = __folio_add_rmap(folio, page, nr_pages, level, &nr_pmdmapped); __folio_mod_stat(folio, nr, nr_pmdmapped); /* See comments in folio_add_anon_rmap_*() */ if (!folio_test_large(folio)) mlock_vma_folio(folio, vma); } /** * folio_add_file_rmap_ptes - add PTE mappings to a page range of a folio * @folio: The folio to add the mappings to * @page: The first page to add * @nr_pages: The number of pages that will be mapped using PTEs * @vma: The vm area in which the mappings are added * * The page range of the folio is defined by [page, page + nr_pages) * * The caller needs to hold the page table lock. */ void folio_add_file_rmap_ptes(struct folio *folio, struct page *page, int nr_pages, struct vm_area_struct *vma) { __folio_add_file_rmap(folio, page, nr_pages, vma, RMAP_LEVEL_PTE); } /** * folio_add_file_rmap_pmd - add a PMD mapping to a page range of a folio * @folio: The folio to add the mapping to * @page: The first page to add * @vma: The vm area in which the mapping is added * * The page range of the folio is defined by [page, page + HPAGE_PMD_NR) * * The caller needs to hold the page table lock. */ void folio_add_file_rmap_pmd(struct folio *folio, struct page *page, struct vm_area_struct *vma) { #ifdef CONFIG_TRANSPARENT_HUGEPAGE __folio_add_file_rmap(folio, page, HPAGE_PMD_NR, vma, RMAP_LEVEL_PMD); #else WARN_ON_ONCE(true); #endif } static __always_inline void __folio_remove_rmap(struct folio *folio, struct page *page, int nr_pages, struct vm_area_struct *vma, enum rmap_level level) { atomic_t *mapped = &folio->_nr_pages_mapped; int last = 0, nr = 0, nr_pmdmapped = 0; bool partially_mapped = false; __folio_rmap_sanity_checks(folio, page, nr_pages, level); switch (level) { case RMAP_LEVEL_PTE: if (!folio_test_large(folio)) { nr = atomic_add_negative(-1, &folio->_mapcount); break; } atomic_sub(nr_pages, &folio->_large_mapcount); do { last += atomic_add_negative(-1, &page->_mapcount); } while (page++, --nr_pages > 0); if (last && atomic_sub_return_relaxed(last, mapped) < ENTIRELY_MAPPED) nr = last; partially_mapped = nr && atomic_read(mapped); break; case RMAP_LEVEL_PMD: atomic_dec(&folio->_large_mapcount); last = atomic_add_negative(-1, &folio->_entire_mapcount); if (last) { nr = atomic_sub_return_relaxed(ENTIRELY_MAPPED, mapped); if (likely(nr < ENTIRELY_MAPPED)) { nr_pmdmapped = folio_nr_pages(folio); nr = nr_pmdmapped - (nr & FOLIO_PAGES_MAPPED); /* Raced ahead of another remove and an add? */ if (unlikely(nr < 0)) nr = 0; } else { /* An add of ENTIRELY_MAPPED raced ahead */ nr = 0; } } partially_mapped = nr && nr < nr_pmdmapped; break; } /* * Queue anon large folio for deferred split if at least one page of * the folio is unmapped and at least one page is still mapped. * * Check partially_mapped first to ensure it is a large folio. */ if (partially_mapped && folio_test_anon(folio) && !folio_test_partially_mapped(folio)) deferred_split_folio(folio, true); __folio_mod_stat(folio, -nr, -nr_pmdmapped); /* * It would be tidy to reset folio_test_anon mapping when fully * unmapped, but that might overwrite a racing folio_add_anon_rmap_*() * which increments mapcount after us but sets mapping before us: * so leave the reset to free_pages_prepare, and remember that * it's only reliable while mapped. */ munlock_vma_folio(folio, vma); } /** * folio_remove_rmap_ptes - remove PTE mappings from a page range of a folio * @folio: The folio to remove the mappings from * @page: The first page to remove * @nr_pages: The number of pages that will be removed from the mapping * @vma: The vm area from which the mappings are removed * * The page range of the folio is defined by [page, page + nr_pages) * * The caller needs to hold the page table lock. */ void folio_remove_rmap_ptes(struct folio *folio, struct page *page, int nr_pages, struct vm_area_struct *vma) { __folio_remove_rmap(folio, page, nr_pages, vma, RMAP_LEVEL_PTE); } /** * folio_remove_rmap_pmd - remove a PMD mapping from a page range of a folio * @folio: The folio to remove the mapping from * @page: The first page to remove * @vma: The vm area from which the mapping is removed * * The page range of the folio is defined by [page, page + HPAGE_PMD_NR) * * The caller needs to hold the page table lock. */ void folio_remove_rmap_pmd(struct folio *folio, struct page *page, struct vm_area_struct *vma) { #ifdef CONFIG_TRANSPARENT_HUGEPAGE __folio_remove_rmap(folio, page, HPAGE_PMD_NR, vma, RMAP_LEVEL_PMD); #else WARN_ON_ONCE(true); #endif } /* * @arg: enum ttu_flags will be passed to this argument */ static bool try_to_unmap_one(struct folio *folio, struct vm_area_struct *vma, unsigned long address, void *arg) { struct mm_struct *mm = vma->vm_mm; DEFINE_FOLIO_VMA_WALK(pvmw, folio, vma, address, 0); pte_t pteval; struct page *subpage; bool anon_exclusive, ret = true; struct mmu_notifier_range range; enum ttu_flags flags = (enum ttu_flags)(long)arg; unsigned long pfn; unsigned long hsz = 0; /* * When racing against e.g. zap_pte_range() on another cpu, * in between its ptep_get_and_clear_full() and folio_remove_rmap_*(), * try_to_unmap() may return before page_mapped() has become false, * if page table locking is skipped: use TTU_SYNC to wait for that. */ if (flags & TTU_SYNC) pvmw.flags = PVMW_SYNC; /* * For THP, we have to assume the worse case ie pmd for invalidation. * For hugetlb, it could be much worse if we need to do pud * invalidation in the case of pmd sharing. * * Note that the folio can not be freed in this function as call of * try_to_unmap() must hold a reference on the folio. */ range.end = vma_address_end(&pvmw); mmu_notifier_range_init(&range, MMU_NOTIFY_CLEAR, 0, vma->vm_mm, address, range.end); if (folio_test_hugetlb(folio)) { /* * If sharing is possible, start and end will be adjusted * accordingly. */ adjust_range_if_pmd_sharing_possible(vma, &range.start, &range.end); /* We need the huge page size for set_huge_pte_at() */ hsz = huge_page_size(hstate_vma(vma)); } mmu_notifier_invalidate_range_start(&range); while (page_vma_mapped_walk(&pvmw)) { /* * If the folio is in an mlock()d vma, we must not swap it out. */ if (!(flags & TTU_IGNORE_MLOCK) && (vma->vm_flags & VM_LOCKED)) { /* Restore the mlock which got missed */ if (!folio_test_large(folio)) mlock_vma_folio(folio, vma); goto walk_abort; } if (!pvmw.pte) { if (unmap_huge_pmd_locked(vma, pvmw.address, pvmw.pmd, folio)) goto walk_done; if (flags & TTU_SPLIT_HUGE_PMD) { /* * We temporarily have to drop the PTL and * restart so we can process the PTE-mapped THP. */ split_huge_pmd_locked(vma, pvmw.address, pvmw.pmd, false, folio); flags &= ~TTU_SPLIT_HUGE_PMD; page_vma_mapped_walk_restart(&pvmw); continue; } } /* Unexpected PMD-mapped THP? */ VM_BUG_ON_FOLIO(!pvmw.pte, folio); pfn = pte_pfn(ptep_get(pvmw.pte)); subpage = folio_page(folio, pfn - folio_pfn(folio)); address = pvmw.address; anon_exclusive = folio_test_anon(folio) && PageAnonExclusive(subpage); if (folio_test_hugetlb(folio)) { bool anon = folio_test_anon(folio); /* * The try_to_unmap() is only passed a hugetlb page * in the case where the hugetlb page is poisoned. */ VM_BUG_ON_PAGE(!PageHWPoison(subpage), subpage); /* * huge_pmd_unshare may unmap an entire PMD page. * There is no way of knowing exactly which PMDs may * be cached for this mm, so we must flush them all. * start/end were already adjusted above to cover this * range. */ flush_cache_range(vma, range.start, range.end); /* * To call huge_pmd_unshare, i_mmap_rwsem must be * held in write mode. Caller needs to explicitly * do this outside rmap routines. * * We also must hold hugetlb vma_lock in write mode. * Lock order dictates acquiring vma_lock BEFORE * i_mmap_rwsem. We can only try lock here and fail * if unsuccessful. */ if (!anon) { VM_BUG_ON(!(flags & TTU_RMAP_LOCKED)); if (!hugetlb_vma_trylock_write(vma)) goto walk_abort; if (huge_pmd_unshare(mm, vma, address, pvmw.pte)) { hugetlb_vma_unlock_write(vma); flush_tlb_range(vma, range.start, range.end); /* * The ref count of the PMD page was * dropped which is part of the way map * counting is done for shared PMDs. * Return 'true' here. When there is * no other sharing, huge_pmd_unshare * returns false and we will unmap the * actual page and drop map count * to zero. */ goto walk_done; } hugetlb_vma_unlock_write(vma); } pteval = huge_ptep_clear_flush(vma, address, pvmw.pte); } else { flush_cache_page(vma, address, pfn); /* Nuke the page table entry. */ if (should_defer_flush(mm, flags)) { /* * We clear the PTE but do not flush so potentially * a remote CPU could still be writing to the folio. * If the entry was previously clean then the * architecture must guarantee that a clear->dirty * transition on a cached TLB entry is written through * and traps if the PTE is unmapped. */ pteval = ptep_get_and_clear(mm, address, pvmw.pte); set_tlb_ubc_flush_pending(mm, pteval, address); } else { pteval = ptep_clear_flush(vma, address, pvmw.pte); } } /* * Now the pte is cleared. If this pte was uffd-wp armed, * we may want to replace a none pte with a marker pte if * it's file-backed, so we don't lose the tracking info. */ pte_install_uffd_wp_if_needed(vma, address, pvmw.pte, pteval); /* Set the dirty flag on the folio now the pte is gone. */ if (pte_dirty(pteval)) folio_mark_dirty(folio); /* Update high watermark before we lower rss */ update_hiwater_rss(mm); if (PageHWPoison(subpage) && (flags & TTU_HWPOISON)) { pteval = swp_entry_to_pte(make_hwpoison_entry(subpage)); if (folio_test_hugetlb(folio)) { hugetlb_count_sub(folio_nr_pages(folio), mm); set_huge_pte_at(mm, address, pvmw.pte, pteval, hsz); } else { dec_mm_counter(mm, mm_counter(folio)); set_pte_at(mm, address, pvmw.pte, pteval); } } else if (pte_unused(pteval) && !userfaultfd_armed(vma)) { /* * The guest indicated that the page content is of no * interest anymore. Simply discard the pte, vmscan * will take care of the rest. * A future reference will then fault in a new zero * page. When userfaultfd is active, we must not drop * this page though, as its main user (postcopy * migration) will not expect userfaults on already * copied pages. */ dec_mm_counter(mm, mm_counter(folio)); } else if (folio_test_anon(folio)) { swp_entry_t entry = page_swap_entry(subpage); pte_t swp_pte; /* * Store the swap location in the pte. * See handle_pte_fault() ... */ if (unlikely(folio_test_swapbacked(folio) != folio_test_swapcache(folio))) { WARN_ON_ONCE(1); goto walk_abort; } /* MADV_FREE page check */ if (!folio_test_swapbacked(folio)) { int ref_count, map_count; /* * Synchronize with gup_pte_range(): * - clear PTE; barrier; read refcount * - inc refcount; barrier; read PTE */ smp_mb(); ref_count = folio_ref_count(folio); map_count = folio_mapcount(folio); /* * Order reads for page refcount and dirty flag * (see comments in __remove_mapping()). */ smp_rmb(); /* * The only page refs must be one from isolation * plus the rmap(s) (dropped by discard:). */ if (ref_count == 1 + map_count && (!folio_test_dirty(folio) || /* * Unlike MADV_FREE mappings, VM_DROPPABLE * ones can be dropped even if they've * been dirtied. */ (vma->vm_flags & VM_DROPPABLE))) { dec_mm_counter(mm, MM_ANONPAGES); goto discard; } /* * If the folio was redirtied, it cannot be * discarded. Remap the page to page table. */ set_pte_at(mm, address, pvmw.pte, pteval); /* * Unlike MADV_FREE mappings, VM_DROPPABLE ones * never get swap backed on failure to drop. */ if (!(vma->vm_flags & VM_DROPPABLE)) folio_set_swapbacked(folio); goto walk_abort; } if (swap_duplicate(entry) < 0) { set_pte_at(mm, address, pvmw.pte, pteval); goto walk_abort; } if (arch_unmap_one(mm, vma, address, pteval) < 0) { swap_free(entry); set_pte_at(mm, address, pvmw.pte, pteval); goto walk_abort; } /* See folio_try_share_anon_rmap(): clear PTE first. */ if (anon_exclusive && folio_try_share_anon_rmap_pte(folio, subpage)) { swap_free(entry); set_pte_at(mm, address, pvmw.pte, pteval); goto walk_abort; } if (list_empty(&mm->mmlist)) { spin_lock(&mmlist_lock); if (list_empty(&mm->mmlist)) list_add(&mm->mmlist, &init_mm.mmlist); spin_unlock(&mmlist_lock); } dec_mm_counter(mm, MM_ANONPAGES); inc_mm_counter(mm, MM_SWAPENTS); swp_pte = swp_entry_to_pte(entry); if (anon_exclusive) swp_pte = pte_swp_mkexclusive(swp_pte); if (pte_soft_dirty(pteval)) swp_pte = pte_swp_mksoft_dirty(swp_pte); if (pte_uffd_wp(pteval)) swp_pte = pte_swp_mkuffd_wp(swp_pte); set_pte_at(mm, address, pvmw.pte, swp_pte); } else { /* * This is a locked file-backed folio, * so it cannot be removed from the page * cache and replaced by a new folio before * mmu_notifier_invalidate_range_end, so no * concurrent thread might update its page table * to point at a new folio while a device is * still using this folio. * * See Documentation/mm/mmu_notifier.rst */ dec_mm_counter(mm, mm_counter_file(folio)); } discard: if (unlikely(folio_test_hugetlb(folio))) hugetlb_remove_rmap(folio); else folio_remove_rmap_pte(folio, subpage, vma); if (vma->vm_flags & VM_LOCKED) mlock_drain_local(); folio_put(folio); continue; walk_abort: ret = false; walk_done: page_vma_mapped_walk_done(&pvmw); break; } mmu_notifier_invalidate_range_end(&range); return ret; } static bool invalid_migration_vma(struct vm_area_struct *vma, void *arg) { return vma_is_temporary_stack(vma); } static int folio_not_mapped(struct folio *folio) { return !folio_mapped(folio); } /** * try_to_unmap - Try to remove all page table mappings to a folio. * @folio: The folio to unmap. * @flags: action and flags * * Tries to remove all the page table entries which are mapping this * folio. It is the caller's responsibility to check if the folio is * still mapped if needed (use TTU_SYNC to prevent accounting races). * * Context: Caller must hold the folio lock. */ void try_to_unmap(struct folio *folio, enum ttu_flags flags) { struct rmap_walk_control rwc = { .rmap_one = try_to_unmap_one, .arg = (void *)flags, .done = folio_not_mapped, .anon_lock = folio_lock_anon_vma_read, }; if (flags & TTU_RMAP_LOCKED) rmap_walk_locked(folio, &rwc); else rmap_walk(folio, &rwc); } /* * @arg: enum ttu_flags will be passed to this argument. * * If TTU_SPLIT_HUGE_PMD is specified any PMD mappings will be split into PTEs * containing migration entries. */ static bool try_to_migrate_one(struct folio *folio, struct vm_area_struct *vma, unsigned long address, void *arg) { struct mm_struct *mm = vma->vm_mm; DEFINE_FOLIO_VMA_WALK(pvmw, folio, vma, address, 0); pte_t pteval; struct page *subpage; bool anon_exclusive, ret = true; struct mmu_notifier_range range; enum ttu_flags flags = (enum ttu_flags)(long)arg; unsigned long pfn; unsigned long hsz = 0; /* * When racing against e.g. zap_pte_range() on another cpu, * in between its ptep_get_and_clear_full() and folio_remove_rmap_*(), * try_to_migrate() may return before page_mapped() has become false, * if page table locking is skipped: use TTU_SYNC to wait for that. */ if (flags & TTU_SYNC) pvmw.flags = PVMW_SYNC; /* * unmap_page() in mm/huge_memory.c is the only user of migration with * TTU_SPLIT_HUGE_PMD and it wants to freeze. */ if (flags & TTU_SPLIT_HUGE_PMD) split_huge_pmd_address(vma, address, true, folio); /* * For THP, we have to assume the worse case ie pmd for invalidation. * For hugetlb, it could be much worse if we need to do pud * invalidation in the case of pmd sharing. * * Note that the page can not be free in this function as call of * try_to_unmap() must hold a reference on the page. */ range.end = vma_address_end(&pvmw); mmu_notifier_range_init(&range, MMU_NOTIFY_CLEAR, 0, vma->vm_mm, address, range.end); if (folio_test_hugetlb(folio)) { /* * If sharing is possible, start and end will be adjusted * accordingly. */ adjust_range_if_pmd_sharing_possible(vma, &range.start, &range.end); /* We need the huge page size for set_huge_pte_at() */ hsz = huge_page_size(hstate_vma(vma)); } mmu_notifier_invalidate_range_start(&range); while (page_vma_mapped_walk(&pvmw)) { #ifdef CONFIG_ARCH_ENABLE_THP_MIGRATION /* PMD-mapped THP migration entry */ if (!pvmw.pte) { subpage = folio_page(folio, pmd_pfn(*pvmw.pmd) - folio_pfn(folio)); VM_BUG_ON_FOLIO(folio_test_hugetlb(folio) || !folio_test_pmd_mappable(folio), folio); if (set_pmd_migration_entry(&pvmw, subpage)) { ret = false; page_vma_mapped_walk_done(&pvmw); break; } continue; } #endif /* Unexpected PMD-mapped THP? */ VM_BUG_ON_FOLIO(!pvmw.pte, folio); pfn = pte_pfn(ptep_get(pvmw.pte)); if (folio_is_zone_device(folio)) { /* * Our PTE is a non-present device exclusive entry and * calculating the subpage as for the common case would * result in an invalid pointer. * * Since only PAGE_SIZE pages can currently be * migrated, just set it to page. This will need to be * changed when hugepage migrations to device private * memory are supported. */ VM_BUG_ON_FOLIO(folio_nr_pages(folio) > 1, folio); subpage = &folio->page; } else { subpage = folio_page(folio, pfn - folio_pfn(folio)); } address = pvmw.address; anon_exclusive = folio_test_anon(folio) && PageAnonExclusive(subpage); if (folio_test_hugetlb(folio)) { bool anon = folio_test_anon(folio); /* * huge_pmd_unshare may unmap an entire PMD page. * There is no way of knowing exactly which PMDs may * be cached for this mm, so we must flush them all. * start/end were already adjusted above to cover this * range. */ flush_cache_range(vma, range.start, range.end); /* * To call huge_pmd_unshare, i_mmap_rwsem must be * held in write mode. Caller needs to explicitly * do this outside rmap routines. * * We also must hold hugetlb vma_lock in write mode. * Lock order dictates acquiring vma_lock BEFORE * i_mmap_rwsem. We can only try lock here and * fail if unsuccessful. */ if (!anon) { VM_BUG_ON(!(flags & TTU_RMAP_LOCKED)); if (!hugetlb_vma_trylock_write(vma)) { page_vma_mapped_walk_done(&pvmw); ret = false; break; } if (huge_pmd_unshare(mm, vma, address, pvmw.pte)) { hugetlb_vma_unlock_write(vma); flush_tlb_range(vma, range.start, range.end); /* * The ref count of the PMD page was * dropped which is part of the way map * counting is done for shared PMDs. * Return 'true' here. When there is * no other sharing, huge_pmd_unshare * returns false and we will unmap the * actual page and drop map count * to zero. */ page_vma_mapped_walk_done(&pvmw); break; } hugetlb_vma_unlock_write(vma); } /* Nuke the hugetlb page table entry */ pteval = huge_ptep_clear_flush(vma, address, pvmw.pte); } else { flush_cache_page(vma, address, pfn); /* Nuke the page table entry. */ if (should_defer_flush(mm, flags)) { /* * We clear the PTE but do not flush so potentially * a remote CPU could still be writing to the folio. * If the entry was previously clean then the * architecture must guarantee that a clear->dirty * transition on a cached TLB entry is written through * and traps if the PTE is unmapped. */ pteval = ptep_get_and_clear(mm, address, pvmw.pte); set_tlb_ubc_flush_pending(mm, pteval, address); } else { pteval = ptep_clear_flush(vma, address, pvmw.pte); } } /* Set the dirty flag on the folio now the pte is gone. */ if (pte_dirty(pteval)) folio_mark_dirty(folio); /* Update high watermark before we lower rss */ update_hiwater_rss(mm); if (folio_is_device_private(folio)) { unsigned long pfn = folio_pfn(folio); swp_entry_t entry; pte_t swp_pte; if (anon_exclusive) WARN_ON_ONCE(folio_try_share_anon_rmap_pte(folio, subpage)); /* * Store the pfn of the page in a special migration * pte. do_swap_page() will wait until the migration * pte is removed and then restart fault handling. */ entry = pte_to_swp_entry(pteval); if (is_writable_device_private_entry(entry)) entry = make_writable_migration_entry(pfn); else if (anon_exclusive) entry = make_readable_exclusive_migration_entry(pfn); else entry = make_readable_migration_entry(pfn); swp_pte = swp_entry_to_pte(entry); /* * pteval maps a zone device page and is therefore * a swap pte. */ if (pte_swp_soft_dirty(pteval)) swp_pte = pte_swp_mksoft_dirty(swp_pte); if (pte_swp_uffd_wp(pteval)) swp_pte = pte_swp_mkuffd_wp(swp_pte); set_pte_at(mm, pvmw.address, pvmw.pte, swp_pte); trace_set_migration_pte(pvmw.address, pte_val(swp_pte), folio_order(folio)); /* * No need to invalidate here it will synchronize on * against the special swap migration pte. */ } else if (PageHWPoison(subpage)) { pteval = swp_entry_to_pte(make_hwpoison_entry(subpage)); if (folio_test_hugetlb(folio)) { hugetlb_count_sub(folio_nr_pages(folio), mm); set_huge_pte_at(mm, address, pvmw.pte, pteval, hsz); } else { dec_mm_counter(mm, mm_counter(folio)); set_pte_at(mm, address, pvmw.pte, pteval); } } else if (pte_unused(pteval) && !userfaultfd_armed(vma)) { /* * The guest indicated that the page content is of no * interest anymore. Simply discard the pte, vmscan * will take care of the rest. * A future reference will then fault in a new zero * page. When userfaultfd is active, we must not drop * this page though, as its main user (postcopy * migration) will not expect userfaults on already * copied pages. */ dec_mm_counter(mm, mm_counter(folio)); } else { swp_entry_t entry; pte_t swp_pte; if (arch_unmap_one(mm, vma, address, pteval) < 0) { if (folio_test_hugetlb(folio)) set_huge_pte_at(mm, address, pvmw.pte, pteval, hsz); else set_pte_at(mm, address, pvmw.pte, pteval); ret = false; page_vma_mapped_walk_done(&pvmw); break; } VM_BUG_ON_PAGE(pte_write(pteval) && folio_test_anon(folio) && !anon_exclusive, subpage); /* See folio_try_share_anon_rmap_pte(): clear PTE first. */ if (folio_test_hugetlb(folio)) { if (anon_exclusive && hugetlb_try_share_anon_rmap(folio)) { set_huge_pte_at(mm, address, pvmw.pte, pteval, hsz); ret = false; page_vma_mapped_walk_done(&pvmw); break; } } else if (anon_exclusive && folio_try_share_anon_rmap_pte(folio, subpage)) { set_pte_at(mm, address, pvmw.pte, pteval); ret = false; page_vma_mapped_walk_done(&pvmw); break; } /* * Store the pfn of the page in a special migration * pte. do_swap_page() will wait until the migration * pte is removed and then restart fault handling. */ if (pte_write(pteval)) entry = make_writable_migration_entry( page_to_pfn(subpage)); else if (anon_exclusive) entry = make_readable_exclusive_migration_entry( page_to_pfn(subpage)); else entry = make_readable_migration_entry( page_to_pfn(subpage)); if (pte_young(pteval)) entry = make_migration_entry_young(entry); if (pte_dirty(pteval)) entry = make_migration_entry_dirty(entry); swp_pte = swp_entry_to_pte(entry); if (pte_soft_dirty(pteval)) swp_pte = pte_swp_mksoft_dirty(swp_pte); if (pte_uffd_wp(pteval)) swp_pte = pte_swp_mkuffd_wp(swp_pte); if (folio_test_hugetlb(folio)) set_huge_pte_at(mm, address, pvmw.pte, swp_pte, hsz); else set_pte_at(mm, address, pvmw.pte, swp_pte); trace_set_migration_pte(address, pte_val(swp_pte), folio_order(folio)); /* * No need to invalidate here it will synchronize on * against the special swap migration pte. */ } if (unlikely(folio_test_hugetlb(folio))) hugetlb_remove_rmap(folio); else folio_remove_rmap_pte(folio, subpage, vma); if (vma->vm_flags & VM_LOCKED) mlock_drain_local(); folio_put(folio); } mmu_notifier_invalidate_range_end(&range); return ret; } /** * try_to_migrate - try to replace all page table mappings with swap entries * @folio: the folio to replace page table entries for * @flags: action and flags * * Tries to remove all the page table entries which are mapping this folio and * replace them with special swap entries. Caller must hold the folio lock. */ void try_to_migrate(struct folio *folio, enum ttu_flags flags) { struct rmap_walk_control rwc = { .rmap_one = try_to_migrate_one, .arg = (void *)flags, .done = folio_not_mapped, .anon_lock = folio_lock_anon_vma_read, }; /* * Migration always ignores mlock and only supports TTU_RMAP_LOCKED and * TTU_SPLIT_HUGE_PMD, TTU_SYNC, and TTU_BATCH_FLUSH flags. */ if (WARN_ON_ONCE(flags & ~(TTU_RMAP_LOCKED | TTU_SPLIT_HUGE_PMD | TTU_SYNC | TTU_BATCH_FLUSH))) return; if (folio_is_zone_device(folio) && (!folio_is_device_private(folio) && !folio_is_device_coherent(folio))) return; /* * During exec, a temporary VMA is setup and later moved. * The VMA is moved under the anon_vma lock but not the * page tables leading to a race where migration cannot * find the migration ptes. Rather than increasing the * locking requirements of exec(), migration skips * temporary VMAs until after exec() completes. */ if (!folio_test_ksm(folio) && folio_test_anon(folio)) rwc.invalid_vma = invalid_migration_vma; if (flags & TTU_RMAP_LOCKED) rmap_walk_locked(folio, &rwc); else rmap_walk(folio, &rwc); } #ifdef CONFIG_DEVICE_PRIVATE struct make_exclusive_args { struct mm_struct *mm; unsigned long address; void *owner; bool valid; }; static bool page_make_device_exclusive_one(struct folio *folio, struct vm_area_struct *vma, unsigned long address, void *priv) { struct mm_struct *mm = vma->vm_mm; DEFINE_FOLIO_VMA_WALK(pvmw, folio, vma, address, 0); struct make_exclusive_args *args = priv; pte_t pteval; struct page *subpage; bool ret = true; struct mmu_notifier_range range; swp_entry_t entry; pte_t swp_pte; pte_t ptent; mmu_notifier_range_init_owner(&range, MMU_NOTIFY_EXCLUSIVE, 0, vma->vm_mm, address, min(vma->vm_end, address + folio_size(folio)), args->owner); mmu_notifier_invalidate_range_start(&range); while (page_vma_mapped_walk(&pvmw)) { /* Unexpected PMD-mapped THP? */ VM_BUG_ON_FOLIO(!pvmw.pte, folio); ptent = ptep_get(pvmw.pte); if (!pte_present(ptent)) { ret = false; page_vma_mapped_walk_done(&pvmw); break; } subpage = folio_page(folio, pte_pfn(ptent) - folio_pfn(folio)); address = pvmw.address; /* Nuke the page table entry. */ flush_cache_page(vma, address, pte_pfn(ptent)); pteval = ptep_clear_flush(vma, address, pvmw.pte); /* Set the dirty flag on the folio now the pte is gone. */ if (pte_dirty(pteval)) folio_mark_dirty(folio); /* * Check that our target page is still mapped at the expected * address. */ if (args->mm == mm && args->address == address && pte_write(pteval)) args->valid = true; /* * Store the pfn of the page in a special migration * pte. do_swap_page() will wait until the migration * pte is removed and then restart fault handling. */ if (pte_write(pteval)) entry = make_writable_device_exclusive_entry( page_to_pfn(subpage)); else entry = make_readable_device_exclusive_entry( page_to_pfn(subpage)); swp_pte = swp_entry_to_pte(entry); if (pte_soft_dirty(pteval)) swp_pte = pte_swp_mksoft_dirty(swp_pte); if (pte_uffd_wp(pteval)) swp_pte = pte_swp_mkuffd_wp(swp_pte); set_pte_at(mm, address, pvmw.pte, swp_pte); /* * There is a reference on the page for the swap entry which has * been removed, so shouldn't take another. */ folio_remove_rmap_pte(folio, subpage, vma); } mmu_notifier_invalidate_range_end(&range); return ret; } /** * folio_make_device_exclusive - Mark the folio exclusively owned by a device. * @folio: The folio to replace page table entries for. * @mm: The mm_struct where the folio is expected to be mapped. * @address: Address where the folio is expected to be mapped. * @owner: passed to MMU_NOTIFY_EXCLUSIVE range notifier callbacks * * Tries to remove all the page table entries which are mapping this * folio and replace them with special device exclusive swap entries to * grant a device exclusive access to the folio. * * Context: Caller must hold the folio lock. * Return: false if the page is still mapped, or if it could not be unmapped * from the expected address. Otherwise returns true (success). */ static bool folio_make_device_exclusive(struct folio *folio, struct mm_struct *mm, unsigned long address, void *owner) { struct make_exclusive_args args = { .mm = mm, .address = address, .owner = owner, .valid = false, }; struct rmap_walk_control rwc = { .rmap_one = page_make_device_exclusive_one, .done = folio_not_mapped, .anon_lock = folio_lock_anon_vma_read, .arg = &args, }; /* * Restrict to anonymous folios for now to avoid potential writeback * issues. */ if (!folio_test_anon(folio)) return false; rmap_walk(folio, &rwc); return args.valid && !folio_mapcount(folio); } /** * make_device_exclusive_range() - Mark a range for exclusive use by a device * @mm: mm_struct of associated target process * @start: start of the region to mark for exclusive device access * @end: end address of region * @pages: returns the pages which were successfully marked for exclusive access * @owner: passed to MMU_NOTIFY_EXCLUSIVE range notifier to allow filtering * * Returns: number of pages found in the range by GUP. A page is marked for * exclusive access only if the page pointer is non-NULL. * * This function finds ptes mapping page(s) to the given address range, locks * them and replaces mappings with special swap entries preventing userspace CPU * access. On fault these entries are replaced with the original mapping after * calling MMU notifiers. * * A driver using this to program access from a device must use a mmu notifier * critical section to hold a device specific lock during programming. Once * programming is complete it should drop the page lock and reference after * which point CPU access to the page will revoke the exclusive access. */ int make_device_exclusive_range(struct mm_struct *mm, unsigned long start, unsigned long end, struct page **pages, void *owner) { long npages = (end - start) >> PAGE_SHIFT; long i; npages = get_user_pages_remote(mm, start, npages, FOLL_GET | FOLL_WRITE | FOLL_SPLIT_PMD, pages, NULL); if (npages < 0) return npages; for (i = 0; i < npages; i++, start += PAGE_SIZE) { struct folio *folio = page_folio(pages[i]); if (PageTail(pages[i]) || !folio_trylock(folio)) { folio_put(folio); pages[i] = NULL; continue; } if (!folio_make_device_exclusive(folio, mm, start, owner)) { folio_unlock(folio); folio_put(folio); pages[i] = NULL; } } return npages; } EXPORT_SYMBOL_GPL(make_device_exclusive_range); #endif void __put_anon_vma(struct anon_vma *anon_vma) { struct anon_vma *root = anon_vma->root; anon_vma_free(anon_vma); if (root != anon_vma && atomic_dec_and_test(&root->refcount)) anon_vma_free(root); } static struct anon_vma *rmap_walk_anon_lock(const struct folio *folio, struct rmap_walk_control *rwc) { struct anon_vma *anon_vma; if (rwc->anon_lock) return rwc->anon_lock(folio, rwc); /* * Note: remove_migration_ptes() cannot use folio_lock_anon_vma_read() * because that depends on page_mapped(); but not all its usages * are holding mmap_lock. Users without mmap_lock are required to * take a reference count to prevent the anon_vma disappearing */ anon_vma = folio_anon_vma(folio); if (!anon_vma) return NULL; if (anon_vma_trylock_read(anon_vma)) goto out; if (rwc->try_lock) { anon_vma = NULL; rwc->contended = true; goto out; } anon_vma_lock_read(anon_vma); out: return anon_vma; } /* * rmap_walk_anon - do something to anonymous page using the object-based * rmap method * @folio: the folio to be handled * @rwc: control variable according to each walk type * @locked: caller holds relevant rmap lock * * Find all the mappings of a folio using the mapping pointer and the vma * chains contained in the anon_vma struct it points to. */ static void rmap_walk_anon(struct folio *folio, struct rmap_walk_control *rwc, bool locked) { struct anon_vma *anon_vma; pgoff_t pgoff_start, pgoff_end; struct anon_vma_chain *avc; if (locked) { anon_vma = folio_anon_vma(folio); /* anon_vma disappear under us? */ VM_BUG_ON_FOLIO(!anon_vma, folio); } else { anon_vma = rmap_walk_anon_lock(folio, rwc); } if (!anon_vma) return; pgoff_start = folio_pgoff(folio); pgoff_end = pgoff_start + folio_nr_pages(folio) - 1; anon_vma_interval_tree_foreach(avc, &anon_vma->rb_root, pgoff_start, pgoff_end) { struct vm_area_struct *vma = avc->vma; unsigned long address = vma_address(vma, pgoff_start, folio_nr_pages(folio)); VM_BUG_ON_VMA(address == -EFAULT, vma); cond_resched(); if (rwc->invalid_vma && rwc->invalid_vma(vma, rwc->arg)) continue; if (!rwc->rmap_one(folio, vma, address, rwc->arg)) break; if (rwc->done && rwc->done(folio)) break; } if (!locked) anon_vma_unlock_read(anon_vma); } /* * rmap_walk_file - do something to file page using the object-based rmap method * @folio: the folio to be handled * @rwc: control variable according to each walk type * @locked: caller holds relevant rmap lock * * Find all the mappings of a folio using the mapping pointer and the vma chains * contained in the address_space struct it points to. */ static void rmap_walk_file(struct folio *folio, struct rmap_walk_control *rwc, bool locked) { struct address_space *mapping = folio_mapping(folio); pgoff_t pgoff_start, pgoff_end; struct vm_area_struct *vma; /* * The page lock not only makes sure that page->mapping cannot * suddenly be NULLified by truncation, it makes sure that the * structure at mapping cannot be freed and reused yet, * so we can safely take mapping->i_mmap_rwsem. */ VM_BUG_ON_FOLIO(!folio_test_locked(folio), folio); if (!mapping) return; pgoff_start = folio_pgoff(folio); pgoff_end = pgoff_start + folio_nr_pages(folio) - 1; if (!locked) { if (i_mmap_trylock_read(mapping)) goto lookup; if (rwc->try_lock) { rwc->contended = true; return; } i_mmap_lock_read(mapping); } lookup: vma_interval_tree_foreach(vma, &mapping->i_mmap, pgoff_start, pgoff_end) { unsigned long address = vma_address(vma, pgoff_start, folio_nr_pages(folio)); VM_BUG_ON_VMA(address == -EFAULT, vma); cond_resched(); if (rwc->invalid_vma && rwc->invalid_vma(vma, rwc->arg)) continue; if (!rwc->rmap_one(folio, vma, address, rwc->arg)) goto done; if (rwc->done && rwc->done(folio)) goto done; } done: if (!locked) i_mmap_unlock_read(mapping); } void rmap_walk(struct folio *folio, struct rmap_walk_control *rwc) { if (unlikely(folio_test_ksm(folio))) rmap_walk_ksm(folio, rwc); else if (folio_test_anon(folio)) rmap_walk_anon(folio, rwc, false); else rmap_walk_file(folio, rwc, false); } /* Like rmap_walk, but caller holds relevant rmap lock */ void rmap_walk_locked(struct folio *folio, struct rmap_walk_control *rwc) { /* no ksm support for now */ VM_BUG_ON_FOLIO(folio_test_ksm(folio), folio); if (folio_test_anon(folio)) rmap_walk_anon(folio, rwc, true); else rmap_walk_file(folio, rwc, true); } #ifdef CONFIG_HUGETLB_PAGE /* * The following two functions are for anonymous (private mapped) hugepages. * Unlike common anonymous pages, anonymous hugepages have no accounting code * and no lru code, because we handle hugepages differently from common pages. */ void hugetlb_add_anon_rmap(struct folio *folio, struct vm_area_struct *vma, unsigned long address, rmap_t flags) { VM_WARN_ON_FOLIO(!folio_test_hugetlb(folio), folio); VM_WARN_ON_FOLIO(!folio_test_anon(folio), folio); atomic_inc(&folio->_entire_mapcount); atomic_inc(&folio->_large_mapcount); if (flags & RMAP_EXCLUSIVE) SetPageAnonExclusive(&folio->page); VM_WARN_ON_FOLIO(folio_entire_mapcount(folio) > 1 && PageAnonExclusive(&folio->page), folio); } void hugetlb_add_new_anon_rmap(struct folio *folio, struct vm_area_struct *vma, unsigned long address) { VM_WARN_ON_FOLIO(!folio_test_hugetlb(folio), folio); BUG_ON(address < vma->vm_start || address >= vma->vm_end); /* increment count (starts at -1) */ atomic_set(&folio->_entire_mapcount, 0); atomic_set(&folio->_large_mapcount, 0); folio_clear_hugetlb_restore_reserve(folio); __folio_set_anon(folio, vma, address, true); SetPageAnonExclusive(&folio->page); } #endif /* CONFIG_HUGETLB_PAGE */ |
| 186 187 194 194 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef __LINUX_BACKING_DEV_DEFS_H #define __LINUX_BACKING_DEV_DEFS_H #include <linux/list.h> #include <linux/radix-tree.h> #include <linux/rbtree.h> #include <linux/spinlock.h> #include <linux/percpu_counter.h> #include <linux/percpu-refcount.h> #include <linux/flex_proportions.h> #include <linux/timer.h> #include <linux/workqueue.h> #include <linux/kref.h> #include <linux/refcount.h> struct page; struct device; struct dentry; /* * Bits in bdi_writeback.state */ enum wb_state { WB_registered, /* bdi_register() was done */ WB_writeback_running, /* Writeback is in progress */ WB_has_dirty_io, /* Dirty inodes on ->b_{dirty|io|more_io} */ WB_start_all, /* nr_pages == 0 (all) work pending */ }; enum wb_stat_item { WB_RECLAIMABLE, WB_WRITEBACK, WB_DIRTIED, WB_WRITTEN, NR_WB_STAT_ITEMS }; #define WB_STAT_BATCH (8*(1+ilog2(nr_cpu_ids))) /* * why some writeback work was initiated */ enum wb_reason { WB_REASON_BACKGROUND, WB_REASON_VMSCAN, WB_REASON_SYNC, WB_REASON_PERIODIC, WB_REASON_LAPTOP_TIMER, WB_REASON_FS_FREE_SPACE, /* * There is no bdi forker thread any more and works are done * by emergency worker, however, this is TPs userland visible * and we'll be exposing exactly the same information, * so it has a mismatch name. */ WB_REASON_FORKER_THREAD, WB_REASON_FOREIGN_FLUSH, WB_REASON_MAX, }; struct wb_completion { atomic_t cnt; wait_queue_head_t *waitq; }; #define __WB_COMPLETION_INIT(_waitq) \ (struct wb_completion){ .cnt = ATOMIC_INIT(1), .waitq = (_waitq) } /* * If one wants to wait for one or more wb_writeback_works, each work's * ->done should be set to a wb_completion defined using the following * macro. Once all work items are issued with wb_queue_work(), the caller * can wait for the completion of all using wb_wait_for_completion(). Work * items which are waited upon aren't freed automatically on completion. */ #define WB_COMPLETION_INIT(bdi) __WB_COMPLETION_INIT(&(bdi)->wb_waitq) #define DEFINE_WB_COMPLETION(cmpl, bdi) \ struct wb_completion cmpl = WB_COMPLETION_INIT(bdi) /* * Each wb (bdi_writeback) can perform writeback operations, is measured * and throttled, independently. Without cgroup writeback, each bdi * (bdi_writeback) is served by its embedded bdi->wb. * * On the default hierarchy, blkcg implicitly enables memcg. This allows * using memcg's page ownership for attributing writeback IOs, and every * memcg - blkcg combination can be served by its own wb by assigning a * dedicated wb to each memcg, which enables isolation across different * cgroups and propagation of IO back pressure down from the IO layer upto * the tasks which are generating the dirty pages to be written back. * * A cgroup wb is indexed on its bdi by the ID of the associated memcg, * refcounted with the number of inodes attached to it, and pins the memcg * and the corresponding blkcg. As the corresponding blkcg for a memcg may * change as blkcg is disabled and enabled higher up in the hierarchy, a wb * is tested for blkcg after lookup and removed from index on mismatch so * that a new wb for the combination can be created. * * Each bdi_writeback that is not embedded into the backing_dev_info must hold * a reference to the parent backing_dev_info. See cgwb_create() for details. */ struct bdi_writeback { struct backing_dev_info *bdi; /* our parent bdi */ unsigned long state; /* Always use atomic bitops on this */ unsigned long last_old_flush; /* last old data flush */ struct list_head b_dirty; /* dirty inodes */ struct list_head b_io; /* parked for writeback */ struct list_head b_more_io; /* parked for more writeback */ struct list_head b_dirty_time; /* time stamps are dirty */ spinlock_t list_lock; /* protects the b_* lists */ atomic_t writeback_inodes; /* number of inodes under writeback */ struct percpu_counter stat[NR_WB_STAT_ITEMS]; unsigned long bw_time_stamp; /* last time write bw is updated */ unsigned long dirtied_stamp; unsigned long written_stamp; /* pages written at bw_time_stamp */ unsigned long write_bandwidth; /* the estimated write bandwidth */ unsigned long avg_write_bandwidth; /* further smoothed write bw, > 0 */ /* * The base dirty throttle rate, re-calculated on every 200ms. * All the bdi tasks' dirty rate will be curbed under it. * @dirty_ratelimit tracks the estimated @balanced_dirty_ratelimit * in small steps and is much more smooth/stable than the latter. */ unsigned long dirty_ratelimit; unsigned long balanced_dirty_ratelimit; struct fprop_local_percpu completions; int dirty_exceeded; enum wb_reason start_all_reason; spinlock_t work_lock; /* protects work_list & dwork scheduling */ struct list_head work_list; struct delayed_work dwork; /* work item used for writeback */ struct delayed_work bw_dwork; /* work item used for bandwidth estimate */ struct list_head bdi_node; /* anchored at bdi->wb_list */ #ifdef CONFIG_CGROUP_WRITEBACK struct percpu_ref refcnt; /* used only for !root wb's */ struct fprop_local_percpu memcg_completions; struct cgroup_subsys_state *memcg_css; /* the associated memcg */ struct cgroup_subsys_state *blkcg_css; /* and blkcg */ struct list_head memcg_node; /* anchored at memcg->cgwb_list */ struct list_head blkcg_node; /* anchored at blkcg->cgwb_list */ struct list_head b_attached; /* attached inodes, protected by list_lock */ struct list_head offline_node; /* anchored at offline_cgwbs */ union { struct work_struct release_work; struct rcu_head rcu; }; #endif }; struct backing_dev_info { u64 id; struct rb_node rb_node; /* keyed by ->id */ struct list_head bdi_list; unsigned long ra_pages; /* max readahead in PAGE_SIZE units */ unsigned long io_pages; /* max allowed IO size */ struct kref refcnt; /* Reference counter for the structure */ unsigned int capabilities; /* Device capabilities */ unsigned int min_ratio; unsigned int max_ratio, max_prop_frac; /* * Sum of avg_write_bw of wbs with dirty inodes. > 0 if there are * any dirty wbs, which is depended upon by bdi_has_dirty(). */ atomic_long_t tot_write_bandwidth; /* * Jiffies when last process was dirty throttled on this bdi. Used by * blk-wbt. */ unsigned long last_bdp_sleep; struct bdi_writeback wb; /* the root writeback info for this bdi */ struct list_head wb_list; /* list of all wbs */ #ifdef CONFIG_CGROUP_WRITEBACK struct radix_tree_root cgwb_tree; /* radix tree of active cgroup wbs */ struct mutex cgwb_release_mutex; /* protect shutdown of wb structs */ struct rw_semaphore wb_switch_rwsem; /* no cgwb switch while syncing */ #endif wait_queue_head_t wb_waitq; struct device *dev; char dev_name[64]; struct device *owner; struct timer_list laptop_mode_wb_timer; #ifdef CONFIG_DEBUG_FS struct dentry *debug_dir; #endif }; struct wb_lock_cookie { bool locked; unsigned long flags; }; #ifdef CONFIG_CGROUP_WRITEBACK /** * wb_tryget - try to increment a wb's refcount * @wb: bdi_writeback to get */ static inline bool wb_tryget(struct bdi_writeback *wb) { if (wb != &wb->bdi->wb) return percpu_ref_tryget(&wb->refcnt); return true; } /** * wb_get - increment a wb's refcount * @wb: bdi_writeback to get */ static inline void wb_get(struct bdi_writeback *wb) { if (wb != &wb->bdi->wb) percpu_ref_get(&wb->refcnt); } /** * wb_put - decrement a wb's refcount * @wb: bdi_writeback to put * @nr: number of references to put */ static inline void wb_put_many(struct bdi_writeback *wb, unsigned long nr) { if (WARN_ON_ONCE(!wb->bdi)) { /* * A driver bug might cause a file to be removed before bdi was * initialized. */ return; } if (wb != &wb->bdi->wb) percpu_ref_put_many(&wb->refcnt, nr); } /** * wb_put - decrement a wb's refcount * @wb: bdi_writeback to put */ static inline void wb_put(struct bdi_writeback *wb) { wb_put_many(wb, 1); } /** * wb_dying - is a wb dying? * @wb: bdi_writeback of interest * * Returns whether @wb is unlinked and being drained. */ static inline bool wb_dying(struct bdi_writeback *wb) { return percpu_ref_is_dying(&wb->refcnt); } #else /* CONFIG_CGROUP_WRITEBACK */ static inline bool wb_tryget(struct bdi_writeback *wb) { return true; } static inline void wb_get(struct bdi_writeback *wb) { } static inline void wb_put(struct bdi_writeback *wb) { } static inline void wb_put_many(struct bdi_writeback *wb, unsigned long nr) { } static inline bool wb_dying(struct bdi_writeback *wb) { return false; } #endif /* CONFIG_CGROUP_WRITEBACK */ #endif /* __LINUX_BACKING_DEV_DEFS_H */ |
| 3 3 3 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 | // SPDX-License-Identifier: GPL-2.0 #include <linux/debugfs.h> #include "netdevsim.h" #define NSIM_DEV_HWSTATS_TRAFFIC_MS 100 static struct list_head * nsim_dev_hwstats_get_list_head(struct nsim_dev_hwstats *hwstats, enum netdev_offload_xstats_type type) { switch (type) { case NETDEV_OFFLOAD_XSTATS_TYPE_L3: return &hwstats->l3_list; } WARN_ON_ONCE(1); return NULL; } static void nsim_dev_hwstats_traffic_bump(struct nsim_dev_hwstats *hwstats, enum netdev_offload_xstats_type type) { struct nsim_dev_hwstats_netdev *hwsdev; struct list_head *hwsdev_list; hwsdev_list = nsim_dev_hwstats_get_list_head(hwstats, type); if (WARN_ON(!hwsdev_list)) return; list_for_each_entry(hwsdev, hwsdev_list, list) { if (hwsdev->enabled) { hwsdev->stats.rx_packets += 1; hwsdev->stats.tx_packets += 2; hwsdev->stats.rx_bytes += 100; hwsdev->stats.tx_bytes += 300; } } } static void nsim_dev_hwstats_traffic_work(struct work_struct *work) { struct nsim_dev_hwstats *hwstats; hwstats = container_of(work, struct nsim_dev_hwstats, traffic_dw.work); mutex_lock(&hwstats->hwsdev_list_lock); nsim_dev_hwstats_traffic_bump(hwstats, NETDEV_OFFLOAD_XSTATS_TYPE_L3); mutex_unlock(&hwstats->hwsdev_list_lock); schedule_delayed_work(&hwstats->traffic_dw, msecs_to_jiffies(NSIM_DEV_HWSTATS_TRAFFIC_MS)); } static struct nsim_dev_hwstats_netdev * nsim_dev_hwslist_find_hwsdev(struct list_head *hwsdev_list, int ifindex) { struct nsim_dev_hwstats_netdev *hwsdev; list_for_each_entry(hwsdev, hwsdev_list, list) { if (hwsdev->netdev->ifindex == ifindex) return hwsdev; } return NULL; } static int nsim_dev_hwsdev_enable(struct nsim_dev_hwstats_netdev *hwsdev, struct netlink_ext_ack *extack) { if (hwsdev->fail_enable) { hwsdev->fail_enable = false; NL_SET_ERR_MSG_MOD(extack, "Stats enablement set to fail"); return -ECANCELED; } hwsdev->enabled = true; return 0; } static void nsim_dev_hwsdev_disable(struct nsim_dev_hwstats_netdev *hwsdev) { hwsdev->enabled = false; memset(&hwsdev->stats, 0, sizeof(hwsdev->stats)); } static int nsim_dev_hwsdev_report_delta(struct nsim_dev_hwstats_netdev *hwsdev, struct netdev_notifier_offload_xstats_info *info) { netdev_offload_xstats_report_delta(info->report_delta, &hwsdev->stats); memset(&hwsdev->stats, 0, sizeof(hwsdev->stats)); return 0; } static void nsim_dev_hwsdev_report_used(struct nsim_dev_hwstats_netdev *hwsdev, struct netdev_notifier_offload_xstats_info *info) { if (hwsdev->enabled) netdev_offload_xstats_report_used(info->report_used); } static int nsim_dev_hwstats_event_off_xstats(struct nsim_dev_hwstats *hwstats, struct net_device *dev, unsigned long event, void *ptr) { struct netdev_notifier_offload_xstats_info *info; struct nsim_dev_hwstats_netdev *hwsdev; struct list_head *hwsdev_list; int err = 0; info = ptr; hwsdev_list = nsim_dev_hwstats_get_list_head(hwstats, info->type); if (!hwsdev_list) return 0; mutex_lock(&hwstats->hwsdev_list_lock); hwsdev = nsim_dev_hwslist_find_hwsdev(hwsdev_list, dev->ifindex); if (!hwsdev) goto out; switch (event) { case NETDEV_OFFLOAD_XSTATS_ENABLE: err = nsim_dev_hwsdev_enable(hwsdev, info->info.extack); break; case NETDEV_OFFLOAD_XSTATS_DISABLE: nsim_dev_hwsdev_disable(hwsdev); break; case NETDEV_OFFLOAD_XSTATS_REPORT_USED: nsim_dev_hwsdev_report_used(hwsdev, info); break; case NETDEV_OFFLOAD_XSTATS_REPORT_DELTA: err = nsim_dev_hwsdev_report_delta(hwsdev, info); break; } out: mutex_unlock(&hwstats->hwsdev_list_lock); return err; } static void nsim_dev_hwsdev_fini(struct nsim_dev_hwstats_netdev *hwsdev) { dev_put(hwsdev->netdev); kfree(hwsdev); } static void __nsim_dev_hwstats_event_unregister(struct nsim_dev_hwstats *hwstats, struct net_device *dev, enum netdev_offload_xstats_type type) { struct nsim_dev_hwstats_netdev *hwsdev; struct list_head *hwsdev_list; hwsdev_list = nsim_dev_hwstats_get_list_head(hwstats, type); if (WARN_ON(!hwsdev_list)) return; hwsdev = nsim_dev_hwslist_find_hwsdev(hwsdev_list, dev->ifindex); if (!hwsdev) return; list_del(&hwsdev->list); nsim_dev_hwsdev_fini(hwsdev); } static void nsim_dev_hwstats_event_unregister(struct nsim_dev_hwstats *hwstats, struct net_device *dev) { mutex_lock(&hwstats->hwsdev_list_lock); __nsim_dev_hwstats_event_unregister(hwstats, dev, NETDEV_OFFLOAD_XSTATS_TYPE_L3); mutex_unlock(&hwstats->hwsdev_list_lock); } static int nsim_dev_hwstats_event(struct nsim_dev_hwstats *hwstats, struct net_device *dev, unsigned long event, void *ptr) { switch (event) { case NETDEV_OFFLOAD_XSTATS_ENABLE: case NETDEV_OFFLOAD_XSTATS_DISABLE: case NETDEV_OFFLOAD_XSTATS_REPORT_USED: case NETDEV_OFFLOAD_XSTATS_REPORT_DELTA: return nsim_dev_hwstats_event_off_xstats(hwstats, dev, event, ptr); case NETDEV_UNREGISTER: nsim_dev_hwstats_event_unregister(hwstats, dev); break; } return 0; } static int nsim_dev_netdevice_event(struct notifier_block *nb, unsigned long event, void *ptr) { struct net_device *dev = netdev_notifier_info_to_dev(ptr); struct nsim_dev_hwstats *hwstats; int err = 0; hwstats = container_of(nb, struct nsim_dev_hwstats, netdevice_nb); err = nsim_dev_hwstats_event(hwstats, dev, event, ptr); if (err) return notifier_from_errno(err); return NOTIFY_OK; } static int nsim_dev_hwstats_enable_ifindex(struct nsim_dev_hwstats *hwstats, int ifindex, enum netdev_offload_xstats_type type, struct list_head *hwsdev_list) { struct nsim_dev_hwstats_netdev *hwsdev; struct nsim_dev *nsim_dev; struct net_device *netdev; bool notify = false; struct net *net; int err = 0; nsim_dev = container_of(hwstats, struct nsim_dev, hwstats); net = nsim_dev_net(nsim_dev); rtnl_lock(); mutex_lock(&hwstats->hwsdev_list_lock); hwsdev = nsim_dev_hwslist_find_hwsdev(hwsdev_list, ifindex); if (hwsdev) goto out_unlock_list; netdev = dev_get_by_index(net, ifindex); if (!netdev) { err = -ENODEV; goto out_unlock_list; } hwsdev = kzalloc(sizeof(*hwsdev), GFP_KERNEL); if (!hwsdev) { err = -ENOMEM; goto out_put_netdev; } hwsdev->netdev = netdev; list_add_tail(&hwsdev->list, hwsdev_list); mutex_unlock(&hwstats->hwsdev_list_lock); if (netdev_offload_xstats_enabled(netdev, type)) { nsim_dev_hwsdev_enable(hwsdev, NULL); notify = true; } if (notify) rtnl_offload_xstats_notify(netdev); rtnl_unlock(); return err; out_put_netdev: dev_put(netdev); out_unlock_list: mutex_unlock(&hwstats->hwsdev_list_lock); rtnl_unlock(); return err; } static int nsim_dev_hwstats_disable_ifindex(struct nsim_dev_hwstats *hwstats, int ifindex, enum netdev_offload_xstats_type type, struct list_head *hwsdev_list) { struct nsim_dev_hwstats_netdev *hwsdev; int err = 0; rtnl_lock(); mutex_lock(&hwstats->hwsdev_list_lock); hwsdev = nsim_dev_hwslist_find_hwsdev(hwsdev_list, ifindex); if (hwsdev) list_del(&hwsdev->list); mutex_unlock(&hwstats->hwsdev_list_lock); if (!hwsdev) { err = -ENOENT; goto unlock_out; } if (netdev_offload_xstats_enabled(hwsdev->netdev, type)) { netdev_offload_xstats_push_delta(hwsdev->netdev, type, &hwsdev->stats); rtnl_offload_xstats_notify(hwsdev->netdev); } nsim_dev_hwsdev_fini(hwsdev); unlock_out: rtnl_unlock(); return err; } static int nsim_dev_hwstats_fail_ifindex(struct nsim_dev_hwstats *hwstats, int ifindex, enum netdev_offload_xstats_type type, struct list_head *hwsdev_list) { struct nsim_dev_hwstats_netdev *hwsdev; int err = 0; mutex_lock(&hwstats->hwsdev_list_lock); hwsdev = nsim_dev_hwslist_find_hwsdev(hwsdev_list, ifindex); if (!hwsdev) { err = -ENOENT; goto err_hwsdev_list_unlock; } hwsdev->fail_enable = true; err_hwsdev_list_unlock: mutex_unlock(&hwstats->hwsdev_list_lock); return err; } enum nsim_dev_hwstats_do { NSIM_DEV_HWSTATS_DO_DISABLE, NSIM_DEV_HWSTATS_DO_ENABLE, NSIM_DEV_HWSTATS_DO_FAIL, }; struct nsim_dev_hwstats_fops { const struct file_operations fops; enum nsim_dev_hwstats_do action; enum netdev_offload_xstats_type type; }; static ssize_t nsim_dev_hwstats_do_write(struct file *file, const char __user *data, size_t count, loff_t *ppos) { struct nsim_dev_hwstats *hwstats = file->private_data; struct nsim_dev_hwstats_fops *hwsfops; struct list_head *hwsdev_list; int ifindex; int err; hwsfops = container_of(debugfs_real_fops(file), struct nsim_dev_hwstats_fops, fops); err = kstrtoint_from_user(data, count, 0, &ifindex); if (err) return err; hwsdev_list = nsim_dev_hwstats_get_list_head(hwstats, hwsfops->type); if (WARN_ON(!hwsdev_list)) return -EINVAL; switch (hwsfops->action) { case NSIM_DEV_HWSTATS_DO_DISABLE: err = nsim_dev_hwstats_disable_ifindex(hwstats, ifindex, hwsfops->type, hwsdev_list); break; case NSIM_DEV_HWSTATS_DO_ENABLE: err = nsim_dev_hwstats_enable_ifindex(hwstats, ifindex, hwsfops->type, hwsdev_list); break; case NSIM_DEV_HWSTATS_DO_FAIL: err = nsim_dev_hwstats_fail_ifindex(hwstats, ifindex, hwsfops->type, hwsdev_list); break; } if (err) return err; return count; } #define NSIM_DEV_HWSTATS_FOPS(ACTION, TYPE) \ { \ .fops = { \ .open = simple_open, \ .write = nsim_dev_hwstats_do_write, \ .llseek = generic_file_llseek, \ .owner = THIS_MODULE, \ }, \ .action = ACTION, \ .type = TYPE, \ } static const struct nsim_dev_hwstats_fops nsim_dev_hwstats_l3_disable_fops = NSIM_DEV_HWSTATS_FOPS(NSIM_DEV_HWSTATS_DO_DISABLE, NETDEV_OFFLOAD_XSTATS_TYPE_L3); static const struct nsim_dev_hwstats_fops nsim_dev_hwstats_l3_enable_fops = NSIM_DEV_HWSTATS_FOPS(NSIM_DEV_HWSTATS_DO_ENABLE, NETDEV_OFFLOAD_XSTATS_TYPE_L3); static const struct nsim_dev_hwstats_fops nsim_dev_hwstats_l3_fail_fops = NSIM_DEV_HWSTATS_FOPS(NSIM_DEV_HWSTATS_DO_FAIL, NETDEV_OFFLOAD_XSTATS_TYPE_L3); #undef NSIM_DEV_HWSTATS_FOPS int nsim_dev_hwstats_init(struct nsim_dev *nsim_dev) { struct nsim_dev_hwstats *hwstats = &nsim_dev->hwstats; struct net *net = nsim_dev_net(nsim_dev); int err; mutex_init(&hwstats->hwsdev_list_lock); INIT_LIST_HEAD(&hwstats->l3_list); hwstats->netdevice_nb.notifier_call = nsim_dev_netdevice_event; err = register_netdevice_notifier_net(net, &hwstats->netdevice_nb); if (err) goto err_mutex_destroy; hwstats->ddir = debugfs_create_dir("hwstats", nsim_dev->ddir); if (IS_ERR(hwstats->ddir)) { err = PTR_ERR(hwstats->ddir); goto err_unregister_notifier; } hwstats->l3_ddir = debugfs_create_dir("l3", hwstats->ddir); if (IS_ERR(hwstats->l3_ddir)) { err = PTR_ERR(hwstats->l3_ddir); goto err_remove_hwstats_recursive; } debugfs_create_file("enable_ifindex", 0200, hwstats->l3_ddir, hwstats, &nsim_dev_hwstats_l3_enable_fops.fops); debugfs_create_file("disable_ifindex", 0200, hwstats->l3_ddir, hwstats, &nsim_dev_hwstats_l3_disable_fops.fops); debugfs_create_file("fail_next_enable", 0200, hwstats->l3_ddir, hwstats, &nsim_dev_hwstats_l3_fail_fops.fops); INIT_DELAYED_WORK(&hwstats->traffic_dw, &nsim_dev_hwstats_traffic_work); schedule_delayed_work(&hwstats->traffic_dw, msecs_to_jiffies(NSIM_DEV_HWSTATS_TRAFFIC_MS)); return 0; err_remove_hwstats_recursive: debugfs_remove_recursive(hwstats->ddir); err_unregister_notifier: unregister_netdevice_notifier_net(net, &hwstats->netdevice_nb); err_mutex_destroy: mutex_destroy(&hwstats->hwsdev_list_lock); return err; } static void nsim_dev_hwsdev_list_wipe(struct nsim_dev_hwstats *hwstats, enum netdev_offload_xstats_type type) { struct nsim_dev_hwstats_netdev *hwsdev, *tmp; struct list_head *hwsdev_list; hwsdev_list = nsim_dev_hwstats_get_list_head(hwstats, type); if (WARN_ON(!hwsdev_list)) return; mutex_lock(&hwstats->hwsdev_list_lock); list_for_each_entry_safe(hwsdev, tmp, hwsdev_list, list) { list_del(&hwsdev->list); nsim_dev_hwsdev_fini(hwsdev); } mutex_unlock(&hwstats->hwsdev_list_lock); } void nsim_dev_hwstats_exit(struct nsim_dev *nsim_dev) { struct nsim_dev_hwstats *hwstats = &nsim_dev->hwstats; struct net *net = nsim_dev_net(nsim_dev); cancel_delayed_work_sync(&hwstats->traffic_dw); debugfs_remove_recursive(hwstats->ddir); unregister_netdevice_notifier_net(net, &hwstats->netdevice_nb); nsim_dev_hwsdev_list_wipe(hwstats, NETDEV_OFFLOAD_XSTATS_TYPE_L3); mutex_destroy(&hwstats->hwsdev_list_lock); } |
| 33 194 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 | /* SPDX-License-Identifier: GPL-2.0 */ #undef TRACE_SYSTEM #define TRACE_SYSTEM filemap #if !defined(_TRACE_FILEMAP_H) || defined(TRACE_HEADER_MULTI_READ) #define _TRACE_FILEMAP_H #include <linux/types.h> #include <linux/tracepoint.h> #include <linux/mm.h> #include <linux/memcontrol.h> #include <linux/device.h> #include <linux/kdev_t.h> #include <linux/errseq.h> DECLARE_EVENT_CLASS(mm_filemap_op_page_cache, TP_PROTO(struct folio *folio), TP_ARGS(folio), TP_STRUCT__entry( __field(unsigned long, pfn) __field(unsigned long, i_ino) __field(unsigned long, index) __field(dev_t, s_dev) __field(unsigned char, order) ), TP_fast_assign( __entry->pfn = folio_pfn(folio); __entry->i_ino = folio->mapping->host->i_ino; __entry->index = folio->index; if (folio->mapping->host->i_sb) __entry->s_dev = folio->mapping->host->i_sb->s_dev; else __entry->s_dev = folio->mapping->host->i_rdev; __entry->order = folio_order(folio); ), TP_printk("dev %d:%d ino %lx pfn=0x%lx ofs=%lu order=%u", MAJOR(__entry->s_dev), MINOR(__entry->s_dev), __entry->i_ino, __entry->pfn, __entry->index << PAGE_SHIFT, __entry->order) ); DEFINE_EVENT(mm_filemap_op_page_cache, mm_filemap_delete_from_page_cache, TP_PROTO(struct folio *folio), TP_ARGS(folio) ); DEFINE_EVENT(mm_filemap_op_page_cache, mm_filemap_add_to_page_cache, TP_PROTO(struct folio *folio), TP_ARGS(folio) ); DECLARE_EVENT_CLASS(mm_filemap_op_page_cache_range, TP_PROTO( struct address_space *mapping, pgoff_t index, pgoff_t last_index ), TP_ARGS(mapping, index, last_index), TP_STRUCT__entry( __field(unsigned long, i_ino) __field(dev_t, s_dev) __field(unsigned long, index) __field(unsigned long, last_index) ), TP_fast_assign( __entry->i_ino = mapping->host->i_ino; if (mapping->host->i_sb) __entry->s_dev = mapping->host->i_sb->s_dev; else __entry->s_dev = mapping->host->i_rdev; __entry->index = index; __entry->last_index = last_index; ), TP_printk( "dev=%d:%d ino=%lx ofs=%lld-%lld", MAJOR(__entry->s_dev), MINOR(__entry->s_dev), __entry->i_ino, ((loff_t)__entry->index) << PAGE_SHIFT, ((((loff_t)__entry->last_index + 1) << PAGE_SHIFT) - 1) ) ); DEFINE_EVENT(mm_filemap_op_page_cache_range, mm_filemap_get_pages, TP_PROTO( struct address_space *mapping, pgoff_t index, pgoff_t last_index ), TP_ARGS(mapping, index, last_index) ); DEFINE_EVENT(mm_filemap_op_page_cache_range, mm_filemap_map_pages, TP_PROTO( struct address_space *mapping, pgoff_t index, pgoff_t last_index ), TP_ARGS(mapping, index, last_index) ); TRACE_EVENT(mm_filemap_fault, TP_PROTO(struct address_space *mapping, pgoff_t index), TP_ARGS(mapping, index), TP_STRUCT__entry( __field(unsigned long, i_ino) __field(dev_t, s_dev) __field(unsigned long, index) ), TP_fast_assign( __entry->i_ino = mapping->host->i_ino; if (mapping->host->i_sb) __entry->s_dev = mapping->host->i_sb->s_dev; else __entry->s_dev = mapping->host->i_rdev; __entry->index = index; ), TP_printk( "dev=%d:%d ino=%lx ofs=%lld", MAJOR(__entry->s_dev), MINOR(__entry->s_dev), __entry->i_ino, ((loff_t)__entry->index) << PAGE_SHIFT ) ); TRACE_EVENT(filemap_set_wb_err, TP_PROTO(struct address_space *mapping, errseq_t eseq), TP_ARGS(mapping, eseq), TP_STRUCT__entry( __field(unsigned long, i_ino) __field(dev_t, s_dev) __field(errseq_t, errseq) ), TP_fast_assign( __entry->i_ino = mapping->host->i_ino; __entry->errseq = eseq; if (mapping->host->i_sb) __entry->s_dev = mapping->host->i_sb->s_dev; else __entry->s_dev = mapping->host->i_rdev; ), TP_printk("dev=%d:%d ino=0x%lx errseq=0x%x", MAJOR(__entry->s_dev), MINOR(__entry->s_dev), __entry->i_ino, __entry->errseq) ); TRACE_EVENT(file_check_and_advance_wb_err, TP_PROTO(struct file *file, errseq_t old), TP_ARGS(file, old), TP_STRUCT__entry( __field(struct file *, file) __field(unsigned long, i_ino) __field(dev_t, s_dev) __field(errseq_t, old) __field(errseq_t, new) ), TP_fast_assign( __entry->file = file; __entry->i_ino = file->f_mapping->host->i_ino; if (file->f_mapping->host->i_sb) __entry->s_dev = file->f_mapping->host->i_sb->s_dev; else __entry->s_dev = file->f_mapping->host->i_rdev; __entry->old = old; __entry->new = file->f_wb_err; ), TP_printk("file=%p dev=%d:%d ino=0x%lx old=0x%x new=0x%x", __entry->file, MAJOR(__entry->s_dev), MINOR(__entry->s_dev), __entry->i_ino, __entry->old, __entry->new) ); #endif /* _TRACE_FILEMAP_H */ /* This part must be outside protection */ #include <trace/define_trace.h> |
| 3 421 420 419 1 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 | // SPDX-License-Identifier: GPL-2.0 /* * Copyright (C) 1991, 1992 Linus Torvalds * * This file contains the interface functions for the various time related * system calls: time, stime, gettimeofday, settimeofday, adjtime * * Modification history: * * 1993-09-02 Philip Gladstone * Created file with time related functions from sched/core.c and adjtimex() * 1993-10-08 Torsten Duwe * adjtime interface update and CMOS clock write code * 1995-08-13 Torsten Duwe * kernel PLL updated to 1994-12-13 specs (rfc-1589) * 1999-01-16 Ulrich Windl * Introduced error checking for many cases in adjtimex(). * Updated NTP code according to technical memorandum Jan '96 * "A Kernel Model for Precision Timekeeping" by Dave Mills * Allow time_constant larger than MAXTC(6) for NTP v4 (MAXTC == 10) * (Even though the technical memorandum forbids it) * 2004-07-14 Christoph Lameter * Added getnstimeofday to allow the posix timer functions to return * with nanosecond accuracy */ #include <linux/export.h> #include <linux/kernel.h> #include <linux/timex.h> #include <linux/capability.h> #include <linux/timekeeper_internal.h> #include <linux/errno.h> #include <linux/syscalls.h> #include <linux/security.h> #include <linux/fs.h> #include <linux/math64.h> #include <linux/ptrace.h> #include <linux/uaccess.h> #include <linux/compat.h> #include <asm/unistd.h> #include <generated/timeconst.h> #include "timekeeping.h" /* * The timezone where the local system is located. Used as a default by some * programs who obtain this value by using gettimeofday. */ struct timezone sys_tz; EXPORT_SYMBOL(sys_tz); #ifdef __ARCH_WANT_SYS_TIME /* * sys_time() can be implemented in user-level using * sys_gettimeofday(). Is this for backwards compatibility? If so, * why not move it into the appropriate arch directory (for those * architectures that need it). */ SYSCALL_DEFINE1(time, __kernel_old_time_t __user *, tloc) { __kernel_old_time_t i = (__kernel_old_time_t)ktime_get_real_seconds(); if (tloc) { if (put_user(i,tloc)) return -EFAULT; } force_successful_syscall_return(); return i; } /* * sys_stime() can be implemented in user-level using * sys_settimeofday(). Is this for backwards compatibility? If so, * why not move it into the appropriate arch directory (for those * architectures that need it). */ SYSCALL_DEFINE1(stime, __kernel_old_time_t __user *, tptr) { struct timespec64 tv; int err; if (get_user(tv.tv_sec, tptr)) return -EFAULT; tv.tv_nsec = 0; err = security_settime64(&tv, NULL); if (err) return err; do_settimeofday64(&tv); return 0; } #endif /* __ARCH_WANT_SYS_TIME */ #ifdef CONFIG_COMPAT_32BIT_TIME #ifdef __ARCH_WANT_SYS_TIME32 /* old_time32_t is a 32 bit "long" and needs to get converted. */ SYSCALL_DEFINE1(time32, old_time32_t __user *, tloc) { old_time32_t i; i = (old_time32_t)ktime_get_real_seconds(); if (tloc) { if (put_user(i,tloc)) return -EFAULT; } force_successful_syscall_return(); return i; } SYSCALL_DEFINE1(stime32, old_time32_t __user *, tptr) { struct timespec64 tv; int err; if (get_user(tv.tv_sec, tptr)) return -EFAULT; tv.tv_nsec = 0; err = security_settime64(&tv, NULL); if (err) return err; do_settimeofday64(&tv); return 0; } #endif /* __ARCH_WANT_SYS_TIME32 */ #endif SYSCALL_DEFINE2(gettimeofday, struct __kernel_old_timeval __user *, tv, struct timezone __user *, tz) { if (likely(tv != NULL)) { struct timespec64 ts; ktime_get_real_ts64(&ts); if (put_user(ts.tv_sec, &tv->tv_sec) || put_user(ts.tv_nsec / 1000, &tv->tv_usec)) return -EFAULT; } if (unlikely(tz != NULL)) { if (copy_to_user(tz, &sys_tz, sizeof(sys_tz))) return -EFAULT; } return 0; } /* * In case for some reason the CMOS clock has not already been running * in UTC, but in some local time: The first time we set the timezone, * we will warp the clock so that it is ticking UTC time instead of * local time. Presumably, if someone is setting the timezone then we * are running in an environment where the programs understand about * timezones. This should be done at boot time in the /etc/rc script, * as soon as possible, so that the clock can be set right. Otherwise, * various programs will get confused when the clock gets warped. */ int do_sys_settimeofday64(const struct timespec64 *tv, const struct timezone *tz) { static int firsttime = 1; int error = 0; if (tv && !timespec64_valid_settod(tv)) return -EINVAL; error = security_settime64(tv, tz); if (error) return error; if (tz) { /* Verify we're within the +-15 hrs range */ if (tz->tz_minuteswest > 15*60 || tz->tz_minuteswest < -15*60) return -EINVAL; sys_tz = *tz; update_vsyscall_tz(); if (firsttime) { firsttime = 0; if (!tv) timekeeping_warp_clock(); } } if (tv) return do_settimeofday64(tv); return 0; } SYSCALL_DEFINE2(settimeofday, struct __kernel_old_timeval __user *, tv, struct timezone __user *, tz) { struct timespec64 new_ts; struct timezone new_tz; if (tv) { if (get_user(new_ts.tv_sec, &tv->tv_sec) || get_user(new_ts.tv_nsec, &tv->tv_usec)) return -EFAULT; if (new_ts.tv_nsec > USEC_PER_SEC || new_ts.tv_nsec < 0) return -EINVAL; new_ts.tv_nsec *= NSEC_PER_USEC; } if (tz) { if (copy_from_user(&new_tz, tz, sizeof(*tz))) return -EFAULT; } return do_sys_settimeofday64(tv ? &new_ts : NULL, tz ? &new_tz : NULL); } #ifdef CONFIG_COMPAT COMPAT_SYSCALL_DEFINE2(gettimeofday, struct old_timeval32 __user *, tv, struct timezone __user *, tz) { if (tv) { struct timespec64 ts; ktime_get_real_ts64(&ts); if (put_user(ts.tv_sec, &tv->tv_sec) || put_user(ts.tv_nsec / 1000, &tv->tv_usec)) return -EFAULT; } if (tz) { if (copy_to_user(tz, &sys_tz, sizeof(sys_tz))) return -EFAULT; } return 0; } COMPAT_SYSCALL_DEFINE2(settimeofday, struct old_timeval32 __user *, tv, struct timezone __user *, tz) { struct timespec64 new_ts; struct timezone new_tz; if (tv) { if (get_user(new_ts.tv_sec, &tv->tv_sec) || get_user(new_ts.tv_nsec, &tv->tv_usec)) return -EFAULT; if (new_ts.tv_nsec > USEC_PER_SEC || new_ts.tv_nsec < 0) return -EINVAL; new_ts.tv_nsec *= NSEC_PER_USEC; } if (tz) { if (copy_from_user(&new_tz, tz, sizeof(*tz))) return -EFAULT; } return do_sys_settimeofday64(tv ? &new_ts : NULL, tz ? &new_tz : NULL); } #endif #ifdef CONFIG_64BIT SYSCALL_DEFINE1(adjtimex, struct __kernel_timex __user *, txc_p) { struct __kernel_timex txc; /* Local copy of parameter */ int ret; /* Copy the user data space into the kernel copy * structure. But bear in mind that the structures * may change */ if (copy_from_user(&txc, txc_p, sizeof(struct __kernel_timex))) return -EFAULT; ret = do_adjtimex(&txc); return copy_to_user(txc_p, &txc, sizeof(struct __kernel_timex)) ? -EFAULT : ret; } #endif #ifdef CONFIG_COMPAT_32BIT_TIME int get_old_timex32(struct __kernel_timex *txc, const struct old_timex32 __user *utp) { struct old_timex32 tx32; memset(txc, 0, sizeof(struct __kernel_timex)); if (copy_from_user(&tx32, utp, sizeof(struct old_timex32))) return -EFAULT; txc->modes = tx32.modes; txc->offset = tx32.offset; txc->freq = tx32.freq; txc->maxerror = tx32.maxerror; txc->esterror = tx32.esterror; txc->status = tx32.status; txc->constant = tx32.constant; txc->precision = tx32.precision; txc->tolerance = tx32.tolerance; txc->time.tv_sec = tx32.time.tv_sec; txc->time.tv_usec = tx32.time.tv_usec; txc->tick = tx32.tick; txc->ppsfreq = tx32.ppsfreq; txc->jitter = tx32.jitter; txc->shift = tx32.shift; txc->stabil = tx32.stabil; txc->jitcnt = tx32.jitcnt; txc->calcnt = tx32.calcnt; txc->errcnt = tx32.errcnt; txc->stbcnt = tx32.stbcnt; return 0; } int put_old_timex32(struct old_timex32 __user *utp, const struct __kernel_timex *txc) { struct old_timex32 tx32; memset(&tx32, 0, sizeof(struct old_timex32)); tx32.modes = txc->modes; tx32.offset = txc->offset; tx32.freq = txc->freq; tx32.maxerror = txc->maxerror; tx32.esterror = txc->esterror; tx32.status = txc->status; tx32.constant = txc->constant; tx32.precision = txc->precision; tx32.tolerance = txc->tolerance; tx32.time.tv_sec = txc->time.tv_sec; tx32.time.tv_usec = txc->time.tv_usec; tx32.tick = txc->tick; tx32.ppsfreq = txc->ppsfreq; tx32.jitter = txc->jitter; tx32.shift = txc->shift; tx32.stabil = txc->stabil; tx32.jitcnt = txc->jitcnt; tx32.calcnt = txc->calcnt; tx32.errcnt = txc->errcnt; tx32.stbcnt = txc->stbcnt; tx32.tai = txc->tai; if (copy_to_user(utp, &tx32, sizeof(struct old_timex32))) return -EFAULT; return 0; } SYSCALL_DEFINE1(adjtimex_time32, struct old_timex32 __user *, utp) { struct __kernel_timex txc; int err, ret; err = get_old_timex32(&txc, utp); if (err) return err; ret = do_adjtimex(&txc); err = put_old_timex32(utp, &txc); if (err) return err; return ret; } #endif /** * jiffies_to_msecs - Convert jiffies to milliseconds * @j: jiffies value * * Avoid unnecessary multiplications/divisions in the * two most common HZ cases. * * Return: milliseconds value */ unsigned int jiffies_to_msecs(const unsigned long j) { #if HZ <= MSEC_PER_SEC && !(MSEC_PER_SEC % HZ) return (MSEC_PER_SEC / HZ) * j; #elif HZ > MSEC_PER_SEC && !(HZ % MSEC_PER_SEC) return (j + (HZ / MSEC_PER_SEC) - 1)/(HZ / MSEC_PER_SEC); #else # if BITS_PER_LONG == 32 return (HZ_TO_MSEC_MUL32 * j + (1ULL << HZ_TO_MSEC_SHR32) - 1) >> HZ_TO_MSEC_SHR32; # else return DIV_ROUND_UP(j * HZ_TO_MSEC_NUM, HZ_TO_MSEC_DEN); # endif #endif } EXPORT_SYMBOL(jiffies_to_msecs); /** * jiffies_to_usecs - Convert jiffies to microseconds * @j: jiffies value * * Return: microseconds value */ unsigned int jiffies_to_usecs(const unsigned long j) { /* * Hz usually doesn't go much further MSEC_PER_SEC. * jiffies_to_usecs() and usecs_to_jiffies() depend on that. */ BUILD_BUG_ON(HZ > USEC_PER_SEC); #if !(USEC_PER_SEC % HZ) return (USEC_PER_SEC / HZ) * j; #else # if BITS_PER_LONG == 32 return (HZ_TO_USEC_MUL32 * j) >> HZ_TO_USEC_SHR32; # else return (j * HZ_TO_USEC_NUM) / HZ_TO_USEC_DEN; # endif #endif } EXPORT_SYMBOL(jiffies_to_usecs); /** * mktime64 - Converts date to seconds. * @year0: year to convert * @mon0: month to convert * @day: day to convert * @hour: hour to convert * @min: minute to convert * @sec: second to convert * * Converts Gregorian date to seconds since 1970-01-01 00:00:00. * Assumes input in normal date format, i.e. 1980-12-31 23:59:59 * => year=1980, mon=12, day=31, hour=23, min=59, sec=59. * * [For the Julian calendar (which was used in Russia before 1917, * Britain & colonies before 1752, anywhere else before 1582, * and is still in use by some communities) leave out the * -year/100+year/400 terms, and add 10.] * * This algorithm was first published by Gauss (I think). * * A leap second can be indicated by calling this function with sec as * 60 (allowable under ISO 8601). The leap second is treated the same * as the following second since they don't exist in UNIX time. * * An encoding of midnight at the end of the day as 24:00:00 - ie. midnight * tomorrow - (allowable under ISO 8601) is supported. * * Return: seconds since the epoch time for the given input date */ time64_t mktime64(const unsigned int year0, const unsigned int mon0, const unsigned int day, const unsigned int hour, const unsigned int min, const unsigned int sec) { unsigned int mon = mon0, year = year0; /* 1..12 -> 11,12,1..10 */ if (0 >= (int) (mon -= 2)) { mon += 12; /* Puts Feb last since it has leap day */ year -= 1; } return ((((time64_t) (year/4 - year/100 + year/400 + 367*mon/12 + day) + year*365 - 719499 )*24 + hour /* now have hours - midnight tomorrow handled here */ )*60 + min /* now have minutes */ )*60 + sec; /* finally seconds */ } EXPORT_SYMBOL(mktime64); struct __kernel_old_timeval ns_to_kernel_old_timeval(s64 nsec) { struct timespec64 ts = ns_to_timespec64(nsec); struct __kernel_old_timeval tv; tv.tv_sec = ts.tv_sec; tv.tv_usec = (suseconds_t)ts.tv_nsec / 1000; return tv; } EXPORT_SYMBOL(ns_to_kernel_old_timeval); /** * set_normalized_timespec64 - set timespec sec and nsec parts and normalize * * @ts: pointer to timespec variable to be set * @sec: seconds to set * @nsec: nanoseconds to set * * Set seconds and nanoseconds field of a timespec variable and * normalize to the timespec storage format * * Note: The tv_nsec part is always in the range of 0 <= tv_nsec < NSEC_PER_SEC. * For negative values only the tv_sec field is negative ! */ void set_normalized_timespec64(struct timespec64 *ts, time64_t sec, s64 nsec) { while (nsec >= NSEC_PER_SEC) { /* * The following asm() prevents the compiler from * optimising this loop into a modulo operation. See * also __iter_div_u64_rem() in include/linux/time.h */ asm("" : "+rm"(nsec)); nsec -= NSEC_PER_SEC; ++sec; } while (nsec < 0) { asm("" : "+rm"(nsec)); nsec += NSEC_PER_SEC; --sec; } ts->tv_sec = sec; ts->tv_nsec = nsec; } EXPORT_SYMBOL(set_normalized_timespec64); /** * ns_to_timespec64 - Convert nanoseconds to timespec64 * @nsec: the nanoseconds value to be converted * * Return: the timespec64 representation of the nsec parameter. */ struct timespec64 ns_to_timespec64(s64 nsec) { struct timespec64 ts = { 0, 0 }; s32 rem; if (likely(nsec > 0)) { ts.tv_sec = div_u64_rem(nsec, NSEC_PER_SEC, &rem); ts.tv_nsec = rem; } else if (nsec < 0) { /* * With negative times, tv_sec points to the earlier * second, and tv_nsec counts the nanoseconds since * then, so tv_nsec is always a positive number. */ ts.tv_sec = -div_u64_rem(-nsec - 1, NSEC_PER_SEC, &rem) - 1; ts.tv_nsec = NSEC_PER_SEC - rem - 1; } return ts; } EXPORT_SYMBOL(ns_to_timespec64); /** * __msecs_to_jiffies: - convert milliseconds to jiffies * @m: time in milliseconds * * conversion is done as follows: * * - negative values mean 'infinite timeout' (MAX_JIFFY_OFFSET) * * - 'too large' values [that would result in larger than * MAX_JIFFY_OFFSET values] mean 'infinite timeout' too. * * - all other values are converted to jiffies by either multiplying * the input value by a factor or dividing it with a factor and * handling any 32-bit overflows. * for the details see _msecs_to_jiffies() * * msecs_to_jiffies() checks for the passed in value being a constant * via __builtin_constant_p() allowing gcc to eliminate most of the * code, __msecs_to_jiffies() is called if the value passed does not * allow constant folding and the actual conversion must be done at * runtime. * The _msecs_to_jiffies helpers are the HZ dependent conversion * routines found in include/linux/jiffies.h * * Return: jiffies value */ unsigned long __msecs_to_jiffies(const unsigned int m) { /* * Negative value, means infinite timeout: */ if ((int)m < 0) return MAX_JIFFY_OFFSET; return _msecs_to_jiffies(m); } EXPORT_SYMBOL(__msecs_to_jiffies); /** * __usecs_to_jiffies: - convert microseconds to jiffies * @u: time in milliseconds * * Return: jiffies value */ unsigned long __usecs_to_jiffies(const unsigned int u) { if (u > jiffies_to_usecs(MAX_JIFFY_OFFSET)) return MAX_JIFFY_OFFSET; return _usecs_to_jiffies(u); } EXPORT_SYMBOL(__usecs_to_jiffies); /** * timespec64_to_jiffies - convert a timespec64 value to jiffies * @value: pointer to &struct timespec64 * * The TICK_NSEC - 1 rounds up the value to the next resolution. Note * that a remainder subtract here would not do the right thing as the * resolution values don't fall on second boundaries. I.e. the line: * nsec -= nsec % TICK_NSEC; is NOT a correct resolution rounding. * Note that due to the small error in the multiplier here, this * rounding is incorrect for sufficiently large values of tv_nsec, but * well formed timespecs should have tv_nsec < NSEC_PER_SEC, so we're * OK. * * Rather, we just shift the bits off the right. * * The >> (NSEC_JIFFIE_SC - SEC_JIFFIE_SC) converts the scaled nsec * value to a scaled second value. * * Return: jiffies value */ unsigned long timespec64_to_jiffies(const struct timespec64 *value) { u64 sec = value->tv_sec; long nsec = value->tv_nsec + TICK_NSEC - 1; if (sec >= MAX_SEC_IN_JIFFIES){ sec = MAX_SEC_IN_JIFFIES; nsec = 0; } return ((sec * SEC_CONVERSION) + (((u64)nsec * NSEC_CONVERSION) >> (NSEC_JIFFIE_SC - SEC_JIFFIE_SC))) >> SEC_JIFFIE_SC; } EXPORT_SYMBOL(timespec64_to_jiffies); /** * jiffies_to_timespec64 - convert jiffies value to &struct timespec64 * @jiffies: jiffies value * @value: pointer to &struct timespec64 */ void jiffies_to_timespec64(const unsigned long jiffies, struct timespec64 *value) { /* * Convert jiffies to nanoseconds and separate with * one divide. */ u32 rem; value->tv_sec = div_u64_rem((u64)jiffies * TICK_NSEC, NSEC_PER_SEC, &rem); value->tv_nsec = rem; } EXPORT_SYMBOL(jiffies_to_timespec64); /* * Convert jiffies/jiffies_64 to clock_t and back. */ /** * jiffies_to_clock_t - Convert jiffies to clock_t * @x: jiffies value * * Return: jiffies converted to clock_t (CLOCKS_PER_SEC) */ clock_t jiffies_to_clock_t(unsigned long x) { #if (TICK_NSEC % (NSEC_PER_SEC / USER_HZ)) == 0 # if HZ < USER_HZ return x * (USER_HZ / HZ); # else return x / (HZ / USER_HZ); # endif #else return div_u64((u64)x * TICK_NSEC, NSEC_PER_SEC / USER_HZ); #endif } EXPORT_SYMBOL(jiffies_to_clock_t); /** * clock_t_to_jiffies - Convert clock_t to jiffies * @x: clock_t value * * Return: clock_t value converted to jiffies */ unsigned long clock_t_to_jiffies(unsigned long x) { #if (HZ % USER_HZ)==0 if (x >= ~0UL / (HZ / USER_HZ)) return ~0UL; return x * (HZ / USER_HZ); #else /* Don't worry about loss of precision here .. */ if (x >= ~0UL / HZ * USER_HZ) return ~0UL; /* .. but do try to contain it here */ return div_u64((u64)x * HZ, USER_HZ); #endif } EXPORT_SYMBOL(clock_t_to_jiffies); /** * jiffies_64_to_clock_t - Convert jiffies_64 to clock_t * @x: jiffies_64 value * * Return: jiffies_64 value converted to 64-bit "clock_t" (CLOCKS_PER_SEC) */ u64 jiffies_64_to_clock_t(u64 x) { #if (TICK_NSEC % (NSEC_PER_SEC / USER_HZ)) == 0 # if HZ < USER_HZ x = div_u64(x * USER_HZ, HZ); # elif HZ > USER_HZ x = div_u64(x, HZ / USER_HZ); # else /* Nothing to do */ # endif #else /* * There are better ways that don't overflow early, * but even this doesn't overflow in hundreds of years * in 64 bits, so.. */ x = div_u64(x * TICK_NSEC, (NSEC_PER_SEC / USER_HZ)); #endif return x; } EXPORT_SYMBOL(jiffies_64_to_clock_t); /** * nsec_to_clock_t - Convert nsec value to clock_t * @x: nsec value * * Return: nsec value converted to 64-bit "clock_t" (CLOCKS_PER_SEC) */ u64 nsec_to_clock_t(u64 x) { #if (NSEC_PER_SEC % USER_HZ) == 0 return div_u64(x, NSEC_PER_SEC / USER_HZ); #elif (USER_HZ % 512) == 0 return div_u64(x * USER_HZ / 512, NSEC_PER_SEC / 512); #else /* * max relative error 5.7e-8 (1.8s per year) for USER_HZ <= 1024, * overflow after 64.99 years. * exact for HZ=60, 72, 90, 120, 144, 180, 300, 600, 900, ... */ return div_u64(x * 9, (9ull * NSEC_PER_SEC + (USER_HZ / 2)) / USER_HZ); #endif } /** * jiffies64_to_nsecs - Convert jiffies64 to nanoseconds * @j: jiffies64 value * * Return: nanoseconds value */ u64 jiffies64_to_nsecs(u64 j) { #if !(NSEC_PER_SEC % HZ) return (NSEC_PER_SEC / HZ) * j; # else return div_u64(j * HZ_TO_NSEC_NUM, HZ_TO_NSEC_DEN); #endif } EXPORT_SYMBOL(jiffies64_to_nsecs); /** * jiffies64_to_msecs - Convert jiffies64 to milliseconds * @j: jiffies64 value * * Return: milliseconds value */ u64 jiffies64_to_msecs(const u64 j) { #if HZ <= MSEC_PER_SEC && !(MSEC_PER_SEC % HZ) return (MSEC_PER_SEC / HZ) * j; #else return div_u64(j * HZ_TO_MSEC_NUM, HZ_TO_MSEC_DEN); #endif } EXPORT_SYMBOL(jiffies64_to_msecs); /** * nsecs_to_jiffies64 - Convert nsecs in u64 to jiffies64 * * @n: nsecs in u64 * * Unlike {m,u}secs_to_jiffies, type of input is not unsigned int but u64. * And this doesn't return MAX_JIFFY_OFFSET since this function is designed * for scheduler, not for use in device drivers to calculate timeout value. * * note: * NSEC_PER_SEC = 10^9 = (5^9 * 2^9) = (1953125 * 512) * ULLONG_MAX ns = 18446744073.709551615 secs = about 584 years * * Return: nsecs converted to jiffies64 value */ u64 nsecs_to_jiffies64(u64 n) { #if (NSEC_PER_SEC % HZ) == 0 /* Common case, HZ = 100, 128, 200, 250, 256, 500, 512, 1000 etc. */ return div_u64(n, NSEC_PER_SEC / HZ); #elif (HZ % 512) == 0 /* overflow after 292 years if HZ = 1024 */ return div_u64(n * HZ / 512, NSEC_PER_SEC / 512); #else /* * Generic case - optimized for cases where HZ is a multiple of 3. * overflow after 64.99 years, exact for HZ = 60, 72, 90, 120 etc. */ return div_u64(n * 9, (9ull * NSEC_PER_SEC + HZ / 2) / HZ); #endif } EXPORT_SYMBOL(nsecs_to_jiffies64); /** * nsecs_to_jiffies - Convert nsecs in u64 to jiffies * * @n: nsecs in u64 * * Unlike {m,u}secs_to_jiffies, type of input is not unsigned int but u64. * And this doesn't return MAX_JIFFY_OFFSET since this function is designed * for scheduler, not for use in device drivers to calculate timeout value. * * note: * NSEC_PER_SEC = 10^9 = (5^9 * 2^9) = (1953125 * 512) * ULLONG_MAX ns = 18446744073.709551615 secs = about 584 years * * Return: nsecs converted to jiffies value */ unsigned long nsecs_to_jiffies(u64 n) { return (unsigned long)nsecs_to_jiffies64(n); } EXPORT_SYMBOL_GPL(nsecs_to_jiffies); /** * timespec64_add_safe - Add two timespec64 values and do a safety check * for overflow. * @lhs: first (left) timespec64 to add * @rhs: second (right) timespec64 to add * * It's assumed that both values are valid (>= 0). * And, each timespec64 is in normalized form. * * Return: sum of @lhs + @rhs */ struct timespec64 timespec64_add_safe(const struct timespec64 lhs, const struct timespec64 rhs) { struct timespec64 res; set_normalized_timespec64(&res, (timeu64_t) lhs.tv_sec + rhs.tv_sec, lhs.tv_nsec + rhs.tv_nsec); if (unlikely(res.tv_sec < lhs.tv_sec || res.tv_sec < rhs.tv_sec)) { res.tv_sec = TIME64_MAX; res.tv_nsec = 0; } return res; } /** * get_timespec64 - get user's time value into kernel space * @ts: destination &struct timespec64 * @uts: user's time value as &struct __kernel_timespec * * Handles compat or 32-bit modes. * * Return: 0 on success or negative errno on error */ int get_timespec64(struct timespec64 *ts, const struct __kernel_timespec __user *uts) { struct __kernel_timespec kts; int ret; ret = copy_from_user(&kts, uts, sizeof(kts)); if (ret) return -EFAULT; ts->tv_sec = kts.tv_sec; /* Zero out the padding in compat mode */ if (in_compat_syscall()) kts.tv_nsec &= 0xFFFFFFFFUL; /* In 32-bit mode, this drops the padding */ ts->tv_nsec = kts.tv_nsec; return 0; } EXPORT_SYMBOL_GPL(get_timespec64); /** * put_timespec64 - convert timespec64 value to __kernel_timespec format and * copy the latter to userspace * @ts: input &struct timespec64 * @uts: user's &struct __kernel_timespec * * Return: 0 on success or negative errno on error */ int put_timespec64(const struct timespec64 *ts, struct __kernel_timespec __user *uts) { struct __kernel_timespec kts = { .tv_sec = ts->tv_sec, .tv_nsec = ts->tv_nsec }; return copy_to_user(uts, &kts, sizeof(kts)) ? -EFAULT : 0; } EXPORT_SYMBOL_GPL(put_timespec64); static int __get_old_timespec32(struct timespec64 *ts64, const struct old_timespec32 __user *cts) { struct old_timespec32 ts; int ret; ret = copy_from_user(&ts, cts, sizeof(ts)); if (ret) return -EFAULT; ts64->tv_sec = ts.tv_sec; ts64->tv_nsec = ts.tv_nsec; return 0; } static int __put_old_timespec32(const struct timespec64 *ts64, struct old_timespec32 __user *cts) { struct old_timespec32 ts = { .tv_sec = ts64->tv_sec, .tv_nsec = ts64->tv_nsec }; return copy_to_user(cts, &ts, sizeof(ts)) ? -EFAULT : 0; } /** * get_old_timespec32 - get user's old-format time value into kernel space * @ts: destination &struct timespec64 * @uts: user's old-format time value (&struct old_timespec32) * * Handles X86_X32_ABI compatibility conversion. * * Return: 0 on success or negative errno on error */ int get_old_timespec32(struct timespec64 *ts, const void __user *uts) { if (COMPAT_USE_64BIT_TIME) return copy_from_user(ts, uts, sizeof(*ts)) ? -EFAULT : 0; else return __get_old_timespec32(ts, uts); } EXPORT_SYMBOL_GPL(get_old_timespec32); /** * put_old_timespec32 - convert timespec64 value to &struct old_timespec32 and * copy the latter to userspace * @ts: input &struct timespec64 * @uts: user's &struct old_timespec32 * * Handles X86_X32_ABI compatibility conversion. * * Return: 0 on success or negative errno on error */ int put_old_timespec32(const struct timespec64 *ts, void __user *uts) { if (COMPAT_USE_64BIT_TIME) return copy_to_user(uts, ts, sizeof(*ts)) ? -EFAULT : 0; else return __put_old_timespec32(ts, uts); } EXPORT_SYMBOL_GPL(put_old_timespec32); /** * get_itimerspec64 - get user's &struct __kernel_itimerspec into kernel space * @it: destination &struct itimerspec64 * @uit: user's &struct __kernel_itimerspec * * Return: 0 on success or negative errno on error */ int get_itimerspec64(struct itimerspec64 *it, const struct __kernel_itimerspec __user *uit) { int ret; ret = get_timespec64(&it->it_interval, &uit->it_interval); if (ret) return ret; ret = get_timespec64(&it->it_value, &uit->it_value); return ret; } EXPORT_SYMBOL_GPL(get_itimerspec64); /** * put_itimerspec64 - convert &struct itimerspec64 to __kernel_itimerspec format * and copy the latter to userspace * @it: input &struct itimerspec64 * @uit: user's &struct __kernel_itimerspec * * Return: 0 on success or negative errno on error */ int put_itimerspec64(const struct itimerspec64 *it, struct __kernel_itimerspec __user *uit) { int ret; ret = put_timespec64(&it->it_interval, &uit->it_interval); if (ret) return ret; ret = put_timespec64(&it->it_value, &uit->it_value); return ret; } EXPORT_SYMBOL_GPL(put_itimerspec64); /** * get_old_itimerspec32 - get user's &struct old_itimerspec32 into kernel space * @its: destination &struct itimerspec64 * @uits: user's &struct old_itimerspec32 * * Return: 0 on success or negative errno on error */ int get_old_itimerspec32(struct itimerspec64 *its, const struct old_itimerspec32 __user *uits) { if (__get_old_timespec32(&its->it_interval, &uits->it_interval) || __get_old_timespec32(&its->it_value, &uits->it_value)) return -EFAULT; return 0; } EXPORT_SYMBOL_GPL(get_old_itimerspec32); /** * put_old_itimerspec32 - convert &struct itimerspec64 to &struct * old_itimerspec32 and copy the latter to userspace * @its: input &struct itimerspec64 * @uits: user's &struct old_itimerspec32 * * Return: 0 on success or negative errno on error */ int put_old_itimerspec32(const struct itimerspec64 *its, struct old_itimerspec32 __user *uits) { if (__put_old_timespec32(&its->it_interval, &uits->it_interval) || __put_old_timespec32(&its->it_value, &uits->it_value)) return -EFAULT; return 0; } EXPORT_SYMBOL_GPL(put_old_itimerspec32); |
| 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 | /* SPDX-License-Identifier: GPL-2.0 */ /* * Copyright (C) 2020 ARM Ltd. */ #ifndef __ASM_MTE_H #define __ASM_MTE_H #include <asm/compiler.h> #include <asm/mte-def.h> #ifndef __ASSEMBLY__ #include <linux/bitfield.h> #include <linux/kasan-enabled.h> #include <linux/page-flags.h> #include <linux/sched.h> #include <linux/types.h> #include <asm/pgtable-types.h> void mte_clear_page_tags(void *addr); unsigned long mte_copy_tags_from_user(void *to, const void __user *from, unsigned long n); unsigned long mte_copy_tags_to_user(void __user *to, void *from, unsigned long n); int mte_save_tags(struct page *page); void mte_save_page_tags(const void *page_addr, void *tag_storage); void mte_restore_tags(swp_entry_t entry, struct page *page); void mte_restore_page_tags(void *page_addr, const void *tag_storage); void mte_invalidate_tags(int type, pgoff_t offset); void mte_invalidate_tags_area(int type); void *mte_allocate_tag_storage(void); void mte_free_tag_storage(char *storage); #ifdef CONFIG_ARM64_MTE /* track which pages have valid allocation tags */ #define PG_mte_tagged PG_arch_2 /* simple lock to avoid multiple threads tagging the same page */ #define PG_mte_lock PG_arch_3 static inline void set_page_mte_tagged(struct page *page) { VM_WARN_ON_ONCE(folio_test_hugetlb(page_folio(page))); /* * Ensure that the tags written prior to this function are visible * before the page flags update. */ smp_wmb(); set_bit(PG_mte_tagged, &page->flags); } static inline bool page_mte_tagged(struct page *page) { bool ret = test_bit(PG_mte_tagged, &page->flags); VM_WARN_ON_ONCE(folio_test_hugetlb(page_folio(page))); /* * If the page is tagged, ensure ordering with a likely subsequent * read of the tags. */ if (ret) smp_rmb(); return ret; } /* * Lock the page for tagging and return 'true' if the page can be tagged, * 'false' if already tagged. PG_mte_tagged is never cleared and therefore the * locking only happens once for page initialisation. * * The page MTE lock state: * * Locked: PG_mte_lock && !PG_mte_tagged * Unlocked: !PG_mte_lock || PG_mte_tagged * * Acquire semantics only if the page is tagged (returning 'false'). */ static inline bool try_page_mte_tagging(struct page *page) { VM_WARN_ON_ONCE(folio_test_hugetlb(page_folio(page))); if (!test_and_set_bit(PG_mte_lock, &page->flags)) return true; /* * The tags are either being initialised or may have been initialised * already. Check if the PG_mte_tagged flag has been set or wait * otherwise. */ smp_cond_load_acquire(&page->flags, VAL & (1UL << PG_mte_tagged)); return false; } void mte_zero_clear_page_tags(void *addr); void mte_sync_tags(pte_t pte, unsigned int nr_pages); void mte_copy_page_tags(void *kto, const void *kfrom); void mte_thread_init_user(void); void mte_thread_switch(struct task_struct *next); void mte_cpu_setup(void); void mte_suspend_enter(void); void mte_suspend_exit(void); long set_mte_ctrl(struct task_struct *task, unsigned long arg); long get_mte_ctrl(struct task_struct *task); int mte_ptrace_copy_tags(struct task_struct *child, long request, unsigned long addr, unsigned long data); size_t mte_probe_user_range(const char __user *uaddr, size_t size); #else /* CONFIG_ARM64_MTE */ /* unused if !CONFIG_ARM64_MTE, silence the compiler */ #define PG_mte_tagged 0 static inline void set_page_mte_tagged(struct page *page) { } static inline bool page_mte_tagged(struct page *page) { return false; } static inline bool try_page_mte_tagging(struct page *page) { return false; } static inline void mte_zero_clear_page_tags(void *addr) { } static inline void mte_sync_tags(pte_t pte, unsigned int nr_pages) { } static inline void mte_copy_page_tags(void *kto, const void *kfrom) { } static inline void mte_thread_init_user(void) { } static inline void mte_thread_switch(struct task_struct *next) { } static inline void mte_suspend_enter(void) { } static inline void mte_suspend_exit(void) { } static inline long set_mte_ctrl(struct task_struct *task, unsigned long arg) { return 0; } static inline long get_mte_ctrl(struct task_struct *task) { return 0; } static inline int mte_ptrace_copy_tags(struct task_struct *child, long request, unsigned long addr, unsigned long data) { return -EIO; } #endif /* CONFIG_ARM64_MTE */ #if defined(CONFIG_HUGETLB_PAGE) && defined(CONFIG_ARM64_MTE) static inline void folio_set_hugetlb_mte_tagged(struct folio *folio) { VM_WARN_ON_ONCE(!folio_test_hugetlb(folio)); /* * Ensure that the tags written prior to this function are visible * before the folio flags update. */ smp_wmb(); set_bit(PG_mte_tagged, &folio->flags); } static inline bool folio_test_hugetlb_mte_tagged(struct folio *folio) { bool ret = test_bit(PG_mte_tagged, &folio->flags); VM_WARN_ON_ONCE(!folio_test_hugetlb(folio)); /* * If the folio is tagged, ensure ordering with a likely subsequent * read of the tags. */ if (ret) smp_rmb(); return ret; } static inline bool folio_try_hugetlb_mte_tagging(struct folio *folio) { VM_WARN_ON_ONCE(!folio_test_hugetlb(folio)); if (!test_and_set_bit(PG_mte_lock, &folio->flags)) return true; /* * The tags are either being initialised or may have been initialised * already. Check if the PG_mte_tagged flag has been set or wait * otherwise. */ smp_cond_load_acquire(&folio->flags, VAL & (1UL << PG_mte_tagged)); return false; } #else static inline void folio_set_hugetlb_mte_tagged(struct folio *folio) { } static inline bool folio_test_hugetlb_mte_tagged(struct folio *folio) { return false; } static inline bool folio_try_hugetlb_mte_tagging(struct folio *folio) { return false; } #endif static inline void mte_disable_tco_entry(struct task_struct *task) { if (!system_supports_mte()) return; /* * Re-enable tag checking (TCO set on exception entry). This is only * necessary if MTE is enabled in either the kernel or the userspace * task in synchronous or asymmetric mode (SCTLR_EL1.TCF0 bit 0 is set * for both). With MTE disabled in the kernel and disabled or * asynchronous in userspace, tag check faults (including in uaccesses) * are not reported, therefore there is no need to re-enable checking. * This is beneficial on microarchitectures where re-enabling TCO is * expensive. */ if (kasan_hw_tags_enabled() || (task->thread.sctlr_user & (1UL << SCTLR_EL1_TCF0_SHIFT))) asm volatile(SET_PSTATE_TCO(0)); } #ifdef CONFIG_KASAN_HW_TAGS void mte_check_tfsr_el1(void); static inline void mte_check_tfsr_entry(void) { if (!kasan_hw_tags_enabled()) return; mte_check_tfsr_el1(); } static inline void mte_check_tfsr_exit(void) { if (!kasan_hw_tags_enabled()) return; /* * The asynchronous faults are sync'ed automatically with * TFSR_EL1 on kernel entry but for exit an explicit dsb() * is required. */ dsb(nsh); isb(); mte_check_tfsr_el1(); } #else static inline void mte_check_tfsr_el1(void) { } static inline void mte_check_tfsr_entry(void) { } static inline void mte_check_tfsr_exit(void) { } #endif /* CONFIG_KASAN_HW_TAGS */ #endif /* __ASSEMBLY__ */ #endif /* __ASM_MTE_H */ |
| 148 148 22 22 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 | // SPDX-License-Identifier: GPL-2.0 /* * linux/fs/fcntl.c * * Copyright (C) 1991, 1992 Linus Torvalds */ #include <linux/syscalls.h> #include <linux/init.h> #include <linux/mm.h> #include <linux/sched/task.h> #include <linux/fs.h> #include <linux/filelock.h> #include <linux/file.h> #include <linux/capability.h> #include <linux/dnotify.h> #include <linux/slab.h> #include <linux/module.h> #include <linux/pipe_fs_i.h> #include <linux/security.h> #include <linux/ptrace.h> #include <linux/signal.h> #include <linux/rcupdate.h> #include <linux/pid_namespace.h> #include <linux/user_namespace.h> #include <linux/memfd.h> #include <linux/compat.h> #include <linux/mount.h> #include <linux/rw_hint.h> #include <linux/poll.h> #include <asm/siginfo.h> #include <linux/uaccess.h> #include "internal.h" #define SETFL_MASK (O_APPEND | O_NONBLOCK | O_NDELAY | O_DIRECT | O_NOATIME) static int setfl(int fd, struct file * filp, unsigned int arg) { struct inode * inode = file_inode(filp); int error = 0; /* * O_APPEND cannot be cleared if the file is marked as append-only * and the file is open for write. */ if (((arg ^ filp->f_flags) & O_APPEND) && IS_APPEND(inode)) return -EPERM; /* O_NOATIME can only be set by the owner or superuser */ if ((arg & O_NOATIME) && !(filp->f_flags & O_NOATIME)) if (!inode_owner_or_capable(file_mnt_idmap(filp), inode)) return -EPERM; /* required for strict SunOS emulation */ if (O_NONBLOCK != O_NDELAY) if (arg & O_NDELAY) arg |= O_NONBLOCK; /* Pipe packetized mode is controlled by O_DIRECT flag */ if (!S_ISFIFO(inode->i_mode) && (arg & O_DIRECT) && !(filp->f_mode & FMODE_CAN_ODIRECT)) return -EINVAL; if (filp->f_op->check_flags) error = filp->f_op->check_flags(arg); if (error) return error; /* * ->fasync() is responsible for setting the FASYNC bit. */ if (((arg ^ filp->f_flags) & FASYNC) && filp->f_op->fasync) { error = filp->f_op->fasync(fd, filp, (arg & FASYNC) != 0); if (error < 0) goto out; if (error > 0) error = 0; } spin_lock(&filp->f_lock); filp->f_flags = (arg & SETFL_MASK) | (filp->f_flags & ~SETFL_MASK); filp->f_iocb_flags = iocb_flags(filp); spin_unlock(&filp->f_lock); out: return error; } /* * Allocate an file->f_owner struct if it doesn't exist, handling racing * allocations correctly. */ int file_f_owner_allocate(struct file *file) { struct fown_struct *f_owner; f_owner = file_f_owner(file); if (f_owner) return 0; f_owner = kzalloc(sizeof(struct fown_struct), GFP_KERNEL); if (!f_owner) return -ENOMEM; rwlock_init(&f_owner->lock); f_owner->file = file; /* If someone else raced us, drop our allocation. */ if (unlikely(cmpxchg(&file->f_owner, NULL, f_owner))) kfree(f_owner); return 0; } EXPORT_SYMBOL(file_f_owner_allocate); void file_f_owner_release(struct file *file) { struct fown_struct *f_owner; f_owner = file_f_owner(file); if (f_owner) { put_pid(f_owner->pid); kfree(f_owner); } } void __f_setown(struct file *filp, struct pid *pid, enum pid_type type, int force) { struct fown_struct *f_owner; f_owner = file_f_owner(filp); if (WARN_ON_ONCE(!f_owner)) return; write_lock_irq(&f_owner->lock); if (force || !f_owner->pid) { put_pid(f_owner->pid); f_owner->pid = get_pid(pid); f_owner->pid_type = type; if (pid) { const struct cred *cred = current_cred(); security_file_set_fowner(filp); f_owner->uid = cred->uid; f_owner->euid = cred->euid; } } write_unlock_irq(&f_owner->lock); } EXPORT_SYMBOL(__f_setown); int f_setown(struct file *filp, int who, int force) { enum pid_type type; struct pid *pid = NULL; int ret = 0; might_sleep(); type = PIDTYPE_TGID; if (who < 0) { /* avoid overflow below */ if (who == INT_MIN) return -EINVAL; type = PIDTYPE_PGID; who = -who; } ret = file_f_owner_allocate(filp); if (ret) return ret; rcu_read_lock(); if (who) { pid = find_vpid(who); if (!pid) ret = -ESRCH; } if (!ret) __f_setown(filp, pid, type, force); rcu_read_unlock(); return ret; } EXPORT_SYMBOL(f_setown); void f_delown(struct file *filp) { __f_setown(filp, NULL, PIDTYPE_TGID, 1); } pid_t f_getown(struct file *filp) { pid_t pid = 0; struct fown_struct *f_owner; f_owner = file_f_owner(filp); if (!f_owner) return pid; read_lock_irq(&f_owner->lock); rcu_read_lock(); if (pid_task(f_owner->pid, f_owner->pid_type)) { pid = pid_vnr(f_owner->pid); if (f_owner->pid_type == PIDTYPE_PGID) pid = -pid; } rcu_read_unlock(); read_unlock_irq(&f_owner->lock); return pid; } static int f_setown_ex(struct file *filp, unsigned long arg) { struct f_owner_ex __user *owner_p = (void __user *)arg; struct f_owner_ex owner; struct pid *pid; int type; int ret; ret = copy_from_user(&owner, owner_p, sizeof(owner)); if (ret) return -EFAULT; switch (owner.type) { case F_OWNER_TID: type = PIDTYPE_PID; break; case F_OWNER_PID: type = PIDTYPE_TGID; break; case F_OWNER_PGRP: type = PIDTYPE_PGID; break; default: return -EINVAL; } ret = file_f_owner_allocate(filp); if (ret) return ret; rcu_read_lock(); pid = find_vpid(owner.pid); if (owner.pid && !pid) ret = -ESRCH; else __f_setown(filp, pid, type, 1); rcu_read_unlock(); return ret; } static int f_getown_ex(struct file *filp, unsigned long arg) { struct f_owner_ex __user *owner_p = (void __user *)arg; struct f_owner_ex owner = {}; int ret = 0; struct fown_struct *f_owner; enum pid_type pid_type = PIDTYPE_PID; f_owner = file_f_owner(filp); if (f_owner) { read_lock_irq(&f_owner->lock); rcu_read_lock(); if (pid_task(f_owner->pid, f_owner->pid_type)) owner.pid = pid_vnr(f_owner->pid); rcu_read_unlock(); pid_type = f_owner->pid_type; } switch (pid_type) { case PIDTYPE_PID: owner.type = F_OWNER_TID; break; case PIDTYPE_TGID: owner.type = F_OWNER_PID; break; case PIDTYPE_PGID: owner.type = F_OWNER_PGRP; break; default: WARN_ON(1); ret = -EINVAL; break; } if (f_owner) read_unlock_irq(&f_owner->lock); if (!ret) { ret = copy_to_user(owner_p, &owner, sizeof(owner)); if (ret) ret = -EFAULT; } return ret; } #ifdef CONFIG_CHECKPOINT_RESTORE static int f_getowner_uids(struct file *filp, unsigned long arg) { struct user_namespace *user_ns = current_user_ns(); struct fown_struct *f_owner; uid_t __user *dst = (void __user *)arg; uid_t src[2] = {0, 0}; int err; f_owner = file_f_owner(filp); if (f_owner) { read_lock_irq(&f_owner->lock); src[0] = from_kuid(user_ns, f_owner->uid); src[1] = from_kuid(user_ns, f_owner->euid); read_unlock_irq(&f_owner->lock); } err = put_user(src[0], &dst[0]); err |= put_user(src[1], &dst[1]); return err; } #else static int f_getowner_uids(struct file *filp, unsigned long arg) { return -EINVAL; } #endif static bool rw_hint_valid(u64 hint) { BUILD_BUG_ON(WRITE_LIFE_NOT_SET != RWH_WRITE_LIFE_NOT_SET); BUILD_BUG_ON(WRITE_LIFE_NONE != RWH_WRITE_LIFE_NONE); BUILD_BUG_ON(WRITE_LIFE_SHORT != RWH_WRITE_LIFE_SHORT); BUILD_BUG_ON(WRITE_LIFE_MEDIUM != RWH_WRITE_LIFE_MEDIUM); BUILD_BUG_ON(WRITE_LIFE_LONG != RWH_WRITE_LIFE_LONG); BUILD_BUG_ON(WRITE_LIFE_EXTREME != RWH_WRITE_LIFE_EXTREME); switch (hint) { case RWH_WRITE_LIFE_NOT_SET: case RWH_WRITE_LIFE_NONE: case RWH_WRITE_LIFE_SHORT: case RWH_WRITE_LIFE_MEDIUM: case RWH_WRITE_LIFE_LONG: case RWH_WRITE_LIFE_EXTREME: return true; default: return false; } } static long fcntl_get_rw_hint(struct file *file, unsigned int cmd, unsigned long arg) { struct inode *inode = file_inode(file); u64 __user *argp = (u64 __user *)arg; u64 hint = READ_ONCE(inode->i_write_hint); if (copy_to_user(argp, &hint, sizeof(*argp))) return -EFAULT; return 0; } static long fcntl_set_rw_hint(struct file *file, unsigned int cmd, unsigned long arg) { struct inode *inode = file_inode(file); u64 __user *argp = (u64 __user *)arg; u64 hint; if (!inode_owner_or_capable(file_mnt_idmap(file), inode)) return -EPERM; if (copy_from_user(&hint, argp, sizeof(hint))) return -EFAULT; if (!rw_hint_valid(hint)) return -EINVAL; WRITE_ONCE(inode->i_write_hint, hint); /* * file->f_mapping->host may differ from inode. As an example, * blkdev_open() modifies file->f_mapping. */ if (file->f_mapping->host != inode) WRITE_ONCE(file->f_mapping->host->i_write_hint, hint); return 0; } /* Is the file descriptor a dup of the file? */ static long f_dupfd_query(int fd, struct file *filp) { CLASS(fd_raw, f)(fd); if (fd_empty(f)) return -EBADF; /* * We can do the 'fdput()' immediately, as the only thing that * matters is the pointer value which isn't changed by the fdput. * * Technically we didn't need a ref at all, and 'fdget()' was * overkill, but given our lockless file pointer lookup, the * alternatives are complicated. */ return fd_file(f) == filp; } /* Let the caller figure out whether a given file was just created. */ static long f_created_query(const struct file *filp) { return !!(filp->f_mode & FMODE_CREATED); } static int f_owner_sig(struct file *filp, int signum, bool setsig) { int ret = 0; struct fown_struct *f_owner; might_sleep(); if (setsig) { if (!valid_signal(signum)) return -EINVAL; ret = file_f_owner_allocate(filp); if (ret) return ret; } f_owner = file_f_owner(filp); if (setsig) f_owner->signum = signum; else if (f_owner) ret = f_owner->signum; return ret; } static long do_fcntl(int fd, unsigned int cmd, unsigned long arg, struct file *filp) { void __user *argp = (void __user *)arg; int argi = (int)arg; struct flock flock; long err = -EINVAL; switch (cmd) { case F_CREATED_QUERY: err = f_created_query(filp); break; case F_DUPFD: err = f_dupfd(argi, filp, 0); break; case F_DUPFD_CLOEXEC: err = f_dupfd(argi, filp, O_CLOEXEC); break; case F_DUPFD_QUERY: err = f_dupfd_query(argi, filp); break; case F_GETFD: err = get_close_on_exec(fd) ? FD_CLOEXEC : 0; break; case F_SETFD: err = 0; set_close_on_exec(fd, argi & FD_CLOEXEC); break; case F_GETFL: err = filp->f_flags; break; case F_SETFL: err = setfl(fd, filp, argi); break; #if BITS_PER_LONG != 32 /* 32-bit arches must use fcntl64() */ case F_OFD_GETLK: #endif case F_GETLK: if (copy_from_user(&flock, argp, sizeof(flock))) return -EFAULT; err = fcntl_getlk(filp, cmd, &flock); if (!err && copy_to_user(argp, &flock, sizeof(flock))) return -EFAULT; break; #if BITS_PER_LONG != 32 /* 32-bit arches must use fcntl64() */ case F_OFD_SETLK: case F_OFD_SETLKW: fallthrough; #endif case F_SETLK: case F_SETLKW: if (copy_from_user(&flock, argp, sizeof(flock))) return -EFAULT; err = fcntl_setlk(fd, filp, cmd, &flock); break; case F_GETOWN: /* * XXX If f_owner is a process group, the * negative return value will get converted * into an error. Oops. If we keep the * current syscall conventions, the only way * to fix this will be in libc. */ err = f_getown(filp); force_successful_syscall_return(); break; case F_SETOWN: err = f_setown(filp, argi, 1); break; case F_GETOWN_EX: err = f_getown_ex(filp, arg); break; case F_SETOWN_EX: err = f_setown_ex(filp, arg); break; case F_GETOWNER_UIDS: err = f_getowner_uids(filp, arg); break; case F_GETSIG: err = f_owner_sig(filp, 0, false); break; case F_SETSIG: err = f_owner_sig(filp, argi, true); break; case F_GETLEASE: err = fcntl_getlease(filp); break; case F_SETLEASE: err = fcntl_setlease(fd, filp, argi); break; case F_NOTIFY: err = fcntl_dirnotify(fd, filp, argi); break; case F_SETPIPE_SZ: case F_GETPIPE_SZ: err = pipe_fcntl(filp, cmd, argi); break; case F_ADD_SEALS: case F_GET_SEALS: err = memfd_fcntl(filp, cmd, argi); break; case F_GET_RW_HINT: err = fcntl_get_rw_hint(filp, cmd, arg); break; case F_SET_RW_HINT: err = fcntl_set_rw_hint(filp, cmd, arg); break; default: break; } return err; } static int check_fcntl_cmd(unsigned cmd) { switch (cmd) { case F_CREATED_QUERY: case F_DUPFD: case F_DUPFD_CLOEXEC: case F_DUPFD_QUERY: case F_GETFD: case F_SETFD: case F_GETFL: return 1; } return 0; } SYSCALL_DEFINE3(fcntl, unsigned int, fd, unsigned int, cmd, unsigned long, arg) { CLASS(fd_raw, f)(fd); long err; if (fd_empty(f)) return -EBADF; if (unlikely(fd_file(f)->f_mode & FMODE_PATH)) { if (!check_fcntl_cmd(cmd)) return -EBADF; } err = security_file_fcntl(fd_file(f), cmd, arg); if (!err) err = do_fcntl(fd, cmd, arg, fd_file(f)); return err; } #if BITS_PER_LONG == 32 SYSCALL_DEFINE3(fcntl64, unsigned int, fd, unsigned int, cmd, unsigned long, arg) { void __user *argp = (void __user *)arg; CLASS(fd_raw, f)(fd); struct flock64 flock; long err; if (fd_empty(f)) return -EBADF; if (unlikely(fd_file(f)->f_mode & FMODE_PATH)) { if (!check_fcntl_cmd(cmd)) return -EBADF; } err = security_file_fcntl(fd_file(f), cmd, arg); if (err) return err; switch (cmd) { case F_GETLK64: case F_OFD_GETLK: err = -EFAULT; if (copy_from_user(&flock, argp, sizeof(flock))) break; err = fcntl_getlk64(fd_file(f), cmd, &flock); if (!err && copy_to_user(argp, &flock, sizeof(flock))) err = -EFAULT; break; case F_SETLK64: case F_SETLKW64: case F_OFD_SETLK: case F_OFD_SETLKW: err = -EFAULT; if (copy_from_user(&flock, argp, sizeof(flock))) break; err = fcntl_setlk64(fd, fd_file(f), cmd, &flock); break; default: err = do_fcntl(fd, cmd, arg, fd_file(f)); break; } return err; } #endif #ifdef CONFIG_COMPAT /* careful - don't use anywhere else */ #define copy_flock_fields(dst, src) \ (dst)->l_type = (src)->l_type; \ (dst)->l_whence = (src)->l_whence; \ (dst)->l_start = (src)->l_start; \ (dst)->l_len = (src)->l_len; \ (dst)->l_pid = (src)->l_pid; static int get_compat_flock(struct flock *kfl, const struct compat_flock __user *ufl) { struct compat_flock fl; if (copy_from_user(&fl, ufl, sizeof(struct compat_flock))) return -EFAULT; copy_flock_fields(kfl, &fl); return 0; } static int get_compat_flock64(struct flock *kfl, const struct compat_flock64 __user *ufl) { struct compat_flock64 fl; if (copy_from_user(&fl, ufl, sizeof(struct compat_flock64))) return -EFAULT; copy_flock_fields(kfl, &fl); return 0; } static int put_compat_flock(const struct flock *kfl, struct compat_flock __user *ufl) { struct compat_flock fl; memset(&fl, 0, sizeof(struct compat_flock)); copy_flock_fields(&fl, kfl); if (copy_to_user(ufl, &fl, sizeof(struct compat_flock))) return -EFAULT; return 0; } static int put_compat_flock64(const struct flock *kfl, struct compat_flock64 __user *ufl) { struct compat_flock64 fl; BUILD_BUG_ON(sizeof(kfl->l_start) > sizeof(ufl->l_start)); BUILD_BUG_ON(sizeof(kfl->l_len) > sizeof(ufl->l_len)); memset(&fl, 0, sizeof(struct compat_flock64)); copy_flock_fields(&fl, kfl); if (copy_to_user(ufl, &fl, sizeof(struct compat_flock64))) return -EFAULT; return 0; } #undef copy_flock_fields static unsigned int convert_fcntl_cmd(unsigned int cmd) { switch (cmd) { case F_GETLK64: return F_GETLK; case F_SETLK64: return F_SETLK; case F_SETLKW64: return F_SETLKW; } return cmd; } /* * GETLK was successful and we need to return the data, but it needs to fit in * the compat structure. * l_start shouldn't be too big, unless the original start + end is greater than * COMPAT_OFF_T_MAX, in which case the app was asking for trouble, so we return * -EOVERFLOW in that case. l_len could be too big, in which case we just * truncate it, and only allow the app to see that part of the conflicting lock * that might make sense to it anyway */ static int fixup_compat_flock(struct flock *flock) { if (flock->l_start > COMPAT_OFF_T_MAX) return -EOVERFLOW; if (flock->l_len > COMPAT_OFF_T_MAX) flock->l_len = COMPAT_OFF_T_MAX; return 0; } static long do_compat_fcntl64(unsigned int fd, unsigned int cmd, compat_ulong_t arg) { CLASS(fd_raw, f)(fd); struct flock flock; long err; if (fd_empty(f)) return -EBADF; if (unlikely(fd_file(f)->f_mode & FMODE_PATH)) { if (!check_fcntl_cmd(cmd)) return -EBADF; } err = security_file_fcntl(fd_file(f), cmd, arg); if (err) return err; switch (cmd) { case F_GETLK: err = get_compat_flock(&flock, compat_ptr(arg)); if (err) break; err = fcntl_getlk(fd_file(f), convert_fcntl_cmd(cmd), &flock); if (err) break; err = fixup_compat_flock(&flock); if (!err) err = put_compat_flock(&flock, compat_ptr(arg)); break; case F_GETLK64: case F_OFD_GETLK: err = get_compat_flock64(&flock, compat_ptr(arg)); if (err) break; err = fcntl_getlk(fd_file(f), convert_fcntl_cmd(cmd), &flock); if (!err) err = put_compat_flock64(&flock, compat_ptr(arg)); break; case F_SETLK: case F_SETLKW: err = get_compat_flock(&flock, compat_ptr(arg)); if (err) break; err = fcntl_setlk(fd, fd_file(f), convert_fcntl_cmd(cmd), &flock); break; case F_SETLK64: case F_SETLKW64: case F_OFD_SETLK: case F_OFD_SETLKW: err = get_compat_flock64(&flock, compat_ptr(arg)); if (err) break; err = fcntl_setlk(fd, fd_file(f), convert_fcntl_cmd(cmd), &flock); break; default: err = do_fcntl(fd, cmd, arg, fd_file(f)); break; } return err; } COMPAT_SYSCALL_DEFINE3(fcntl64, unsigned int, fd, unsigned int, cmd, compat_ulong_t, arg) { return do_compat_fcntl64(fd, cmd, arg); } COMPAT_SYSCALL_DEFINE3(fcntl, unsigned int, fd, unsigned int, cmd, compat_ulong_t, arg) { switch (cmd) { case F_GETLK64: case F_SETLK64: case F_SETLKW64: case F_OFD_GETLK: case F_OFD_SETLK: case F_OFD_SETLKW: return -EINVAL; } return do_compat_fcntl64(fd, cmd, arg); } #endif /* Table to convert sigio signal codes into poll band bitmaps */ static const __poll_t band_table[NSIGPOLL] = { EPOLLIN | EPOLLRDNORM, /* POLL_IN */ EPOLLOUT | EPOLLWRNORM | EPOLLWRBAND, /* POLL_OUT */ EPOLLIN | EPOLLRDNORM | EPOLLMSG, /* POLL_MSG */ EPOLLERR, /* POLL_ERR */ EPOLLPRI | EPOLLRDBAND, /* POLL_PRI */ EPOLLHUP | EPOLLERR /* POLL_HUP */ }; static inline int sigio_perm(struct task_struct *p, struct fown_struct *fown, int sig) { const struct cred *cred; int ret; rcu_read_lock(); cred = __task_cred(p); ret = ((uid_eq(fown->euid, GLOBAL_ROOT_UID) || uid_eq(fown->euid, cred->suid) || uid_eq(fown->euid, cred->uid) || uid_eq(fown->uid, cred->suid) || uid_eq(fown->uid, cred->uid)) && !security_file_send_sigiotask(p, fown, sig)); rcu_read_unlock(); return ret; } static void send_sigio_to_task(struct task_struct *p, struct fown_struct *fown, int fd, int reason, enum pid_type type) { /* * F_SETSIG can change ->signum lockless in parallel, make * sure we read it once and use the same value throughout. */ int signum = READ_ONCE(fown->signum); if (!sigio_perm(p, fown, signum)) return; switch (signum) { default: { kernel_siginfo_t si; /* Queue a rt signal with the appropriate fd as its value. We use SI_SIGIO as the source, not SI_KERNEL, since kernel signals always get delivered even if we can't queue. Failure to queue in this case _should_ be reported; we fall back to SIGIO in that case. --sct */ clear_siginfo(&si); si.si_signo = signum; si.si_errno = 0; si.si_code = reason; /* * Posix definies POLL_IN and friends to be signal * specific si_codes for SIG_POLL. Linux extended * these si_codes to other signals in a way that is * ambiguous if other signals also have signal * specific si_codes. In that case use SI_SIGIO instead * to remove the ambiguity. */ if ((signum != SIGPOLL) && sig_specific_sicodes(signum)) si.si_code = SI_SIGIO; /* Make sure we are called with one of the POLL_* reasons, otherwise we could leak kernel stack into userspace. */ BUG_ON((reason < POLL_IN) || ((reason - POLL_IN) >= NSIGPOLL)); if (reason - POLL_IN >= NSIGPOLL) si.si_band = ~0L; else si.si_band = mangle_poll(band_table[reason - POLL_IN]); si.si_fd = fd; if (!do_send_sig_info(signum, &si, p, type)) break; } fallthrough; /* fall back on the old plain SIGIO signal */ case 0: do_send_sig_info(SIGIO, SEND_SIG_PRIV, p, type); } } void send_sigio(struct fown_struct *fown, int fd, int band) { struct task_struct *p; enum pid_type type; unsigned long flags; struct pid *pid; read_lock_irqsave(&fown->lock, flags); type = fown->pid_type; pid = fown->pid; if (!pid) goto out_unlock_fown; if (type <= PIDTYPE_TGID) { rcu_read_lock(); p = pid_task(pid, PIDTYPE_PID); if (p) send_sigio_to_task(p, fown, fd, band, type); rcu_read_unlock(); } else { read_lock(&tasklist_lock); do_each_pid_task(pid, type, p) { send_sigio_to_task(p, fown, fd, band, type); } while_each_pid_task(pid, type, p); read_unlock(&tasklist_lock); } out_unlock_fown: read_unlock_irqrestore(&fown->lock, flags); } static void send_sigurg_to_task(struct task_struct *p, struct fown_struct *fown, enum pid_type type) { if (sigio_perm(p, fown, SIGURG)) do_send_sig_info(SIGURG, SEND_SIG_PRIV, p, type); } int send_sigurg(struct file *file) { struct fown_struct *fown; struct task_struct *p; enum pid_type type; struct pid *pid; unsigned long flags; int ret = 0; fown = file_f_owner(file); if (!fown) return 0; read_lock_irqsave(&fown->lock, flags); type = fown->pid_type; pid = fown->pid; if (!pid) goto out_unlock_fown; ret = 1; if (type <= PIDTYPE_TGID) { rcu_read_lock(); p = pid_task(pid, PIDTYPE_PID); if (p) send_sigurg_to_task(p, fown, type); rcu_read_unlock(); } else { read_lock(&tasklist_lock); do_each_pid_task(pid, type, p) { send_sigurg_to_task(p, fown, type); } while_each_pid_task(pid, type, p); read_unlock(&tasklist_lock); } out_unlock_fown: read_unlock_irqrestore(&fown->lock, flags); return ret; } static DEFINE_SPINLOCK(fasync_lock); static struct kmem_cache *fasync_cache __ro_after_init; /* * Remove a fasync entry. If successfully removed, return * positive and clear the FASYNC flag. If no entry exists, * do nothing and return 0. * * NOTE! It is very important that the FASYNC flag always * match the state "is the filp on a fasync list". * */ int fasync_remove_entry(struct file *filp, struct fasync_struct **fapp) { struct fasync_struct *fa, **fp; int result = 0; spin_lock(&filp->f_lock); spin_lock(&fasync_lock); for (fp = fapp; (fa = *fp) != NULL; fp = &fa->fa_next) { if (fa->fa_file != filp) continue; write_lock_irq(&fa->fa_lock); fa->fa_file = NULL; write_unlock_irq(&fa->fa_lock); *fp = fa->fa_next; kfree_rcu(fa, fa_rcu); filp->f_flags &= ~FASYNC; result = 1; break; } spin_unlock(&fasync_lock); spin_unlock(&filp->f_lock); return result; } struct fasync_struct *fasync_alloc(void) { return kmem_cache_alloc(fasync_cache, GFP_KERNEL); } /* * NOTE! This can be used only for unused fasync entries: * entries that actually got inserted on the fasync list * need to be released by rcu - see fasync_remove_entry. */ void fasync_free(struct fasync_struct *new) { kmem_cache_free(fasync_cache, new); } /* * Insert a new entry into the fasync list. Return the pointer to the * old one if we didn't use the new one. * * NOTE! It is very important that the FASYNC flag always * match the state "is the filp on a fasync list". */ struct fasync_struct *fasync_insert_entry(int fd, struct file *filp, struct fasync_struct **fapp, struct fasync_struct *new) { struct fasync_struct *fa, **fp; spin_lock(&filp->f_lock); spin_lock(&fasync_lock); for (fp = fapp; (fa = *fp) != NULL; fp = &fa->fa_next) { if (fa->fa_file != filp) continue; write_lock_irq(&fa->fa_lock); fa->fa_fd = fd; write_unlock_irq(&fa->fa_lock); goto out; } rwlock_init(&new->fa_lock); new->magic = FASYNC_MAGIC; new->fa_file = filp; new->fa_fd = fd; new->fa_next = *fapp; rcu_assign_pointer(*fapp, new); filp->f_flags |= FASYNC; out: spin_unlock(&fasync_lock); spin_unlock(&filp->f_lock); return fa; } /* * Add a fasync entry. Return negative on error, positive if * added, and zero if did nothing but change an existing one. */ static int fasync_add_entry(int fd, struct file *filp, struct fasync_struct **fapp) { struct fasync_struct *new; new = fasync_alloc(); if (!new) return -ENOMEM; /* * fasync_insert_entry() returns the old (update) entry if * it existed. * * So free the (unused) new entry and return 0 to let the * caller know that we didn't add any new fasync entries. */ if (fasync_insert_entry(fd, filp, fapp, new)) { fasync_free(new); return 0; } return 1; } /* * fasync_helper() is used by almost all character device drivers * to set up the fasync queue, and for regular files by the file * lease code. It returns negative on error, 0 if it did no changes * and positive if it added/deleted the entry. */ int fasync_helper(int fd, struct file * filp, int on, struct fasync_struct **fapp) { if (!on) return fasync_remove_entry(filp, fapp); return fasync_add_entry(fd, filp, fapp); } EXPORT_SYMBOL(fasync_helper); /* * rcu_read_lock() is held */ static void kill_fasync_rcu(struct fasync_struct *fa, int sig, int band) { while (fa) { struct fown_struct *fown; unsigned long flags; if (fa->magic != FASYNC_MAGIC) { printk(KERN_ERR "kill_fasync: bad magic number in " "fasync_struct!\n"); return; } read_lock_irqsave(&fa->fa_lock, flags); if (fa->fa_file) { fown = file_f_owner(fa->fa_file); if (!fown) goto next; /* Don't send SIGURG to processes which have not set a queued signum: SIGURG has its own default signalling mechanism. */ if (!(sig == SIGURG && fown->signum == 0)) send_sigio(fown, fa->fa_fd, band); } next: read_unlock_irqrestore(&fa->fa_lock, flags); fa = rcu_dereference(fa->fa_next); } } void kill_fasync(struct fasync_struct **fp, int sig, int band) { /* First a quick test without locking: usually * the list is empty. */ if (*fp) { rcu_read_lock(); kill_fasync_rcu(rcu_dereference(*fp), sig, band); rcu_read_unlock(); } } EXPORT_SYMBOL(kill_fasync); static int __init fcntl_init(void) { /* * Please add new bits here to ensure allocation uniqueness. * Exceptions: O_NONBLOCK is a two bit define on parisc; O_NDELAY * is defined as O_NONBLOCK on some platforms and not on others. */ BUILD_BUG_ON(21 - 1 /* for O_RDONLY being 0 */ != HWEIGHT32( (VALID_OPEN_FLAGS & ~(O_NONBLOCK | O_NDELAY)) | __FMODE_EXEC | __FMODE_NONOTIFY)); fasync_cache = kmem_cache_create("fasync_cache", sizeof(struct fasync_struct), 0, SLAB_PANIC | SLAB_ACCOUNT, NULL); return 0; } module_init(fcntl_init) |
| 1204 1202 1202 1198 1200 1206 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 | // SPDX-License-Identifier: GPL-2.0 #include <linux/compiler.h> #include <linux/context_tracking.h> #include <linux/errno.h> #include <linux/nospec.h> #include <linux/ptrace.h> #include <linux/randomize_kstack.h> #include <linux/syscalls.h> #include <asm/debug-monitors.h> #include <asm/exception.h> #include <asm/fpsimd.h> #include <asm/syscall.h> #include <asm/thread_info.h> #include <asm/unistd.h> #include <asm/unistd_compat_32.h> long compat_arm_syscall(struct pt_regs *regs, int scno); long sys_ni_syscall(void); static long do_ni_syscall(struct pt_regs *regs, int scno) { if (is_compat_task()) { long ret = compat_arm_syscall(regs, scno); if (ret != -ENOSYS) return ret; } return sys_ni_syscall(); } static long __invoke_syscall(struct pt_regs *regs, syscall_fn_t syscall_fn) { return syscall_fn(regs); } static void invoke_syscall(struct pt_regs *regs, unsigned int scno, unsigned int sc_nr, const syscall_fn_t syscall_table[]) { long ret; add_random_kstack_offset(); if (scno < sc_nr) { syscall_fn_t syscall_fn; syscall_fn = syscall_table[array_index_nospec(scno, sc_nr)]; ret = __invoke_syscall(regs, syscall_fn); } else { ret = do_ni_syscall(regs, scno); } syscall_set_return_value(current, regs, 0, ret); /* * This value will get limited by KSTACK_OFFSET_MAX(), which is 10 * bits. The actual entropy will be further reduced by the compiler * when applying stack alignment constraints: the AAPCS mandates a * 16-byte aligned SP at function boundaries, which will remove the * 4 low bits from any entropy chosen here. * * The resulting 6 bits of entropy is seen in SP[9:4]. */ choose_random_kstack_offset(get_random_u16()); } static inline bool has_syscall_work(unsigned long flags) { return unlikely(flags & _TIF_SYSCALL_WORK); } static void el0_svc_common(struct pt_regs *regs, int scno, int sc_nr, const syscall_fn_t syscall_table[]) { unsigned long flags = read_thread_flags(); regs->orig_x0 = regs->regs[0]; regs->syscallno = scno; /* * BTI note: * The architecture does not guarantee that SPSR.BTYPE is zero * on taking an SVC, so we could return to userspace with a * non-zero BTYPE after the syscall. * * This shouldn't matter except when userspace is explicitly * doing something stupid, such as setting PROT_BTI on a page * that lacks conforming BTI/PACIxSP instructions, falling * through from one executable page to another with differing * PROT_BTI, or messing with BTYPE via ptrace: in such cases, * userspace should not be surprised if a SIGILL occurs on * syscall return. * * So, don't touch regs->pstate & PSR_BTYPE_MASK here. * (Similarly for HVC and SMC elsewhere.) */ if (flags & _TIF_MTE_ASYNC_FAULT) { /* * Process the asynchronous tag check fault before the actual * syscall. do_notify_resume() will send a signal to userspace * before the syscall is restarted. */ syscall_set_return_value(current, regs, -ERESTARTNOINTR, 0); return; } if (has_syscall_work(flags)) { /* * The de-facto standard way to skip a system call using ptrace * is to set the system call to -1 (NO_SYSCALL) and set x0 to a * suitable error code for consumption by userspace. However, * this cannot be distinguished from a user-issued syscall(-1) * and so we must set x0 to -ENOSYS here in case the tracer doesn't * issue the skip and we fall into trace_exit with x0 preserved. * * This is slightly odd because it also means that if a tracer * sets the system call number to -1 but does not initialise x0, * then x0 will be preserved for all system calls apart from a * user-issued syscall(-1). However, requesting a skip and not * setting the return value is unlikely to do anything sensible * anyway. */ if (scno == NO_SYSCALL) syscall_set_return_value(current, regs, -ENOSYS, 0); scno = syscall_trace_enter(regs); if (scno == NO_SYSCALL) goto trace_exit; } invoke_syscall(regs, scno, sc_nr, syscall_table); /* * The tracing status may have changed under our feet, so we have to * check again. However, if we were tracing entry, then we always trace * exit regardless, as the old entry assembly did. */ if (!has_syscall_work(flags) && !IS_ENABLED(CONFIG_DEBUG_RSEQ)) { flags = read_thread_flags(); if (!has_syscall_work(flags) && !(flags & _TIF_SINGLESTEP)) return; } trace_exit: syscall_trace_exit(regs); } void do_el0_svc(struct pt_regs *regs) { el0_svc_common(regs, regs->regs[8], __NR_syscalls, sys_call_table); } #ifdef CONFIG_COMPAT void do_el0_svc_compat(struct pt_regs *regs) { el0_svc_common(regs, regs->regs[7], __NR_compat32_syscalls, compat_sys_call_table); } #endif |
| 179 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 | // SPDX-License-Identifier: GPL-2.0-only /* * mm/readahead.c - address_space-level file readahead. * * Copyright (C) 2002, Linus Torvalds * * 09Apr2002 Andrew Morton * Initial version. */ /** * DOC: Readahead Overview * * Readahead is used to read content into the page cache before it is * explicitly requested by the application. Readahead only ever * attempts to read folios that are not yet in the page cache. If a * folio is present but not up-to-date, readahead will not try to read * it. In that case a simple ->read_folio() will be requested. * * Readahead is triggered when an application read request (whether a * system call or a page fault) finds that the requested folio is not in * the page cache, or that it is in the page cache and has the * readahead flag set. This flag indicates that the folio was read * as part of a previous readahead request and now that it has been * accessed, it is time for the next readahead. * * Each readahead request is partly synchronous read, and partly async * readahead. This is reflected in the struct file_ra_state which * contains ->size being the total number of pages, and ->async_size * which is the number of pages in the async section. The readahead * flag will be set on the first folio in this async section to trigger * a subsequent readahead. Once a series of sequential reads has been * established, there should be no need for a synchronous component and * all readahead request will be fully asynchronous. * * When either of the triggers causes a readahead, three numbers need * to be determined: the start of the region to read, the size of the * region, and the size of the async tail. * * The start of the region is simply the first page address at or after * the accessed address, which is not currently populated in the page * cache. This is found with a simple search in the page cache. * * The size of the async tail is determined by subtracting the size that * was explicitly requested from the determined request size, unless * this would be less than zero - then zero is used. NOTE THIS * CALCULATION IS WRONG WHEN THE START OF THE REGION IS NOT THE ACCESSED * PAGE. ALSO THIS CALCULATION IS NOT USED CONSISTENTLY. * * The size of the region is normally determined from the size of the * previous readahead which loaded the preceding pages. This may be * discovered from the struct file_ra_state for simple sequential reads, * or from examining the state of the page cache when multiple * sequential reads are interleaved. Specifically: where the readahead * was triggered by the readahead flag, the size of the previous * readahead is assumed to be the number of pages from the triggering * page to the start of the new readahead. In these cases, the size of * the previous readahead is scaled, often doubled, for the new * readahead, though see get_next_ra_size() for details. * * If the size of the previous read cannot be determined, the number of * preceding pages in the page cache is used to estimate the size of * a previous read. This estimate could easily be misled by random * reads being coincidentally adjacent, so it is ignored unless it is * larger than the current request, and it is not scaled up, unless it * is at the start of file. * * In general readahead is accelerated at the start of the file, as * reads from there are often sequential. There are other minor * adjustments to the readahead size in various special cases and these * are best discovered by reading the code. * * The above calculation, based on the previous readahead size, * determines the size of the readahead, to which any requested read * size may be added. * * Readahead requests are sent to the filesystem using the ->readahead() * address space operation, for which mpage_readahead() is a canonical * implementation. ->readahead() should normally initiate reads on all * folios, but may fail to read any or all folios without causing an I/O * error. The page cache reading code will issue a ->read_folio() request * for any folio which ->readahead() did not read, and only an error * from this will be final. * * ->readahead() will generally call readahead_folio() repeatedly to get * each folio from those prepared for readahead. It may fail to read a * folio by: * * * not calling readahead_folio() sufficiently many times, effectively * ignoring some folios, as might be appropriate if the path to * storage is congested. * * * failing to actually submit a read request for a given folio, * possibly due to insufficient resources, or * * * getting an error during subsequent processing of a request. * * In the last two cases, the folio should be unlocked by the filesystem * to indicate that the read attempt has failed. In the first case the * folio will be unlocked by the VFS. * * Those folios not in the final ``async_size`` of the request should be * considered to be important and ->readahead() should not fail them due * to congestion or temporary resource unavailability, but should wait * for necessary resources (e.g. memory or indexing information) to * become available. Folios in the final ``async_size`` may be * considered less urgent and failure to read them is more acceptable. * In this case it is best to use filemap_remove_folio() to remove the * folios from the page cache as is automatically done for folios that * were not fetched with readahead_folio(). This will allow a * subsequent synchronous readahead request to try them again. If they * are left in the page cache, then they will be read individually using * ->read_folio() which may be less efficient. */ #include <linux/blkdev.h> #include <linux/kernel.h> #include <linux/dax.h> #include <linux/gfp.h> #include <linux/export.h> #include <linux/backing-dev.h> #include <linux/task_io_accounting_ops.h> #include <linux/pagemap.h> #include <linux/psi.h> #include <linux/syscalls.h> #include <linux/file.h> #include <linux/mm_inline.h> #include <linux/blk-cgroup.h> #include <linux/fadvise.h> #include <linux/sched/mm.h> #include "internal.h" /* * Initialise a struct file's readahead state. Assumes that the caller has * memset *ra to zero. */ void file_ra_state_init(struct file_ra_state *ra, struct address_space *mapping) { ra->ra_pages = inode_to_bdi(mapping->host)->ra_pages; ra->prev_pos = -1; } EXPORT_SYMBOL_GPL(file_ra_state_init); static void read_pages(struct readahead_control *rac) { const struct address_space_operations *aops = rac->mapping->a_ops; struct folio *folio; struct blk_plug plug; if (!readahead_count(rac)) return; if (unlikely(rac->_workingset)) psi_memstall_enter(&rac->_pflags); blk_start_plug(&plug); if (aops->readahead) { aops->readahead(rac); /* * Clean up the remaining folios. The sizes in ->ra * may be used to size the next readahead, so make sure * they accurately reflect what happened. */ while ((folio = readahead_folio(rac)) != NULL) { unsigned long nr = folio_nr_pages(folio); folio_get(folio); rac->ra->size -= nr; if (rac->ra->async_size >= nr) { rac->ra->async_size -= nr; filemap_remove_folio(folio); } folio_unlock(folio); folio_put(folio); } } else { while ((folio = readahead_folio(rac)) != NULL) aops->read_folio(rac->file, folio); } blk_finish_plug(&plug); if (unlikely(rac->_workingset)) psi_memstall_leave(&rac->_pflags); rac->_workingset = false; BUG_ON(readahead_count(rac)); } /** * page_cache_ra_unbounded - Start unchecked readahead. * @ractl: Readahead control. * @nr_to_read: The number of pages to read. * @lookahead_size: Where to start the next readahead. * * This function is for filesystems to call when they want to start * readahead beyond a file's stated i_size. This is almost certainly * not the function you want to call. Use page_cache_async_readahead() * or page_cache_sync_readahead() instead. * * Context: File is referenced by caller. Mutexes may be held by caller. * May sleep, but will not reenter filesystem to reclaim memory. */ void page_cache_ra_unbounded(struct readahead_control *ractl, unsigned long nr_to_read, unsigned long lookahead_size) { struct address_space *mapping = ractl->mapping; unsigned long index = readahead_index(ractl); gfp_t gfp_mask = readahead_gfp_mask(mapping); unsigned long mark = ULONG_MAX, i = 0; unsigned int min_nrpages = mapping_min_folio_nrpages(mapping); /* * Partway through the readahead operation, we will have added * locked pages to the page cache, but will not yet have submitted * them for I/O. Adding another page may need to allocate memory, * which can trigger memory reclaim. Telling the VM we're in * the middle of a filesystem operation will cause it to not * touch file-backed pages, preventing a deadlock. Most (all?) * filesystems already specify __GFP_NOFS in their mapping's * gfp_mask, but let's be explicit here. */ unsigned int nofs = memalloc_nofs_save(); filemap_invalidate_lock_shared(mapping); index = mapping_align_index(mapping, index); /* * As iterator `i` is aligned to min_nrpages, round_up the * difference between nr_to_read and lookahead_size to mark the * index that only has lookahead or "async_region" to set the * readahead flag. */ if (lookahead_size <= nr_to_read) { unsigned long ra_folio_index; ra_folio_index = round_up(readahead_index(ractl) + nr_to_read - lookahead_size, min_nrpages); mark = ra_folio_index - index; } nr_to_read += readahead_index(ractl) - index; ractl->_index = index; /* * Preallocate as many pages as we will need. */ while (i < nr_to_read) { struct folio *folio = xa_load(&mapping->i_pages, index + i); int ret; if (folio && !xa_is_value(folio)) { /* * Page already present? Kick off the current batch * of contiguous pages before continuing with the * next batch. This page may be the one we would * have intended to mark as Readahead, but we don't * have a stable reference to this page, and it's * not worth getting one just for that. */ read_pages(ractl); ractl->_index += min_nrpages; i = ractl->_index + ractl->_nr_pages - index; continue; } folio = filemap_alloc_folio(gfp_mask, mapping_min_folio_order(mapping)); if (!folio) break; ret = filemap_add_folio(mapping, folio, index + i, gfp_mask); if (ret < 0) { folio_put(folio); if (ret == -ENOMEM) break; read_pages(ractl); ractl->_index += min_nrpages; i = ractl->_index + ractl->_nr_pages - index; continue; } if (i == mark) folio_set_readahead(folio); ractl->_workingset |= folio_test_workingset(folio); ractl->_nr_pages += min_nrpages; i += min_nrpages; } /* * Now start the IO. We ignore I/O errors - if the folio is not * uptodate then the caller will launch read_folio again, and * will then handle the error. */ read_pages(ractl); filemap_invalidate_unlock_shared(mapping); memalloc_nofs_restore(nofs); } EXPORT_SYMBOL_GPL(page_cache_ra_unbounded); /* * do_page_cache_ra() actually reads a chunk of disk. It allocates * the pages first, then submits them for I/O. This avoids the very bad * behaviour which would occur if page allocations are causing VM writeback. * We really don't want to intermingle reads and writes like that. */ static void do_page_cache_ra(struct readahead_control *ractl, unsigned long nr_to_read, unsigned long lookahead_size) { struct inode *inode = ractl->mapping->host; unsigned long index = readahead_index(ractl); loff_t isize = i_size_read(inode); pgoff_t end_index; /* The last page we want to read */ if (isize == 0) return; end_index = (isize - 1) >> PAGE_SHIFT; if (index > end_index) return; /* Don't read past the page containing the last byte of the file */ if (nr_to_read > end_index - index) nr_to_read = end_index - index + 1; page_cache_ra_unbounded(ractl, nr_to_read, lookahead_size); } /* * Chunk the readahead into 2 megabyte units, so that we don't pin too much * memory at once. */ void force_page_cache_ra(struct readahead_control *ractl, unsigned long nr_to_read) { struct address_space *mapping = ractl->mapping; struct file_ra_state *ra = ractl->ra; struct backing_dev_info *bdi = inode_to_bdi(mapping->host); unsigned long max_pages; if (unlikely(!mapping->a_ops->read_folio && !mapping->a_ops->readahead)) return; /* * If the request exceeds the readahead window, allow the read to * be up to the optimal hardware IO size */ max_pages = max_t(unsigned long, bdi->io_pages, ra->ra_pages); nr_to_read = min_t(unsigned long, nr_to_read, max_pages); while (nr_to_read) { unsigned long this_chunk = (2 * 1024 * 1024) / PAGE_SIZE; if (this_chunk > nr_to_read) this_chunk = nr_to_read; do_page_cache_ra(ractl, this_chunk, 0); nr_to_read -= this_chunk; } } /* * Set the initial window size, round to next power of 2 and square * for small size, x 4 for medium, and x 2 for large * for 128k (32 page) max ra * 1-2 page = 16k, 3-4 page 32k, 5-8 page = 64k, > 8 page = 128k initial */ static unsigned long get_init_ra_size(unsigned long size, unsigned long max) { unsigned long newsize = roundup_pow_of_two(size); if (newsize <= max / 32) newsize = newsize * 4; else if (newsize <= max / 4) newsize = newsize * 2; else newsize = max; return newsize; } /* * Get the previous window size, ramp it up, and * return it as the new window size. */ static unsigned long get_next_ra_size(struct file_ra_state *ra, unsigned long max) { unsigned long cur = ra->size; if (cur < max / 16) return 4 * cur; if (cur <= max / 2) return 2 * cur; return max; } /* * On-demand readahead design. * * The fields in struct file_ra_state represent the most-recently-executed * readahead attempt: * * |<----- async_size ---------| * |------------------- size -------------------->| * |==================#===========================| * ^start ^page marked with PG_readahead * * To overlap application thinking time and disk I/O time, we do * `readahead pipelining': Do not wait until the application consumed all * readahead pages and stalled on the missing page at readahead_index; * Instead, submit an asynchronous readahead I/O as soon as there are * only async_size pages left in the readahead window. Normally async_size * will be equal to size, for maximum pipelining. * * In interleaved sequential reads, concurrent streams on the same fd can * be invalidating each other's readahead state. So we flag the new readahead * page at (start+size-async_size) with PG_readahead, and use it as readahead * indicator. The flag won't be set on already cached pages, to avoid the * readahead-for-nothing fuss, saving pointless page cache lookups. * * prev_pos tracks the last visited byte in the _previous_ read request. * It should be maintained by the caller, and will be used for detecting * small random reads. Note that the readahead algorithm checks loosely * for sequential patterns. Hence interleaved reads might be served as * sequential ones. * * There is a special-case: if the first page which the application tries to * read happens to be the first page of the file, it is assumed that a linear * read is about to happen and the window is immediately set to the initial size * based on I/O request size and the max_readahead. * * The code ramps up the readahead size aggressively at first, but slow down as * it approaches max_readhead. */ static inline int ra_alloc_folio(struct readahead_control *ractl, pgoff_t index, pgoff_t mark, unsigned int order, gfp_t gfp) { int err; struct folio *folio = filemap_alloc_folio(gfp, order); if (!folio) return -ENOMEM; mark = round_down(mark, 1UL << order); if (index == mark) folio_set_readahead(folio); err = filemap_add_folio(ractl->mapping, folio, index, gfp); if (err) { folio_put(folio); return err; } ractl->_nr_pages += 1UL << order; ractl->_workingset |= folio_test_workingset(folio); return 0; } void page_cache_ra_order(struct readahead_control *ractl, struct file_ra_state *ra, unsigned int new_order) { struct address_space *mapping = ractl->mapping; pgoff_t index = readahead_index(ractl); unsigned int min_order = mapping_min_folio_order(mapping); pgoff_t limit = (i_size_read(mapping->host) - 1) >> PAGE_SHIFT; pgoff_t mark = index + ra->size - ra->async_size; unsigned int nofs; int err = 0; gfp_t gfp = readahead_gfp_mask(mapping); unsigned int min_ra_size = max(4, mapping_min_folio_nrpages(mapping)); /* * Fallback when size < min_nrpages as each folio should be * at least min_nrpages anyway. */ if (!mapping_large_folio_support(mapping) || ra->size < min_ra_size) goto fallback; limit = min(limit, index + ra->size - 1); if (new_order < mapping_max_folio_order(mapping)) new_order += 2; new_order = min(mapping_max_folio_order(mapping), new_order); new_order = min_t(unsigned int, new_order, ilog2(ra->size)); new_order = max(new_order, min_order); /* See comment in page_cache_ra_unbounded() */ nofs = memalloc_nofs_save(); filemap_invalidate_lock_shared(mapping); /* * If the new_order is greater than min_order and index is * already aligned to new_order, then this will be noop as index * aligned to new_order should also be aligned to min_order. */ ractl->_index = mapping_align_index(mapping, index); index = readahead_index(ractl); while (index <= limit) { unsigned int order = new_order; /* Align with smaller pages if needed */ if (index & ((1UL << order) - 1)) order = __ffs(index); /* Don't allocate pages past EOF */ while (order > min_order && index + (1UL << order) - 1 > limit) order--; err = ra_alloc_folio(ractl, index, mark, order, gfp); if (err) break; index += 1UL << order; } read_pages(ractl); filemap_invalidate_unlock_shared(mapping); memalloc_nofs_restore(nofs); /* * If there were already pages in the page cache, then we may have * left some gaps. Let the regular readahead code take care of this * situation. */ if (!err) return; fallback: do_page_cache_ra(ractl, ra->size, ra->async_size); } static unsigned long ractl_max_pages(struct readahead_control *ractl, unsigned long req_size) { struct backing_dev_info *bdi = inode_to_bdi(ractl->mapping->host); unsigned long max_pages = ractl->ra->ra_pages; /* * If the request exceeds the readahead window, allow the read to * be up to the optimal hardware IO size */ if (req_size > max_pages && bdi->io_pages > max_pages) max_pages = min(req_size, bdi->io_pages); return max_pages; } void page_cache_sync_ra(struct readahead_control *ractl, unsigned long req_count) { pgoff_t index = readahead_index(ractl); bool do_forced_ra = ractl->file && (ractl->file->f_mode & FMODE_RANDOM); struct file_ra_state *ra = ractl->ra; unsigned long max_pages, contig_count; pgoff_t prev_index, miss; /* * Even if readahead is disabled, issue this request as readahead * as we'll need it to satisfy the requested range. The forced * readahead will do the right thing and limit the read to just the * requested range, which we'll set to 1 page for this case. */ if (!ra->ra_pages || blk_cgroup_congested()) { if (!ractl->file) return; req_count = 1; do_forced_ra = true; } /* be dumb */ if (do_forced_ra) { force_page_cache_ra(ractl, req_count); return; } max_pages = ractl_max_pages(ractl, req_count); prev_index = (unsigned long long)ra->prev_pos >> PAGE_SHIFT; /* * A start of file, oversized read, or sequential cache miss: * trivial case: (index - prev_index) == 1 * unaligned reads: (index - prev_index) == 0 */ if (!index || req_count > max_pages || index - prev_index <= 1UL) { ra->start = index; ra->size = get_init_ra_size(req_count, max_pages); ra->async_size = ra->size > req_count ? ra->size - req_count : ra->size >> 1; goto readit; } /* * Query the page cache and look for the traces(cached history pages) * that a sequential stream would leave behind. */ rcu_read_lock(); miss = page_cache_prev_miss(ractl->mapping, index - 1, max_pages); rcu_read_unlock(); contig_count = index - miss - 1; /* * Standalone, small random read. Read as is, and do not pollute the * readahead state. */ if (contig_count <= req_count) { do_page_cache_ra(ractl, req_count, 0); return; } /* * File cached from the beginning: * it is a strong indication of long-run stream (or whole-file-read) */ if (miss == ULONG_MAX) contig_count *= 2; ra->start = index; ra->size = min(contig_count + req_count, max_pages); ra->async_size = 1; readit: ractl->_index = ra->start; page_cache_ra_order(ractl, ra, 0); } EXPORT_SYMBOL_GPL(page_cache_sync_ra); void page_cache_async_ra(struct readahead_control *ractl, struct folio *folio, unsigned long req_count) { unsigned long max_pages; struct file_ra_state *ra = ractl->ra; pgoff_t index = readahead_index(ractl); pgoff_t expected, start; unsigned int order = folio_order(folio); /* no readahead */ if (!ra->ra_pages) return; /* * Same bit is used for PG_readahead and PG_reclaim. */ if (folio_test_writeback(folio)) return; folio_clear_readahead(folio); if (blk_cgroup_congested()) return; max_pages = ractl_max_pages(ractl, req_count); /* * It's the expected callback index, assume sequential access. * Ramp up sizes, and push forward the readahead window. */ expected = round_down(ra->start + ra->size - ra->async_size, 1UL << order); if (index == expected) { ra->start += ra->size; ra->size = get_next_ra_size(ra, max_pages); ra->async_size = ra->size; goto readit; } /* * Hit a marked folio without valid readahead state. * E.g. interleaved reads. * Query the pagecache for async_size, which normally equals to * readahead size. Ramp it up and use it as the new readahead size. */ rcu_read_lock(); start = page_cache_next_miss(ractl->mapping, index + 1, max_pages); rcu_read_unlock(); if (!start || start - index > max_pages) return; ra->start = start; ra->size = start - index; /* old async_size */ ra->size += req_count; ra->size = get_next_ra_size(ra, max_pages); ra->async_size = ra->size; readit: ractl->_index = ra->start; page_cache_ra_order(ractl, ra, order); } EXPORT_SYMBOL_GPL(page_cache_async_ra); ssize_t ksys_readahead(int fd, loff_t offset, size_t count) { CLASS(fd, f)(fd); if (fd_empty(f) || !(fd_file(f)->f_mode & FMODE_READ)) return -EBADF; /* * The readahead() syscall is intended to run only on files * that can execute readahead. If readahead is not possible * on this file, then we must return -EINVAL. */ if (!fd_file(f)->f_mapping || !fd_file(f)->f_mapping->a_ops || (!S_ISREG(file_inode(fd_file(f))->i_mode) && !S_ISBLK(file_inode(fd_file(f))->i_mode))) return -EINVAL; return vfs_fadvise(fd_file(f), offset, count, POSIX_FADV_WILLNEED); } SYSCALL_DEFINE3(readahead, int, fd, loff_t, offset, size_t, count) { return ksys_readahead(fd, offset, count); } #if defined(CONFIG_COMPAT) && defined(__ARCH_WANT_COMPAT_READAHEAD) COMPAT_SYSCALL_DEFINE4(readahead, int, fd, compat_arg_u64_dual(offset), size_t, count) { return ksys_readahead(fd, compat_arg_u64_glue(offset), count); } #endif /** * readahead_expand - Expand a readahead request * @ractl: The request to be expanded * @new_start: The revised start * @new_len: The revised size of the request * * Attempt to expand a readahead request outwards from the current size to the * specified size by inserting locked pages before and after the current window * to increase the size to the new window. This may involve the insertion of * THPs, in which case the window may get expanded even beyond what was * requested. * * The algorithm will stop if it encounters a conflicting page already in the * pagecache and leave a smaller expansion than requested. * * The caller must check for this by examining the revised @ractl object for a * different expansion than was requested. */ void readahead_expand(struct readahead_control *ractl, loff_t new_start, size_t new_len) { struct address_space *mapping = ractl->mapping; struct file_ra_state *ra = ractl->ra; pgoff_t new_index, new_nr_pages; gfp_t gfp_mask = readahead_gfp_mask(mapping); unsigned long min_nrpages = mapping_min_folio_nrpages(mapping); unsigned int min_order = mapping_min_folio_order(mapping); new_index = new_start / PAGE_SIZE; /* * Readahead code should have aligned the ractl->_index to * min_nrpages before calling readahead aops. */ VM_BUG_ON(!IS_ALIGNED(ractl->_index, min_nrpages)); /* Expand the leading edge downwards */ while (ractl->_index > new_index) { unsigned long index = ractl->_index - 1; struct folio *folio = xa_load(&mapping->i_pages, index); if (folio && !xa_is_value(folio)) return; /* Folio apparently present */ folio = filemap_alloc_folio(gfp_mask, min_order); if (!folio) return; index = mapping_align_index(mapping, index); if (filemap_add_folio(mapping, folio, index, gfp_mask) < 0) { folio_put(folio); return; } if (unlikely(folio_test_workingset(folio)) && !ractl->_workingset) { ractl->_workingset = true; psi_memstall_enter(&ractl->_pflags); } ractl->_nr_pages += min_nrpages; ractl->_index = folio->index; } new_len += new_start - readahead_pos(ractl); new_nr_pages = DIV_ROUND_UP(new_len, PAGE_SIZE); /* Expand the trailing edge upwards */ while (ractl->_nr_pages < new_nr_pages) { unsigned long index = ractl->_index + ractl->_nr_pages; struct folio *folio = xa_load(&mapping->i_pages, index); if (folio && !xa_is_value(folio)) return; /* Folio apparently present */ folio = filemap_alloc_folio(gfp_mask, min_order); if (!folio) return; index = mapping_align_index(mapping, index); if (filemap_add_folio(mapping, folio, index, gfp_mask) < 0) { folio_put(folio); return; } if (unlikely(folio_test_workingset(folio)) && !ractl->_workingset) { ractl->_workingset = true; psi_memstall_enter(&ractl->_pflags); } ractl->_nr_pages += min_nrpages; if (ra) { ra->size += min_nrpages; ra->async_size += min_nrpages; } } } EXPORT_SYMBOL(readahead_expand); |
| 657 656 656 656 658 656 657 659 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 | // SPDX-License-Identifier: GPL-2.0 #include <linux/mm.h> #include <linux/mmzone.h> #include <linux/memblock.h> #include <linux/page_ext.h> #include <linux/memory.h> #include <linux/vmalloc.h> #include <linux/kmemleak.h> #include <linux/page_owner.h> #include <linux/page_idle.h> #include <linux/page_table_check.h> #include <linux/rcupdate.h> #include <linux/pgalloc_tag.h> /* * struct page extension * * This is the feature to manage memory for extended data per page. * * Until now, we must modify struct page itself to store extra data per page. * This requires rebuilding the kernel and it is really time consuming process. * And, sometimes, rebuild is impossible due to third party module dependency. * At last, enlarging struct page could cause un-wanted system behaviour change. * * This feature is intended to overcome above mentioned problems. This feature * allocates memory for extended data per page in certain place rather than * the struct page itself. This memory can be accessed by the accessor * functions provided by this code. During the boot process, it checks whether * allocation of huge chunk of memory is needed or not. If not, it avoids * allocating memory at all. With this advantage, we can include this feature * into the kernel in default and can avoid rebuild and solve related problems. * * To help these things to work well, there are two callbacks for clients. One * is the need callback which is mandatory if user wants to avoid useless * memory allocation at boot-time. The other is optional, init callback, which * is used to do proper initialization after memory is allocated. * * The need callback is used to decide whether extended memory allocation is * needed or not. Sometimes users want to deactivate some features in this * boot and extra memory would be unnecessary. In this case, to avoid * allocating huge chunk of memory, each clients represent their need of * extra memory through the need callback. If one of the need callbacks * returns true, it means that someone needs extra memory so that * page extension core should allocates memory for page extension. If * none of need callbacks return true, memory isn't needed at all in this boot * and page extension core can skip to allocate memory. As result, * none of memory is wasted. * * When need callback returns true, page_ext checks if there is a request for * extra memory through size in struct page_ext_operations. If it is non-zero, * extra space is allocated for each page_ext entry and offset is returned to * user through offset in struct page_ext_operations. * * The init callback is used to do proper initialization after page extension * is completely initialized. In sparse memory system, extra memory is * allocated some time later than memmap is allocated. In other words, lifetime * of memory for page extension isn't same with memmap for struct page. * Therefore, clients can't store extra data until page extension is * initialized, even if pages are allocated and used freely. This could * cause inadequate state of extra data per page, so, to prevent it, client * can utilize this callback to initialize the state of it correctly. */ #ifdef CONFIG_SPARSEMEM #define PAGE_EXT_INVALID (0x1) #endif #if defined(CONFIG_PAGE_IDLE_FLAG) && !defined(CONFIG_64BIT) static bool need_page_idle(void) { return true; } static struct page_ext_operations page_idle_ops __initdata = { .need = need_page_idle, .need_shared_flags = true, }; #endif static struct page_ext_operations *page_ext_ops[] __initdata = { #ifdef CONFIG_PAGE_OWNER &page_owner_ops, #endif #if defined(CONFIG_PAGE_IDLE_FLAG) && !defined(CONFIG_64BIT) &page_idle_ops, #endif #ifdef CONFIG_MEM_ALLOC_PROFILING &page_alloc_tagging_ops, #endif #ifdef CONFIG_PAGE_TABLE_CHECK &page_table_check_ops, #endif }; unsigned long page_ext_size; static unsigned long total_usage; #ifdef CONFIG_MEM_ALLOC_PROFILING_DEBUG /* * To ensure correct allocation tagging for pages, page_ext should be available * before the first page allocation. Otherwise early task stacks will be * allocated before page_ext initialization and missing tags will be flagged. */ bool early_page_ext __meminitdata = true; #else bool early_page_ext __meminitdata; #endif static int __init setup_early_page_ext(char *str) { early_page_ext = true; return 0; } early_param("early_page_ext", setup_early_page_ext); static bool __init invoke_need_callbacks(void) { int i; int entries = ARRAY_SIZE(page_ext_ops); bool need = false; for (i = 0; i < entries; i++) { if (page_ext_ops[i]->need()) { if (page_ext_ops[i]->need_shared_flags) { page_ext_size = sizeof(struct page_ext); break; } } } for (i = 0; i < entries; i++) { if (page_ext_ops[i]->need()) { page_ext_ops[i]->offset = page_ext_size; page_ext_size += page_ext_ops[i]->size; need = true; } } return need; } static void __init invoke_init_callbacks(void) { int i; int entries = ARRAY_SIZE(page_ext_ops); for (i = 0; i < entries; i++) { if (page_ext_ops[i]->init) page_ext_ops[i]->init(); } } static inline struct page_ext *get_entry(void *base, unsigned long index) { return base + page_ext_size * index; } #ifndef CONFIG_SPARSEMEM void __init page_ext_init_flatmem_late(void) { invoke_init_callbacks(); } void __meminit pgdat_page_ext_init(struct pglist_data *pgdat) { pgdat->node_page_ext = NULL; } static struct page_ext *lookup_page_ext(const struct page *page) { unsigned long pfn = page_to_pfn(page); unsigned long index; struct page_ext *base; WARN_ON_ONCE(!rcu_read_lock_held()); base = NODE_DATA(page_to_nid(page))->node_page_ext; /* * The sanity checks the page allocator does upon freeing a * page can reach here before the page_ext arrays are * allocated when feeding a range of pages to the allocator * for the first time during bootup or memory hotplug. */ if (unlikely(!base)) return NULL; index = pfn - round_down(node_start_pfn(page_to_nid(page)), MAX_ORDER_NR_PAGES); return get_entry(base, index); } static int __init alloc_node_page_ext(int nid) { struct page_ext *base; unsigned long table_size; unsigned long nr_pages; nr_pages = NODE_DATA(nid)->node_spanned_pages; if (!nr_pages) return 0; /* * Need extra space if node range is not aligned with * MAX_ORDER_NR_PAGES. When page allocator's buddy algorithm * checks buddy's status, range could be out of exact node range. */ if (!IS_ALIGNED(node_start_pfn(nid), MAX_ORDER_NR_PAGES) || !IS_ALIGNED(node_end_pfn(nid), MAX_ORDER_NR_PAGES)) nr_pages += MAX_ORDER_NR_PAGES; table_size = page_ext_size * nr_pages; base = memblock_alloc_try_nid( table_size, PAGE_SIZE, __pa(MAX_DMA_ADDRESS), MEMBLOCK_ALLOC_ACCESSIBLE, nid); if (!base) return -ENOMEM; NODE_DATA(nid)->node_page_ext = base; total_usage += table_size; memmap_boot_pages_add(DIV_ROUND_UP(table_size, PAGE_SIZE)); return 0; } void __init page_ext_init_flatmem(void) { int nid, fail; if (!invoke_need_callbacks()) return; for_each_online_node(nid) { fail = alloc_node_page_ext(nid); if (fail) goto fail; } pr_info("allocated %ld bytes of page_ext\n", total_usage); return; fail: pr_crit("allocation of page_ext failed.\n"); panic("Out of memory"); } #else /* CONFIG_SPARSEMEM */ static bool page_ext_invalid(struct page_ext *page_ext) { return !page_ext || (((unsigned long)page_ext & PAGE_EXT_INVALID) == PAGE_EXT_INVALID); } static struct page_ext *lookup_page_ext(const struct page *page) { unsigned long pfn = page_to_pfn(page); struct mem_section *section = __pfn_to_section(pfn); struct page_ext *page_ext = READ_ONCE(section->page_ext); WARN_ON_ONCE(!rcu_read_lock_held()); /* * The sanity checks the page allocator does upon freeing a * page can reach here before the page_ext arrays are * allocated when feeding a range of pages to the allocator * for the first time during bootup or memory hotplug. */ if (page_ext_invalid(page_ext)) return NULL; return get_entry(page_ext, pfn); } static void *__meminit alloc_page_ext(size_t size, int nid) { gfp_t flags = GFP_KERNEL | __GFP_ZERO | __GFP_NOWARN; void *addr = NULL; addr = alloc_pages_exact_nid(nid, size, flags); if (addr) kmemleak_alloc(addr, size, 1, flags); else addr = vzalloc_node(size, nid); if (addr) memmap_pages_add(DIV_ROUND_UP(size, PAGE_SIZE)); return addr; } static int __meminit init_section_page_ext(unsigned long pfn, int nid) { struct mem_section *section; struct page_ext *base; unsigned long table_size; section = __pfn_to_section(pfn); if (section->page_ext) return 0; table_size = page_ext_size * PAGES_PER_SECTION; base = alloc_page_ext(table_size, nid); /* * The value stored in section->page_ext is (base - pfn) * and it does not point to the memory block allocated above, * causing kmemleak false positives. */ kmemleak_not_leak(base); if (!base) { pr_err("page ext allocation failure\n"); return -ENOMEM; } /* * The passed "pfn" may not be aligned to SECTION. For the calculation * we need to apply a mask. */ pfn &= PAGE_SECTION_MASK; section->page_ext = (void *)base - page_ext_size * pfn; total_usage += table_size; return 0; } static void free_page_ext(void *addr) { size_t table_size; struct page *page; table_size = page_ext_size * PAGES_PER_SECTION; memmap_pages_add(-1L * (DIV_ROUND_UP(table_size, PAGE_SIZE))); if (is_vmalloc_addr(addr)) { vfree(addr); } else { page = virt_to_page(addr); BUG_ON(PageReserved(page)); kmemleak_free(addr); free_pages_exact(addr, table_size); } } static void __free_page_ext(unsigned long pfn) { struct mem_section *ms; struct page_ext *base; ms = __pfn_to_section(pfn); if (!ms || !ms->page_ext) return; base = READ_ONCE(ms->page_ext); /* * page_ext here can be valid while doing the roll back * operation in online_page_ext(). */ if (page_ext_invalid(base)) base = (void *)base - PAGE_EXT_INVALID; WRITE_ONCE(ms->page_ext, NULL); base = get_entry(base, pfn); free_page_ext(base); } static void __invalidate_page_ext(unsigned long pfn) { struct mem_section *ms; void *val; ms = __pfn_to_section(pfn); if (!ms || !ms->page_ext) return; val = (void *)ms->page_ext + PAGE_EXT_INVALID; WRITE_ONCE(ms->page_ext, val); } static int __meminit online_page_ext(unsigned long start_pfn, unsigned long nr_pages, int nid) { unsigned long start, end, pfn; int fail = 0; start = SECTION_ALIGN_DOWN(start_pfn); end = SECTION_ALIGN_UP(start_pfn + nr_pages); if (nid == NUMA_NO_NODE) { /* * In this case, "nid" already exists and contains valid memory. * "start_pfn" passed to us is a pfn which is an arg for * online__pages(), and start_pfn should exist. */ nid = pfn_to_nid(start_pfn); VM_BUG_ON(!node_online(nid)); } for (pfn = start; !fail && pfn < end; pfn += PAGES_PER_SECTION) fail = init_section_page_ext(pfn, nid); if (!fail) return 0; /* rollback */ end = pfn - PAGES_PER_SECTION; for (pfn = start; pfn < end; pfn += PAGES_PER_SECTION) __free_page_ext(pfn); return -ENOMEM; } static void __meminit offline_page_ext(unsigned long start_pfn, unsigned long nr_pages) { unsigned long start, end, pfn; start = SECTION_ALIGN_DOWN(start_pfn); end = SECTION_ALIGN_UP(start_pfn + nr_pages); /* * Freeing of page_ext is done in 3 steps to avoid * use-after-free of it: * 1) Traverse all the sections and mark their page_ext * as invalid. * 2) Wait for all the existing users of page_ext who * started before invalidation to finish. * 3) Free the page_ext. */ for (pfn = start; pfn < end; pfn += PAGES_PER_SECTION) __invalidate_page_ext(pfn); synchronize_rcu(); for (pfn = start; pfn < end; pfn += PAGES_PER_SECTION) __free_page_ext(pfn); } static int __meminit page_ext_callback(struct notifier_block *self, unsigned long action, void *arg) { struct memory_notify *mn = arg; int ret = 0; switch (action) { case MEM_GOING_ONLINE: ret = online_page_ext(mn->start_pfn, mn->nr_pages, mn->status_change_nid); break; case MEM_OFFLINE: offline_page_ext(mn->start_pfn, mn->nr_pages); break; case MEM_CANCEL_ONLINE: offline_page_ext(mn->start_pfn, mn->nr_pages); break; case MEM_GOING_OFFLINE: break; case MEM_ONLINE: case MEM_CANCEL_OFFLINE: break; } return notifier_from_errno(ret); } void __init page_ext_init(void) { unsigned long pfn; int nid; if (!invoke_need_callbacks()) return; for_each_node_state(nid, N_MEMORY) { unsigned long start_pfn, end_pfn; start_pfn = node_start_pfn(nid); end_pfn = node_end_pfn(nid); /* * start_pfn and end_pfn may not be aligned to SECTION and the * page->flags of out of node pages are not initialized. So we * scan [start_pfn, the biggest section's pfn < end_pfn) here. */ for (pfn = start_pfn; pfn < end_pfn; pfn = ALIGN(pfn + 1, PAGES_PER_SECTION)) { if (!pfn_valid(pfn)) continue; /* * Nodes's pfns can be overlapping. * We know some arch can have a nodes layout such as * -------------pfn--------------> * N0 | N1 | N2 | N0 | N1 | N2|.... */ if (pfn_to_nid(pfn) != nid) continue; if (init_section_page_ext(pfn, nid)) goto oom; cond_resched(); } } hotplug_memory_notifier(page_ext_callback, DEFAULT_CALLBACK_PRI); pr_info("allocated %ld bytes of page_ext\n", total_usage); invoke_init_callbacks(); return; oom: panic("Out of memory"); } void __meminit pgdat_page_ext_init(struct pglist_data *pgdat) { } #endif /** * page_ext_get() - Get the extended information for a page. * @page: The page we're interested in. * * Ensures that the page_ext will remain valid until page_ext_put() * is called. * * Return: NULL if no page_ext exists for this page. * Context: Any context. Caller may not sleep until they have called * page_ext_put(). */ struct page_ext *page_ext_get(const struct page *page) { struct page_ext *page_ext; rcu_read_lock(); page_ext = lookup_page_ext(page); if (!page_ext) { rcu_read_unlock(); return NULL; } return page_ext; } /** * page_ext_put() - Working with page extended information is done. * @page_ext: Page extended information received from page_ext_get(). * * The page extended information of the page may not be valid after this * function is called. * * Return: None. * Context: Any context with corresponding page_ext_get() is called. */ void page_ext_put(struct page_ext *page_ext) { if (unlikely(!page_ext)) return; rcu_read_unlock(); } |
| 54 21 21 425 1 21 21 54 54 54 54 54 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _LINUX_SCHED_SIGNAL_H #define _LINUX_SCHED_SIGNAL_H #include <linux/rculist.h> #include <linux/signal.h> #include <linux/sched.h> #include <linux/sched/jobctl.h> #include <linux/sched/task.h> #include <linux/cred.h> #include <linux/refcount.h> #include <linux/pid.h> #include <linux/posix-timers.h> #include <linux/mm_types.h> #include <asm/ptrace.h> /* * Types defining task->signal and task->sighand and APIs using them: */ struct sighand_struct { spinlock_t siglock; refcount_t count; wait_queue_head_t signalfd_wqh; struct k_sigaction action[_NSIG]; }; /* * Per-process accounting stats: */ struct pacct_struct { int ac_flag; long ac_exitcode; unsigned long ac_mem; u64 ac_utime, ac_stime; unsigned long ac_minflt, ac_majflt; }; struct cpu_itimer { u64 expires; u64 incr; }; /* * This is the atomic variant of task_cputime, which can be used for * storing and updating task_cputime statistics without locking. */ struct task_cputime_atomic { atomic64_t utime; atomic64_t stime; atomic64_t sum_exec_runtime; }; #define INIT_CPUTIME_ATOMIC \ (struct task_cputime_atomic) { \ .utime = ATOMIC64_INIT(0), \ .stime = ATOMIC64_INIT(0), \ .sum_exec_runtime = ATOMIC64_INIT(0), \ } /** * struct thread_group_cputimer - thread group interval timer counts * @cputime_atomic: atomic thread group interval timers. * * This structure contains the version of task_cputime, above, that is * used for thread group CPU timer calculations. */ struct thread_group_cputimer { struct task_cputime_atomic cputime_atomic; }; struct multiprocess_signals { sigset_t signal; struct hlist_node node; }; struct core_thread { struct task_struct *task; struct core_thread *next; }; struct core_state { atomic_t nr_threads; struct core_thread dumper; struct completion startup; }; /* * NOTE! "signal_struct" does not have its own * locking, because a shared signal_struct always * implies a shared sighand_struct, so locking * sighand_struct is always a proper superset of * the locking of signal_struct. */ struct signal_struct { refcount_t sigcnt; atomic_t live; int nr_threads; int quick_threads; struct list_head thread_head; wait_queue_head_t wait_chldexit; /* for wait4() */ /* current thread group signal load-balancing target: */ struct task_struct *curr_target; /* shared signal handling: */ struct sigpending shared_pending; /* For collecting multiprocess signals during fork */ struct hlist_head multiprocess; /* thread group exit support */ int group_exit_code; /* notify group_exec_task when notify_count is less or equal to 0 */ int notify_count; struct task_struct *group_exec_task; /* thread group stop support, overloads group_exit_code too */ int group_stop_count; unsigned int flags; /* see SIGNAL_* flags below */ struct core_state *core_state; /* coredumping support */ /* * PR_SET_CHILD_SUBREAPER marks a process, like a service * manager, to re-parent orphan (double-forking) child processes * to this process instead of 'init'. The service manager is * able to receive SIGCHLD signals and is able to investigate * the process until it calls wait(). All children of this * process will inherit a flag if they should look for a * child_subreaper process at exit. */ unsigned int is_child_subreaper:1; unsigned int has_child_subreaper:1; #ifdef CONFIG_POSIX_TIMERS /* POSIX.1b Interval Timers */ unsigned int next_posix_timer_id; struct hlist_head posix_timers; struct hlist_head ignored_posix_timers; /* ITIMER_REAL timer for the process */ struct hrtimer real_timer; ktime_t it_real_incr; /* * ITIMER_PROF and ITIMER_VIRTUAL timers for the process, we use * CPUCLOCK_PROF and CPUCLOCK_VIRT for indexing array as these * values are defined to 0 and 1 respectively */ struct cpu_itimer it[2]; /* * Thread group totals for process CPU timers. * See thread_group_cputimer(), et al, for details. */ struct thread_group_cputimer cputimer; #endif /* Empty if CONFIG_POSIX_TIMERS=n */ struct posix_cputimers posix_cputimers; /* PID/PID hash table linkage. */ struct pid *pids[PIDTYPE_MAX]; #ifdef CONFIG_NO_HZ_FULL atomic_t tick_dep_mask; #endif struct pid *tty_old_pgrp; /* boolean value for session group leader */ int leader; struct tty_struct *tty; /* NULL if no tty */ #ifdef CONFIG_SCHED_AUTOGROUP struct autogroup *autogroup; #endif /* * Cumulative resource counters for dead threads in the group, * and for reaped dead child processes forked by this group. * Live threads maintain their own counters and add to these * in __exit_signal, except for the group leader. */ seqlock_t stats_lock; u64 utime, stime, cutime, cstime; u64 gtime; u64 cgtime; struct prev_cputime prev_cputime; unsigned long nvcsw, nivcsw, cnvcsw, cnivcsw; unsigned long min_flt, maj_flt, cmin_flt, cmaj_flt; unsigned long inblock, oublock, cinblock, coublock; unsigned long maxrss, cmaxrss; struct task_io_accounting ioac; /* * Cumulative ns of schedule CPU time fo dead threads in the * group, not including a zombie group leader, (This only differs * from jiffies_to_ns(utime + stime) if sched_clock uses something * other than jiffies.) */ unsigned long long sum_sched_runtime; /* * We don't bother to synchronize most readers of this at all, * because there is no reader checking a limit that actually needs * to get both rlim_cur and rlim_max atomically, and either one * alone is a single word that can safely be read normally. * getrlimit/setrlimit use task_lock(current->group_leader) to * protect this instead of the siglock, because they really * have no need to disable irqs. */ struct rlimit rlim[RLIM_NLIMITS]; #ifdef CONFIG_BSD_PROCESS_ACCT struct pacct_struct pacct; /* per-process accounting information */ #endif #ifdef CONFIG_TASKSTATS struct taskstats *stats; #endif #ifdef CONFIG_AUDIT unsigned audit_tty; struct tty_audit_buf *tty_audit_buf; #endif /* * Thread is the potential origin of an oom condition; kill first on * oom */ bool oom_flag_origin; short oom_score_adj; /* OOM kill score adjustment */ short oom_score_adj_min; /* OOM kill score adjustment min value. * Only settable by CAP_SYS_RESOURCE. */ struct mm_struct *oom_mm; /* recorded mm when the thread group got * killed by the oom killer */ struct mutex cred_guard_mutex; /* guard against foreign influences on * credential calculations * (notably. ptrace) * Deprecated do not use in new code. * Use exec_update_lock instead. */ struct rw_semaphore exec_update_lock; /* Held while task_struct is * being updated during exec, * and may have inconsistent * permissions. */ } __randomize_layout; /* * Bits in flags field of signal_struct. */ #define SIGNAL_STOP_STOPPED 0x00000001 /* job control stop in effect */ #define SIGNAL_STOP_CONTINUED 0x00000002 /* SIGCONT since WCONTINUED reap */ #define SIGNAL_GROUP_EXIT 0x00000004 /* group exit in progress */ /* * Pending notifications to parent. */ #define SIGNAL_CLD_STOPPED 0x00000010 #define SIGNAL_CLD_CONTINUED 0x00000020 #define SIGNAL_CLD_MASK (SIGNAL_CLD_STOPPED|SIGNAL_CLD_CONTINUED) #define SIGNAL_UNKILLABLE 0x00000040 /* for init: ignore fatal signals */ #define SIGNAL_STOP_MASK (SIGNAL_CLD_MASK | SIGNAL_STOP_STOPPED | \ SIGNAL_STOP_CONTINUED) static inline void signal_set_stop_flags(struct signal_struct *sig, unsigned int flags) { WARN_ON(sig->flags & SIGNAL_GROUP_EXIT); sig->flags = (sig->flags & ~SIGNAL_STOP_MASK) | flags; } extern void flush_signals(struct task_struct *); extern void ignore_signals(struct task_struct *); extern void flush_signal_handlers(struct task_struct *, int force_default); extern int dequeue_signal(sigset_t *mask, kernel_siginfo_t *info, enum pid_type *type); static inline int kernel_dequeue_signal(void) { struct task_struct *task = current; kernel_siginfo_t __info; enum pid_type __type; int ret; spin_lock_irq(&task->sighand->siglock); ret = dequeue_signal(&task->blocked, &__info, &__type); spin_unlock_irq(&task->sighand->siglock); return ret; } static inline void kernel_signal_stop(void) { spin_lock_irq(¤t->sighand->siglock); if (current->jobctl & JOBCTL_STOP_DEQUEUED) { current->jobctl |= JOBCTL_STOPPED; set_special_state(TASK_STOPPED); } spin_unlock_irq(¤t->sighand->siglock); schedule(); } int force_sig_fault_to_task(int sig, int code, void __user *addr, struct task_struct *t); int force_sig_fault(int sig, int code, void __user *addr); int send_sig_fault(int sig, int code, void __user *addr, struct task_struct *t); int force_sig_mceerr(int code, void __user *, short); int send_sig_mceerr(int code, void __user *, short, struct task_struct *); int force_sig_bnderr(void __user *addr, void __user *lower, void __user *upper); int force_sig_pkuerr(void __user *addr, u32 pkey); int send_sig_perf(void __user *addr, u32 type, u64 sig_data); int force_sig_ptrace_errno_trap(int errno, void __user *addr); int force_sig_fault_trapno(int sig, int code, void __user *addr, int trapno); int send_sig_fault_trapno(int sig, int code, void __user *addr, int trapno, struct task_struct *t); int force_sig_seccomp(int syscall, int reason, bool force_coredump); extern int send_sig_info(int, struct kernel_siginfo *, struct task_struct *); extern void force_sigsegv(int sig); extern int force_sig_info(struct kernel_siginfo *); extern int __kill_pgrp_info(int sig, struct kernel_siginfo *info, struct pid *pgrp); extern int kill_pid_info(int sig, struct kernel_siginfo *info, struct pid *pid); extern int kill_pid_usb_asyncio(int sig, int errno, sigval_t addr, struct pid *, const struct cred *); extern int kill_pgrp(struct pid *pid, int sig, int priv); extern int kill_pid(struct pid *pid, int sig, int priv); extern __must_check bool do_notify_parent(struct task_struct *, int); extern void __wake_up_parent(struct task_struct *p, struct task_struct *parent); extern void force_sig(int); extern void force_fatal_sig(int); extern void force_exit_sig(int); extern int send_sig(int, struct task_struct *, int); extern int zap_other_threads(struct task_struct *p); extern int do_sigaction(int, struct k_sigaction *, struct k_sigaction *); static inline void clear_notify_signal(void) { clear_thread_flag(TIF_NOTIFY_SIGNAL); smp_mb__after_atomic(); } /* * Returns 'true' if kick_process() is needed to force a transition from * user -> kernel to guarantee expedient run of TWA_SIGNAL based task_work. */ static inline bool __set_notify_signal(struct task_struct *task) { return !test_and_set_tsk_thread_flag(task, TIF_NOTIFY_SIGNAL) && !wake_up_state(task, TASK_INTERRUPTIBLE); } /* * Called to break out of interruptible wait loops, and enter the * exit_to_user_mode_loop(). */ static inline void set_notify_signal(struct task_struct *task) { if (__set_notify_signal(task)) kick_process(task); } static inline int restart_syscall(void) { set_tsk_thread_flag(current, TIF_SIGPENDING); return -ERESTARTNOINTR; } static inline int task_sigpending(struct task_struct *p) { return unlikely(test_tsk_thread_flag(p,TIF_SIGPENDING)); } static inline int signal_pending(struct task_struct *p) { /* * TIF_NOTIFY_SIGNAL isn't really a signal, but it requires the same * behavior in terms of ensuring that we break out of wait loops * so that notify signal callbacks can be processed. */ if (unlikely(test_tsk_thread_flag(p, TIF_NOTIFY_SIGNAL))) return 1; return task_sigpending(p); } static inline int __fatal_signal_pending(struct task_struct *p) { return unlikely(sigismember(&p->pending.signal, SIGKILL)); } static inline int fatal_signal_pending(struct task_struct *p) { return task_sigpending(p) && __fatal_signal_pending(p); } static inline int signal_pending_state(unsigned int state, struct task_struct *p) { if (!(state & (TASK_INTERRUPTIBLE | TASK_WAKEKILL))) return 0; if (!signal_pending(p)) return 0; return (state & TASK_INTERRUPTIBLE) || __fatal_signal_pending(p); } /* * This should only be used in fault handlers to decide whether we * should stop the current fault routine to handle the signals * instead, especially with the case where we've got interrupted with * a VM_FAULT_RETRY. */ static inline bool fault_signal_pending(vm_fault_t fault_flags, struct pt_regs *regs) { return unlikely((fault_flags & VM_FAULT_RETRY) && (fatal_signal_pending(current) || (user_mode(regs) && signal_pending(current)))); } /* * Reevaluate whether the task has signals pending delivery. * Wake the task if so. * This is required every time the blocked sigset_t changes. * callers must hold sighand->siglock. */ extern void recalc_sigpending(void); extern void calculate_sigpending(void); extern void signal_wake_up_state(struct task_struct *t, unsigned int state); static inline void signal_wake_up(struct task_struct *t, bool fatal) { unsigned int state = 0; if (fatal && !(t->jobctl & JOBCTL_PTRACE_FROZEN)) { t->jobctl &= ~(JOBCTL_STOPPED | JOBCTL_TRACED); state = TASK_WAKEKILL | __TASK_TRACED; } signal_wake_up_state(t, state); } static inline void ptrace_signal_wake_up(struct task_struct *t, bool resume) { unsigned int state = 0; if (resume) { t->jobctl &= ~JOBCTL_TRACED; state = __TASK_TRACED; } signal_wake_up_state(t, state); } void task_join_group_stop(struct task_struct *task); #ifdef TIF_RESTORE_SIGMASK /* * Legacy restore_sigmask accessors. These are inefficient on * SMP architectures because they require atomic operations. */ /** * set_restore_sigmask() - make sure saved_sigmask processing gets done * * This sets TIF_RESTORE_SIGMASK and ensures that the arch signal code * will run before returning to user mode, to process the flag. For * all callers, TIF_SIGPENDING is already set or it's no harm to set * it. TIF_RESTORE_SIGMASK need not be in the set of bits that the * arch code will notice on return to user mode, in case those bits * are scarce. We set TIF_SIGPENDING here to ensure that the arch * signal code always gets run when TIF_RESTORE_SIGMASK is set. */ static inline void set_restore_sigmask(void) { set_thread_flag(TIF_RESTORE_SIGMASK); } static inline void clear_tsk_restore_sigmask(struct task_struct *task) { clear_tsk_thread_flag(task, TIF_RESTORE_SIGMASK); } static inline void clear_restore_sigmask(void) { clear_thread_flag(TIF_RESTORE_SIGMASK); } static inline bool test_tsk_restore_sigmask(struct task_struct *task) { return test_tsk_thread_flag(task, TIF_RESTORE_SIGMASK); } static inline bool test_restore_sigmask(void) { return test_thread_flag(TIF_RESTORE_SIGMASK); } static inline bool test_and_clear_restore_sigmask(void) { return test_and_clear_thread_flag(TIF_RESTORE_SIGMASK); } #else /* TIF_RESTORE_SIGMASK */ /* Higher-quality implementation, used if TIF_RESTORE_SIGMASK doesn't exist. */ static inline void set_restore_sigmask(void) { current->restore_sigmask = true; } static inline void clear_tsk_restore_sigmask(struct task_struct *task) { task->restore_sigmask = false; } static inline void clear_restore_sigmask(void) { current->restore_sigmask = false; } static inline bool test_restore_sigmask(void) { return current->restore_sigmask; } static inline bool test_tsk_restore_sigmask(struct task_struct *task) { return task->restore_sigmask; } static inline bool test_and_clear_restore_sigmask(void) { if (!current->restore_sigmask) return false; current->restore_sigmask = false; return true; } #endif static inline void restore_saved_sigmask(void) { if (test_and_clear_restore_sigmask()) __set_current_blocked(¤t->saved_sigmask); } extern int set_user_sigmask(const sigset_t __user *umask, size_t sigsetsize); static inline void restore_saved_sigmask_unless(bool interrupted) { if (interrupted) WARN_ON(!signal_pending(current)); else restore_saved_sigmask(); } static inline sigset_t *sigmask_to_save(void) { sigset_t *res = ¤t->blocked; if (unlikely(test_restore_sigmask())) res = ¤t->saved_sigmask; return res; } static inline int kill_cad_pid(int sig, int priv) { return kill_pid(cad_pid, sig, priv); } /* These can be the second arg to send_sig_info/send_group_sig_info. */ #define SEND_SIG_NOINFO ((struct kernel_siginfo *) 0) #define SEND_SIG_PRIV ((struct kernel_siginfo *) 1) static inline int __on_sig_stack(unsigned long sp) { #ifdef CONFIG_STACK_GROWSUP return sp >= current->sas_ss_sp && sp - current->sas_ss_sp < current->sas_ss_size; #else return sp > current->sas_ss_sp && sp - current->sas_ss_sp <= current->sas_ss_size; #endif } /* * True if we are on the alternate signal stack. */ static inline int on_sig_stack(unsigned long sp) { /* * If the signal stack is SS_AUTODISARM then, by construction, we * can't be on the signal stack unless user code deliberately set * SS_AUTODISARM when we were already on it. * * This improves reliability: if user state gets corrupted such that * the stack pointer points very close to the end of the signal stack, * then this check will enable the signal to be handled anyway. */ if (current->sas_ss_flags & SS_AUTODISARM) return 0; return __on_sig_stack(sp); } static inline int sas_ss_flags(unsigned long sp) { if (!current->sas_ss_size) return SS_DISABLE; return on_sig_stack(sp) ? SS_ONSTACK : 0; } static inline void sas_ss_reset(struct task_struct *p) { p->sas_ss_sp = 0; p->sas_ss_size = 0; p->sas_ss_flags = SS_DISABLE; } static inline unsigned long sigsp(unsigned long sp, struct ksignal *ksig) { if (unlikely((ksig->ka.sa.sa_flags & SA_ONSTACK)) && ! sas_ss_flags(sp)) #ifdef CONFIG_STACK_GROWSUP return current->sas_ss_sp; #else return current->sas_ss_sp + current->sas_ss_size; #endif return sp; } extern void __cleanup_sighand(struct sighand_struct *); extern void flush_itimer_signals(void); #define tasklist_empty() \ list_empty(&init_task.tasks) #define next_task(p) \ list_entry_rcu((p)->tasks.next, struct task_struct, tasks) #define for_each_process(p) \ for (p = &init_task ; (p = next_task(p)) != &init_task ; ) extern bool current_is_single_threaded(void); /* * Without tasklist/siglock it is only rcu-safe if g can't exit/exec, * otherwise next_thread(t) will never reach g after list_del_rcu(g). */ #define while_each_thread(g, t) \ while ((t = next_thread(t)) != g) #define for_other_threads(p, t) \ for (t = p; (t = next_thread(t)) != p; ) #define __for_each_thread(signal, t) \ list_for_each_entry_rcu(t, &(signal)->thread_head, thread_node, \ lockdep_is_held(&tasklist_lock)) #define for_each_thread(p, t) \ __for_each_thread((p)->signal, t) /* Careful: this is a double loop, 'break' won't work as expected. */ #define for_each_process_thread(p, t) \ for_each_process(p) for_each_thread(p, t) typedef int (*proc_visitor)(struct task_struct *p, void *data); void walk_process_tree(struct task_struct *top, proc_visitor, void *); static inline struct pid *task_pid_type(struct task_struct *task, enum pid_type type) { struct pid *pid; if (type == PIDTYPE_PID) pid = task_pid(task); else pid = task->signal->pids[type]; return pid; } static inline struct pid *task_tgid(struct task_struct *task) { return task->signal->pids[PIDTYPE_TGID]; } /* * Without tasklist or RCU lock it is not safe to dereference * the result of task_pgrp/task_session even if task == current, * we can race with another thread doing sys_setsid/sys_setpgid. */ static inline struct pid *task_pgrp(struct task_struct *task) { return task->signal->pids[PIDTYPE_PGID]; } static inline struct pid *task_session(struct task_struct *task) { return task->signal->pids[PIDTYPE_SID]; } static inline int get_nr_threads(struct task_struct *task) { return task->signal->nr_threads; } static inline bool thread_group_leader(struct task_struct *p) { return p->exit_signal >= 0; } static inline bool same_thread_group(struct task_struct *p1, struct task_struct *p2) { return p1->signal == p2->signal; } /* * returns NULL if p is the last thread in the thread group */ static inline struct task_struct *__next_thread(struct task_struct *p) { return list_next_or_null_rcu(&p->signal->thread_head, &p->thread_node, struct task_struct, thread_node); } static inline struct task_struct *next_thread(struct task_struct *p) { return __next_thread(p) ?: p->group_leader; } static inline int thread_group_empty(struct task_struct *p) { return thread_group_leader(p) && list_is_last(&p->thread_node, &p->signal->thread_head); } #define delay_group_leader(p) \ (thread_group_leader(p) && !thread_group_empty(p)) extern struct sighand_struct *__lock_task_sighand(struct task_struct *task, unsigned long *flags); static inline struct sighand_struct *lock_task_sighand(struct task_struct *task, unsigned long *flags) { struct sighand_struct *ret; ret = __lock_task_sighand(task, flags); (void)__cond_lock(&task->sighand->siglock, ret); return ret; } static inline void unlock_task_sighand(struct task_struct *task, unsigned long *flags) { spin_unlock_irqrestore(&task->sighand->siglock, *flags); } #ifdef CONFIG_LOCKDEP extern void lockdep_assert_task_sighand_held(struct task_struct *task); #else static inline void lockdep_assert_task_sighand_held(struct task_struct *task) { } #endif static inline unsigned long task_rlimit(const struct task_struct *task, unsigned int limit) { return READ_ONCE(task->signal->rlim[limit].rlim_cur); } static inline unsigned long task_rlimit_max(const struct task_struct *task, unsigned int limit) { return READ_ONCE(task->signal->rlim[limit].rlim_max); } static inline unsigned long rlimit(unsigned int limit) { return task_rlimit(current, limit); } static inline unsigned long rlimit_max(unsigned int limit) { return task_rlimit_max(current, limit); } #endif /* _LINUX_SCHED_SIGNAL_H */ |
| 3 3 3 3 3 3 3 3 3 3 3 3 3 3 3 3 3 3 3 3 3 3 3 3 3 3 3 3 3 3 3 3 3 3 3 3 3 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 1522 1523 1524 1525 1526 1527 1528 1529 1530 1531 1532 1533 1534 1535 1536 1537 1538 1539 1540 1541 1542 1543 1544 1545 1546 1547 1548 1549 1550 1551 1552 1553 1554 1555 1556 1557 1558 1559 1560 1561 1562 1563 1564 1565 1566 1567 1568 1569 1570 1571 1572 1573 1574 1575 1576 1577 1578 1579 1580 1581 1582 1583 1584 1585 1586 1587 1588 1589 1590 1591 1592 1593 1594 1595 1596 1597 1598 1599 1600 1601 1602 1603 1604 1605 1606 1607 1608 1609 1610 1611 1612 1613 1614 1615 1616 1617 1618 1619 1620 1621 1622 1623 1624 1625 1626 1627 1628 1629 1630 1631 1632 1633 1634 1635 1636 1637 1638 1639 1640 1641 1642 1643 1644 1645 1646 1647 1648 1649 1650 1651 1652 1653 1654 1655 1656 1657 1658 1659 1660 1661 1662 1663 1664 1665 1666 1667 1668 1669 1670 1671 1672 1673 1674 1675 1676 1677 1678 1679 1680 1681 1682 1683 1684 1685 1686 1687 1688 1689 1690 1691 1692 1693 1694 1695 1696 1697 1698 1699 1700 1701 1702 1703 1704 1705 1706 1707 1708 1709 1710 1711 1712 1713 1714 1715 1716 1717 1718 1719 1720 1721 1722 1723 1724 1725 1726 1727 1728 1729 1730 1731 1732 1733 1734 1735 1736 1737 1738 1739 1740 1741 1742 1743 1744 1745 1746 1747 1748 1749 1750 1751 1752 1753 1754 1755 1756 1757 1758 1759 1760 1761 1762 1763 1764 1765 1766 1767 1768 1769 1770 1771 1772 1773 1774 1775 1776 1777 1778 1779 1780 1781 1782 1783 1784 1785 1786 1787 1788 1789 1790 1791 1792 1793 1794 1795 1796 1797 1798 1799 1800 1801 1802 1803 1804 1805 1806 1807 1808 1809 1810 1811 1812 1813 1814 1815 1816 1817 1818 1819 1820 1821 1822 1823 1824 1825 1826 1827 1828 1829 1830 1831 1832 1833 1834 1835 1836 1837 1838 1839 1840 1841 1842 1843 1844 1845 1846 1847 1848 1849 1850 1851 1852 1853 1854 1855 1856 1857 1858 1859 1860 1861 1862 1863 1864 1865 1866 1867 1868 1869 1870 1871 1872 1873 1874 1875 1876 1877 1878 1879 1880 1881 1882 1883 1884 1885 1886 1887 1888 1889 1890 1891 1892 1893 1894 1895 1896 1897 1898 1899 1900 1901 1902 1903 1904 1905 1906 1907 1908 1909 1910 1911 1912 1913 1914 1915 1916 1917 1918 1919 1920 1921 1922 1923 1924 1925 1926 1927 1928 1929 1930 1931 1932 1933 1934 1935 1936 1937 1938 1939 1940 1941 1942 1943 1944 1945 1946 1947 1948 1949 1950 1951 1952 1953 1954 1955 1956 1957 1958 1959 1960 1961 1962 1963 1964 1965 1966 1967 1968 1969 1970 1971 1972 1973 1974 1975 1976 1977 1978 1979 1980 1981 1982 1983 1984 1985 1986 1987 1988 1989 1990 1991 1992 1993 1994 1995 1996 1997 1998 1999 2000 2001 2002 2003 2004 2005 2006 2007 2008 2009 2010 2011 2012 2013 2014 2015 2016 2017 2018 2019 2020 2021 2022 2023 2024 2025 2026 2027 2028 2029 2030 2031 2032 2033 2034 2035 2036 2037 2038 2039 2040 2041 2042 2043 2044 2045 2046 2047 2048 2049 2050 2051 2052 2053 2054 2055 2056 2057 2058 2059 2060 2061 2062 2063 2064 2065 2066 2067 2068 2069 2070 2071 2072 2073 2074 2075 2076 2077 2078 2079 2080 2081 2082 2083 2084 2085 2086 2087 2088 2089 2090 2091 2092 2093 2094 2095 2096 2097 2098 2099 2100 2101 2102 2103 2104 2105 2106 2107 2108 2109 2110 2111 2112 2113 2114 2115 2116 2117 2118 2119 2120 2121 2122 2123 2124 2125 2126 2127 2128 2129 2130 2131 2132 2133 2134 2135 2136 2137 2138 2139 2140 2141 2142 2143 2144 2145 2146 2147 2148 2149 2150 2151 2152 2153 2154 2155 2156 2157 2158 2159 2160 2161 2162 2163 2164 2165 2166 2167 2168 2169 2170 2171 2172 2173 2174 2175 2176 2177 2178 2179 2180 2181 2182 2183 2184 2185 2186 2187 2188 2189 2190 2191 2192 2193 2194 2195 2196 2197 2198 2199 2200 2201 2202 2203 2204 2205 2206 2207 2208 2209 2210 2211 2212 2213 2214 2215 2216 2217 2218 2219 2220 2221 2222 2223 2224 2225 2226 2227 2228 2229 2230 2231 2232 2233 2234 2235 2236 2237 2238 2239 2240 2241 2242 2243 2244 2245 2246 2247 2248 2249 2250 2251 2252 2253 2254 2255 2256 2257 2258 2259 2260 2261 2262 2263 2264 2265 2266 2267 2268 2269 2270 2271 2272 2273 2274 2275 2276 2277 2278 2279 2280 2281 2282 2283 2284 2285 2286 2287 2288 2289 2290 2291 2292 2293 2294 2295 2296 2297 2298 2299 2300 2301 2302 2303 2304 2305 2306 2307 2308 2309 2310 2311 2312 2313 2314 2315 2316 2317 2318 2319 2320 2321 2322 2323 2324 2325 2326 2327 2328 2329 2330 2331 2332 2333 2334 2335 2336 2337 2338 2339 2340 2341 2342 2343 2344 2345 2346 2347 2348 2349 2350 2351 2352 2353 2354 2355 2356 2357 2358 2359 2360 2361 2362 2363 2364 2365 2366 2367 2368 2369 2370 2371 2372 2373 2374 2375 2376 2377 2378 2379 2380 2381 2382 2383 2384 2385 2386 2387 2388 2389 2390 2391 2392 2393 2394 2395 2396 2397 2398 2399 2400 2401 2402 2403 2404 2405 2406 2407 2408 2409 2410 2411 2412 2413 2414 2415 2416 2417 2418 2419 2420 2421 2422 2423 2424 2425 2426 2427 2428 2429 2430 2431 2432 2433 2434 2435 2436 2437 2438 2439 2440 2441 2442 2443 2444 2445 2446 2447 2448 2449 2450 2451 2452 2453 2454 2455 2456 2457 2458 2459 2460 2461 2462 2463 2464 2465 2466 2467 2468 2469 2470 2471 2472 2473 2474 2475 2476 2477 2478 2479 2480 2481 2482 2483 2484 2485 2486 2487 2488 2489 2490 2491 2492 2493 2494 2495 2496 2497 2498 2499 2500 2501 2502 2503 2504 2505 2506 2507 2508 2509 2510 2511 2512 2513 2514 2515 2516 2517 2518 2519 2520 2521 2522 2523 2524 2525 2526 2527 2528 2529 2530 2531 2532 2533 2534 2535 2536 2537 2538 2539 2540 2541 2542 2543 2544 2545 2546 2547 2548 2549 2550 2551 2552 2553 2554 2555 2556 2557 2558 2559 2560 2561 2562 2563 2564 2565 2566 2567 2568 2569 2570 2571 2572 2573 2574 2575 2576 2577 2578 2579 2580 2581 2582 2583 2584 2585 2586 2587 2588 2589 2590 2591 2592 2593 2594 2595 2596 2597 2598 2599 2600 2601 2602 2603 2604 2605 2606 2607 2608 2609 2610 2611 2612 2613 2614 2615 2616 2617 2618 2619 2620 2621 2622 2623 2624 2625 2626 2627 2628 2629 2630 2631 2632 2633 2634 2635 2636 2637 2638 2639 2640 2641 2642 2643 2644 2645 2646 2647 2648 2649 2650 2651 2652 2653 2654 2655 2656 2657 2658 2659 2660 2661 2662 2663 2664 2665 2666 2667 2668 2669 2670 2671 2672 2673 2674 2675 2676 2677 2678 2679 2680 2681 2682 2683 2684 2685 2686 2687 2688 2689 2690 2691 2692 2693 2694 2695 2696 2697 2698 2699 2700 2701 2702 2703 2704 2705 2706 2707 2708 2709 2710 2711 2712 2713 2714 2715 2716 2717 2718 2719 2720 2721 2722 2723 2724 2725 2726 2727 2728 2729 2730 2731 2732 2733 2734 2735 2736 2737 2738 2739 2740 2741 2742 2743 2744 2745 2746 2747 2748 2749 2750 2751 2752 2753 2754 2755 2756 2757 2758 2759 2760 2761 2762 2763 2764 2765 2766 2767 2768 2769 2770 2771 2772 2773 | // SPDX-License-Identifier: GPL-2.0-or-later /* * Linux INET6 implementation * Forwarding Information Database * * Authors: * Pedro Roque <roque@di.fc.ul.pt> * * Changes: * Yuji SEKIYA @USAGI: Support default route on router node; * remove ip6_null_entry from the top of * routing table. * Ville Nuorvala: Fixed routing subtrees. */ #define pr_fmt(fmt) "IPv6: " fmt #include <linux/bpf.h> #include <linux/errno.h> #include <linux/types.h> #include <linux/net.h> #include <linux/route.h> #include <linux/netdevice.h> #include <linux/in6.h> #include <linux/init.h> #include <linux/list.h> #include <linux/slab.h> #include <net/ip.h> #include <net/ipv6.h> #include <net/ndisc.h> #include <net/addrconf.h> #include <net/lwtunnel.h> #include <net/fib_notifier.h> #include <net/ip_fib.h> #include <net/ip6_fib.h> #include <net/ip6_route.h> static struct kmem_cache *fib6_node_kmem __read_mostly; struct fib6_cleaner { struct fib6_walker w; struct net *net; int (*func)(struct fib6_info *, void *arg); int sernum; void *arg; bool skip_notify; }; #ifdef CONFIG_IPV6_SUBTREES #define FWS_INIT FWS_S #else #define FWS_INIT FWS_L #endif static struct fib6_info *fib6_find_prefix(struct net *net, struct fib6_table *table, struct fib6_node *fn); static struct fib6_node *fib6_repair_tree(struct net *net, struct fib6_table *table, struct fib6_node *fn); static int fib6_walk(struct net *net, struct fib6_walker *w); static int fib6_walk_continue(struct fib6_walker *w); /* * A routing update causes an increase of the serial number on the * affected subtree. This allows for cached routes to be asynchronously * tested when modifications are made to the destination cache as a * result of redirects, path MTU changes, etc. */ static void fib6_gc_timer_cb(struct timer_list *t); #define FOR_WALKERS(net, w) \ list_for_each_entry(w, &(net)->ipv6.fib6_walkers, lh) static void fib6_walker_link(struct net *net, struct fib6_walker *w) { write_lock_bh(&net->ipv6.fib6_walker_lock); list_add(&w->lh, &net->ipv6.fib6_walkers); write_unlock_bh(&net->ipv6.fib6_walker_lock); } static void fib6_walker_unlink(struct net *net, struct fib6_walker *w) { write_lock_bh(&net->ipv6.fib6_walker_lock); list_del(&w->lh); write_unlock_bh(&net->ipv6.fib6_walker_lock); } static int fib6_new_sernum(struct net *net) { int new, old = atomic_read(&net->ipv6.fib6_sernum); do { new = old < INT_MAX ? old + 1 : 1; } while (!atomic_try_cmpxchg(&net->ipv6.fib6_sernum, &old, new)); return new; } enum { FIB6_NO_SERNUM_CHANGE = 0, }; void fib6_update_sernum(struct net *net, struct fib6_info *f6i) { struct fib6_node *fn; fn = rcu_dereference_protected(f6i->fib6_node, lockdep_is_held(&f6i->fib6_table->tb6_lock)); if (fn) WRITE_ONCE(fn->fn_sernum, fib6_new_sernum(net)); } /* * Auxiliary address test functions for the radix tree. * * These assume a 32bit processor (although it will work on * 64bit processors) */ /* * test bit */ #if defined(__LITTLE_ENDIAN) # define BITOP_BE32_SWIZZLE (0x1F & ~7) #else # define BITOP_BE32_SWIZZLE 0 #endif static __be32 addr_bit_set(const void *token, int fn_bit) { const __be32 *addr = token; /* * Here, * 1 << ((~fn_bit ^ BITOP_BE32_SWIZZLE) & 0x1f) * is optimized version of * htonl(1 << ((~fn_bit)&0x1F)) * See include/asm-generic/bitops/le.h. */ return (__force __be32)(1 << ((~fn_bit ^ BITOP_BE32_SWIZZLE) & 0x1f)) & addr[fn_bit >> 5]; } struct fib6_info *fib6_info_alloc(gfp_t gfp_flags, bool with_fib6_nh) { struct fib6_info *f6i; size_t sz = sizeof(*f6i); if (with_fib6_nh) sz += sizeof(struct fib6_nh); f6i = kzalloc(sz, gfp_flags); if (!f6i) return NULL; /* fib6_siblings is a union with nh_list, so this initializes both */ INIT_LIST_HEAD(&f6i->fib6_siblings); refcount_set(&f6i->fib6_ref, 1); INIT_HLIST_NODE(&f6i->gc_link); return f6i; } void fib6_info_destroy_rcu(struct rcu_head *head) { struct fib6_info *f6i = container_of(head, struct fib6_info, rcu); WARN_ON(f6i->fib6_node); if (f6i->nh) nexthop_put(f6i->nh); else fib6_nh_release(f6i->fib6_nh); ip_fib_metrics_put(f6i->fib6_metrics); kfree(f6i); } EXPORT_SYMBOL_GPL(fib6_info_destroy_rcu); static struct fib6_node *node_alloc(struct net *net) { struct fib6_node *fn; fn = kmem_cache_zalloc(fib6_node_kmem, GFP_ATOMIC); if (fn) net->ipv6.rt6_stats->fib_nodes++; return fn; } static void node_free_immediate(struct net *net, struct fib6_node *fn) { kmem_cache_free(fib6_node_kmem, fn); net->ipv6.rt6_stats->fib_nodes--; } static void node_free(struct net *net, struct fib6_node *fn) { kfree_rcu(fn, rcu); net->ipv6.rt6_stats->fib_nodes--; } static void fib6_free_table(struct fib6_table *table) { inetpeer_invalidate_tree(&table->tb6_peers); kfree(table); } static void fib6_link_table(struct net *net, struct fib6_table *tb) { unsigned int h; /* * Initialize table lock at a single place to give lockdep a key, * tables aren't visible prior to being linked to the list. */ spin_lock_init(&tb->tb6_lock); h = tb->tb6_id & (FIB6_TABLE_HASHSZ - 1); /* * No protection necessary, this is the only list mutatation * operation, tables never disappear once they exist. */ hlist_add_head_rcu(&tb->tb6_hlist, &net->ipv6.fib_table_hash[h]); } #ifdef CONFIG_IPV6_MULTIPLE_TABLES static struct fib6_table *fib6_alloc_table(struct net *net, u32 id) { struct fib6_table *table; table = kzalloc(sizeof(*table), GFP_ATOMIC); if (table) { table->tb6_id = id; rcu_assign_pointer(table->tb6_root.leaf, net->ipv6.fib6_null_entry); table->tb6_root.fn_flags = RTN_ROOT | RTN_TL_ROOT | RTN_RTINFO; inet_peer_base_init(&table->tb6_peers); INIT_HLIST_HEAD(&table->tb6_gc_hlist); } return table; } struct fib6_table *fib6_new_table(struct net *net, u32 id) { struct fib6_table *tb; if (id == 0) id = RT6_TABLE_MAIN; tb = fib6_get_table(net, id); if (tb) return tb; tb = fib6_alloc_table(net, id); if (tb) fib6_link_table(net, tb); return tb; } EXPORT_SYMBOL_GPL(fib6_new_table); struct fib6_table *fib6_get_table(struct net *net, u32 id) { struct fib6_table *tb; struct hlist_head *head; unsigned int h; if (id == 0) id = RT6_TABLE_MAIN; h = id & (FIB6_TABLE_HASHSZ - 1); rcu_read_lock(); head = &net->ipv6.fib_table_hash[h]; hlist_for_each_entry_rcu(tb, head, tb6_hlist) { if (tb->tb6_id == id) { rcu_read_unlock(); return tb; } } rcu_read_unlock(); return NULL; } EXPORT_SYMBOL_GPL(fib6_get_table); static void __net_init fib6_tables_init(struct net *net) { fib6_link_table(net, net->ipv6.fib6_main_tbl); fib6_link_table(net, net->ipv6.fib6_local_tbl); } #else struct fib6_table *fib6_new_table(struct net *net, u32 id) { return fib6_get_table(net, id); } struct fib6_table *fib6_get_table(struct net *net, u32 id) { return net->ipv6.fib6_main_tbl; } struct dst_entry *fib6_rule_lookup(struct net *net, struct flowi6 *fl6, const struct sk_buff *skb, int flags, pol_lookup_t lookup) { struct rt6_info *rt; rt = pol_lookup_func(lookup, net, net->ipv6.fib6_main_tbl, fl6, skb, flags); if (rt->dst.error == -EAGAIN) { ip6_rt_put_flags(rt, flags); rt = net->ipv6.ip6_null_entry; if (!(flags & RT6_LOOKUP_F_DST_NOREF)) dst_hold(&rt->dst); } return &rt->dst; } /* called with rcu lock held; no reference taken on fib6_info */ int fib6_lookup(struct net *net, int oif, struct flowi6 *fl6, struct fib6_result *res, int flags) { return fib6_table_lookup(net, net->ipv6.fib6_main_tbl, oif, fl6, res, flags); } static void __net_init fib6_tables_init(struct net *net) { fib6_link_table(net, net->ipv6.fib6_main_tbl); } #endif unsigned int fib6_tables_seq_read(const struct net *net) { unsigned int h, fib_seq = 0; rcu_read_lock(); for (h = 0; h < FIB6_TABLE_HASHSZ; h++) { const struct hlist_head *head = &net->ipv6.fib_table_hash[h]; const struct fib6_table *tb; hlist_for_each_entry_rcu(tb, head, tb6_hlist) fib_seq += READ_ONCE(tb->fib_seq); } rcu_read_unlock(); return fib_seq; } static int call_fib6_entry_notifier(struct notifier_block *nb, enum fib_event_type event_type, struct fib6_info *rt, struct netlink_ext_ack *extack) { struct fib6_entry_notifier_info info = { .info.extack = extack, .rt = rt, }; return call_fib6_notifier(nb, event_type, &info.info); } static int call_fib6_multipath_entry_notifier(struct notifier_block *nb, enum fib_event_type event_type, struct fib6_info *rt, unsigned int nsiblings, struct netlink_ext_ack *extack) { struct fib6_entry_notifier_info info = { .info.extack = extack, .rt = rt, .nsiblings = nsiblings, }; return call_fib6_notifier(nb, event_type, &info.info); } int call_fib6_entry_notifiers(struct net *net, enum fib_event_type event_type, struct fib6_info *rt, struct netlink_ext_ack *extack) { struct fib6_entry_notifier_info info = { .info.extack = extack, .rt = rt, }; WRITE_ONCE(rt->fib6_table->fib_seq, rt->fib6_table->fib_seq + 1); return call_fib6_notifiers(net, event_type, &info.info); } int call_fib6_multipath_entry_notifiers(struct net *net, enum fib_event_type event_type, struct fib6_info *rt, unsigned int nsiblings, struct netlink_ext_ack *extack) { struct fib6_entry_notifier_info info = { .info.extack = extack, .rt = rt, .nsiblings = nsiblings, }; WRITE_ONCE(rt->fib6_table->fib_seq, rt->fib6_table->fib_seq + 1); return call_fib6_notifiers(net, event_type, &info.info); } int call_fib6_entry_notifiers_replace(struct net *net, struct fib6_info *rt) { struct fib6_entry_notifier_info info = { .rt = rt, .nsiblings = rt->fib6_nsiblings, }; WRITE_ONCE(rt->fib6_table->fib_seq, rt->fib6_table->fib_seq + 1); return call_fib6_notifiers(net, FIB_EVENT_ENTRY_REPLACE, &info.info); } struct fib6_dump_arg { struct net *net; struct notifier_block *nb; struct netlink_ext_ack *extack; }; static int fib6_rt_dump(struct fib6_info *rt, struct fib6_dump_arg *arg) { enum fib_event_type fib_event = FIB_EVENT_ENTRY_REPLACE; int err; if (!rt || rt == arg->net->ipv6.fib6_null_entry) return 0; if (rt->fib6_nsiblings) err = call_fib6_multipath_entry_notifier(arg->nb, fib_event, rt, rt->fib6_nsiblings, arg->extack); else err = call_fib6_entry_notifier(arg->nb, fib_event, rt, arg->extack); return err; } static int fib6_node_dump(struct fib6_walker *w) { int err; err = fib6_rt_dump(w->leaf, w->args); w->leaf = NULL; return err; } static int fib6_table_dump(struct net *net, struct fib6_table *tb, struct fib6_walker *w) { int err; w->root = &tb->tb6_root; spin_lock_bh(&tb->tb6_lock); err = fib6_walk(net, w); spin_unlock_bh(&tb->tb6_lock); return err; } /* Called with rcu_read_lock() */ int fib6_tables_dump(struct net *net, struct notifier_block *nb, struct netlink_ext_ack *extack) { struct fib6_dump_arg arg; struct fib6_walker *w; unsigned int h; int err = 0; w = kzalloc(sizeof(*w), GFP_ATOMIC); if (!w) return -ENOMEM; w->func = fib6_node_dump; arg.net = net; arg.nb = nb; arg.extack = extack; w->args = &arg; for (h = 0; h < FIB6_TABLE_HASHSZ; h++) { struct hlist_head *head = &net->ipv6.fib_table_hash[h]; struct fib6_table *tb; hlist_for_each_entry_rcu(tb, head, tb6_hlist) { err = fib6_table_dump(net, tb, w); if (err) goto out; } } out: kfree(w); /* The tree traversal function should never return a positive value. */ return err > 0 ? -EINVAL : err; } static int fib6_dump_node(struct fib6_walker *w) { int res; struct fib6_info *rt; for_each_fib6_walker_rt(w) { res = rt6_dump_route(rt, w->args, w->skip_in_node); if (res >= 0) { /* Frame is full, suspend walking */ w->leaf = rt; /* We'll restart from this node, so if some routes were * already dumped, skip them next time. */ w->skip_in_node += res; return 1; } w->skip_in_node = 0; /* Multipath routes are dumped in one route with the * RTA_MULTIPATH attribute. Jump 'rt' to point to the * last sibling of this route (no need to dump the * sibling routes again) */ if (rt->fib6_nsiblings) rt = list_last_entry(&rt->fib6_siblings, struct fib6_info, fib6_siblings); } w->leaf = NULL; return 0; } static void fib6_dump_end(struct netlink_callback *cb) { struct net *net = sock_net(cb->skb->sk); struct fib6_walker *w = (void *)cb->args[2]; if (w) { if (cb->args[4]) { cb->args[4] = 0; fib6_walker_unlink(net, w); } cb->args[2] = 0; kfree(w); } cb->done = (void *)cb->args[3]; cb->args[1] = 3; } static int fib6_dump_done(struct netlink_callback *cb) { fib6_dump_end(cb); return cb->done ? cb->done(cb) : 0; } static int fib6_dump_table(struct fib6_table *table, struct sk_buff *skb, struct netlink_callback *cb) { struct net *net = sock_net(skb->sk); struct fib6_walker *w; int res; w = (void *)cb->args[2]; w->root = &table->tb6_root; if (cb->args[4] == 0) { w->count = 0; w->skip = 0; w->skip_in_node = 0; spin_lock_bh(&table->tb6_lock); res = fib6_walk(net, w); spin_unlock_bh(&table->tb6_lock); if (res > 0) { cb->args[4] = 1; cb->args[5] = READ_ONCE(w->root->fn_sernum); } } else { int sernum = READ_ONCE(w->root->fn_sernum); if (cb->args[5] != sernum) { /* Begin at the root if the tree changed */ cb->args[5] = sernum; w->state = FWS_INIT; w->node = w->root; w->skip = w->count; w->skip_in_node = 0; } else w->skip = 0; spin_lock_bh(&table->tb6_lock); res = fib6_walk_continue(w); spin_unlock_bh(&table->tb6_lock); if (res <= 0) { fib6_walker_unlink(net, w); cb->args[4] = 0; } } return res; } static int inet6_dump_fib(struct sk_buff *skb, struct netlink_callback *cb) { struct rt6_rtnl_dump_arg arg = { .filter.dump_exceptions = true, .filter.dump_routes = true, .filter.rtnl_held = false, }; const struct nlmsghdr *nlh = cb->nlh; struct net *net = sock_net(skb->sk); unsigned int e = 0, s_e; struct hlist_head *head; struct fib6_walker *w; struct fib6_table *tb; unsigned int h, s_h; int err = 0; rcu_read_lock(); if (cb->strict_check) { err = ip_valid_fib_dump_req(net, nlh, &arg.filter, cb); if (err < 0) goto unlock; } else if (nlmsg_len(nlh) >= sizeof(struct rtmsg)) { struct rtmsg *rtm = nlmsg_data(nlh); if (rtm->rtm_flags & RTM_F_PREFIX) arg.filter.flags = RTM_F_PREFIX; } w = (void *)cb->args[2]; if (!w) { /* New dump: * * 1. allocate and initialize walker. */ w = kzalloc(sizeof(*w), GFP_ATOMIC); if (!w) { err = -ENOMEM; goto unlock; } w->func = fib6_dump_node; cb->args[2] = (long)w; /* 2. hook callback destructor. */ cb->args[3] = (long)cb->done; cb->done = fib6_dump_done; } arg.skb = skb; arg.cb = cb; arg.net = net; w->args = &arg; if (arg.filter.table_id) { tb = fib6_get_table(net, arg.filter.table_id); if (!tb) { if (rtnl_msg_family(cb->nlh) != PF_INET6) goto unlock; NL_SET_ERR_MSG_MOD(cb->extack, "FIB table does not exist"); err = -ENOENT; goto unlock; } if (!cb->args[0]) { err = fib6_dump_table(tb, skb, cb); if (!err) cb->args[0] = 1; } goto unlock; } s_h = cb->args[0]; s_e = cb->args[1]; for (h = s_h; h < FIB6_TABLE_HASHSZ; h++, s_e = 0) { e = 0; head = &net->ipv6.fib_table_hash[h]; hlist_for_each_entry_rcu(tb, head, tb6_hlist) { if (e < s_e) goto next; err = fib6_dump_table(tb, skb, cb); if (err != 0) goto out; next: e++; } } out: cb->args[1] = e; cb->args[0] = h; unlock: rcu_read_unlock(); if (err <= 0) fib6_dump_end(cb); return err; } void fib6_metric_set(struct fib6_info *f6i, int metric, u32 val) { if (!f6i) return; if (f6i->fib6_metrics == &dst_default_metrics) { struct dst_metrics *p = kzalloc(sizeof(*p), GFP_ATOMIC); if (!p) return; refcount_set(&p->refcnt, 1); f6i->fib6_metrics = p; } f6i->fib6_metrics->metrics[metric - 1] = val; } /* * Routing Table * * return the appropriate node for a routing tree "add" operation * by either creating and inserting or by returning an existing * node. */ static struct fib6_node *fib6_add_1(struct net *net, struct fib6_table *table, struct fib6_node *root, struct in6_addr *addr, int plen, int offset, int allow_create, int replace_required, struct netlink_ext_ack *extack) { struct fib6_node *fn, *in, *ln; struct fib6_node *pn = NULL; struct rt6key *key; int bit; __be32 dir = 0; /* insert node in tree */ fn = root; do { struct fib6_info *leaf = rcu_dereference_protected(fn->leaf, lockdep_is_held(&table->tb6_lock)); key = (struct rt6key *)((u8 *)leaf + offset); /* * Prefix match */ if (plen < fn->fn_bit || !ipv6_prefix_equal(&key->addr, addr, fn->fn_bit)) { if (!allow_create) { if (replace_required) { NL_SET_ERR_MSG(extack, "Can not replace route - no match found"); pr_warn("Can't replace route, no match found\n"); return ERR_PTR(-ENOENT); } pr_warn("NLM_F_CREATE should be set when creating new route\n"); } goto insert_above; } /* * Exact match ? */ if (plen == fn->fn_bit) { /* clean up an intermediate node */ if (!(fn->fn_flags & RTN_RTINFO)) { RCU_INIT_POINTER(fn->leaf, NULL); fib6_info_release(leaf); /* remove null_entry in the root node */ } else if (fn->fn_flags & RTN_TL_ROOT && rcu_access_pointer(fn->leaf) == net->ipv6.fib6_null_entry) { RCU_INIT_POINTER(fn->leaf, NULL); } return fn; } /* * We have more bits to go */ /* Try to walk down on tree. */ dir = addr_bit_set(addr, fn->fn_bit); pn = fn; fn = dir ? rcu_dereference_protected(fn->right, lockdep_is_held(&table->tb6_lock)) : rcu_dereference_protected(fn->left, lockdep_is_held(&table->tb6_lock)); } while (fn); if (!allow_create) { /* We should not create new node because * NLM_F_REPLACE was specified without NLM_F_CREATE * I assume it is safe to require NLM_F_CREATE when * REPLACE flag is used! Later we may want to remove the * check for replace_required, because according * to netlink specification, NLM_F_CREATE * MUST be specified if new route is created. * That would keep IPv6 consistent with IPv4 */ if (replace_required) { NL_SET_ERR_MSG(extack, "Can not replace route - no match found"); pr_warn("Can't replace route, no match found\n"); return ERR_PTR(-ENOENT); } pr_warn("NLM_F_CREATE should be set when creating new route\n"); } /* * We walked to the bottom of tree. * Create new leaf node without children. */ ln = node_alloc(net); if (!ln) return ERR_PTR(-ENOMEM); ln->fn_bit = plen; RCU_INIT_POINTER(ln->parent, pn); if (dir) rcu_assign_pointer(pn->right, ln); else rcu_assign_pointer(pn->left, ln); return ln; insert_above: /* * split since we don't have a common prefix anymore or * we have a less significant route. * we've to insert an intermediate node on the list * this new node will point to the one we need to create * and the current */ pn = rcu_dereference_protected(fn->parent, lockdep_is_held(&table->tb6_lock)); /* find 1st bit in difference between the 2 addrs. See comment in __ipv6_addr_diff: bit may be an invalid value, but if it is >= plen, the value is ignored in any case. */ bit = __ipv6_addr_diff(addr, &key->addr, sizeof(*addr)); /* * (intermediate)[in] * / \ * (new leaf node)[ln] (old node)[fn] */ if (plen > bit) { in = node_alloc(net); ln = node_alloc(net); if (!in || !ln) { if (in) node_free_immediate(net, in); if (ln) node_free_immediate(net, ln); return ERR_PTR(-ENOMEM); } /* * new intermediate node. * RTN_RTINFO will * be off since that an address that chooses one of * the branches would not match less specific routes * in the other branch */ in->fn_bit = bit; RCU_INIT_POINTER(in->parent, pn); in->leaf = fn->leaf; fib6_info_hold(rcu_dereference_protected(in->leaf, lockdep_is_held(&table->tb6_lock))); /* update parent pointer */ if (dir) rcu_assign_pointer(pn->right, in); else rcu_assign_pointer(pn->left, in); ln->fn_bit = plen; RCU_INIT_POINTER(ln->parent, in); rcu_assign_pointer(fn->parent, in); if (addr_bit_set(addr, bit)) { rcu_assign_pointer(in->right, ln); rcu_assign_pointer(in->left, fn); } else { rcu_assign_pointer(in->left, ln); rcu_assign_pointer(in->right, fn); } } else { /* plen <= bit */ /* * (new leaf node)[ln] * / \ * (old node)[fn] NULL */ ln = node_alloc(net); if (!ln) return ERR_PTR(-ENOMEM); ln->fn_bit = plen; RCU_INIT_POINTER(ln->parent, pn); if (addr_bit_set(&key->addr, plen)) RCU_INIT_POINTER(ln->right, fn); else RCU_INIT_POINTER(ln->left, fn); rcu_assign_pointer(fn->parent, ln); if (dir) rcu_assign_pointer(pn->right, ln); else rcu_assign_pointer(pn->left, ln); } return ln; } static void __fib6_drop_pcpu_from(struct fib6_nh *fib6_nh, const struct fib6_info *match, const struct fib6_table *table) { int cpu; if (!fib6_nh->rt6i_pcpu) return; rcu_read_lock(); /* release the reference to this fib entry from * all of its cached pcpu routes */ for_each_possible_cpu(cpu) { struct rt6_info **ppcpu_rt; struct rt6_info *pcpu_rt; ppcpu_rt = per_cpu_ptr(fib6_nh->rt6i_pcpu, cpu); /* Paired with xchg() in rt6_get_pcpu_route() */ pcpu_rt = READ_ONCE(*ppcpu_rt); /* only dropping the 'from' reference if the cached route * is using 'match'. The cached pcpu_rt->from only changes * from a fib6_info to NULL (ip6_dst_destroy); it can never * change from one fib6_info reference to another */ if (pcpu_rt && rcu_access_pointer(pcpu_rt->from) == match) { struct fib6_info *from; from = unrcu_pointer(xchg(&pcpu_rt->from, NULL)); fib6_info_release(from); } } rcu_read_unlock(); } struct fib6_nh_pcpu_arg { struct fib6_info *from; const struct fib6_table *table; }; static int fib6_nh_drop_pcpu_from(struct fib6_nh *nh, void *_arg) { struct fib6_nh_pcpu_arg *arg = _arg; __fib6_drop_pcpu_from(nh, arg->from, arg->table); return 0; } static void fib6_drop_pcpu_from(struct fib6_info *f6i, const struct fib6_table *table) { /* Make sure rt6_make_pcpu_route() wont add other percpu routes * while we are cleaning them here. */ f6i->fib6_destroying = 1; mb(); /* paired with the cmpxchg() in rt6_make_pcpu_route() */ if (f6i->nh) { struct fib6_nh_pcpu_arg arg = { .from = f6i, .table = table }; nexthop_for_each_fib6_nh(f6i->nh, fib6_nh_drop_pcpu_from, &arg); } else { struct fib6_nh *fib6_nh; fib6_nh = f6i->fib6_nh; __fib6_drop_pcpu_from(fib6_nh, f6i, table); } } static void fib6_purge_rt(struct fib6_info *rt, struct fib6_node *fn, struct net *net) { struct fib6_table *table = rt->fib6_table; /* Flush all cached dst in exception table */ rt6_flush_exceptions(rt); fib6_drop_pcpu_from(rt, table); if (rt->nh && !list_empty(&rt->nh_list)) list_del_init(&rt->nh_list); if (refcount_read(&rt->fib6_ref) != 1) { /* This route is used as dummy address holder in some split * nodes. It is not leaked, but it still holds other resources, * which must be released in time. So, scan ascendant nodes * and replace dummy references to this route with references * to still alive ones. */ while (fn) { struct fib6_info *leaf = rcu_dereference_protected(fn->leaf, lockdep_is_held(&table->tb6_lock)); struct fib6_info *new_leaf; if (!(fn->fn_flags & RTN_RTINFO) && leaf == rt) { new_leaf = fib6_find_prefix(net, table, fn); fib6_info_hold(new_leaf); rcu_assign_pointer(fn->leaf, new_leaf); fib6_info_release(rt); } fn = rcu_dereference_protected(fn->parent, lockdep_is_held(&table->tb6_lock)); } } fib6_clean_expires(rt); fib6_remove_gc_list(rt); } /* * Insert routing information in a node. */ static int fib6_add_rt2node(struct fib6_node *fn, struct fib6_info *rt, struct nl_info *info, struct netlink_ext_ack *extack) { struct fib6_info *leaf = rcu_dereference_protected(fn->leaf, lockdep_is_held(&rt->fib6_table->tb6_lock)); struct fib6_info *iter = NULL; struct fib6_info __rcu **ins; struct fib6_info __rcu **fallback_ins = NULL; int replace = (info->nlh && (info->nlh->nlmsg_flags & NLM_F_REPLACE)); int add = (!info->nlh || (info->nlh->nlmsg_flags & NLM_F_CREATE)); int found = 0; bool rt_can_ecmp = rt6_qualify_for_ecmp(rt); bool notify_sibling_rt = false; u16 nlflags = NLM_F_EXCL; int err; if (info->nlh && (info->nlh->nlmsg_flags & NLM_F_APPEND)) nlflags |= NLM_F_APPEND; ins = &fn->leaf; for (iter = leaf; iter; iter = rcu_dereference_protected(iter->fib6_next, lockdep_is_held(&rt->fib6_table->tb6_lock))) { /* * Search for duplicates */ if (iter->fib6_metric == rt->fib6_metric) { /* * Same priority level */ if (info->nlh && (info->nlh->nlmsg_flags & NLM_F_EXCL)) return -EEXIST; nlflags &= ~NLM_F_EXCL; if (replace) { if (rt_can_ecmp == rt6_qualify_for_ecmp(iter)) { found++; break; } fallback_ins = fallback_ins ?: ins; goto next_iter; } if (rt6_duplicate_nexthop(iter, rt)) { if (rt->fib6_nsiblings) rt->fib6_nsiblings = 0; if (!(iter->fib6_flags & RTF_EXPIRES)) return -EEXIST; if (!(rt->fib6_flags & RTF_EXPIRES)) { fib6_clean_expires(iter); fib6_remove_gc_list(iter); } else { fib6_set_expires(iter, rt->expires); fib6_add_gc_list(iter); } if (rt->fib6_pmtu) fib6_metric_set(iter, RTAX_MTU, rt->fib6_pmtu); return -EEXIST; } /* If we have the same destination and the same metric, * but not the same gateway, then the route we try to * add is sibling to this route, increment our counter * of siblings, and later we will add our route to the * list. * Only static routes (which don't have flag * RTF_EXPIRES) are used for ECMPv6. * * To avoid long list, we only had siblings if the * route have a gateway. */ if (rt_can_ecmp && rt6_qualify_for_ecmp(iter)) rt->fib6_nsiblings++; } if (iter->fib6_metric > rt->fib6_metric) break; next_iter: ins = &iter->fib6_next; } if (fallback_ins && !found) { /* No matching route with same ecmp-able-ness found, replace * first matching route */ ins = fallback_ins; iter = rcu_dereference_protected(*ins, lockdep_is_held(&rt->fib6_table->tb6_lock)); found++; } /* Reset round-robin state, if necessary */ if (ins == &fn->leaf) fn->rr_ptr = NULL; /* Link this route to others same route. */ if (rt->fib6_nsiblings) { unsigned int fib6_nsiblings; struct fib6_info *sibling, *temp_sibling; /* Find the first route that have the same metric */ sibling = leaf; notify_sibling_rt = true; while (sibling) { if (sibling->fib6_metric == rt->fib6_metric && rt6_qualify_for_ecmp(sibling)) { list_add_tail_rcu(&rt->fib6_siblings, &sibling->fib6_siblings); break; } sibling = rcu_dereference_protected(sibling->fib6_next, lockdep_is_held(&rt->fib6_table->tb6_lock)); notify_sibling_rt = false; } /* For each sibling in the list, increment the counter of * siblings. BUG() if counters does not match, list of siblings * is broken! */ fib6_nsiblings = 0; list_for_each_entry_safe(sibling, temp_sibling, &rt->fib6_siblings, fib6_siblings) { sibling->fib6_nsiblings++; BUG_ON(sibling->fib6_nsiblings != rt->fib6_nsiblings); fib6_nsiblings++; } BUG_ON(fib6_nsiblings != rt->fib6_nsiblings); rt6_multipath_rebalance(temp_sibling); } /* * insert node */ if (!replace) { if (!add) pr_warn("NLM_F_CREATE should be set when creating new route\n"); add: nlflags |= NLM_F_CREATE; /* The route should only be notified if it is the first * route in the node or if it is added as a sibling * route to the first route in the node. */ if (!info->skip_notify_kernel && (notify_sibling_rt || ins == &fn->leaf)) { enum fib_event_type fib_event; if (notify_sibling_rt) fib_event = FIB_EVENT_ENTRY_APPEND; else fib_event = FIB_EVENT_ENTRY_REPLACE; err = call_fib6_entry_notifiers(info->nl_net, fib_event, rt, extack); if (err) { struct fib6_info *sibling, *next_sibling; /* If the route has siblings, then it first * needs to be unlinked from them. */ if (!rt->fib6_nsiblings) return err; list_for_each_entry_safe(sibling, next_sibling, &rt->fib6_siblings, fib6_siblings) sibling->fib6_nsiblings--; rt->fib6_nsiblings = 0; list_del_rcu(&rt->fib6_siblings); rt6_multipath_rebalance(next_sibling); return err; } } rcu_assign_pointer(rt->fib6_next, iter); fib6_info_hold(rt); rcu_assign_pointer(rt->fib6_node, fn); rcu_assign_pointer(*ins, rt); if (!info->skip_notify) inet6_rt_notify(RTM_NEWROUTE, rt, info, nlflags); info->nl_net->ipv6.rt6_stats->fib_rt_entries++; if (!(fn->fn_flags & RTN_RTINFO)) { info->nl_net->ipv6.rt6_stats->fib_route_nodes++; fn->fn_flags |= RTN_RTINFO; } } else { int nsiblings; if (!found) { if (add) goto add; pr_warn("NLM_F_REPLACE set, but no existing node found!\n"); return -ENOENT; } if (!info->skip_notify_kernel && ins == &fn->leaf) { err = call_fib6_entry_notifiers(info->nl_net, FIB_EVENT_ENTRY_REPLACE, rt, extack); if (err) return err; } fib6_info_hold(rt); rcu_assign_pointer(rt->fib6_node, fn); rt->fib6_next = iter->fib6_next; rcu_assign_pointer(*ins, rt); if (!info->skip_notify) inet6_rt_notify(RTM_NEWROUTE, rt, info, NLM_F_REPLACE); if (!(fn->fn_flags & RTN_RTINFO)) { info->nl_net->ipv6.rt6_stats->fib_route_nodes++; fn->fn_flags |= RTN_RTINFO; } nsiblings = iter->fib6_nsiblings; iter->fib6_node = NULL; fib6_purge_rt(iter, fn, info->nl_net); if (rcu_access_pointer(fn->rr_ptr) == iter) fn->rr_ptr = NULL; fib6_info_release(iter); if (nsiblings) { /* Replacing an ECMP route, remove all siblings */ ins = &rt->fib6_next; iter = rcu_dereference_protected(*ins, lockdep_is_held(&rt->fib6_table->tb6_lock)); while (iter) { if (iter->fib6_metric > rt->fib6_metric) break; if (rt6_qualify_for_ecmp(iter)) { *ins = iter->fib6_next; iter->fib6_node = NULL; fib6_purge_rt(iter, fn, info->nl_net); if (rcu_access_pointer(fn->rr_ptr) == iter) fn->rr_ptr = NULL; fib6_info_release(iter); nsiblings--; info->nl_net->ipv6.rt6_stats->fib_rt_entries--; } else { ins = &iter->fib6_next; } iter = rcu_dereference_protected(*ins, lockdep_is_held(&rt->fib6_table->tb6_lock)); } WARN_ON(nsiblings != 0); } } return 0; } static void fib6_start_gc(struct net *net, struct fib6_info *rt) { if (!timer_pending(&net->ipv6.ip6_fib_timer) && (rt->fib6_flags & RTF_EXPIRES)) mod_timer(&net->ipv6.ip6_fib_timer, jiffies + net->ipv6.sysctl.ip6_rt_gc_interval); } void fib6_force_start_gc(struct net *net) { if (!timer_pending(&net->ipv6.ip6_fib_timer)) mod_timer(&net->ipv6.ip6_fib_timer, jiffies + net->ipv6.sysctl.ip6_rt_gc_interval); } static void __fib6_update_sernum_upto_root(struct fib6_info *rt, int sernum) { struct fib6_node *fn = rcu_dereference_protected(rt->fib6_node, lockdep_is_held(&rt->fib6_table->tb6_lock)); /* paired with smp_rmb() in fib6_get_cookie_safe() */ smp_wmb(); while (fn) { WRITE_ONCE(fn->fn_sernum, sernum); fn = rcu_dereference_protected(fn->parent, lockdep_is_held(&rt->fib6_table->tb6_lock)); } } void fib6_update_sernum_upto_root(struct net *net, struct fib6_info *rt) { __fib6_update_sernum_upto_root(rt, fib6_new_sernum(net)); } /* allow ipv4 to update sernum via ipv6_stub */ void fib6_update_sernum_stub(struct net *net, struct fib6_info *f6i) { spin_lock_bh(&f6i->fib6_table->tb6_lock); fib6_update_sernum_upto_root(net, f6i); spin_unlock_bh(&f6i->fib6_table->tb6_lock); } /* * Add routing information to the routing tree. * <destination addr>/<source addr> * with source addr info in sub-trees * Need to own table->tb6_lock */ int fib6_add(struct fib6_node *root, struct fib6_info *rt, struct nl_info *info, struct netlink_ext_ack *extack) { struct fib6_table *table = rt->fib6_table; struct fib6_node *fn; #ifdef CONFIG_IPV6_SUBTREES struct fib6_node *pn = NULL; #endif int err = -ENOMEM; int allow_create = 1; int replace_required = 0; if (info->nlh) { if (!(info->nlh->nlmsg_flags & NLM_F_CREATE)) allow_create = 0; if (info->nlh->nlmsg_flags & NLM_F_REPLACE) replace_required = 1; } if (!allow_create && !replace_required) pr_warn("RTM_NEWROUTE with no NLM_F_CREATE or NLM_F_REPLACE\n"); fn = fib6_add_1(info->nl_net, table, root, &rt->fib6_dst.addr, rt->fib6_dst.plen, offsetof(struct fib6_info, fib6_dst), allow_create, replace_required, extack); if (IS_ERR(fn)) { err = PTR_ERR(fn); fn = NULL; goto out; } #ifdef CONFIG_IPV6_SUBTREES pn = fn; if (rt->fib6_src.plen) { struct fib6_node *sn; if (!rcu_access_pointer(fn->subtree)) { struct fib6_node *sfn; /* * Create subtree. * * fn[main tree] * | * sfn[subtree root] * \ * sn[new leaf node] */ /* Create subtree root node */ sfn = node_alloc(info->nl_net); if (!sfn) goto failure; fib6_info_hold(info->nl_net->ipv6.fib6_null_entry); rcu_assign_pointer(sfn->leaf, info->nl_net->ipv6.fib6_null_entry); sfn->fn_flags = RTN_ROOT; /* Now add the first leaf node to new subtree */ sn = fib6_add_1(info->nl_net, table, sfn, &rt->fib6_src.addr, rt->fib6_src.plen, offsetof(struct fib6_info, fib6_src), allow_create, replace_required, extack); if (IS_ERR(sn)) { /* If it is failed, discard just allocated root, and then (in failure) stale node in main tree. */ node_free_immediate(info->nl_net, sfn); err = PTR_ERR(sn); goto failure; } /* Now link new subtree to main tree */ rcu_assign_pointer(sfn->parent, fn); rcu_assign_pointer(fn->subtree, sfn); } else { sn = fib6_add_1(info->nl_net, table, FIB6_SUBTREE(fn), &rt->fib6_src.addr, rt->fib6_src.plen, offsetof(struct fib6_info, fib6_src), allow_create, replace_required, extack); if (IS_ERR(sn)) { err = PTR_ERR(sn); goto failure; } } if (!rcu_access_pointer(fn->leaf)) { if (fn->fn_flags & RTN_TL_ROOT) { /* put back null_entry for root node */ rcu_assign_pointer(fn->leaf, info->nl_net->ipv6.fib6_null_entry); } else { fib6_info_hold(rt); rcu_assign_pointer(fn->leaf, rt); } } fn = sn; } #endif err = fib6_add_rt2node(fn, rt, info, extack); if (!err) { if (rt->nh) list_add(&rt->nh_list, &rt->nh->f6i_list); __fib6_update_sernum_upto_root(rt, fib6_new_sernum(info->nl_net)); if (rt->fib6_flags & RTF_EXPIRES) fib6_add_gc_list(rt); fib6_start_gc(info->nl_net, rt); } out: if (err) { #ifdef CONFIG_IPV6_SUBTREES /* * If fib6_add_1 has cleared the old leaf pointer in the * super-tree leaf node we have to find a new one for it. */ if (pn != fn) { struct fib6_info *pn_leaf = rcu_dereference_protected(pn->leaf, lockdep_is_held(&table->tb6_lock)); if (pn_leaf == rt) { pn_leaf = NULL; RCU_INIT_POINTER(pn->leaf, NULL); fib6_info_release(rt); } if (!pn_leaf && !(pn->fn_flags & RTN_RTINFO)) { pn_leaf = fib6_find_prefix(info->nl_net, table, pn); if (!pn_leaf) pn_leaf = info->nl_net->ipv6.fib6_null_entry; fib6_info_hold(pn_leaf); rcu_assign_pointer(pn->leaf, pn_leaf); } } #endif goto failure; } else if (fib6_requires_src(rt)) { fib6_routes_require_src_inc(info->nl_net); } return err; failure: /* fn->leaf could be NULL and fib6_repair_tree() needs to be called if: * 1. fn is an intermediate node and we failed to add the new * route to it in both subtree creation failure and fib6_add_rt2node() * failure case. * 2. fn is the root node in the table and we fail to add the first * default route to it. */ if (fn && (!(fn->fn_flags & (RTN_RTINFO|RTN_ROOT)) || (fn->fn_flags & RTN_TL_ROOT && !rcu_access_pointer(fn->leaf)))) fib6_repair_tree(info->nl_net, table, fn); return err; } /* * Routing tree lookup * */ struct lookup_args { int offset; /* key offset on fib6_info */ const struct in6_addr *addr; /* search key */ }; static struct fib6_node *fib6_node_lookup_1(struct fib6_node *root, struct lookup_args *args) { struct fib6_node *fn; __be32 dir; if (unlikely(args->offset == 0)) return NULL; /* * Descend on a tree */ fn = root; for (;;) { struct fib6_node *next; dir = addr_bit_set(args->addr, fn->fn_bit); next = dir ? rcu_dereference(fn->right) : rcu_dereference(fn->left); if (next) { fn = next; continue; } break; } while (fn) { struct fib6_node *subtree = FIB6_SUBTREE(fn); if (subtree || fn->fn_flags & RTN_RTINFO) { struct fib6_info *leaf = rcu_dereference(fn->leaf); struct rt6key *key; if (!leaf) goto backtrack; key = (struct rt6key *) ((u8 *)leaf + args->offset); if (ipv6_prefix_equal(&key->addr, args->addr, key->plen)) { #ifdef CONFIG_IPV6_SUBTREES if (subtree) { struct fib6_node *sfn; sfn = fib6_node_lookup_1(subtree, args + 1); if (!sfn) goto backtrack; fn = sfn; } #endif if (fn->fn_flags & RTN_RTINFO) return fn; } } backtrack: if (fn->fn_flags & RTN_ROOT) break; fn = rcu_dereference(fn->parent); } return NULL; } /* called with rcu_read_lock() held */ struct fib6_node *fib6_node_lookup(struct fib6_node *root, const struct in6_addr *daddr, const struct in6_addr *saddr) { struct fib6_node *fn; struct lookup_args args[] = { { .offset = offsetof(struct fib6_info, fib6_dst), .addr = daddr, }, #ifdef CONFIG_IPV6_SUBTREES { .offset = offsetof(struct fib6_info, fib6_src), .addr = saddr, }, #endif { .offset = 0, /* sentinel */ } }; fn = fib6_node_lookup_1(root, daddr ? args : args + 1); if (!fn || fn->fn_flags & RTN_TL_ROOT) fn = root; return fn; } /* * Get node with specified destination prefix (and source prefix, * if subtrees are used) * exact_match == true means we try to find fn with exact match of * the passed in prefix addr * exact_match == false means we try to find fn with longest prefix * match of the passed in prefix addr. This is useful for finding fn * for cached route as it will be stored in the exception table under * the node with longest prefix length. */ static struct fib6_node *fib6_locate_1(struct fib6_node *root, const struct in6_addr *addr, int plen, int offset, bool exact_match) { struct fib6_node *fn, *prev = NULL; for (fn = root; fn ; ) { struct fib6_info *leaf = rcu_dereference(fn->leaf); struct rt6key *key; /* This node is being deleted */ if (!leaf) { if (plen <= fn->fn_bit) goto out; else goto next; } key = (struct rt6key *)((u8 *)leaf + offset); /* * Prefix match */ if (plen < fn->fn_bit || !ipv6_prefix_equal(&key->addr, addr, fn->fn_bit)) goto out; if (plen == fn->fn_bit) return fn; if (fn->fn_flags & RTN_RTINFO) prev = fn; next: /* * We have more bits to go */ if (addr_bit_set(addr, fn->fn_bit)) fn = rcu_dereference(fn->right); else fn = rcu_dereference(fn->left); } out: if (exact_match) return NULL; else return prev; } struct fib6_node *fib6_locate(struct fib6_node *root, const struct in6_addr *daddr, int dst_len, const struct in6_addr *saddr, int src_len, bool exact_match) { struct fib6_node *fn; fn = fib6_locate_1(root, daddr, dst_len, offsetof(struct fib6_info, fib6_dst), exact_match); #ifdef CONFIG_IPV6_SUBTREES if (src_len) { WARN_ON(saddr == NULL); if (fn) { struct fib6_node *subtree = FIB6_SUBTREE(fn); if (subtree) { fn = fib6_locate_1(subtree, saddr, src_len, offsetof(struct fib6_info, fib6_src), exact_match); } } } #endif if (fn && fn->fn_flags & RTN_RTINFO) return fn; return NULL; } /* * Deletion * */ static struct fib6_info *fib6_find_prefix(struct net *net, struct fib6_table *table, struct fib6_node *fn) { struct fib6_node *child_left, *child_right; if (fn->fn_flags & RTN_ROOT) return net->ipv6.fib6_null_entry; while (fn) { child_left = rcu_dereference_protected(fn->left, lockdep_is_held(&table->tb6_lock)); child_right = rcu_dereference_protected(fn->right, lockdep_is_held(&table->tb6_lock)); if (child_left) return rcu_dereference_protected(child_left->leaf, lockdep_is_held(&table->tb6_lock)); if (child_right) return rcu_dereference_protected(child_right->leaf, lockdep_is_held(&table->tb6_lock)); fn = FIB6_SUBTREE(fn); } return NULL; } /* * Called to trim the tree of intermediate nodes when possible. "fn" * is the node we want to try and remove. * Need to own table->tb6_lock */ static struct fib6_node *fib6_repair_tree(struct net *net, struct fib6_table *table, struct fib6_node *fn) { int children; int nstate; struct fib6_node *child; struct fib6_walker *w; int iter = 0; /* Set fn->leaf to null_entry for root node. */ if (fn->fn_flags & RTN_TL_ROOT) { rcu_assign_pointer(fn->leaf, net->ipv6.fib6_null_entry); return fn; } for (;;) { struct fib6_node *fn_r = rcu_dereference_protected(fn->right, lockdep_is_held(&table->tb6_lock)); struct fib6_node *fn_l = rcu_dereference_protected(fn->left, lockdep_is_held(&table->tb6_lock)); struct fib6_node *pn = rcu_dereference_protected(fn->parent, lockdep_is_held(&table->tb6_lock)); struct fib6_node *pn_r = rcu_dereference_protected(pn->right, lockdep_is_held(&table->tb6_lock)); struct fib6_node *pn_l = rcu_dereference_protected(pn->left, lockdep_is_held(&table->tb6_lock)); struct fib6_info *fn_leaf = rcu_dereference_protected(fn->leaf, lockdep_is_held(&table->tb6_lock)); struct fib6_info *pn_leaf = rcu_dereference_protected(pn->leaf, lockdep_is_held(&table->tb6_lock)); struct fib6_info *new_fn_leaf; pr_debug("fixing tree: plen=%d iter=%d\n", fn->fn_bit, iter); iter++; WARN_ON(fn->fn_flags & RTN_RTINFO); WARN_ON(fn->fn_flags & RTN_TL_ROOT); WARN_ON(fn_leaf); children = 0; child = NULL; if (fn_r) { child = fn_r; children |= 1; } if (fn_l) { child = fn_l; children |= 2; } if (children == 3 || FIB6_SUBTREE(fn) #ifdef CONFIG_IPV6_SUBTREES /* Subtree root (i.e. fn) may have one child */ || (children && fn->fn_flags & RTN_ROOT) #endif ) { new_fn_leaf = fib6_find_prefix(net, table, fn); #if RT6_DEBUG >= 2 if (!new_fn_leaf) { WARN_ON(!new_fn_leaf); new_fn_leaf = net->ipv6.fib6_null_entry; } #endif fib6_info_hold(new_fn_leaf); rcu_assign_pointer(fn->leaf, new_fn_leaf); return pn; } #ifdef CONFIG_IPV6_SUBTREES if (FIB6_SUBTREE(pn) == fn) { WARN_ON(!(fn->fn_flags & RTN_ROOT)); RCU_INIT_POINTER(pn->subtree, NULL); nstate = FWS_L; } else { WARN_ON(fn->fn_flags & RTN_ROOT); #endif if (pn_r == fn) rcu_assign_pointer(pn->right, child); else if (pn_l == fn) rcu_assign_pointer(pn->left, child); #if RT6_DEBUG >= 2 else WARN_ON(1); #endif if (child) rcu_assign_pointer(child->parent, pn); nstate = FWS_R; #ifdef CONFIG_IPV6_SUBTREES } #endif read_lock(&net->ipv6.fib6_walker_lock); FOR_WALKERS(net, w) { if (!child) { if (w->node == fn) { pr_debug("W %p adjusted by delnode 1, s=%d/%d\n", w, w->state, nstate); w->node = pn; w->state = nstate; } } else { if (w->node == fn) { w->node = child; if (children&2) { pr_debug("W %p adjusted by delnode 2, s=%d\n", w, w->state); w->state = w->state >= FWS_R ? FWS_U : FWS_INIT; } else { pr_debug("W %p adjusted by delnode 2, s=%d\n", w, w->state); w->state = w->state >= FWS_C ? FWS_U : FWS_INIT; } } } } read_unlock(&net->ipv6.fib6_walker_lock); node_free(net, fn); if (pn->fn_flags & RTN_RTINFO || FIB6_SUBTREE(pn)) return pn; RCU_INIT_POINTER(pn->leaf, NULL); fib6_info_release(pn_leaf); fn = pn; } } static void fib6_del_route(struct fib6_table *table, struct fib6_node *fn, struct fib6_info __rcu **rtp, struct nl_info *info) { struct fib6_info *leaf, *replace_rt = NULL; struct fib6_walker *w; struct fib6_info *rt = rcu_dereference_protected(*rtp, lockdep_is_held(&table->tb6_lock)); struct net *net = info->nl_net; bool notify_del = false; /* If the deleted route is the first in the node and it is not part of * a multipath route, then we need to replace it with the next route * in the node, if exists. */ leaf = rcu_dereference_protected(fn->leaf, lockdep_is_held(&table->tb6_lock)); if (leaf == rt && !rt->fib6_nsiblings) { if (rcu_access_pointer(rt->fib6_next)) replace_rt = rcu_dereference_protected(rt->fib6_next, lockdep_is_held(&table->tb6_lock)); else notify_del = true; } /* Unlink it */ *rtp = rt->fib6_next; rt->fib6_node = NULL; net->ipv6.rt6_stats->fib_rt_entries--; net->ipv6.rt6_stats->fib_discarded_routes++; /* Reset round-robin state, if necessary */ if (rcu_access_pointer(fn->rr_ptr) == rt) fn->rr_ptr = NULL; /* Remove this entry from other siblings */ if (rt->fib6_nsiblings) { struct fib6_info *sibling, *next_sibling; /* The route is deleted from a multipath route. If this * multipath route is the first route in the node, then we need * to emit a delete notification. Otherwise, we need to skip * the notification. */ if (rt->fib6_metric == leaf->fib6_metric && rt6_qualify_for_ecmp(leaf)) notify_del = true; list_for_each_entry_safe(sibling, next_sibling, &rt->fib6_siblings, fib6_siblings) sibling->fib6_nsiblings--; rt->fib6_nsiblings = 0; list_del_rcu(&rt->fib6_siblings); rt6_multipath_rebalance(next_sibling); } /* Adjust walkers */ read_lock(&net->ipv6.fib6_walker_lock); FOR_WALKERS(net, w) { if (w->state == FWS_C && w->leaf == rt) { pr_debug("walker %p adjusted by delroute\n", w); w->leaf = rcu_dereference_protected(rt->fib6_next, lockdep_is_held(&table->tb6_lock)); if (!w->leaf) w->state = FWS_U; } } read_unlock(&net->ipv6.fib6_walker_lock); /* If it was last route, call fib6_repair_tree() to: * 1. For root node, put back null_entry as how the table was created. * 2. For other nodes, expunge its radix tree node. */ if (!rcu_access_pointer(fn->leaf)) { if (!(fn->fn_flags & RTN_TL_ROOT)) { fn->fn_flags &= ~RTN_RTINFO; net->ipv6.rt6_stats->fib_route_nodes--; } fn = fib6_repair_tree(net, table, fn); } fib6_purge_rt(rt, fn, net); if (!info->skip_notify_kernel) { if (notify_del) call_fib6_entry_notifiers(net, FIB_EVENT_ENTRY_DEL, rt, NULL); else if (replace_rt) call_fib6_entry_notifiers_replace(net, replace_rt); } if (!info->skip_notify) inet6_rt_notify(RTM_DELROUTE, rt, info, 0); fib6_info_release(rt); } /* Need to own table->tb6_lock */ int fib6_del(struct fib6_info *rt, struct nl_info *info) { struct net *net = info->nl_net; struct fib6_info __rcu **rtp; struct fib6_info __rcu **rtp_next; struct fib6_table *table; struct fib6_node *fn; if (rt == net->ipv6.fib6_null_entry) return -ENOENT; table = rt->fib6_table; fn = rcu_dereference_protected(rt->fib6_node, lockdep_is_held(&table->tb6_lock)); if (!fn) return -ENOENT; WARN_ON(!(fn->fn_flags & RTN_RTINFO)); /* * Walk the leaf entries looking for ourself */ for (rtp = &fn->leaf; *rtp; rtp = rtp_next) { struct fib6_info *cur = rcu_dereference_protected(*rtp, lockdep_is_held(&table->tb6_lock)); if (rt == cur) { if (fib6_requires_src(cur)) fib6_routes_require_src_dec(info->nl_net); fib6_del_route(table, fn, rtp, info); return 0; } rtp_next = &cur->fib6_next; } return -ENOENT; } /* * Tree traversal function. * * Certainly, it is not interrupt safe. * However, it is internally reenterable wrt itself and fib6_add/fib6_del. * It means, that we can modify tree during walking * and use this function for garbage collection, clone pruning, * cleaning tree when a device goes down etc. etc. * * It guarantees that every node will be traversed, * and that it will be traversed only once. * * Callback function w->func may return: * 0 -> continue walking. * positive value -> walking is suspended (used by tree dumps, * and probably by gc, if it will be split to several slices) * negative value -> terminate walking. * * The function itself returns: * 0 -> walk is complete. * >0 -> walk is incomplete (i.e. suspended) * <0 -> walk is terminated by an error. * * This function is called with tb6_lock held. */ static int fib6_walk_continue(struct fib6_walker *w) { struct fib6_node *fn, *pn, *left, *right; /* w->root should always be table->tb6_root */ WARN_ON_ONCE(!(w->root->fn_flags & RTN_TL_ROOT)); for (;;) { fn = w->node; if (!fn) return 0; switch (w->state) { #ifdef CONFIG_IPV6_SUBTREES case FWS_S: if (FIB6_SUBTREE(fn)) { w->node = FIB6_SUBTREE(fn); continue; } w->state = FWS_L; fallthrough; #endif case FWS_L: left = rcu_dereference_protected(fn->left, 1); if (left) { w->node = left; w->state = FWS_INIT; continue; } w->state = FWS_R; fallthrough; case FWS_R: right = rcu_dereference_protected(fn->right, 1); if (right) { w->node = right; w->state = FWS_INIT; continue; } w->state = FWS_C; w->leaf = rcu_dereference_protected(fn->leaf, 1); fallthrough; case FWS_C: if (w->leaf && fn->fn_flags & RTN_RTINFO) { int err; if (w->skip) { w->skip--; goto skip; } err = w->func(w); if (err) return err; w->count++; continue; } skip: w->state = FWS_U; fallthrough; case FWS_U: if (fn == w->root) return 0; pn = rcu_dereference_protected(fn->parent, 1); left = rcu_dereference_protected(pn->left, 1); right = rcu_dereference_protected(pn->right, 1); w->node = pn; #ifdef CONFIG_IPV6_SUBTREES if (FIB6_SUBTREE(pn) == fn) { WARN_ON(!(fn->fn_flags & RTN_ROOT)); w->state = FWS_L; continue; } #endif if (left == fn) { w->state = FWS_R; continue; } if (right == fn) { w->state = FWS_C; w->leaf = rcu_dereference_protected(w->node->leaf, 1); continue; } #if RT6_DEBUG >= 2 WARN_ON(1); #endif } } } static int fib6_walk(struct net *net, struct fib6_walker *w) { int res; w->state = FWS_INIT; w->node = w->root; fib6_walker_link(net, w); res = fib6_walk_continue(w); if (res <= 0) fib6_walker_unlink(net, w); return res; } static int fib6_clean_node(struct fib6_walker *w) { int res; struct fib6_info *rt; struct fib6_cleaner *c = container_of(w, struct fib6_cleaner, w); struct nl_info info = { .nl_net = c->net, .skip_notify = c->skip_notify, }; if (c->sernum != FIB6_NO_SERNUM_CHANGE && READ_ONCE(w->node->fn_sernum) != c->sernum) WRITE_ONCE(w->node->fn_sernum, c->sernum); if (!c->func) { WARN_ON_ONCE(c->sernum == FIB6_NO_SERNUM_CHANGE); w->leaf = NULL; return 0; } for_each_fib6_walker_rt(w) { res = c->func(rt, c->arg); if (res == -1) { w->leaf = rt; res = fib6_del(rt, &info); if (res) { #if RT6_DEBUG >= 2 pr_debug("%s: del failed: rt=%p@%p err=%d\n", __func__, rt, rcu_access_pointer(rt->fib6_node), res); #endif continue; } return 0; } else if (res == -2) { if (WARN_ON(!rt->fib6_nsiblings)) continue; rt = list_last_entry(&rt->fib6_siblings, struct fib6_info, fib6_siblings); continue; } WARN_ON(res != 0); } w->leaf = rt; return 0; } /* * Convenient frontend to tree walker. * * func is called on each route. * It may return -2 -> skip multipath route. * -1 -> delete this route. * 0 -> continue walking */ static void fib6_clean_tree(struct net *net, struct fib6_node *root, int (*func)(struct fib6_info *, void *arg), int sernum, void *arg, bool skip_notify) { struct fib6_cleaner c; c.w.root = root; c.w.func = fib6_clean_node; c.w.count = 0; c.w.skip = 0; c.w.skip_in_node = 0; c.func = func; c.sernum = sernum; c.arg = arg; c.net = net; c.skip_notify = skip_notify; fib6_walk(net, &c.w); } static void __fib6_clean_all(struct net *net, int (*func)(struct fib6_info *, void *), int sernum, void *arg, bool skip_notify) { struct fib6_table *table; struct hlist_head *head; unsigned int h; rcu_read_lock(); for (h = 0; h < FIB6_TABLE_HASHSZ; h++) { head = &net->ipv6.fib_table_hash[h]; hlist_for_each_entry_rcu(table, head, tb6_hlist) { spin_lock_bh(&table->tb6_lock); fib6_clean_tree(net, &table->tb6_root, func, sernum, arg, skip_notify); spin_unlock_bh(&table->tb6_lock); } } rcu_read_unlock(); } void fib6_clean_all(struct net *net, int (*func)(struct fib6_info *, void *), void *arg) { __fib6_clean_all(net, func, FIB6_NO_SERNUM_CHANGE, arg, false); } void fib6_clean_all_skip_notify(struct net *net, int (*func)(struct fib6_info *, void *), void *arg) { __fib6_clean_all(net, func, FIB6_NO_SERNUM_CHANGE, arg, true); } static void fib6_flush_trees(struct net *net) { int new_sernum = fib6_new_sernum(net); __fib6_clean_all(net, NULL, new_sernum, NULL, false); } /* * Garbage collection */ static int fib6_age(struct fib6_info *rt, struct fib6_gc_args *gc_args) { unsigned long now = jiffies; /* * check addrconf expiration here. * Routes are expired even if they are in use. */ if (rt->fib6_flags & RTF_EXPIRES && rt->expires) { if (time_after(now, rt->expires)) { pr_debug("expiring %p\n", rt); return -1; } gc_args->more++; } /* Also age clones in the exception table. * Note, that clones are aged out * only if they are not in use now. */ rt6_age_exceptions(rt, gc_args, now); return 0; } static void fib6_gc_table(struct net *net, struct fib6_table *tb6, struct fib6_gc_args *gc_args) { struct fib6_info *rt; struct hlist_node *n; struct nl_info info = { .nl_net = net, .skip_notify = false, }; hlist_for_each_entry_safe(rt, n, &tb6->tb6_gc_hlist, gc_link) if (fib6_age(rt, gc_args) == -1) fib6_del(rt, &info); } static void fib6_gc_all(struct net *net, struct fib6_gc_args *gc_args) { struct fib6_table *table; struct hlist_head *head; unsigned int h; rcu_read_lock(); for (h = 0; h < FIB6_TABLE_HASHSZ; h++) { head = &net->ipv6.fib_table_hash[h]; hlist_for_each_entry_rcu(table, head, tb6_hlist) { spin_lock_bh(&table->tb6_lock); fib6_gc_table(net, table, gc_args); spin_unlock_bh(&table->tb6_lock); } } rcu_read_unlock(); } void fib6_run_gc(unsigned long expires, struct net *net, bool force) { struct fib6_gc_args gc_args; unsigned long now; if (force) { spin_lock_bh(&net->ipv6.fib6_gc_lock); } else if (!spin_trylock_bh(&net->ipv6.fib6_gc_lock)) { mod_timer(&net->ipv6.ip6_fib_timer, jiffies + HZ); return; } gc_args.timeout = expires ? (int)expires : net->ipv6.sysctl.ip6_rt_gc_interval; gc_args.more = 0; fib6_gc_all(net, &gc_args); now = jiffies; net->ipv6.ip6_rt_last_gc = now; if (gc_args.more) mod_timer(&net->ipv6.ip6_fib_timer, round_jiffies(now + net->ipv6.sysctl.ip6_rt_gc_interval)); else del_timer(&net->ipv6.ip6_fib_timer); spin_unlock_bh(&net->ipv6.fib6_gc_lock); } static void fib6_gc_timer_cb(struct timer_list *t) { struct net *arg = from_timer(arg, t, ipv6.ip6_fib_timer); fib6_run_gc(0, arg, true); } static int __net_init fib6_net_init(struct net *net) { size_t size = sizeof(struct hlist_head) * FIB6_TABLE_HASHSZ; int err; err = fib6_notifier_init(net); if (err) return err; /* Default to 3-tuple */ net->ipv6.sysctl.multipath_hash_fields = FIB_MULTIPATH_HASH_FIELD_DEFAULT_MASK; spin_lock_init(&net->ipv6.fib6_gc_lock); rwlock_init(&net->ipv6.fib6_walker_lock); INIT_LIST_HEAD(&net->ipv6.fib6_walkers); timer_setup(&net->ipv6.ip6_fib_timer, fib6_gc_timer_cb, 0); net->ipv6.rt6_stats = kzalloc(sizeof(*net->ipv6.rt6_stats), GFP_KERNEL); if (!net->ipv6.rt6_stats) goto out_notifier; /* Avoid false sharing : Use at least a full cache line */ size = max_t(size_t, size, L1_CACHE_BYTES); net->ipv6.fib_table_hash = kzalloc(size, GFP_KERNEL); if (!net->ipv6.fib_table_hash) goto out_rt6_stats; net->ipv6.fib6_main_tbl = kzalloc(sizeof(*net->ipv6.fib6_main_tbl), GFP_KERNEL); if (!net->ipv6.fib6_main_tbl) goto out_fib_table_hash; net->ipv6.fib6_main_tbl->tb6_id = RT6_TABLE_MAIN; rcu_assign_pointer(net->ipv6.fib6_main_tbl->tb6_root.leaf, net->ipv6.fib6_null_entry); net->ipv6.fib6_main_tbl->tb6_root.fn_flags = RTN_ROOT | RTN_TL_ROOT | RTN_RTINFO; inet_peer_base_init(&net->ipv6.fib6_main_tbl->tb6_peers); INIT_HLIST_HEAD(&net->ipv6.fib6_main_tbl->tb6_gc_hlist); #ifdef CONFIG_IPV6_MULTIPLE_TABLES net->ipv6.fib6_local_tbl = kzalloc(sizeof(*net->ipv6.fib6_local_tbl), GFP_KERNEL); if (!net->ipv6.fib6_local_tbl) goto out_fib6_main_tbl; net->ipv6.fib6_local_tbl->tb6_id = RT6_TABLE_LOCAL; rcu_assign_pointer(net->ipv6.fib6_local_tbl->tb6_root.leaf, net->ipv6.fib6_null_entry); net->ipv6.fib6_local_tbl->tb6_root.fn_flags = RTN_ROOT | RTN_TL_ROOT | RTN_RTINFO; inet_peer_base_init(&net->ipv6.fib6_local_tbl->tb6_peers); INIT_HLIST_HEAD(&net->ipv6.fib6_local_tbl->tb6_gc_hlist); #endif fib6_tables_init(net); return 0; #ifdef CONFIG_IPV6_MULTIPLE_TABLES out_fib6_main_tbl: kfree(net->ipv6.fib6_main_tbl); #endif out_fib_table_hash: kfree(net->ipv6.fib_table_hash); out_rt6_stats: kfree(net->ipv6.rt6_stats); out_notifier: fib6_notifier_exit(net); return -ENOMEM; } static void fib6_net_exit(struct net *net) { unsigned int i; del_timer_sync(&net->ipv6.ip6_fib_timer); for (i = 0; i < FIB6_TABLE_HASHSZ; i++) { struct hlist_head *head = &net->ipv6.fib_table_hash[i]; struct hlist_node *tmp; struct fib6_table *tb; hlist_for_each_entry_safe(tb, tmp, head, tb6_hlist) { hlist_del(&tb->tb6_hlist); fib6_free_table(tb); } } kfree(net->ipv6.fib_table_hash); kfree(net->ipv6.rt6_stats); fib6_notifier_exit(net); } static struct pernet_operations fib6_net_ops = { .init = fib6_net_init, .exit = fib6_net_exit, }; static const struct rtnl_msg_handler fib6_rtnl_msg_handlers[] __initconst_or_module = { {.owner = THIS_MODULE, .protocol = PF_INET6, .msgtype = RTM_GETROUTE, .dumpit = inet6_dump_fib, .flags = RTNL_FLAG_DUMP_UNLOCKED | RTNL_FLAG_DUMP_SPLIT_NLM_DONE}, }; int __init fib6_init(void) { int ret = -ENOMEM; fib6_node_kmem = KMEM_CACHE(fib6_node, SLAB_HWCACHE_ALIGN | SLAB_ACCOUNT); if (!fib6_node_kmem) goto out; ret = register_pernet_subsys(&fib6_net_ops); if (ret) goto out_kmem_cache_create; ret = rtnl_register_many(fib6_rtnl_msg_handlers); if (ret) goto out_unregister_subsys; __fib6_flush_trees = fib6_flush_trees; out: return ret; out_unregister_subsys: unregister_pernet_subsys(&fib6_net_ops); out_kmem_cache_create: kmem_cache_destroy(fib6_node_kmem); goto out; } void fib6_gc_cleanup(void) { unregister_pernet_subsys(&fib6_net_ops); kmem_cache_destroy(fib6_node_kmem); } #ifdef CONFIG_PROC_FS static int ipv6_route_native_seq_show(struct seq_file *seq, void *v) { struct fib6_info *rt = v; struct ipv6_route_iter *iter = seq->private; struct fib6_nh *fib6_nh = rt->fib6_nh; unsigned int flags = rt->fib6_flags; const struct net_device *dev; if (rt->nh) fib6_nh = nexthop_fib6_nh(rt->nh); seq_printf(seq, "%pi6 %02x ", &rt->fib6_dst.addr, rt->fib6_dst.plen); #ifdef CONFIG_IPV6_SUBTREES seq_printf(seq, "%pi6 %02x ", &rt->fib6_src.addr, rt->fib6_src.plen); #else seq_puts(seq, "00000000000000000000000000000000 00 "); #endif if (fib6_nh->fib_nh_gw_family) { flags |= RTF_GATEWAY; seq_printf(seq, "%pi6", &fib6_nh->fib_nh_gw6); } else { seq_puts(seq, "00000000000000000000000000000000"); } dev = fib6_nh->fib_nh_dev; seq_printf(seq, " %08x %08x %08x %08x %8s\n", rt->fib6_metric, refcount_read(&rt->fib6_ref), 0, flags, dev ? dev->name : ""); iter->w.leaf = NULL; return 0; } static int ipv6_route_yield(struct fib6_walker *w) { struct ipv6_route_iter *iter = w->args; if (!iter->skip) return 1; do { iter->w.leaf = rcu_dereference_protected( iter->w.leaf->fib6_next, lockdep_is_held(&iter->tbl->tb6_lock)); iter->skip--; if (!iter->skip && iter->w.leaf) return 1; } while (iter->w.leaf); return 0; } static void ipv6_route_seq_setup_walk(struct ipv6_route_iter *iter, struct net *net) { memset(&iter->w, 0, sizeof(iter->w)); iter->w.func = ipv6_route_yield; iter->w.root = &iter->tbl->tb6_root; iter->w.state = FWS_INIT; iter->w.node = iter->w.root; iter->w.args = iter; iter->sernum = READ_ONCE(iter->w.root->fn_sernum); INIT_LIST_HEAD(&iter->w.lh); fib6_walker_link(net, &iter->w); } static struct fib6_table *ipv6_route_seq_next_table(struct fib6_table *tbl, struct net *net) { unsigned int h; struct hlist_node *node; if (tbl) { h = (tbl->tb6_id & (FIB6_TABLE_HASHSZ - 1)) + 1; node = rcu_dereference(hlist_next_rcu(&tbl->tb6_hlist)); } else { h = 0; node = NULL; } while (!node && h < FIB6_TABLE_HASHSZ) { node = rcu_dereference( hlist_first_rcu(&net->ipv6.fib_table_hash[h++])); } return hlist_entry_safe(node, struct fib6_table, tb6_hlist); } static void ipv6_route_check_sernum(struct ipv6_route_iter *iter) { int sernum = READ_ONCE(iter->w.root->fn_sernum); if (iter->sernum != sernum) { iter->sernum = sernum; iter->w.state = FWS_INIT; iter->w.node = iter->w.root; WARN_ON(iter->w.skip); iter->w.skip = iter->w.count; } } static void *ipv6_route_seq_next(struct seq_file *seq, void *v, loff_t *pos) { int r; struct fib6_info *n; struct net *net = seq_file_net(seq); struct ipv6_route_iter *iter = seq->private; ++(*pos); if (!v) goto iter_table; n = rcu_dereference(((struct fib6_info *)v)->fib6_next); if (n) return n; iter_table: ipv6_route_check_sernum(iter); spin_lock_bh(&iter->tbl->tb6_lock); r = fib6_walk_continue(&iter->w); spin_unlock_bh(&iter->tbl->tb6_lock); if (r > 0) { return iter->w.leaf; } else if (r < 0) { fib6_walker_unlink(net, &iter->w); return NULL; } fib6_walker_unlink(net, &iter->w); iter->tbl = ipv6_route_seq_next_table(iter->tbl, net); if (!iter->tbl) return NULL; ipv6_route_seq_setup_walk(iter, net); goto iter_table; } static void *ipv6_route_seq_start(struct seq_file *seq, loff_t *pos) __acquires(RCU) { struct net *net = seq_file_net(seq); struct ipv6_route_iter *iter = seq->private; rcu_read_lock(); iter->tbl = ipv6_route_seq_next_table(NULL, net); iter->skip = *pos; if (iter->tbl) { loff_t p = 0; ipv6_route_seq_setup_walk(iter, net); return ipv6_route_seq_next(seq, NULL, &p); } else { return NULL; } } static bool ipv6_route_iter_active(struct ipv6_route_iter *iter) { struct fib6_walker *w = &iter->w; return w->node && !(w->state == FWS_U && w->node == w->root); } static void ipv6_route_native_seq_stop(struct seq_file *seq, void *v) __releases(RCU) { struct net *net = seq_file_net(seq); struct ipv6_route_iter *iter = seq->private; if (ipv6_route_iter_active(iter)) fib6_walker_unlink(net, &iter->w); rcu_read_unlock(); } #if IS_BUILTIN(CONFIG_IPV6) && defined(CONFIG_BPF_SYSCALL) static int ipv6_route_prog_seq_show(struct bpf_prog *prog, struct bpf_iter_meta *meta, void *v) { struct bpf_iter__ipv6_route ctx; ctx.meta = meta; ctx.rt = v; return bpf_iter_run_prog(prog, &ctx); } static int ipv6_route_seq_show(struct seq_file *seq, void *v) { struct ipv6_route_iter *iter = seq->private; struct bpf_iter_meta meta; struct bpf_prog *prog; int ret; meta.seq = seq; prog = bpf_iter_get_info(&meta, false); if (!prog) return ipv6_route_native_seq_show(seq, v); ret = ipv6_route_prog_seq_show(prog, &meta, v); iter->w.leaf = NULL; return ret; } static void ipv6_route_seq_stop(struct seq_file *seq, void *v) { struct bpf_iter_meta meta; struct bpf_prog *prog; if (!v) { meta.seq = seq; prog = bpf_iter_get_info(&meta, true); if (prog) (void)ipv6_route_prog_seq_show(prog, &meta, v); } ipv6_route_native_seq_stop(seq, v); } #else static int ipv6_route_seq_show(struct seq_file *seq, void *v) { return ipv6_route_native_seq_show(seq, v); } static void ipv6_route_seq_stop(struct seq_file *seq, void *v) { ipv6_route_native_seq_stop(seq, v); } #endif const struct seq_operations ipv6_route_seq_ops = { .start = ipv6_route_seq_start, .next = ipv6_route_seq_next, .stop = ipv6_route_seq_stop, .show = ipv6_route_seq_show }; #endif /* CONFIG_PROC_FS */ |
| 54 54 116 1051 21 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 | /* SPDX-License-Identifier: GPL-2.0 */ /* thread_info.h: common low-level thread information accessors * * Copyright (C) 2002 David Howells (dhowells@redhat.com) * - Incorporating suggestions made by Linus Torvalds */ #ifndef _LINUX_THREAD_INFO_H #define _LINUX_THREAD_INFO_H #include <linux/types.h> #include <linux/limits.h> #include <linux/bug.h> #include <linux/restart_block.h> #include <linux/errno.h> #ifdef CONFIG_THREAD_INFO_IN_TASK /* * For CONFIG_THREAD_INFO_IN_TASK kernels we need <asm/current.h> for the * definition of current, but for !CONFIG_THREAD_INFO_IN_TASK kernels, * including <asm/current.h> can cause a circular dependency on some platforms. */ #include <asm/current.h> #define current_thread_info() ((struct thread_info *)current) #endif #include <linux/bitops.h> /* * For per-arch arch_within_stack_frames() implementations, defined in * asm/thread_info.h. */ enum { BAD_STACK = -1, NOT_STACK = 0, GOOD_FRAME, GOOD_STACK, }; #ifdef CONFIG_GENERIC_ENTRY enum syscall_work_bit { SYSCALL_WORK_BIT_SECCOMP, SYSCALL_WORK_BIT_SYSCALL_TRACEPOINT, SYSCALL_WORK_BIT_SYSCALL_TRACE, SYSCALL_WORK_BIT_SYSCALL_EMU, SYSCALL_WORK_BIT_SYSCALL_AUDIT, SYSCALL_WORK_BIT_SYSCALL_USER_DISPATCH, SYSCALL_WORK_BIT_SYSCALL_EXIT_TRAP, }; #define SYSCALL_WORK_SECCOMP BIT(SYSCALL_WORK_BIT_SECCOMP) #define SYSCALL_WORK_SYSCALL_TRACEPOINT BIT(SYSCALL_WORK_BIT_SYSCALL_TRACEPOINT) #define SYSCALL_WORK_SYSCALL_TRACE BIT(SYSCALL_WORK_BIT_SYSCALL_TRACE) #define SYSCALL_WORK_SYSCALL_EMU BIT(SYSCALL_WORK_BIT_SYSCALL_EMU) #define SYSCALL_WORK_SYSCALL_AUDIT BIT(SYSCALL_WORK_BIT_SYSCALL_AUDIT) #define SYSCALL_WORK_SYSCALL_USER_DISPATCH BIT(SYSCALL_WORK_BIT_SYSCALL_USER_DISPATCH) #define SYSCALL_WORK_SYSCALL_EXIT_TRAP BIT(SYSCALL_WORK_BIT_SYSCALL_EXIT_TRAP) #endif #include <asm/thread_info.h> #ifndef TIF_NEED_RESCHED_LAZY #ifdef CONFIG_ARCH_HAS_PREEMPT_LAZY #error Inconsistent PREEMPT_LAZY #endif #define TIF_NEED_RESCHED_LAZY TIF_NEED_RESCHED #define _TIF_NEED_RESCHED_LAZY _TIF_NEED_RESCHED #endif #ifdef __KERNEL__ #ifndef arch_set_restart_data #define arch_set_restart_data(restart) do { } while (0) #endif static inline long set_restart_fn(struct restart_block *restart, long (*fn)(struct restart_block *)) { restart->fn = fn; arch_set_restart_data(restart); return -ERESTART_RESTARTBLOCK; } #ifndef THREAD_ALIGN #define THREAD_ALIGN THREAD_SIZE #endif #define THREADINFO_GFP (GFP_KERNEL_ACCOUNT | __GFP_ZERO) /* * flag set/clear/test wrappers * - pass TIF_xxxx constants to these functions */ static inline void set_ti_thread_flag(struct thread_info *ti, int flag) { set_bit(flag, (unsigned long *)&ti->flags); } static inline void clear_ti_thread_flag(struct thread_info *ti, int flag) { clear_bit(flag, (unsigned long *)&ti->flags); } static inline void update_ti_thread_flag(struct thread_info *ti, int flag, bool value) { if (value) set_ti_thread_flag(ti, flag); else clear_ti_thread_flag(ti, flag); } static inline int test_and_set_ti_thread_flag(struct thread_info *ti, int flag) { return test_and_set_bit(flag, (unsigned long *)&ti->flags); } static inline int test_and_clear_ti_thread_flag(struct thread_info *ti, int flag) { return test_and_clear_bit(flag, (unsigned long *)&ti->flags); } static inline int test_ti_thread_flag(struct thread_info *ti, int flag) { return test_bit(flag, (unsigned long *)&ti->flags); } /* * This may be used in noinstr code, and needs to be __always_inline to prevent * inadvertent instrumentation. */ static __always_inline unsigned long read_ti_thread_flags(struct thread_info *ti) { return READ_ONCE(ti->flags); } #define set_thread_flag(flag) \ set_ti_thread_flag(current_thread_info(), flag) #define clear_thread_flag(flag) \ clear_ti_thread_flag(current_thread_info(), flag) #define update_thread_flag(flag, value) \ update_ti_thread_flag(current_thread_info(), flag, value) #define test_and_set_thread_flag(flag) \ test_and_set_ti_thread_flag(current_thread_info(), flag) #define test_and_clear_thread_flag(flag) \ test_and_clear_ti_thread_flag(current_thread_info(), flag) #define test_thread_flag(flag) \ test_ti_thread_flag(current_thread_info(), flag) #define read_thread_flags() \ read_ti_thread_flags(current_thread_info()) #define read_task_thread_flags(t) \ read_ti_thread_flags(task_thread_info(t)) #ifdef CONFIG_GENERIC_ENTRY #define set_syscall_work(fl) \ set_bit(SYSCALL_WORK_BIT_##fl, ¤t_thread_info()->syscall_work) #define test_syscall_work(fl) \ test_bit(SYSCALL_WORK_BIT_##fl, ¤t_thread_info()->syscall_work) #define clear_syscall_work(fl) \ clear_bit(SYSCALL_WORK_BIT_##fl, ¤t_thread_info()->syscall_work) #define set_task_syscall_work(t, fl) \ set_bit(SYSCALL_WORK_BIT_##fl, &task_thread_info(t)->syscall_work) #define test_task_syscall_work(t, fl) \ test_bit(SYSCALL_WORK_BIT_##fl, &task_thread_info(t)->syscall_work) #define clear_task_syscall_work(t, fl) \ clear_bit(SYSCALL_WORK_BIT_##fl, &task_thread_info(t)->syscall_work) #else /* CONFIG_GENERIC_ENTRY */ #define set_syscall_work(fl) \ set_ti_thread_flag(current_thread_info(), TIF_##fl) #define test_syscall_work(fl) \ test_ti_thread_flag(current_thread_info(), TIF_##fl) #define clear_syscall_work(fl) \ clear_ti_thread_flag(current_thread_info(), TIF_##fl) #define set_task_syscall_work(t, fl) \ set_ti_thread_flag(task_thread_info(t), TIF_##fl) #define test_task_syscall_work(t, fl) \ test_ti_thread_flag(task_thread_info(t), TIF_##fl) #define clear_task_syscall_work(t, fl) \ clear_ti_thread_flag(task_thread_info(t), TIF_##fl) #endif /* !CONFIG_GENERIC_ENTRY */ #ifdef _ASM_GENERIC_BITOPS_INSTRUMENTED_NON_ATOMIC_H static __always_inline bool tif_test_bit(int bit) { return arch_test_bit(bit, (unsigned long *)(¤t_thread_info()->flags)); } #else static __always_inline bool tif_test_bit(int bit) { return test_bit(bit, (unsigned long *)(¤t_thread_info()->flags)); } #endif /* _ASM_GENERIC_BITOPS_INSTRUMENTED_NON_ATOMIC_H */ static __always_inline bool tif_need_resched(void) { return tif_test_bit(TIF_NEED_RESCHED); } #ifndef CONFIG_HAVE_ARCH_WITHIN_STACK_FRAMES static inline int arch_within_stack_frames(const void * const stack, const void * const stackend, const void *obj, unsigned long len) { return 0; } #endif #ifdef CONFIG_HARDENED_USERCOPY extern void __check_object_size(const void *ptr, unsigned long n, bool to_user); static __always_inline void check_object_size(const void *ptr, unsigned long n, bool to_user) { if (!__builtin_constant_p(n)) __check_object_size(ptr, n, to_user); } #else static inline void check_object_size(const void *ptr, unsigned long n, bool to_user) { } #endif /* CONFIG_HARDENED_USERCOPY */ extern void __compiletime_error("copy source size is too small") __bad_copy_from(void); extern void __compiletime_error("copy destination size is too small") __bad_copy_to(void); void __copy_overflow(int size, unsigned long count); static inline void copy_overflow(int size, unsigned long count) { if (IS_ENABLED(CONFIG_BUG)) __copy_overflow(size, count); } static __always_inline __must_check bool check_copy_size(const void *addr, size_t bytes, bool is_source) { int sz = __builtin_object_size(addr, 0); if (unlikely(sz >= 0 && sz < bytes)) { if (!__builtin_constant_p(bytes)) copy_overflow(sz, bytes); else if (is_source) __bad_copy_from(); else __bad_copy_to(); return false; } if (WARN_ON_ONCE(bytes > INT_MAX)) return false; check_object_size(addr, bytes, is_source); return true; } #ifndef arch_setup_new_exec static inline void arch_setup_new_exec(void) { } #endif void arch_task_cache_init(void); /* for CONFIG_SH */ void arch_release_task_struct(struct task_struct *tsk); int arch_dup_task_struct(struct task_struct *dst, struct task_struct *src); #endif /* __KERNEL__ */ #endif /* _LINUX_THREAD_INFO_H */ |
| 3 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 | // SPDX-License-Identifier: GPL-2.0 /* Copyright 2011-2014 Autronica Fire and Security AS * * Author(s): * 2011-2014 Arvid Brodin, arvid.brodin@alten.se * This file contains device methods for creating, using and destroying * virtual HSR or PRP devices. */ #include <linux/netdevice.h> #include <linux/skbuff.h> #include <linux/etherdevice.h> #include <linux/rtnetlink.h> #include <linux/pkt_sched.h> #include "hsr_device.h" #include "hsr_slave.h" #include "hsr_framereg.h" #include "hsr_main.h" #include "hsr_forward.h" static bool is_admin_up(struct net_device *dev) { return dev && (dev->flags & IFF_UP); } static bool is_slave_up(struct net_device *dev) { return dev && is_admin_up(dev) && netif_oper_up(dev); } static void hsr_set_operstate(struct hsr_port *master, bool has_carrier) { struct net_device *dev = master->dev; if (!is_admin_up(dev)) { netdev_set_operstate(dev, IF_OPER_DOWN); return; } if (has_carrier) netdev_set_operstate(dev, IF_OPER_UP); else netdev_set_operstate(dev, IF_OPER_LOWERLAYERDOWN); } static bool hsr_check_carrier(struct hsr_port *master) { struct hsr_port *port; ASSERT_RTNL(); hsr_for_each_port(master->hsr, port) { if (port->type != HSR_PT_MASTER && is_slave_up(port->dev)) { netif_carrier_on(master->dev); return true; } } netif_carrier_off(master->dev); return false; } static void hsr_check_announce(struct net_device *hsr_dev) { struct hsr_priv *hsr; hsr = netdev_priv(hsr_dev); if (netif_running(hsr_dev) && netif_oper_up(hsr_dev)) { /* Enable announce timer and start sending supervisory frames */ if (!timer_pending(&hsr->announce_timer)) { hsr->announce_count = 0; mod_timer(&hsr->announce_timer, jiffies + msecs_to_jiffies(HSR_ANNOUNCE_INTERVAL)); } if (hsr->redbox && !timer_pending(&hsr->announce_proxy_timer)) mod_timer(&hsr->announce_proxy_timer, jiffies + msecs_to_jiffies(HSR_ANNOUNCE_INTERVAL) / 2); } else { /* Deactivate the announce timer */ timer_delete(&hsr->announce_timer); if (hsr->redbox) timer_delete(&hsr->announce_proxy_timer); } } void hsr_check_carrier_and_operstate(struct hsr_priv *hsr) { struct hsr_port *master; bool has_carrier; master = hsr_port_get_hsr(hsr, HSR_PT_MASTER); /* netif_stacked_transfer_operstate() cannot be used here since * it doesn't set IF_OPER_LOWERLAYERDOWN (?) */ has_carrier = hsr_check_carrier(master); hsr_set_operstate(master, has_carrier); hsr_check_announce(master->dev); } int hsr_get_max_mtu(struct hsr_priv *hsr) { unsigned int mtu_max; struct hsr_port *port; mtu_max = ETH_DATA_LEN; hsr_for_each_port(hsr, port) if (port->type != HSR_PT_MASTER) mtu_max = min(port->dev->mtu, mtu_max); if (mtu_max < HSR_HLEN) return 0; return mtu_max - HSR_HLEN; } static int hsr_dev_change_mtu(struct net_device *dev, int new_mtu) { struct hsr_priv *hsr; hsr = netdev_priv(dev); if (new_mtu > hsr_get_max_mtu(hsr)) { netdev_info(dev, "A HSR master's MTU cannot be greater than the smallest MTU of its slaves minus the HSR Tag length (%d octets).\n", HSR_HLEN); return -EINVAL; } WRITE_ONCE(dev->mtu, new_mtu); return 0; } static int hsr_dev_open(struct net_device *dev) { struct hsr_priv *hsr; struct hsr_port *port; const char *designation = NULL; hsr = netdev_priv(dev); hsr_for_each_port(hsr, port) { if (port->type == HSR_PT_MASTER) continue; switch (port->type) { case HSR_PT_SLAVE_A: designation = "Slave A"; break; case HSR_PT_SLAVE_B: designation = "Slave B"; break; case HSR_PT_INTERLINK: designation = "Interlink"; break; default: designation = "Unknown"; } if (!is_slave_up(port->dev)) netdev_warn(dev, "%s (%s) is not up; please bring it up to get a fully working HSR network\n", designation, port->dev->name); } if (!designation) netdev_warn(dev, "No slave devices configured\n"); return 0; } static int hsr_dev_close(struct net_device *dev) { struct hsr_port *port; struct hsr_priv *hsr; hsr = netdev_priv(dev); hsr_for_each_port(hsr, port) { if (port->type == HSR_PT_MASTER) continue; switch (port->type) { case HSR_PT_SLAVE_A: case HSR_PT_SLAVE_B: dev_uc_unsync(port->dev, dev); dev_mc_unsync(port->dev, dev); break; default: break; } } return 0; } static netdev_features_t hsr_features_recompute(struct hsr_priv *hsr, netdev_features_t features) { netdev_features_t mask; struct hsr_port *port; mask = features; /* Mask out all features that, if supported by one device, should be * enabled for all devices (see NETIF_F_ONE_FOR_ALL). * * Anything that's off in mask will not be enabled - so only things * that were in features originally, and also is in NETIF_F_ONE_FOR_ALL, * may become enabled. */ features &= ~NETIF_F_ONE_FOR_ALL; hsr_for_each_port(hsr, port) features = netdev_increment_features(features, port->dev->features, mask); return features; } static netdev_features_t hsr_fix_features(struct net_device *dev, netdev_features_t features) { struct hsr_priv *hsr = netdev_priv(dev); return hsr_features_recompute(hsr, features); } static netdev_tx_t hsr_dev_xmit(struct sk_buff *skb, struct net_device *dev) { struct hsr_priv *hsr = netdev_priv(dev); struct hsr_port *master; master = hsr_port_get_hsr(hsr, HSR_PT_MASTER); if (master) { skb->dev = master->dev; skb_reset_mac_header(skb); skb_reset_mac_len(skb); spin_lock_bh(&hsr->seqnr_lock); hsr_forward_skb(skb, master); spin_unlock_bh(&hsr->seqnr_lock); } else { dev_core_stats_tx_dropped_inc(dev); dev_kfree_skb_any(skb); } return NETDEV_TX_OK; } static const struct header_ops hsr_header_ops = { .create = eth_header, .parse = eth_header_parse, }; static struct sk_buff *hsr_init_skb(struct hsr_port *master, int extra) { struct hsr_priv *hsr = master->hsr; struct sk_buff *skb; int hlen, tlen; int len; hlen = LL_RESERVED_SPACE(master->dev); tlen = master->dev->needed_tailroom; len = sizeof(struct hsr_sup_tag) + sizeof(struct hsr_sup_payload); /* skb size is same for PRP/HSR frames, only difference * being, for PRP it is a trailer and for HSR it is a * header. * RedBox might use @extra more bytes. */ skb = dev_alloc_skb(len + extra + hlen + tlen); if (!skb) return skb; skb_reserve(skb, hlen); skb->dev = master->dev; skb->priority = TC_PRIO_CONTROL; skb_reset_network_header(skb); skb_reset_transport_header(skb); if (dev_hard_header(skb, skb->dev, ETH_P_PRP, hsr->sup_multicast_addr, skb->dev->dev_addr, skb->len) <= 0) goto out; skb_reset_mac_header(skb); skb_reset_mac_len(skb); return skb; out: kfree_skb(skb); return NULL; } static void send_hsr_supervision_frame(struct hsr_port *port, unsigned long *interval, const unsigned char *addr) { struct hsr_priv *hsr = port->hsr; __u8 type = HSR_TLV_LIFE_CHECK; struct hsr_sup_payload *hsr_sp; struct hsr_sup_tlv *hsr_stlv; struct hsr_sup_tag *hsr_stag; struct sk_buff *skb; int extra = 0; *interval = msecs_to_jiffies(HSR_LIFE_CHECK_INTERVAL); if (hsr->announce_count < 3 && hsr->prot_version == 0) { type = HSR_TLV_ANNOUNCE; *interval = msecs_to_jiffies(HSR_ANNOUNCE_INTERVAL); hsr->announce_count++; } if (hsr->redbox) extra = sizeof(struct hsr_sup_tlv) + sizeof(struct hsr_sup_payload); skb = hsr_init_skb(port, extra); if (!skb) { netdev_warn_once(port->dev, "HSR: Could not send supervision frame\n"); return; } hsr_stag = skb_put(skb, sizeof(struct hsr_sup_tag)); set_hsr_stag_path(hsr_stag, (hsr->prot_version ? 0x0 : 0xf)); set_hsr_stag_HSR_ver(hsr_stag, hsr->prot_version); /* From HSRv1 on we have separate supervision sequence numbers. */ spin_lock_bh(&hsr->seqnr_lock); if (hsr->prot_version > 0) { hsr_stag->sequence_nr = htons(hsr->sup_sequence_nr); hsr->sup_sequence_nr++; } else { hsr_stag->sequence_nr = htons(hsr->sequence_nr); hsr->sequence_nr++; } hsr_stag->tlv.HSR_TLV_type = type; /* TODO: Why 12 in HSRv0? */ hsr_stag->tlv.HSR_TLV_length = hsr->prot_version ? sizeof(struct hsr_sup_payload) : 12; /* Payload: MacAddressA / SAN MAC from ProxyNodeTable */ hsr_sp = skb_put(skb, sizeof(struct hsr_sup_payload)); ether_addr_copy(hsr_sp->macaddress_A, addr); if (hsr->redbox && hsr_is_node_in_db(&hsr->proxy_node_db, addr)) { hsr_stlv = skb_put(skb, sizeof(struct hsr_sup_tlv)); hsr_stlv->HSR_TLV_type = PRP_TLV_REDBOX_MAC; hsr_stlv->HSR_TLV_length = sizeof(struct hsr_sup_payload); /* Payload: MacAddressRedBox */ hsr_sp = skb_put(skb, sizeof(struct hsr_sup_payload)); ether_addr_copy(hsr_sp->macaddress_A, hsr->macaddress_redbox); } if (skb_put_padto(skb, ETH_ZLEN)) { spin_unlock_bh(&hsr->seqnr_lock); return; } hsr_forward_skb(skb, port); spin_unlock_bh(&hsr->seqnr_lock); return; } static void send_prp_supervision_frame(struct hsr_port *master, unsigned long *interval, const unsigned char *addr) { struct hsr_priv *hsr = master->hsr; struct hsr_sup_payload *hsr_sp; struct hsr_sup_tag *hsr_stag; struct sk_buff *skb; skb = hsr_init_skb(master, 0); if (!skb) { netdev_warn_once(master->dev, "PRP: Could not send supervision frame\n"); return; } *interval = msecs_to_jiffies(HSR_LIFE_CHECK_INTERVAL); hsr_stag = skb_put(skb, sizeof(struct hsr_sup_tag)); set_hsr_stag_path(hsr_stag, (hsr->prot_version ? 0x0 : 0xf)); set_hsr_stag_HSR_ver(hsr_stag, (hsr->prot_version ? 1 : 0)); /* From HSRv1 on we have separate supervision sequence numbers. */ spin_lock_bh(&hsr->seqnr_lock); hsr_stag->sequence_nr = htons(hsr->sup_sequence_nr); hsr->sup_sequence_nr++; hsr_stag->tlv.HSR_TLV_type = PRP_TLV_LIFE_CHECK_DD; hsr_stag->tlv.HSR_TLV_length = sizeof(struct hsr_sup_payload); /* Payload: MacAddressA */ hsr_sp = skb_put(skb, sizeof(struct hsr_sup_payload)); ether_addr_copy(hsr_sp->macaddress_A, master->dev->dev_addr); if (skb_put_padto(skb, ETH_ZLEN)) { spin_unlock_bh(&hsr->seqnr_lock); return; } hsr_forward_skb(skb, master); spin_unlock_bh(&hsr->seqnr_lock); } /* Announce (supervision frame) timer function */ static void hsr_announce(struct timer_list *t) { struct hsr_priv *hsr; struct hsr_port *master; unsigned long interval; hsr = from_timer(hsr, t, announce_timer); rcu_read_lock(); master = hsr_port_get_hsr(hsr, HSR_PT_MASTER); hsr->proto_ops->send_sv_frame(master, &interval, master->dev->dev_addr); if (is_admin_up(master->dev)) mod_timer(&hsr->announce_timer, jiffies + interval); rcu_read_unlock(); } /* Announce (supervision frame) timer function for RedBox */ static void hsr_proxy_announce(struct timer_list *t) { struct hsr_priv *hsr = from_timer(hsr, t, announce_proxy_timer); struct hsr_port *interlink; unsigned long interval = 0; struct hsr_node *node; rcu_read_lock(); /* RedBOX sends supervisory frames to HSR network with MAC addresses * of SAN nodes stored in ProxyNodeTable. */ interlink = hsr_port_get_hsr(hsr, HSR_PT_INTERLINK); if (!interlink) goto done; list_for_each_entry_rcu(node, &hsr->proxy_node_db, mac_list) { if (hsr_addr_is_redbox(hsr, node->macaddress_A)) continue; hsr->proto_ops->send_sv_frame(interlink, &interval, node->macaddress_A); } if (is_admin_up(interlink->dev)) { if (!interval) interval = msecs_to_jiffies(HSR_ANNOUNCE_INTERVAL); mod_timer(&hsr->announce_proxy_timer, jiffies + interval); } done: rcu_read_unlock(); } void hsr_del_ports(struct hsr_priv *hsr) { struct hsr_port *port; port = hsr_port_get_hsr(hsr, HSR_PT_SLAVE_A); if (port) hsr_del_port(port); port = hsr_port_get_hsr(hsr, HSR_PT_SLAVE_B); if (port) hsr_del_port(port); port = hsr_port_get_hsr(hsr, HSR_PT_INTERLINK); if (port) hsr_del_port(port); port = hsr_port_get_hsr(hsr, HSR_PT_MASTER); if (port) hsr_del_port(port); } static void hsr_set_rx_mode(struct net_device *dev) { struct hsr_port *port; struct hsr_priv *hsr; hsr = netdev_priv(dev); hsr_for_each_port(hsr, port) { if (port->type == HSR_PT_MASTER) continue; switch (port->type) { case HSR_PT_SLAVE_A: case HSR_PT_SLAVE_B: dev_mc_sync_multiple(port->dev, dev); dev_uc_sync_multiple(port->dev, dev); break; default: break; } } } static void hsr_change_rx_flags(struct net_device *dev, int change) { struct hsr_port *port; struct hsr_priv *hsr; hsr = netdev_priv(dev); hsr_for_each_port(hsr, port) { if (port->type == HSR_PT_MASTER) continue; switch (port->type) { case HSR_PT_SLAVE_A: case HSR_PT_SLAVE_B: if (change & IFF_ALLMULTI) dev_set_allmulti(port->dev, dev->flags & IFF_ALLMULTI ? 1 : -1); break; default: break; } } } static int hsr_ndo_vlan_rx_add_vid(struct net_device *dev, __be16 proto, u16 vid) { bool is_slave_a_added = false; bool is_slave_b_added = false; struct hsr_port *port; struct hsr_priv *hsr; int ret = 0; hsr = netdev_priv(dev); hsr_for_each_port(hsr, port) { if (port->type == HSR_PT_MASTER || port->type == HSR_PT_INTERLINK) continue; ret = vlan_vid_add(port->dev, proto, vid); switch (port->type) { case HSR_PT_SLAVE_A: if (ret) { /* clean up Slave-B */ netdev_err(dev, "add vid failed for Slave-A\n"); if (is_slave_b_added) vlan_vid_del(port->dev, proto, vid); return ret; } is_slave_a_added = true; break; case HSR_PT_SLAVE_B: if (ret) { /* clean up Slave-A */ netdev_err(dev, "add vid failed for Slave-B\n"); if (is_slave_a_added) vlan_vid_del(port->dev, proto, vid); return ret; } is_slave_b_added = true; break; default: break; } } return 0; } static int hsr_ndo_vlan_rx_kill_vid(struct net_device *dev, __be16 proto, u16 vid) { struct hsr_port *port; struct hsr_priv *hsr; hsr = netdev_priv(dev); hsr_for_each_port(hsr, port) { switch (port->type) { case HSR_PT_SLAVE_A: case HSR_PT_SLAVE_B: vlan_vid_del(port->dev, proto, vid); break; default: break; } } return 0; } static const struct net_device_ops hsr_device_ops = { .ndo_change_mtu = hsr_dev_change_mtu, .ndo_open = hsr_dev_open, .ndo_stop = hsr_dev_close, .ndo_start_xmit = hsr_dev_xmit, .ndo_change_rx_flags = hsr_change_rx_flags, .ndo_fix_features = hsr_fix_features, .ndo_set_rx_mode = hsr_set_rx_mode, .ndo_vlan_rx_add_vid = hsr_ndo_vlan_rx_add_vid, .ndo_vlan_rx_kill_vid = hsr_ndo_vlan_rx_kill_vid, }; static const struct device_type hsr_type = { .name = "hsr", }; static struct hsr_proto_ops hsr_ops = { .send_sv_frame = send_hsr_supervision_frame, .create_tagged_frame = hsr_create_tagged_frame, .get_untagged_frame = hsr_get_untagged_frame, .drop_frame = hsr_drop_frame, .fill_frame_info = hsr_fill_frame_info, .invalid_dan_ingress_frame = hsr_invalid_dan_ingress_frame, }; static struct hsr_proto_ops prp_ops = { .send_sv_frame = send_prp_supervision_frame, .create_tagged_frame = prp_create_tagged_frame, .get_untagged_frame = prp_get_untagged_frame, .drop_frame = prp_drop_frame, .fill_frame_info = prp_fill_frame_info, .handle_san_frame = prp_handle_san_frame, .update_san_info = prp_update_san_info, }; void hsr_dev_setup(struct net_device *dev) { eth_hw_addr_random(dev); ether_setup(dev); dev->min_mtu = 0; dev->header_ops = &hsr_header_ops; dev->netdev_ops = &hsr_device_ops; SET_NETDEV_DEVTYPE(dev, &hsr_type); dev->priv_flags |= IFF_NO_QUEUE | IFF_DISABLE_NETPOLL; /* Prevent recursive tx locking */ dev->lltx = true; /* Not sure about this. Taken from bridge code. netdevice.h says * it means "Does not change network namespaces". */ dev->netns_local = true; dev->needs_free_netdev = true; dev->hw_features = NETIF_F_SG | NETIF_F_FRAGLIST | NETIF_F_HIGHDMA | NETIF_F_GSO_MASK | NETIF_F_HW_CSUM | NETIF_F_HW_VLAN_CTAG_TX | NETIF_F_HW_VLAN_CTAG_FILTER; dev->features = dev->hw_features; } /* Return true if dev is a HSR master; return false otherwise. */ bool is_hsr_master(struct net_device *dev) { return (dev->netdev_ops->ndo_start_xmit == hsr_dev_xmit); } EXPORT_SYMBOL(is_hsr_master); /* Default multicast address for HSR Supervision frames */ static const unsigned char def_multicast_addr[ETH_ALEN] __aligned(2) = { 0x01, 0x15, 0x4e, 0x00, 0x01, 0x00 }; int hsr_dev_finalize(struct net_device *hsr_dev, struct net_device *slave[2], struct net_device *interlink, unsigned char multicast_spec, u8 protocol_version, struct netlink_ext_ack *extack) { bool unregister = false; struct hsr_priv *hsr; int res; hsr = netdev_priv(hsr_dev); INIT_LIST_HEAD(&hsr->ports); INIT_LIST_HEAD(&hsr->node_db); INIT_LIST_HEAD(&hsr->proxy_node_db); spin_lock_init(&hsr->list_lock); eth_hw_addr_set(hsr_dev, slave[0]->dev_addr); /* initialize protocol specific functions */ if (protocol_version == PRP_V1) { /* For PRP, lan_id has most significant 3 bits holding * the net_id of PRP_LAN_ID */ hsr->net_id = PRP_LAN_ID << 1; hsr->proto_ops = &prp_ops; } else { hsr->proto_ops = &hsr_ops; } /* Make sure we recognize frames from ourselves in hsr_rcv() */ res = hsr_create_self_node(hsr, hsr_dev->dev_addr, slave[1]->dev_addr); if (res < 0) return res; spin_lock_init(&hsr->seqnr_lock); /* Overflow soon to find bugs easier: */ hsr->sequence_nr = HSR_SEQNR_START; hsr->sup_sequence_nr = HSR_SUP_SEQNR_START; timer_setup(&hsr->announce_timer, hsr_announce, 0); timer_setup(&hsr->prune_timer, hsr_prune_nodes, 0); timer_setup(&hsr->prune_proxy_timer, hsr_prune_proxy_nodes, 0); timer_setup(&hsr->announce_proxy_timer, hsr_proxy_announce, 0); ether_addr_copy(hsr->sup_multicast_addr, def_multicast_addr); hsr->sup_multicast_addr[ETH_ALEN - 1] = multicast_spec; hsr->prot_version = protocol_version; /* Make sure the 1st call to netif_carrier_on() gets through */ netif_carrier_off(hsr_dev); res = hsr_add_port(hsr, hsr_dev, HSR_PT_MASTER, extack); if (res) goto err_add_master; /* HSR forwarding offload supported in lower device? */ if ((slave[0]->features & NETIF_F_HW_HSR_FWD) && (slave[1]->features & NETIF_F_HW_HSR_FWD)) hsr->fwd_offloaded = true; if ((slave[0]->features & NETIF_F_HW_VLAN_CTAG_FILTER) && (slave[1]->features & NETIF_F_HW_VLAN_CTAG_FILTER)) hsr_dev->features |= NETIF_F_HW_VLAN_CTAG_FILTER; res = register_netdevice(hsr_dev); if (res) goto err_unregister; unregister = true; res = hsr_add_port(hsr, slave[0], HSR_PT_SLAVE_A, extack); if (res) goto err_unregister; res = hsr_add_port(hsr, slave[1], HSR_PT_SLAVE_B, extack); if (res) goto err_unregister; if (interlink) { res = hsr_add_port(hsr, interlink, HSR_PT_INTERLINK, extack); if (res) goto err_unregister; hsr->redbox = true; ether_addr_copy(hsr->macaddress_redbox, interlink->dev_addr); mod_timer(&hsr->prune_proxy_timer, jiffies + msecs_to_jiffies(PRUNE_PROXY_PERIOD)); } hsr_debugfs_init(hsr, hsr_dev); mod_timer(&hsr->prune_timer, jiffies + msecs_to_jiffies(PRUNE_PERIOD)); return 0; err_unregister: hsr_del_ports(hsr); err_add_master: hsr_del_self_node(hsr); if (unregister) unregister_netdevice(hsr_dev); return res; } |
| 3 3 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 | // SPDX-License-Identifier: (GPL-2.0 OR BSD-3-Clause) /* raw.c - Raw sockets for protocol family CAN * * Copyright (c) 2002-2007 Volkswagen Group Electronic Research * All rights reserved. * * Redistribution and use in source and binary forms, with or without * modification, are permitted provided that the following conditions * are met: * 1. Redistributions of source code must retain the above copyright * notice, this list of conditions and the following disclaimer. * 2. Redistributions in binary form must reproduce the above copyright * notice, this list of conditions and the following disclaimer in the * documentation and/or other materials provided with the distribution. * 3. Neither the name of Volkswagen nor the names of its contributors * may be used to endorse or promote products derived from this software * without specific prior written permission. * * Alternatively, provided that this notice is retained in full, this * software may be distributed under the terms of the GNU General * Public License ("GPL") version 2, in which case the provisions of the * GPL apply INSTEAD OF those given above. * * The provided data structures and external interfaces from this code * are not restricted to be used by modules with a GPL compatible license. * * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS * "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT * LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR * A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT * OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, * SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT * LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, * DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY * THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT * (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE * OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH * DAMAGE. * */ #include <linux/module.h> #include <linux/init.h> #include <linux/uio.h> #include <linux/net.h> #include <linux/slab.h> #include <linux/netdevice.h> #include <linux/socket.h> #include <linux/if_arp.h> #include <linux/skbuff.h> #include <linux/can.h> #include <linux/can/core.h> #include <linux/can/dev.h> /* for can_is_canxl_dev_mtu() */ #include <linux/can/skb.h> #include <linux/can/raw.h> #include <net/sock.h> #include <net/net_namespace.h> MODULE_DESCRIPTION("PF_CAN raw protocol"); MODULE_LICENSE("Dual BSD/GPL"); MODULE_AUTHOR("Urs Thuermann <urs.thuermann@volkswagen.de>"); MODULE_ALIAS("can-proto-1"); #define RAW_MIN_NAMELEN CAN_REQUIRED_SIZE(struct sockaddr_can, can_ifindex) #define MASK_ALL 0 /* A raw socket has a list of can_filters attached to it, each receiving * the CAN frames matching that filter. If the filter list is empty, * no CAN frames will be received by the socket. The default after * opening the socket, is to have one filter which receives all frames. * The filter list is allocated dynamically with the exception of the * list containing only one item. This common case is optimized by * storing the single filter in dfilter, to avoid using dynamic memory. */ struct uniqframe { int skbcnt; const struct sk_buff *skb; unsigned int join_rx_count; }; struct raw_sock { struct sock sk; int bound; int ifindex; struct net_device *dev; netdevice_tracker dev_tracker; struct list_head notifier; int loopback; int recv_own_msgs; int fd_frames; int xl_frames; struct can_raw_vcid_options raw_vcid_opts; canid_t tx_vcid_shifted; canid_t rx_vcid_shifted; canid_t rx_vcid_mask_shifted; int join_filters; int count; /* number of active filters */ struct can_filter dfilter; /* default/single filter */ struct can_filter *filter; /* pointer to filter(s) */ can_err_mask_t err_mask; struct uniqframe __percpu *uniq; }; static LIST_HEAD(raw_notifier_list); static DEFINE_SPINLOCK(raw_notifier_lock); static struct raw_sock *raw_busy_notifier; /* Return pointer to store the extra msg flags for raw_recvmsg(). * We use the space of one unsigned int beyond the 'struct sockaddr_can' * in skb->cb. */ static inline unsigned int *raw_flags(struct sk_buff *skb) { sock_skb_cb_check_size(sizeof(struct sockaddr_can) + sizeof(unsigned int)); /* return pointer after struct sockaddr_can */ return (unsigned int *)(&((struct sockaddr_can *)skb->cb)[1]); } static inline struct raw_sock *raw_sk(const struct sock *sk) { return (struct raw_sock *)sk; } static void raw_rcv(struct sk_buff *oskb, void *data) { struct sock *sk = (struct sock *)data; struct raw_sock *ro = raw_sk(sk); struct sockaddr_can *addr; struct sk_buff *skb; unsigned int *pflags; /* check the received tx sock reference */ if (!ro->recv_own_msgs && oskb->sk == sk) return; /* make sure to not pass oversized frames to the socket */ if (!ro->fd_frames && can_is_canfd_skb(oskb)) return; if (can_is_canxl_skb(oskb)) { struct canxl_frame *cxl = (struct canxl_frame *)oskb->data; /* make sure to not pass oversized frames to the socket */ if (!ro->xl_frames) return; /* filter CAN XL VCID content */ if (ro->raw_vcid_opts.flags & CAN_RAW_XL_VCID_RX_FILTER) { /* apply VCID filter if user enabled the filter */ if ((cxl->prio & ro->rx_vcid_mask_shifted) != (ro->rx_vcid_shifted & ro->rx_vcid_mask_shifted)) return; } else { /* no filter => do not forward VCID tagged frames */ if (cxl->prio & CANXL_VCID_MASK) return; } } /* eliminate multiple filter matches for the same skb */ if (this_cpu_ptr(ro->uniq)->skb == oskb && this_cpu_ptr(ro->uniq)->skbcnt == can_skb_prv(oskb)->skbcnt) { if (!ro->join_filters) return; this_cpu_inc(ro->uniq->join_rx_count); /* drop frame until all enabled filters matched */ if (this_cpu_ptr(ro->uniq)->join_rx_count < ro->count) return; } else { this_cpu_ptr(ro->uniq)->skb = oskb; this_cpu_ptr(ro->uniq)->skbcnt = can_skb_prv(oskb)->skbcnt; this_cpu_ptr(ro->uniq)->join_rx_count = 1; /* drop first frame to check all enabled filters? */ if (ro->join_filters && ro->count > 1) return; } /* clone the given skb to be able to enqueue it into the rcv queue */ skb = skb_clone(oskb, GFP_ATOMIC); if (!skb) return; /* Put the datagram to the queue so that raw_recvmsg() can get * it from there. We need to pass the interface index to * raw_recvmsg(). We pass a whole struct sockaddr_can in * skb->cb containing the interface index. */ sock_skb_cb_check_size(sizeof(struct sockaddr_can)); addr = (struct sockaddr_can *)skb->cb; memset(addr, 0, sizeof(*addr)); addr->can_family = AF_CAN; addr->can_ifindex = skb->dev->ifindex; /* add CAN specific message flags for raw_recvmsg() */ pflags = raw_flags(skb); *pflags = 0; if (oskb->sk) *pflags |= MSG_DONTROUTE; if (oskb->sk == sk) *pflags |= MSG_CONFIRM; if (sock_queue_rcv_skb(sk, skb) < 0) kfree_skb(skb); } static int raw_enable_filters(struct net *net, struct net_device *dev, struct sock *sk, struct can_filter *filter, int count) { int err = 0; int i; for (i = 0; i < count; i++) { err = can_rx_register(net, dev, filter[i].can_id, filter[i].can_mask, raw_rcv, sk, "raw", sk); if (err) { /* clean up successfully registered filters */ while (--i >= 0) can_rx_unregister(net, dev, filter[i].can_id, filter[i].can_mask, raw_rcv, sk); break; } } return err; } static int raw_enable_errfilter(struct net *net, struct net_device *dev, struct sock *sk, can_err_mask_t err_mask) { int err = 0; if (err_mask) err = can_rx_register(net, dev, 0, err_mask | CAN_ERR_FLAG, raw_rcv, sk, "raw", sk); return err; } static void raw_disable_filters(struct net *net, struct net_device *dev, struct sock *sk, struct can_filter *filter, int count) { int i; for (i = 0; i < count; i++) can_rx_unregister(net, dev, filter[i].can_id, filter[i].can_mask, raw_rcv, sk); } static inline void raw_disable_errfilter(struct net *net, struct net_device *dev, struct sock *sk, can_err_mask_t err_mask) { if (err_mask) can_rx_unregister(net, dev, 0, err_mask | CAN_ERR_FLAG, raw_rcv, sk); } static inline void raw_disable_allfilters(struct net *net, struct net_device *dev, struct sock *sk) { struct raw_sock *ro = raw_sk(sk); raw_disable_filters(net, dev, sk, ro->filter, ro->count); raw_disable_errfilter(net, dev, sk, ro->err_mask); } static int raw_enable_allfilters(struct net *net, struct net_device *dev, struct sock *sk) { struct raw_sock *ro = raw_sk(sk); int err; err = raw_enable_filters(net, dev, sk, ro->filter, ro->count); if (!err) { err = raw_enable_errfilter(net, dev, sk, ro->err_mask); if (err) raw_disable_filters(net, dev, sk, ro->filter, ro->count); } return err; } static void raw_notify(struct raw_sock *ro, unsigned long msg, struct net_device *dev) { struct sock *sk = &ro->sk; if (!net_eq(dev_net(dev), sock_net(sk))) return; if (ro->dev != dev) return; switch (msg) { case NETDEV_UNREGISTER: lock_sock(sk); /* remove current filters & unregister */ if (ro->bound) { raw_disable_allfilters(dev_net(dev), dev, sk); netdev_put(dev, &ro->dev_tracker); } if (ro->count > 1) kfree(ro->filter); ro->ifindex = 0; ro->bound = 0; ro->dev = NULL; ro->count = 0; release_sock(sk); sk->sk_err = ENODEV; if (!sock_flag(sk, SOCK_DEAD)) sk_error_report(sk); break; case NETDEV_DOWN: sk->sk_err = ENETDOWN; if (!sock_flag(sk, SOCK_DEAD)) sk_error_report(sk); break; } } static int raw_notifier(struct notifier_block *nb, unsigned long msg, void *ptr) { struct net_device *dev = netdev_notifier_info_to_dev(ptr); if (dev->type != ARPHRD_CAN) return NOTIFY_DONE; if (msg != NETDEV_UNREGISTER && msg != NETDEV_DOWN) return NOTIFY_DONE; if (unlikely(raw_busy_notifier)) /* Check for reentrant bug. */ return NOTIFY_DONE; spin_lock(&raw_notifier_lock); list_for_each_entry(raw_busy_notifier, &raw_notifier_list, notifier) { spin_unlock(&raw_notifier_lock); raw_notify(raw_busy_notifier, msg, dev); spin_lock(&raw_notifier_lock); } raw_busy_notifier = NULL; spin_unlock(&raw_notifier_lock); return NOTIFY_DONE; } static int raw_init(struct sock *sk) { struct raw_sock *ro = raw_sk(sk); ro->bound = 0; ro->ifindex = 0; ro->dev = NULL; /* set default filter to single entry dfilter */ ro->dfilter.can_id = 0; ro->dfilter.can_mask = MASK_ALL; ro->filter = &ro->dfilter; ro->count = 1; /* set default loopback behaviour */ ro->loopback = 1; ro->recv_own_msgs = 0; ro->fd_frames = 0; ro->xl_frames = 0; ro->join_filters = 0; /* alloc_percpu provides zero'ed memory */ ro->uniq = alloc_percpu(struct uniqframe); if (unlikely(!ro->uniq)) return -ENOMEM; /* set notifier */ spin_lock(&raw_notifier_lock); list_add_tail(&ro->notifier, &raw_notifier_list); spin_unlock(&raw_notifier_lock); return 0; } static int raw_release(struct socket *sock) { struct sock *sk = sock->sk; struct raw_sock *ro; if (!sk) return 0; ro = raw_sk(sk); spin_lock(&raw_notifier_lock); while (raw_busy_notifier == ro) { spin_unlock(&raw_notifier_lock); schedule_timeout_uninterruptible(1); spin_lock(&raw_notifier_lock); } list_del(&ro->notifier); spin_unlock(&raw_notifier_lock); rtnl_lock(); lock_sock(sk); /* remove current filters & unregister */ if (ro->bound) { if (ro->dev) { raw_disable_allfilters(dev_net(ro->dev), ro->dev, sk); netdev_put(ro->dev, &ro->dev_tracker); } else { raw_disable_allfilters(sock_net(sk), NULL, sk); } } if (ro->count > 1) kfree(ro->filter); ro->ifindex = 0; ro->bound = 0; ro->dev = NULL; ro->count = 0; free_percpu(ro->uniq); sock_orphan(sk); sock->sk = NULL; release_sock(sk); rtnl_unlock(); sock_put(sk); return 0; } static int raw_bind(struct socket *sock, struct sockaddr *uaddr, int len) { struct sockaddr_can *addr = (struct sockaddr_can *)uaddr; struct sock *sk = sock->sk; struct raw_sock *ro = raw_sk(sk); struct net_device *dev = NULL; int ifindex; int err = 0; int notify_enetdown = 0; if (len < RAW_MIN_NAMELEN) return -EINVAL; if (addr->can_family != AF_CAN) return -EINVAL; rtnl_lock(); lock_sock(sk); if (ro->bound && addr->can_ifindex == ro->ifindex) goto out; if (addr->can_ifindex) { dev = dev_get_by_index(sock_net(sk), addr->can_ifindex); if (!dev) { err = -ENODEV; goto out; } if (dev->type != ARPHRD_CAN) { err = -ENODEV; goto out_put_dev; } if (!(dev->flags & IFF_UP)) notify_enetdown = 1; ifindex = dev->ifindex; /* filters set by default/setsockopt */ err = raw_enable_allfilters(sock_net(sk), dev, sk); if (err) goto out_put_dev; } else { ifindex = 0; /* filters set by default/setsockopt */ err = raw_enable_allfilters(sock_net(sk), NULL, sk); } if (!err) { if (ro->bound) { /* unregister old filters */ if (ro->dev) { raw_disable_allfilters(dev_net(ro->dev), ro->dev, sk); /* drop reference to old ro->dev */ netdev_put(ro->dev, &ro->dev_tracker); } else { raw_disable_allfilters(sock_net(sk), NULL, sk); } } ro->ifindex = ifindex; ro->bound = 1; /* bind() ok -> hold a reference for new ro->dev */ ro->dev = dev; if (ro->dev) netdev_hold(ro->dev, &ro->dev_tracker, GFP_KERNEL); } out_put_dev: /* remove potential reference from dev_get_by_index() */ dev_put(dev); out: release_sock(sk); rtnl_unlock(); if (notify_enetdown) { sk->sk_err = ENETDOWN; if (!sock_flag(sk, SOCK_DEAD)) sk_error_report(sk); } return err; } static int raw_getname(struct socket *sock, struct sockaddr *uaddr, int peer) { struct sockaddr_can *addr = (struct sockaddr_can *)uaddr; struct sock *sk = sock->sk; struct raw_sock *ro = raw_sk(sk); if (peer) return -EOPNOTSUPP; memset(addr, 0, RAW_MIN_NAMELEN); addr->can_family = AF_CAN; addr->can_ifindex = ro->ifindex; return RAW_MIN_NAMELEN; } static int raw_setsockopt(struct socket *sock, int level, int optname, sockptr_t optval, unsigned int optlen) { struct sock *sk = sock->sk; struct raw_sock *ro = raw_sk(sk); struct can_filter *filter = NULL; /* dyn. alloc'ed filters */ struct can_filter sfilter; /* single filter */ struct net_device *dev = NULL; can_err_mask_t err_mask = 0; int fd_frames; int count = 0; int err = 0; if (level != SOL_CAN_RAW) return -EINVAL; switch (optname) { case CAN_RAW_FILTER: if (optlen % sizeof(struct can_filter) != 0) return -EINVAL; if (optlen > CAN_RAW_FILTER_MAX * sizeof(struct can_filter)) return -EINVAL; count = optlen / sizeof(struct can_filter); if (count > 1) { /* filter does not fit into dfilter => alloc space */ filter = memdup_sockptr(optval, optlen); if (IS_ERR(filter)) return PTR_ERR(filter); } else if (count == 1) { if (copy_from_sockptr(&sfilter, optval, sizeof(sfilter))) return -EFAULT; } rtnl_lock(); lock_sock(sk); dev = ro->dev; if (ro->bound && dev) { if (dev->reg_state != NETREG_REGISTERED) { if (count > 1) kfree(filter); err = -ENODEV; goto out_fil; } } if (ro->bound) { /* (try to) register the new filters */ if (count == 1) err = raw_enable_filters(sock_net(sk), dev, sk, &sfilter, 1); else err = raw_enable_filters(sock_net(sk), dev, sk, filter, count); if (err) { if (count > 1) kfree(filter); goto out_fil; } /* remove old filter registrations */ raw_disable_filters(sock_net(sk), dev, sk, ro->filter, ro->count); } /* remove old filter space */ if (ro->count > 1) kfree(ro->filter); /* link new filters to the socket */ if (count == 1) { /* copy filter data for single filter */ ro->dfilter = sfilter; filter = &ro->dfilter; } ro->filter = filter; ro->count = count; out_fil: release_sock(sk); rtnl_unlock(); break; case CAN_RAW_ERR_FILTER: if (optlen != sizeof(err_mask)) return -EINVAL; if (copy_from_sockptr(&err_mask, optval, optlen)) return -EFAULT; err_mask &= CAN_ERR_MASK; rtnl_lock(); lock_sock(sk); dev = ro->dev; if (ro->bound && dev) { if (dev->reg_state != NETREG_REGISTERED) { err = -ENODEV; goto out_err; } } /* remove current error mask */ if (ro->bound) { /* (try to) register the new err_mask */ err = raw_enable_errfilter(sock_net(sk), dev, sk, err_mask); if (err) goto out_err; /* remove old err_mask registration */ raw_disable_errfilter(sock_net(sk), dev, sk, ro->err_mask); } /* link new err_mask to the socket */ ro->err_mask = err_mask; out_err: release_sock(sk); rtnl_unlock(); break; case CAN_RAW_LOOPBACK: if (optlen != sizeof(ro->loopback)) return -EINVAL; if (copy_from_sockptr(&ro->loopback, optval, optlen)) return -EFAULT; break; case CAN_RAW_RECV_OWN_MSGS: if (optlen != sizeof(ro->recv_own_msgs)) return -EINVAL; if (copy_from_sockptr(&ro->recv_own_msgs, optval, optlen)) return -EFAULT; break; case CAN_RAW_FD_FRAMES: if (optlen != sizeof(fd_frames)) return -EINVAL; if (copy_from_sockptr(&fd_frames, optval, optlen)) return -EFAULT; /* Enabling CAN XL includes CAN FD */ if (ro->xl_frames && !fd_frames) return -EINVAL; ro->fd_frames = fd_frames; break; case CAN_RAW_XL_FRAMES: if (optlen != sizeof(ro->xl_frames)) return -EINVAL; if (copy_from_sockptr(&ro->xl_frames, optval, optlen)) return -EFAULT; /* Enabling CAN XL includes CAN FD */ if (ro->xl_frames) ro->fd_frames = ro->xl_frames; break; case CAN_RAW_XL_VCID_OPTS: if (optlen != sizeof(ro->raw_vcid_opts)) return -EINVAL; if (copy_from_sockptr(&ro->raw_vcid_opts, optval, optlen)) return -EFAULT; /* prepare 32 bit values for handling in hot path */ ro->tx_vcid_shifted = ro->raw_vcid_opts.tx_vcid << CANXL_VCID_OFFSET; ro->rx_vcid_shifted = ro->raw_vcid_opts.rx_vcid << CANXL_VCID_OFFSET; ro->rx_vcid_mask_shifted = ro->raw_vcid_opts.rx_vcid_mask << CANXL_VCID_OFFSET; break; case CAN_RAW_JOIN_FILTERS: if (optlen != sizeof(ro->join_filters)) return -EINVAL; if (copy_from_sockptr(&ro->join_filters, optval, optlen)) return -EFAULT; break; default: return -ENOPROTOOPT; } return err; } static int raw_getsockopt(struct socket *sock, int level, int optname, char __user *optval, int __user *optlen) { struct sock *sk = sock->sk; struct raw_sock *ro = raw_sk(sk); int len; void *val; if (level != SOL_CAN_RAW) return -EINVAL; if (get_user(len, optlen)) return -EFAULT; if (len < 0) return -EINVAL; switch (optname) { case CAN_RAW_FILTER: { int err = 0; lock_sock(sk); if (ro->count > 0) { int fsize = ro->count * sizeof(struct can_filter); /* user space buffer to small for filter list? */ if (len < fsize) { /* return -ERANGE and needed space in optlen */ err = -ERANGE; if (put_user(fsize, optlen)) err = -EFAULT; } else { if (len > fsize) len = fsize; if (copy_to_user(optval, ro->filter, len)) err = -EFAULT; } } else { len = 0; } release_sock(sk); if (!err) err = put_user(len, optlen); return err; } case CAN_RAW_ERR_FILTER: if (len > sizeof(can_err_mask_t)) len = sizeof(can_err_mask_t); val = &ro->err_mask; break; case CAN_RAW_LOOPBACK: if (len > sizeof(int)) len = sizeof(int); val = &ro->loopback; break; case CAN_RAW_RECV_OWN_MSGS: if (len > sizeof(int)) len = sizeof(int); val = &ro->recv_own_msgs; break; case CAN_RAW_FD_FRAMES: if (len > sizeof(int)) len = sizeof(int); val = &ro->fd_frames; break; case CAN_RAW_XL_FRAMES: if (len > sizeof(int)) len = sizeof(int); val = &ro->xl_frames; break; case CAN_RAW_XL_VCID_OPTS: { int err = 0; /* user space buffer to small for VCID opts? */ if (len < sizeof(ro->raw_vcid_opts)) { /* return -ERANGE and needed space in optlen */ err = -ERANGE; if (put_user(sizeof(ro->raw_vcid_opts), optlen)) err = -EFAULT; } else { if (len > sizeof(ro->raw_vcid_opts)) len = sizeof(ro->raw_vcid_opts); if (copy_to_user(optval, &ro->raw_vcid_opts, len)) err = -EFAULT; } if (!err) err = put_user(len, optlen); return err; } case CAN_RAW_JOIN_FILTERS: if (len > sizeof(int)) len = sizeof(int); val = &ro->join_filters; break; default: return -ENOPROTOOPT; } if (put_user(len, optlen)) return -EFAULT; if (copy_to_user(optval, val, len)) return -EFAULT; return 0; } static void raw_put_canxl_vcid(struct raw_sock *ro, struct sk_buff *skb) { struct canxl_frame *cxl = (struct canxl_frame *)skb->data; /* sanitize non CAN XL bits */ cxl->prio &= (CANXL_PRIO_MASK | CANXL_VCID_MASK); /* clear VCID in CAN XL frame if pass through is disabled */ if (!(ro->raw_vcid_opts.flags & CAN_RAW_XL_VCID_TX_PASS)) cxl->prio &= CANXL_PRIO_MASK; /* set VCID in CAN XL frame if enabled */ if (ro->raw_vcid_opts.flags & CAN_RAW_XL_VCID_TX_SET) { cxl->prio &= CANXL_PRIO_MASK; cxl->prio |= ro->tx_vcid_shifted; } } static unsigned int raw_check_txframe(struct raw_sock *ro, struct sk_buff *skb, int mtu) { /* Classical CAN -> no checks for flags and device capabilities */ if (can_is_can_skb(skb)) return CAN_MTU; /* CAN FD -> needs to be enabled and a CAN FD or CAN XL device */ if (ro->fd_frames && can_is_canfd_skb(skb) && (mtu == CANFD_MTU || can_is_canxl_dev_mtu(mtu))) return CANFD_MTU; /* CAN XL -> needs to be enabled and a CAN XL device */ if (ro->xl_frames && can_is_canxl_skb(skb) && can_is_canxl_dev_mtu(mtu)) return CANXL_MTU; return 0; } static int raw_sendmsg(struct socket *sock, struct msghdr *msg, size_t size) { struct sock *sk = sock->sk; struct raw_sock *ro = raw_sk(sk); struct sockcm_cookie sockc; struct sk_buff *skb; struct net_device *dev; unsigned int txmtu; int ifindex; int err = -EINVAL; /* check for valid CAN frame sizes */ if (size < CANXL_HDR_SIZE + CANXL_MIN_DLEN || size > CANXL_MTU) return -EINVAL; if (msg->msg_name) { DECLARE_SOCKADDR(struct sockaddr_can *, addr, msg->msg_name); if (msg->msg_namelen < RAW_MIN_NAMELEN) return -EINVAL; if (addr->can_family != AF_CAN) return -EINVAL; ifindex = addr->can_ifindex; } else { ifindex = ro->ifindex; } dev = dev_get_by_index(sock_net(sk), ifindex); if (!dev) return -ENXIO; skb = sock_alloc_send_skb(sk, size + sizeof(struct can_skb_priv), msg->msg_flags & MSG_DONTWAIT, &err); if (!skb) goto put_dev; can_skb_reserve(skb); can_skb_prv(skb)->ifindex = dev->ifindex; can_skb_prv(skb)->skbcnt = 0; /* fill the skb before testing for valid CAN frames */ err = memcpy_from_msg(skb_put(skb, size), msg, size); if (err < 0) goto free_skb; err = -EINVAL; /* check for valid CAN (CC/FD/XL) frame content */ txmtu = raw_check_txframe(ro, skb, dev->mtu); if (!txmtu) goto free_skb; /* only CANXL: clear/forward/set VCID value */ if (txmtu == CANXL_MTU) raw_put_canxl_vcid(ro, skb); sockcm_init(&sockc, sk); if (msg->msg_controllen) { err = sock_cmsg_send(sk, msg, &sockc); if (unlikely(err)) goto free_skb; } skb->dev = dev; skb->priority = READ_ONCE(sk->sk_priority); skb->mark = READ_ONCE(sk->sk_mark); skb->tstamp = sockc.transmit_time; skb_setup_tx_timestamp(skb, &sockc); err = can_send(skb, ro->loopback); dev_put(dev); if (err) goto send_failed; return size; free_skb: kfree_skb(skb); put_dev: dev_put(dev); send_failed: return err; } static int raw_recvmsg(struct socket *sock, struct msghdr *msg, size_t size, int flags) { struct sock *sk = sock->sk; struct sk_buff *skb; int err = 0; if (flags & MSG_ERRQUEUE) return sock_recv_errqueue(sk, msg, size, SOL_CAN_RAW, SCM_CAN_RAW_ERRQUEUE); skb = skb_recv_datagram(sk, flags, &err); if (!skb) return err; if (size < skb->len) msg->msg_flags |= MSG_TRUNC; else size = skb->len; err = memcpy_to_msg(msg, skb->data, size); if (err < 0) { skb_free_datagram(sk, skb); return err; } sock_recv_cmsgs(msg, sk, skb); if (msg->msg_name) { __sockaddr_check_size(RAW_MIN_NAMELEN); msg->msg_namelen = RAW_MIN_NAMELEN; memcpy(msg->msg_name, skb->cb, msg->msg_namelen); } /* assign the flags that have been recorded in raw_rcv() */ msg->msg_flags |= *(raw_flags(skb)); skb_free_datagram(sk, skb); return size; } static int raw_sock_no_ioctlcmd(struct socket *sock, unsigned int cmd, unsigned long arg) { /* no ioctls for socket layer -> hand it down to NIC layer */ return -ENOIOCTLCMD; } static const struct proto_ops raw_ops = { .family = PF_CAN, .release = raw_release, .bind = raw_bind, .connect = sock_no_connect, .socketpair = sock_no_socketpair, .accept = sock_no_accept, .getname = raw_getname, .poll = datagram_poll, .ioctl = raw_sock_no_ioctlcmd, .gettstamp = sock_gettstamp, .listen = sock_no_listen, .shutdown = sock_no_shutdown, .setsockopt = raw_setsockopt, .getsockopt = raw_getsockopt, .sendmsg = raw_sendmsg, .recvmsg = raw_recvmsg, .mmap = sock_no_mmap, }; static struct proto raw_proto __read_mostly = { .name = "CAN_RAW", .owner = THIS_MODULE, .obj_size = sizeof(struct raw_sock), .init = raw_init, }; static const struct can_proto raw_can_proto = { .type = SOCK_RAW, .protocol = CAN_RAW, .ops = &raw_ops, .prot = &raw_proto, }; static struct notifier_block canraw_notifier = { .notifier_call = raw_notifier }; static __init int raw_module_init(void) { int err; pr_info("can: raw protocol\n"); err = register_netdevice_notifier(&canraw_notifier); if (err) return err; err = can_proto_register(&raw_can_proto); if (err < 0) { pr_err("can: registration of raw protocol failed\n"); goto register_proto_failed; } return 0; register_proto_failed: unregister_netdevice_notifier(&canraw_notifier); return err; } static __exit void raw_module_exit(void) { can_proto_unregister(&raw_can_proto); unregister_netdevice_notifier(&canraw_notifier); } module_init(raw_module_init); module_exit(raw_module_exit); |
| 1 465 282 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _ASM_GENERIC_BITOPS_LOCK_H_ #define _ASM_GENERIC_BITOPS_LOCK_H_ #include <linux/atomic.h> #include <linux/compiler.h> #include <asm/barrier.h> /** * arch_test_and_set_bit_lock - Set a bit and return its old value, for lock * @nr: Bit to set * @addr: Address to count from * * This operation is atomic and provides acquire barrier semantics if * the returned value is 0. * It can be used to implement bit locks. */ static __always_inline int arch_test_and_set_bit_lock(unsigned int nr, volatile unsigned long *p) { long old; unsigned long mask = BIT_MASK(nr); p += BIT_WORD(nr); if (READ_ONCE(*p) & mask) return 1; old = raw_atomic_long_fetch_or_acquire(mask, (atomic_long_t *)p); return !!(old & mask); } /** * arch_clear_bit_unlock - Clear a bit in memory, for unlock * @nr: the bit to set * @addr: the address to start counting from * * This operation is atomic and provides release barrier semantics. */ static __always_inline void arch_clear_bit_unlock(unsigned int nr, volatile unsigned long *p) { p += BIT_WORD(nr); raw_atomic_long_fetch_andnot_release(BIT_MASK(nr), (atomic_long_t *)p); } /** * arch___clear_bit_unlock - Clear a bit in memory, for unlock * @nr: the bit to set * @addr: the address to start counting from * * A weaker form of clear_bit_unlock() as used by __bit_lock_unlock(). If all * the bits in the word are protected by this lock some archs can use weaker * ops to safely unlock. * * See for example x86's implementation. */ static inline void arch___clear_bit_unlock(unsigned int nr, volatile unsigned long *p) { unsigned long old; p += BIT_WORD(nr); old = READ_ONCE(*p); old &= ~BIT_MASK(nr); raw_atomic_long_set_release((atomic_long_t *)p, old); } #ifndef arch_xor_unlock_is_negative_byte static inline bool arch_xor_unlock_is_negative_byte(unsigned long mask, volatile unsigned long *p) { long old; old = raw_atomic_long_fetch_xor_release(mask, (atomic_long_t *)p); return !!(old & BIT(7)); } #endif #include <asm-generic/bitops/instrumented-lock.h> #endif /* _ASM_GENERIC_BITOPS_LOCK_H_ */ |
| 362 41 41 96 362 34 358 361 361 361 361 357 97 358 358 98 98 357 358 34 352 256 177 178 357 358 100 98 98 98 98 97 359 359 34 34 34 100 100 14 14 304 20 357 357 417 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef LINUX_MM_INLINE_H #define LINUX_MM_INLINE_H #include <linux/atomic.h> #include <linux/huge_mm.h> #include <linux/mm_types.h> #include <linux/swap.h> #include <linux/string.h> #include <linux/userfaultfd_k.h> #include <linux/swapops.h> /** * folio_is_file_lru - Should the folio be on a file LRU or anon LRU? * @folio: The folio to test. * * We would like to get this info without a page flag, but the state * needs to survive until the folio is last deleted from the LRU, which * could be as far down as __page_cache_release. * * Return: An integer (not a boolean!) used to sort a folio onto the * right LRU list and to account folios correctly. * 1 if @folio is a regular filesystem backed page cache folio * or a lazily freed anonymous folio (e.g. via MADV_FREE). * 0 if @folio is a normal anonymous folio, a tmpfs folio or otherwise * ram or swap backed folio. */ static inline int folio_is_file_lru(struct folio *folio) { return !folio_test_swapbacked(folio); } static inline int page_is_file_lru(struct page *page) { return folio_is_file_lru(page_folio(page)); } static __always_inline void __update_lru_size(struct lruvec *lruvec, enum lru_list lru, enum zone_type zid, long nr_pages) { struct pglist_data *pgdat = lruvec_pgdat(lruvec); lockdep_assert_held(&lruvec->lru_lock); WARN_ON_ONCE(nr_pages != (int)nr_pages); __mod_lruvec_state(lruvec, NR_LRU_BASE + lru, nr_pages); __mod_zone_page_state(&pgdat->node_zones[zid], NR_ZONE_LRU_BASE + lru, nr_pages); } static __always_inline void update_lru_size(struct lruvec *lruvec, enum lru_list lru, enum zone_type zid, long nr_pages) { __update_lru_size(lruvec, lru, zid, nr_pages); #ifdef CONFIG_MEMCG mem_cgroup_update_lru_size(lruvec, lru, zid, nr_pages); #endif } /** * __folio_clear_lru_flags - Clear page lru flags before releasing a page. * @folio: The folio that was on lru and now has a zero reference. */ static __always_inline void __folio_clear_lru_flags(struct folio *folio) { VM_BUG_ON_FOLIO(!folio_test_lru(folio), folio); __folio_clear_lru(folio); /* this shouldn't happen, so leave the flags to bad_page() */ if (folio_test_active(folio) && folio_test_unevictable(folio)) return; __folio_clear_active(folio); __folio_clear_unevictable(folio); } /** * folio_lru_list - Which LRU list should a folio be on? * @folio: The folio to test. * * Return: The LRU list a folio should be on, as an index * into the array of LRU lists. */ static __always_inline enum lru_list folio_lru_list(struct folio *folio) { enum lru_list lru; VM_BUG_ON_FOLIO(folio_test_active(folio) && folio_test_unevictable(folio), folio); if (folio_test_unevictable(folio)) return LRU_UNEVICTABLE; lru = folio_is_file_lru(folio) ? LRU_INACTIVE_FILE : LRU_INACTIVE_ANON; if (folio_test_active(folio)) lru += LRU_ACTIVE; return lru; } #ifdef CONFIG_LRU_GEN #ifdef CONFIG_LRU_GEN_ENABLED static inline bool lru_gen_enabled(void) { DECLARE_STATIC_KEY_TRUE(lru_gen_caps[NR_LRU_GEN_CAPS]); return static_branch_likely(&lru_gen_caps[LRU_GEN_CORE]); } #else static inline bool lru_gen_enabled(void) { DECLARE_STATIC_KEY_FALSE(lru_gen_caps[NR_LRU_GEN_CAPS]); return static_branch_unlikely(&lru_gen_caps[LRU_GEN_CORE]); } #endif static inline bool lru_gen_in_fault(void) { return current->in_lru_fault; } static inline int lru_gen_from_seq(unsigned long seq) { return seq % MAX_NR_GENS; } static inline int lru_hist_from_seq(unsigned long seq) { return seq % NR_HIST_GENS; } static inline int lru_tier_from_refs(int refs) { VM_WARN_ON_ONCE(refs > BIT(LRU_REFS_WIDTH)); /* see the comment in folio_lru_refs() */ return order_base_2(refs + 1); } static inline int folio_lru_refs(struct folio *folio) { unsigned long flags = READ_ONCE(folio->flags); bool workingset = flags & BIT(PG_workingset); /* * Return the number of accesses beyond PG_referenced, i.e., N-1 if the * total number of accesses is N>1, since N=0,1 both map to the first * tier. lru_tier_from_refs() will account for this off-by-one. Also see * the comment on MAX_NR_TIERS. */ return ((flags & LRU_REFS_MASK) >> LRU_REFS_PGOFF) + workingset; } static inline void folio_clear_lru_refs(struct folio *folio) { set_mask_bits(&folio->flags, LRU_REFS_MASK | LRU_REFS_FLAGS, 0); } static inline int folio_lru_gen(struct folio *folio) { unsigned long flags = READ_ONCE(folio->flags); return ((flags & LRU_GEN_MASK) >> LRU_GEN_PGOFF) - 1; } static inline bool lru_gen_is_active(struct lruvec *lruvec, int gen) { unsigned long max_seq = lruvec->lrugen.max_seq; VM_WARN_ON_ONCE(gen >= MAX_NR_GENS); /* see the comment on MIN_NR_GENS */ return gen == lru_gen_from_seq(max_seq) || gen == lru_gen_from_seq(max_seq - 1); } static inline void lru_gen_update_size(struct lruvec *lruvec, struct folio *folio, int old_gen, int new_gen) { int type = folio_is_file_lru(folio); int zone = folio_zonenum(folio); int delta = folio_nr_pages(folio); enum lru_list lru = type * LRU_INACTIVE_FILE; struct lru_gen_folio *lrugen = &lruvec->lrugen; VM_WARN_ON_ONCE(old_gen != -1 && old_gen >= MAX_NR_GENS); VM_WARN_ON_ONCE(new_gen != -1 && new_gen >= MAX_NR_GENS); VM_WARN_ON_ONCE(old_gen == -1 && new_gen == -1); if (old_gen >= 0) WRITE_ONCE(lrugen->nr_pages[old_gen][type][zone], lrugen->nr_pages[old_gen][type][zone] - delta); if (new_gen >= 0) WRITE_ONCE(lrugen->nr_pages[new_gen][type][zone], lrugen->nr_pages[new_gen][type][zone] + delta); /* addition */ if (old_gen < 0) { if (lru_gen_is_active(lruvec, new_gen)) lru += LRU_ACTIVE; __update_lru_size(lruvec, lru, zone, delta); return; } /* deletion */ if (new_gen < 0) { if (lru_gen_is_active(lruvec, old_gen)) lru += LRU_ACTIVE; __update_lru_size(lruvec, lru, zone, -delta); return; } /* promotion */ if (!lru_gen_is_active(lruvec, old_gen) && lru_gen_is_active(lruvec, new_gen)) { __update_lru_size(lruvec, lru, zone, -delta); __update_lru_size(lruvec, lru + LRU_ACTIVE, zone, delta); } /* demotion requires isolation, e.g., lru_deactivate_fn() */ VM_WARN_ON_ONCE(lru_gen_is_active(lruvec, old_gen) && !lru_gen_is_active(lruvec, new_gen)); } static inline bool lru_gen_add_folio(struct lruvec *lruvec, struct folio *folio, bool reclaiming) { unsigned long seq; unsigned long flags; unsigned long mask; int gen = folio_lru_gen(folio); int type = folio_is_file_lru(folio); int zone = folio_zonenum(folio); struct lru_gen_folio *lrugen = &lruvec->lrugen; VM_WARN_ON_ONCE_FOLIO(gen != -1, folio); if (folio_test_unevictable(folio) || !lrugen->enabled) return false; /* * There are four common cases for this page: * 1. If it's hot, i.e., freshly faulted in, add it to the youngest * generation, and it's protected over the rest below. * 2. If it can't be evicted immediately, i.e., a dirty page pending * writeback, add it to the second youngest generation. * 3. If it should be evicted first, e.g., cold and clean from * folio_rotate_reclaimable(), add it to the oldest generation. * 4. Everything else falls between 2 & 3 above and is added to the * second oldest generation if it's considered inactive, or the * oldest generation otherwise. See lru_gen_is_active(). */ if (folio_test_active(folio)) seq = lrugen->max_seq; else if ((type == LRU_GEN_ANON && !folio_test_swapcache(folio)) || (folio_test_reclaim(folio) && (folio_test_dirty(folio) || folio_test_writeback(folio)))) seq = lrugen->max_seq - 1; else if (reclaiming || lrugen->min_seq[type] + MIN_NR_GENS >= lrugen->max_seq) seq = lrugen->min_seq[type]; else seq = lrugen->min_seq[type] + 1; gen = lru_gen_from_seq(seq); flags = (gen + 1UL) << LRU_GEN_PGOFF; /* see the comment on MIN_NR_GENS about PG_active */ mask = LRU_GEN_MASK; /* * Don't clear PG_workingset here because it can affect PSI accounting * if the activation is due to workingset refault. */ if (folio_test_active(folio)) mask |= LRU_REFS_MASK | BIT(PG_referenced) | BIT(PG_active); set_mask_bits(&folio->flags, mask, flags); lru_gen_update_size(lruvec, folio, -1, gen); /* for folio_rotate_reclaimable() */ if (reclaiming) list_add_tail(&folio->lru, &lrugen->folios[gen][type][zone]); else list_add(&folio->lru, &lrugen->folios[gen][type][zone]); return true; } static inline bool lru_gen_del_folio(struct lruvec *lruvec, struct folio *folio, bool reclaiming) { unsigned long flags; int gen = folio_lru_gen(folio); if (gen < 0) return false; VM_WARN_ON_ONCE_FOLIO(folio_test_active(folio), folio); VM_WARN_ON_ONCE_FOLIO(folio_test_unevictable(folio), folio); /* for folio_migrate_flags() */ flags = !reclaiming && lru_gen_is_active(lruvec, gen) ? BIT(PG_active) : 0; flags = set_mask_bits(&folio->flags, LRU_GEN_MASK, flags); gen = ((flags & LRU_GEN_MASK) >> LRU_GEN_PGOFF) - 1; lru_gen_update_size(lruvec, folio, gen, -1); list_del(&folio->lru); return true; } static inline void folio_migrate_refs(struct folio *new, struct folio *old) { unsigned long refs = READ_ONCE(old->flags) & LRU_REFS_MASK; set_mask_bits(&new->flags, LRU_REFS_MASK, refs); } #else /* !CONFIG_LRU_GEN */ static inline bool lru_gen_enabled(void) { return false; } static inline bool lru_gen_in_fault(void) { return false; } static inline bool lru_gen_add_folio(struct lruvec *lruvec, struct folio *folio, bool reclaiming) { return false; } static inline bool lru_gen_del_folio(struct lruvec *lruvec, struct folio *folio, bool reclaiming) { return false; } static inline void folio_migrate_refs(struct folio *new, struct folio *old) { } #endif /* CONFIG_LRU_GEN */ static __always_inline void lruvec_add_folio(struct lruvec *lruvec, struct folio *folio) { enum lru_list lru = folio_lru_list(folio); if (lru_gen_add_folio(lruvec, folio, false)) return; update_lru_size(lruvec, lru, folio_zonenum(folio), folio_nr_pages(folio)); if (lru != LRU_UNEVICTABLE) list_add(&folio->lru, &lruvec->lists[lru]); } static __always_inline void lruvec_add_folio_tail(struct lruvec *lruvec, struct folio *folio) { enum lru_list lru = folio_lru_list(folio); if (lru_gen_add_folio(lruvec, folio, true)) return; update_lru_size(lruvec, lru, folio_zonenum(folio), folio_nr_pages(folio)); /* This is not expected to be used on LRU_UNEVICTABLE */ list_add_tail(&folio->lru, &lruvec->lists[lru]); } static __always_inline void lruvec_del_folio(struct lruvec *lruvec, struct folio *folio) { enum lru_list lru = folio_lru_list(folio); if (lru_gen_del_folio(lruvec, folio, false)) return; if (lru != LRU_UNEVICTABLE) list_del(&folio->lru); update_lru_size(lruvec, lru, folio_zonenum(folio), -folio_nr_pages(folio)); } #ifdef CONFIG_ANON_VMA_NAME /* mmap_lock should be read-locked */ static inline void anon_vma_name_get(struct anon_vma_name *anon_name) { if (anon_name) kref_get(&anon_name->kref); } static inline void anon_vma_name_put(struct anon_vma_name *anon_name) { if (anon_name) kref_put(&anon_name->kref, anon_vma_name_free); } static inline struct anon_vma_name *anon_vma_name_reuse(struct anon_vma_name *anon_name) { /* Prevent anon_name refcount saturation early on */ if (kref_read(&anon_name->kref) < REFCOUNT_MAX) { anon_vma_name_get(anon_name); return anon_name; } return anon_vma_name_alloc(anon_name->name); } static inline void dup_anon_vma_name(struct vm_area_struct *orig_vma, struct vm_area_struct *new_vma) { struct anon_vma_name *anon_name = anon_vma_name(orig_vma); if (anon_name) new_vma->anon_name = anon_vma_name_reuse(anon_name); } static inline void free_anon_vma_name(struct vm_area_struct *vma) { /* * Not using anon_vma_name because it generates a warning if mmap_lock * is not held, which might be the case here. */ anon_vma_name_put(vma->anon_name); } static inline bool anon_vma_name_eq(struct anon_vma_name *anon_name1, struct anon_vma_name *anon_name2) { if (anon_name1 == anon_name2) return true; return anon_name1 && anon_name2 && !strcmp(anon_name1->name, anon_name2->name); } #else /* CONFIG_ANON_VMA_NAME */ static inline void anon_vma_name_get(struct anon_vma_name *anon_name) {} static inline void anon_vma_name_put(struct anon_vma_name *anon_name) {} static inline void dup_anon_vma_name(struct vm_area_struct *orig_vma, struct vm_area_struct *new_vma) {} static inline void free_anon_vma_name(struct vm_area_struct *vma) {} static inline bool anon_vma_name_eq(struct anon_vma_name *anon_name1, struct anon_vma_name *anon_name2) { return true; } #endif /* CONFIG_ANON_VMA_NAME */ static inline void init_tlb_flush_pending(struct mm_struct *mm) { atomic_set(&mm->tlb_flush_pending, 0); } static inline void inc_tlb_flush_pending(struct mm_struct *mm) { atomic_inc(&mm->tlb_flush_pending); /* * The only time this value is relevant is when there are indeed pages * to flush. And we'll only flush pages after changing them, which * requires the PTL. * * So the ordering here is: * * atomic_inc(&mm->tlb_flush_pending); * spin_lock(&ptl); * ... * set_pte_at(); * spin_unlock(&ptl); * * spin_lock(&ptl) * mm_tlb_flush_pending(); * .... * spin_unlock(&ptl); * * flush_tlb_range(); * atomic_dec(&mm->tlb_flush_pending); * * Where the increment if constrained by the PTL unlock, it thus * ensures that the increment is visible if the PTE modification is * visible. After all, if there is no PTE modification, nobody cares * about TLB flushes either. * * This very much relies on users (mm_tlb_flush_pending() and * mm_tlb_flush_nested()) only caring about _specific_ PTEs (and * therefore specific PTLs), because with SPLIT_PTE_PTLOCKS and RCpc * locks (PPC) the unlock of one doesn't order against the lock of * another PTL. * * The decrement is ordered by the flush_tlb_range(), such that * mm_tlb_flush_pending() will not return false unless all flushes have * completed. */ } static inline void dec_tlb_flush_pending(struct mm_struct *mm) { /* * See inc_tlb_flush_pending(). * * This cannot be smp_mb__before_atomic() because smp_mb() simply does * not order against TLB invalidate completion, which is what we need. * * Therefore we must rely on tlb_flush_*() to guarantee order. */ atomic_dec(&mm->tlb_flush_pending); } static inline bool mm_tlb_flush_pending(struct mm_struct *mm) { /* * Must be called after having acquired the PTL; orders against that * PTLs release and therefore ensures that if we observe the modified * PTE we must also observe the increment from inc_tlb_flush_pending(). * * That is, it only guarantees to return true if there is a flush * pending for _this_ PTL. */ return atomic_read(&mm->tlb_flush_pending); } static inline bool mm_tlb_flush_nested(struct mm_struct *mm) { /* * Similar to mm_tlb_flush_pending(), we must have acquired the PTL * for which there is a TLB flush pending in order to guarantee * we've seen both that PTE modification and the increment. * * (no requirement on actually still holding the PTL, that is irrelevant) */ return atomic_read(&mm->tlb_flush_pending) > 1; } #ifdef CONFIG_MMU /* * Computes the pte marker to copy from the given source entry into dst_vma. * If no marker should be copied, returns 0. * The caller should insert a new pte created with make_pte_marker(). */ static inline pte_marker copy_pte_marker( swp_entry_t entry, struct vm_area_struct *dst_vma) { pte_marker srcm = pte_marker_get(entry); /* Always copy error entries. */ pte_marker dstm = srcm & (PTE_MARKER_POISONED | PTE_MARKER_GUARD); /* Only copy PTE markers if UFFD register matches. */ if ((srcm & PTE_MARKER_UFFD_WP) && userfaultfd_wp(dst_vma)) dstm |= PTE_MARKER_UFFD_WP; return dstm; } #endif /* * If this pte is wr-protected by uffd-wp in any form, arm the special pte to * replace a none pte. NOTE! This should only be called when *pte is already * cleared so we will never accidentally replace something valuable. Meanwhile * none pte also means we are not demoting the pte so tlb flushed is not needed. * E.g., when pte cleared the caller should have taken care of the tlb flush. * * Must be called with pgtable lock held so that no thread will see the none * pte, and if they see it, they'll fault and serialize at the pgtable lock. * * This function is a no-op if PTE_MARKER_UFFD_WP is not enabled. */ static inline void pte_install_uffd_wp_if_needed(struct vm_area_struct *vma, unsigned long addr, pte_t *pte, pte_t pteval) { #ifdef CONFIG_PTE_MARKER_UFFD_WP bool arm_uffd_pte = false; /* The current status of the pte should be "cleared" before calling */ WARN_ON_ONCE(!pte_none(ptep_get(pte))); /* * NOTE: userfaultfd_wp_unpopulated() doesn't need this whole * thing, because when zapping either it means it's dropping the * page, or in TTU where the present pte will be quickly replaced * with a swap pte. There's no way of leaking the bit. */ if (vma_is_anonymous(vma) || !userfaultfd_wp(vma)) return; /* A uffd-wp wr-protected normal pte */ if (unlikely(pte_present(pteval) && pte_uffd_wp(pteval))) arm_uffd_pte = true; /* * A uffd-wp wr-protected swap pte. Note: this should even cover an * existing pte marker with uffd-wp bit set. */ if (unlikely(pte_swp_uffd_wp_any(pteval))) arm_uffd_pte = true; if (unlikely(arm_uffd_pte)) set_pte_at(vma->vm_mm, addr, pte, make_pte_marker(PTE_MARKER_UFFD_WP)); #endif } static inline bool vma_has_recency(struct vm_area_struct *vma) { if (vma->vm_flags & (VM_SEQ_READ | VM_RAND_READ)) return false; if (vma->vm_file && (vma->vm_file->f_mode & FMODE_NOREUSE)) return false; return true; } #endif |
| 162 162 161 162 161 234 234 234 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 | // SPDX-License-Identifier: GPL-2.0 /* * linux/drivers/char/misc.c * * Generic misc open routine by Johan Myreen * * Based on code from Linus * * Teemu Rantanen's Microsoft Busmouse support and Derrick Cole's * changes incorporated into 0.97pl4 * by Peter Cervasio (pete%q106fm.uucp@wupost.wustl.edu) (08SEP92) * See busmouse.c for particulars. * * Made things a lot mode modular - easy to compile in just one or two * of the misc drivers, as they are now completely independent. Linus. * * Support for loadable modules. 8-Sep-95 Philip Blundell <pjb27@cam.ac.uk> * * Fixed a failing symbol register to free the device registration * Alan Cox <alan@lxorguk.ukuu.org.uk> 21-Jan-96 * * Dynamic minors and /proc/mice by Alessandro Rubini. 26-Mar-96 * * Renamed to misc and miscdevice to be more accurate. Alan Cox 26-Mar-96 * * Handling of mouse minor numbers for kerneld: * Idea by Jacques Gelinas <jack@solucorp.qc.ca>, * adapted by Bjorn Ekwall <bj0rn@blox.se> * corrected by Alan Cox <alan@lxorguk.ukuu.org.uk> * * Changes for kmod (from kerneld): * Cyrus Durgin <cider@speakeasy.org> * * Added devfs support. Richard Gooch <rgooch@atnf.csiro.au> 10-Jan-1998 */ #include <linux/module.h> #include <linux/fs.h> #include <linux/errno.h> #include <linux/miscdevice.h> #include <linux/kernel.h> #include <linux/major.h> #include <linux/mutex.h> #include <linux/proc_fs.h> #include <linux/seq_file.h> #include <linux/stat.h> #include <linux/init.h> #include <linux/device.h> #include <linux/tty.h> #include <linux/kmod.h> #include <linux/gfp.h> /* * Head entry for the doubly linked miscdevice list */ static LIST_HEAD(misc_list); static DEFINE_MUTEX(misc_mtx); /* * Assigned numbers, used for dynamic minors */ #define DYNAMIC_MINORS 128 /* like dynamic majors */ static DEFINE_IDA(misc_minors_ida); static int misc_minor_alloc(void) { int ret; ret = ida_alloc_max(&misc_minors_ida, DYNAMIC_MINORS - 1, GFP_KERNEL); if (ret >= 0) { ret = DYNAMIC_MINORS - ret - 1; } else { ret = ida_alloc_range(&misc_minors_ida, MISC_DYNAMIC_MINOR + 1, MINORMASK, GFP_KERNEL); } return ret; } static void misc_minor_free(int minor) { if (minor < DYNAMIC_MINORS) ida_free(&misc_minors_ida, DYNAMIC_MINORS - minor - 1); else if (minor > MISC_DYNAMIC_MINOR) ida_free(&misc_minors_ida, minor); } #ifdef CONFIG_PROC_FS static void *misc_seq_start(struct seq_file *seq, loff_t *pos) { mutex_lock(&misc_mtx); return seq_list_start(&misc_list, *pos); } static void *misc_seq_next(struct seq_file *seq, void *v, loff_t *pos) { return seq_list_next(v, &misc_list, pos); } static void misc_seq_stop(struct seq_file *seq, void *v) { mutex_unlock(&misc_mtx); } static int misc_seq_show(struct seq_file *seq, void *v) { const struct miscdevice *p = list_entry(v, struct miscdevice, list); seq_printf(seq, "%3i %s\n", p->minor, p->name ? p->name : ""); return 0; } static const struct seq_operations misc_seq_ops = { .start = misc_seq_start, .next = misc_seq_next, .stop = misc_seq_stop, .show = misc_seq_show, }; #endif static int misc_open(struct inode *inode, struct file *file) { int minor = iminor(inode); struct miscdevice *c = NULL, *iter; int err = -ENODEV; const struct file_operations *new_fops = NULL; mutex_lock(&misc_mtx); list_for_each_entry(iter, &misc_list, list) { if (iter->minor != minor) continue; c = iter; new_fops = fops_get(iter->fops); break; } if (!new_fops) { mutex_unlock(&misc_mtx); request_module("char-major-%d-%d", MISC_MAJOR, minor); mutex_lock(&misc_mtx); list_for_each_entry(iter, &misc_list, list) { if (iter->minor != minor) continue; c = iter; new_fops = fops_get(iter->fops); break; } if (!new_fops) goto fail; } /* * Place the miscdevice in the file's * private_data so it can be used by the * file operations, including f_op->open below */ file->private_data = c; err = 0; replace_fops(file, new_fops); if (file->f_op->open) err = file->f_op->open(inode, file); fail: mutex_unlock(&misc_mtx); return err; } static char *misc_devnode(const struct device *dev, umode_t *mode) { const struct miscdevice *c = dev_get_drvdata(dev); if (mode && c->mode) *mode = c->mode; if (c->nodename) return kstrdup(c->nodename, GFP_KERNEL); return NULL; } static const struct class misc_class = { .name = "misc", .devnode = misc_devnode, }; static const struct file_operations misc_fops = { .owner = THIS_MODULE, .open = misc_open, .llseek = noop_llseek, }; /** * misc_register - register a miscellaneous device * @misc: device structure * * Register a miscellaneous device with the kernel. If the minor * number is set to %MISC_DYNAMIC_MINOR a minor number is assigned * and placed in the minor field of the structure. For other cases * the minor number requested is used. * * The structure passed is linked into the kernel and may not be * destroyed until it has been unregistered. By default, an open() * syscall to the device sets file->private_data to point to the * structure. Drivers don't need open in fops for this. * * A zero is returned on success and a negative errno code for * failure. */ int misc_register(struct miscdevice *misc) { dev_t dev; int err = 0; bool is_dynamic = (misc->minor == MISC_DYNAMIC_MINOR); INIT_LIST_HEAD(&misc->list); mutex_lock(&misc_mtx); if (is_dynamic) { int i = misc_minor_alloc(); if (i < 0) { err = -EBUSY; goto out; } misc->minor = i; } else { struct miscdevice *c; list_for_each_entry(c, &misc_list, list) { if (c->minor == misc->minor) { err = -EBUSY; goto out; } } } dev = MKDEV(MISC_MAJOR, misc->minor); misc->this_device = device_create_with_groups(&misc_class, misc->parent, dev, misc, misc->groups, "%s", misc->name); if (IS_ERR(misc->this_device)) { if (is_dynamic) { misc_minor_free(misc->minor); misc->minor = MISC_DYNAMIC_MINOR; } err = PTR_ERR(misc->this_device); goto out; } /* * Add it to the front, so that later devices can "override" * earlier defaults */ list_add(&misc->list, &misc_list); out: mutex_unlock(&misc_mtx); return err; } EXPORT_SYMBOL(misc_register); /** * misc_deregister - unregister a miscellaneous device * @misc: device to unregister * * Unregister a miscellaneous device that was previously * successfully registered with misc_register(). */ void misc_deregister(struct miscdevice *misc) { if (WARN_ON(list_empty(&misc->list))) return; mutex_lock(&misc_mtx); list_del(&misc->list); device_destroy(&misc_class, MKDEV(MISC_MAJOR, misc->minor)); misc_minor_free(misc->minor); mutex_unlock(&misc_mtx); } EXPORT_SYMBOL(misc_deregister); static int __init misc_init(void) { int err; struct proc_dir_entry *ret; ret = proc_create_seq("misc", 0, NULL, &misc_seq_ops); err = class_register(&misc_class); if (err) goto fail_remove; err = -EIO; if (register_chrdev(MISC_MAJOR, "misc", &misc_fops)) goto fail_printk; return 0; fail_printk: pr_err("unable to get major %d for misc devices\n", MISC_MAJOR); class_unregister(&misc_class); fail_remove: if (ret) remove_proc_entry("misc", NULL); return err; } subsys_initcall(misc_init); |
| 177 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 | /* SPDX-License-Identifier: GPL-2.0 */ /* * Prevent the compiler from merging or refetching reads or writes. The * compiler is also forbidden from reordering successive instances of * READ_ONCE and WRITE_ONCE, but only when the compiler is aware of some * particular ordering. One way to make the compiler aware of ordering is to * put the two invocations of READ_ONCE or WRITE_ONCE in different C * statements. * * These two macros will also work on aggregate data types like structs or * unions. * * Their two major use cases are: (1) Mediating communication between * process-level code and irq/NMI handlers, all running on the same CPU, * and (2) Ensuring that the compiler does not fold, spindle, or otherwise * mutilate accesses that either do not require ordering or that interact * with an explicit memory barrier or atomic instruction that provides the * required ordering. */ #ifndef __ASM_GENERIC_RWONCE_H #define __ASM_GENERIC_RWONCE_H #ifndef __ASSEMBLY__ #include <linux/compiler_types.h> #include <linux/kasan-checks.h> #include <linux/kcsan-checks.h> /* * Yes, this permits 64-bit accesses on 32-bit architectures. These will * actually be atomic in some cases (namely Armv7 + LPAE), but for others we * rely on the access being split into 2x32-bit accesses for a 32-bit quantity * (e.g. a virtual address) and a strong prevailing wind. */ #define compiletime_assert_rwonce_type(t) \ compiletime_assert(__native_word(t) || sizeof(t) == sizeof(long long), \ "Unsupported access size for {READ,WRITE}_ONCE().") /* * Use __READ_ONCE() instead of READ_ONCE() if you do not require any * atomicity. Note that this may result in tears! */ #ifndef __READ_ONCE #define __READ_ONCE(x) (*(const volatile __unqual_scalar_typeof(x) *)&(x)) #endif #define READ_ONCE(x) \ ({ \ compiletime_assert_rwonce_type(x); \ __READ_ONCE(x); \ }) #define __WRITE_ONCE(x, val) \ do { \ *(volatile typeof(x) *)&(x) = (val); \ } while (0) #define WRITE_ONCE(x, val) \ do { \ compiletime_assert_rwonce_type(x); \ __WRITE_ONCE(x, val); \ } while (0) static __no_sanitize_or_inline unsigned long __read_once_word_nocheck(const void *addr) { return __READ_ONCE(*(unsigned long *)addr); } /* * Use READ_ONCE_NOCHECK() instead of READ_ONCE() if you need to load a * word from memory atomically but without telling KASAN/KCSAN. This is * usually used by unwinding code when walking the stack of a running process. */ #define READ_ONCE_NOCHECK(x) \ ({ \ compiletime_assert(sizeof(x) == sizeof(unsigned long), \ "Unsupported access size for READ_ONCE_NOCHECK()."); \ (typeof(x))__read_once_word_nocheck(&(x)); \ }) static __no_kasan_or_inline unsigned long read_word_at_a_time(const void *addr) { kasan_check_read(addr, 1); return *(unsigned long *)addr; } #endif /* __ASSEMBLY__ */ #endif /* __ASM_GENERIC_RWONCE_H */ |
| 194 281 15 137 136 331 331 332 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 | // SPDX-License-Identifier: GPL-2.0-or-later /* Common capabilities, needed by capability.o. */ #include <linux/capability.h> #include <linux/audit.h> #include <linux/init.h> #include <linux/kernel.h> #include <linux/lsm_hooks.h> #include <linux/file.h> #include <linux/mm.h> #include <linux/mman.h> #include <linux/pagemap.h> #include <linux/swap.h> #include <linux/skbuff.h> #include <linux/netlink.h> #include <linux/ptrace.h> #include <linux/xattr.h> #include <linux/hugetlb.h> #include <linux/mount.h> #include <linux/sched.h> #include <linux/prctl.h> #include <linux/securebits.h> #include <linux/user_namespace.h> #include <linux/binfmts.h> #include <linux/personality.h> #include <linux/mnt_idmapping.h> #include <uapi/linux/lsm.h> /* * If a non-root user executes a setuid-root binary in * !secure(SECURE_NOROOT) mode, then we raise capabilities. * However if fE is also set, then the intent is for only * the file capabilities to be applied, and the setuid-root * bit is left on either to change the uid (plausible) or * to get full privilege on a kernel without file capabilities * support. So in that case we do not raise capabilities. * * Warn if that happens, once per boot. */ static void warn_setuid_and_fcaps_mixed(const char *fname) { static int warned; if (!warned) { printk(KERN_INFO "warning: `%s' has both setuid-root and" " effective capabilities. Therefore not raising all" " capabilities.\n", fname); warned = 1; } } /** * cap_capable - Determine whether a task has a particular effective capability * @cred: The credentials to use * @targ_ns: The user namespace in which we need the capability * @cap: The capability to check for * @opts: Bitmask of options defined in include/linux/security.h * * Determine whether the nominated task has the specified capability amongst * its effective set, returning 0 if it does, -ve if it does not. * * NOTE WELL: cap_has_capability() cannot be used like the kernel's capable() * and has_capability() functions. That is, it has the reverse semantics: * cap_has_capability() returns 0 when a task has a capability, but the * kernel's capable() and has_capability() returns 1 for this case. */ int cap_capable(const struct cred *cred, struct user_namespace *targ_ns, int cap, unsigned int opts) { struct user_namespace *ns = targ_ns; /* See if cred has the capability in the target user namespace * by examining the target user namespace and all of the target * user namespace's parents. */ for (;;) { /* Do we have the necessary capabilities? */ if (ns == cred->user_ns) return cap_raised(cred->cap_effective, cap) ? 0 : -EPERM; /* * If we're already at a lower level than we're looking for, * we're done searching. */ if (ns->level <= cred->user_ns->level) return -EPERM; /* * The owner of the user namespace in the parent of the * user namespace has all caps. */ if ((ns->parent == cred->user_ns) && uid_eq(ns->owner, cred->euid)) return 0; /* * If you have a capability in a parent user ns, then you have * it over all children user namespaces as well. */ ns = ns->parent; } /* We never get here */ } /** * cap_settime - Determine whether the current process may set the system clock * @ts: The time to set * @tz: The timezone to set * * Determine whether the current process may set the system clock and timezone * information, returning 0 if permission granted, -ve if denied. */ int cap_settime(const struct timespec64 *ts, const struct timezone *tz) { if (!capable(CAP_SYS_TIME)) return -EPERM; return 0; } /** * cap_ptrace_access_check - Determine whether the current process may access * another * @child: The process to be accessed * @mode: The mode of attachment. * * If we are in the same or an ancestor user_ns and have all the target * task's capabilities, then ptrace access is allowed. * If we have the ptrace capability to the target user_ns, then ptrace * access is allowed. * Else denied. * * Determine whether a process may access another, returning 0 if permission * granted, -ve if denied. */ int cap_ptrace_access_check(struct task_struct *child, unsigned int mode) { int ret = 0; const struct cred *cred, *child_cred; const kernel_cap_t *caller_caps; rcu_read_lock(); cred = current_cred(); child_cred = __task_cred(child); if (mode & PTRACE_MODE_FSCREDS) caller_caps = &cred->cap_effective; else caller_caps = &cred->cap_permitted; if (cred->user_ns == child_cred->user_ns && cap_issubset(child_cred->cap_permitted, *caller_caps)) goto out; if (ns_capable(child_cred->user_ns, CAP_SYS_PTRACE)) goto out; ret = -EPERM; out: rcu_read_unlock(); return ret; } /** * cap_ptrace_traceme - Determine whether another process may trace the current * @parent: The task proposed to be the tracer * * If parent is in the same or an ancestor user_ns and has all current's * capabilities, then ptrace access is allowed. * If parent has the ptrace capability to current's user_ns, then ptrace * access is allowed. * Else denied. * * Determine whether the nominated task is permitted to trace the current * process, returning 0 if permission is granted, -ve if denied. */ int cap_ptrace_traceme(struct task_struct *parent) { int ret = 0; const struct cred *cred, *child_cred; rcu_read_lock(); cred = __task_cred(parent); child_cred = current_cred(); if (cred->user_ns == child_cred->user_ns && cap_issubset(child_cred->cap_permitted, cred->cap_permitted)) goto out; if (has_ns_capability(parent, child_cred->user_ns, CAP_SYS_PTRACE)) goto out; ret = -EPERM; out: rcu_read_unlock(); return ret; } /** * cap_capget - Retrieve a task's capability sets * @target: The task from which to retrieve the capability sets * @effective: The place to record the effective set * @inheritable: The place to record the inheritable set * @permitted: The place to record the permitted set * * This function retrieves the capabilities of the nominated task and returns * them to the caller. */ int cap_capget(const struct task_struct *target, kernel_cap_t *effective, kernel_cap_t *inheritable, kernel_cap_t *permitted) { const struct cred *cred; /* Derived from kernel/capability.c:sys_capget. */ rcu_read_lock(); cred = __task_cred(target); *effective = cred->cap_effective; *inheritable = cred->cap_inheritable; *permitted = cred->cap_permitted; rcu_read_unlock(); return 0; } /* * Determine whether the inheritable capabilities are limited to the old * permitted set. Returns 1 if they are limited, 0 if they are not. */ static inline int cap_inh_is_capped(void) { /* they are so limited unless the current task has the CAP_SETPCAP * capability */ if (cap_capable(current_cred(), current_cred()->user_ns, CAP_SETPCAP, CAP_OPT_NONE) == 0) return 0; return 1; } /** * cap_capset - Validate and apply proposed changes to current's capabilities * @new: The proposed new credentials; alterations should be made here * @old: The current task's current credentials * @effective: A pointer to the proposed new effective capabilities set * @inheritable: A pointer to the proposed new inheritable capabilities set * @permitted: A pointer to the proposed new permitted capabilities set * * This function validates and applies a proposed mass change to the current * process's capability sets. The changes are made to the proposed new * credentials, and assuming no error, will be committed by the caller of LSM. */ int cap_capset(struct cred *new, const struct cred *old, const kernel_cap_t *effective, const kernel_cap_t *inheritable, const kernel_cap_t *permitted) { if (cap_inh_is_capped() && !cap_issubset(*inheritable, cap_combine(old->cap_inheritable, old->cap_permitted))) /* incapable of using this inheritable set */ return -EPERM; if (!cap_issubset(*inheritable, cap_combine(old->cap_inheritable, old->cap_bset))) /* no new pI capabilities outside bounding set */ return -EPERM; /* verify restrictions on target's new Permitted set */ if (!cap_issubset(*permitted, old->cap_permitted)) return -EPERM; /* verify the _new_Effective_ is a subset of the _new_Permitted_ */ if (!cap_issubset(*effective, *permitted)) return -EPERM; new->cap_effective = *effective; new->cap_inheritable = *inheritable; new->cap_permitted = *permitted; /* * Mask off ambient bits that are no longer both permitted and * inheritable. */ new->cap_ambient = cap_intersect(new->cap_ambient, cap_intersect(*permitted, *inheritable)); if (WARN_ON(!cap_ambient_invariant_ok(new))) return -EINVAL; return 0; } /** * cap_inode_need_killpriv - Determine if inode change affects privileges * @dentry: The inode/dentry in being changed with change marked ATTR_KILL_PRIV * * Determine if an inode having a change applied that's marked ATTR_KILL_PRIV * affects the security markings on that inode, and if it is, should * inode_killpriv() be invoked or the change rejected. * * Return: 1 if security.capability has a value, meaning inode_killpriv() * is required, 0 otherwise, meaning inode_killpriv() is not required. */ int cap_inode_need_killpriv(struct dentry *dentry) { struct inode *inode = d_backing_inode(dentry); int error; error = __vfs_getxattr(dentry, inode, XATTR_NAME_CAPS, NULL, 0); return error > 0; } /** * cap_inode_killpriv - Erase the security markings on an inode * * @idmap: idmap of the mount the inode was found from * @dentry: The inode/dentry to alter * * Erase the privilege-enhancing security markings on an inode. * * If the inode has been found through an idmapped mount the idmap of * the vfsmount must be passed through @idmap. This function will then * take care to map the inode according to @idmap before checking * permissions. On non-idmapped mounts or if permission checking is to be * performed on the raw inode simply pass @nop_mnt_idmap. * * Return: 0 if successful, -ve on error. */ int cap_inode_killpriv(struct mnt_idmap *idmap, struct dentry *dentry) { int error; error = __vfs_removexattr(idmap, dentry, XATTR_NAME_CAPS); if (error == -EOPNOTSUPP) error = 0; return error; } static bool rootid_owns_currentns(vfsuid_t rootvfsuid) { struct user_namespace *ns; kuid_t kroot; if (!vfsuid_valid(rootvfsuid)) return false; kroot = vfsuid_into_kuid(rootvfsuid); for (ns = current_user_ns();; ns = ns->parent) { if (from_kuid(ns, kroot) == 0) return true; if (ns == &init_user_ns) break; } return false; } static __u32 sansflags(__u32 m) { return m & ~VFS_CAP_FLAGS_EFFECTIVE; } static bool is_v2header(int size, const struct vfs_cap_data *cap) { if (size != XATTR_CAPS_SZ_2) return false; return sansflags(le32_to_cpu(cap->magic_etc)) == VFS_CAP_REVISION_2; } static bool is_v3header(int size, const struct vfs_cap_data *cap) { if (size != XATTR_CAPS_SZ_3) return false; return sansflags(le32_to_cpu(cap->magic_etc)) == VFS_CAP_REVISION_3; } /* * getsecurity: We are called for security.* before any attempt to read the * xattr from the inode itself. * * This gives us a chance to read the on-disk value and convert it. If we * return -EOPNOTSUPP, then vfs_getxattr() will call the i_op handler. * * Note we are not called by vfs_getxattr_alloc(), but that is only called * by the integrity subsystem, which really wants the unconverted values - * so that's good. */ int cap_inode_getsecurity(struct mnt_idmap *idmap, struct inode *inode, const char *name, void **buffer, bool alloc) { int size; kuid_t kroot; vfsuid_t vfsroot; u32 nsmagic, magic; uid_t root, mappedroot; char *tmpbuf = NULL; struct vfs_cap_data *cap; struct vfs_ns_cap_data *nscap = NULL; struct dentry *dentry; struct user_namespace *fs_ns; if (strcmp(name, "capability") != 0) return -EOPNOTSUPP; dentry = d_find_any_alias(inode); if (!dentry) return -EINVAL; size = vfs_getxattr_alloc(idmap, dentry, XATTR_NAME_CAPS, &tmpbuf, sizeof(struct vfs_ns_cap_data), GFP_NOFS); dput(dentry); /* gcc11 complains if we don't check for !tmpbuf */ if (size < 0 || !tmpbuf) goto out_free; fs_ns = inode->i_sb->s_user_ns; cap = (struct vfs_cap_data *) tmpbuf; if (is_v2header(size, cap)) { root = 0; } else if (is_v3header(size, cap)) { nscap = (struct vfs_ns_cap_data *) tmpbuf; root = le32_to_cpu(nscap->rootid); } else { size = -EINVAL; goto out_free; } kroot = make_kuid(fs_ns, root); /* If this is an idmapped mount shift the kuid. */ vfsroot = make_vfsuid(idmap, fs_ns, kroot); /* If the root kuid maps to a valid uid in current ns, then return * this as a nscap. */ mappedroot = from_kuid(current_user_ns(), vfsuid_into_kuid(vfsroot)); if (mappedroot != (uid_t)-1 && mappedroot != (uid_t)0) { size = sizeof(struct vfs_ns_cap_data); if (alloc) { if (!nscap) { /* v2 -> v3 conversion */ nscap = kzalloc(size, GFP_ATOMIC); if (!nscap) { size = -ENOMEM; goto out_free; } nsmagic = VFS_CAP_REVISION_3; magic = le32_to_cpu(cap->magic_etc); if (magic & VFS_CAP_FLAGS_EFFECTIVE) nsmagic |= VFS_CAP_FLAGS_EFFECTIVE; memcpy(&nscap->data, &cap->data, sizeof(__le32) * 2 * VFS_CAP_U32); nscap->magic_etc = cpu_to_le32(nsmagic); } else { /* use allocated v3 buffer */ tmpbuf = NULL; } nscap->rootid = cpu_to_le32(mappedroot); *buffer = nscap; } goto out_free; } if (!rootid_owns_currentns(vfsroot)) { size = -EOVERFLOW; goto out_free; } /* This comes from a parent namespace. Return as a v2 capability */ size = sizeof(struct vfs_cap_data); if (alloc) { if (nscap) { /* v3 -> v2 conversion */ cap = kzalloc(size, GFP_ATOMIC); if (!cap) { size = -ENOMEM; goto out_free; } magic = VFS_CAP_REVISION_2; nsmagic = le32_to_cpu(nscap->magic_etc); if (nsmagic & VFS_CAP_FLAGS_EFFECTIVE) magic |= VFS_CAP_FLAGS_EFFECTIVE; memcpy(&cap->data, &nscap->data, sizeof(__le32) * 2 * VFS_CAP_U32); cap->magic_etc = cpu_to_le32(magic); } else { /* use unconverted v2 */ tmpbuf = NULL; } *buffer = cap; } out_free: kfree(tmpbuf); return size; } /** * rootid_from_xattr - translate root uid of vfs caps * * @value: vfs caps value which may be modified by this function * @size: size of @ivalue * @task_ns: user namespace of the caller */ static vfsuid_t rootid_from_xattr(const void *value, size_t size, struct user_namespace *task_ns) { const struct vfs_ns_cap_data *nscap = value; uid_t rootid = 0; if (size == XATTR_CAPS_SZ_3) rootid = le32_to_cpu(nscap->rootid); return VFSUIDT_INIT(make_kuid(task_ns, rootid)); } static bool validheader(size_t size, const struct vfs_cap_data *cap) { return is_v2header(size, cap) || is_v3header(size, cap); } /** * cap_convert_nscap - check vfs caps * * @idmap: idmap of the mount the inode was found from * @dentry: used to retrieve inode to check permissions on * @ivalue: vfs caps value which may be modified by this function * @size: size of @ivalue * * User requested a write of security.capability. If needed, update the * xattr to change from v2 to v3, or to fixup the v3 rootid. * * If the inode has been found through an idmapped mount the idmap of * the vfsmount must be passed through @idmap. This function will then * take care to map the inode according to @idmap before checking * permissions. On non-idmapped mounts or if permission checking is to be * performed on the raw inode simply pass @nop_mnt_idmap. * * Return: On success, return the new size; on error, return < 0. */ int cap_convert_nscap(struct mnt_idmap *idmap, struct dentry *dentry, const void **ivalue, size_t size) { struct vfs_ns_cap_data *nscap; uid_t nsrootid; const struct vfs_cap_data *cap = *ivalue; __u32 magic, nsmagic; struct inode *inode = d_backing_inode(dentry); struct user_namespace *task_ns = current_user_ns(), *fs_ns = inode->i_sb->s_user_ns; kuid_t rootid; vfsuid_t vfsrootid; size_t newsize; if (!*ivalue) return -EINVAL; if (!validheader(size, cap)) return -EINVAL; if (!capable_wrt_inode_uidgid(idmap, inode, CAP_SETFCAP)) return -EPERM; if (size == XATTR_CAPS_SZ_2 && (idmap == &nop_mnt_idmap)) if (ns_capable(inode->i_sb->s_user_ns, CAP_SETFCAP)) /* user is privileged, just write the v2 */ return size; vfsrootid = rootid_from_xattr(*ivalue, size, task_ns); if (!vfsuid_valid(vfsrootid)) return -EINVAL; rootid = from_vfsuid(idmap, fs_ns, vfsrootid); if (!uid_valid(rootid)) return -EINVAL; nsrootid = from_kuid(fs_ns, rootid); if (nsrootid == -1) return -EINVAL; newsize = sizeof(struct vfs_ns_cap_data); nscap = kmalloc(newsize, GFP_ATOMIC); if (!nscap) return -ENOMEM; nscap->rootid = cpu_to_le32(nsrootid); nsmagic = VFS_CAP_REVISION_3; magic = le32_to_cpu(cap->magic_etc); if (magic & VFS_CAP_FLAGS_EFFECTIVE) nsmagic |= VFS_CAP_FLAGS_EFFECTIVE; nscap->magic_etc = cpu_to_le32(nsmagic); memcpy(&nscap->data, &cap->data, sizeof(__le32) * 2 * VFS_CAP_U32); *ivalue = nscap; return newsize; } /* * Calculate the new process capability sets from the capability sets attached * to a file. */ static inline int bprm_caps_from_vfs_caps(struct cpu_vfs_cap_data *caps, struct linux_binprm *bprm, bool *effective, bool *has_fcap) { struct cred *new = bprm->cred; int ret = 0; if (caps->magic_etc & VFS_CAP_FLAGS_EFFECTIVE) *effective = true; if (caps->magic_etc & VFS_CAP_REVISION_MASK) *has_fcap = true; /* * pP' = (X & fP) | (pI & fI) * The addition of pA' is handled later. */ new->cap_permitted.val = (new->cap_bset.val & caps->permitted.val) | (new->cap_inheritable.val & caps->inheritable.val); if (caps->permitted.val & ~new->cap_permitted.val) /* insufficient to execute correctly */ ret = -EPERM; /* * For legacy apps, with no internal support for recognizing they * do not have enough capabilities, we return an error if they are * missing some "forced" (aka file-permitted) capabilities. */ return *effective ? ret : 0; } /** * get_vfs_caps_from_disk - retrieve vfs caps from disk * * @idmap: idmap of the mount the inode was found from * @dentry: dentry from which @inode is retrieved * @cpu_caps: vfs capabilities * * Extract the on-exec-apply capability sets for an executable file. * * If the inode has been found through an idmapped mount the idmap of * the vfsmount must be passed through @idmap. This function will then * take care to map the inode according to @idmap before checking * permissions. On non-idmapped mounts or if permission checking is to be * performed on the raw inode simply pass @nop_mnt_idmap. */ int get_vfs_caps_from_disk(struct mnt_idmap *idmap, const struct dentry *dentry, struct cpu_vfs_cap_data *cpu_caps) { struct inode *inode = d_backing_inode(dentry); __u32 magic_etc; int size; struct vfs_ns_cap_data data, *nscaps = &data; struct vfs_cap_data *caps = (struct vfs_cap_data *) &data; kuid_t rootkuid; vfsuid_t rootvfsuid; struct user_namespace *fs_ns; memset(cpu_caps, 0, sizeof(struct cpu_vfs_cap_data)); if (!inode) return -ENODATA; fs_ns = inode->i_sb->s_user_ns; size = __vfs_getxattr((struct dentry *)dentry, inode, XATTR_NAME_CAPS, &data, XATTR_CAPS_SZ); if (size == -ENODATA || size == -EOPNOTSUPP) /* no data, that's ok */ return -ENODATA; if (size < 0) return size; if (size < sizeof(magic_etc)) return -EINVAL; cpu_caps->magic_etc = magic_etc = le32_to_cpu(caps->magic_etc); rootkuid = make_kuid(fs_ns, 0); switch (magic_etc & VFS_CAP_REVISION_MASK) { case VFS_CAP_REVISION_1: if (size != XATTR_CAPS_SZ_1) return -EINVAL; break; case VFS_CAP_REVISION_2: if (size != XATTR_CAPS_SZ_2) return -EINVAL; break; case VFS_CAP_REVISION_3: if (size != XATTR_CAPS_SZ_3) return -EINVAL; rootkuid = make_kuid(fs_ns, le32_to_cpu(nscaps->rootid)); break; default: return -EINVAL; } rootvfsuid = make_vfsuid(idmap, fs_ns, rootkuid); if (!vfsuid_valid(rootvfsuid)) return -ENODATA; /* Limit the caps to the mounter of the filesystem * or the more limited uid specified in the xattr. */ if (!rootid_owns_currentns(rootvfsuid)) return -ENODATA; cpu_caps->permitted.val = le32_to_cpu(caps->data[0].permitted); cpu_caps->inheritable.val = le32_to_cpu(caps->data[0].inheritable); /* * Rev1 had just a single 32-bit word, later expanded * to a second one for the high bits */ if ((magic_etc & VFS_CAP_REVISION_MASK) != VFS_CAP_REVISION_1) { cpu_caps->permitted.val += (u64)le32_to_cpu(caps->data[1].permitted) << 32; cpu_caps->inheritable.val += (u64)le32_to_cpu(caps->data[1].inheritable) << 32; } cpu_caps->permitted.val &= CAP_VALID_MASK; cpu_caps->inheritable.val &= CAP_VALID_MASK; cpu_caps->rootid = vfsuid_into_kuid(rootvfsuid); return 0; } /* * Attempt to get the on-exec apply capability sets for an executable file from * its xattrs and, if present, apply them to the proposed credentials being * constructed by execve(). */ static int get_file_caps(struct linux_binprm *bprm, const struct file *file, bool *effective, bool *has_fcap) { int rc = 0; struct cpu_vfs_cap_data vcaps; cap_clear(bprm->cred->cap_permitted); if (!file_caps_enabled) return 0; if (!mnt_may_suid(file->f_path.mnt)) return 0; /* * This check is redundant with mnt_may_suid() but is kept to make * explicit that capability bits are limited to s_user_ns and its * descendants. */ if (!current_in_userns(file->f_path.mnt->mnt_sb->s_user_ns)) return 0; rc = get_vfs_caps_from_disk(file_mnt_idmap(file), file->f_path.dentry, &vcaps); if (rc < 0) { if (rc == -EINVAL) printk(KERN_NOTICE "Invalid argument reading file caps for %s\n", bprm->filename); else if (rc == -ENODATA) rc = 0; goto out; } rc = bprm_caps_from_vfs_caps(&vcaps, bprm, effective, has_fcap); out: if (rc) cap_clear(bprm->cred->cap_permitted); return rc; } static inline bool root_privileged(void) { return !issecure(SECURE_NOROOT); } static inline bool __is_real(kuid_t uid, struct cred *cred) { return uid_eq(cred->uid, uid); } static inline bool __is_eff(kuid_t uid, struct cred *cred) { return uid_eq(cred->euid, uid); } static inline bool __is_suid(kuid_t uid, struct cred *cred) { return !__is_real(uid, cred) && __is_eff(uid, cred); } /* * handle_privileged_root - Handle case of privileged root * @bprm: The execution parameters, including the proposed creds * @has_fcap: Are any file capabilities set? * @effective: Do we have effective root privilege? * @root_uid: This namespace' root UID WRT initial USER namespace * * Handle the case where root is privileged and hasn't been neutered by * SECURE_NOROOT. If file capabilities are set, they won't be combined with * set UID root and nothing is changed. If we are root, cap_permitted is * updated. If we have become set UID root, the effective bit is set. */ static void handle_privileged_root(struct linux_binprm *bprm, bool has_fcap, bool *effective, kuid_t root_uid) { const struct cred *old = current_cred(); struct cred *new = bprm->cred; if (!root_privileged()) return; /* * If the legacy file capability is set, then don't set privs * for a setuid root binary run by a non-root user. Do set it * for a root user just to cause least surprise to an admin. */ if (has_fcap && __is_suid(root_uid, new)) { warn_setuid_and_fcaps_mixed(bprm->filename); return; } /* * To support inheritance of root-permissions and suid-root * executables under compatibility mode, we override the * capability sets for the file. */ if (__is_eff(root_uid, new) || __is_real(root_uid, new)) { /* pP' = (cap_bset & ~0) | (pI & ~0) */ new->cap_permitted = cap_combine(old->cap_bset, old->cap_inheritable); } /* * If only the real uid is 0, we do not set the effective bit. */ if (__is_eff(root_uid, new)) *effective = true; } #define __cap_gained(field, target, source) \ !cap_issubset(target->cap_##field, source->cap_##field) #define __cap_grew(target, source, cred) \ !cap_issubset(cred->cap_##target, cred->cap_##source) #define __cap_full(field, cred) \ cap_issubset(CAP_FULL_SET, cred->cap_##field) static inline bool __is_setuid(struct cred *new, const struct cred *old) { return !uid_eq(new->euid, old->uid); } static inline bool __is_setgid(struct cred *new, const struct cred *old) { return !gid_eq(new->egid, old->gid); } /* * 1) Audit candidate if current->cap_effective is set * * We do not bother to audit if 3 things are true: * 1) cap_effective has all caps * 2) we became root *OR* are were already root * 3) root is supposed to have all caps (SECURE_NOROOT) * Since this is just a normal root execing a process. * * Number 1 above might fail if you don't have a full bset, but I think * that is interesting information to audit. * * A number of other conditions require logging: * 2) something prevented setuid root getting all caps * 3) non-setuid root gets fcaps * 4) non-setuid root gets ambient */ static inline bool nonroot_raised_pE(struct cred *new, const struct cred *old, kuid_t root, bool has_fcap) { bool ret = false; if ((__cap_grew(effective, ambient, new) && !(__cap_full(effective, new) && (__is_eff(root, new) || __is_real(root, new)) && root_privileged())) || (root_privileged() && __is_suid(root, new) && !__cap_full(effective, new)) || (!__is_setuid(new, old) && ((has_fcap && __cap_gained(permitted, new, old)) || __cap_gained(ambient, new, old)))) ret = true; return ret; } /** * cap_bprm_creds_from_file - Set up the proposed credentials for execve(). * @bprm: The execution parameters, including the proposed creds * @file: The file to pull the credentials from * * Set up the proposed credentials for a new execution context being * constructed by execve(). The proposed creds in @bprm->cred is altered, * which won't take effect immediately. * * Return: 0 if successful, -ve on error. */ int cap_bprm_creds_from_file(struct linux_binprm *bprm, const struct file *file) { /* Process setpcap binaries and capabilities for uid 0 */ const struct cred *old = current_cred(); struct cred *new = bprm->cred; bool effective = false, has_fcap = false, is_setid; int ret; kuid_t root_uid; if (WARN_ON(!cap_ambient_invariant_ok(old))) return -EPERM; ret = get_file_caps(bprm, file, &effective, &has_fcap); if (ret < 0) return ret; root_uid = make_kuid(new->user_ns, 0); handle_privileged_root(bprm, has_fcap, &effective, root_uid); /* if we have fs caps, clear dangerous personality flags */ if (__cap_gained(permitted, new, old)) bprm->per_clear |= PER_CLEAR_ON_SETID; /* Don't let someone trace a set[ug]id/setpcap binary with the revised * credentials unless they have the appropriate permit. * * In addition, if NO_NEW_PRIVS, then ensure we get no new privs. */ is_setid = __is_setuid(new, old) || __is_setgid(new, old); if ((is_setid || __cap_gained(permitted, new, old)) && ((bprm->unsafe & ~LSM_UNSAFE_PTRACE) || !ptracer_capable(current, new->user_ns))) { /* downgrade; they get no more than they had, and maybe less */ if (!ns_capable(new->user_ns, CAP_SETUID) || (bprm->unsafe & LSM_UNSAFE_NO_NEW_PRIVS)) { new->euid = new->uid; new->egid = new->gid; } new->cap_permitted = cap_intersect(new->cap_permitted, old->cap_permitted); } new->suid = new->fsuid = new->euid; new->sgid = new->fsgid = new->egid; /* File caps or setid cancels ambient. */ if (has_fcap || is_setid) cap_clear(new->cap_ambient); /* * Now that we've computed pA', update pP' to give: * pP' = (X & fP) | (pI & fI) | pA' */ new->cap_permitted = cap_combine(new->cap_permitted, new->cap_ambient); /* * Set pE' = (fE ? pP' : pA'). Because pA' is zero if fE is set, * this is the same as pE' = (fE ? pP' : 0) | pA'. */ if (effective) new->cap_effective = new->cap_permitted; else new->cap_effective = new->cap_ambient; if (WARN_ON(!cap_ambient_invariant_ok(new))) return -EPERM; if (nonroot_raised_pE(new, old, root_uid, has_fcap)) { ret = audit_log_bprm_fcaps(bprm, new, old); if (ret < 0) return ret; } new->securebits &= ~issecure_mask(SECURE_KEEP_CAPS); if (WARN_ON(!cap_ambient_invariant_ok(new))) return -EPERM; /* Check for privilege-elevated exec. */ if (is_setid || (!__is_real(root_uid, new) && (effective || __cap_grew(permitted, ambient, new)))) bprm->secureexec = 1; return 0; } /** * cap_inode_setxattr - Determine whether an xattr may be altered * @dentry: The inode/dentry being altered * @name: The name of the xattr to be changed * @value: The value that the xattr will be changed to * @size: The size of value * @flags: The replacement flag * * Determine whether an xattr may be altered or set on an inode, returning 0 if * permission is granted, -ve if denied. * * This is used to make sure security xattrs don't get updated or set by those * who aren't privileged to do so. */ int cap_inode_setxattr(struct dentry *dentry, const char *name, const void *value, size_t size, int flags) { struct user_namespace *user_ns = dentry->d_sb->s_user_ns; /* Ignore non-security xattrs */ if (strncmp(name, XATTR_SECURITY_PREFIX, XATTR_SECURITY_PREFIX_LEN) != 0) return 0; /* * For XATTR_NAME_CAPS the check will be done in * cap_convert_nscap(), called by setxattr() */ if (strcmp(name, XATTR_NAME_CAPS) == 0) return 0; if (!ns_capable(user_ns, CAP_SYS_ADMIN)) return -EPERM; return 0; } /** * cap_inode_removexattr - Determine whether an xattr may be removed * * @idmap: idmap of the mount the inode was found from * @dentry: The inode/dentry being altered * @name: The name of the xattr to be changed * * Determine whether an xattr may be removed from an inode, returning 0 if * permission is granted, -ve if denied. * * If the inode has been found through an idmapped mount the idmap of * the vfsmount must be passed through @idmap. This function will then * take care to map the inode according to @idmap before checking * permissions. On non-idmapped mounts or if permission checking is to be * performed on the raw inode simply pass @nop_mnt_idmap. * * This is used to make sure security xattrs don't get removed by those who * aren't privileged to remove them. */ int cap_inode_removexattr(struct mnt_idmap *idmap, struct dentry *dentry, const char *name) { struct user_namespace *user_ns = dentry->d_sb->s_user_ns; /* Ignore non-security xattrs */ if (strncmp(name, XATTR_SECURITY_PREFIX, XATTR_SECURITY_PREFIX_LEN) != 0) return 0; if (strcmp(name, XATTR_NAME_CAPS) == 0) { /* security.capability gets namespaced */ struct inode *inode = d_backing_inode(dentry); if (!inode) return -EINVAL; if (!capable_wrt_inode_uidgid(idmap, inode, CAP_SETFCAP)) return -EPERM; return 0; } if (!ns_capable(user_ns, CAP_SYS_ADMIN)) return -EPERM; return 0; } /* * cap_emulate_setxuid() fixes the effective / permitted capabilities of * a process after a call to setuid, setreuid, or setresuid. * * 1) When set*uiding _from_ one of {r,e,s}uid == 0 _to_ all of * {r,e,s}uid != 0, the permitted and effective capabilities are * cleared. * * 2) When set*uiding _from_ euid == 0 _to_ euid != 0, the effective * capabilities of the process are cleared. * * 3) When set*uiding _from_ euid != 0 _to_ euid == 0, the effective * capabilities are set to the permitted capabilities. * * fsuid is handled elsewhere. fsuid == 0 and {r,e,s}uid!= 0 should * never happen. * * -astor * * cevans - New behaviour, Oct '99 * A process may, via prctl(), elect to keep its capabilities when it * calls setuid() and switches away from uid==0. Both permitted and * effective sets will be retained. * Without this change, it was impossible for a daemon to drop only some * of its privilege. The call to setuid(!=0) would drop all privileges! * Keeping uid 0 is not an option because uid 0 owns too many vital * files.. * Thanks to Olaf Kirch and Peter Benie for spotting this. */ static inline void cap_emulate_setxuid(struct cred *new, const struct cred *old) { kuid_t root_uid = make_kuid(old->user_ns, 0); if ((uid_eq(old->uid, root_uid) || uid_eq(old->euid, root_uid) || uid_eq(old->suid, root_uid)) && (!uid_eq(new->uid, root_uid) && !uid_eq(new->euid, root_uid) && !uid_eq(new->suid, root_uid))) { if (!issecure(SECURE_KEEP_CAPS)) { cap_clear(new->cap_permitted); cap_clear(new->cap_effective); } /* * Pre-ambient programs expect setresuid to nonroot followed * by exec to drop capabilities. We should make sure that * this remains the case. */ cap_clear(new->cap_ambient); } if (uid_eq(old->euid, root_uid) && !uid_eq(new->euid, root_uid)) cap_clear(new->cap_effective); if (!uid_eq(old->euid, root_uid) && uid_eq(new->euid, root_uid)) new->cap_effective = new->cap_permitted; } /** * cap_task_fix_setuid - Fix up the results of setuid() call * @new: The proposed credentials * @old: The current task's current credentials * @flags: Indications of what has changed * * Fix up the results of setuid() call before the credential changes are * actually applied. * * Return: 0 to grant the changes, -ve to deny them. */ int cap_task_fix_setuid(struct cred *new, const struct cred *old, int flags) { switch (flags) { case LSM_SETID_RE: case LSM_SETID_ID: case LSM_SETID_RES: /* juggle the capabilities to follow [RES]UID changes unless * otherwise suppressed */ if (!issecure(SECURE_NO_SETUID_FIXUP)) cap_emulate_setxuid(new, old); break; case LSM_SETID_FS: /* juggle the capabilities to follow FSUID changes, unless * otherwise suppressed * * FIXME - is fsuser used for all CAP_FS_MASK capabilities? * if not, we might be a bit too harsh here. */ if (!issecure(SECURE_NO_SETUID_FIXUP)) { kuid_t root_uid = make_kuid(old->user_ns, 0); if (uid_eq(old->fsuid, root_uid) && !uid_eq(new->fsuid, root_uid)) new->cap_effective = cap_drop_fs_set(new->cap_effective); if (!uid_eq(old->fsuid, root_uid) && uid_eq(new->fsuid, root_uid)) new->cap_effective = cap_raise_fs_set(new->cap_effective, new->cap_permitted); } break; default: return -EINVAL; } return 0; } /* * Rationale: code calling task_setscheduler, task_setioprio, and * task_setnice, assumes that * . if capable(cap_sys_nice), then those actions should be allowed * . if not capable(cap_sys_nice), but acting on your own processes, * then those actions should be allowed * This is insufficient now since you can call code without suid, but * yet with increased caps. * So we check for increased caps on the target process. */ static int cap_safe_nice(struct task_struct *p) { int is_subset, ret = 0; rcu_read_lock(); is_subset = cap_issubset(__task_cred(p)->cap_permitted, current_cred()->cap_permitted); if (!is_subset && !ns_capable(__task_cred(p)->user_ns, CAP_SYS_NICE)) ret = -EPERM; rcu_read_unlock(); return ret; } /** * cap_task_setscheduler - Determine if scheduler policy change is permitted * @p: The task to affect * * Determine if the requested scheduler policy change is permitted for the * specified task. * * Return: 0 if permission is granted, -ve if denied. */ int cap_task_setscheduler(struct task_struct *p) { return cap_safe_nice(p); } /** * cap_task_setioprio - Determine if I/O priority change is permitted * @p: The task to affect * @ioprio: The I/O priority to set * * Determine if the requested I/O priority change is permitted for the specified * task. * * Return: 0 if permission is granted, -ve if denied. */ int cap_task_setioprio(struct task_struct *p, int ioprio) { return cap_safe_nice(p); } /** * cap_task_setnice - Determine if task priority change is permitted * @p: The task to affect * @nice: The nice value to set * * Determine if the requested task priority change is permitted for the * specified task. * * Return: 0 if permission is granted, -ve if denied. */ int cap_task_setnice(struct task_struct *p, int nice) { return cap_safe_nice(p); } /* * Implement PR_CAPBSET_DROP. Attempt to remove the specified capability from * the current task's bounding set. Returns 0 on success, -ve on error. */ static int cap_prctl_drop(unsigned long cap) { struct cred *new; if (!ns_capable(current_user_ns(), CAP_SETPCAP)) return -EPERM; if (!cap_valid(cap)) return -EINVAL; new = prepare_creds(); if (!new) return -ENOMEM; cap_lower(new->cap_bset, cap); return commit_creds(new); } /** * cap_task_prctl - Implement process control functions for this security module * @option: The process control function requested * @arg2: The argument data for this function * @arg3: The argument data for this function * @arg4: The argument data for this function * @arg5: The argument data for this function * * Allow process control functions (sys_prctl()) to alter capabilities; may * also deny access to other functions not otherwise implemented here. * * Return: 0 or +ve on success, -ENOSYS if this function is not implemented * here, other -ve on error. If -ENOSYS is returned, sys_prctl() and other LSM * modules will consider performing the function. */ int cap_task_prctl(int option, unsigned long arg2, unsigned long arg3, unsigned long arg4, unsigned long arg5) { const struct cred *old = current_cred(); struct cred *new; switch (option) { case PR_CAPBSET_READ: if (!cap_valid(arg2)) return -EINVAL; return !!cap_raised(old->cap_bset, arg2); case PR_CAPBSET_DROP: return cap_prctl_drop(arg2); /* * The next four prctl's remain to assist with transitioning a * system from legacy UID=0 based privilege (when filesystem * capabilities are not in use) to a system using filesystem * capabilities only - as the POSIX.1e draft intended. * * Note: * * PR_SET_SECUREBITS = * issecure_mask(SECURE_KEEP_CAPS_LOCKED) * | issecure_mask(SECURE_NOROOT) * | issecure_mask(SECURE_NOROOT_LOCKED) * | issecure_mask(SECURE_NO_SETUID_FIXUP) * | issecure_mask(SECURE_NO_SETUID_FIXUP_LOCKED) * * will ensure that the current process and all of its * children will be locked into a pure * capability-based-privilege environment. */ case PR_SET_SECUREBITS: if ((((old->securebits & SECURE_ALL_LOCKS) >> 1) & (old->securebits ^ arg2)) /*[1]*/ || ((old->securebits & SECURE_ALL_LOCKS & ~arg2)) /*[2]*/ || (arg2 & ~(SECURE_ALL_LOCKS | SECURE_ALL_BITS)) /*[3]*/ || (cap_capable(current_cred(), current_cred()->user_ns, CAP_SETPCAP, CAP_OPT_NONE) != 0) /*[4]*/ /* * [1] no changing of bits that are locked * [2] no unlocking of locks * [3] no setting of unsupported bits * [4] doing anything requires privilege (go read about * the "sendmail capabilities bug") */ ) /* cannot change a locked bit */ return -EPERM; new = prepare_creds(); if (!new) return -ENOMEM; new->securebits = arg2; return commit_creds(new); case PR_GET_SECUREBITS: return old->securebits; case PR_GET_KEEPCAPS: return !!issecure(SECURE_KEEP_CAPS); case PR_SET_KEEPCAPS: if (arg2 > 1) /* Note, we rely on arg2 being unsigned here */ return -EINVAL; if (issecure(SECURE_KEEP_CAPS_LOCKED)) return -EPERM; new = prepare_creds(); if (!new) return -ENOMEM; if (arg2) new->securebits |= issecure_mask(SECURE_KEEP_CAPS); else new->securebits &= ~issecure_mask(SECURE_KEEP_CAPS); return commit_creds(new); case PR_CAP_AMBIENT: if (arg2 == PR_CAP_AMBIENT_CLEAR_ALL) { if (arg3 | arg4 | arg5) return -EINVAL; new = prepare_creds(); if (!new) return -ENOMEM; cap_clear(new->cap_ambient); return commit_creds(new); } if (((!cap_valid(arg3)) | arg4 | arg5)) return -EINVAL; if (arg2 == PR_CAP_AMBIENT_IS_SET) { return !!cap_raised(current_cred()->cap_ambient, arg3); } else if (arg2 != PR_CAP_AMBIENT_RAISE && arg2 != PR_CAP_AMBIENT_LOWER) { return -EINVAL; } else { if (arg2 == PR_CAP_AMBIENT_RAISE && (!cap_raised(current_cred()->cap_permitted, arg3) || !cap_raised(current_cred()->cap_inheritable, arg3) || issecure(SECURE_NO_CAP_AMBIENT_RAISE))) return -EPERM; new = prepare_creds(); if (!new) return -ENOMEM; if (arg2 == PR_CAP_AMBIENT_RAISE) cap_raise(new->cap_ambient, arg3); else cap_lower(new->cap_ambient, arg3); return commit_creds(new); } default: /* No functionality available - continue with default */ return -ENOSYS; } } /** * cap_vm_enough_memory - Determine whether a new virtual mapping is permitted * @mm: The VM space in which the new mapping is to be made * @pages: The size of the mapping * * Determine whether the allocation of a new virtual mapping by the current * task is permitted. * * Return: 0 if permission granted, negative error code if not. */ int cap_vm_enough_memory(struct mm_struct *mm, long pages) { return cap_capable(current_cred(), &init_user_ns, CAP_SYS_ADMIN, CAP_OPT_NOAUDIT); } /** * cap_mmap_addr - check if able to map given addr * @addr: address attempting to be mapped * * If the process is attempting to map memory below dac_mmap_min_addr they need * CAP_SYS_RAWIO. The other parameters to this function are unused by the * capability security module. * * Return: 0 if this mapping should be allowed or -EPERM if not. */ int cap_mmap_addr(unsigned long addr) { int ret = 0; if (addr < dac_mmap_min_addr) { ret = cap_capable(current_cred(), &init_user_ns, CAP_SYS_RAWIO, CAP_OPT_NONE); /* set PF_SUPERPRIV if it turns out we allow the low mmap */ if (ret == 0) current->flags |= PF_SUPERPRIV; } return ret; } int cap_mmap_file(struct file *file, unsigned long reqprot, unsigned long prot, unsigned long flags) { return 0; } #ifdef CONFIG_SECURITY static const struct lsm_id capability_lsmid = { .name = "capability", .id = LSM_ID_CAPABILITY, }; static struct security_hook_list capability_hooks[] __ro_after_init = { LSM_HOOK_INIT(capable, cap_capable), LSM_HOOK_INIT(settime, cap_settime), LSM_HOOK_INIT(ptrace_access_check, cap_ptrace_access_check), LSM_HOOK_INIT(ptrace_traceme, cap_ptrace_traceme), LSM_HOOK_INIT(capget, cap_capget), LSM_HOOK_INIT(capset, cap_capset), LSM_HOOK_INIT(bprm_creds_from_file, cap_bprm_creds_from_file), LSM_HOOK_INIT(inode_need_killpriv, cap_inode_need_killpriv), LSM_HOOK_INIT(inode_killpriv, cap_inode_killpriv), LSM_HOOK_INIT(inode_getsecurity, cap_inode_getsecurity), LSM_HOOK_INIT(mmap_addr, cap_mmap_addr), LSM_HOOK_INIT(mmap_file, cap_mmap_file), LSM_HOOK_INIT(task_fix_setuid, cap_task_fix_setuid), LSM_HOOK_INIT(task_prctl, cap_task_prctl), LSM_HOOK_INIT(task_setscheduler, cap_task_setscheduler), LSM_HOOK_INIT(task_setioprio, cap_task_setioprio), LSM_HOOK_INIT(task_setnice, cap_task_setnice), LSM_HOOK_INIT(vm_enough_memory, cap_vm_enough_memory), }; static int __init capability_init(void) { security_add_hooks(capability_hooks, ARRAY_SIZE(capability_hooks), &capability_lsmid); return 0; } DEFINE_LSM(capability) = { .name = "capability", .order = LSM_ORDER_FIRST, .init = capability_init, }; #endif /* CONFIG_SECURITY */ |
| 8 8 8 8 8 8 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _LINUX_HIGHMEM_H #define _LINUX_HIGHMEM_H #include <linux/fs.h> #include <linux/kernel.h> #include <linux/bug.h> #include <linux/cacheflush.h> #include <linux/kmsan.h> #include <linux/mm.h> #include <linux/uaccess.h> #include <linux/hardirq.h> #include "highmem-internal.h" /** * kmap - Map a page for long term usage * @page: Pointer to the page to be mapped * * Returns: The virtual address of the mapping * * Can only be invoked from preemptible task context because on 32bit * systems with CONFIG_HIGHMEM enabled this function might sleep. * * For systems with CONFIG_HIGHMEM=n and for pages in the low memory area * this returns the virtual address of the direct kernel mapping. * * The returned virtual address is globally visible and valid up to the * point where it is unmapped via kunmap(). The pointer can be handed to * other contexts. * * For highmem pages on 32bit systems this can be slow as the mapping space * is limited and protected by a global lock. In case that there is no * mapping slot available the function blocks until a slot is released via * kunmap(). */ static inline void *kmap(struct page *page); /** * kunmap - Unmap the virtual address mapped by kmap() * @page: Pointer to the page which was mapped by kmap() * * Counterpart to kmap(). A NOOP for CONFIG_HIGHMEM=n and for mappings of * pages in the low memory area. */ static inline void kunmap(struct page *page); /** * kmap_to_page - Get the page for a kmap'ed address * @addr: The address to look up * * Returns: The page which is mapped to @addr. */ static inline struct page *kmap_to_page(void *addr); /** * kmap_flush_unused - Flush all unused kmap mappings in order to * remove stray mappings */ static inline void kmap_flush_unused(void); /** * kmap_local_page - Map a page for temporary usage * @page: Pointer to the page to be mapped * * Returns: The virtual address of the mapping * * Can be invoked from any context, including interrupts. * * Requires careful handling when nesting multiple mappings because the map * management is stack based. The unmap has to be in the reverse order of * the map operation: * * addr1 = kmap_local_page(page1); * addr2 = kmap_local_page(page2); * ... * kunmap_local(addr2); * kunmap_local(addr1); * * Unmapping addr1 before addr2 is invalid and causes malfunction. * * Contrary to kmap() mappings the mapping is only valid in the context of * the caller and cannot be handed to other contexts. * * On CONFIG_HIGHMEM=n kernels and for low memory pages this returns the * virtual address of the direct mapping. Only real highmem pages are * temporarily mapped. * * While kmap_local_page() is significantly faster than kmap() for the highmem * case it comes with restrictions about the pointer validity. * * On HIGHMEM enabled systems mapping a highmem page has the side effect of * disabling migration in order to keep the virtual address stable across * preemption. No caller of kmap_local_page() can rely on this side effect. */ static inline void *kmap_local_page(struct page *page); /** * kmap_local_folio - Map a page in this folio for temporary usage * @folio: The folio containing the page. * @offset: The byte offset within the folio which identifies the page. * * Requires careful handling when nesting multiple mappings because the map * management is stack based. The unmap has to be in the reverse order of * the map operation:: * * addr1 = kmap_local_folio(folio1, offset1); * addr2 = kmap_local_folio(folio2, offset2); * ... * kunmap_local(addr2); * kunmap_local(addr1); * * Unmapping addr1 before addr2 is invalid and causes malfunction. * * Contrary to kmap() mappings the mapping is only valid in the context of * the caller and cannot be handed to other contexts. * * On CONFIG_HIGHMEM=n kernels and for low memory pages this returns the * virtual address of the direct mapping. Only real highmem pages are * temporarily mapped. * * While it is significantly faster than kmap() for the highmem case it * comes with restrictions about the pointer validity. * * On HIGHMEM enabled systems mapping a highmem page has the side effect of * disabling migration in order to keep the virtual address stable across * preemption. No caller of kmap_local_folio() can rely on this side effect. * * Context: Can be invoked from any context. * Return: The virtual address of @offset. */ static inline void *kmap_local_folio(struct folio *folio, size_t offset); /** * kmap_atomic - Atomically map a page for temporary usage - Deprecated! * @page: Pointer to the page to be mapped * * Returns: The virtual address of the mapping * * In fact a wrapper around kmap_local_page() which also disables pagefaults * and, depending on PREEMPT_RT configuration, also CPU migration and * preemption. Therefore users should not count on the latter two side effects. * * Mappings should always be released by kunmap_atomic(). * * Do not use in new code. Use kmap_local_page() instead. * * It is used in atomic context when code wants to access the contents of a * page that might be allocated from high memory (see __GFP_HIGHMEM), for * example a page in the pagecache. The API has two functions, and they * can be used in a manner similar to the following:: * * // Find the page of interest. * struct page *page = find_get_page(mapping, offset); * * // Gain access to the contents of that page. * void *vaddr = kmap_atomic(page); * * // Do something to the contents of that page. * memset(vaddr, 0, PAGE_SIZE); * * // Unmap that page. * kunmap_atomic(vaddr); * * Note that the kunmap_atomic() call takes the result of the kmap_atomic() * call, not the argument. * * If you need to map two pages because you want to copy from one page to * another you need to keep the kmap_atomic calls strictly nested, like: * * vaddr1 = kmap_atomic(page1); * vaddr2 = kmap_atomic(page2); * * memcpy(vaddr1, vaddr2, PAGE_SIZE); * * kunmap_atomic(vaddr2); * kunmap_atomic(vaddr1); */ static inline void *kmap_atomic(struct page *page); /* Highmem related interfaces for management code */ static inline unsigned long nr_free_highpages(void); static inline unsigned long totalhigh_pages(void); #ifndef ARCH_HAS_FLUSH_ANON_PAGE static inline void flush_anon_page(struct vm_area_struct *vma, struct page *page, unsigned long vmaddr) { } #endif #ifndef ARCH_IMPLEMENTS_FLUSH_KERNEL_VMAP_RANGE static inline void flush_kernel_vmap_range(void *vaddr, int size) { } static inline void invalidate_kernel_vmap_range(void *vaddr, int size) { } #endif /* when CONFIG_HIGHMEM is not set these will be plain clear/copy_page */ #ifndef clear_user_highpage static inline void clear_user_highpage(struct page *page, unsigned long vaddr) { void *addr = kmap_local_page(page); clear_user_page(addr, vaddr, page); kunmap_local(addr); } #endif #ifndef vma_alloc_zeroed_movable_folio /** * vma_alloc_zeroed_movable_folio - Allocate a zeroed page for a VMA. * @vma: The VMA the page is to be allocated for. * @vaddr: The virtual address the page will be inserted into. * * This function will allocate a page suitable for inserting into this * VMA at this virtual address. It may be allocated from highmem or * the movable zone. An architecture may provide its own implementation. * * Return: A folio containing one allocated and zeroed page or NULL if * we are out of memory. */ static inline struct folio *vma_alloc_zeroed_movable_folio(struct vm_area_struct *vma, unsigned long vaddr) { return vma_alloc_folio(GFP_HIGHUSER_MOVABLE | __GFP_ZERO, 0, vma, vaddr); } #endif static inline void clear_highpage(struct page *page) { void *kaddr = kmap_local_page(page); clear_page(kaddr); kunmap_local(kaddr); } static inline void clear_highpage_kasan_tagged(struct page *page) { void *kaddr = kmap_local_page(page); clear_page(kasan_reset_tag(kaddr)); kunmap_local(kaddr); } #ifndef __HAVE_ARCH_TAG_CLEAR_HIGHPAGE static inline void tag_clear_highpage(struct page *page) { } #endif /* * If we pass in a base or tail page, we can zero up to PAGE_SIZE. * If we pass in a head page, we can zero up to the size of the compound page. */ #ifdef CONFIG_HIGHMEM void zero_user_segments(struct page *page, unsigned start1, unsigned end1, unsigned start2, unsigned end2); #else static inline void zero_user_segments(struct page *page, unsigned start1, unsigned end1, unsigned start2, unsigned end2) { void *kaddr = kmap_local_page(page); unsigned int i; BUG_ON(end1 > page_size(page) || end2 > page_size(page)); if (end1 > start1) memset(kaddr + start1, 0, end1 - start1); if (end2 > start2) memset(kaddr + start2, 0, end2 - start2); kunmap_local(kaddr); for (i = 0; i < compound_nr(page); i++) flush_dcache_page(page + i); } #endif static inline void zero_user_segment(struct page *page, unsigned start, unsigned end) { zero_user_segments(page, start, end, 0, 0); } static inline void zero_user(struct page *page, unsigned start, unsigned size) { zero_user_segments(page, start, start + size, 0, 0); } #ifndef __HAVE_ARCH_COPY_USER_HIGHPAGE static inline void copy_user_highpage(struct page *to, struct page *from, unsigned long vaddr, struct vm_area_struct *vma) { char *vfrom, *vto; vfrom = kmap_local_page(from); vto = kmap_local_page(to); copy_user_page(vto, vfrom, vaddr, to); kmsan_unpoison_memory(page_address(to), PAGE_SIZE); kunmap_local(vto); kunmap_local(vfrom); } #endif #ifndef __HAVE_ARCH_COPY_HIGHPAGE static inline void copy_highpage(struct page *to, struct page *from) { char *vfrom, *vto; vfrom = kmap_local_page(from); vto = kmap_local_page(to); copy_page(vto, vfrom); kmsan_copy_page_meta(to, from); kunmap_local(vto); kunmap_local(vfrom); } #endif #ifdef copy_mc_to_kernel /* * If architecture supports machine check exception handling, define the * #MC versions of copy_user_highpage and copy_highpage. They copy a memory * page with #MC in source page (@from) handled, and return the number * of bytes not copied if there was a #MC, otherwise 0 for success. */ static inline int copy_mc_user_highpage(struct page *to, struct page *from, unsigned long vaddr, struct vm_area_struct *vma) { unsigned long ret; char *vfrom, *vto; vfrom = kmap_local_page(from); vto = kmap_local_page(to); ret = copy_mc_to_kernel(vto, vfrom, PAGE_SIZE); if (!ret) kmsan_unpoison_memory(page_address(to), PAGE_SIZE); kunmap_local(vto); kunmap_local(vfrom); if (ret) memory_failure_queue(page_to_pfn(from), 0); return ret; } static inline int copy_mc_highpage(struct page *to, struct page *from) { unsigned long ret; char *vfrom, *vto; vfrom = kmap_local_page(from); vto = kmap_local_page(to); ret = copy_mc_to_kernel(vto, vfrom, PAGE_SIZE); if (!ret) kmsan_copy_page_meta(to, from); kunmap_local(vto); kunmap_local(vfrom); if (ret) memory_failure_queue(page_to_pfn(from), 0); return ret; } #else static inline int copy_mc_user_highpage(struct page *to, struct page *from, unsigned long vaddr, struct vm_area_struct *vma) { copy_user_highpage(to, from, vaddr, vma); return 0; } static inline int copy_mc_highpage(struct page *to, struct page *from) { copy_highpage(to, from); return 0; } #endif static inline void memcpy_page(struct page *dst_page, size_t dst_off, struct page *src_page, size_t src_off, size_t len) { char *dst = kmap_local_page(dst_page); char *src = kmap_local_page(src_page); VM_BUG_ON(dst_off + len > PAGE_SIZE || src_off + len > PAGE_SIZE); memcpy(dst + dst_off, src + src_off, len); kunmap_local(src); kunmap_local(dst); } static inline void memset_page(struct page *page, size_t offset, int val, size_t len) { char *addr = kmap_local_page(page); VM_BUG_ON(offset + len > PAGE_SIZE); memset(addr + offset, val, len); kunmap_local(addr); } static inline void memcpy_from_page(char *to, struct page *page, size_t offset, size_t len) { char *from = kmap_local_page(page); VM_BUG_ON(offset + len > PAGE_SIZE); memcpy(to, from + offset, len); kunmap_local(from); } static inline void memcpy_to_page(struct page *page, size_t offset, const char *from, size_t len) { char *to = kmap_local_page(page); VM_BUG_ON(offset + len > PAGE_SIZE); memcpy(to + offset, from, len); flush_dcache_page(page); kunmap_local(to); } static inline void memzero_page(struct page *page, size_t offset, size_t len) { char *addr = kmap_local_page(page); VM_BUG_ON(offset + len > PAGE_SIZE); memset(addr + offset, 0, len); flush_dcache_page(page); kunmap_local(addr); } /** * memcpy_from_folio - Copy a range of bytes from a folio. * @to: The memory to copy to. * @folio: The folio to read from. * @offset: The first byte in the folio to read. * @len: The number of bytes to copy. */ static inline void memcpy_from_folio(char *to, struct folio *folio, size_t offset, size_t len) { VM_BUG_ON(offset + len > folio_size(folio)); do { const char *from = kmap_local_folio(folio, offset); size_t chunk = len; if (folio_test_highmem(folio) && chunk > PAGE_SIZE - offset_in_page(offset)) chunk = PAGE_SIZE - offset_in_page(offset); memcpy(to, from, chunk); kunmap_local(from); to += chunk; offset += chunk; len -= chunk; } while (len > 0); } /** * memcpy_to_folio - Copy a range of bytes to a folio. * @folio: The folio to write to. * @offset: The first byte in the folio to store to. * @from: The memory to copy from. * @len: The number of bytes to copy. */ static inline void memcpy_to_folio(struct folio *folio, size_t offset, const char *from, size_t len) { VM_BUG_ON(offset + len > folio_size(folio)); do { char *to = kmap_local_folio(folio, offset); size_t chunk = len; if (folio_test_highmem(folio) && chunk > PAGE_SIZE - offset_in_page(offset)) chunk = PAGE_SIZE - offset_in_page(offset); memcpy(to, from, chunk); kunmap_local(to); from += chunk; offset += chunk; len -= chunk; } while (len > 0); flush_dcache_folio(folio); } /** * folio_zero_tail - Zero the tail of a folio. * @folio: The folio to zero. * @offset: The byte offset in the folio to start zeroing at. * @kaddr: The address the folio is currently mapped to. * * If you have already used kmap_local_folio() to map a folio, written * some data to it and now need to zero the end of the folio (and flush * the dcache), you can use this function. If you do not have the * folio kmapped (eg the folio has been partially populated by DMA), * use folio_zero_range() or folio_zero_segment() instead. * * Return: An address which can be passed to kunmap_local(). */ static inline __must_check void *folio_zero_tail(struct folio *folio, size_t offset, void *kaddr) { size_t len = folio_size(folio) - offset; if (folio_test_highmem(folio)) { size_t max = PAGE_SIZE - offset_in_page(offset); while (len > max) { memset(kaddr, 0, max); kunmap_local(kaddr); len -= max; offset += max; max = PAGE_SIZE; kaddr = kmap_local_folio(folio, offset); } } memset(kaddr, 0, len); flush_dcache_folio(folio); return kaddr; } /** * folio_fill_tail - Copy some data to a folio and pad with zeroes. * @folio: The destination folio. * @offset: The offset into @folio at which to start copying. * @from: The data to copy. * @len: How many bytes of data to copy. * * This function is most useful for filesystems which support inline data. * When they want to copy data from the inode into the page cache, this * function does everything for them. It supports large folios even on * HIGHMEM configurations. */ static inline void folio_fill_tail(struct folio *folio, size_t offset, const char *from, size_t len) { char *to = kmap_local_folio(folio, offset); VM_BUG_ON(offset + len > folio_size(folio)); if (folio_test_highmem(folio)) { size_t max = PAGE_SIZE - offset_in_page(offset); while (len > max) { memcpy(to, from, max); kunmap_local(to); len -= max; from += max; offset += max; max = PAGE_SIZE; to = kmap_local_folio(folio, offset); } } memcpy(to, from, len); to = folio_zero_tail(folio, offset + len, to + len); kunmap_local(to); } /** * memcpy_from_file_folio - Copy some bytes from a file folio. * @to: The destination buffer. * @folio: The folio to copy from. * @pos: The position in the file. * @len: The maximum number of bytes to copy. * * Copy up to @len bytes from this folio. This may be limited by PAGE_SIZE * if the folio comes from HIGHMEM, and by the size of the folio. * * Return: The number of bytes copied from the folio. */ static inline size_t memcpy_from_file_folio(char *to, struct folio *folio, loff_t pos, size_t len) { size_t offset = offset_in_folio(folio, pos); char *from = kmap_local_folio(folio, offset); if (folio_test_highmem(folio)) { offset = offset_in_page(offset); len = min_t(size_t, len, PAGE_SIZE - offset); } else len = min(len, folio_size(folio) - offset); memcpy(to, from, len); kunmap_local(from); return len; } /** * folio_zero_segments() - Zero two byte ranges in a folio. * @folio: The folio to write to. * @start1: The first byte to zero. * @xend1: One more than the last byte in the first range. * @start2: The first byte to zero in the second range. * @xend2: One more than the last byte in the second range. */ static inline void folio_zero_segments(struct folio *folio, size_t start1, size_t xend1, size_t start2, size_t xend2) { zero_user_segments(&folio->page, start1, xend1, start2, xend2); } /** * folio_zero_segment() - Zero a byte range in a folio. * @folio: The folio to write to. * @start: The first byte to zero. * @xend: One more than the last byte to zero. */ static inline void folio_zero_segment(struct folio *folio, size_t start, size_t xend) { zero_user_segments(&folio->page, start, xend, 0, 0); } /** * folio_zero_range() - Zero a byte range in a folio. * @folio: The folio to write to. * @start: The first byte to zero. * @length: The number of bytes to zero. */ static inline void folio_zero_range(struct folio *folio, size_t start, size_t length) { zero_user_segments(&folio->page, start, start + length, 0, 0); } /** * folio_release_kmap - Unmap a folio and drop a refcount. * @folio: The folio to release. * @addr: The address previously returned by a call to kmap_local_folio(). * * It is common, eg in directory handling to kmap a folio. This function * unmaps the folio and drops the refcount that was being held to keep the * folio alive while we accessed it. */ static inline void folio_release_kmap(struct folio *folio, void *addr) { kunmap_local(addr); folio_put(folio); } static inline void unmap_and_put_page(struct page *page, void *addr) { folio_release_kmap(page_folio(page), addr); } #endif /* _LINUX_HIGHMEM_H */ |
| 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 | /* SPDX-License-Identifier: GPL-2.0-or-later */ /* * VLAN An implementation of 802.1Q VLAN tagging. * * Authors: Ben Greear <greearb@candelatech.com> */ #ifndef _LINUX_IF_VLAN_H_ #define _LINUX_IF_VLAN_H_ #include <linux/netdevice.h> #include <linux/etherdevice.h> #include <linux/rtnetlink.h> #include <linux/bug.h> #include <uapi/linux/if_vlan.h> #define VLAN_HLEN 4 /* The additional bytes required by VLAN * (in addition to the Ethernet header) */ #define VLAN_ETH_HLEN 18 /* Total octets in header. */ #define VLAN_ETH_ZLEN 64 /* Min. octets in frame sans FCS */ /* * According to 802.3ac, the packet can be 4 bytes longer. --Klika Jan */ #define VLAN_ETH_DATA_LEN 1500 /* Max. octets in payload */ #define VLAN_ETH_FRAME_LEN 1518 /* Max. octets in frame sans FCS */ #define VLAN_MAX_DEPTH 8 /* Max. number of nested VLAN tags parsed */ /* * struct vlan_hdr - vlan header * @h_vlan_TCI: priority and VLAN ID * @h_vlan_encapsulated_proto: packet type ID or len */ struct vlan_hdr { __be16 h_vlan_TCI; __be16 h_vlan_encapsulated_proto; }; /** * struct vlan_ethhdr - vlan ethernet header (ethhdr + vlan_hdr) * @h_dest: destination ethernet address * @h_source: source ethernet address * @h_vlan_proto: ethernet protocol * @h_vlan_TCI: priority and VLAN ID * @h_vlan_encapsulated_proto: packet type ID or len */ struct vlan_ethhdr { struct_group(addrs, unsigned char h_dest[ETH_ALEN]; unsigned char h_source[ETH_ALEN]; ); __be16 h_vlan_proto; __be16 h_vlan_TCI; __be16 h_vlan_encapsulated_proto; }; #include <linux/skbuff.h> static inline struct vlan_ethhdr *vlan_eth_hdr(const struct sk_buff *skb) { return (struct vlan_ethhdr *)skb_mac_header(skb); } /* Prefer this version in TX path, instead of * skb_reset_mac_header() + vlan_eth_hdr() */ static inline struct vlan_ethhdr *skb_vlan_eth_hdr(const struct sk_buff *skb) { return (struct vlan_ethhdr *)skb->data; } #define VLAN_PRIO_MASK 0xe000 /* Priority Code Point */ #define VLAN_PRIO_SHIFT 13 #define VLAN_CFI_MASK 0x1000 /* Canonical Format Indicator / Drop Eligible Indicator */ #define VLAN_VID_MASK 0x0fff /* VLAN Identifier */ #define VLAN_N_VID 4096 /* found in socket.c */ extern void vlan_ioctl_set(int (*hook)(struct net *, void __user *)); static inline bool is_vlan_dev(const struct net_device *dev) { return dev->priv_flags & IFF_802_1Q_VLAN; } #define skb_vlan_tag_present(__skb) (!!(__skb)->vlan_all) #define skb_vlan_tag_get(__skb) ((__skb)->vlan_tci) #define skb_vlan_tag_get_id(__skb) ((__skb)->vlan_tci & VLAN_VID_MASK) #define skb_vlan_tag_get_cfi(__skb) (!!((__skb)->vlan_tci & VLAN_CFI_MASK)) #define skb_vlan_tag_get_prio(__skb) (((__skb)->vlan_tci & VLAN_PRIO_MASK) >> VLAN_PRIO_SHIFT) static inline int vlan_get_rx_ctag_filter_info(struct net_device *dev) { ASSERT_RTNL(); return notifier_to_errno(call_netdevice_notifiers(NETDEV_CVLAN_FILTER_PUSH_INFO, dev)); } static inline void vlan_drop_rx_ctag_filter_info(struct net_device *dev) { ASSERT_RTNL(); call_netdevice_notifiers(NETDEV_CVLAN_FILTER_DROP_INFO, dev); } static inline int vlan_get_rx_stag_filter_info(struct net_device *dev) { ASSERT_RTNL(); return notifier_to_errno(call_netdevice_notifiers(NETDEV_SVLAN_FILTER_PUSH_INFO, dev)); } static inline void vlan_drop_rx_stag_filter_info(struct net_device *dev) { ASSERT_RTNL(); call_netdevice_notifiers(NETDEV_SVLAN_FILTER_DROP_INFO, dev); } /** * struct vlan_pcpu_stats - VLAN percpu rx/tx stats * @rx_packets: number of received packets * @rx_bytes: number of received bytes * @rx_multicast: number of received multicast packets * @tx_packets: number of transmitted packets * @tx_bytes: number of transmitted bytes * @syncp: synchronization point for 64bit counters * @rx_errors: number of rx errors * @tx_dropped: number of tx drops */ struct vlan_pcpu_stats { u64_stats_t rx_packets; u64_stats_t rx_bytes; u64_stats_t rx_multicast; u64_stats_t tx_packets; u64_stats_t tx_bytes; struct u64_stats_sync syncp; u32 rx_errors; u32 tx_dropped; }; #if defined(CONFIG_VLAN_8021Q) || defined(CONFIG_VLAN_8021Q_MODULE) extern struct net_device *__vlan_find_dev_deep_rcu(struct net_device *real_dev, __be16 vlan_proto, u16 vlan_id); extern int vlan_for_each(struct net_device *dev, int (*action)(struct net_device *dev, int vid, void *arg), void *arg); extern struct net_device *vlan_dev_real_dev(const struct net_device *dev); extern u16 vlan_dev_vlan_id(const struct net_device *dev); extern __be16 vlan_dev_vlan_proto(const struct net_device *dev); /** * struct vlan_priority_tci_mapping - vlan egress priority mappings * @priority: skb priority * @vlan_qos: vlan priority: (skb->priority << 13) & 0xE000 * @next: pointer to next struct */ struct vlan_priority_tci_mapping { u32 priority; u16 vlan_qos; struct vlan_priority_tci_mapping *next; }; struct proc_dir_entry; struct netpoll; /** * struct vlan_dev_priv - VLAN private device data * @nr_ingress_mappings: number of ingress priority mappings * @ingress_priority_map: ingress priority mappings * @nr_egress_mappings: number of egress priority mappings * @egress_priority_map: hash of egress priority mappings * @vlan_proto: VLAN encapsulation protocol * @vlan_id: VLAN identifier * @flags: device flags * @real_dev: underlying netdevice * @dev_tracker: refcount tracker for @real_dev reference * @real_dev_addr: address of underlying netdevice * @dent: proc dir entry * @vlan_pcpu_stats: ptr to percpu rx stats */ struct vlan_dev_priv { unsigned int nr_ingress_mappings; u32 ingress_priority_map[8]; unsigned int nr_egress_mappings; struct vlan_priority_tci_mapping *egress_priority_map[16]; __be16 vlan_proto; u16 vlan_id; u16 flags; struct net_device *real_dev; netdevice_tracker dev_tracker; unsigned char real_dev_addr[ETH_ALEN]; struct proc_dir_entry *dent; struct vlan_pcpu_stats __percpu *vlan_pcpu_stats; #ifdef CONFIG_NET_POLL_CONTROLLER struct netpoll *netpoll; #endif }; static inline struct vlan_dev_priv *vlan_dev_priv(const struct net_device *dev) { return netdev_priv(dev); } static inline u16 vlan_dev_get_egress_qos_mask(struct net_device *dev, u32 skprio) { struct vlan_priority_tci_mapping *mp; smp_rmb(); /* coupled with smp_wmb() in vlan_dev_set_egress_priority() */ mp = vlan_dev_priv(dev)->egress_priority_map[(skprio & 0xF)]; while (mp) { if (mp->priority == skprio) { return mp->vlan_qos; /* This should already be shifted * to mask correctly with the * VLAN's TCI */ } mp = mp->next; } return 0; } extern bool vlan_do_receive(struct sk_buff **skb); extern int vlan_vid_add(struct net_device *dev, __be16 proto, u16 vid); extern void vlan_vid_del(struct net_device *dev, __be16 proto, u16 vid); extern int vlan_vids_add_by_dev(struct net_device *dev, const struct net_device *by_dev); extern void vlan_vids_del_by_dev(struct net_device *dev, const struct net_device *by_dev); extern bool vlan_uses_dev(const struct net_device *dev); #else static inline struct net_device * __vlan_find_dev_deep_rcu(struct net_device *real_dev, __be16 vlan_proto, u16 vlan_id) { return NULL; } static inline int vlan_for_each(struct net_device *dev, int (*action)(struct net_device *dev, int vid, void *arg), void *arg) { return 0; } static inline struct net_device *vlan_dev_real_dev(const struct net_device *dev) { BUG(); return NULL; } static inline u16 vlan_dev_vlan_id(const struct net_device *dev) { BUG(); return 0; } static inline __be16 vlan_dev_vlan_proto(const struct net_device *dev) { BUG(); return 0; } static inline u16 vlan_dev_get_egress_qos_mask(struct net_device *dev, u32 skprio) { return 0; } static inline bool vlan_do_receive(struct sk_buff **skb) { return false; } static inline int vlan_vid_add(struct net_device *dev, __be16 proto, u16 vid) { return 0; } static inline void vlan_vid_del(struct net_device *dev, __be16 proto, u16 vid) { } static inline int vlan_vids_add_by_dev(struct net_device *dev, const struct net_device *by_dev) { return 0; } static inline void vlan_vids_del_by_dev(struct net_device *dev, const struct net_device *by_dev) { } static inline bool vlan_uses_dev(const struct net_device *dev) { return false; } #endif /** * eth_type_vlan - check for valid vlan ether type. * @ethertype: ether type to check * * Returns true if the ether type is a vlan ether type. */ static inline bool eth_type_vlan(__be16 ethertype) { switch (ethertype) { case htons(ETH_P_8021Q): case htons(ETH_P_8021AD): return true; default: return false; } } static inline bool vlan_hw_offload_capable(netdev_features_t features, __be16 proto) { if (proto == htons(ETH_P_8021Q) && features & NETIF_F_HW_VLAN_CTAG_TX) return true; if (proto == htons(ETH_P_8021AD) && features & NETIF_F_HW_VLAN_STAG_TX) return true; return false; } /** * __vlan_insert_inner_tag - inner VLAN tag inserting * @skb: skbuff to tag * @vlan_proto: VLAN encapsulation protocol * @vlan_tci: VLAN TCI to insert * @mac_len: MAC header length including outer vlan headers * * Inserts the VLAN tag into @skb as part of the payload at offset mac_len * Returns error if skb_cow_head fails. * * Does not change skb->protocol so this function can be used during receive. */ static inline int __vlan_insert_inner_tag(struct sk_buff *skb, __be16 vlan_proto, u16 vlan_tci, unsigned int mac_len) { struct vlan_ethhdr *veth; if (skb_cow_head(skb, VLAN_HLEN) < 0) return -ENOMEM; skb_push(skb, VLAN_HLEN); /* Move the mac header sans proto to the beginning of the new header. */ if (likely(mac_len > ETH_TLEN)) memmove(skb->data, skb->data + VLAN_HLEN, mac_len - ETH_TLEN); if (skb_mac_header_was_set(skb)) skb->mac_header -= VLAN_HLEN; veth = (struct vlan_ethhdr *)(skb->data + mac_len - ETH_HLEN); /* first, the ethernet type */ if (likely(mac_len >= ETH_TLEN)) { /* h_vlan_encapsulated_proto should already be populated, and * skb->data has space for h_vlan_proto */ veth->h_vlan_proto = vlan_proto; } else { /* h_vlan_encapsulated_proto should not be populated, and * skb->data has no space for h_vlan_proto */ veth->h_vlan_encapsulated_proto = skb->protocol; } /* now, the TCI */ veth->h_vlan_TCI = htons(vlan_tci); return 0; } /** * __vlan_insert_tag - regular VLAN tag inserting * @skb: skbuff to tag * @vlan_proto: VLAN encapsulation protocol * @vlan_tci: VLAN TCI to insert * * Inserts the VLAN tag into @skb as part of the payload * Returns error if skb_cow_head fails. * * Does not change skb->protocol so this function can be used during receive. */ static inline int __vlan_insert_tag(struct sk_buff *skb, __be16 vlan_proto, u16 vlan_tci) { return __vlan_insert_inner_tag(skb, vlan_proto, vlan_tci, ETH_HLEN); } /** * vlan_insert_inner_tag - inner VLAN tag inserting * @skb: skbuff to tag * @vlan_proto: VLAN encapsulation protocol * @vlan_tci: VLAN TCI to insert * @mac_len: MAC header length including outer vlan headers * * Inserts the VLAN tag into @skb as part of the payload at offset mac_len * Returns a VLAN tagged skb. This might change skb->head. * * Following the skb_unshare() example, in case of error, the calling function * doesn't have to worry about freeing the original skb. * * Does not change skb->protocol so this function can be used during receive. */ static inline struct sk_buff *vlan_insert_inner_tag(struct sk_buff *skb, __be16 vlan_proto, u16 vlan_tci, unsigned int mac_len) { int err; err = __vlan_insert_inner_tag(skb, vlan_proto, vlan_tci, mac_len); if (err) { dev_kfree_skb_any(skb); return NULL; } return skb; } /** * vlan_insert_tag - regular VLAN tag inserting * @skb: skbuff to tag * @vlan_proto: VLAN encapsulation protocol * @vlan_tci: VLAN TCI to insert * * Inserts the VLAN tag into @skb as part of the payload * Returns a VLAN tagged skb. This might change skb->head. * * Following the skb_unshare() example, in case of error, the calling function * doesn't have to worry about freeing the original skb. * * Does not change skb->protocol so this function can be used during receive. */ static inline struct sk_buff *vlan_insert_tag(struct sk_buff *skb, __be16 vlan_proto, u16 vlan_tci) { return vlan_insert_inner_tag(skb, vlan_proto, vlan_tci, ETH_HLEN); } /** * vlan_insert_tag_set_proto - regular VLAN tag inserting * @skb: skbuff to tag * @vlan_proto: VLAN encapsulation protocol * @vlan_tci: VLAN TCI to insert * * Inserts the VLAN tag into @skb as part of the payload * Returns a VLAN tagged skb. This might change skb->head. * * Following the skb_unshare() example, in case of error, the calling function * doesn't have to worry about freeing the original skb. */ static inline struct sk_buff *vlan_insert_tag_set_proto(struct sk_buff *skb, __be16 vlan_proto, u16 vlan_tci) { skb = vlan_insert_tag(skb, vlan_proto, vlan_tci); if (skb) skb->protocol = vlan_proto; return skb; } /** * __vlan_hwaccel_clear_tag - clear hardware accelerated VLAN info * @skb: skbuff to clear * * Clears the VLAN information from @skb */ static inline void __vlan_hwaccel_clear_tag(struct sk_buff *skb) { skb->vlan_all = 0; } /** * __vlan_hwaccel_copy_tag - copy hardware accelerated VLAN info from another skb * @dst: skbuff to copy to * @src: skbuff to copy from * * Copies VLAN information from @src to @dst (for branchless code) */ static inline void __vlan_hwaccel_copy_tag(struct sk_buff *dst, const struct sk_buff *src) { dst->vlan_all = src->vlan_all; } /* * __vlan_hwaccel_push_inside - pushes vlan tag to the payload * @skb: skbuff to tag * * Pushes the VLAN tag from @skb->vlan_tci inside to the payload. * * Following the skb_unshare() example, in case of error, the calling function * doesn't have to worry about freeing the original skb. */ static inline struct sk_buff *__vlan_hwaccel_push_inside(struct sk_buff *skb) { skb = vlan_insert_tag_set_proto(skb, skb->vlan_proto, skb_vlan_tag_get(skb)); if (likely(skb)) __vlan_hwaccel_clear_tag(skb); return skb; } /** * __vlan_hwaccel_put_tag - hardware accelerated VLAN inserting * @skb: skbuff to tag * @vlan_proto: VLAN encapsulation protocol * @vlan_tci: VLAN TCI to insert * * Puts the VLAN TCI in @skb->vlan_tci and lets the device do the rest */ static inline void __vlan_hwaccel_put_tag(struct sk_buff *skb, __be16 vlan_proto, u16 vlan_tci) { skb->vlan_proto = vlan_proto; skb->vlan_tci = vlan_tci; } /** * __vlan_get_tag - get the VLAN ID that is part of the payload * @skb: skbuff to query * @vlan_tci: buffer to store value * * Returns error if the skb is not of VLAN type */ static inline int __vlan_get_tag(const struct sk_buff *skb, u16 *vlan_tci) { struct vlan_ethhdr *veth = skb_vlan_eth_hdr(skb); if (!eth_type_vlan(veth->h_vlan_proto)) return -ENODATA; *vlan_tci = ntohs(veth->h_vlan_TCI); return 0; } /** * __vlan_hwaccel_get_tag - get the VLAN ID that is in @skb->cb[] * @skb: skbuff to query * @vlan_tci: buffer to store value * * Returns error if @skb->vlan_tci is not set correctly */ static inline int __vlan_hwaccel_get_tag(const struct sk_buff *skb, u16 *vlan_tci) { if (skb_vlan_tag_present(skb)) { *vlan_tci = skb_vlan_tag_get(skb); return 0; } else { *vlan_tci = 0; return -ENODATA; } } /** * vlan_get_tag - get the VLAN ID from the skb * @skb: skbuff to query * @vlan_tci: buffer to store value * * Returns error if the skb is not VLAN tagged */ static inline int vlan_get_tag(const struct sk_buff *skb, u16 *vlan_tci) { if (skb->dev->features & NETIF_F_HW_VLAN_CTAG_TX) { return __vlan_hwaccel_get_tag(skb, vlan_tci); } else { return __vlan_get_tag(skb, vlan_tci); } } /** * vlan_get_protocol - get protocol EtherType. * @skb: skbuff to query * @type: first vlan protocol * @depth: buffer to store length of eth and vlan tags in bytes * * Returns the EtherType of the packet, regardless of whether it is * vlan encapsulated (normal or hardware accelerated) or not. */ static inline __be16 __vlan_get_protocol(const struct sk_buff *skb, __be16 type, int *depth) { unsigned int vlan_depth = skb->mac_len, parse_depth = VLAN_MAX_DEPTH; /* if type is 802.1Q/AD then the header should already be * present at mac_len - VLAN_HLEN (if mac_len > 0), or at * ETH_HLEN otherwise */ if (eth_type_vlan(type)) { if (vlan_depth) { if (WARN_ON(vlan_depth < VLAN_HLEN)) return 0; vlan_depth -= VLAN_HLEN; } else { vlan_depth = ETH_HLEN; } do { struct vlan_hdr vhdr, *vh; vh = skb_header_pointer(skb, vlan_depth, sizeof(vhdr), &vhdr); if (unlikely(!vh || !--parse_depth)) return 0; type = vh->h_vlan_encapsulated_proto; vlan_depth += VLAN_HLEN; } while (eth_type_vlan(type)); } if (depth) *depth = vlan_depth; return type; } /** * vlan_get_protocol - get protocol EtherType. * @skb: skbuff to query * * Returns the EtherType of the packet, regardless of whether it is * vlan encapsulated (normal or hardware accelerated) or not. */ static inline __be16 vlan_get_protocol(const struct sk_buff *skb) { return __vlan_get_protocol(skb, skb->protocol, NULL); } /* This version of __vlan_get_protocol() also pulls mac header in skb->head */ static inline __be16 vlan_get_protocol_and_depth(struct sk_buff *skb, __be16 type, int *depth) { int maclen; type = __vlan_get_protocol(skb, type, &maclen); if (type) { if (!pskb_may_pull(skb, maclen)) type = 0; else if (depth) *depth = maclen; } return type; } /* A getter for the SKB protocol field which will handle VLAN tags consistently * whether VLAN acceleration is enabled or not. */ static inline __be16 skb_protocol(const struct sk_buff *skb, bool skip_vlan) { if (!skip_vlan) /* VLAN acceleration strips the VLAN header from the skb and * moves it to skb->vlan_proto */ return skb_vlan_tag_present(skb) ? skb->vlan_proto : skb->protocol; return vlan_get_protocol(skb); } static inline void vlan_set_encap_proto(struct sk_buff *skb, struct vlan_hdr *vhdr) { __be16 proto; unsigned short *rawp; /* * Was a VLAN packet, grab the encapsulated protocol, which the layer * three protocols care about. */ proto = vhdr->h_vlan_encapsulated_proto; if (eth_proto_is_802_3(proto)) { skb->protocol = proto; return; } rawp = (unsigned short *)(vhdr + 1); if (*rawp == 0xFFFF) /* * This is a magic hack to spot IPX packets. Older Novell * breaks the protocol design and runs IPX over 802.3 without * an 802.2 LLC layer. We look for FFFF which isn't a used * 802.2 SSAP/DSAP. This won't work for fault tolerant netware * but does for the rest. */ skb->protocol = htons(ETH_P_802_3); else /* * Real 802.2 LLC */ skb->protocol = htons(ETH_P_802_2); } /** * vlan_remove_tag - remove outer VLAN tag from payload * @skb: skbuff to remove tag from * @vlan_tci: buffer to store value * * Expects the skb to contain a VLAN tag in the payload, and to have skb->data * pointing at the MAC header. * * Returns a new pointer to skb->data, or NULL on failure to pull. */ static inline void *vlan_remove_tag(struct sk_buff *skb, u16 *vlan_tci) { struct vlan_hdr *vhdr = (struct vlan_hdr *)(skb->data + ETH_HLEN); *vlan_tci = ntohs(vhdr->h_vlan_TCI); memmove(skb->data + VLAN_HLEN, skb->data, 2 * ETH_ALEN); vlan_set_encap_proto(skb, vhdr); return __skb_pull(skb, VLAN_HLEN); } /** * skb_vlan_tagged - check if skb is vlan tagged. * @skb: skbuff to query * * Returns true if the skb is tagged, regardless of whether it is hardware * accelerated or not. */ static inline bool skb_vlan_tagged(const struct sk_buff *skb) { if (!skb_vlan_tag_present(skb) && likely(!eth_type_vlan(skb->protocol))) return false; return true; } /** * skb_vlan_tagged_multi - check if skb is vlan tagged with multiple headers. * @skb: skbuff to query * * Returns true if the skb is tagged with multiple vlan headers, regardless * of whether it is hardware accelerated or not. */ static inline bool skb_vlan_tagged_multi(struct sk_buff *skb) { __be16 protocol = skb->protocol; if (!skb_vlan_tag_present(skb)) { struct vlan_ethhdr *veh; if (likely(!eth_type_vlan(protocol))) return false; if (unlikely(!pskb_may_pull(skb, VLAN_ETH_HLEN))) return false; veh = skb_vlan_eth_hdr(skb); protocol = veh->h_vlan_encapsulated_proto; } if (!eth_type_vlan(protocol)) return false; return true; } /** * vlan_features_check - drop unsafe features for skb with multiple tags. * @skb: skbuff to query * @features: features to be checked * * Returns features without unsafe ones if the skb has multiple tags. */ static inline netdev_features_t vlan_features_check(struct sk_buff *skb, netdev_features_t features) { if (skb_vlan_tagged_multi(skb)) { /* In the case of multi-tagged packets, use a direct mask * instead of using netdev_interesect_features(), to make * sure that only devices supporting NETIF_F_HW_CSUM will * have checksum offloading support. */ features &= NETIF_F_SG | NETIF_F_HIGHDMA | NETIF_F_HW_CSUM | NETIF_F_FRAGLIST | NETIF_F_HW_VLAN_CTAG_TX | NETIF_F_HW_VLAN_STAG_TX; } return features; } /** * compare_vlan_header - Compare two vlan headers * @h1: Pointer to vlan header * @h2: Pointer to vlan header * * Compare two vlan headers, returns 0 if equal. * * Please note that alignment of h1 & h2 are only guaranteed to be 16 bits. */ static inline unsigned long compare_vlan_header(const struct vlan_hdr *h1, const struct vlan_hdr *h2) { #if defined(CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS) return *(u32 *)h1 ^ *(u32 *)h2; #else return ((__force u32)h1->h_vlan_TCI ^ (__force u32)h2->h_vlan_TCI) | ((__force u32)h1->h_vlan_encapsulated_proto ^ (__force u32)h2->h_vlan_encapsulated_proto); #endif } #endif /* !(_LINUX_IF_VLAN_H_) */ |
| 36 36 36 36 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 1522 1523 1524 1525 1526 1527 1528 1529 1530 1531 1532 1533 1534 1535 1536 1537 1538 1539 1540 1541 1542 1543 1544 1545 1546 1547 1548 1549 1550 1551 1552 1553 1554 1555 1556 1557 1558 1559 1560 1561 1562 1563 1564 1565 1566 1567 1568 1569 1570 1571 1572 1573 1574 1575 1576 1577 1578 1579 1580 1581 1582 1583 1584 1585 1586 1587 1588 1589 1590 1591 1592 1593 1594 1595 1596 1597 1598 1599 1600 1601 1602 1603 1604 1605 1606 1607 1608 1609 1610 1611 1612 1613 1614 1615 1616 1617 1618 1619 1620 1621 1622 1623 1624 1625 1626 1627 1628 1629 1630 1631 1632 1633 1634 1635 1636 1637 1638 1639 1640 1641 1642 1643 1644 1645 1646 1647 1648 1649 1650 1651 1652 1653 1654 1655 1656 1657 1658 1659 1660 1661 1662 1663 1664 1665 1666 1667 1668 1669 1670 1671 1672 1673 1674 1675 1676 1677 1678 1679 1680 1681 1682 1683 1684 1685 1686 1687 1688 1689 1690 1691 1692 1693 1694 1695 1696 1697 1698 1699 1700 1701 1702 1703 1704 1705 1706 1707 1708 1709 1710 1711 1712 1713 1714 1715 1716 1717 1718 1719 1720 1721 1722 1723 1724 1725 1726 1727 1728 1729 1730 1731 1732 1733 1734 1735 1736 1737 1738 1739 1740 1741 1742 1743 1744 1745 1746 1747 1748 1749 1750 1751 1752 1753 1754 1755 1756 1757 1758 1759 1760 1761 1762 1763 1764 1765 1766 1767 1768 1769 1770 1771 1772 1773 1774 1775 1776 1777 1778 1779 1780 1781 1782 1783 1784 1785 1786 1787 1788 1789 1790 1791 1792 1793 1794 1795 1796 1797 1798 1799 1800 1801 1802 1803 1804 1805 1806 1807 1808 1809 1810 1811 1812 1813 1814 1815 1816 1817 1818 1819 1820 1821 1822 1823 1824 1825 1826 1827 1828 1829 1830 1831 1832 1833 1834 1835 1836 1837 1838 1839 1840 1841 1842 1843 1844 1845 1846 1847 1848 1849 1850 1851 1852 1853 1854 1855 1856 1857 1858 1859 1860 1861 1862 1863 1864 1865 1866 1867 1868 1869 1870 1871 1872 1873 1874 1875 1876 1877 1878 1879 1880 1881 1882 1883 1884 1885 1886 1887 1888 1889 1890 1891 1892 1893 1894 1895 1896 1897 1898 1899 1900 1901 1902 1903 1904 1905 1906 1907 1908 1909 1910 1911 1912 1913 1914 1915 1916 1917 1918 1919 1920 1921 1922 1923 1924 1925 1926 1927 1928 1929 1930 1931 1932 1933 1934 1935 1936 1937 1938 1939 1940 1941 1942 1943 1944 1945 1946 1947 1948 1949 1950 1951 1952 1953 1954 1955 1956 1957 1958 1959 1960 1961 1962 1963 1964 1965 1966 1967 1968 1969 1970 1971 1972 1973 1974 1975 1976 1977 1978 1979 1980 1981 1982 1983 1984 1985 1986 1987 1988 1989 1990 1991 1992 1993 1994 1995 1996 1997 1998 1999 2000 2001 2002 2003 2004 2005 2006 2007 2008 2009 2010 2011 2012 2013 2014 2015 2016 2017 2018 2019 2020 2021 2022 2023 2024 2025 2026 2027 2028 2029 2030 2031 2032 2033 2034 2035 2036 2037 2038 2039 2040 2041 2042 2043 2044 2045 2046 2047 2048 2049 2050 2051 2052 2053 2054 2055 2056 2057 2058 2059 2060 2061 2062 2063 2064 2065 2066 2067 2068 2069 2070 2071 2072 2073 2074 2075 2076 2077 2078 2079 2080 2081 2082 2083 2084 2085 2086 2087 2088 2089 2090 2091 2092 2093 2094 2095 2096 2097 2098 2099 2100 2101 2102 2103 2104 2105 2106 2107 2108 2109 2110 2111 2112 2113 2114 2115 2116 2117 2118 2119 2120 2121 2122 2123 2124 2125 2126 2127 2128 2129 2130 2131 2132 2133 2134 2135 2136 2137 2138 2139 2140 2141 2142 2143 2144 2145 2146 2147 2148 2149 2150 2151 2152 2153 2154 2155 2156 2157 2158 2159 2160 2161 2162 2163 2164 2165 2166 2167 2168 2169 2170 2171 2172 2173 2174 2175 2176 2177 2178 2179 2180 2181 2182 2183 2184 2185 2186 2187 2188 2189 2190 2191 2192 2193 2194 2195 2196 2197 2198 2199 2200 2201 2202 2203 2204 2205 2206 2207 2208 2209 2210 2211 2212 2213 2214 2215 2216 2217 2218 2219 2220 2221 2222 2223 2224 2225 2226 2227 2228 2229 2230 2231 2232 2233 2234 2235 2236 2237 2238 2239 2240 2241 2242 2243 2244 2245 2246 2247 2248 2249 2250 2251 2252 2253 2254 2255 2256 2257 2258 2259 2260 2261 2262 2263 2264 2265 2266 2267 2268 2269 2270 2271 2272 2273 2274 2275 2276 2277 2278 2279 2280 2281 2282 2283 2284 2285 2286 2287 2288 2289 2290 2291 2292 2293 2294 2295 2296 2297 2298 2299 2300 2301 2302 2303 2304 2305 2306 2307 2308 2309 2310 2311 2312 2313 2314 2315 2316 2317 2318 2319 2320 2321 2322 2323 2324 2325 2326 2327 2328 2329 2330 2331 2332 2333 2334 2335 2336 2337 2338 2339 2340 2341 2342 2343 2344 2345 2346 2347 2348 2349 2350 2351 2352 2353 2354 2355 2356 2357 2358 2359 2360 2361 2362 2363 2364 2365 2366 2367 2368 2369 2370 2371 2372 2373 2374 2375 2376 2377 2378 2379 2380 2381 2382 2383 2384 2385 2386 2387 2388 2389 2390 2391 2392 2393 2394 2395 2396 2397 2398 2399 2400 2401 2402 2403 2404 2405 2406 2407 2408 2409 2410 2411 2412 2413 2414 2415 2416 2417 2418 2419 2420 2421 2422 2423 2424 2425 2426 2427 2428 2429 2430 2431 2432 2433 2434 2435 2436 2437 2438 2439 2440 2441 2442 2443 2444 2445 2446 2447 2448 2449 2450 2451 2452 2453 2454 2455 2456 2457 2458 2459 2460 2461 2462 2463 2464 2465 2466 2467 2468 2469 2470 2471 2472 2473 2474 2475 2476 2477 2478 2479 2480 2481 2482 2483 2484 2485 2486 2487 2488 2489 2490 2491 2492 2493 2494 2495 2496 2497 2498 2499 2500 2501 2502 2503 2504 2505 2506 2507 2508 2509 2510 2511 2512 2513 2514 2515 2516 2517 2518 2519 2520 2521 2522 2523 2524 2525 2526 2527 2528 2529 2530 2531 2532 2533 2534 2535 2536 2537 2538 2539 2540 2541 2542 2543 2544 2545 2546 2547 2548 2549 2550 2551 2552 2553 2554 2555 2556 2557 2558 2559 2560 2561 2562 2563 2564 2565 2566 2567 2568 2569 2570 2571 2572 2573 2574 2575 2576 2577 2578 2579 2580 2581 2582 2583 2584 2585 2586 2587 2588 2589 2590 2591 2592 2593 2594 2595 2596 2597 2598 2599 2600 2601 2602 2603 2604 2605 2606 2607 2608 2609 2610 2611 2612 2613 2614 2615 2616 2617 2618 2619 2620 2621 2622 2623 2624 2625 2626 2627 2628 2629 2630 2631 2632 2633 2634 2635 2636 2637 2638 2639 2640 2641 2642 2643 2644 2645 2646 2647 2648 2649 2650 2651 2652 2653 2654 2655 2656 2657 2658 2659 2660 2661 2662 2663 2664 2665 2666 2667 2668 2669 2670 2671 2672 2673 2674 2675 2676 2677 2678 2679 2680 2681 2682 2683 2684 2685 2686 2687 2688 2689 2690 2691 2692 2693 2694 2695 2696 2697 2698 2699 2700 2701 2702 2703 2704 2705 2706 2707 2708 2709 2710 2711 2712 2713 2714 2715 2716 2717 2718 2719 2720 2721 2722 2723 2724 2725 2726 2727 2728 2729 2730 2731 2732 2733 2734 2735 2736 2737 2738 2739 2740 2741 2742 2743 2744 2745 2746 2747 2748 2749 2750 2751 2752 2753 2754 2755 2756 2757 2758 2759 2760 2761 2762 2763 2764 2765 2766 2767 2768 2769 2770 2771 2772 2773 2774 2775 2776 2777 2778 2779 2780 2781 2782 2783 2784 2785 2786 2787 2788 2789 2790 2791 2792 2793 2794 2795 2796 2797 2798 2799 2800 2801 2802 2803 2804 2805 2806 2807 2808 2809 2810 2811 2812 2813 2814 2815 2816 2817 2818 2819 2820 2821 2822 2823 2824 2825 2826 2827 2828 2829 2830 2831 2832 2833 2834 2835 2836 2837 2838 2839 2840 2841 2842 2843 2844 2845 2846 2847 2848 2849 2850 2851 2852 2853 2854 2855 2856 2857 2858 2859 2860 2861 2862 2863 2864 2865 2866 2867 2868 2869 2870 2871 2872 2873 2874 2875 2876 2877 2878 2879 2880 2881 2882 2883 2884 2885 2886 2887 2888 2889 2890 2891 2892 2893 2894 2895 2896 2897 2898 2899 2900 2901 2902 2903 2904 2905 2906 2907 2908 2909 2910 2911 2912 2913 2914 2915 2916 2917 2918 2919 2920 2921 2922 2923 2924 2925 2926 2927 2928 2929 2930 2931 2932 2933 2934 2935 2936 2937 2938 2939 2940 2941 2942 2943 2944 2945 2946 2947 2948 2949 2950 2951 2952 2953 2954 2955 2956 2957 2958 2959 2960 2961 2962 2963 2964 2965 2966 2967 2968 2969 2970 2971 2972 2973 2974 2975 2976 2977 2978 2979 2980 2981 2982 2983 2984 2985 2986 2987 2988 2989 2990 2991 2992 2993 2994 2995 2996 2997 2998 2999 3000 3001 3002 3003 3004 3005 3006 3007 3008 3009 3010 3011 3012 3013 3014 3015 3016 3017 3018 3019 3020 3021 3022 3023 3024 3025 3026 3027 3028 3029 3030 3031 3032 3033 3034 3035 3036 3037 3038 3039 3040 3041 3042 3043 3044 3045 3046 3047 3048 3049 3050 3051 3052 3053 3054 3055 3056 3057 3058 3059 3060 3061 3062 3063 3064 3065 3066 3067 3068 3069 3070 3071 3072 3073 3074 3075 3076 3077 3078 3079 3080 3081 3082 3083 3084 3085 3086 3087 3088 3089 3090 3091 3092 3093 3094 3095 3096 3097 3098 3099 3100 3101 3102 3103 3104 3105 3106 3107 3108 3109 3110 3111 3112 3113 3114 3115 3116 3117 3118 3119 3120 3121 3122 3123 3124 3125 3126 3127 3128 3129 3130 3131 3132 3133 3134 3135 3136 3137 3138 3139 3140 3141 3142 3143 3144 3145 3146 3147 3148 3149 3150 3151 3152 3153 3154 3155 3156 3157 3158 3159 3160 3161 3162 3163 3164 3165 3166 3167 3168 3169 3170 3171 3172 3173 3174 3175 3176 3177 3178 3179 3180 3181 3182 3183 3184 3185 3186 3187 3188 3189 3190 3191 3192 3193 3194 3195 3196 3197 3198 3199 3200 3201 3202 3203 3204 3205 3206 3207 3208 3209 3210 3211 3212 3213 3214 3215 3216 3217 3218 3219 3220 3221 3222 3223 3224 3225 3226 3227 3228 3229 3230 3231 3232 3233 3234 3235 3236 3237 3238 3239 3240 3241 3242 3243 3244 3245 3246 3247 3248 3249 3250 3251 3252 3253 3254 3255 3256 3257 3258 3259 3260 3261 3262 3263 3264 3265 3266 3267 3268 3269 3270 3271 3272 3273 3274 3275 3276 3277 3278 3279 3280 3281 3282 3283 3284 3285 3286 3287 3288 3289 3290 3291 3292 3293 3294 3295 3296 3297 3298 3299 3300 3301 3302 3303 3304 3305 3306 3307 3308 3309 3310 3311 3312 3313 3314 3315 3316 3317 3318 3319 3320 3321 3322 3323 3324 3325 3326 3327 3328 3329 3330 3331 3332 3333 3334 3335 3336 3337 3338 3339 3340 3341 3342 3343 3344 3345 3346 3347 3348 3349 3350 3351 3352 3353 3354 3355 3356 3357 3358 3359 3360 3361 3362 3363 3364 3365 3366 3367 3368 3369 3370 3371 3372 3373 3374 3375 3376 3377 3378 3379 3380 3381 3382 3383 3384 3385 3386 3387 3388 3389 3390 3391 3392 3393 3394 3395 3396 3397 3398 3399 3400 3401 3402 3403 3404 3405 3406 3407 3408 3409 3410 3411 3412 3413 3414 3415 3416 3417 3418 3419 3420 3421 3422 3423 3424 3425 3426 3427 3428 3429 3430 3431 3432 3433 3434 3435 3436 3437 3438 3439 3440 3441 3442 3443 3444 3445 3446 3447 3448 3449 3450 3451 3452 3453 3454 3455 3456 3457 3458 3459 3460 3461 3462 3463 3464 3465 3466 3467 3468 3469 3470 3471 3472 3473 3474 3475 3476 3477 3478 3479 3480 3481 3482 3483 3484 3485 3486 3487 3488 3489 3490 3491 3492 3493 3494 3495 3496 3497 3498 3499 3500 3501 3502 3503 3504 3505 3506 3507 3508 3509 3510 3511 3512 3513 3514 3515 3516 3517 3518 3519 3520 3521 3522 3523 3524 3525 3526 3527 3528 3529 3530 3531 3532 3533 3534 3535 3536 3537 3538 3539 3540 3541 3542 3543 3544 3545 3546 3547 3548 3549 3550 3551 3552 3553 3554 3555 3556 3557 3558 3559 3560 3561 3562 3563 3564 3565 3566 3567 3568 3569 3570 3571 3572 3573 3574 3575 3576 3577 3578 3579 3580 3581 3582 3583 3584 3585 3586 3587 3588 3589 3590 3591 3592 3593 3594 3595 3596 3597 3598 3599 3600 3601 3602 3603 3604 3605 3606 3607 3608 3609 3610 3611 3612 3613 3614 3615 3616 3617 3618 3619 3620 3621 3622 3623 3624 3625 3626 3627 3628 3629 3630 3631 3632 3633 3634 3635 3636 3637 3638 3639 3640 3641 3642 3643 3644 3645 3646 3647 3648 3649 3650 3651 3652 3653 3654 3655 3656 3657 3658 3659 3660 3661 3662 3663 3664 3665 3666 3667 3668 3669 3670 3671 3672 3673 3674 3675 3676 3677 3678 3679 3680 3681 3682 3683 3684 3685 3686 3687 3688 3689 3690 3691 3692 3693 3694 3695 3696 3697 3698 | // SPDX-License-Identifier: GPL-2.0+ /* * Driver core for serial ports * * Based on drivers/char/serial.c, by Linus Torvalds, Theodore Ts'o. * * Copyright 1999 ARM Limited * Copyright (C) 2000-2001 Deep Blue Solutions Ltd. */ #include <linux/module.h> #include <linux/tty.h> #include <linux/tty_flip.h> #include <linux/slab.h> #include <linux/sched/signal.h> #include <linux/init.h> #include <linux/console.h> #include <linux/gpio/consumer.h> #include <linux/kernel.h> #include <linux/of.h> #include <linux/pm_runtime.h> #include <linux/proc_fs.h> #include <linux/seq_file.h> #include <linux/device.h> #include <linux/serial.h> /* for serial_state and serial_icounter_struct */ #include <linux/serial_core.h> #include <linux/sysrq.h> #include <linux/delay.h> #include <linux/mutex.h> #include <linux/math64.h> #include <linux/security.h> #include <linux/irq.h> #include <linux/uaccess.h> #include "serial_base.h" /* * This is used to lock changes in serial line configuration. */ static DEFINE_MUTEX(port_mutex); /* * lockdep: port->lock is initialized in two places, but we * want only one lock-class: */ static struct lock_class_key port_lock_key; #define HIGH_BITS_OFFSET ((sizeof(long)-sizeof(int))*8) /* * Max time with active RTS before/after data is sent. */ #define RS485_MAX_RTS_DELAY 100 /* msecs */ static void uart_change_pm(struct uart_state *state, enum uart_pm_state pm_state); static void uart_port_shutdown(struct tty_port *port); static int uart_dcd_enabled(struct uart_port *uport) { return !!(uport->status & UPSTAT_DCD_ENABLE); } static inline struct uart_port *uart_port_ref(struct uart_state *state) { if (atomic_add_unless(&state->refcount, 1, 0)) return state->uart_port; return NULL; } static inline void uart_port_deref(struct uart_port *uport) { if (atomic_dec_and_test(&uport->state->refcount)) wake_up(&uport->state->remove_wait); } #define uart_port_lock(state, flags) \ ({ \ struct uart_port *__uport = uart_port_ref(state); \ if (__uport) \ uart_port_lock_irqsave(__uport, &flags); \ __uport; \ }) #define uart_port_unlock(uport, flags) \ ({ \ struct uart_port *__uport = uport; \ if (__uport) { \ uart_port_unlock_irqrestore(__uport, flags); \ uart_port_deref(__uport); \ } \ }) static inline struct uart_port *uart_port_check(struct uart_state *state) { lockdep_assert_held(&state->port.mutex); return state->uart_port; } /** * uart_write_wakeup - schedule write processing * @port: port to be processed * * This routine is used by the interrupt handler to schedule processing in the * software interrupt portion of the driver. A driver is expected to call this * function when the number of characters in the transmit buffer have dropped * below a threshold. * * Locking: @port->lock should be held */ void uart_write_wakeup(struct uart_port *port) { struct uart_state *state = port->state; /* * This means you called this function _after_ the port was * closed. No cookie for you. */ BUG_ON(!state); tty_port_tty_wakeup(&state->port); } EXPORT_SYMBOL(uart_write_wakeup); static void uart_stop(struct tty_struct *tty) { struct uart_state *state = tty->driver_data; struct uart_port *port; unsigned long flags; port = uart_port_lock(state, flags); if (port) port->ops->stop_tx(port); uart_port_unlock(port, flags); } static void __uart_start(struct uart_state *state) { struct uart_port *port = state->uart_port; struct serial_port_device *port_dev; int err; if (!port || port->flags & UPF_DEAD || uart_tx_stopped(port)) return; port_dev = port->port_dev; /* Increment the runtime PM usage count for the active check below */ err = pm_runtime_get(&port_dev->dev); if (err < 0 && err != -EINPROGRESS) { pm_runtime_put_noidle(&port_dev->dev); return; } /* * Start TX if enabled, and kick runtime PM. If the device is not * enabled, serial_port_runtime_resume() calls start_tx() again * after enabling the device. */ if (!pm_runtime_enabled(port->dev) || pm_runtime_active(&port_dev->dev)) port->ops->start_tx(port); pm_runtime_mark_last_busy(&port_dev->dev); pm_runtime_put_autosuspend(&port_dev->dev); } static void uart_start(struct tty_struct *tty) { struct uart_state *state = tty->driver_data; struct uart_port *port; unsigned long flags; port = uart_port_lock(state, flags); __uart_start(state); uart_port_unlock(port, flags); } static void uart_update_mctrl(struct uart_port *port, unsigned int set, unsigned int clear) { unsigned long flags; unsigned int old; uart_port_lock_irqsave(port, &flags); old = port->mctrl; port->mctrl = (old & ~clear) | set; if (old != port->mctrl && !(port->rs485.flags & SER_RS485_ENABLED)) port->ops->set_mctrl(port, port->mctrl); uart_port_unlock_irqrestore(port, flags); } #define uart_set_mctrl(port, set) uart_update_mctrl(port, set, 0) #define uart_clear_mctrl(port, clear) uart_update_mctrl(port, 0, clear) static void uart_port_dtr_rts(struct uart_port *uport, bool active) { if (active) uart_set_mctrl(uport, TIOCM_DTR | TIOCM_RTS); else uart_clear_mctrl(uport, TIOCM_DTR | TIOCM_RTS); } /* Caller holds port mutex */ static void uart_change_line_settings(struct tty_struct *tty, struct uart_state *state, const struct ktermios *old_termios) { struct uart_port *uport = uart_port_check(state); struct ktermios *termios; bool old_hw_stopped; /* * If we have no tty, termios, or the port does not exist, * then we can't set the parameters for this port. */ if (!tty || uport->type == PORT_UNKNOWN) return; termios = &tty->termios; uport->ops->set_termios(uport, termios, old_termios); /* * Set modem status enables based on termios cflag */ uart_port_lock_irq(uport); if (termios->c_cflag & CRTSCTS) uport->status |= UPSTAT_CTS_ENABLE; else uport->status &= ~UPSTAT_CTS_ENABLE; if (termios->c_cflag & CLOCAL) uport->status &= ~UPSTAT_DCD_ENABLE; else uport->status |= UPSTAT_DCD_ENABLE; /* reset sw-assisted CTS flow control based on (possibly) new mode */ old_hw_stopped = uport->hw_stopped; uport->hw_stopped = uart_softcts_mode(uport) && !(uport->ops->get_mctrl(uport) & TIOCM_CTS); if (uport->hw_stopped != old_hw_stopped) { if (!old_hw_stopped) uport->ops->stop_tx(uport); else __uart_start(state); } uart_port_unlock_irq(uport); } static int uart_alloc_xmit_buf(struct tty_port *port) { struct uart_state *state = container_of(port, struct uart_state, port); struct uart_port *uport; unsigned long flags; unsigned long page; /* * Initialise and allocate the transmit and temporary * buffer. */ page = get_zeroed_page(GFP_KERNEL); if (!page) return -ENOMEM; uport = uart_port_lock(state, flags); if (!state->port.xmit_buf) { state->port.xmit_buf = (unsigned char *)page; kfifo_init(&state->port.xmit_fifo, state->port.xmit_buf, PAGE_SIZE); uart_port_unlock(uport, flags); } else { uart_port_unlock(uport, flags); /* * Do not free() the page under the port lock, see * uart_free_xmit_buf(). */ free_page(page); } return 0; } static void uart_free_xmit_buf(struct tty_port *port) { struct uart_state *state = container_of(port, struct uart_state, port); struct uart_port *uport; unsigned long flags; char *xmit_buf; /* * Do not free() the transmit buffer page under the port lock since * this can create various circular locking scenarios. For instance, * console driver may need to allocate/free a debug object, which * can end up in printk() recursion. */ uport = uart_port_lock(state, flags); xmit_buf = port->xmit_buf; port->xmit_buf = NULL; INIT_KFIFO(port->xmit_fifo); uart_port_unlock(uport, flags); free_page((unsigned long)xmit_buf); } /* * Startup the port. This will be called once per open. All calls * will be serialised by the per-port mutex. */ static int uart_port_startup(struct tty_struct *tty, struct uart_state *state, bool init_hw) { struct uart_port *uport = uart_port_check(state); int retval; if (uport->type == PORT_UNKNOWN) return 1; /* * Make sure the device is in D0 state. */ uart_change_pm(state, UART_PM_STATE_ON); retval = uart_alloc_xmit_buf(&state->port); if (retval) return retval; retval = uport->ops->startup(uport); if (retval == 0) { if (uart_console(uport) && uport->cons->cflag) { tty->termios.c_cflag = uport->cons->cflag; tty->termios.c_ispeed = uport->cons->ispeed; tty->termios.c_ospeed = uport->cons->ospeed; uport->cons->cflag = 0; uport->cons->ispeed = 0; uport->cons->ospeed = 0; } /* * Initialise the hardware port settings. */ uart_change_line_settings(tty, state, NULL); /* * Setup the RTS and DTR signals once the * port is open and ready to respond. */ if (init_hw && C_BAUD(tty)) uart_port_dtr_rts(uport, true); } /* * This is to allow setserial on this port. People may want to set * port/irq/type and then reconfigure the port properly if it failed * now. */ if (retval && capable(CAP_SYS_ADMIN)) return 1; return retval; } static int uart_startup(struct tty_struct *tty, struct uart_state *state, bool init_hw) { struct tty_port *port = &state->port; struct uart_port *uport; int retval; if (tty_port_initialized(port)) goto out_base_port_startup; retval = uart_port_startup(tty, state, init_hw); if (retval) { set_bit(TTY_IO_ERROR, &tty->flags); return retval; } out_base_port_startup: uport = uart_port_check(state); if (!uport) return -EIO; serial_base_port_startup(uport); return 0; } /* * This routine will shutdown a serial port; interrupts are disabled, and * DTR is dropped if the hangup on close termio flag is on. Calls to * uart_shutdown are serialised by the per-port semaphore. * * uport == NULL if uart_port has already been removed */ static void uart_shutdown(struct tty_struct *tty, struct uart_state *state) { struct uart_port *uport = uart_port_check(state); struct tty_port *port = &state->port; /* * Set the TTY IO error marker */ if (tty) set_bit(TTY_IO_ERROR, &tty->flags); if (uport) serial_base_port_shutdown(uport); if (tty_port_initialized(port)) { tty_port_set_initialized(port, false); /* * Turn off DTR and RTS early. */ if (uport) { if (uart_console(uport) && tty) { uport->cons->cflag = tty->termios.c_cflag; uport->cons->ispeed = tty->termios.c_ispeed; uport->cons->ospeed = tty->termios.c_ospeed; } if (!tty || C_HUPCL(tty)) uart_port_dtr_rts(uport, false); } uart_port_shutdown(port); } /* * It's possible for shutdown to be called after suspend if we get * a DCD drop (hangup) at just the right time. Clear suspended bit so * we don't try to resume a port that has been shutdown. */ tty_port_set_suspended(port, false); uart_free_xmit_buf(port); } /** * uart_update_timeout - update per-port frame timing information * @port: uart_port structure describing the port * @cflag: termios cflag value * @baud: speed of the port * * Set the @port frame timing information from which the FIFO timeout value is * derived. The @cflag value should reflect the actual hardware settings as * number of bits, parity, stop bits and baud rate is taken into account here. * * Locking: caller is expected to take @port->lock */ void uart_update_timeout(struct uart_port *port, unsigned int cflag, unsigned int baud) { u64 temp = tty_get_frame_size(cflag); temp *= NSEC_PER_SEC; port->frame_time = (unsigned int)DIV64_U64_ROUND_UP(temp, baud); } EXPORT_SYMBOL(uart_update_timeout); /** * uart_get_baud_rate - return baud rate for a particular port * @port: uart_port structure describing the port in question. * @termios: desired termios settings * @old: old termios (or %NULL) * @min: minimum acceptable baud rate * @max: maximum acceptable baud rate * * Decode the termios structure into a numeric baud rate, taking account of the * magic 38400 baud rate (with spd_* flags), and mapping the %B0 rate to 9600 * baud. * * If the new baud rate is invalid, try the @old termios setting. If it's still * invalid, we try 9600 baud. If that is also invalid 0 is returned. * * The @termios structure is updated to reflect the baud rate we're actually * going to be using. Don't do this for the case where B0 is requested ("hang * up"). * * Locking: caller dependent */ unsigned int uart_get_baud_rate(struct uart_port *port, struct ktermios *termios, const struct ktermios *old, unsigned int min, unsigned int max) { unsigned int try; unsigned int baud; unsigned int altbaud; int hung_up = 0; upf_t flags = port->flags & UPF_SPD_MASK; switch (flags) { case UPF_SPD_HI: altbaud = 57600; break; case UPF_SPD_VHI: altbaud = 115200; break; case UPF_SPD_SHI: altbaud = 230400; break; case UPF_SPD_WARP: altbaud = 460800; break; default: altbaud = 38400; break; } for (try = 0; try < 2; try++) { baud = tty_termios_baud_rate(termios); /* * The spd_hi, spd_vhi, spd_shi, spd_warp kludge... * Die! Die! Die! */ if (try == 0 && baud == 38400) baud = altbaud; /* * Special case: B0 rate. */ if (baud == 0) { hung_up = 1; baud = 9600; } if (baud >= min && baud <= max) return baud; /* * Oops, the quotient was zero. Try again with * the old baud rate if possible. */ termios->c_cflag &= ~CBAUD; if (old) { baud = tty_termios_baud_rate(old); if (!hung_up) tty_termios_encode_baud_rate(termios, baud, baud); old = NULL; continue; } /* * As a last resort, if the range cannot be met then clip to * the nearest chip supported rate. */ if (!hung_up) { if (baud <= min) tty_termios_encode_baud_rate(termios, min + 1, min + 1); else tty_termios_encode_baud_rate(termios, max - 1, max - 1); } } return 0; } EXPORT_SYMBOL(uart_get_baud_rate); /** * uart_get_divisor - return uart clock divisor * @port: uart_port structure describing the port * @baud: desired baud rate * * Calculate the divisor (baud_base / baud) for the specified @baud, * appropriately rounded. * * If 38400 baud and custom divisor is selected, return the custom divisor * instead. * * Locking: caller dependent */ unsigned int uart_get_divisor(struct uart_port *port, unsigned int baud) { unsigned int quot; /* * Old custom speed handling. */ if (baud == 38400 && (port->flags & UPF_SPD_MASK) == UPF_SPD_CUST) quot = port->custom_divisor; else quot = DIV_ROUND_CLOSEST(port->uartclk, 16 * baud); return quot; } EXPORT_SYMBOL(uart_get_divisor); static int uart_put_char(struct tty_struct *tty, u8 c) { struct uart_state *state = tty->driver_data; struct uart_port *port; unsigned long flags; int ret = 0; port = uart_port_lock(state, flags); if (!state->port.xmit_buf) { uart_port_unlock(port, flags); return 0; } if (port) ret = kfifo_put(&state->port.xmit_fifo, c); uart_port_unlock(port, flags); return ret; } static void uart_flush_chars(struct tty_struct *tty) { uart_start(tty); } static ssize_t uart_write(struct tty_struct *tty, const u8 *buf, size_t count) { struct uart_state *state = tty->driver_data; struct uart_port *port; unsigned long flags; int ret = 0; /* * This means you called this function _after_ the port was * closed. No cookie for you. */ if (WARN_ON(!state)) return -EL3HLT; port = uart_port_lock(state, flags); if (!state->port.xmit_buf) { uart_port_unlock(port, flags); return 0; } if (port) ret = kfifo_in(&state->port.xmit_fifo, buf, count); __uart_start(state); uart_port_unlock(port, flags); return ret; } static unsigned int uart_write_room(struct tty_struct *tty) { struct uart_state *state = tty->driver_data; struct uart_port *port; unsigned long flags; unsigned int ret; port = uart_port_lock(state, flags); ret = kfifo_avail(&state->port.xmit_fifo); uart_port_unlock(port, flags); return ret; } static unsigned int uart_chars_in_buffer(struct tty_struct *tty) { struct uart_state *state = tty->driver_data; struct uart_port *port; unsigned long flags; unsigned int ret; port = uart_port_lock(state, flags); ret = kfifo_len(&state->port.xmit_fifo); uart_port_unlock(port, flags); return ret; } static void uart_flush_buffer(struct tty_struct *tty) { struct uart_state *state = tty->driver_data; struct uart_port *port; unsigned long flags; /* * This means you called this function _after_ the port was * closed. No cookie for you. */ if (WARN_ON(!state)) return; pr_debug("uart_flush_buffer(%d) called\n", tty->index); port = uart_port_lock(state, flags); if (!port) return; kfifo_reset(&state->port.xmit_fifo); if (port->ops->flush_buffer) port->ops->flush_buffer(port); uart_port_unlock(port, flags); tty_port_tty_wakeup(&state->port); } /* * This function performs low-level write of high-priority XON/XOFF * character and accounting for it. * * Requires uart_port to implement .serial_out(). */ void uart_xchar_out(struct uart_port *uport, int offset) { serial_port_out(uport, offset, uport->x_char); uport->icount.tx++; uport->x_char = 0; } EXPORT_SYMBOL_GPL(uart_xchar_out); /* * This function is used to send a high-priority XON/XOFF character to * the device */ static void uart_send_xchar(struct tty_struct *tty, u8 ch) { struct uart_state *state = tty->driver_data; struct uart_port *port; unsigned long flags; port = uart_port_ref(state); if (!port) return; if (port->ops->send_xchar) port->ops->send_xchar(port, ch); else { uart_port_lock_irqsave(port, &flags); port->x_char = ch; if (ch) port->ops->start_tx(port); uart_port_unlock_irqrestore(port, flags); } uart_port_deref(port); } static void uart_throttle(struct tty_struct *tty) { struct uart_state *state = tty->driver_data; upstat_t mask = UPSTAT_SYNC_FIFO; struct uart_port *port; port = uart_port_ref(state); if (!port) return; if (I_IXOFF(tty)) mask |= UPSTAT_AUTOXOFF; if (C_CRTSCTS(tty)) mask |= UPSTAT_AUTORTS; if (port->status & mask) { port->ops->throttle(port); mask &= ~port->status; } if (mask & UPSTAT_AUTORTS) uart_clear_mctrl(port, TIOCM_RTS); if (mask & UPSTAT_AUTOXOFF) uart_send_xchar(tty, STOP_CHAR(tty)); uart_port_deref(port); } static void uart_unthrottle(struct tty_struct *tty) { struct uart_state *state = tty->driver_data; upstat_t mask = UPSTAT_SYNC_FIFO; struct uart_port *port; port = uart_port_ref(state); if (!port) return; if (I_IXOFF(tty)) mask |= UPSTAT_AUTOXOFF; if (C_CRTSCTS(tty)) mask |= UPSTAT_AUTORTS; if (port->status & mask) { port->ops->unthrottle(port); mask &= ~port->status; } if (mask & UPSTAT_AUTORTS) uart_set_mctrl(port, TIOCM_RTS); if (mask & UPSTAT_AUTOXOFF) uart_send_xchar(tty, START_CHAR(tty)); uart_port_deref(port); } static int uart_get_info(struct tty_port *port, struct serial_struct *retinfo) { struct uart_state *state = container_of(port, struct uart_state, port); struct uart_port *uport; int ret = -ENODEV; /* Initialize structure in case we error out later to prevent any stack info leakage. */ *retinfo = (struct serial_struct){}; /* * Ensure the state we copy is consistent and no hardware changes * occur as we go */ mutex_lock(&port->mutex); uport = uart_port_check(state); if (!uport) goto out; retinfo->type = uport->type; retinfo->line = uport->line; retinfo->port = uport->iobase; if (HIGH_BITS_OFFSET) retinfo->port_high = (long) uport->iobase >> HIGH_BITS_OFFSET; retinfo->irq = uport->irq; retinfo->flags = (__force int)uport->flags; retinfo->xmit_fifo_size = uport->fifosize; retinfo->baud_base = uport->uartclk / 16; retinfo->close_delay = jiffies_to_msecs(port->close_delay) / 10; retinfo->closing_wait = port->closing_wait == ASYNC_CLOSING_WAIT_NONE ? ASYNC_CLOSING_WAIT_NONE : jiffies_to_msecs(port->closing_wait) / 10; retinfo->custom_divisor = uport->custom_divisor; retinfo->hub6 = uport->hub6; retinfo->io_type = uport->iotype; retinfo->iomem_reg_shift = uport->regshift; retinfo->iomem_base = (void *)(unsigned long)uport->mapbase; ret = 0; out: mutex_unlock(&port->mutex); return ret; } static int uart_get_info_user(struct tty_struct *tty, struct serial_struct *ss) { struct uart_state *state = tty->driver_data; struct tty_port *port = &state->port; return uart_get_info(port, ss) < 0 ? -EIO : 0; } static int uart_set_info(struct tty_struct *tty, struct tty_port *port, struct uart_state *state, struct serial_struct *new_info) { struct uart_port *uport = uart_port_check(state); unsigned long new_port; unsigned int change_irq, change_port, closing_wait; unsigned int old_custom_divisor, close_delay; upf_t old_flags, new_flags; int retval = 0; if (!uport) return -EIO; new_port = new_info->port; if (HIGH_BITS_OFFSET) new_port += (unsigned long) new_info->port_high << HIGH_BITS_OFFSET; new_info->irq = irq_canonicalize(new_info->irq); close_delay = msecs_to_jiffies(new_info->close_delay * 10); closing_wait = new_info->closing_wait == ASYNC_CLOSING_WAIT_NONE ? ASYNC_CLOSING_WAIT_NONE : msecs_to_jiffies(new_info->closing_wait * 10); change_irq = !(uport->flags & UPF_FIXED_PORT) && new_info->irq != uport->irq; /* * Since changing the 'type' of the port changes its resource * allocations, we should treat type changes the same as * IO port changes. */ change_port = !(uport->flags & UPF_FIXED_PORT) && (new_port != uport->iobase || (unsigned long)new_info->iomem_base != uport->mapbase || new_info->hub6 != uport->hub6 || new_info->io_type != uport->iotype || new_info->iomem_reg_shift != uport->regshift || new_info->type != uport->type); old_flags = uport->flags; new_flags = (__force upf_t)new_info->flags; old_custom_divisor = uport->custom_divisor; if (!(uport->flags & UPF_FIXED_PORT)) { unsigned int uartclk = new_info->baud_base * 16; /* check needs to be done here before other settings made */ if (uartclk == 0) { retval = -EINVAL; goto exit; } } if (!capable(CAP_SYS_ADMIN)) { retval = -EPERM; if (change_irq || change_port || (new_info->baud_base != uport->uartclk / 16) || (close_delay != port->close_delay) || (closing_wait != port->closing_wait) || (new_info->xmit_fifo_size && new_info->xmit_fifo_size != uport->fifosize) || (((new_flags ^ old_flags) & ~UPF_USR_MASK) != 0)) goto exit; uport->flags = ((uport->flags & ~UPF_USR_MASK) | (new_flags & UPF_USR_MASK)); uport->custom_divisor = new_info->custom_divisor; goto check_and_exit; } if (change_irq || change_port) { retval = security_locked_down(LOCKDOWN_TIOCSSERIAL); if (retval) goto exit; } /* * Ask the low level driver to verify the settings. */ if (uport->ops->verify_port) retval = uport->ops->verify_port(uport, new_info); if ((new_info->irq >= irq_get_nr_irqs()) || (new_info->irq < 0) || (new_info->baud_base < 9600)) retval = -EINVAL; if (retval) goto exit; if (change_port || change_irq) { retval = -EBUSY; /* * Make sure that we are the sole user of this port. */ if (tty_port_users(port) > 1) goto exit; /* * We need to shutdown the serial port at the old * port/type/irq combination. */ uart_shutdown(tty, state); } if (change_port) { unsigned long old_iobase, old_mapbase; unsigned int old_type, old_iotype, old_hub6, old_shift; old_iobase = uport->iobase; old_mapbase = uport->mapbase; old_type = uport->type; old_hub6 = uport->hub6; old_iotype = uport->iotype; old_shift = uport->regshift; /* * Free and release old regions */ if (old_type != PORT_UNKNOWN && uport->ops->release_port) uport->ops->release_port(uport); uport->iobase = new_port; uport->type = new_info->type; uport->hub6 = new_info->hub6; uport->iotype = new_info->io_type; uport->regshift = new_info->iomem_reg_shift; uport->mapbase = (unsigned long)new_info->iomem_base; /* * Claim and map the new regions */ if (uport->type != PORT_UNKNOWN && uport->ops->request_port) { retval = uport->ops->request_port(uport); } else { /* Always success - Jean II */ retval = 0; } /* * If we fail to request resources for the * new port, try to restore the old settings. */ if (retval) { uport->iobase = old_iobase; uport->type = old_type; uport->hub6 = old_hub6; uport->iotype = old_iotype; uport->regshift = old_shift; uport->mapbase = old_mapbase; if (old_type != PORT_UNKNOWN) { retval = uport->ops->request_port(uport); /* * If we failed to restore the old settings, * we fail like this. */ if (retval) uport->type = PORT_UNKNOWN; /* * We failed anyway. */ retval = -EBUSY; } /* Added to return the correct error -Ram Gupta */ goto exit; } } if (change_irq) uport->irq = new_info->irq; if (!(uport->flags & UPF_FIXED_PORT)) uport->uartclk = new_info->baud_base * 16; uport->flags = (uport->flags & ~UPF_CHANGE_MASK) | (new_flags & UPF_CHANGE_MASK); uport->custom_divisor = new_info->custom_divisor; port->close_delay = close_delay; port->closing_wait = closing_wait; if (new_info->xmit_fifo_size) uport->fifosize = new_info->xmit_fifo_size; check_and_exit: retval = 0; if (uport->type == PORT_UNKNOWN) goto exit; if (tty_port_initialized(port)) { if (((old_flags ^ uport->flags) & UPF_SPD_MASK) || old_custom_divisor != uport->custom_divisor) { /* * If they're setting up a custom divisor or speed, * instead of clearing it, then bitch about it. */ if (uport->flags & UPF_SPD_MASK) { dev_notice_ratelimited(uport->dev, "%s sets custom speed on %s. This is deprecated.\n", current->comm, tty_name(port->tty)); } uart_change_line_settings(tty, state, NULL); } } else { retval = uart_startup(tty, state, true); if (retval == 0) tty_port_set_initialized(port, true); if (retval > 0) retval = 0; } exit: return retval; } static int uart_set_info_user(struct tty_struct *tty, struct serial_struct *ss) { struct uart_state *state = tty->driver_data; struct tty_port *port = &state->port; int retval; down_write(&tty->termios_rwsem); /* * This semaphore protects port->count. It is also * very useful to prevent opens. Also, take the * port configuration semaphore to make sure that a * module insertion/removal doesn't change anything * under us. */ mutex_lock(&port->mutex); retval = uart_set_info(tty, port, state, ss); mutex_unlock(&port->mutex); up_write(&tty->termios_rwsem); return retval; } /** * uart_get_lsr_info - get line status register info * @tty: tty associated with the UART * @state: UART being queried * @value: returned modem value */ static int uart_get_lsr_info(struct tty_struct *tty, struct uart_state *state, unsigned int __user *value) { struct uart_port *uport = uart_port_check(state); unsigned int result; result = uport->ops->tx_empty(uport); /* * If we're about to load something into the transmit * register, we'll pretend the transmitter isn't empty to * avoid a race condition (depending on when the transmit * interrupt happens). */ if (uport->x_char || (!kfifo_is_empty(&state->port.xmit_fifo) && !uart_tx_stopped(uport))) result &= ~TIOCSER_TEMT; return put_user(result, value); } static int uart_tiocmget(struct tty_struct *tty) { struct uart_state *state = tty->driver_data; struct tty_port *port = &state->port; struct uart_port *uport; int result; guard(mutex)(&port->mutex); uport = uart_port_check(state); if (!uport || tty_io_error(tty)) return -EIO; uart_port_lock_irq(uport); result = uport->mctrl; result |= uport->ops->get_mctrl(uport); uart_port_unlock_irq(uport); return result; } static int uart_tiocmset(struct tty_struct *tty, unsigned int set, unsigned int clear) { struct uart_state *state = tty->driver_data; struct tty_port *port = &state->port; struct uart_port *uport; guard(mutex)(&port->mutex); uport = uart_port_check(state); if (!uport || tty_io_error(tty)) return -EIO; uart_update_mctrl(uport, set, clear); return 0; } static int uart_break_ctl(struct tty_struct *tty, int break_state) { struct uart_state *state = tty->driver_data; struct tty_port *port = &state->port; struct uart_port *uport; guard(mutex)(&port->mutex); uport = uart_port_check(state); if (!uport) return -EIO; if (uport->type != PORT_UNKNOWN && uport->ops->break_ctl) uport->ops->break_ctl(uport, break_state); return 0; } static int uart_do_autoconfig(struct tty_struct *tty, struct uart_state *state) { struct tty_port *port = &state->port; struct uart_port *uport; int flags, ret; if (!capable(CAP_SYS_ADMIN)) return -EPERM; /* * Take the per-port semaphore. This prevents count from * changing, and hence any extra opens of the port while * we're auto-configuring. */ scoped_cond_guard(mutex_intr, return -ERESTARTSYS, &port->mutex) { uport = uart_port_check(state); if (!uport) return -EIO; if (tty_port_users(port) != 1) return -EBUSY; uart_shutdown(tty, state); /* * If we already have a port type configured, * we must release its resources. */ if (uport->type != PORT_UNKNOWN && uport->ops->release_port) uport->ops->release_port(uport); flags = UART_CONFIG_TYPE; if (uport->flags & UPF_AUTO_IRQ) flags |= UART_CONFIG_IRQ; /* * This will claim the ports resources if * a port is found. */ uport->ops->config_port(uport, flags); ret = uart_startup(tty, state, true); if (ret < 0) return ret; if (ret > 0) return 0; tty_port_set_initialized(port, true); } return 0; } static void uart_enable_ms(struct uart_port *uport) { /* * Force modem status interrupts on */ if (uport->ops->enable_ms) uport->ops->enable_ms(uport); } /* * Wait for any of the 4 modem inputs (DCD,RI,DSR,CTS) to change * - mask passed in arg for lines of interest * (use |'ed TIOCM_RNG/DSR/CD/CTS for masking) * Caller should use TIOCGICOUNT to see which one it was * * FIXME: This wants extracting into a common all driver implementation * of TIOCMWAIT using tty_port. */ static int uart_wait_modem_status(struct uart_state *state, unsigned long arg) { struct uart_port *uport; struct tty_port *port = &state->port; DECLARE_WAITQUEUE(wait, current); struct uart_icount cprev, cnow; int ret; /* * note the counters on entry */ uport = uart_port_ref(state); if (!uport) return -EIO; uart_port_lock_irq(uport); memcpy(&cprev, &uport->icount, sizeof(struct uart_icount)); uart_enable_ms(uport); uart_port_unlock_irq(uport); add_wait_queue(&port->delta_msr_wait, &wait); for (;;) { uart_port_lock_irq(uport); memcpy(&cnow, &uport->icount, sizeof(struct uart_icount)); uart_port_unlock_irq(uport); set_current_state(TASK_INTERRUPTIBLE); if (((arg & TIOCM_RNG) && (cnow.rng != cprev.rng)) || ((arg & TIOCM_DSR) && (cnow.dsr != cprev.dsr)) || ((arg & TIOCM_CD) && (cnow.dcd != cprev.dcd)) || ((arg & TIOCM_CTS) && (cnow.cts != cprev.cts))) { ret = 0; break; } schedule(); /* see if a signal did it */ if (signal_pending(current)) { ret = -ERESTARTSYS; break; } cprev = cnow; } __set_current_state(TASK_RUNNING); remove_wait_queue(&port->delta_msr_wait, &wait); uart_port_deref(uport); return ret; } /* * Get counter of input serial line interrupts (DCD,RI,DSR,CTS) * Return: write counters to the user passed counter struct * NB: both 1->0 and 0->1 transitions are counted except for * RI where only 0->1 is counted. */ static int uart_get_icount(struct tty_struct *tty, struct serial_icounter_struct *icount) { struct uart_state *state = tty->driver_data; struct uart_icount cnow; struct uart_port *uport; uport = uart_port_ref(state); if (!uport) return -EIO; uart_port_lock_irq(uport); memcpy(&cnow, &uport->icount, sizeof(struct uart_icount)); uart_port_unlock_irq(uport); uart_port_deref(uport); icount->cts = cnow.cts; icount->dsr = cnow.dsr; icount->rng = cnow.rng; icount->dcd = cnow.dcd; icount->rx = cnow.rx; icount->tx = cnow.tx; icount->frame = cnow.frame; icount->overrun = cnow.overrun; icount->parity = cnow.parity; icount->brk = cnow.brk; icount->buf_overrun = cnow.buf_overrun; return 0; } #define SER_RS485_LEGACY_FLAGS (SER_RS485_ENABLED | SER_RS485_RTS_ON_SEND | \ SER_RS485_RTS_AFTER_SEND | SER_RS485_RX_DURING_TX | \ SER_RS485_TERMINATE_BUS) static int uart_check_rs485_flags(struct uart_port *port, struct serial_rs485 *rs485) { u32 flags = rs485->flags; /* Don't return -EINVAL for unsupported legacy flags */ flags &= ~SER_RS485_LEGACY_FLAGS; /* * For any bit outside of the legacy ones that is not supported by * the driver, return -EINVAL. */ if (flags & ~port->rs485_supported.flags) return -EINVAL; /* Asking for address w/o addressing mode? */ if (!(rs485->flags & SER_RS485_ADDRB) && (rs485->flags & (SER_RS485_ADDR_RECV|SER_RS485_ADDR_DEST))) return -EINVAL; /* Address given but not enabled? */ if (!(rs485->flags & SER_RS485_ADDR_RECV) && rs485->addr_recv) return -EINVAL; if (!(rs485->flags & SER_RS485_ADDR_DEST) && rs485->addr_dest) return -EINVAL; return 0; } static void uart_sanitize_serial_rs485_delays(struct uart_port *port, struct serial_rs485 *rs485) { if (!port->rs485_supported.delay_rts_before_send) { if (rs485->delay_rts_before_send) { dev_warn_ratelimited(port->dev, "%s (%d): RTS delay before sending not supported\n", port->name, port->line); } rs485->delay_rts_before_send = 0; } else if (rs485->delay_rts_before_send > RS485_MAX_RTS_DELAY) { rs485->delay_rts_before_send = RS485_MAX_RTS_DELAY; dev_warn_ratelimited(port->dev, "%s (%d): RTS delay before sending clamped to %u ms\n", port->name, port->line, rs485->delay_rts_before_send); } if (!port->rs485_supported.delay_rts_after_send) { if (rs485->delay_rts_after_send) { dev_warn_ratelimited(port->dev, "%s (%d): RTS delay after sending not supported\n", port->name, port->line); } rs485->delay_rts_after_send = 0; } else if (rs485->delay_rts_after_send > RS485_MAX_RTS_DELAY) { rs485->delay_rts_after_send = RS485_MAX_RTS_DELAY; dev_warn_ratelimited(port->dev, "%s (%d): RTS delay after sending clamped to %u ms\n", port->name, port->line, rs485->delay_rts_after_send); } } static void uart_sanitize_serial_rs485(struct uart_port *port, struct serial_rs485 *rs485) { u32 supported_flags = port->rs485_supported.flags; if (!(rs485->flags & SER_RS485_ENABLED)) { memset(rs485, 0, sizeof(*rs485)); return; } /* Clear other RS485 flags but SER_RS485_TERMINATE_BUS and return if enabling RS422 */ if (rs485->flags & SER_RS485_MODE_RS422) { rs485->flags &= (SER_RS485_ENABLED | SER_RS485_MODE_RS422 | SER_RS485_TERMINATE_BUS); return; } rs485->flags &= supported_flags; /* Pick sane settings if the user hasn't */ if (!(rs485->flags & SER_RS485_RTS_ON_SEND) == !(rs485->flags & SER_RS485_RTS_AFTER_SEND)) { if (supported_flags & SER_RS485_RTS_ON_SEND) { rs485->flags |= SER_RS485_RTS_ON_SEND; rs485->flags &= ~SER_RS485_RTS_AFTER_SEND; dev_warn_ratelimited(port->dev, "%s (%d): invalid RTS setting, using RTS_ON_SEND instead\n", port->name, port->line); } else { rs485->flags |= SER_RS485_RTS_AFTER_SEND; rs485->flags &= ~SER_RS485_RTS_ON_SEND; dev_warn_ratelimited(port->dev, "%s (%d): invalid RTS setting, using RTS_AFTER_SEND instead\n", port->name, port->line); } } uart_sanitize_serial_rs485_delays(port, rs485); /* Return clean padding area to userspace */ memset(rs485->padding0, 0, sizeof(rs485->padding0)); memset(rs485->padding1, 0, sizeof(rs485->padding1)); } static void uart_set_rs485_termination(struct uart_port *port, const struct serial_rs485 *rs485) { if (!(rs485->flags & SER_RS485_ENABLED)) return; gpiod_set_value_cansleep(port->rs485_term_gpio, !!(rs485->flags & SER_RS485_TERMINATE_BUS)); } static void uart_set_rs485_rx_during_tx(struct uart_port *port, const struct serial_rs485 *rs485) { if (!(rs485->flags & SER_RS485_ENABLED)) return; gpiod_set_value_cansleep(port->rs485_rx_during_tx_gpio, !!(rs485->flags & SER_RS485_RX_DURING_TX)); } static int uart_rs485_config(struct uart_port *port) { struct serial_rs485 *rs485 = &port->rs485; unsigned long flags; int ret; if (!(rs485->flags & SER_RS485_ENABLED)) return 0; uart_sanitize_serial_rs485(port, rs485); uart_set_rs485_termination(port, rs485); uart_set_rs485_rx_during_tx(port, rs485); uart_port_lock_irqsave(port, &flags); ret = port->rs485_config(port, NULL, rs485); uart_port_unlock_irqrestore(port, flags); if (ret) { memset(rs485, 0, sizeof(*rs485)); /* unset GPIOs */ gpiod_set_value_cansleep(port->rs485_term_gpio, 0); gpiod_set_value_cansleep(port->rs485_rx_during_tx_gpio, 0); } return ret; } static int uart_get_rs485_config(struct uart_port *port, struct serial_rs485 __user *rs485) { unsigned long flags; struct serial_rs485 aux; uart_port_lock_irqsave(port, &flags); aux = port->rs485; uart_port_unlock_irqrestore(port, flags); if (copy_to_user(rs485, &aux, sizeof(aux))) return -EFAULT; return 0; } static int uart_set_rs485_config(struct tty_struct *tty, struct uart_port *port, struct serial_rs485 __user *rs485_user) { struct serial_rs485 rs485; int ret; unsigned long flags; if (!(port->rs485_supported.flags & SER_RS485_ENABLED)) return -ENOTTY; if (copy_from_user(&rs485, rs485_user, sizeof(*rs485_user))) return -EFAULT; ret = uart_check_rs485_flags(port, &rs485); if (ret) return ret; uart_sanitize_serial_rs485(port, &rs485); uart_set_rs485_termination(port, &rs485); uart_set_rs485_rx_during_tx(port, &rs485); uart_port_lock_irqsave(port, &flags); ret = port->rs485_config(port, &tty->termios, &rs485); if (!ret) { port->rs485 = rs485; /* Reset RTS and other mctrl lines when disabling RS485 */ if (!(rs485.flags & SER_RS485_ENABLED)) port->ops->set_mctrl(port, port->mctrl); } uart_port_unlock_irqrestore(port, flags); if (ret) { /* restore old GPIO settings */ gpiod_set_value_cansleep(port->rs485_term_gpio, !!(port->rs485.flags & SER_RS485_TERMINATE_BUS)); gpiod_set_value_cansleep(port->rs485_rx_during_tx_gpio, !!(port->rs485.flags & SER_RS485_RX_DURING_TX)); return ret; } if (copy_to_user(rs485_user, &port->rs485, sizeof(port->rs485))) return -EFAULT; return 0; } static int uart_get_iso7816_config(struct uart_port *port, struct serial_iso7816 __user *iso7816) { unsigned long flags; struct serial_iso7816 aux; if (!port->iso7816_config) return -ENOTTY; uart_port_lock_irqsave(port, &flags); aux = port->iso7816; uart_port_unlock_irqrestore(port, flags); if (copy_to_user(iso7816, &aux, sizeof(aux))) return -EFAULT; return 0; } static int uart_set_iso7816_config(struct uart_port *port, struct serial_iso7816 __user *iso7816_user) { struct serial_iso7816 iso7816; int i, ret; unsigned long flags; if (!port->iso7816_config) return -ENOTTY; if (copy_from_user(&iso7816, iso7816_user, sizeof(*iso7816_user))) return -EFAULT; /* * There are 5 words reserved for future use. Check that userspace * doesn't put stuff in there to prevent breakages in the future. */ for (i = 0; i < ARRAY_SIZE(iso7816.reserved); i++) if (iso7816.reserved[i]) return -EINVAL; uart_port_lock_irqsave(port, &flags); ret = port->iso7816_config(port, &iso7816); uart_port_unlock_irqrestore(port, flags); if (ret) return ret; if (copy_to_user(iso7816_user, &port->iso7816, sizeof(port->iso7816))) return -EFAULT; return 0; } /* * Called via sys_ioctl. We can use spin_lock_irq() here. */ static int uart_ioctl(struct tty_struct *tty, unsigned int cmd, unsigned long arg) { struct uart_state *state = tty->driver_data; struct tty_port *port = &state->port; struct uart_port *uport; void __user *uarg = (void __user *)arg; int ret = -ENOIOCTLCMD; /* * These ioctls don't rely on the hardware to be present. */ switch (cmd) { case TIOCSERCONFIG: down_write(&tty->termios_rwsem); ret = uart_do_autoconfig(tty, state); up_write(&tty->termios_rwsem); break; } if (ret != -ENOIOCTLCMD) goto out; if (tty_io_error(tty)) { ret = -EIO; goto out; } /* * The following should only be used when hardware is present. */ switch (cmd) { case TIOCMIWAIT: ret = uart_wait_modem_status(state, arg); break; } if (ret != -ENOIOCTLCMD) goto out; /* rs485_config requires more locking than others */ if (cmd == TIOCSRS485) down_write(&tty->termios_rwsem); mutex_lock(&port->mutex); uport = uart_port_check(state); if (!uport || tty_io_error(tty)) { ret = -EIO; goto out_up; } /* * All these rely on hardware being present and need to be * protected against the tty being hung up. */ switch (cmd) { case TIOCSERGETLSR: /* Get line status register */ ret = uart_get_lsr_info(tty, state, uarg); break; case TIOCGRS485: ret = uart_get_rs485_config(uport, uarg); break; case TIOCSRS485: ret = uart_set_rs485_config(tty, uport, uarg); break; case TIOCSISO7816: ret = uart_set_iso7816_config(state->uart_port, uarg); break; case TIOCGISO7816: ret = uart_get_iso7816_config(state->uart_port, uarg); break; default: if (uport->ops->ioctl) ret = uport->ops->ioctl(uport, cmd, arg); break; } out_up: mutex_unlock(&port->mutex); if (cmd == TIOCSRS485) up_write(&tty->termios_rwsem); out: return ret; } static void uart_set_ldisc(struct tty_struct *tty) { struct uart_state *state = tty->driver_data; struct uart_port *uport; struct tty_port *port = &state->port; if (!tty_port_initialized(port)) return; mutex_lock(&state->port.mutex); uport = uart_port_check(state); if (uport && uport->ops->set_ldisc) uport->ops->set_ldisc(uport, &tty->termios); mutex_unlock(&state->port.mutex); } static void uart_set_termios(struct tty_struct *tty, const struct ktermios *old_termios) { struct uart_state *state = tty->driver_data; struct uart_port *uport; unsigned int cflag = tty->termios.c_cflag; unsigned int iflag_mask = IGNBRK|BRKINT|IGNPAR|PARMRK|INPCK; bool sw_changed = false; guard(mutex)(&state->port.mutex); uport = uart_port_check(state); if (!uport) return; /* * Drivers doing software flow control also need to know * about changes to these input settings. */ if (uport->flags & UPF_SOFT_FLOW) { iflag_mask |= IXANY|IXON|IXOFF; sw_changed = tty->termios.c_cc[VSTART] != old_termios->c_cc[VSTART] || tty->termios.c_cc[VSTOP] != old_termios->c_cc[VSTOP]; } /* * These are the bits that are used to setup various * flags in the low level driver. We can ignore the Bfoo * bits in c_cflag; c_[io]speed will always be set * appropriately by set_termios() in tty_ioctl.c */ if ((cflag ^ old_termios->c_cflag) == 0 && tty->termios.c_ospeed == old_termios->c_ospeed && tty->termios.c_ispeed == old_termios->c_ispeed && ((tty->termios.c_iflag ^ old_termios->c_iflag) & iflag_mask) == 0 && !sw_changed) return; uart_change_line_settings(tty, state, old_termios); /* reload cflag from termios; port driver may have overridden flags */ cflag = tty->termios.c_cflag; /* Handle transition to B0 status */ if (((old_termios->c_cflag & CBAUD) != B0) && ((cflag & CBAUD) == B0)) uart_clear_mctrl(uport, TIOCM_RTS | TIOCM_DTR); /* Handle transition away from B0 status */ else if (((old_termios->c_cflag & CBAUD) == B0) && ((cflag & CBAUD) != B0)) { unsigned int mask = TIOCM_DTR; if (!(cflag & CRTSCTS) || !tty_throttled(tty)) mask |= TIOCM_RTS; uart_set_mctrl(uport, mask); } } /* * Calls to uart_close() are serialised via the tty_lock in * drivers/tty/tty_io.c:tty_release() * drivers/tty/tty_io.c:do_tty_hangup() */ static void uart_close(struct tty_struct *tty, struct file *filp) { struct uart_state *state = tty->driver_data; if (!state) { struct uart_driver *drv = tty->driver->driver_state; struct tty_port *port; state = drv->state + tty->index; port = &state->port; spin_lock_irq(&port->lock); --port->count; spin_unlock_irq(&port->lock); return; } pr_debug("uart_close(%d) called\n", tty->index); tty_port_close(tty->port, tty, filp); } static void uart_tty_port_shutdown(struct tty_port *port) { struct uart_state *state = container_of(port, struct uart_state, port); struct uart_port *uport = uart_port_check(state); /* * At this point, we stop accepting input. To do this, we * disable the receive line status interrupts. */ if (WARN(!uport, "detached port still initialized!\n")) return; uart_port_lock_irq(uport); uport->ops->stop_rx(uport); uart_port_unlock_irq(uport); serial_base_port_shutdown(uport); uart_port_shutdown(port); /* * It's possible for shutdown to be called after suspend if we get * a DCD drop (hangup) at just the right time. Clear suspended bit so * we don't try to resume a port that has been shutdown. */ tty_port_set_suspended(port, false); uart_free_xmit_buf(port); uart_change_pm(state, UART_PM_STATE_OFF); } static void uart_wait_until_sent(struct tty_struct *tty, int timeout) { struct uart_state *state = tty->driver_data; struct uart_port *port; unsigned long char_time, expire, fifo_timeout; port = uart_port_ref(state); if (!port) return; if (port->type == PORT_UNKNOWN || port->fifosize == 0) { uart_port_deref(port); return; } /* * Set the check interval to be 1/5 of the estimated time to * send a single character, and make it at least 1. The check * interval should also be less than the timeout. * * Note: we have to use pretty tight timings here to satisfy * the NIST-PCTS. */ char_time = max(nsecs_to_jiffies(port->frame_time / 5), 1UL); if (timeout && timeout < char_time) char_time = timeout; if (!uart_cts_enabled(port)) { /* * If the transmitter hasn't cleared in twice the approximate * amount of time to send the entire FIFO, it probably won't * ever clear. This assumes the UART isn't doing flow * control, which is currently the case. Hence, if it ever * takes longer than FIFO timeout, this is probably due to a * UART bug of some kind. So, we clamp the timeout parameter at * 2 * FIFO timeout. */ fifo_timeout = uart_fifo_timeout(port); if (timeout == 0 || timeout > 2 * fifo_timeout) timeout = 2 * fifo_timeout; } expire = jiffies + timeout; pr_debug("uart_wait_until_sent(%d), jiffies=%lu, expire=%lu...\n", port->line, jiffies, expire); /* * Check whether the transmitter is empty every 'char_time'. * 'timeout' / 'expire' give us the maximum amount of time * we wait. */ while (!port->ops->tx_empty(port)) { msleep_interruptible(jiffies_to_msecs(char_time)); if (signal_pending(current)) break; if (timeout && time_after(jiffies, expire)) break; } uart_port_deref(port); } /* * Calls to uart_hangup() are serialised by the tty_lock in * drivers/tty/tty_io.c:do_tty_hangup() * This runs from a workqueue and can sleep for a _short_ time only. */ static void uart_hangup(struct tty_struct *tty) { struct uart_state *state = tty->driver_data; struct tty_port *port = &state->port; struct uart_port *uport; unsigned long flags; pr_debug("uart_hangup(%d)\n", tty->index); mutex_lock(&port->mutex); uport = uart_port_check(state); WARN(!uport, "hangup of detached port!\n"); if (tty_port_active(port)) { uart_flush_buffer(tty); uart_shutdown(tty, state); spin_lock_irqsave(&port->lock, flags); port->count = 0; spin_unlock_irqrestore(&port->lock, flags); tty_port_set_active(port, false); tty_port_tty_set(port, NULL); if (uport && !uart_console(uport)) uart_change_pm(state, UART_PM_STATE_OFF); wake_up_interruptible(&port->open_wait); wake_up_interruptible(&port->delta_msr_wait); } mutex_unlock(&port->mutex); } /* uport == NULL if uart_port has already been removed */ static void uart_port_shutdown(struct tty_port *port) { struct uart_state *state = container_of(port, struct uart_state, port); struct uart_port *uport = uart_port_check(state); /* * clear delta_msr_wait queue to avoid mem leaks: we may free * the irq here so the queue might never be woken up. Note * that we won't end up waiting on delta_msr_wait again since * any outstanding file descriptors should be pointing at * hung_up_tty_fops now. */ wake_up_interruptible(&port->delta_msr_wait); if (uport) { /* Free the IRQ and disable the port. */ uport->ops->shutdown(uport); /* Ensure that the IRQ handler isn't running on another CPU. */ synchronize_irq(uport->irq); } } static bool uart_carrier_raised(struct tty_port *port) { struct uart_state *state = container_of(port, struct uart_state, port); struct uart_port *uport; int mctrl; uport = uart_port_ref(state); /* * Should never observe uport == NULL since checks for hangup should * abort the tty_port_block_til_ready() loop before checking for carrier * raised -- but report carrier raised if it does anyway so open will * continue and not sleep */ if (WARN_ON(!uport)) return true; uart_port_lock_irq(uport); uart_enable_ms(uport); mctrl = uport->ops->get_mctrl(uport); uart_port_unlock_irq(uport); uart_port_deref(uport); return mctrl & TIOCM_CAR; } static void uart_dtr_rts(struct tty_port *port, bool active) { struct uart_state *state = container_of(port, struct uart_state, port); struct uart_port *uport; uport = uart_port_ref(state); if (!uport) return; uart_port_dtr_rts(uport, active); uart_port_deref(uport); } static int uart_install(struct tty_driver *driver, struct tty_struct *tty) { struct uart_driver *drv = driver->driver_state; struct uart_state *state = drv->state + tty->index; tty->driver_data = state; return tty_standard_install(driver, tty); } /* * Calls to uart_open are serialised by the tty_lock in * drivers/tty/tty_io.c:tty_open() * Note that if this fails, then uart_close() _will_ be called. * * In time, we want to scrap the "opening nonpresent ports" * behaviour and implement an alternative way for setserial * to set base addresses/ports/types. This will allow us to * get rid of a certain amount of extra tests. */ static int uart_open(struct tty_struct *tty, struct file *filp) { struct uart_state *state = tty->driver_data; int retval; retval = tty_port_open(&state->port, tty, filp); if (retval > 0) retval = 0; return retval; } static int uart_port_activate(struct tty_port *port, struct tty_struct *tty) { struct uart_state *state = container_of(port, struct uart_state, port); struct uart_port *uport; int ret; uport = uart_port_check(state); if (!uport || uport->flags & UPF_DEAD) return -ENXIO; /* * Start up the serial port. */ ret = uart_startup(tty, state, false); if (ret > 0) tty_port_set_active(port, true); return ret; } static const char *uart_type(struct uart_port *port) { const char *str = NULL; if (port->ops->type) str = port->ops->type(port); if (!str) str = "unknown"; return str; } #ifdef CONFIG_PROC_FS static void uart_line_info(struct seq_file *m, struct uart_driver *drv, int i) { struct uart_state *state = drv->state + i; struct tty_port *port = &state->port; enum uart_pm_state pm_state; struct uart_port *uport; char stat_buf[32]; unsigned int status; int mmio; guard(mutex)(&port->mutex); uport = uart_port_check(state); if (!uport) return; mmio = uport->iotype >= UPIO_MEM; seq_printf(m, "%d: uart:%s %s%08llX irq:%d", uport->line, uart_type(uport), mmio ? "mmio:0x" : "port:", mmio ? (unsigned long long)uport->mapbase : (unsigned long long)uport->iobase, uport->irq); if (uport->type == PORT_UNKNOWN) { seq_putc(m, '\n'); return; } if (capable(CAP_SYS_ADMIN)) { pm_state = state->pm_state; if (pm_state != UART_PM_STATE_ON) uart_change_pm(state, UART_PM_STATE_ON); uart_port_lock_irq(uport); status = uport->ops->get_mctrl(uport); uart_port_unlock_irq(uport); if (pm_state != UART_PM_STATE_ON) uart_change_pm(state, pm_state); seq_printf(m, " tx:%d rx:%d", uport->icount.tx, uport->icount.rx); if (uport->icount.frame) seq_printf(m, " fe:%d", uport->icount.frame); if (uport->icount.parity) seq_printf(m, " pe:%d", uport->icount.parity); if (uport->icount.brk) seq_printf(m, " brk:%d", uport->icount.brk); if (uport->icount.overrun) seq_printf(m, " oe:%d", uport->icount.overrun); if (uport->icount.buf_overrun) seq_printf(m, " bo:%d", uport->icount.buf_overrun); #define INFOBIT(bit, str) \ if (uport->mctrl & (bit)) \ strncat(stat_buf, (str), sizeof(stat_buf) - \ strlen(stat_buf) - 2) #define STATBIT(bit, str) \ if (status & (bit)) \ strncat(stat_buf, (str), sizeof(stat_buf) - \ strlen(stat_buf) - 2) stat_buf[0] = '\0'; stat_buf[1] = '\0'; INFOBIT(TIOCM_RTS, "|RTS"); STATBIT(TIOCM_CTS, "|CTS"); INFOBIT(TIOCM_DTR, "|DTR"); STATBIT(TIOCM_DSR, "|DSR"); STATBIT(TIOCM_CAR, "|CD"); STATBIT(TIOCM_RNG, "|RI"); if (stat_buf[0]) stat_buf[0] = ' '; seq_puts(m, stat_buf); } seq_putc(m, '\n'); #undef STATBIT #undef INFOBIT } static int uart_proc_show(struct seq_file *m, void *v) { struct tty_driver *ttydrv = m->private; struct uart_driver *drv = ttydrv->driver_state; int i; seq_printf(m, "serinfo:1.0 driver%s%s revision:%s\n", "", "", ""); for (i = 0; i < drv->nr; i++) uart_line_info(m, drv, i); return 0; } #endif static void uart_port_spin_lock_init(struct uart_port *port) { spin_lock_init(&port->lock); lockdep_set_class(&port->lock, &port_lock_key); } #if defined(CONFIG_SERIAL_CORE_CONSOLE) || defined(CONFIG_CONSOLE_POLL) /** * uart_console_write - write a console message to a serial port * @port: the port to write the message * @s: array of characters * @count: number of characters in string to write * @putchar: function to write character to port */ void uart_console_write(struct uart_port *port, const char *s, unsigned int count, void (*putchar)(struct uart_port *, unsigned char)) { unsigned int i; for (i = 0; i < count; i++, s++) { if (*s == '\n') putchar(port, '\r'); putchar(port, *s); } } EXPORT_SYMBOL_GPL(uart_console_write); /** * uart_get_console - get uart port for console * @ports: ports to search in * @nr: number of @ports * @co: console to search for * Returns: uart_port for the console @co * * Check whether an invalid uart number has been specified (as @co->index), and * if so, search for the first available port that does have console support. */ struct uart_port * __init uart_get_console(struct uart_port *ports, int nr, struct console *co) { int idx = co->index; if (idx < 0 || idx >= nr || (ports[idx].iobase == 0 && ports[idx].membase == NULL)) for (idx = 0; idx < nr; idx++) if (ports[idx].iobase != 0 || ports[idx].membase != NULL) break; co->index = idx; return ports + idx; } /** * uart_parse_earlycon - Parse earlycon options * @p: ptr to 2nd field (ie., just beyond '<name>,') * @iotype: ptr for decoded iotype (out) * @addr: ptr for decoded mapbase/iobase (out) * @options: ptr for <options> field; %NULL if not present (out) * * Decodes earlycon kernel command line parameters of the form: * * earlycon=<name>,io|mmio|mmio16|mmio32|mmio32be|mmio32native,<addr>,<options> * * console=<name>,io|mmio|mmio16|mmio32|mmio32be|mmio32native,<addr>,<options> * * The optional form: * * earlycon=<name>,0x<addr>,<options> * * console=<name>,0x<addr>,<options> * * is also accepted; the returned @iotype will be %UPIO_MEM. * * Returns: 0 on success or -%EINVAL on failure */ int uart_parse_earlycon(char *p, unsigned char *iotype, resource_size_t *addr, char **options) { if (strncmp(p, "mmio,", 5) == 0) { *iotype = UPIO_MEM; p += 5; } else if (strncmp(p, "mmio16,", 7) == 0) { *iotype = UPIO_MEM16; p += 7; } else if (strncmp(p, "mmio32,", 7) == 0) { *iotype = UPIO_MEM32; p += 7; } else if (strncmp(p, "mmio32be,", 9) == 0) { *iotype = UPIO_MEM32BE; p += 9; } else if (strncmp(p, "mmio32native,", 13) == 0) { *iotype = IS_ENABLED(CONFIG_CPU_BIG_ENDIAN) ? UPIO_MEM32BE : UPIO_MEM32; p += 13; } else if (strncmp(p, "io,", 3) == 0) { *iotype = UPIO_PORT; p += 3; } else if (strncmp(p, "0x", 2) == 0) { *iotype = UPIO_MEM; } else { return -EINVAL; } /* * Before you replace it with kstrtoull(), think about options separator * (',') it will not tolerate */ *addr = simple_strtoull(p, NULL, 0); p = strchr(p, ','); if (p) p++; *options = p; return 0; } EXPORT_SYMBOL_GPL(uart_parse_earlycon); /** * uart_parse_options - Parse serial port baud/parity/bits/flow control. * @options: pointer to option string * @baud: pointer to an 'int' variable for the baud rate. * @parity: pointer to an 'int' variable for the parity. * @bits: pointer to an 'int' variable for the number of data bits. * @flow: pointer to an 'int' variable for the flow control character. * * uart_parse_options() decodes a string containing the serial console * options. The format of the string is <baud><parity><bits><flow>, * eg: 115200n8r */ void uart_parse_options(const char *options, int *baud, int *parity, int *bits, int *flow) { const char *s = options; *baud = simple_strtoul(s, NULL, 10); while (*s >= '0' && *s <= '9') s++; if (*s) *parity = *s++; if (*s) *bits = *s++ - '0'; if (*s) *flow = *s; } EXPORT_SYMBOL_GPL(uart_parse_options); /** * uart_set_options - setup the serial console parameters * @port: pointer to the serial ports uart_port structure * @co: console pointer * @baud: baud rate * @parity: parity character - 'n' (none), 'o' (odd), 'e' (even) * @bits: number of data bits * @flow: flow control character - 'r' (rts) * * Locking: Caller must hold console_list_lock in order to serialize * early initialization of the serial-console lock. */ int uart_set_options(struct uart_port *port, struct console *co, int baud, int parity, int bits, int flow) { struct ktermios termios; static struct ktermios dummy; /* * Ensure that the serial-console lock is initialised early. * * Note that the console-registered check is needed because * kgdboc can call uart_set_options() for an already registered * console via tty_find_polling_driver() and uart_poll_init(). */ if (!uart_console_registered_locked(port) && !port->console_reinit) uart_port_spin_lock_init(port); memset(&termios, 0, sizeof(struct ktermios)); termios.c_cflag |= CREAD | HUPCL | CLOCAL; tty_termios_encode_baud_rate(&termios, baud, baud); if (bits == 7) termios.c_cflag |= CS7; else termios.c_cflag |= CS8; switch (parity) { case 'o': case 'O': termios.c_cflag |= PARODD; fallthrough; case 'e': case 'E': termios.c_cflag |= PARENB; break; } if (flow == 'r') termios.c_cflag |= CRTSCTS; /* * some uarts on other side don't support no flow control. * So we set * DTR in host uart to make them happy */ port->mctrl |= TIOCM_DTR; port->ops->set_termios(port, &termios, &dummy); /* * Allow the setting of the UART parameters with a NULL console * too: */ if (co) { co->cflag = termios.c_cflag; co->ispeed = termios.c_ispeed; co->ospeed = termios.c_ospeed; } return 0; } EXPORT_SYMBOL_GPL(uart_set_options); #endif /* CONFIG_SERIAL_CORE_CONSOLE */ /** * uart_change_pm - set power state of the port * * @state: port descriptor * @pm_state: new state * * Locking: port->mutex has to be held */ static void uart_change_pm(struct uart_state *state, enum uart_pm_state pm_state) { struct uart_port *port = uart_port_check(state); if (state->pm_state != pm_state) { if (port && port->ops->pm) port->ops->pm(port, pm_state, state->pm_state); state->pm_state = pm_state; } } struct uart_match { struct uart_port *port; struct uart_driver *driver; }; static int serial_match_port(struct device *dev, void *data) { struct uart_match *match = data; struct tty_driver *tty_drv = match->driver->tty_driver; dev_t devt = MKDEV(tty_drv->major, tty_drv->minor_start) + match->port->line; return dev->devt == devt; /* Actually, only one tty per port */ } int uart_suspend_port(struct uart_driver *drv, struct uart_port *uport) { struct uart_state *state = drv->state + uport->line; struct tty_port *port = &state->port; struct device *tty_dev; struct uart_match match = {uport, drv}; guard(mutex)(&port->mutex); tty_dev = device_find_child(&uport->port_dev->dev, &match, serial_match_port); if (tty_dev && device_may_wakeup(tty_dev)) { enable_irq_wake(uport->irq); put_device(tty_dev); return 0; } put_device(tty_dev); /* * Nothing to do if the console is not suspending * except stop_rx to prevent any asynchronous data * over RX line. However ensure that we will be * able to Re-start_rx later. */ if (!console_suspend_enabled && uart_console(uport)) { if (uport->ops->start_rx) { uart_port_lock_irq(uport); uport->ops->stop_rx(uport); uart_port_unlock_irq(uport); } device_set_awake_path(uport->dev); return 0; } uport->suspended = 1; if (tty_port_initialized(port)) { const struct uart_ops *ops = uport->ops; int tries; unsigned int mctrl; tty_port_set_suspended(port, true); tty_port_set_initialized(port, false); uart_port_lock_irq(uport); ops->stop_tx(uport); if (!(uport->rs485.flags & SER_RS485_ENABLED)) ops->set_mctrl(uport, 0); /* save mctrl so it can be restored on resume */ mctrl = uport->mctrl; uport->mctrl = 0; ops->stop_rx(uport); uart_port_unlock_irq(uport); /* * Wait for the transmitter to empty. */ for (tries = 3; !ops->tx_empty(uport) && tries; tries--) msleep(10); if (!tries) dev_err(uport->dev, "%s: Unable to drain transmitter\n", uport->name); ops->shutdown(uport); uport->mctrl = mctrl; } /* * Disable the console device before suspending. */ if (uart_console(uport)) console_stop(uport->cons); uart_change_pm(state, UART_PM_STATE_OFF); return 0; } EXPORT_SYMBOL(uart_suspend_port); int uart_resume_port(struct uart_driver *drv, struct uart_port *uport) { struct uart_state *state = drv->state + uport->line; struct tty_port *port = &state->port; struct device *tty_dev; struct uart_match match = {uport, drv}; struct ktermios termios; guard(mutex)(&port->mutex); tty_dev = device_find_child(&uport->port_dev->dev, &match, serial_match_port); if (!uport->suspended && device_may_wakeup(tty_dev)) { if (irqd_is_wakeup_set(irq_get_irq_data((uport->irq)))) disable_irq_wake(uport->irq); put_device(tty_dev); return 0; } put_device(tty_dev); uport->suspended = 0; /* * Re-enable the console device after suspending. */ if (uart_console(uport)) { /* * First try to use the console cflag setting. */ memset(&termios, 0, sizeof(struct ktermios)); termios.c_cflag = uport->cons->cflag; termios.c_ispeed = uport->cons->ispeed; termios.c_ospeed = uport->cons->ospeed; /* * If that's unset, use the tty termios setting. */ if (port->tty && termios.c_cflag == 0) termios = port->tty->termios; if (console_suspend_enabled) uart_change_pm(state, UART_PM_STATE_ON); uport->ops->set_termios(uport, &termios, NULL); if (!console_suspend_enabled && uport->ops->start_rx) { uart_port_lock_irq(uport); uport->ops->start_rx(uport); uart_port_unlock_irq(uport); } if (console_suspend_enabled) console_start(uport->cons); } if (tty_port_suspended(port)) { const struct uart_ops *ops = uport->ops; int ret; uart_change_pm(state, UART_PM_STATE_ON); uart_port_lock_irq(uport); if (!(uport->rs485.flags & SER_RS485_ENABLED)) ops->set_mctrl(uport, 0); uart_port_unlock_irq(uport); if (console_suspend_enabled || !uart_console(uport)) { /* Protected by port mutex for now */ struct tty_struct *tty = port->tty; ret = ops->startup(uport); if (ret == 0) { if (tty) uart_change_line_settings(tty, state, NULL); uart_rs485_config(uport); uart_port_lock_irq(uport); if (!(uport->rs485.flags & SER_RS485_ENABLED)) ops->set_mctrl(uport, uport->mctrl); ops->start_tx(uport); uart_port_unlock_irq(uport); tty_port_set_initialized(port, true); } else { /* * Failed to resume - maybe hardware went away? * Clear the "initialized" flag so we won't try * to call the low level drivers shutdown method. */ uart_shutdown(tty, state); } } tty_port_set_suspended(port, false); } return 0; } EXPORT_SYMBOL(uart_resume_port); static inline void uart_report_port(struct uart_driver *drv, struct uart_port *port) { char address[64]; switch (port->iotype) { case UPIO_PORT: snprintf(address, sizeof(address), "I/O 0x%lx", port->iobase); break; case UPIO_HUB6: snprintf(address, sizeof(address), "I/O 0x%lx offset 0x%x", port->iobase, port->hub6); break; case UPIO_MEM: case UPIO_MEM16: case UPIO_MEM32: case UPIO_MEM32BE: case UPIO_AU: case UPIO_TSI: snprintf(address, sizeof(address), "MMIO 0x%llx", (unsigned long long)port->mapbase); break; default: strscpy(address, "*unknown*", sizeof(address)); break; } pr_info("%s%s%s at %s (irq = %d, base_baud = %d) is a %s\n", port->dev ? dev_name(port->dev) : "", port->dev ? ": " : "", port->name, address, port->irq, port->uartclk / 16, uart_type(port)); /* The magic multiplier feature is a bit obscure, so report it too. */ if (port->flags & UPF_MAGIC_MULTIPLIER) pr_info("%s%s%s extra baud rates supported: %d, %d", port->dev ? dev_name(port->dev) : "", port->dev ? ": " : "", port->name, port->uartclk / 8, port->uartclk / 4); } static void uart_configure_port(struct uart_driver *drv, struct uart_state *state, struct uart_port *port) { unsigned int flags; /* * If there isn't a port here, don't do anything further. */ if (!port->iobase && !port->mapbase && !port->membase) return; /* * Now do the auto configuration stuff. Note that config_port * is expected to claim the resources and map the port for us. */ flags = 0; if (port->flags & UPF_AUTO_IRQ) flags |= UART_CONFIG_IRQ; if (port->flags & UPF_BOOT_AUTOCONF) { if (!(port->flags & UPF_FIXED_TYPE)) { port->type = PORT_UNKNOWN; flags |= UART_CONFIG_TYPE; } /* Synchronize with possible boot console. */ if (uart_console(port)) console_lock(); port->ops->config_port(port, flags); if (uart_console(port)) console_unlock(); } if (port->type != PORT_UNKNOWN) { unsigned long flags; uart_report_port(drv, port); /* Synchronize with possible boot console. */ if (uart_console(port)) console_lock(); /* Power up port for set_mctrl() */ uart_change_pm(state, UART_PM_STATE_ON); /* * Ensure that the modem control lines are de-activated. * keep the DTR setting that is set in uart_set_options() * We probably don't need a spinlock around this, but */ uart_port_lock_irqsave(port, &flags); port->mctrl &= TIOCM_DTR; if (!(port->rs485.flags & SER_RS485_ENABLED)) port->ops->set_mctrl(port, port->mctrl); uart_port_unlock_irqrestore(port, flags); uart_rs485_config(port); if (uart_console(port)) console_unlock(); /* * If this driver supports console, and it hasn't been * successfully registered yet, try to re-register it. * It may be that the port was not available. */ if (port->cons && !console_is_registered(port->cons)) register_console(port->cons); /* * Power down all ports by default, except the * console if we have one. */ if (!uart_console(port)) uart_change_pm(state, UART_PM_STATE_OFF); } } #ifdef CONFIG_CONSOLE_POLL static int uart_poll_init(struct tty_driver *driver, int line, char *options) { struct uart_driver *drv = driver->driver_state; struct uart_state *state = drv->state + line; enum uart_pm_state pm_state; struct tty_port *tport; struct uart_port *port; int baud = 9600; int bits = 8; int parity = 'n'; int flow = 'n'; int ret = 0; tport = &state->port; guard(mutex)(&tport->mutex); port = uart_port_check(state); if (!port || port->type == PORT_UNKNOWN || !(port->ops->poll_get_char && port->ops->poll_put_char)) return -1; pm_state = state->pm_state; uart_change_pm(state, UART_PM_STATE_ON); if (port->ops->poll_init) { /* * We don't set initialized as we only initialized the hw, * e.g. state->xmit is still uninitialized. */ if (!tty_port_initialized(tport)) ret = port->ops->poll_init(port); } if (!ret && options) { uart_parse_options(options, &baud, &parity, &bits, &flow); console_list_lock(); ret = uart_set_options(port, NULL, baud, parity, bits, flow); console_list_unlock(); } if (ret) uart_change_pm(state, pm_state); return ret; } static int uart_poll_get_char(struct tty_driver *driver, int line) { struct uart_driver *drv = driver->driver_state; struct uart_state *state = drv->state + line; struct uart_port *port; int ret = -1; port = uart_port_ref(state); if (port) { ret = port->ops->poll_get_char(port); uart_port_deref(port); } return ret; } static void uart_poll_put_char(struct tty_driver *driver, int line, char ch) { struct uart_driver *drv = driver->driver_state; struct uart_state *state = drv->state + line; struct uart_port *port; port = uart_port_ref(state); if (!port) return; if (ch == '\n') port->ops->poll_put_char(port, '\r'); port->ops->poll_put_char(port, ch); uart_port_deref(port); } #endif static const struct tty_operations uart_ops = { .install = uart_install, .open = uart_open, .close = uart_close, .write = uart_write, .put_char = uart_put_char, .flush_chars = uart_flush_chars, .write_room = uart_write_room, .chars_in_buffer= uart_chars_in_buffer, .flush_buffer = uart_flush_buffer, .ioctl = uart_ioctl, .throttle = uart_throttle, .unthrottle = uart_unthrottle, .send_xchar = uart_send_xchar, .set_termios = uart_set_termios, .set_ldisc = uart_set_ldisc, .stop = uart_stop, .start = uart_start, .hangup = uart_hangup, .break_ctl = uart_break_ctl, .wait_until_sent= uart_wait_until_sent, #ifdef CONFIG_PROC_FS .proc_show = uart_proc_show, #endif .tiocmget = uart_tiocmget, .tiocmset = uart_tiocmset, .set_serial = uart_set_info_user, .get_serial = uart_get_info_user, .get_icount = uart_get_icount, #ifdef CONFIG_CONSOLE_POLL .poll_init = uart_poll_init, .poll_get_char = uart_poll_get_char, .poll_put_char = uart_poll_put_char, #endif }; static const struct tty_port_operations uart_port_ops = { .carrier_raised = uart_carrier_raised, .dtr_rts = uart_dtr_rts, .activate = uart_port_activate, .shutdown = uart_tty_port_shutdown, }; /** * uart_register_driver - register a driver with the uart core layer * @drv: low level driver structure * * Register a uart driver with the core driver. We in turn register with the * tty layer, and initialise the core driver per-port state. * * We have a proc file in /proc/tty/driver which is named after the normal * driver. * * @drv->port should be %NULL, and the per-port structures should be registered * using uart_add_one_port() after this call has succeeded. * * Locking: none, Interrupts: enabled */ int uart_register_driver(struct uart_driver *drv) { struct tty_driver *normal; int i, retval = -ENOMEM; BUG_ON(drv->state); /* * Maybe we should be using a slab cache for this, especially if * we have a large number of ports to handle. */ drv->state = kcalloc(drv->nr, sizeof(struct uart_state), GFP_KERNEL); if (!drv->state) goto out; normal = tty_alloc_driver(drv->nr, TTY_DRIVER_REAL_RAW | TTY_DRIVER_DYNAMIC_DEV); if (IS_ERR(normal)) { retval = PTR_ERR(normal); goto out_kfree; } drv->tty_driver = normal; normal->driver_name = drv->driver_name; normal->name = drv->dev_name; normal->major = drv->major; normal->minor_start = drv->minor; normal->type = TTY_DRIVER_TYPE_SERIAL; normal->subtype = SERIAL_TYPE_NORMAL; normal->init_termios = tty_std_termios; normal->init_termios.c_cflag = B9600 | CS8 | CREAD | HUPCL | CLOCAL; normal->init_termios.c_ispeed = normal->init_termios.c_ospeed = 9600; normal->driver_state = drv; tty_set_operations(normal, &uart_ops); /* * Initialise the UART state(s). */ for (i = 0; i < drv->nr; i++) { struct uart_state *state = drv->state + i; struct tty_port *port = &state->port; tty_port_init(port); port->ops = &uart_port_ops; } retval = tty_register_driver(normal); if (retval >= 0) return retval; for (i = 0; i < drv->nr; i++) tty_port_destroy(&drv->state[i].port); tty_driver_kref_put(normal); out_kfree: kfree(drv->state); out: return retval; } EXPORT_SYMBOL(uart_register_driver); /** * uart_unregister_driver - remove a driver from the uart core layer * @drv: low level driver structure * * Remove all references to a driver from the core driver. The low level * driver must have removed all its ports via the uart_remove_one_port() if it * registered them with uart_add_one_port(). (I.e. @drv->port is %NULL.) * * Locking: none, Interrupts: enabled */ void uart_unregister_driver(struct uart_driver *drv) { struct tty_driver *p = drv->tty_driver; unsigned int i; tty_unregister_driver(p); tty_driver_kref_put(p); for (i = 0; i < drv->nr; i++) tty_port_destroy(&drv->state[i].port); kfree(drv->state); drv->state = NULL; drv->tty_driver = NULL; } EXPORT_SYMBOL(uart_unregister_driver); struct tty_driver *uart_console_device(struct console *co, int *index) { struct uart_driver *p = co->data; *index = co->index; return p->tty_driver; } EXPORT_SYMBOL_GPL(uart_console_device); static ssize_t uartclk_show(struct device *dev, struct device_attribute *attr, char *buf) { struct serial_struct tmp; struct tty_port *port = dev_get_drvdata(dev); uart_get_info(port, &tmp); return sprintf(buf, "%d\n", tmp.baud_base * 16); } static ssize_t type_show(struct device *dev, struct device_attribute *attr, char *buf) { struct serial_struct tmp; struct tty_port *port = dev_get_drvdata(dev); uart_get_info(port, &tmp); return sprintf(buf, "%d\n", tmp.type); } static ssize_t line_show(struct device *dev, struct device_attribute *attr, char *buf) { struct serial_struct tmp; struct tty_port *port = dev_get_drvdata(dev); uart_get_info(port, &tmp); return sprintf(buf, "%d\n", tmp.line); } static ssize_t port_show(struct device *dev, struct device_attribute *attr, char *buf) { struct serial_struct tmp; struct tty_port *port = dev_get_drvdata(dev); unsigned long ioaddr; uart_get_info(port, &tmp); ioaddr = tmp.port; if (HIGH_BITS_OFFSET) ioaddr |= (unsigned long)tmp.port_high << HIGH_BITS_OFFSET; return sprintf(buf, "0x%lX\n", ioaddr); } static ssize_t irq_show(struct device *dev, struct device_attribute *attr, char *buf) { struct serial_struct tmp; struct tty_port *port = dev_get_drvdata(dev); uart_get_info(port, &tmp); return sprintf(buf, "%d\n", tmp.irq); } static ssize_t flags_show(struct device *dev, struct device_attribute *attr, char *buf) { struct serial_struct tmp; struct tty_port *port = dev_get_drvdata(dev); uart_get_info(port, &tmp); return sprintf(buf, "0x%X\n", tmp.flags); } static ssize_t xmit_fifo_size_show(struct device *dev, struct device_attribute *attr, char *buf) { struct serial_struct tmp; struct tty_port *port = dev_get_drvdata(dev); uart_get_info(port, &tmp); return sprintf(buf, "%d\n", tmp.xmit_fifo_size); } static ssize_t close_delay_show(struct device *dev, struct device_attribute *attr, char *buf) { struct serial_struct tmp; struct tty_port *port = dev_get_drvdata(dev); uart_get_info(port, &tmp); return sprintf(buf, "%d\n", tmp.close_delay); } static ssize_t closing_wait_show(struct device *dev, struct device_attribute *attr, char *buf) { struct serial_struct tmp; struct tty_port *port = dev_get_drvdata(dev); uart_get_info(port, &tmp); return sprintf(buf, "%d\n", tmp.closing_wait); } static ssize_t custom_divisor_show(struct device *dev, struct device_attribute *attr, char *buf) { struct serial_struct tmp; struct tty_port *port = dev_get_drvdata(dev); uart_get_info(port, &tmp); return sprintf(buf, "%d\n", tmp.custom_divisor); } static ssize_t io_type_show(struct device *dev, struct device_attribute *attr, char *buf) { struct serial_struct tmp; struct tty_port *port = dev_get_drvdata(dev); uart_get_info(port, &tmp); return sprintf(buf, "%d\n", tmp.io_type); } static ssize_t iomem_base_show(struct device *dev, struct device_attribute *attr, char *buf) { struct serial_struct tmp; struct tty_port *port = dev_get_drvdata(dev); uart_get_info(port, &tmp); return sprintf(buf, "0x%lX\n", (unsigned long)tmp.iomem_base); } static ssize_t iomem_reg_shift_show(struct device *dev, struct device_attribute *attr, char *buf) { struct serial_struct tmp; struct tty_port *port = dev_get_drvdata(dev); uart_get_info(port, &tmp); return sprintf(buf, "%d\n", tmp.iomem_reg_shift); } static ssize_t console_show(struct device *dev, struct device_attribute *attr, char *buf) { struct tty_port *port = dev_get_drvdata(dev); struct uart_state *state = container_of(port, struct uart_state, port); struct uart_port *uport; bool console = false; mutex_lock(&port->mutex); uport = uart_port_check(state); if (uport) console = uart_console_registered(uport); mutex_unlock(&port->mutex); return sprintf(buf, "%c\n", console ? 'Y' : 'N'); } static ssize_t console_store(struct device *dev, struct device_attribute *attr, const char *buf, size_t count) { struct tty_port *port = dev_get_drvdata(dev); struct uart_state *state = container_of(port, struct uart_state, port); struct uart_port *uport; bool oldconsole, newconsole; int ret; ret = kstrtobool(buf, &newconsole); if (ret) return ret; mutex_lock(&port->mutex); uport = uart_port_check(state); if (uport) { oldconsole = uart_console_registered(uport); if (oldconsole && !newconsole) { ret = unregister_console(uport->cons); } else if (!oldconsole && newconsole) { if (uart_console(uport)) { uport->console_reinit = 1; register_console(uport->cons); } else { ret = -ENOENT; } } } else { ret = -ENXIO; } mutex_unlock(&port->mutex); return ret < 0 ? ret : count; } static DEVICE_ATTR_RO(uartclk); static DEVICE_ATTR_RO(type); static DEVICE_ATTR_RO(line); static DEVICE_ATTR_RO(port); static DEVICE_ATTR_RO(irq); static DEVICE_ATTR_RO(flags); static DEVICE_ATTR_RO(xmit_fifo_size); static DEVICE_ATTR_RO(close_delay); static DEVICE_ATTR_RO(closing_wait); static DEVICE_ATTR_RO(custom_divisor); static DEVICE_ATTR_RO(io_type); static DEVICE_ATTR_RO(iomem_base); static DEVICE_ATTR_RO(iomem_reg_shift); static DEVICE_ATTR_RW(console); static struct attribute *tty_dev_attrs[] = { &dev_attr_uartclk.attr, &dev_attr_type.attr, &dev_attr_line.attr, &dev_attr_port.attr, &dev_attr_irq.attr, &dev_attr_flags.attr, &dev_attr_xmit_fifo_size.attr, &dev_attr_close_delay.attr, &dev_attr_closing_wait.attr, &dev_attr_custom_divisor.attr, &dev_attr_io_type.attr, &dev_attr_iomem_base.attr, &dev_attr_iomem_reg_shift.attr, &dev_attr_console.attr, NULL }; static const struct attribute_group tty_dev_attr_group = { .attrs = tty_dev_attrs, }; /** * serial_core_add_one_port - attach a driver-defined port structure * @drv: pointer to the uart low level driver structure for this port * @uport: uart port structure to use for this port. * * Context: task context, might sleep * * This allows the driver @drv to register its own uart_port structure with the * core driver. The main purpose is to allow the low level uart drivers to * expand uart_port, rather than having yet more levels of structures. * Caller must hold port_mutex. */ static int serial_core_add_one_port(struct uart_driver *drv, struct uart_port *uport) { struct uart_state *state; struct tty_port *port; int ret = 0; struct device *tty_dev; int num_groups; if (uport->line >= drv->nr) return -EINVAL; state = drv->state + uport->line; port = &state->port; mutex_lock(&port->mutex); if (state->uart_port) { ret = -EINVAL; goto out; } /* Link the port to the driver state table and vice versa */ atomic_set(&state->refcount, 1); init_waitqueue_head(&state->remove_wait); state->uart_port = uport; uport->state = state; /* * If this port is in use as a console then the spinlock is already * initialised. */ if (!uart_console_registered(uport)) uart_port_spin_lock_init(uport); state->pm_state = UART_PM_STATE_UNDEFINED; uart_port_set_cons(uport, drv->cons); uport->minor = drv->tty_driver->minor_start + uport->line; uport->name = kasprintf(GFP_KERNEL, "%s%d", drv->dev_name, drv->tty_driver->name_base + uport->line); if (!uport->name) { ret = -ENOMEM; goto out; } if (uport->cons && uport->dev) of_console_check(uport->dev->of_node, uport->cons->name, uport->line); tty_port_link_device(port, drv->tty_driver, uport->line); uart_configure_port(drv, state, uport); port->console = uart_console(uport); num_groups = 2; if (uport->attr_group) num_groups++; uport->tty_groups = kcalloc(num_groups, sizeof(*uport->tty_groups), GFP_KERNEL); if (!uport->tty_groups) { ret = -ENOMEM; goto out; } uport->tty_groups[0] = &tty_dev_attr_group; if (uport->attr_group) uport->tty_groups[1] = uport->attr_group; /* Ensure serdev drivers can call serdev_device_open() right away */ uport->flags &= ~UPF_DEAD; /* * Register the port whether it's detected or not. This allows * setserial to be used to alter this port's parameters. */ tty_dev = tty_port_register_device_attr_serdev(port, drv->tty_driver, uport->line, uport->dev, &uport->port_dev->dev, port, uport->tty_groups); if (!IS_ERR(tty_dev)) { device_set_wakeup_capable(tty_dev, 1); } else { uport->flags |= UPF_DEAD; dev_err(uport->dev, "Cannot register tty device on line %d\n", uport->line); } out: mutex_unlock(&port->mutex); return ret; } /** * serial_core_remove_one_port - detach a driver defined port structure * @drv: pointer to the uart low level driver structure for this port * @uport: uart port structure for this port * * Context: task context, might sleep * * This unhooks (and hangs up) the specified port structure from the core * driver. No further calls will be made to the low-level code for this port. * Caller must hold port_mutex. */ static void serial_core_remove_one_port(struct uart_driver *drv, struct uart_port *uport) { struct uart_state *state = drv->state + uport->line; struct tty_port *port = &state->port; struct uart_port *uart_port; struct tty_struct *tty; mutex_lock(&port->mutex); uart_port = uart_port_check(state); if (uart_port != uport) dev_alert(uport->dev, "Removing wrong port: %p != %p\n", uart_port, uport); if (!uart_port) { mutex_unlock(&port->mutex); return; } mutex_unlock(&port->mutex); /* * Remove the devices from the tty layer */ tty_port_unregister_device(port, drv->tty_driver, uport->line); tty = tty_port_tty_get(port); if (tty) { tty_vhangup(port->tty); tty_kref_put(tty); } /* * If the port is used as a console, unregister it */ if (uart_console(uport)) unregister_console(uport->cons); /* * Free the port IO and memory resources, if any. */ if (uport->type != PORT_UNKNOWN && uport->ops->release_port) uport->ops->release_port(uport); kfree(uport->tty_groups); kfree(uport->name); /* * Indicate that there isn't a port here anymore. */ uport->type = PORT_UNKNOWN; uport->port_dev = NULL; mutex_lock(&port->mutex); WARN_ON(atomic_dec_return(&state->refcount) < 0); wait_event(state->remove_wait, !atomic_read(&state->refcount)); state->uart_port = NULL; mutex_unlock(&port->mutex); } /** * uart_match_port - are the two ports equivalent? * @port1: first port * @port2: second port * * This utility function can be used to determine whether two uart_port * structures describe the same port. */ bool uart_match_port(const struct uart_port *port1, const struct uart_port *port2) { if (port1->iotype != port2->iotype) return false; switch (port1->iotype) { case UPIO_PORT: return port1->iobase == port2->iobase; case UPIO_HUB6: return port1->iobase == port2->iobase && port1->hub6 == port2->hub6; case UPIO_MEM: case UPIO_MEM16: case UPIO_MEM32: case UPIO_MEM32BE: case UPIO_AU: case UPIO_TSI: return port1->mapbase == port2->mapbase; } return false; } EXPORT_SYMBOL(uart_match_port); static struct serial_ctrl_device * serial_core_get_ctrl_dev(struct serial_port_device *port_dev) { struct device *dev = &port_dev->dev; return to_serial_base_ctrl_device(dev->parent); } /* * Find a registered serial core controller device if one exists. Returns * the first device matching the ctrl_id. Caller must hold port_mutex. */ static struct serial_ctrl_device *serial_core_ctrl_find(struct uart_driver *drv, struct device *phys_dev, int ctrl_id) { struct uart_state *state; int i; lockdep_assert_held(&port_mutex); for (i = 0; i < drv->nr; i++) { state = drv->state + i; if (!state->uart_port || !state->uart_port->port_dev) continue; if (state->uart_port->dev == phys_dev && state->uart_port->ctrl_id == ctrl_id) return serial_core_get_ctrl_dev(state->uart_port->port_dev); } return NULL; } static struct serial_ctrl_device *serial_core_ctrl_device_add(struct uart_port *port) { return serial_base_ctrl_add(port, port->dev); } static int serial_core_port_device_add(struct serial_ctrl_device *ctrl_dev, struct uart_port *port) { struct serial_port_device *port_dev; port_dev = serial_base_port_add(port, ctrl_dev); if (IS_ERR(port_dev)) return PTR_ERR(port_dev); port->port_dev = port_dev; return 0; } /* * Initialize a serial core port device, and a controller device if needed. */ int serial_core_register_port(struct uart_driver *drv, struct uart_port *port) { struct serial_ctrl_device *ctrl_dev, *new_ctrl_dev = NULL; int ret; mutex_lock(&port_mutex); /* * Prevent serial_port_runtime_resume() from trying to use the port * until serial_core_add_one_port() has completed */ port->flags |= UPF_DEAD; /* Inititalize a serial core controller device if needed */ ctrl_dev = serial_core_ctrl_find(drv, port->dev, port->ctrl_id); if (!ctrl_dev) { new_ctrl_dev = serial_core_ctrl_device_add(port); if (IS_ERR(new_ctrl_dev)) { ret = PTR_ERR(new_ctrl_dev); goto err_unlock; } ctrl_dev = new_ctrl_dev; } /* * Initialize a serial core port device. Tag the port dead to prevent * serial_port_runtime_resume() trying to do anything until port has * been registered. It gets cleared by serial_core_add_one_port(). */ ret = serial_core_port_device_add(ctrl_dev, port); if (ret) goto err_unregister_ctrl_dev; ret = serial_base_match_and_update_preferred_console(drv, port); if (ret) goto err_unregister_port_dev; ret = serial_core_add_one_port(drv, port); if (ret) goto err_unregister_port_dev; mutex_unlock(&port_mutex); return 0; err_unregister_port_dev: serial_base_port_device_remove(port->port_dev); err_unregister_ctrl_dev: serial_base_ctrl_device_remove(new_ctrl_dev); err_unlock: mutex_unlock(&port_mutex); return ret; } /* * Removes a serial core port device, and the related serial core controller * device if the last instance. */ void serial_core_unregister_port(struct uart_driver *drv, struct uart_port *port) { struct device *phys_dev = port->dev; struct serial_port_device *port_dev = port->port_dev; struct serial_ctrl_device *ctrl_dev = serial_core_get_ctrl_dev(port_dev); int ctrl_id = port->ctrl_id; mutex_lock(&port_mutex); port->flags |= UPF_DEAD; serial_core_remove_one_port(drv, port); /* Note that struct uart_port *port is no longer valid at this point */ serial_base_port_device_remove(port_dev); /* Drop the serial core controller device if no ports are using it */ if (!serial_core_ctrl_find(drv, phys_dev, ctrl_id)) serial_base_ctrl_device_remove(ctrl_dev); mutex_unlock(&port_mutex); } /** * uart_handle_dcd_change - handle a change of carrier detect state * @uport: uart_port structure for the open port * @active: new carrier detect status * * Caller must hold uport->lock. */ void uart_handle_dcd_change(struct uart_port *uport, bool active) { struct tty_port *port = &uport->state->port; struct tty_struct *tty = port->tty; struct tty_ldisc *ld; lockdep_assert_held_once(&uport->lock); if (tty) { ld = tty_ldisc_ref(tty); if (ld) { if (ld->ops->dcd_change) ld->ops->dcd_change(tty, active); tty_ldisc_deref(ld); } } uport->icount.dcd++; if (uart_dcd_enabled(uport)) { if (active) wake_up_interruptible(&port->open_wait); else if (tty) tty_hangup(tty); } } EXPORT_SYMBOL_GPL(uart_handle_dcd_change); /** * uart_handle_cts_change - handle a change of clear-to-send state * @uport: uart_port structure for the open port * @active: new clear-to-send status * * Caller must hold uport->lock. */ void uart_handle_cts_change(struct uart_port *uport, bool active) { lockdep_assert_held_once(&uport->lock); uport->icount.cts++; if (uart_softcts_mode(uport)) { if (uport->hw_stopped) { if (active) { uport->hw_stopped = false; uport->ops->start_tx(uport); uart_write_wakeup(uport); } } else { if (!active) { uport->hw_stopped = true; uport->ops->stop_tx(uport); } } } } EXPORT_SYMBOL_GPL(uart_handle_cts_change); /** * uart_insert_char - push a char to the uart layer * * User is responsible to call tty_flip_buffer_push when they are done with * insertion. * * @port: corresponding port * @status: state of the serial port RX buffer (LSR for 8250) * @overrun: mask of overrun bits in @status * @ch: character to push * @flag: flag for the character (see TTY_NORMAL and friends) */ void uart_insert_char(struct uart_port *port, unsigned int status, unsigned int overrun, u8 ch, u8 flag) { struct tty_port *tport = &port->state->port; if ((status & port->ignore_status_mask & ~overrun) == 0) if (tty_insert_flip_char(tport, ch, flag) == 0) ++port->icount.buf_overrun; /* * Overrun is special. Since it's reported immediately, * it doesn't affect the current character. */ if (status & ~port->ignore_status_mask & overrun) if (tty_insert_flip_char(tport, 0, TTY_OVERRUN) == 0) ++port->icount.buf_overrun; } EXPORT_SYMBOL_GPL(uart_insert_char); #ifdef CONFIG_MAGIC_SYSRQ_SERIAL static const u8 sysrq_toggle_seq[] = CONFIG_MAGIC_SYSRQ_SERIAL_SEQUENCE; static void uart_sysrq_on(struct work_struct *w) { int sysrq_toggle_seq_len = strlen(sysrq_toggle_seq); sysrq_toggle_support(1); pr_info("SysRq is enabled by magic sequence '%*pE' on serial\n", sysrq_toggle_seq_len, sysrq_toggle_seq); } static DECLARE_WORK(sysrq_enable_work, uart_sysrq_on); /** * uart_try_toggle_sysrq - Enables SysRq from serial line * @port: uart_port structure where char(s) after BREAK met * @ch: new character in the sequence after received BREAK * * Enables magic SysRq when the required sequence is met on port * (see CONFIG_MAGIC_SYSRQ_SERIAL_SEQUENCE). * * Returns: %false if @ch is out of enabling sequence and should be * handled some other way, %true if @ch was consumed. */ bool uart_try_toggle_sysrq(struct uart_port *port, u8 ch) { int sysrq_toggle_seq_len = strlen(sysrq_toggle_seq); if (!sysrq_toggle_seq_len) return false; BUILD_BUG_ON(ARRAY_SIZE(sysrq_toggle_seq) >= U8_MAX); if (sysrq_toggle_seq[port->sysrq_seq] != ch) { port->sysrq_seq = 0; return false; } if (++port->sysrq_seq < sysrq_toggle_seq_len) { port->sysrq = jiffies + SYSRQ_TIMEOUT; return true; } schedule_work(&sysrq_enable_work); port->sysrq = 0; return true; } EXPORT_SYMBOL_GPL(uart_try_toggle_sysrq); #endif /** * uart_get_rs485_mode() - retrieve rs485 properties for given uart * @port: uart device's target port * * This function implements the device tree binding described in * Documentation/devicetree/bindings/serial/rs485.txt. */ int uart_get_rs485_mode(struct uart_port *port) { struct serial_rs485 *rs485conf = &port->rs485; struct device *dev = port->dev; enum gpiod_flags dflags; struct gpio_desc *desc; u32 rs485_delay[2]; int ret; if (!(port->rs485_supported.flags & SER_RS485_ENABLED)) return 0; ret = device_property_read_u32_array(dev, "rs485-rts-delay", rs485_delay, 2); if (!ret) { rs485conf->delay_rts_before_send = rs485_delay[0]; rs485conf->delay_rts_after_send = rs485_delay[1]; } else { rs485conf->delay_rts_before_send = 0; rs485conf->delay_rts_after_send = 0; } uart_sanitize_serial_rs485_delays(port, rs485conf); /* * Clear full-duplex and enabled flags, set RTS polarity to active high * to get to a defined state with the following properties: */ rs485conf->flags &= ~(SER_RS485_RX_DURING_TX | SER_RS485_ENABLED | SER_RS485_TERMINATE_BUS | SER_RS485_RTS_AFTER_SEND); rs485conf->flags |= SER_RS485_RTS_ON_SEND; if (device_property_read_bool(dev, "rs485-rx-during-tx")) rs485conf->flags |= SER_RS485_RX_DURING_TX; if (device_property_read_bool(dev, "linux,rs485-enabled-at-boot-time")) rs485conf->flags |= SER_RS485_ENABLED; if (device_property_read_bool(dev, "rs485-rts-active-low")) { rs485conf->flags &= ~SER_RS485_RTS_ON_SEND; rs485conf->flags |= SER_RS485_RTS_AFTER_SEND; } /* * Disabling termination by default is the safe choice: Else if many * bus participants enable it, no communication is possible at all. * Works fine for short cables and users may enable for longer cables. */ desc = devm_gpiod_get_optional(dev, "rs485-term", GPIOD_OUT_LOW); if (IS_ERR(desc)) return dev_err_probe(dev, PTR_ERR(desc), "Cannot get rs485-term-gpios\n"); port->rs485_term_gpio = desc; if (port->rs485_term_gpio) port->rs485_supported.flags |= SER_RS485_TERMINATE_BUS; dflags = (rs485conf->flags & SER_RS485_RX_DURING_TX) ? GPIOD_OUT_HIGH : GPIOD_OUT_LOW; desc = devm_gpiod_get_optional(dev, "rs485-rx-during-tx", dflags); if (IS_ERR(desc)) return dev_err_probe(dev, PTR_ERR(desc), "Cannot get rs485-rx-during-tx-gpios\n"); port->rs485_rx_during_tx_gpio = desc; if (port->rs485_rx_during_tx_gpio) port->rs485_supported.flags |= SER_RS485_RX_DURING_TX; return 0; } EXPORT_SYMBOL_GPL(uart_get_rs485_mode); /* Compile-time assertions for serial_rs485 layout */ static_assert(offsetof(struct serial_rs485, padding) == (offsetof(struct serial_rs485, delay_rts_after_send) + sizeof(__u32))); static_assert(offsetof(struct serial_rs485, padding1) == offsetof(struct serial_rs485, padding[1])); static_assert((offsetof(struct serial_rs485, padding[4]) + sizeof(__u32)) == sizeof(struct serial_rs485)); MODULE_DESCRIPTION("Serial driver core"); MODULE_LICENSE("GPL"); |
| 237 237 237 237 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 | /* SPDX-License-Identifier: GPL-2.0 */ /* * generic net pointers */ #ifndef __NET_GENERIC_H__ #define __NET_GENERIC_H__ #include <linux/bug.h> #include <linux/rcupdate.h> #include <net/net_namespace.h> /* * Generic net pointers are to be used by modules to put some private * stuff on the struct net without explicit struct net modification * * The rules are simple: * 1. set pernet_operations->id. After register_pernet_device you * will have the id of your private pointer. * 2. set pernet_operations->size to have the code allocate and free * a private structure pointed to from struct net. * 3. do not change this pointer while the net is alive; * 4. do not try to have any private reference on the net_generic object. * * After accomplishing all of the above, the private pointer can be * accessed with the net_generic() call. */ struct net_generic { union { struct { unsigned int len; struct rcu_head rcu; } s; DECLARE_FLEX_ARRAY(void *, ptr); }; }; static inline void *net_generic(const struct net *net, unsigned int id) { struct net_generic *ng; void *ptr; rcu_read_lock(); ng = rcu_dereference(net->gen); ptr = ng->ptr[id]; rcu_read_unlock(); return ptr; } #endif |
| 3 3 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 1522 1523 1524 1525 1526 1527 1528 1529 1530 1531 1532 1533 1534 1535 1536 1537 1538 1539 1540 1541 1542 1543 1544 1545 1546 1547 1548 1549 1550 1551 1552 1553 1554 1555 1556 1557 1558 1559 1560 1561 1562 1563 1564 1565 1566 1567 1568 1569 1570 1571 1572 1573 1574 1575 1576 1577 1578 1579 1580 1581 1582 1583 1584 1585 1586 1587 1588 1589 1590 1591 1592 1593 1594 1595 1596 1597 1598 1599 1600 1601 1602 1603 1604 1605 1606 1607 1608 1609 1610 1611 1612 1613 1614 1615 1616 1617 1618 1619 1620 1621 1622 1623 1624 1625 1626 1627 1628 1629 1630 1631 1632 1633 1634 1635 1636 1637 1638 1639 1640 1641 1642 1643 1644 1645 1646 1647 1648 1649 1650 1651 1652 1653 1654 1655 1656 1657 1658 1659 1660 1661 1662 1663 1664 1665 1666 1667 1668 1669 1670 1671 1672 1673 1674 1675 1676 1677 1678 1679 1680 1681 1682 1683 1684 1685 1686 1687 1688 1689 1690 1691 1692 1693 1694 1695 1696 1697 1698 1699 1700 1701 1702 1703 1704 1705 1706 1707 1708 1709 1710 1711 1712 1713 1714 1715 1716 1717 1718 1719 1720 1721 1722 1723 1724 1725 1726 1727 1728 1729 1730 1731 1732 1733 1734 1735 1736 1737 1738 1739 1740 1741 1742 1743 1744 1745 1746 1747 1748 1749 1750 1751 1752 1753 1754 1755 1756 1757 1758 1759 1760 1761 1762 1763 1764 1765 1766 1767 1768 1769 1770 1771 1772 1773 1774 1775 1776 1777 1778 1779 1780 1781 1782 1783 1784 1785 1786 1787 1788 1789 1790 1791 1792 1793 1794 1795 1796 1797 1798 1799 1800 1801 1802 1803 1804 1805 1806 1807 1808 1809 1810 1811 1812 1813 1814 1815 1816 1817 1818 1819 1820 1821 1822 1823 1824 1825 1826 1827 1828 1829 1830 1831 1832 1833 1834 1835 1836 1837 1838 1839 1840 1841 1842 1843 1844 1845 1846 1847 1848 1849 1850 1851 1852 1853 1854 1855 1856 1857 1858 1859 1860 1861 1862 1863 1864 1865 1866 1867 1868 1869 1870 1871 1872 1873 1874 1875 1876 1877 1878 1879 1880 1881 1882 1883 1884 1885 1886 1887 1888 1889 1890 1891 1892 1893 1894 1895 1896 1897 1898 1899 1900 1901 1902 1903 1904 1905 1906 1907 1908 1909 1910 1911 1912 1913 1914 1915 1916 1917 1918 1919 1920 1921 1922 1923 1924 1925 1926 1927 1928 1929 1930 1931 1932 1933 1934 1935 1936 1937 1938 1939 1940 1941 1942 1943 1944 1945 1946 1947 1948 1949 1950 1951 1952 1953 1954 1955 1956 1957 1958 1959 1960 1961 1962 1963 1964 1965 1966 1967 1968 1969 1970 1971 1972 1973 1974 1975 1976 1977 1978 1979 1980 1981 1982 1983 1984 1985 1986 1987 1988 1989 1990 1991 1992 1993 1994 1995 1996 1997 1998 1999 2000 2001 2002 2003 2004 2005 2006 2007 2008 2009 2010 2011 2012 2013 2014 2015 2016 2017 2018 2019 2020 2021 2022 2023 2024 2025 2026 2027 2028 2029 2030 2031 2032 2033 2034 2035 2036 2037 2038 2039 2040 2041 2042 2043 2044 2045 2046 2047 2048 2049 2050 2051 2052 2053 2054 2055 2056 2057 2058 2059 2060 2061 2062 2063 2064 2065 2066 2067 2068 2069 2070 2071 2072 2073 2074 2075 2076 2077 2078 2079 2080 2081 2082 2083 2084 2085 2086 2087 2088 2089 2090 2091 2092 2093 2094 2095 2096 2097 2098 2099 2100 2101 2102 2103 2104 2105 2106 2107 2108 2109 2110 2111 2112 2113 2114 2115 2116 2117 2118 2119 2120 2121 2122 2123 2124 2125 2126 2127 2128 2129 2130 2131 2132 2133 2134 2135 2136 2137 2138 2139 2140 2141 2142 2143 2144 2145 2146 2147 2148 2149 2150 2151 2152 2153 2154 2155 2156 2157 2158 2159 2160 2161 2162 2163 2164 2165 2166 2167 2168 2169 2170 2171 2172 2173 2174 2175 2176 2177 2178 2179 2180 2181 2182 2183 2184 2185 2186 2187 2188 2189 2190 2191 2192 2193 2194 2195 2196 2197 2198 2199 2200 2201 2202 2203 2204 2205 2206 2207 2208 2209 2210 2211 2212 2213 2214 2215 2216 2217 2218 2219 2220 2221 2222 2223 2224 2225 2226 2227 2228 2229 2230 2231 2232 2233 2234 2235 2236 2237 2238 2239 2240 2241 2242 2243 2244 2245 2246 2247 2248 2249 2250 2251 2252 2253 2254 2255 2256 2257 2258 2259 2260 2261 2262 2263 2264 2265 2266 2267 2268 2269 2270 2271 2272 2273 2274 2275 2276 2277 2278 2279 2280 2281 2282 2283 2284 2285 2286 2287 2288 2289 2290 2291 2292 2293 2294 2295 2296 2297 2298 2299 2300 2301 2302 2303 2304 2305 2306 2307 2308 2309 2310 2311 2312 2313 2314 2315 2316 2317 2318 2319 2320 2321 2322 2323 2324 2325 2326 2327 2328 2329 2330 2331 2332 2333 2334 2335 2336 2337 2338 2339 2340 2341 2342 2343 2344 2345 2346 2347 2348 2349 2350 2351 2352 2353 2354 2355 2356 2357 2358 2359 2360 2361 2362 2363 2364 2365 2366 2367 2368 2369 2370 2371 2372 2373 2374 2375 2376 2377 2378 2379 2380 2381 2382 2383 2384 2385 2386 2387 2388 2389 2390 2391 2392 2393 2394 2395 2396 2397 2398 2399 2400 2401 2402 2403 2404 2405 2406 2407 2408 2409 2410 2411 2412 2413 2414 2415 2416 2417 2418 2419 2420 2421 2422 2423 2424 2425 2426 2427 2428 2429 2430 2431 2432 2433 2434 2435 2436 2437 2438 2439 2440 2441 2442 2443 2444 2445 2446 2447 2448 2449 2450 2451 2452 2453 2454 2455 2456 2457 2458 2459 2460 2461 2462 2463 2464 2465 2466 2467 2468 2469 2470 2471 2472 2473 2474 2475 2476 2477 2478 2479 2480 2481 2482 2483 2484 2485 2486 2487 2488 2489 2490 2491 2492 2493 2494 2495 2496 2497 2498 2499 2500 2501 2502 2503 2504 2505 2506 2507 2508 2509 2510 2511 2512 2513 2514 2515 2516 2517 2518 2519 2520 2521 2522 2523 2524 2525 2526 2527 2528 2529 2530 2531 2532 2533 2534 2535 2536 2537 2538 2539 2540 2541 2542 2543 2544 2545 2546 2547 2548 2549 2550 2551 2552 2553 2554 2555 2556 2557 2558 2559 2560 2561 2562 2563 2564 2565 2566 2567 2568 2569 2570 2571 2572 2573 2574 2575 2576 2577 2578 2579 2580 2581 2582 2583 2584 2585 2586 2587 2588 2589 2590 2591 2592 2593 2594 2595 2596 2597 2598 2599 2600 2601 2602 2603 2604 2605 2606 2607 2608 2609 2610 2611 2612 2613 2614 2615 2616 2617 2618 2619 2620 2621 2622 2623 2624 2625 2626 2627 2628 2629 2630 2631 2632 2633 2634 2635 2636 2637 2638 2639 2640 2641 2642 2643 2644 2645 2646 2647 2648 2649 2650 2651 2652 2653 2654 2655 2656 2657 2658 2659 2660 2661 2662 2663 2664 2665 2666 2667 2668 2669 2670 2671 2672 2673 2674 2675 2676 2677 2678 2679 2680 2681 2682 2683 2684 2685 2686 2687 2688 2689 2690 2691 2692 2693 2694 2695 2696 2697 2698 2699 2700 2701 2702 2703 2704 2705 2706 2707 2708 2709 2710 2711 2712 2713 2714 2715 2716 2717 2718 2719 2720 2721 2722 2723 2724 2725 2726 2727 2728 2729 2730 2731 2732 2733 2734 2735 2736 2737 2738 2739 2740 2741 2742 2743 2744 2745 2746 2747 2748 2749 2750 2751 2752 2753 2754 2755 2756 2757 2758 2759 2760 2761 2762 2763 2764 2765 2766 2767 2768 2769 2770 2771 2772 2773 2774 2775 2776 2777 2778 2779 2780 2781 2782 2783 2784 2785 2786 2787 2788 2789 2790 2791 2792 2793 2794 2795 2796 2797 2798 2799 2800 2801 2802 2803 2804 2805 2806 2807 2808 2809 2810 2811 2812 2813 2814 2815 2816 2817 2818 2819 2820 2821 2822 2823 2824 2825 2826 2827 2828 2829 2830 2831 2832 2833 2834 2835 2836 2837 2838 2839 2840 2841 2842 2843 2844 2845 2846 2847 2848 2849 2850 2851 2852 2853 2854 2855 2856 2857 2858 2859 2860 2861 2862 2863 2864 2865 2866 2867 2868 2869 2870 2871 2872 2873 2874 2875 2876 2877 2878 2879 2880 2881 2882 2883 2884 2885 2886 2887 2888 2889 2890 2891 2892 2893 2894 2895 2896 2897 2898 2899 2900 2901 2902 2903 2904 2905 2906 2907 2908 2909 2910 2911 2912 2913 2914 2915 2916 2917 2918 2919 2920 2921 2922 2923 2924 2925 2926 2927 2928 2929 2930 2931 2932 2933 2934 2935 2936 2937 2938 2939 2940 2941 2942 2943 2944 2945 2946 2947 2948 2949 2950 2951 2952 2953 2954 2955 2956 2957 2958 2959 2960 2961 2962 2963 2964 2965 2966 2967 2968 2969 2970 2971 2972 2973 2974 2975 2976 2977 2978 2979 2980 2981 2982 2983 2984 2985 2986 2987 2988 2989 2990 2991 2992 2993 2994 2995 2996 2997 2998 2999 3000 3001 3002 3003 3004 3005 3006 3007 3008 3009 3010 3011 3012 3013 3014 3015 3016 3017 3018 3019 3020 3021 3022 3023 3024 3025 3026 3027 3028 3029 3030 3031 3032 3033 3034 3035 3036 3037 3038 3039 3040 3041 3042 3043 3044 3045 3046 3047 3048 3049 3050 3051 3052 3053 3054 3055 3056 3057 3058 3059 3060 3061 3062 3063 3064 3065 3066 3067 3068 3069 3070 3071 3072 3073 3074 3075 3076 3077 3078 3079 3080 3081 3082 3083 3084 3085 3086 3087 3088 3089 3090 3091 3092 3093 3094 3095 3096 3097 3098 3099 3100 3101 3102 3103 3104 3105 3106 3107 3108 3109 3110 3111 3112 3113 3114 3115 3116 3117 3118 3119 3120 3121 3122 3123 3124 3125 3126 3127 3128 3129 3130 3131 3132 3133 3134 3135 3136 3137 3138 3139 3140 3141 3142 3143 3144 3145 3146 3147 3148 3149 3150 3151 3152 3153 3154 3155 3156 3157 3158 3159 3160 3161 3162 3163 3164 3165 3166 3167 3168 3169 3170 3171 3172 3173 3174 3175 3176 3177 3178 3179 3180 3181 3182 3183 3184 3185 3186 3187 3188 3189 3190 3191 3192 3193 3194 3195 3196 3197 3198 3199 3200 3201 3202 3203 3204 3205 3206 3207 3208 3209 3210 3211 3212 3213 3214 3215 3216 3217 3218 3219 3220 3221 3222 3223 3224 3225 3226 3227 3228 3229 3230 3231 3232 3233 3234 3235 3236 3237 3238 3239 3240 3241 3242 3243 3244 3245 3246 3247 3248 3249 3250 3251 3252 3253 3254 3255 3256 3257 3258 3259 3260 3261 3262 3263 3264 3265 3266 3267 3268 3269 3270 3271 3272 3273 3274 3275 3276 3277 3278 3279 3280 3281 3282 3283 3284 3285 3286 3287 3288 3289 3290 3291 3292 3293 3294 3295 3296 3297 3298 3299 3300 3301 3302 3303 3304 3305 3306 3307 3308 3309 3310 3311 3312 3313 3314 3315 3316 3317 3318 3319 3320 3321 3322 3323 3324 3325 3326 3327 3328 3329 3330 3331 3332 3333 3334 3335 3336 3337 3338 3339 3340 3341 3342 3343 3344 3345 3346 3347 3348 3349 3350 3351 3352 3353 3354 3355 3356 3357 3358 3359 3360 3361 3362 3363 3364 3365 3366 3367 3368 3369 3370 3371 3372 3373 3374 3375 3376 3377 3378 3379 3380 3381 3382 3383 3384 3385 3386 3387 3388 3389 3390 3391 3392 3393 3394 3395 3396 3397 3398 3399 3400 3401 3402 3403 3404 3405 3406 3407 3408 3409 3410 3411 3412 3413 3414 3415 3416 3417 3418 3419 3420 3421 3422 3423 3424 3425 3426 3427 3428 3429 3430 3431 3432 3433 3434 3435 3436 3437 3438 3439 3440 3441 3442 3443 3444 3445 3446 3447 3448 3449 3450 3451 3452 3453 3454 3455 3456 3457 3458 3459 3460 3461 3462 3463 3464 3465 3466 3467 3468 3469 3470 3471 3472 3473 3474 3475 3476 3477 3478 3479 3480 3481 3482 3483 3484 3485 3486 3487 3488 3489 3490 3491 3492 3493 3494 3495 3496 3497 3498 3499 3500 3501 3502 3503 3504 3505 3506 3507 3508 3509 3510 3511 3512 3513 3514 3515 3516 3517 3518 3519 3520 3521 3522 3523 3524 3525 3526 3527 3528 3529 3530 3531 3532 3533 3534 3535 3536 3537 3538 3539 3540 3541 3542 3543 3544 3545 3546 3547 3548 3549 3550 3551 3552 3553 3554 3555 3556 3557 3558 3559 3560 3561 3562 3563 3564 3565 3566 3567 3568 3569 3570 3571 3572 3573 3574 3575 3576 3577 3578 3579 3580 3581 3582 3583 3584 3585 3586 3587 3588 3589 3590 3591 3592 3593 3594 3595 3596 3597 3598 3599 3600 3601 3602 3603 3604 3605 3606 3607 3608 3609 3610 3611 3612 3613 3614 3615 3616 3617 3618 3619 3620 3621 3622 3623 3624 3625 3626 3627 3628 3629 3630 3631 3632 3633 3634 3635 3636 3637 3638 3639 3640 3641 3642 3643 3644 3645 3646 3647 3648 3649 3650 3651 3652 3653 3654 3655 3656 3657 3658 3659 3660 3661 3662 3663 3664 3665 3666 3667 3668 3669 3670 3671 3672 3673 3674 3675 3676 3677 3678 3679 3680 3681 3682 3683 3684 3685 3686 3687 3688 3689 3690 3691 3692 3693 3694 3695 3696 3697 3698 3699 3700 3701 3702 3703 3704 3705 3706 3707 3708 3709 3710 3711 3712 3713 3714 3715 3716 3717 3718 3719 3720 3721 3722 3723 3724 3725 3726 3727 3728 3729 3730 3731 3732 3733 3734 3735 3736 3737 3738 3739 3740 3741 3742 3743 3744 3745 3746 3747 3748 3749 3750 3751 3752 3753 3754 3755 3756 3757 3758 3759 3760 3761 3762 3763 3764 3765 3766 3767 3768 3769 3770 3771 3772 3773 3774 3775 3776 3777 3778 3779 3780 3781 3782 3783 3784 3785 3786 3787 3788 3789 3790 3791 3792 3793 3794 3795 3796 3797 3798 3799 3800 3801 3802 3803 3804 3805 3806 3807 3808 3809 3810 3811 3812 3813 3814 3815 3816 3817 3818 3819 3820 3821 3822 3823 3824 3825 3826 3827 3828 3829 3830 3831 3832 3833 3834 3835 3836 3837 3838 3839 3840 3841 3842 3843 3844 3845 3846 3847 3848 3849 3850 3851 3852 3853 3854 3855 3856 3857 3858 3859 3860 3861 3862 3863 3864 3865 3866 3867 3868 3869 3870 3871 3872 3873 3874 3875 3876 3877 3878 3879 3880 3881 3882 3883 3884 3885 3886 3887 3888 3889 3890 3891 3892 3893 3894 3895 3896 3897 3898 3899 3900 3901 3902 3903 3904 3905 3906 3907 3908 3909 3910 3911 3912 3913 3914 3915 3916 3917 3918 3919 3920 3921 3922 3923 3924 3925 3926 3927 3928 3929 3930 3931 3932 3933 3934 3935 3936 3937 3938 3939 3940 3941 3942 3943 3944 3945 3946 3947 3948 3949 3950 3951 3952 3953 3954 3955 3956 3957 3958 3959 3960 3961 3962 3963 3964 3965 3966 3967 3968 3969 3970 3971 3972 3973 3974 3975 3976 3977 3978 3979 3980 3981 3982 3983 3984 3985 3986 3987 3988 3989 3990 3991 3992 3993 3994 3995 3996 3997 3998 3999 4000 4001 4002 4003 4004 4005 4006 4007 4008 4009 4010 4011 4012 4013 4014 4015 4016 4017 4018 4019 4020 4021 4022 4023 4024 4025 4026 4027 4028 4029 4030 4031 4032 4033 4034 4035 4036 4037 4038 4039 4040 4041 4042 4043 4044 4045 4046 4047 4048 4049 4050 4051 4052 4053 4054 4055 4056 4057 4058 4059 4060 4061 4062 4063 4064 4065 4066 4067 4068 4069 4070 4071 4072 4073 4074 4075 4076 4077 4078 4079 4080 4081 4082 4083 4084 4085 4086 4087 4088 4089 4090 4091 4092 4093 4094 4095 4096 4097 4098 4099 4100 4101 4102 4103 4104 4105 4106 4107 4108 4109 4110 4111 4112 4113 4114 4115 4116 4117 4118 4119 4120 4121 4122 4123 4124 4125 4126 4127 4128 4129 4130 4131 4132 4133 4134 4135 4136 4137 4138 4139 4140 4141 4142 4143 4144 4145 4146 4147 4148 4149 4150 4151 4152 4153 4154 4155 4156 4157 4158 4159 4160 4161 4162 4163 4164 4165 4166 4167 4168 4169 4170 4171 4172 4173 4174 4175 4176 4177 4178 4179 4180 4181 4182 4183 4184 4185 4186 4187 4188 4189 4190 4191 4192 4193 4194 4195 4196 4197 4198 4199 4200 4201 4202 4203 4204 4205 4206 4207 4208 4209 4210 4211 4212 4213 4214 4215 4216 4217 4218 4219 4220 4221 4222 4223 4224 4225 4226 4227 4228 4229 4230 4231 4232 4233 4234 4235 4236 4237 4238 4239 4240 4241 4242 4243 4244 4245 4246 4247 4248 4249 4250 4251 4252 4253 4254 4255 4256 4257 4258 4259 4260 4261 4262 4263 4264 4265 4266 4267 4268 4269 4270 4271 4272 4273 4274 4275 4276 4277 4278 4279 4280 4281 4282 4283 4284 4285 4286 4287 4288 4289 4290 4291 4292 4293 4294 4295 4296 4297 4298 4299 4300 4301 4302 4303 4304 4305 4306 4307 4308 4309 4310 4311 4312 4313 4314 4315 4316 4317 4318 4319 4320 4321 4322 4323 4324 4325 4326 4327 4328 4329 4330 4331 4332 4333 4334 4335 4336 4337 4338 4339 4340 4341 4342 4343 4344 4345 4346 4347 4348 4349 4350 4351 4352 4353 4354 4355 4356 4357 4358 4359 4360 4361 4362 4363 4364 4365 4366 4367 4368 4369 4370 4371 4372 4373 4374 4375 4376 4377 4378 4379 4380 4381 4382 4383 4384 4385 4386 4387 4388 4389 4390 4391 4392 4393 4394 4395 4396 4397 4398 4399 4400 4401 4402 4403 4404 4405 4406 4407 4408 4409 4410 4411 4412 4413 4414 4415 4416 4417 4418 4419 4420 4421 4422 4423 4424 4425 4426 4427 4428 4429 4430 4431 4432 4433 4434 4435 4436 4437 4438 4439 4440 4441 4442 4443 4444 4445 4446 4447 4448 4449 4450 4451 4452 4453 4454 4455 4456 4457 4458 4459 4460 4461 4462 4463 4464 4465 4466 4467 4468 4469 4470 4471 4472 4473 4474 4475 4476 4477 4478 4479 4480 4481 4482 4483 4484 4485 4486 4487 4488 4489 4490 4491 4492 4493 4494 4495 4496 4497 4498 4499 4500 4501 4502 4503 4504 4505 4506 4507 4508 4509 4510 4511 4512 4513 4514 4515 4516 4517 4518 4519 4520 4521 4522 4523 4524 4525 4526 4527 4528 4529 4530 4531 4532 4533 4534 4535 4536 4537 4538 4539 4540 4541 4542 4543 4544 4545 4546 4547 4548 4549 4550 4551 4552 4553 4554 4555 4556 4557 4558 4559 4560 4561 4562 4563 4564 4565 4566 4567 4568 4569 4570 4571 4572 4573 4574 4575 4576 4577 4578 4579 4580 4581 4582 4583 4584 4585 4586 4587 4588 4589 4590 4591 4592 4593 4594 4595 4596 4597 4598 4599 4600 4601 4602 4603 4604 4605 4606 4607 4608 4609 4610 4611 4612 4613 4614 4615 4616 4617 4618 4619 4620 4621 4622 4623 4624 4625 4626 4627 4628 4629 4630 4631 4632 4633 4634 4635 4636 4637 4638 4639 4640 4641 4642 4643 4644 4645 4646 4647 4648 4649 4650 4651 4652 4653 4654 4655 4656 4657 4658 4659 4660 4661 4662 4663 4664 4665 4666 4667 4668 4669 4670 4671 4672 4673 4674 4675 4676 4677 4678 4679 4680 4681 4682 4683 4684 4685 4686 4687 4688 4689 4690 4691 4692 4693 4694 4695 4696 4697 4698 4699 4700 4701 4702 4703 4704 4705 4706 4707 4708 4709 4710 4711 4712 4713 4714 4715 4716 4717 4718 4719 4720 4721 4722 4723 4724 4725 4726 4727 4728 4729 4730 4731 4732 4733 4734 4735 4736 4737 4738 4739 4740 4741 4742 4743 4744 4745 4746 4747 4748 4749 4750 4751 4752 4753 4754 4755 4756 4757 4758 4759 4760 4761 4762 4763 4764 4765 4766 4767 4768 4769 4770 4771 4772 4773 4774 4775 4776 4777 4778 4779 4780 4781 4782 4783 4784 4785 4786 4787 4788 4789 4790 4791 4792 4793 4794 4795 4796 4797 4798 4799 4800 4801 4802 4803 4804 4805 4806 4807 4808 4809 4810 4811 4812 4813 4814 4815 4816 4817 4818 4819 4820 4821 4822 4823 4824 4825 4826 4827 4828 4829 4830 4831 4832 4833 4834 4835 4836 4837 4838 4839 4840 4841 4842 4843 4844 4845 4846 4847 4848 4849 4850 4851 4852 4853 4854 4855 4856 4857 4858 4859 4860 4861 4862 4863 4864 4865 4866 4867 4868 4869 4870 4871 4872 4873 4874 4875 4876 4877 4878 4879 4880 4881 4882 4883 4884 4885 4886 4887 4888 4889 4890 4891 4892 4893 4894 4895 4896 4897 4898 4899 4900 4901 4902 4903 4904 4905 4906 4907 4908 4909 4910 4911 4912 4913 4914 4915 4916 4917 4918 4919 4920 4921 4922 4923 4924 4925 4926 4927 4928 4929 4930 4931 4932 4933 4934 4935 4936 4937 4938 4939 4940 4941 4942 4943 4944 4945 4946 4947 4948 4949 4950 4951 4952 4953 4954 4955 4956 4957 4958 4959 4960 4961 4962 4963 4964 4965 4966 4967 4968 4969 4970 4971 4972 4973 4974 4975 4976 4977 4978 4979 4980 4981 4982 | // SPDX-License-Identifier: GPL-2.0-only /* * VXLAN: Virtual eXtensible Local Area Network * * Copyright (c) 2012-2013 Vyatta Inc. */ #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt #include <linux/kernel.h> #include <linux/module.h> #include <linux/errno.h> #include <linux/slab.h> #include <linux/udp.h> #include <linux/igmp.h> #include <linux/if_ether.h> #include <linux/ethtool.h> #include <net/arp.h> #include <net/ndisc.h> #include <net/gro.h> #include <net/ipv6_stubs.h> #include <net/ip.h> #include <net/icmp.h> #include <net/rtnetlink.h> #include <net/inet_ecn.h> #include <net/net_namespace.h> #include <net/netns/generic.h> #include <net/tun_proto.h> #include <net/vxlan.h> #include <net/nexthop.h> #if IS_ENABLED(CONFIG_IPV6) #include <net/ip6_tunnel.h> #include <net/ip6_checksum.h> #endif #include "vxlan_private.h" #define VXLAN_VERSION "0.1" #define FDB_AGE_DEFAULT 300 /* 5 min */ #define FDB_AGE_INTERVAL (10 * HZ) /* rescan interval */ /* UDP port for VXLAN traffic. * The IANA assigned port is 4789, but the Linux default is 8472 * for compatibility with early adopters. */ static unsigned short vxlan_port __read_mostly = 8472; module_param_named(udp_port, vxlan_port, ushort, 0444); MODULE_PARM_DESC(udp_port, "Destination UDP port"); static bool log_ecn_error = true; module_param(log_ecn_error, bool, 0644); MODULE_PARM_DESC(log_ecn_error, "Log packets received with corrupted ECN"); unsigned int vxlan_net_id; const u8 all_zeros_mac[ETH_ALEN + 2]; static struct rtnl_link_ops vxlan_link_ops; static int vxlan_sock_add(struct vxlan_dev *vxlan); static void vxlan_vs_del_dev(struct vxlan_dev *vxlan); /* salt for hash table */ static u32 vxlan_salt __read_mostly; static inline bool vxlan_collect_metadata(struct vxlan_sock *vs) { return vs->flags & VXLAN_F_COLLECT_METADATA || ip_tunnel_collect_metadata(); } /* Find VXLAN socket based on network namespace, address family, UDP port, * enabled unshareable flags and socket device binding (see l3mdev with * non-default VRF). */ static struct vxlan_sock *vxlan_find_sock(struct net *net, sa_family_t family, __be16 port, u32 flags, int ifindex) { struct vxlan_sock *vs; flags &= VXLAN_F_RCV_FLAGS; hlist_for_each_entry_rcu(vs, vs_head(net, port), hlist) { if (inet_sk(vs->sock->sk)->inet_sport == port && vxlan_get_sk_family(vs) == family && vs->flags == flags && vs->sock->sk->sk_bound_dev_if == ifindex) return vs; } return NULL; } static struct vxlan_dev *vxlan_vs_find_vni(struct vxlan_sock *vs, int ifindex, __be32 vni, struct vxlan_vni_node **vninode) { struct vxlan_vni_node *vnode; struct vxlan_dev_node *node; /* For flow based devices, map all packets to VNI 0 */ if (vs->flags & VXLAN_F_COLLECT_METADATA && !(vs->flags & VXLAN_F_VNIFILTER)) vni = 0; hlist_for_each_entry_rcu(node, vni_head(vs, vni), hlist) { if (!node->vxlan) continue; vnode = NULL; if (node->vxlan->cfg.flags & VXLAN_F_VNIFILTER) { vnode = vxlan_vnifilter_lookup(node->vxlan, vni); if (!vnode) continue; } else if (node->vxlan->default_dst.remote_vni != vni) { continue; } if (IS_ENABLED(CONFIG_IPV6)) { const struct vxlan_config *cfg = &node->vxlan->cfg; if ((cfg->flags & VXLAN_F_IPV6_LINKLOCAL) && cfg->remote_ifindex != ifindex) continue; } if (vninode) *vninode = vnode; return node->vxlan; } return NULL; } /* Look up VNI in a per net namespace table */ static struct vxlan_dev *vxlan_find_vni(struct net *net, int ifindex, __be32 vni, sa_family_t family, __be16 port, u32 flags) { struct vxlan_sock *vs; vs = vxlan_find_sock(net, family, port, flags, ifindex); if (!vs) return NULL; return vxlan_vs_find_vni(vs, ifindex, vni, NULL); } /* Fill in neighbour message in skbuff. */ static int vxlan_fdb_info(struct sk_buff *skb, struct vxlan_dev *vxlan, const struct vxlan_fdb *fdb, u32 portid, u32 seq, int type, unsigned int flags, const struct vxlan_rdst *rdst) { unsigned long now = jiffies; struct nda_cacheinfo ci; bool send_ip, send_eth; struct nlmsghdr *nlh; struct nexthop *nh; struct ndmsg *ndm; int nh_family; u32 nh_id; nlh = nlmsg_put(skb, portid, seq, type, sizeof(*ndm), flags); if (nlh == NULL) return -EMSGSIZE; ndm = nlmsg_data(nlh); memset(ndm, 0, sizeof(*ndm)); send_eth = send_ip = true; rcu_read_lock(); nh = rcu_dereference(fdb->nh); if (nh) { nh_family = nexthop_get_family(nh); nh_id = nh->id; } rcu_read_unlock(); if (type == RTM_GETNEIGH) { if (rdst) { send_ip = !vxlan_addr_any(&rdst->remote_ip); ndm->ndm_family = send_ip ? rdst->remote_ip.sa.sa_family : AF_INET; } else if (nh) { ndm->ndm_family = nh_family; } send_eth = !is_zero_ether_addr(fdb->eth_addr); } else ndm->ndm_family = AF_BRIDGE; ndm->ndm_state = fdb->state; ndm->ndm_ifindex = vxlan->dev->ifindex; ndm->ndm_flags = fdb->flags; if (rdst && rdst->offloaded) ndm->ndm_flags |= NTF_OFFLOADED; ndm->ndm_type = RTN_UNICAST; if (!net_eq(dev_net(vxlan->dev), vxlan->net) && nla_put_s32(skb, NDA_LINK_NETNSID, peernet2id(dev_net(vxlan->dev), vxlan->net))) goto nla_put_failure; if (send_eth && nla_put(skb, NDA_LLADDR, ETH_ALEN, &fdb->eth_addr)) goto nla_put_failure; if (nh) { if (nla_put_u32(skb, NDA_NH_ID, nh_id)) goto nla_put_failure; } else if (rdst) { if (send_ip && vxlan_nla_put_addr(skb, NDA_DST, &rdst->remote_ip)) goto nla_put_failure; if (rdst->remote_port && rdst->remote_port != vxlan->cfg.dst_port && nla_put_be16(skb, NDA_PORT, rdst->remote_port)) goto nla_put_failure; if (rdst->remote_vni != vxlan->default_dst.remote_vni && nla_put_u32(skb, NDA_VNI, be32_to_cpu(rdst->remote_vni))) goto nla_put_failure; if (rdst->remote_ifindex && nla_put_u32(skb, NDA_IFINDEX, rdst->remote_ifindex)) goto nla_put_failure; } if ((vxlan->cfg.flags & VXLAN_F_COLLECT_METADATA) && fdb->vni && nla_put_u32(skb, NDA_SRC_VNI, be32_to_cpu(fdb->vni))) goto nla_put_failure; ci.ndm_used = jiffies_to_clock_t(now - fdb->used); ci.ndm_confirmed = 0; ci.ndm_updated = jiffies_to_clock_t(now - fdb->updated); ci.ndm_refcnt = 0; if (nla_put(skb, NDA_CACHEINFO, sizeof(ci), &ci)) goto nla_put_failure; nlmsg_end(skb, nlh); return 0; nla_put_failure: nlmsg_cancel(skb, nlh); return -EMSGSIZE; } static inline size_t vxlan_nlmsg_size(void) { return NLMSG_ALIGN(sizeof(struct ndmsg)) + nla_total_size(ETH_ALEN) /* NDA_LLADDR */ + nla_total_size(sizeof(struct in6_addr)) /* NDA_DST */ + nla_total_size(sizeof(__be16)) /* NDA_PORT */ + nla_total_size(sizeof(__be32)) /* NDA_VNI */ + nla_total_size(sizeof(__u32)) /* NDA_IFINDEX */ + nla_total_size(sizeof(__s32)) /* NDA_LINK_NETNSID */ + nla_total_size(sizeof(struct nda_cacheinfo)); } static void __vxlan_fdb_notify(struct vxlan_dev *vxlan, struct vxlan_fdb *fdb, struct vxlan_rdst *rd, int type) { struct net *net = dev_net(vxlan->dev); struct sk_buff *skb; int err = -ENOBUFS; skb = nlmsg_new(vxlan_nlmsg_size(), GFP_ATOMIC); if (skb == NULL) goto errout; err = vxlan_fdb_info(skb, vxlan, fdb, 0, 0, type, 0, rd); if (err < 0) { /* -EMSGSIZE implies BUG in vxlan_nlmsg_size() */ WARN_ON(err == -EMSGSIZE); kfree_skb(skb); goto errout; } rtnl_notify(skb, net, 0, RTNLGRP_NEIGH, NULL, GFP_ATOMIC); return; errout: rtnl_set_sk_err(net, RTNLGRP_NEIGH, err); } static void vxlan_fdb_switchdev_notifier_info(const struct vxlan_dev *vxlan, const struct vxlan_fdb *fdb, const struct vxlan_rdst *rd, struct netlink_ext_ack *extack, struct switchdev_notifier_vxlan_fdb_info *fdb_info) { fdb_info->info.dev = vxlan->dev; fdb_info->info.extack = extack; fdb_info->remote_ip = rd->remote_ip; fdb_info->remote_port = rd->remote_port; fdb_info->remote_vni = rd->remote_vni; fdb_info->remote_ifindex = rd->remote_ifindex; memcpy(fdb_info->eth_addr, fdb->eth_addr, ETH_ALEN); fdb_info->vni = fdb->vni; fdb_info->offloaded = rd->offloaded; fdb_info->added_by_user = fdb->flags & NTF_VXLAN_ADDED_BY_USER; } static int vxlan_fdb_switchdev_call_notifiers(struct vxlan_dev *vxlan, struct vxlan_fdb *fdb, struct vxlan_rdst *rd, bool adding, struct netlink_ext_ack *extack) { struct switchdev_notifier_vxlan_fdb_info info; enum switchdev_notifier_type notifier_type; int ret; if (WARN_ON(!rd)) return 0; notifier_type = adding ? SWITCHDEV_VXLAN_FDB_ADD_TO_DEVICE : SWITCHDEV_VXLAN_FDB_DEL_TO_DEVICE; vxlan_fdb_switchdev_notifier_info(vxlan, fdb, rd, NULL, &info); ret = call_switchdev_notifiers(notifier_type, vxlan->dev, &info.info, extack); return notifier_to_errno(ret); } static int vxlan_fdb_notify(struct vxlan_dev *vxlan, struct vxlan_fdb *fdb, struct vxlan_rdst *rd, int type, bool swdev_notify, struct netlink_ext_ack *extack) { int err; if (swdev_notify && rd) { switch (type) { case RTM_NEWNEIGH: err = vxlan_fdb_switchdev_call_notifiers(vxlan, fdb, rd, true, extack); if (err) return err; break; case RTM_DELNEIGH: vxlan_fdb_switchdev_call_notifiers(vxlan, fdb, rd, false, extack); break; } } __vxlan_fdb_notify(vxlan, fdb, rd, type); return 0; } static void vxlan_ip_miss(struct net_device *dev, union vxlan_addr *ipa) { struct vxlan_dev *vxlan = netdev_priv(dev); struct vxlan_fdb f = { .state = NUD_STALE, }; struct vxlan_rdst remote = { .remote_ip = *ipa, /* goes to NDA_DST */ .remote_vni = cpu_to_be32(VXLAN_N_VID), }; vxlan_fdb_notify(vxlan, &f, &remote, RTM_GETNEIGH, true, NULL); } static void vxlan_fdb_miss(struct vxlan_dev *vxlan, const u8 eth_addr[ETH_ALEN]) { struct vxlan_fdb f = { .state = NUD_STALE, }; struct vxlan_rdst remote = { }; memcpy(f.eth_addr, eth_addr, ETH_ALEN); vxlan_fdb_notify(vxlan, &f, &remote, RTM_GETNEIGH, true, NULL); } /* Hash Ethernet address */ static u32 eth_hash(const unsigned char *addr) { u64 value = get_unaligned((u64 *)addr); /* only want 6 bytes */ #ifdef __BIG_ENDIAN value >>= 16; #else value <<= 16; #endif return hash_64(value, FDB_HASH_BITS); } u32 eth_vni_hash(const unsigned char *addr, __be32 vni) { /* use 1 byte of OUI and 3 bytes of NIC */ u32 key = get_unaligned((u32 *)(addr + 2)); return jhash_2words(key, vni, vxlan_salt) & (FDB_HASH_SIZE - 1); } u32 fdb_head_index(struct vxlan_dev *vxlan, const u8 *mac, __be32 vni) { if (vxlan->cfg.flags & VXLAN_F_COLLECT_METADATA) return eth_vni_hash(mac, vni); else return eth_hash(mac); } /* Hash chain to use given mac address */ static inline struct hlist_head *vxlan_fdb_head(struct vxlan_dev *vxlan, const u8 *mac, __be32 vni) { return &vxlan->fdb_head[fdb_head_index(vxlan, mac, vni)]; } /* Look up Ethernet address in forwarding table */ static struct vxlan_fdb *__vxlan_find_mac(struct vxlan_dev *vxlan, const u8 *mac, __be32 vni) { struct hlist_head *head = vxlan_fdb_head(vxlan, mac, vni); struct vxlan_fdb *f; hlist_for_each_entry_rcu(f, head, hlist) { if (ether_addr_equal(mac, f->eth_addr)) { if (vxlan->cfg.flags & VXLAN_F_COLLECT_METADATA) { if (vni == f->vni) return f; } else { return f; } } } return NULL; } static struct vxlan_fdb *vxlan_find_mac(struct vxlan_dev *vxlan, const u8 *mac, __be32 vni) { struct vxlan_fdb *f; f = __vxlan_find_mac(vxlan, mac, vni); if (f && f->used != jiffies) f->used = jiffies; return f; } /* caller should hold vxlan->hash_lock */ static struct vxlan_rdst *vxlan_fdb_find_rdst(struct vxlan_fdb *f, union vxlan_addr *ip, __be16 port, __be32 vni, __u32 ifindex) { struct vxlan_rdst *rd; list_for_each_entry(rd, &f->remotes, list) { if (vxlan_addr_equal(&rd->remote_ip, ip) && rd->remote_port == port && rd->remote_vni == vni && rd->remote_ifindex == ifindex) return rd; } return NULL; } int vxlan_fdb_find_uc(struct net_device *dev, const u8 *mac, __be32 vni, struct switchdev_notifier_vxlan_fdb_info *fdb_info) { struct vxlan_dev *vxlan = netdev_priv(dev); u8 eth_addr[ETH_ALEN + 2] = { 0 }; struct vxlan_rdst *rdst; struct vxlan_fdb *f; int rc = 0; if (is_multicast_ether_addr(mac) || is_zero_ether_addr(mac)) return -EINVAL; ether_addr_copy(eth_addr, mac); rcu_read_lock(); f = __vxlan_find_mac(vxlan, eth_addr, vni); if (!f) { rc = -ENOENT; goto out; } rdst = first_remote_rcu(f); vxlan_fdb_switchdev_notifier_info(vxlan, f, rdst, NULL, fdb_info); out: rcu_read_unlock(); return rc; } EXPORT_SYMBOL_GPL(vxlan_fdb_find_uc); static int vxlan_fdb_notify_one(struct notifier_block *nb, const struct vxlan_dev *vxlan, const struct vxlan_fdb *f, const struct vxlan_rdst *rdst, struct netlink_ext_ack *extack) { struct switchdev_notifier_vxlan_fdb_info fdb_info; int rc; vxlan_fdb_switchdev_notifier_info(vxlan, f, rdst, extack, &fdb_info); rc = nb->notifier_call(nb, SWITCHDEV_VXLAN_FDB_ADD_TO_DEVICE, &fdb_info); return notifier_to_errno(rc); } int vxlan_fdb_replay(const struct net_device *dev, __be32 vni, struct notifier_block *nb, struct netlink_ext_ack *extack) { struct vxlan_dev *vxlan; struct vxlan_rdst *rdst; struct vxlan_fdb *f; unsigned int h; int rc = 0; if (!netif_is_vxlan(dev)) return -EINVAL; vxlan = netdev_priv(dev); for (h = 0; h < FDB_HASH_SIZE; ++h) { spin_lock_bh(&vxlan->hash_lock[h]); hlist_for_each_entry(f, &vxlan->fdb_head[h], hlist) { if (f->vni == vni) { list_for_each_entry(rdst, &f->remotes, list) { rc = vxlan_fdb_notify_one(nb, vxlan, f, rdst, extack); if (rc) goto unlock; } } } spin_unlock_bh(&vxlan->hash_lock[h]); } return 0; unlock: spin_unlock_bh(&vxlan->hash_lock[h]); return rc; } EXPORT_SYMBOL_GPL(vxlan_fdb_replay); void vxlan_fdb_clear_offload(const struct net_device *dev, __be32 vni) { struct vxlan_dev *vxlan; struct vxlan_rdst *rdst; struct vxlan_fdb *f; unsigned int h; if (!netif_is_vxlan(dev)) return; vxlan = netdev_priv(dev); for (h = 0; h < FDB_HASH_SIZE; ++h) { spin_lock_bh(&vxlan->hash_lock[h]); hlist_for_each_entry(f, &vxlan->fdb_head[h], hlist) if (f->vni == vni) list_for_each_entry(rdst, &f->remotes, list) rdst->offloaded = false; spin_unlock_bh(&vxlan->hash_lock[h]); } } EXPORT_SYMBOL_GPL(vxlan_fdb_clear_offload); /* Replace destination of unicast mac */ static int vxlan_fdb_replace(struct vxlan_fdb *f, union vxlan_addr *ip, __be16 port, __be32 vni, __u32 ifindex, struct vxlan_rdst *oldrd) { struct vxlan_rdst *rd; rd = vxlan_fdb_find_rdst(f, ip, port, vni, ifindex); if (rd) return 0; rd = list_first_entry_or_null(&f->remotes, struct vxlan_rdst, list); if (!rd) return 0; *oldrd = *rd; dst_cache_reset(&rd->dst_cache); rd->remote_ip = *ip; rd->remote_port = port; rd->remote_vni = vni; rd->remote_ifindex = ifindex; rd->offloaded = false; return 1; } /* Add/update destinations for multicast */ static int vxlan_fdb_append(struct vxlan_fdb *f, union vxlan_addr *ip, __be16 port, __be32 vni, __u32 ifindex, struct vxlan_rdst **rdp) { struct vxlan_rdst *rd; rd = vxlan_fdb_find_rdst(f, ip, port, vni, ifindex); if (rd) return 0; rd = kmalloc(sizeof(*rd), GFP_ATOMIC); if (rd == NULL) return -ENOMEM; if (dst_cache_init(&rd->dst_cache, GFP_ATOMIC)) { kfree(rd); return -ENOMEM; } rd->remote_ip = *ip; rd->remote_port = port; rd->offloaded = false; rd->remote_vni = vni; rd->remote_ifindex = ifindex; list_add_tail_rcu(&rd->list, &f->remotes); *rdp = rd; return 1; } static bool vxlan_parse_gpe_proto(struct vxlanhdr *hdr, __be16 *protocol) { struct vxlanhdr_gpe *gpe = (struct vxlanhdr_gpe *)hdr; /* Need to have Next Protocol set for interfaces in GPE mode. */ if (!gpe->np_applied) return false; /* "The initial version is 0. If a receiver does not support the * version indicated it MUST drop the packet. */ if (gpe->version != 0) return false; /* "When the O bit is set to 1, the packet is an OAM packet and OAM * processing MUST occur." However, we don't implement OAM * processing, thus drop the packet. */ if (gpe->oam_flag) return false; *protocol = tun_p_to_eth_p(gpe->next_protocol); if (!*protocol) return false; return true; } static struct vxlanhdr *vxlan_gro_remcsum(struct sk_buff *skb, unsigned int off, struct vxlanhdr *vh, size_t hdrlen, __be32 vni_field, struct gro_remcsum *grc, bool nopartial) { size_t start, offset; if (skb->remcsum_offload) return vh; if (!NAPI_GRO_CB(skb)->csum_valid) return NULL; start = vxlan_rco_start(vni_field); offset = start + vxlan_rco_offset(vni_field); vh = skb_gro_remcsum_process(skb, (void *)vh, off, hdrlen, start, offset, grc, nopartial); skb->remcsum_offload = 1; return vh; } static struct vxlanhdr *vxlan_gro_prepare_receive(struct sock *sk, struct list_head *head, struct sk_buff *skb, struct gro_remcsum *grc) { struct sk_buff *p; struct vxlanhdr *vh, *vh2; unsigned int hlen, off_vx; struct vxlan_sock *vs = rcu_dereference_sk_user_data(sk); __be32 flags; skb_gro_remcsum_init(grc); off_vx = skb_gro_offset(skb); hlen = off_vx + sizeof(*vh); vh = skb_gro_header(skb, hlen, off_vx); if (unlikely(!vh)) return NULL; skb_gro_postpull_rcsum(skb, vh, sizeof(struct vxlanhdr)); flags = vh->vx_flags; if ((flags & VXLAN_HF_RCO) && (vs->flags & VXLAN_F_REMCSUM_RX)) { vh = vxlan_gro_remcsum(skb, off_vx, vh, sizeof(struct vxlanhdr), vh->vx_vni, grc, !!(vs->flags & VXLAN_F_REMCSUM_NOPARTIAL)); if (!vh) return NULL; } skb_gro_pull(skb, sizeof(struct vxlanhdr)); /* pull vxlan header */ list_for_each_entry(p, head, list) { if (!NAPI_GRO_CB(p)->same_flow) continue; vh2 = (struct vxlanhdr *)(p->data + off_vx); if (vh->vx_flags != vh2->vx_flags || vh->vx_vni != vh2->vx_vni) { NAPI_GRO_CB(p)->same_flow = 0; continue; } } return vh; } static struct sk_buff *vxlan_gro_receive(struct sock *sk, struct list_head *head, struct sk_buff *skb) { struct sk_buff *pp = NULL; struct gro_remcsum grc; int flush = 1; if (vxlan_gro_prepare_receive(sk, head, skb, &grc)) { pp = call_gro_receive(eth_gro_receive, head, skb); flush = 0; } skb_gro_flush_final_remcsum(skb, pp, flush, &grc); return pp; } static struct sk_buff *vxlan_gpe_gro_receive(struct sock *sk, struct list_head *head, struct sk_buff *skb) { const struct packet_offload *ptype; struct sk_buff *pp = NULL; struct gro_remcsum grc; struct vxlanhdr *vh; __be16 protocol; int flush = 1; vh = vxlan_gro_prepare_receive(sk, head, skb, &grc); if (vh) { if (!vxlan_parse_gpe_proto(vh, &protocol)) goto out; ptype = gro_find_receive_by_type(protocol); if (!ptype) goto out; pp = call_gro_receive(ptype->callbacks.gro_receive, head, skb); flush = 0; } out: skb_gro_flush_final_remcsum(skb, pp, flush, &grc); return pp; } static int vxlan_gro_complete(struct sock *sk, struct sk_buff *skb, int nhoff) { /* Sets 'skb->inner_mac_header' since we are always called with * 'skb->encapsulation' set. */ return eth_gro_complete(skb, nhoff + sizeof(struct vxlanhdr)); } static int vxlan_gpe_gro_complete(struct sock *sk, struct sk_buff *skb, int nhoff) { struct vxlanhdr *vh = (struct vxlanhdr *)(skb->data + nhoff); const struct packet_offload *ptype; int err = -ENOSYS; __be16 protocol; if (!vxlan_parse_gpe_proto(vh, &protocol)) return err; ptype = gro_find_complete_by_type(protocol); if (ptype) err = ptype->callbacks.gro_complete(skb, nhoff + sizeof(struct vxlanhdr)); return err; } static struct vxlan_fdb *vxlan_fdb_alloc(struct vxlan_dev *vxlan, const u8 *mac, __u16 state, __be32 src_vni, __u16 ndm_flags) { struct vxlan_fdb *f; f = kmalloc(sizeof(*f), GFP_ATOMIC); if (!f) return NULL; f->state = state; f->flags = ndm_flags; f->updated = f->used = jiffies; f->vni = src_vni; f->nh = NULL; RCU_INIT_POINTER(f->vdev, vxlan); INIT_LIST_HEAD(&f->nh_list); INIT_LIST_HEAD(&f->remotes); memcpy(f->eth_addr, mac, ETH_ALEN); return f; } static void vxlan_fdb_insert(struct vxlan_dev *vxlan, const u8 *mac, __be32 src_vni, struct vxlan_fdb *f) { ++vxlan->addrcnt; hlist_add_head_rcu(&f->hlist, vxlan_fdb_head(vxlan, mac, src_vni)); } static int vxlan_fdb_nh_update(struct vxlan_dev *vxlan, struct vxlan_fdb *fdb, u32 nhid, struct netlink_ext_ack *extack) { struct nexthop *old_nh = rtnl_dereference(fdb->nh); struct nexthop *nh; int err = -EINVAL; if (old_nh && old_nh->id == nhid) return 0; nh = nexthop_find_by_id(vxlan->net, nhid); if (!nh) { NL_SET_ERR_MSG(extack, "Nexthop id does not exist"); goto err_inval; } if (!nexthop_get(nh)) { NL_SET_ERR_MSG(extack, "Nexthop has been deleted"); nh = NULL; goto err_inval; } if (!nexthop_is_fdb(nh)) { NL_SET_ERR_MSG(extack, "Nexthop is not a fdb nexthop"); goto err_inval; } if (!nexthop_is_multipath(nh)) { NL_SET_ERR_MSG(extack, "Nexthop is not a multipath group"); goto err_inval; } /* check nexthop group family */ switch (vxlan->default_dst.remote_ip.sa.sa_family) { case AF_INET: if (!nexthop_has_v4(nh)) { err = -EAFNOSUPPORT; NL_SET_ERR_MSG(extack, "Nexthop group family not supported"); goto err_inval; } break; case AF_INET6: if (nexthop_has_v4(nh)) { err = -EAFNOSUPPORT; NL_SET_ERR_MSG(extack, "Nexthop group family not supported"); goto err_inval; } } if (old_nh) { list_del_rcu(&fdb->nh_list); nexthop_put(old_nh); } rcu_assign_pointer(fdb->nh, nh); list_add_tail_rcu(&fdb->nh_list, &nh->fdb_list); return 1; err_inval: if (nh) nexthop_put(nh); return err; } int vxlan_fdb_create(struct vxlan_dev *vxlan, const u8 *mac, union vxlan_addr *ip, __u16 state, __be16 port, __be32 src_vni, __be32 vni, __u32 ifindex, __u16 ndm_flags, u32 nhid, struct vxlan_fdb **fdb, struct netlink_ext_ack *extack) { struct vxlan_rdst *rd = NULL; struct vxlan_fdb *f; int rc; if (vxlan->cfg.addrmax && vxlan->addrcnt >= vxlan->cfg.addrmax) return -ENOSPC; netdev_dbg(vxlan->dev, "add %pM -> %pIS\n", mac, ip); f = vxlan_fdb_alloc(vxlan, mac, state, src_vni, ndm_flags); if (!f) return -ENOMEM; if (nhid) rc = vxlan_fdb_nh_update(vxlan, f, nhid, extack); else rc = vxlan_fdb_append(f, ip, port, vni, ifindex, &rd); if (rc < 0) goto errout; *fdb = f; return 0; errout: kfree(f); return rc; } static void __vxlan_fdb_free(struct vxlan_fdb *f) { struct vxlan_rdst *rd, *nd; struct nexthop *nh; nh = rcu_dereference_raw(f->nh); if (nh) { rcu_assign_pointer(f->nh, NULL); rcu_assign_pointer(f->vdev, NULL); nexthop_put(nh); } list_for_each_entry_safe(rd, nd, &f->remotes, list) { dst_cache_destroy(&rd->dst_cache); kfree(rd); } kfree(f); } static void vxlan_fdb_free(struct rcu_head *head) { struct vxlan_fdb *f = container_of(head, struct vxlan_fdb, rcu); __vxlan_fdb_free(f); } static void vxlan_fdb_destroy(struct vxlan_dev *vxlan, struct vxlan_fdb *f, bool do_notify, bool swdev_notify) { struct vxlan_rdst *rd; netdev_dbg(vxlan->dev, "delete %pM\n", f->eth_addr); --vxlan->addrcnt; if (do_notify) { if (rcu_access_pointer(f->nh)) vxlan_fdb_notify(vxlan, f, NULL, RTM_DELNEIGH, swdev_notify, NULL); else list_for_each_entry(rd, &f->remotes, list) vxlan_fdb_notify(vxlan, f, rd, RTM_DELNEIGH, swdev_notify, NULL); } hlist_del_rcu(&f->hlist); list_del_rcu(&f->nh_list); call_rcu(&f->rcu, vxlan_fdb_free); } static void vxlan_dst_free(struct rcu_head *head) { struct vxlan_rdst *rd = container_of(head, struct vxlan_rdst, rcu); dst_cache_destroy(&rd->dst_cache); kfree(rd); } static int vxlan_fdb_update_existing(struct vxlan_dev *vxlan, union vxlan_addr *ip, __u16 state, __u16 flags, __be16 port, __be32 vni, __u32 ifindex, __u16 ndm_flags, struct vxlan_fdb *f, u32 nhid, bool swdev_notify, struct netlink_ext_ack *extack) { __u16 fdb_flags = (ndm_flags & ~NTF_USE); struct vxlan_rdst *rd = NULL; struct vxlan_rdst oldrd; int notify = 0; int rc = 0; int err; if (nhid && !rcu_access_pointer(f->nh)) { NL_SET_ERR_MSG(extack, "Cannot replace an existing non nexthop fdb with a nexthop"); return -EOPNOTSUPP; } if (nhid && (flags & NLM_F_APPEND)) { NL_SET_ERR_MSG(extack, "Cannot append to a nexthop fdb"); return -EOPNOTSUPP; } /* Do not allow an externally learned entry to take over an entry added * by the user. */ if (!(fdb_flags & NTF_EXT_LEARNED) || !(f->flags & NTF_VXLAN_ADDED_BY_USER)) { if (f->state != state) { f->state = state; f->updated = jiffies; notify = 1; } if (f->flags != fdb_flags) { f->flags = fdb_flags; f->updated = jiffies; notify = 1; } } if ((flags & NLM_F_REPLACE)) { /* Only change unicasts */ if (!(is_multicast_ether_addr(f->eth_addr) || is_zero_ether_addr(f->eth_addr))) { if (nhid) { rc = vxlan_fdb_nh_update(vxlan, f, nhid, extack); if (rc < 0) return rc; } else { rc = vxlan_fdb_replace(f, ip, port, vni, ifindex, &oldrd); } notify |= rc; } else { NL_SET_ERR_MSG(extack, "Cannot replace non-unicast fdb entries"); return -EOPNOTSUPP; } } if ((flags & NLM_F_APPEND) && (is_multicast_ether_addr(f->eth_addr) || is_zero_ether_addr(f->eth_addr))) { rc = vxlan_fdb_append(f, ip, port, vni, ifindex, &rd); if (rc < 0) return rc; notify |= rc; } if (ndm_flags & NTF_USE) f->used = jiffies; if (notify) { if (rd == NULL) rd = first_remote_rtnl(f); err = vxlan_fdb_notify(vxlan, f, rd, RTM_NEWNEIGH, swdev_notify, extack); if (err) goto err_notify; } return 0; err_notify: if (nhid) return err; if ((flags & NLM_F_REPLACE) && rc) *rd = oldrd; else if ((flags & NLM_F_APPEND) && rc) { list_del_rcu(&rd->list); call_rcu(&rd->rcu, vxlan_dst_free); } return err; } static int vxlan_fdb_update_create(struct vxlan_dev *vxlan, const u8 *mac, union vxlan_addr *ip, __u16 state, __u16 flags, __be16 port, __be32 src_vni, __be32 vni, __u32 ifindex, __u16 ndm_flags, u32 nhid, bool swdev_notify, struct netlink_ext_ack *extack) { __u16 fdb_flags = (ndm_flags & ~NTF_USE); struct vxlan_fdb *f; int rc; /* Disallow replace to add a multicast entry */ if ((flags & NLM_F_REPLACE) && (is_multicast_ether_addr(mac) || is_zero_ether_addr(mac))) return -EOPNOTSUPP; netdev_dbg(vxlan->dev, "add %pM -> %pIS\n", mac, ip); rc = vxlan_fdb_create(vxlan, mac, ip, state, port, src_vni, vni, ifindex, fdb_flags, nhid, &f, extack); if (rc < 0) return rc; vxlan_fdb_insert(vxlan, mac, src_vni, f); rc = vxlan_fdb_notify(vxlan, f, first_remote_rtnl(f), RTM_NEWNEIGH, swdev_notify, extack); if (rc) goto err_notify; return 0; err_notify: vxlan_fdb_destroy(vxlan, f, false, false); return rc; } /* Add new entry to forwarding table -- assumes lock held */ int vxlan_fdb_update(struct vxlan_dev *vxlan, const u8 *mac, union vxlan_addr *ip, __u16 state, __u16 flags, __be16 port, __be32 src_vni, __be32 vni, __u32 ifindex, __u16 ndm_flags, u32 nhid, bool swdev_notify, struct netlink_ext_ack *extack) { struct vxlan_fdb *f; f = __vxlan_find_mac(vxlan, mac, src_vni); if (f) { if (flags & NLM_F_EXCL) { netdev_dbg(vxlan->dev, "lost race to create %pM\n", mac); return -EEXIST; } return vxlan_fdb_update_existing(vxlan, ip, state, flags, port, vni, ifindex, ndm_flags, f, nhid, swdev_notify, extack); } else { if (!(flags & NLM_F_CREATE)) return -ENOENT; return vxlan_fdb_update_create(vxlan, mac, ip, state, flags, port, src_vni, vni, ifindex, ndm_flags, nhid, swdev_notify, extack); } } static void vxlan_fdb_dst_destroy(struct vxlan_dev *vxlan, struct vxlan_fdb *f, struct vxlan_rdst *rd, bool swdev_notify) { list_del_rcu(&rd->list); vxlan_fdb_notify(vxlan, f, rd, RTM_DELNEIGH, swdev_notify, NULL); call_rcu(&rd->rcu, vxlan_dst_free); } static int vxlan_fdb_parse(struct nlattr *tb[], struct vxlan_dev *vxlan, union vxlan_addr *ip, __be16 *port, __be32 *src_vni, __be32 *vni, u32 *ifindex, u32 *nhid, struct netlink_ext_ack *extack) { struct net *net = dev_net(vxlan->dev); int err; if (tb[NDA_NH_ID] && (tb[NDA_DST] || tb[NDA_VNI] || tb[NDA_IFINDEX] || tb[NDA_PORT])) { NL_SET_ERR_MSG(extack, "DST, VNI, ifindex and port are mutually exclusive with NH_ID"); return -EINVAL; } if (tb[NDA_DST]) { err = vxlan_nla_get_addr(ip, tb[NDA_DST]); if (err) { NL_SET_ERR_MSG(extack, "Unsupported address family"); return err; } } else { union vxlan_addr *remote = &vxlan->default_dst.remote_ip; if (remote->sa.sa_family == AF_INET) { ip->sin.sin_addr.s_addr = htonl(INADDR_ANY); ip->sa.sa_family = AF_INET; #if IS_ENABLED(CONFIG_IPV6) } else { ip->sin6.sin6_addr = in6addr_any; ip->sa.sa_family = AF_INET6; #endif } } if (tb[NDA_PORT]) { if (nla_len(tb[NDA_PORT]) != sizeof(__be16)) { NL_SET_ERR_MSG(extack, "Invalid vxlan port"); return -EINVAL; } *port = nla_get_be16(tb[NDA_PORT]); } else { *port = vxlan->cfg.dst_port; } if (tb[NDA_VNI]) { if (nla_len(tb[NDA_VNI]) != sizeof(u32)) { NL_SET_ERR_MSG(extack, "Invalid vni"); return -EINVAL; } *vni = cpu_to_be32(nla_get_u32(tb[NDA_VNI])); } else { *vni = vxlan->default_dst.remote_vni; } if (tb[NDA_SRC_VNI]) { if (nla_len(tb[NDA_SRC_VNI]) != sizeof(u32)) { NL_SET_ERR_MSG(extack, "Invalid src vni"); return -EINVAL; } *src_vni = cpu_to_be32(nla_get_u32(tb[NDA_SRC_VNI])); } else { *src_vni = vxlan->default_dst.remote_vni; } if (tb[NDA_IFINDEX]) { struct net_device *tdev; if (nla_len(tb[NDA_IFINDEX]) != sizeof(u32)) { NL_SET_ERR_MSG(extack, "Invalid ifindex"); return -EINVAL; } *ifindex = nla_get_u32(tb[NDA_IFINDEX]); tdev = __dev_get_by_index(net, *ifindex); if (!tdev) { NL_SET_ERR_MSG(extack, "Device not found"); return -EADDRNOTAVAIL; } } else { *ifindex = 0; } *nhid = nla_get_u32_default(tb[NDA_NH_ID], 0); return 0; } /* Add static entry (via netlink) */ static int vxlan_fdb_add(struct ndmsg *ndm, struct nlattr *tb[], struct net_device *dev, const unsigned char *addr, u16 vid, u16 flags, bool *notified, struct netlink_ext_ack *extack) { struct vxlan_dev *vxlan = netdev_priv(dev); /* struct net *net = dev_net(vxlan->dev); */ union vxlan_addr ip; __be16 port; __be32 src_vni, vni; u32 ifindex, nhid; u32 hash_index; int err; if (!(ndm->ndm_state & (NUD_PERMANENT|NUD_REACHABLE))) { pr_info("RTM_NEWNEIGH with invalid state %#x\n", ndm->ndm_state); return -EINVAL; } if (!tb || (!tb[NDA_DST] && !tb[NDA_NH_ID])) return -EINVAL; err = vxlan_fdb_parse(tb, vxlan, &ip, &port, &src_vni, &vni, &ifindex, &nhid, extack); if (err) return err; if (vxlan->default_dst.remote_ip.sa.sa_family != ip.sa.sa_family) return -EAFNOSUPPORT; hash_index = fdb_head_index(vxlan, addr, src_vni); spin_lock_bh(&vxlan->hash_lock[hash_index]); err = vxlan_fdb_update(vxlan, addr, &ip, ndm->ndm_state, flags, port, src_vni, vni, ifindex, ndm->ndm_flags | NTF_VXLAN_ADDED_BY_USER, nhid, true, extack); spin_unlock_bh(&vxlan->hash_lock[hash_index]); if (!err) *notified = true; return err; } int __vxlan_fdb_delete(struct vxlan_dev *vxlan, const unsigned char *addr, union vxlan_addr ip, __be16 port, __be32 src_vni, __be32 vni, u32 ifindex, bool swdev_notify) { struct vxlan_rdst *rd = NULL; struct vxlan_fdb *f; int err = -ENOENT; f = vxlan_find_mac(vxlan, addr, src_vni); if (!f) return err; if (!vxlan_addr_any(&ip)) { rd = vxlan_fdb_find_rdst(f, &ip, port, vni, ifindex); if (!rd) goto out; } /* remove a destination if it's not the only one on the list, * otherwise destroy the fdb entry */ if (rd && !list_is_singular(&f->remotes)) { vxlan_fdb_dst_destroy(vxlan, f, rd, swdev_notify); goto out; } vxlan_fdb_destroy(vxlan, f, true, swdev_notify); out: return 0; } /* Delete entry (via netlink) */ static int vxlan_fdb_delete(struct ndmsg *ndm, struct nlattr *tb[], struct net_device *dev, const unsigned char *addr, u16 vid, bool *notified, struct netlink_ext_ack *extack) { struct vxlan_dev *vxlan = netdev_priv(dev); union vxlan_addr ip; __be32 src_vni, vni; u32 ifindex, nhid; u32 hash_index; __be16 port; int err; err = vxlan_fdb_parse(tb, vxlan, &ip, &port, &src_vni, &vni, &ifindex, &nhid, extack); if (err) return err; hash_index = fdb_head_index(vxlan, addr, src_vni); spin_lock_bh(&vxlan->hash_lock[hash_index]); err = __vxlan_fdb_delete(vxlan, addr, ip, port, src_vni, vni, ifindex, true); spin_unlock_bh(&vxlan->hash_lock[hash_index]); if (!err) *notified = true; return err; } /* Dump forwarding table */ static int vxlan_fdb_dump(struct sk_buff *skb, struct netlink_callback *cb, struct net_device *dev, struct net_device *filter_dev, int *idx) { struct vxlan_dev *vxlan = netdev_priv(dev); unsigned int h; int err = 0; for (h = 0; h < FDB_HASH_SIZE; ++h) { struct vxlan_fdb *f; rcu_read_lock(); hlist_for_each_entry_rcu(f, &vxlan->fdb_head[h], hlist) { struct vxlan_rdst *rd; if (rcu_access_pointer(f->nh)) { if (*idx < cb->args[2]) goto skip_nh; err = vxlan_fdb_info(skb, vxlan, f, NETLINK_CB(cb->skb).portid, cb->nlh->nlmsg_seq, RTM_NEWNEIGH, NLM_F_MULTI, NULL); if (err < 0) { rcu_read_unlock(); goto out; } skip_nh: *idx += 1; continue; } list_for_each_entry_rcu(rd, &f->remotes, list) { if (*idx < cb->args[2]) goto skip; err = vxlan_fdb_info(skb, vxlan, f, NETLINK_CB(cb->skb).portid, cb->nlh->nlmsg_seq, RTM_NEWNEIGH, NLM_F_MULTI, rd); if (err < 0) { rcu_read_unlock(); goto out; } skip: *idx += 1; } } rcu_read_unlock(); } out: return err; } static int vxlan_fdb_get(struct sk_buff *skb, struct nlattr *tb[], struct net_device *dev, const unsigned char *addr, u16 vid, u32 portid, u32 seq, struct netlink_ext_ack *extack) { struct vxlan_dev *vxlan = netdev_priv(dev); struct vxlan_fdb *f; __be32 vni; int err; if (tb[NDA_VNI]) vni = cpu_to_be32(nla_get_u32(tb[NDA_VNI])); else vni = vxlan->default_dst.remote_vni; rcu_read_lock(); f = __vxlan_find_mac(vxlan, addr, vni); if (!f) { NL_SET_ERR_MSG(extack, "Fdb entry not found"); err = -ENOENT; goto errout; } err = vxlan_fdb_info(skb, vxlan, f, portid, seq, RTM_NEWNEIGH, 0, first_remote_rcu(f)); errout: rcu_read_unlock(); return err; } /* Watch incoming packets to learn mapping between Ethernet address * and Tunnel endpoint. */ static enum skb_drop_reason vxlan_snoop(struct net_device *dev, union vxlan_addr *src_ip, const u8 *src_mac, u32 src_ifindex, __be32 vni) { struct vxlan_dev *vxlan = netdev_priv(dev); struct vxlan_fdb *f; u32 ifindex = 0; /* Ignore packets from invalid src-address */ if (!is_valid_ether_addr(src_mac)) return SKB_DROP_REASON_MAC_INVALID_SOURCE; #if IS_ENABLED(CONFIG_IPV6) if (src_ip->sa.sa_family == AF_INET6 && (ipv6_addr_type(&src_ip->sin6.sin6_addr) & IPV6_ADDR_LINKLOCAL)) ifindex = src_ifindex; #endif f = vxlan_find_mac(vxlan, src_mac, vni); if (likely(f)) { struct vxlan_rdst *rdst = first_remote_rcu(f); if (likely(vxlan_addr_equal(&rdst->remote_ip, src_ip) && rdst->remote_ifindex == ifindex)) return SKB_NOT_DROPPED_YET; /* Don't migrate static entries, drop packets */ if (f->state & (NUD_PERMANENT | NUD_NOARP)) return SKB_DROP_REASON_VXLAN_ENTRY_EXISTS; /* Don't override an fdb with nexthop with a learnt entry */ if (rcu_access_pointer(f->nh)) return SKB_DROP_REASON_VXLAN_ENTRY_EXISTS; if (net_ratelimit()) netdev_info(dev, "%pM migrated from %pIS to %pIS\n", src_mac, &rdst->remote_ip.sa, &src_ip->sa); rdst->remote_ip = *src_ip; f->updated = jiffies; vxlan_fdb_notify(vxlan, f, rdst, RTM_NEWNEIGH, true, NULL); } else { u32 hash_index = fdb_head_index(vxlan, src_mac, vni); /* learned new entry */ spin_lock(&vxlan->hash_lock[hash_index]); /* close off race between vxlan_flush and incoming packets */ if (netif_running(dev)) vxlan_fdb_update(vxlan, src_mac, src_ip, NUD_REACHABLE, NLM_F_EXCL|NLM_F_CREATE, vxlan->cfg.dst_port, vni, vxlan->default_dst.remote_vni, ifindex, NTF_SELF, 0, true, NULL); spin_unlock(&vxlan->hash_lock[hash_index]); } return SKB_NOT_DROPPED_YET; } static bool __vxlan_sock_release_prep(struct vxlan_sock *vs) { struct vxlan_net *vn; if (!vs) return false; if (!refcount_dec_and_test(&vs->refcnt)) return false; vn = net_generic(sock_net(vs->sock->sk), vxlan_net_id); spin_lock(&vn->sock_lock); hlist_del_rcu(&vs->hlist); udp_tunnel_notify_del_rx_port(vs->sock, (vs->flags & VXLAN_F_GPE) ? UDP_TUNNEL_TYPE_VXLAN_GPE : UDP_TUNNEL_TYPE_VXLAN); spin_unlock(&vn->sock_lock); return true; } static void vxlan_sock_release(struct vxlan_dev *vxlan) { struct vxlan_sock *sock4 = rtnl_dereference(vxlan->vn4_sock); #if IS_ENABLED(CONFIG_IPV6) struct vxlan_sock *sock6 = rtnl_dereference(vxlan->vn6_sock); RCU_INIT_POINTER(vxlan->vn6_sock, NULL); #endif RCU_INIT_POINTER(vxlan->vn4_sock, NULL); synchronize_net(); if (vxlan->cfg.flags & VXLAN_F_VNIFILTER) vxlan_vs_del_vnigrp(vxlan); else vxlan_vs_del_dev(vxlan); if (__vxlan_sock_release_prep(sock4)) { udp_tunnel_sock_release(sock4->sock); kfree(sock4); } #if IS_ENABLED(CONFIG_IPV6) if (__vxlan_sock_release_prep(sock6)) { udp_tunnel_sock_release(sock6->sock); kfree(sock6); } #endif } static enum skb_drop_reason vxlan_remcsum(struct vxlanhdr *unparsed, struct sk_buff *skb, u32 vxflags) { enum skb_drop_reason reason; size_t start, offset; if (!(unparsed->vx_flags & VXLAN_HF_RCO) || skb->remcsum_offload) goto out; start = vxlan_rco_start(unparsed->vx_vni); offset = start + vxlan_rco_offset(unparsed->vx_vni); reason = pskb_may_pull_reason(skb, offset + sizeof(u16)); if (reason) return reason; skb_remcsum_process(skb, (void *)(vxlan_hdr(skb) + 1), start, offset, !!(vxflags & VXLAN_F_REMCSUM_NOPARTIAL)); out: unparsed->vx_flags &= ~VXLAN_HF_RCO; unparsed->vx_vni &= VXLAN_VNI_MASK; return SKB_NOT_DROPPED_YET; } static void vxlan_parse_gbp_hdr(struct vxlanhdr *unparsed, struct sk_buff *skb, u32 vxflags, struct vxlan_metadata *md) { struct vxlanhdr_gbp *gbp = (struct vxlanhdr_gbp *)unparsed; struct metadata_dst *tun_dst; if (!(unparsed->vx_flags & VXLAN_HF_GBP)) goto out; md->gbp = ntohs(gbp->policy_id); tun_dst = (struct metadata_dst *)skb_dst(skb); if (tun_dst) { __set_bit(IP_TUNNEL_VXLAN_OPT_BIT, tun_dst->u.tun_info.key.tun_flags); tun_dst->u.tun_info.options_len = sizeof(*md); } if (gbp->dont_learn) md->gbp |= VXLAN_GBP_DONT_LEARN; if (gbp->policy_applied) md->gbp |= VXLAN_GBP_POLICY_APPLIED; /* In flow-based mode, GBP is carried in dst_metadata */ if (!(vxflags & VXLAN_F_COLLECT_METADATA)) skb->mark = md->gbp; out: unparsed->vx_flags &= ~VXLAN_GBP_USED_BITS; } static enum skb_drop_reason vxlan_set_mac(struct vxlan_dev *vxlan, struct vxlan_sock *vs, struct sk_buff *skb, __be32 vni) { union vxlan_addr saddr; u32 ifindex = skb->dev->ifindex; skb_reset_mac_header(skb); skb->protocol = eth_type_trans(skb, vxlan->dev); skb_postpull_rcsum(skb, eth_hdr(skb), ETH_HLEN); /* Ignore packet loops (and multicast echo) */ if (ether_addr_equal(eth_hdr(skb)->h_source, vxlan->dev->dev_addr)) return SKB_DROP_REASON_LOCAL_MAC; /* Get address from the outer IP header */ if (vxlan_get_sk_family(vs) == AF_INET) { saddr.sin.sin_addr.s_addr = ip_hdr(skb)->saddr; saddr.sa.sa_family = AF_INET; #if IS_ENABLED(CONFIG_IPV6) } else { saddr.sin6.sin6_addr = ipv6_hdr(skb)->saddr; saddr.sa.sa_family = AF_INET6; #endif } if (!(vxlan->cfg.flags & VXLAN_F_LEARN)) return SKB_NOT_DROPPED_YET; return vxlan_snoop(skb->dev, &saddr, eth_hdr(skb)->h_source, ifindex, vni); } static bool vxlan_ecn_decapsulate(struct vxlan_sock *vs, void *oiph, struct sk_buff *skb) { int err = 0; if (vxlan_get_sk_family(vs) == AF_INET) err = IP_ECN_decapsulate(oiph, skb); #if IS_ENABLED(CONFIG_IPV6) else err = IP6_ECN_decapsulate(oiph, skb); #endif if (unlikely(err) && log_ecn_error) { if (vxlan_get_sk_family(vs) == AF_INET) net_info_ratelimited("non-ECT from %pI4 with TOS=%#x\n", &((struct iphdr *)oiph)->saddr, ((struct iphdr *)oiph)->tos); else net_info_ratelimited("non-ECT from %pI6\n", &((struct ipv6hdr *)oiph)->saddr); } return err <= 1; } /* Callback from net/ipv4/udp.c to receive packets */ static int vxlan_rcv(struct sock *sk, struct sk_buff *skb) { struct vxlan_vni_node *vninode = NULL; struct vxlan_dev *vxlan; struct vxlan_sock *vs; struct vxlanhdr unparsed; struct vxlan_metadata _md; struct vxlan_metadata *md = &_md; __be16 protocol = htons(ETH_P_TEB); enum skb_drop_reason reason; bool raw_proto = false; void *oiph; __be32 vni = 0; int nh; /* Need UDP and VXLAN header to be present */ reason = pskb_may_pull_reason(skb, VXLAN_HLEN); if (reason) goto drop; unparsed = *vxlan_hdr(skb); /* VNI flag always required to be set */ if (!(unparsed.vx_flags & VXLAN_HF_VNI)) { netdev_dbg(skb->dev, "invalid vxlan flags=%#x vni=%#x\n", ntohl(vxlan_hdr(skb)->vx_flags), ntohl(vxlan_hdr(skb)->vx_vni)); reason = SKB_DROP_REASON_VXLAN_INVALID_HDR; /* Return non vxlan pkt */ goto drop; } unparsed.vx_flags &= ~VXLAN_HF_VNI; unparsed.vx_vni &= ~VXLAN_VNI_MASK; vs = rcu_dereference_sk_user_data(sk); if (!vs) goto drop; vni = vxlan_vni(vxlan_hdr(skb)->vx_vni); vxlan = vxlan_vs_find_vni(vs, skb->dev->ifindex, vni, &vninode); if (!vxlan) { reason = SKB_DROP_REASON_VXLAN_VNI_NOT_FOUND; goto drop; } /* For backwards compatibility, only allow reserved fields to be * used by VXLAN extensions if explicitly requested. */ if (vs->flags & VXLAN_F_GPE) { if (!vxlan_parse_gpe_proto(&unparsed, &protocol)) goto drop; unparsed.vx_flags &= ~VXLAN_GPE_USED_BITS; raw_proto = true; } if (__iptunnel_pull_header(skb, VXLAN_HLEN, protocol, raw_proto, !net_eq(vxlan->net, dev_net(vxlan->dev)))) { reason = SKB_DROP_REASON_NOMEM; goto drop; } if (vs->flags & VXLAN_F_REMCSUM_RX) { reason = vxlan_remcsum(&unparsed, skb, vs->flags); if (unlikely(reason)) goto drop; } if (vxlan_collect_metadata(vs)) { IP_TUNNEL_DECLARE_FLAGS(flags) = { }; struct metadata_dst *tun_dst; __set_bit(IP_TUNNEL_KEY_BIT, flags); tun_dst = udp_tun_rx_dst(skb, vxlan_get_sk_family(vs), flags, key32_to_tunnel_id(vni), sizeof(*md)); if (!tun_dst) { reason = SKB_DROP_REASON_NOMEM; goto drop; } md = ip_tunnel_info_opts(&tun_dst->u.tun_info); skb_dst_set(skb, (struct dst_entry *)tun_dst); } else { memset(md, 0, sizeof(*md)); } if (vs->flags & VXLAN_F_GBP) vxlan_parse_gbp_hdr(&unparsed, skb, vs->flags, md); /* Note that GBP and GPE can never be active together. This is * ensured in vxlan_dev_configure. */ if (unparsed.vx_flags || unparsed.vx_vni) { /* If there are any unprocessed flags remaining treat * this as a malformed packet. This behavior diverges from * VXLAN RFC (RFC7348) which stipulates that bits in reserved * in reserved fields are to be ignored. The approach here * maintains compatibility with previous stack code, and also * is more robust and provides a little more security in * adding extensions to VXLAN. */ reason = SKB_DROP_REASON_VXLAN_INVALID_HDR; goto drop; } if (!raw_proto) { reason = vxlan_set_mac(vxlan, vs, skb, vni); if (reason) goto drop; } else { skb_reset_mac_header(skb); skb->dev = vxlan->dev; skb->pkt_type = PACKET_HOST; } /* Save offset of outer header relative to skb->head, * because we are going to reset the network header to the inner header * and might change skb->head. */ nh = skb_network_header(skb) - skb->head; skb_reset_network_header(skb); reason = pskb_inet_may_pull_reason(skb); if (reason) { DEV_STATS_INC(vxlan->dev, rx_length_errors); DEV_STATS_INC(vxlan->dev, rx_errors); vxlan_vnifilter_count(vxlan, vni, vninode, VXLAN_VNI_STATS_RX_ERRORS, 0); goto drop; } /* Get the outer header. */ oiph = skb->head + nh; if (!vxlan_ecn_decapsulate(vs, oiph, skb)) { reason = SKB_DROP_REASON_IP_TUNNEL_ECN; DEV_STATS_INC(vxlan->dev, rx_frame_errors); DEV_STATS_INC(vxlan->dev, rx_errors); vxlan_vnifilter_count(vxlan, vni, vninode, VXLAN_VNI_STATS_RX_ERRORS, 0); goto drop; } rcu_read_lock(); if (unlikely(!(vxlan->dev->flags & IFF_UP))) { rcu_read_unlock(); dev_core_stats_rx_dropped_inc(vxlan->dev); vxlan_vnifilter_count(vxlan, vni, vninode, VXLAN_VNI_STATS_RX_DROPS, 0); reason = SKB_DROP_REASON_DEV_READY; goto drop; } dev_sw_netstats_rx_add(vxlan->dev, skb->len); vxlan_vnifilter_count(vxlan, vni, vninode, VXLAN_VNI_STATS_RX, skb->len); gro_cells_receive(&vxlan->gro_cells, skb); rcu_read_unlock(); return 0; drop: reason = reason ?: SKB_DROP_REASON_NOT_SPECIFIED; /* Consume bad packet */ kfree_skb_reason(skb, reason); return 0; } /* Callback from net/ipv{4,6}/udp.c to check that we have a VNI for errors */ static int vxlan_err_lookup(struct sock *sk, struct sk_buff *skb) { struct vxlan_dev *vxlan; struct vxlan_sock *vs; struct vxlanhdr *hdr; __be32 vni; if (!pskb_may_pull(skb, skb_transport_offset(skb) + VXLAN_HLEN)) return -EINVAL; hdr = vxlan_hdr(skb); if (!(hdr->vx_flags & VXLAN_HF_VNI)) return -EINVAL; vs = rcu_dereference_sk_user_data(sk); if (!vs) return -ENOENT; vni = vxlan_vni(hdr->vx_vni); vxlan = vxlan_vs_find_vni(vs, skb->dev->ifindex, vni, NULL); if (!vxlan) return -ENOENT; return 0; } static int arp_reduce(struct net_device *dev, struct sk_buff *skb, __be32 vni) { struct vxlan_dev *vxlan = netdev_priv(dev); struct arphdr *parp; u8 *arpptr, *sha; __be32 sip, tip; struct neighbour *n; if (dev->flags & IFF_NOARP) goto out; if (!pskb_may_pull(skb, arp_hdr_len(dev))) { dev_core_stats_tx_dropped_inc(dev); vxlan_vnifilter_count(vxlan, vni, NULL, VXLAN_VNI_STATS_TX_DROPS, 0); goto out; } parp = arp_hdr(skb); if ((parp->ar_hrd != htons(ARPHRD_ETHER) && parp->ar_hrd != htons(ARPHRD_IEEE802)) || parp->ar_pro != htons(ETH_P_IP) || parp->ar_op != htons(ARPOP_REQUEST) || parp->ar_hln != dev->addr_len || parp->ar_pln != 4) goto out; arpptr = (u8 *)parp + sizeof(struct arphdr); sha = arpptr; arpptr += dev->addr_len; /* sha */ memcpy(&sip, arpptr, sizeof(sip)); arpptr += sizeof(sip); arpptr += dev->addr_len; /* tha */ memcpy(&tip, arpptr, sizeof(tip)); if (ipv4_is_loopback(tip) || ipv4_is_multicast(tip)) goto out; n = neigh_lookup(&arp_tbl, &tip, dev); if (n) { struct vxlan_fdb *f; struct sk_buff *reply; if (!(READ_ONCE(n->nud_state) & NUD_CONNECTED)) { neigh_release(n); goto out; } f = vxlan_find_mac(vxlan, n->ha, vni); if (f && vxlan_addr_any(&(first_remote_rcu(f)->remote_ip))) { /* bridge-local neighbor */ neigh_release(n); goto out; } reply = arp_create(ARPOP_REPLY, ETH_P_ARP, sip, dev, tip, sha, n->ha, sha); neigh_release(n); if (reply == NULL) goto out; skb_reset_mac_header(reply); __skb_pull(reply, skb_network_offset(reply)); reply->ip_summed = CHECKSUM_UNNECESSARY; reply->pkt_type = PACKET_HOST; if (netif_rx(reply) == NET_RX_DROP) { dev_core_stats_rx_dropped_inc(dev); vxlan_vnifilter_count(vxlan, vni, NULL, VXLAN_VNI_STATS_RX_DROPS, 0); } } else if (vxlan->cfg.flags & VXLAN_F_L3MISS) { union vxlan_addr ipa = { .sin.sin_addr.s_addr = tip, .sin.sin_family = AF_INET, }; vxlan_ip_miss(dev, &ipa); } out: consume_skb(skb); return NETDEV_TX_OK; } #if IS_ENABLED(CONFIG_IPV6) static struct sk_buff *vxlan_na_create(struct sk_buff *request, struct neighbour *n, bool isrouter) { struct net_device *dev = request->dev; struct sk_buff *reply; struct nd_msg *ns, *na; struct ipv6hdr *pip6; u8 *daddr; int na_olen = 8; /* opt hdr + ETH_ALEN for target */ int ns_olen; int i, len; if (dev == NULL || !pskb_may_pull(request, request->len)) return NULL; len = LL_RESERVED_SPACE(dev) + sizeof(struct ipv6hdr) + sizeof(*na) + na_olen + dev->needed_tailroom; reply = alloc_skb(len, GFP_ATOMIC); if (reply == NULL) return NULL; reply->protocol = htons(ETH_P_IPV6); reply->dev = dev; skb_reserve(reply, LL_RESERVED_SPACE(request->dev)); skb_push(reply, sizeof(struct ethhdr)); skb_reset_mac_header(reply); ns = (struct nd_msg *)(ipv6_hdr(request) + 1); daddr = eth_hdr(request)->h_source; ns_olen = request->len - skb_network_offset(request) - sizeof(struct ipv6hdr) - sizeof(*ns); for (i = 0; i < ns_olen-1; i += (ns->opt[i+1]<<3)) { if (!ns->opt[i + 1]) { kfree_skb(reply); return NULL; } if (ns->opt[i] == ND_OPT_SOURCE_LL_ADDR) { daddr = ns->opt + i + sizeof(struct nd_opt_hdr); break; } } /* Ethernet header */ ether_addr_copy(eth_hdr(reply)->h_dest, daddr); ether_addr_copy(eth_hdr(reply)->h_source, n->ha); eth_hdr(reply)->h_proto = htons(ETH_P_IPV6); reply->protocol = htons(ETH_P_IPV6); skb_pull(reply, sizeof(struct ethhdr)); skb_reset_network_header(reply); skb_put(reply, sizeof(struct ipv6hdr)); /* IPv6 header */ pip6 = ipv6_hdr(reply); memset(pip6, 0, sizeof(struct ipv6hdr)); pip6->version = 6; pip6->priority = ipv6_hdr(request)->priority; pip6->nexthdr = IPPROTO_ICMPV6; pip6->hop_limit = 255; pip6->daddr = ipv6_hdr(request)->saddr; pip6->saddr = *(struct in6_addr *)n->primary_key; skb_pull(reply, sizeof(struct ipv6hdr)); skb_reset_transport_header(reply); /* Neighbor Advertisement */ na = skb_put_zero(reply, sizeof(*na) + na_olen); na->icmph.icmp6_type = NDISC_NEIGHBOUR_ADVERTISEMENT; na->icmph.icmp6_router = isrouter; na->icmph.icmp6_override = 1; na->icmph.icmp6_solicited = 1; na->target = ns->target; ether_addr_copy(&na->opt[2], n->ha); na->opt[0] = ND_OPT_TARGET_LL_ADDR; na->opt[1] = na_olen >> 3; na->icmph.icmp6_cksum = csum_ipv6_magic(&pip6->saddr, &pip6->daddr, sizeof(*na)+na_olen, IPPROTO_ICMPV6, csum_partial(na, sizeof(*na)+na_olen, 0)); pip6->payload_len = htons(sizeof(*na)+na_olen); skb_push(reply, sizeof(struct ipv6hdr)); reply->ip_summed = CHECKSUM_UNNECESSARY; return reply; } static int neigh_reduce(struct net_device *dev, struct sk_buff *skb, __be32 vni) { struct vxlan_dev *vxlan = netdev_priv(dev); const struct in6_addr *daddr; const struct ipv6hdr *iphdr; struct inet6_dev *in6_dev; struct neighbour *n; struct nd_msg *msg; rcu_read_lock(); in6_dev = __in6_dev_get(dev); if (!in6_dev) goto out; iphdr = ipv6_hdr(skb); daddr = &iphdr->daddr; msg = (struct nd_msg *)(iphdr + 1); if (ipv6_addr_loopback(daddr) || ipv6_addr_is_multicast(&msg->target)) goto out; n = neigh_lookup(ipv6_stub->nd_tbl, &msg->target, dev); if (n) { struct vxlan_fdb *f; struct sk_buff *reply; if (!(READ_ONCE(n->nud_state) & NUD_CONNECTED)) { neigh_release(n); goto out; } f = vxlan_find_mac(vxlan, n->ha, vni); if (f && vxlan_addr_any(&(first_remote_rcu(f)->remote_ip))) { /* bridge-local neighbor */ neigh_release(n); goto out; } reply = vxlan_na_create(skb, n, !!(f ? f->flags & NTF_ROUTER : 0)); neigh_release(n); if (reply == NULL) goto out; if (netif_rx(reply) == NET_RX_DROP) { dev_core_stats_rx_dropped_inc(dev); vxlan_vnifilter_count(vxlan, vni, NULL, VXLAN_VNI_STATS_RX_DROPS, 0); } } else if (vxlan->cfg.flags & VXLAN_F_L3MISS) { union vxlan_addr ipa = { .sin6.sin6_addr = msg->target, .sin6.sin6_family = AF_INET6, }; vxlan_ip_miss(dev, &ipa); } out: rcu_read_unlock(); consume_skb(skb); return NETDEV_TX_OK; } #endif static bool route_shortcircuit(struct net_device *dev, struct sk_buff *skb) { struct vxlan_dev *vxlan = netdev_priv(dev); struct neighbour *n; if (is_multicast_ether_addr(eth_hdr(skb)->h_dest)) return false; n = NULL; switch (ntohs(eth_hdr(skb)->h_proto)) { case ETH_P_IP: { struct iphdr *pip; if (!pskb_may_pull(skb, sizeof(struct iphdr))) return false; pip = ip_hdr(skb); n = neigh_lookup(&arp_tbl, &pip->daddr, dev); if (!n && (vxlan->cfg.flags & VXLAN_F_L3MISS)) { union vxlan_addr ipa = { .sin.sin_addr.s_addr = pip->daddr, .sin.sin_family = AF_INET, }; vxlan_ip_miss(dev, &ipa); return false; } break; } #if IS_ENABLED(CONFIG_IPV6) case ETH_P_IPV6: { struct ipv6hdr *pip6; if (!pskb_may_pull(skb, sizeof(struct ipv6hdr))) return false; pip6 = ipv6_hdr(skb); n = neigh_lookup(ipv6_stub->nd_tbl, &pip6->daddr, dev); if (!n && (vxlan->cfg.flags & VXLAN_F_L3MISS)) { union vxlan_addr ipa = { .sin6.sin6_addr = pip6->daddr, .sin6.sin6_family = AF_INET6, }; vxlan_ip_miss(dev, &ipa); return false; } break; } #endif default: return false; } if (n) { bool diff; diff = !ether_addr_equal(eth_hdr(skb)->h_dest, n->ha); if (diff) { memcpy(eth_hdr(skb)->h_source, eth_hdr(skb)->h_dest, dev->addr_len); memcpy(eth_hdr(skb)->h_dest, n->ha, dev->addr_len); } neigh_release(n); return diff; } return false; } static int vxlan_build_gpe_hdr(struct vxlanhdr *vxh, __be16 protocol) { struct vxlanhdr_gpe *gpe = (struct vxlanhdr_gpe *)vxh; gpe->np_applied = 1; gpe->next_protocol = tun_p_from_eth_p(protocol); if (!gpe->next_protocol) return -EPFNOSUPPORT; return 0; } static int vxlan_build_skb(struct sk_buff *skb, struct dst_entry *dst, int iphdr_len, __be32 vni, struct vxlan_metadata *md, u32 vxflags, bool udp_sum) { struct vxlanhdr *vxh; int min_headroom; int err; int type = udp_sum ? SKB_GSO_UDP_TUNNEL_CSUM : SKB_GSO_UDP_TUNNEL; __be16 inner_protocol = htons(ETH_P_TEB); if ((vxflags & VXLAN_F_REMCSUM_TX) && skb->ip_summed == CHECKSUM_PARTIAL) { int csum_start = skb_checksum_start_offset(skb); if (csum_start <= VXLAN_MAX_REMCSUM_START && !(csum_start & VXLAN_RCO_SHIFT_MASK) && (skb->csum_offset == offsetof(struct udphdr, check) || skb->csum_offset == offsetof(struct tcphdr, check))) type |= SKB_GSO_TUNNEL_REMCSUM; } min_headroom = LL_RESERVED_SPACE(dst->dev) + dst->header_len + VXLAN_HLEN + iphdr_len; /* Need space for new headers (invalidates iph ptr) */ err = skb_cow_head(skb, min_headroom); if (unlikely(err)) return err; err = iptunnel_handle_offloads(skb, type); if (err) return err; vxh = __skb_push(skb, sizeof(*vxh)); vxh->vx_flags = VXLAN_HF_VNI; vxh->vx_vni = vxlan_vni_field(vni); if (type & SKB_GSO_TUNNEL_REMCSUM) { unsigned int start; start = skb_checksum_start_offset(skb) - sizeof(struct vxlanhdr); vxh->vx_vni |= vxlan_compute_rco(start, skb->csum_offset); vxh->vx_flags |= VXLAN_HF_RCO; if (!skb_is_gso(skb)) { skb->ip_summed = CHECKSUM_NONE; skb->encapsulation = 0; } } if (vxflags & VXLAN_F_GBP) vxlan_build_gbp_hdr(vxh, md); if (vxflags & VXLAN_F_GPE) { err = vxlan_build_gpe_hdr(vxh, skb->protocol); if (err < 0) return err; inner_protocol = skb->protocol; } skb_set_inner_protocol(skb, inner_protocol); return 0; } /* Bypass encapsulation if the destination is local */ static void vxlan_encap_bypass(struct sk_buff *skb, struct vxlan_dev *src_vxlan, struct vxlan_dev *dst_vxlan, __be32 vni, bool snoop) { union vxlan_addr loopback; union vxlan_addr *remote_ip = &dst_vxlan->default_dst.remote_ip; struct net_device *dev; int len = skb->len; skb->pkt_type = PACKET_HOST; skb->encapsulation = 0; skb->dev = dst_vxlan->dev; __skb_pull(skb, skb_network_offset(skb)); if (remote_ip->sa.sa_family == AF_INET) { loopback.sin.sin_addr.s_addr = htonl(INADDR_LOOPBACK); loopback.sa.sa_family = AF_INET; #if IS_ENABLED(CONFIG_IPV6) } else { loopback.sin6.sin6_addr = in6addr_loopback; loopback.sa.sa_family = AF_INET6; #endif } rcu_read_lock(); dev = skb->dev; if (unlikely(!(dev->flags & IFF_UP))) { kfree_skb_reason(skb, SKB_DROP_REASON_DEV_READY); goto drop; } if ((dst_vxlan->cfg.flags & VXLAN_F_LEARN) && snoop) vxlan_snoop(dev, &loopback, eth_hdr(skb)->h_source, 0, vni); dev_sw_netstats_tx_add(src_vxlan->dev, 1, len); vxlan_vnifilter_count(src_vxlan, vni, NULL, VXLAN_VNI_STATS_TX, len); if (__netif_rx(skb) == NET_RX_SUCCESS) { dev_sw_netstats_rx_add(dst_vxlan->dev, len); vxlan_vnifilter_count(dst_vxlan, vni, NULL, VXLAN_VNI_STATS_RX, len); } else { drop: dev_core_stats_rx_dropped_inc(dev); vxlan_vnifilter_count(dst_vxlan, vni, NULL, VXLAN_VNI_STATS_RX_DROPS, 0); } rcu_read_unlock(); } static int encap_bypass_if_local(struct sk_buff *skb, struct net_device *dev, struct vxlan_dev *vxlan, int addr_family, __be16 dst_port, int dst_ifindex, __be32 vni, struct dst_entry *dst, u32 rt_flags) { #if IS_ENABLED(CONFIG_IPV6) /* IPv6 rt-flags are checked against RTF_LOCAL, but the value of * RTF_LOCAL is equal to RTCF_LOCAL. So to keep code simple * we can use RTCF_LOCAL which works for ipv4 and ipv6 route entry. */ BUILD_BUG_ON(RTCF_LOCAL != RTF_LOCAL); #endif /* Bypass encapsulation if the destination is local */ if (rt_flags & RTCF_LOCAL && !(rt_flags & (RTCF_BROADCAST | RTCF_MULTICAST)) && vxlan->cfg.flags & VXLAN_F_LOCALBYPASS) { struct vxlan_dev *dst_vxlan; dst_release(dst); dst_vxlan = vxlan_find_vni(vxlan->net, dst_ifindex, vni, addr_family, dst_port, vxlan->cfg.flags); if (!dst_vxlan) { DEV_STATS_INC(dev, tx_errors); vxlan_vnifilter_count(vxlan, vni, NULL, VXLAN_VNI_STATS_TX_ERRORS, 0); kfree_skb_reason(skb, SKB_DROP_REASON_VXLAN_VNI_NOT_FOUND); return -ENOENT; } vxlan_encap_bypass(skb, vxlan, dst_vxlan, vni, true); return 1; } return 0; } void vxlan_xmit_one(struct sk_buff *skb, struct net_device *dev, __be32 default_vni, struct vxlan_rdst *rdst, bool did_rsc) { struct dst_cache *dst_cache; struct ip_tunnel_info *info; struct ip_tunnel_key *pkey; struct ip_tunnel_key key; struct vxlan_dev *vxlan = netdev_priv(dev); const struct iphdr *old_iph; struct vxlan_metadata _md; struct vxlan_metadata *md = &_md; unsigned int pkt_len = skb->len; __be16 src_port = 0, dst_port; struct dst_entry *ndst = NULL; int addr_family; __u8 tos, ttl; int ifindex; int err; u32 flags = vxlan->cfg.flags; bool use_cache; bool udp_sum = false; bool xnet = !net_eq(vxlan->net, dev_net(vxlan->dev)); enum skb_drop_reason reason; bool no_eth_encap; __be32 vni = 0; no_eth_encap = flags & VXLAN_F_GPE && skb->protocol != htons(ETH_P_TEB); reason = skb_vlan_inet_prepare(skb, no_eth_encap); if (reason) goto drop; reason = SKB_DROP_REASON_NOT_SPECIFIED; old_iph = ip_hdr(skb); info = skb_tunnel_info(skb); use_cache = ip_tunnel_dst_cache_usable(skb, info); if (rdst) { memset(&key, 0, sizeof(key)); pkey = &key; if (vxlan_addr_any(&rdst->remote_ip)) { if (did_rsc) { /* short-circuited back to local bridge */ vxlan_encap_bypass(skb, vxlan, vxlan, default_vni, true); return; } goto drop; } addr_family = vxlan->cfg.saddr.sa.sa_family; dst_port = rdst->remote_port ? rdst->remote_port : vxlan->cfg.dst_port; vni = (rdst->remote_vni) ? : default_vni; ifindex = rdst->remote_ifindex; if (addr_family == AF_INET) { key.u.ipv4.src = vxlan->cfg.saddr.sin.sin_addr.s_addr; key.u.ipv4.dst = rdst->remote_ip.sin.sin_addr.s_addr; } else { key.u.ipv6.src = vxlan->cfg.saddr.sin6.sin6_addr; key.u.ipv6.dst = rdst->remote_ip.sin6.sin6_addr; } dst_cache = &rdst->dst_cache; md->gbp = skb->mark; if (flags & VXLAN_F_TTL_INHERIT) { ttl = ip_tunnel_get_ttl(old_iph, skb); } else { ttl = vxlan->cfg.ttl; if (!ttl && vxlan_addr_multicast(&rdst->remote_ip)) ttl = 1; } tos = vxlan->cfg.tos; if (tos == 1) tos = ip_tunnel_get_dsfield(old_iph, skb); if (tos && !info) use_cache = false; if (addr_family == AF_INET) udp_sum = !(flags & VXLAN_F_UDP_ZERO_CSUM_TX); else udp_sum = !(flags & VXLAN_F_UDP_ZERO_CSUM6_TX); #if IS_ENABLED(CONFIG_IPV6) switch (vxlan->cfg.label_policy) { case VXLAN_LABEL_FIXED: key.label = vxlan->cfg.label; break; case VXLAN_LABEL_INHERIT: key.label = ip_tunnel_get_flowlabel(old_iph, skb); break; default: DEBUG_NET_WARN_ON_ONCE(1); goto drop; } #endif } else { if (!info) { WARN_ONCE(1, "%s: Missing encapsulation instructions\n", dev->name); goto drop; } pkey = &info->key; addr_family = ip_tunnel_info_af(info); dst_port = info->key.tp_dst ? : vxlan->cfg.dst_port; vni = tunnel_id_to_key32(info->key.tun_id); ifindex = 0; dst_cache = &info->dst_cache; if (test_bit(IP_TUNNEL_VXLAN_OPT_BIT, info->key.tun_flags)) { if (info->options_len < sizeof(*md)) goto drop; md = ip_tunnel_info_opts(info); } ttl = info->key.ttl; tos = info->key.tos; udp_sum = test_bit(IP_TUNNEL_CSUM_BIT, info->key.tun_flags); } src_port = udp_flow_src_port(dev_net(dev), skb, vxlan->cfg.port_min, vxlan->cfg.port_max, true); rcu_read_lock(); if (addr_family == AF_INET) { struct vxlan_sock *sock4 = rcu_dereference(vxlan->vn4_sock); struct rtable *rt; __be16 df = 0; __be32 saddr; if (!ifindex) ifindex = sock4->sock->sk->sk_bound_dev_if; rt = udp_tunnel_dst_lookup(skb, dev, vxlan->net, ifindex, &saddr, pkey, src_port, dst_port, tos, use_cache ? dst_cache : NULL); if (IS_ERR(rt)) { err = PTR_ERR(rt); reason = SKB_DROP_REASON_IP_OUTNOROUTES; goto tx_error; } if (!info) { /* Bypass encapsulation if the destination is local */ err = encap_bypass_if_local(skb, dev, vxlan, AF_INET, dst_port, ifindex, vni, &rt->dst, rt->rt_flags); if (err) goto out_unlock; if (vxlan->cfg.df == VXLAN_DF_SET) { df = htons(IP_DF); } else if (vxlan->cfg.df == VXLAN_DF_INHERIT) { struct ethhdr *eth = eth_hdr(skb); if (ntohs(eth->h_proto) == ETH_P_IPV6 || (ntohs(eth->h_proto) == ETH_P_IP && old_iph->frag_off & htons(IP_DF))) df = htons(IP_DF); } } else if (test_bit(IP_TUNNEL_DONT_FRAGMENT_BIT, info->key.tun_flags)) { df = htons(IP_DF); } ndst = &rt->dst; err = skb_tunnel_check_pmtu(skb, ndst, vxlan_headroom(flags & VXLAN_F_GPE), netif_is_any_bridge_port(dev)); if (err < 0) { goto tx_error; } else if (err) { if (info) { struct ip_tunnel_info *unclone; unclone = skb_tunnel_info_unclone(skb); if (unlikely(!unclone)) goto tx_error; unclone->key.u.ipv4.src = pkey->u.ipv4.dst; unclone->key.u.ipv4.dst = saddr; } vxlan_encap_bypass(skb, vxlan, vxlan, vni, false); dst_release(ndst); goto out_unlock; } tos = ip_tunnel_ecn_encap(tos, old_iph, skb); ttl = ttl ? : ip4_dst_hoplimit(&rt->dst); err = vxlan_build_skb(skb, ndst, sizeof(struct iphdr), vni, md, flags, udp_sum); if (err < 0) { reason = SKB_DROP_REASON_NOMEM; goto tx_error; } udp_tunnel_xmit_skb(rt, sock4->sock->sk, skb, saddr, pkey->u.ipv4.dst, tos, ttl, df, src_port, dst_port, xnet, !udp_sum); #if IS_ENABLED(CONFIG_IPV6) } else { struct vxlan_sock *sock6 = rcu_dereference(vxlan->vn6_sock); struct in6_addr saddr; if (!ifindex) ifindex = sock6->sock->sk->sk_bound_dev_if; ndst = udp_tunnel6_dst_lookup(skb, dev, vxlan->net, sock6->sock, ifindex, &saddr, pkey, src_port, dst_port, tos, use_cache ? dst_cache : NULL); if (IS_ERR(ndst)) { err = PTR_ERR(ndst); ndst = NULL; reason = SKB_DROP_REASON_IP_OUTNOROUTES; goto tx_error; } if (!info) { u32 rt6i_flags = dst_rt6_info(ndst)->rt6i_flags; err = encap_bypass_if_local(skb, dev, vxlan, AF_INET6, dst_port, ifindex, vni, ndst, rt6i_flags); if (err) goto out_unlock; } err = skb_tunnel_check_pmtu(skb, ndst, vxlan_headroom((flags & VXLAN_F_GPE) | VXLAN_F_IPV6), netif_is_any_bridge_port(dev)); if (err < 0) { goto tx_error; } else if (err) { if (info) { struct ip_tunnel_info *unclone; unclone = skb_tunnel_info_unclone(skb); if (unlikely(!unclone)) goto tx_error; unclone->key.u.ipv6.src = pkey->u.ipv6.dst; unclone->key.u.ipv6.dst = saddr; } vxlan_encap_bypass(skb, vxlan, vxlan, vni, false); dst_release(ndst); goto out_unlock; } tos = ip_tunnel_ecn_encap(tos, old_iph, skb); ttl = ttl ? : ip6_dst_hoplimit(ndst); skb_scrub_packet(skb, xnet); err = vxlan_build_skb(skb, ndst, sizeof(struct ipv6hdr), vni, md, flags, udp_sum); if (err < 0) { reason = SKB_DROP_REASON_NOMEM; goto tx_error; } udp_tunnel6_xmit_skb(ndst, sock6->sock->sk, skb, dev, &saddr, &pkey->u.ipv6.dst, tos, ttl, pkey->label, src_port, dst_port, !udp_sum); #endif } vxlan_vnifilter_count(vxlan, vni, NULL, VXLAN_VNI_STATS_TX, pkt_len); out_unlock: rcu_read_unlock(); return; drop: dev_core_stats_tx_dropped_inc(dev); vxlan_vnifilter_count(vxlan, vni, NULL, VXLAN_VNI_STATS_TX_DROPS, 0); kfree_skb_reason(skb, reason); return; tx_error: rcu_read_unlock(); if (err == -ELOOP) DEV_STATS_INC(dev, collisions); else if (err == -ENETUNREACH) DEV_STATS_INC(dev, tx_carrier_errors); dst_release(ndst); DEV_STATS_INC(dev, tx_errors); vxlan_vnifilter_count(vxlan, vni, NULL, VXLAN_VNI_STATS_TX_ERRORS, 0); kfree_skb_reason(skb, reason); } static void vxlan_xmit_nh(struct sk_buff *skb, struct net_device *dev, struct vxlan_fdb *f, __be32 vni, bool did_rsc) { struct vxlan_rdst nh_rdst; struct nexthop *nh; bool do_xmit; u32 hash; memset(&nh_rdst, 0, sizeof(struct vxlan_rdst)); hash = skb_get_hash(skb); rcu_read_lock(); nh = rcu_dereference(f->nh); if (!nh) { rcu_read_unlock(); goto drop; } do_xmit = vxlan_fdb_nh_path_select(nh, hash, &nh_rdst); rcu_read_unlock(); if (likely(do_xmit)) vxlan_xmit_one(skb, dev, vni, &nh_rdst, did_rsc); else goto drop; return; drop: dev_core_stats_tx_dropped_inc(dev); vxlan_vnifilter_count(netdev_priv(dev), vni, NULL, VXLAN_VNI_STATS_TX_DROPS, 0); dev_kfree_skb(skb); } static netdev_tx_t vxlan_xmit_nhid(struct sk_buff *skb, struct net_device *dev, u32 nhid, __be32 vni) { struct vxlan_dev *vxlan = netdev_priv(dev); struct vxlan_rdst nh_rdst; struct nexthop *nh; bool do_xmit; u32 hash; memset(&nh_rdst, 0, sizeof(struct vxlan_rdst)); hash = skb_get_hash(skb); rcu_read_lock(); nh = nexthop_find_by_id(dev_net(dev), nhid); if (unlikely(!nh || !nexthop_is_fdb(nh) || !nexthop_is_multipath(nh))) { rcu_read_unlock(); goto drop; } do_xmit = vxlan_fdb_nh_path_select(nh, hash, &nh_rdst); rcu_read_unlock(); if (vxlan->cfg.saddr.sa.sa_family != nh_rdst.remote_ip.sa.sa_family) goto drop; if (likely(do_xmit)) vxlan_xmit_one(skb, dev, vni, &nh_rdst, false); else goto drop; return NETDEV_TX_OK; drop: dev_core_stats_tx_dropped_inc(dev); vxlan_vnifilter_count(netdev_priv(dev), vni, NULL, VXLAN_VNI_STATS_TX_DROPS, 0); dev_kfree_skb(skb); return NETDEV_TX_OK; } /* Transmit local packets over Vxlan * * Outer IP header inherits ECN and DF from inner header. * Outer UDP destination is the VXLAN assigned port. * source port is based on hash of flow */ static netdev_tx_t vxlan_xmit(struct sk_buff *skb, struct net_device *dev) { struct vxlan_dev *vxlan = netdev_priv(dev); struct vxlan_rdst *rdst, *fdst = NULL; const struct ip_tunnel_info *info; struct vxlan_fdb *f; struct ethhdr *eth; __be32 vni = 0; u32 nhid = 0; bool did_rsc; info = skb_tunnel_info(skb); skb_reset_mac_header(skb); if (vxlan->cfg.flags & VXLAN_F_COLLECT_METADATA) { if (info && info->mode & IP_TUNNEL_INFO_BRIDGE && info->mode & IP_TUNNEL_INFO_TX) { vni = tunnel_id_to_key32(info->key.tun_id); nhid = info->key.nhid; } else { if (info && info->mode & IP_TUNNEL_INFO_TX) vxlan_xmit_one(skb, dev, vni, NULL, false); else kfree_skb_reason(skb, SKB_DROP_REASON_TUNNEL_TXINFO); return NETDEV_TX_OK; } } if (vxlan->cfg.flags & VXLAN_F_PROXY) { eth = eth_hdr(skb); if (ntohs(eth->h_proto) == ETH_P_ARP) return arp_reduce(dev, skb, vni); #if IS_ENABLED(CONFIG_IPV6) else if (ntohs(eth->h_proto) == ETH_P_IPV6 && pskb_may_pull(skb, sizeof(struct ipv6hdr) + sizeof(struct nd_msg)) && ipv6_hdr(skb)->nexthdr == IPPROTO_ICMPV6) { struct nd_msg *m = (struct nd_msg *)(ipv6_hdr(skb) + 1); if (m->icmph.icmp6_code == 0 && m->icmph.icmp6_type == NDISC_NEIGHBOUR_SOLICITATION) return neigh_reduce(dev, skb, vni); } #endif } if (nhid) return vxlan_xmit_nhid(skb, dev, nhid, vni); if (vxlan->cfg.flags & VXLAN_F_MDB) { struct vxlan_mdb_entry *mdb_entry; rcu_read_lock(); mdb_entry = vxlan_mdb_entry_skb_get(vxlan, skb, vni); if (mdb_entry) { netdev_tx_t ret; ret = vxlan_mdb_xmit(vxlan, mdb_entry, skb); rcu_read_unlock(); return ret; } rcu_read_unlock(); } eth = eth_hdr(skb); f = vxlan_find_mac(vxlan, eth->h_dest, vni); did_rsc = false; if (f && (f->flags & NTF_ROUTER) && (vxlan->cfg.flags & VXLAN_F_RSC) && (ntohs(eth->h_proto) == ETH_P_IP || ntohs(eth->h_proto) == ETH_P_IPV6)) { did_rsc = route_shortcircuit(dev, skb); if (did_rsc) f = vxlan_find_mac(vxlan, eth->h_dest, vni); } if (f == NULL) { f = vxlan_find_mac(vxlan, all_zeros_mac, vni); if (f == NULL) { if ((vxlan->cfg.flags & VXLAN_F_L2MISS) && !is_multicast_ether_addr(eth->h_dest)) vxlan_fdb_miss(vxlan, eth->h_dest); dev_core_stats_tx_dropped_inc(dev); vxlan_vnifilter_count(vxlan, vni, NULL, VXLAN_VNI_STATS_TX_DROPS, 0); kfree_skb_reason(skb, SKB_DROP_REASON_VXLAN_NO_REMOTE); return NETDEV_TX_OK; } } if (rcu_access_pointer(f->nh)) { vxlan_xmit_nh(skb, dev, f, (vni ? : vxlan->default_dst.remote_vni), did_rsc); } else { list_for_each_entry_rcu(rdst, &f->remotes, list) { struct sk_buff *skb1; if (!fdst) { fdst = rdst; continue; } skb1 = skb_clone(skb, GFP_ATOMIC); if (skb1) vxlan_xmit_one(skb1, dev, vni, rdst, did_rsc); } if (fdst) vxlan_xmit_one(skb, dev, vni, fdst, did_rsc); else kfree_skb_reason(skb, SKB_DROP_REASON_VXLAN_NO_REMOTE); } return NETDEV_TX_OK; } /* Walk the forwarding table and purge stale entries */ static void vxlan_cleanup(struct timer_list *t) { struct vxlan_dev *vxlan = from_timer(vxlan, t, age_timer); unsigned long next_timer = jiffies + FDB_AGE_INTERVAL; unsigned int h; if (!netif_running(vxlan->dev)) return; for (h = 0; h < FDB_HASH_SIZE; ++h) { struct hlist_node *p, *n; spin_lock(&vxlan->hash_lock[h]); hlist_for_each_safe(p, n, &vxlan->fdb_head[h]) { struct vxlan_fdb *f = container_of(p, struct vxlan_fdb, hlist); unsigned long timeout; if (f->state & (NUD_PERMANENT | NUD_NOARP)) continue; if (f->flags & NTF_EXT_LEARNED) continue; timeout = f->used + vxlan->cfg.age_interval * HZ; if (time_before_eq(timeout, jiffies)) { netdev_dbg(vxlan->dev, "garbage collect %pM\n", f->eth_addr); f->state = NUD_STALE; vxlan_fdb_destroy(vxlan, f, true, true); } else if (time_before(timeout, next_timer)) next_timer = timeout; } spin_unlock(&vxlan->hash_lock[h]); } mod_timer(&vxlan->age_timer, next_timer); } static void vxlan_vs_del_dev(struct vxlan_dev *vxlan) { struct vxlan_net *vn = net_generic(vxlan->net, vxlan_net_id); spin_lock(&vn->sock_lock); hlist_del_init_rcu(&vxlan->hlist4.hlist); #if IS_ENABLED(CONFIG_IPV6) hlist_del_init_rcu(&vxlan->hlist6.hlist); #endif spin_unlock(&vn->sock_lock); } static void vxlan_vs_add_dev(struct vxlan_sock *vs, struct vxlan_dev *vxlan, struct vxlan_dev_node *node) { struct vxlan_net *vn = net_generic(vxlan->net, vxlan_net_id); __be32 vni = vxlan->default_dst.remote_vni; node->vxlan = vxlan; spin_lock(&vn->sock_lock); hlist_add_head_rcu(&node->hlist, vni_head(vs, vni)); spin_unlock(&vn->sock_lock); } /* Setup stats when device is created */ static int vxlan_init(struct net_device *dev) { struct vxlan_dev *vxlan = netdev_priv(dev); int err; if (vxlan->cfg.flags & VXLAN_F_VNIFILTER) vxlan_vnigroup_init(vxlan); err = gro_cells_init(&vxlan->gro_cells, dev); if (err) goto err_vnigroup_uninit; err = vxlan_mdb_init(vxlan); if (err) goto err_gro_cells_destroy; netdev_lockdep_set_classes(dev); return 0; err_gro_cells_destroy: gro_cells_destroy(&vxlan->gro_cells); err_vnigroup_uninit: if (vxlan->cfg.flags & VXLAN_F_VNIFILTER) vxlan_vnigroup_uninit(vxlan); return err; } static void vxlan_fdb_delete_default(struct vxlan_dev *vxlan, __be32 vni) { struct vxlan_fdb *f; u32 hash_index = fdb_head_index(vxlan, all_zeros_mac, vni); spin_lock_bh(&vxlan->hash_lock[hash_index]); f = __vxlan_find_mac(vxlan, all_zeros_mac, vni); if (f) vxlan_fdb_destroy(vxlan, f, true, true); spin_unlock_bh(&vxlan->hash_lock[hash_index]); } static void vxlan_uninit(struct net_device *dev) { struct vxlan_dev *vxlan = netdev_priv(dev); vxlan_mdb_fini(vxlan); if (vxlan->cfg.flags & VXLAN_F_VNIFILTER) vxlan_vnigroup_uninit(vxlan); gro_cells_destroy(&vxlan->gro_cells); vxlan_fdb_delete_default(vxlan, vxlan->cfg.vni); } /* Start ageing timer and join group when device is brought up */ static int vxlan_open(struct net_device *dev) { struct vxlan_dev *vxlan = netdev_priv(dev); int ret; ret = vxlan_sock_add(vxlan); if (ret < 0) return ret; ret = vxlan_multicast_join(vxlan); if (ret) { vxlan_sock_release(vxlan); return ret; } if (vxlan->cfg.age_interval) mod_timer(&vxlan->age_timer, jiffies + FDB_AGE_INTERVAL); return ret; } struct vxlan_fdb_flush_desc { bool ignore_default_entry; unsigned long state; unsigned long state_mask; unsigned long flags; unsigned long flags_mask; __be32 src_vni; u32 nhid; __be32 vni; __be16 port; union vxlan_addr dst_ip; }; static bool vxlan_fdb_is_default_entry(const struct vxlan_fdb *f, const struct vxlan_dev *vxlan) { return is_zero_ether_addr(f->eth_addr) && f->vni == vxlan->cfg.vni; } static bool vxlan_fdb_nhid_matches(const struct vxlan_fdb *f, u32 nhid) { struct nexthop *nh = rtnl_dereference(f->nh); return nh && nh->id == nhid; } static bool vxlan_fdb_flush_matches(const struct vxlan_fdb *f, const struct vxlan_dev *vxlan, const struct vxlan_fdb_flush_desc *desc) { if (desc->state_mask && (f->state & desc->state_mask) != desc->state) return false; if (desc->flags_mask && (f->flags & desc->flags_mask) != desc->flags) return false; if (desc->ignore_default_entry && vxlan_fdb_is_default_entry(f, vxlan)) return false; if (desc->src_vni && f->vni != desc->src_vni) return false; if (desc->nhid && !vxlan_fdb_nhid_matches(f, desc->nhid)) return false; return true; } static bool vxlan_fdb_flush_should_match_remotes(const struct vxlan_fdb_flush_desc *desc) { return desc->vni || desc->port || desc->dst_ip.sa.sa_family; } static bool vxlan_fdb_flush_remote_matches(const struct vxlan_fdb_flush_desc *desc, const struct vxlan_rdst *rd) { if (desc->vni && rd->remote_vni != desc->vni) return false; if (desc->port && rd->remote_port != desc->port) return false; if (desc->dst_ip.sa.sa_family && !vxlan_addr_equal(&rd->remote_ip, &desc->dst_ip)) return false; return true; } static void vxlan_fdb_flush_match_remotes(struct vxlan_fdb *f, struct vxlan_dev *vxlan, const struct vxlan_fdb_flush_desc *desc, bool *p_destroy_fdb) { bool remotes_flushed = false; struct vxlan_rdst *rd, *tmp; list_for_each_entry_safe(rd, tmp, &f->remotes, list) { if (!vxlan_fdb_flush_remote_matches(desc, rd)) continue; vxlan_fdb_dst_destroy(vxlan, f, rd, true); remotes_flushed = true; } *p_destroy_fdb = remotes_flushed && list_empty(&f->remotes); } /* Purge the forwarding table */ static void vxlan_flush(struct vxlan_dev *vxlan, const struct vxlan_fdb_flush_desc *desc) { bool match_remotes = vxlan_fdb_flush_should_match_remotes(desc); unsigned int h; for (h = 0; h < FDB_HASH_SIZE; ++h) { struct hlist_node *p, *n; spin_lock_bh(&vxlan->hash_lock[h]); hlist_for_each_safe(p, n, &vxlan->fdb_head[h]) { struct vxlan_fdb *f = container_of(p, struct vxlan_fdb, hlist); if (!vxlan_fdb_flush_matches(f, vxlan, desc)) continue; if (match_remotes) { bool destroy_fdb = false; vxlan_fdb_flush_match_remotes(f, vxlan, desc, &destroy_fdb); if (!destroy_fdb) continue; } vxlan_fdb_destroy(vxlan, f, true, true); } spin_unlock_bh(&vxlan->hash_lock[h]); } } static const struct nla_policy vxlan_del_bulk_policy[NDA_MAX + 1] = { [NDA_SRC_VNI] = { .type = NLA_U32 }, [NDA_NH_ID] = { .type = NLA_U32 }, [NDA_VNI] = { .type = NLA_U32 }, [NDA_PORT] = { .type = NLA_U16 }, [NDA_DST] = NLA_POLICY_RANGE(NLA_BINARY, sizeof(struct in_addr), sizeof(struct in6_addr)), [NDA_NDM_STATE_MASK] = { .type = NLA_U16 }, [NDA_NDM_FLAGS_MASK] = { .type = NLA_U8 }, }; #define VXLAN_FDB_FLUSH_IGNORED_NDM_FLAGS (NTF_MASTER | NTF_SELF) #define VXLAN_FDB_FLUSH_ALLOWED_NDM_STATES (NUD_PERMANENT | NUD_NOARP) #define VXLAN_FDB_FLUSH_ALLOWED_NDM_FLAGS (NTF_EXT_LEARNED | NTF_OFFLOADED | \ NTF_ROUTER) static int vxlan_fdb_delete_bulk(struct nlmsghdr *nlh, struct net_device *dev, struct netlink_ext_ack *extack) { struct vxlan_dev *vxlan = netdev_priv(dev); struct vxlan_fdb_flush_desc desc = {}; struct ndmsg *ndm = nlmsg_data(nlh); struct nlattr *tb[NDA_MAX + 1]; u8 ndm_flags; int err; ndm_flags = ndm->ndm_flags & ~VXLAN_FDB_FLUSH_IGNORED_NDM_FLAGS; err = nlmsg_parse(nlh, sizeof(*ndm), tb, NDA_MAX, vxlan_del_bulk_policy, extack); if (err) return err; if (ndm_flags & ~VXLAN_FDB_FLUSH_ALLOWED_NDM_FLAGS) { NL_SET_ERR_MSG(extack, "Unsupported fdb flush ndm flag bits set"); return -EINVAL; } if (ndm->ndm_state & ~VXLAN_FDB_FLUSH_ALLOWED_NDM_STATES) { NL_SET_ERR_MSG(extack, "Unsupported fdb flush ndm state bits set"); return -EINVAL; } desc.state = ndm->ndm_state; desc.flags = ndm_flags; if (tb[NDA_NDM_STATE_MASK]) desc.state_mask = nla_get_u16(tb[NDA_NDM_STATE_MASK]); if (tb[NDA_NDM_FLAGS_MASK]) desc.flags_mask = nla_get_u8(tb[NDA_NDM_FLAGS_MASK]); if (tb[NDA_SRC_VNI]) desc.src_vni = cpu_to_be32(nla_get_u32(tb[NDA_SRC_VNI])); if (tb[NDA_NH_ID]) desc.nhid = nla_get_u32(tb[NDA_NH_ID]); if (tb[NDA_VNI]) desc.vni = cpu_to_be32(nla_get_u32(tb[NDA_VNI])); if (tb[NDA_PORT]) desc.port = nla_get_be16(tb[NDA_PORT]); if (tb[NDA_DST]) { union vxlan_addr ip; err = vxlan_nla_get_addr(&ip, tb[NDA_DST]); if (err) { NL_SET_ERR_MSG_ATTR(extack, tb[NDA_DST], "Unsupported address family"); return err; } desc.dst_ip = ip; } vxlan_flush(vxlan, &desc); return 0; } /* Cleanup timer and forwarding table on shutdown */ static int vxlan_stop(struct net_device *dev) { struct vxlan_dev *vxlan = netdev_priv(dev); struct vxlan_fdb_flush_desc desc = { /* Default entry is deleted at vxlan_uninit. */ .ignore_default_entry = true, .state = 0, .state_mask = NUD_PERMANENT | NUD_NOARP, }; vxlan_multicast_leave(vxlan); del_timer_sync(&vxlan->age_timer); vxlan_flush(vxlan, &desc); vxlan_sock_release(vxlan); return 0; } /* Stub, nothing needs to be done. */ static void vxlan_set_multicast_list(struct net_device *dev) { } static int vxlan_change_mtu(struct net_device *dev, int new_mtu) { struct vxlan_dev *vxlan = netdev_priv(dev); struct vxlan_rdst *dst = &vxlan->default_dst; struct net_device *lowerdev = __dev_get_by_index(vxlan->net, dst->remote_ifindex); /* This check is different than dev->max_mtu, because it looks at * the lowerdev->mtu, rather than the static dev->max_mtu */ if (lowerdev) { int max_mtu = lowerdev->mtu - vxlan_headroom(vxlan->cfg.flags); if (new_mtu > max_mtu) return -EINVAL; } WRITE_ONCE(dev->mtu, new_mtu); return 0; } static int vxlan_fill_metadata_dst(struct net_device *dev, struct sk_buff *skb) { struct vxlan_dev *vxlan = netdev_priv(dev); struct ip_tunnel_info *info = skb_tunnel_info(skb); __be16 sport, dport; sport = udp_flow_src_port(dev_net(dev), skb, vxlan->cfg.port_min, vxlan->cfg.port_max, true); dport = info->key.tp_dst ? : vxlan->cfg.dst_port; if (ip_tunnel_info_af(info) == AF_INET) { struct vxlan_sock *sock4 = rcu_dereference(vxlan->vn4_sock); struct rtable *rt; if (!sock4) return -EIO; rt = udp_tunnel_dst_lookup(skb, dev, vxlan->net, 0, &info->key.u.ipv4.src, &info->key, sport, dport, info->key.tos, &info->dst_cache); if (IS_ERR(rt)) return PTR_ERR(rt); ip_rt_put(rt); } else { #if IS_ENABLED(CONFIG_IPV6) struct vxlan_sock *sock6 = rcu_dereference(vxlan->vn6_sock); struct dst_entry *ndst; if (!sock6) return -EIO; ndst = udp_tunnel6_dst_lookup(skb, dev, vxlan->net, sock6->sock, 0, &info->key.u.ipv6.src, &info->key, sport, dport, info->key.tos, &info->dst_cache); if (IS_ERR(ndst)) return PTR_ERR(ndst); dst_release(ndst); #else /* !CONFIG_IPV6 */ return -EPFNOSUPPORT; #endif } info->key.tp_src = sport; info->key.tp_dst = dport; return 0; } static const struct net_device_ops vxlan_netdev_ether_ops = { .ndo_init = vxlan_init, .ndo_uninit = vxlan_uninit, .ndo_open = vxlan_open, .ndo_stop = vxlan_stop, .ndo_start_xmit = vxlan_xmit, .ndo_set_rx_mode = vxlan_set_multicast_list, .ndo_change_mtu = vxlan_change_mtu, .ndo_validate_addr = eth_validate_addr, .ndo_set_mac_address = eth_mac_addr, .ndo_fdb_add = vxlan_fdb_add, .ndo_fdb_del = vxlan_fdb_delete, .ndo_fdb_del_bulk = vxlan_fdb_delete_bulk, .ndo_fdb_dump = vxlan_fdb_dump, .ndo_fdb_get = vxlan_fdb_get, .ndo_mdb_add = vxlan_mdb_add, .ndo_mdb_del = vxlan_mdb_del, .ndo_mdb_del_bulk = vxlan_mdb_del_bulk, .ndo_mdb_dump = vxlan_mdb_dump, .ndo_mdb_get = vxlan_mdb_get, .ndo_fill_metadata_dst = vxlan_fill_metadata_dst, }; static const struct net_device_ops vxlan_netdev_raw_ops = { .ndo_init = vxlan_init, .ndo_uninit = vxlan_uninit, .ndo_open = vxlan_open, .ndo_stop = vxlan_stop, .ndo_start_xmit = vxlan_xmit, .ndo_change_mtu = vxlan_change_mtu, .ndo_fill_metadata_dst = vxlan_fill_metadata_dst, }; /* Info for udev, that this is a virtual tunnel endpoint */ static const struct device_type vxlan_type = { .name = "vxlan", }; /* Calls the ndo_udp_tunnel_add of the caller in order to * supply the listening VXLAN udp ports. Callers are expected * to implement the ndo_udp_tunnel_add. */ static void vxlan_offload_rx_ports(struct net_device *dev, bool push) { struct vxlan_sock *vs; struct net *net = dev_net(dev); struct vxlan_net *vn = net_generic(net, vxlan_net_id); unsigned int i; spin_lock(&vn->sock_lock); for (i = 0; i < PORT_HASH_SIZE; ++i) { hlist_for_each_entry_rcu(vs, &vn->sock_list[i], hlist) { unsigned short type; if (vs->flags & VXLAN_F_GPE) type = UDP_TUNNEL_TYPE_VXLAN_GPE; else type = UDP_TUNNEL_TYPE_VXLAN; if (push) udp_tunnel_push_rx_port(dev, vs->sock, type); else udp_tunnel_drop_rx_port(dev, vs->sock, type); } } spin_unlock(&vn->sock_lock); } /* Initialize the device structure. */ static void vxlan_setup(struct net_device *dev) { struct vxlan_dev *vxlan = netdev_priv(dev); unsigned int h; eth_hw_addr_random(dev); ether_setup(dev); dev->needs_free_netdev = true; SET_NETDEV_DEVTYPE(dev, &vxlan_type); dev->features |= NETIF_F_SG | NETIF_F_HW_CSUM | NETIF_F_FRAGLIST; dev->features |= NETIF_F_RXCSUM; dev->features |= NETIF_F_GSO_SOFTWARE; dev->vlan_features = dev->features; dev->hw_features |= NETIF_F_SG | NETIF_F_HW_CSUM | NETIF_F_FRAGLIST; dev->hw_features |= NETIF_F_RXCSUM; dev->hw_features |= NETIF_F_GSO_SOFTWARE; netif_keep_dst(dev); dev->priv_flags |= IFF_NO_QUEUE; dev->change_proto_down = true; dev->lltx = true; /* MTU range: 68 - 65535 */ dev->min_mtu = ETH_MIN_MTU; dev->max_mtu = ETH_MAX_MTU; dev->pcpu_stat_type = NETDEV_PCPU_STAT_TSTATS; INIT_LIST_HEAD(&vxlan->next); timer_setup(&vxlan->age_timer, vxlan_cleanup, TIMER_DEFERRABLE); vxlan->dev = dev; for (h = 0; h < FDB_HASH_SIZE; ++h) { spin_lock_init(&vxlan->hash_lock[h]); INIT_HLIST_HEAD(&vxlan->fdb_head[h]); } } static void vxlan_ether_setup(struct net_device *dev) { dev->priv_flags &= ~IFF_TX_SKB_SHARING; dev->priv_flags |= IFF_LIVE_ADDR_CHANGE; dev->netdev_ops = &vxlan_netdev_ether_ops; } static void vxlan_raw_setup(struct net_device *dev) { dev->header_ops = NULL; dev->type = ARPHRD_NONE; dev->hard_header_len = 0; dev->addr_len = 0; dev->flags = IFF_POINTOPOINT | IFF_NOARP | IFF_MULTICAST; dev->netdev_ops = &vxlan_netdev_raw_ops; } static const struct nla_policy vxlan_policy[IFLA_VXLAN_MAX + 1] = { [IFLA_VXLAN_UNSPEC] = { .strict_start_type = IFLA_VXLAN_LOCALBYPASS }, [IFLA_VXLAN_ID] = { .type = NLA_U32 }, [IFLA_VXLAN_GROUP] = { .len = sizeof_field(struct iphdr, daddr) }, [IFLA_VXLAN_GROUP6] = { .len = sizeof(struct in6_addr) }, [IFLA_VXLAN_LINK] = { .type = NLA_U32 }, [IFLA_VXLAN_LOCAL] = { .len = sizeof_field(struct iphdr, saddr) }, [IFLA_VXLAN_LOCAL6] = { .len = sizeof(struct in6_addr) }, [IFLA_VXLAN_TOS] = { .type = NLA_U8 }, [IFLA_VXLAN_TTL] = { .type = NLA_U8 }, [IFLA_VXLAN_LABEL] = { .type = NLA_U32 }, [IFLA_VXLAN_LEARNING] = { .type = NLA_U8 }, [IFLA_VXLAN_AGEING] = { .type = NLA_U32 }, [IFLA_VXLAN_LIMIT] = { .type = NLA_U32 }, [IFLA_VXLAN_PORT_RANGE] = { .len = sizeof(struct ifla_vxlan_port_range) }, [IFLA_VXLAN_PROXY] = { .type = NLA_U8 }, [IFLA_VXLAN_RSC] = { .type = NLA_U8 }, [IFLA_VXLAN_L2MISS] = { .type = NLA_U8 }, [IFLA_VXLAN_L3MISS] = { .type = NLA_U8 }, [IFLA_VXLAN_COLLECT_METADATA] = { .type = NLA_U8 }, [IFLA_VXLAN_PORT] = { .type = NLA_U16 }, [IFLA_VXLAN_UDP_CSUM] = { .type = NLA_U8 }, [IFLA_VXLAN_UDP_ZERO_CSUM6_TX] = { .type = NLA_U8 }, [IFLA_VXLAN_UDP_ZERO_CSUM6_RX] = { .type = NLA_U8 }, [IFLA_VXLAN_REMCSUM_TX] = { .type = NLA_U8 }, [IFLA_VXLAN_REMCSUM_RX] = { .type = NLA_U8 }, [IFLA_VXLAN_GBP] = { .type = NLA_FLAG, }, [IFLA_VXLAN_GPE] = { .type = NLA_FLAG, }, [IFLA_VXLAN_REMCSUM_NOPARTIAL] = { .type = NLA_FLAG }, [IFLA_VXLAN_TTL_INHERIT] = { .type = NLA_FLAG }, [IFLA_VXLAN_DF] = { .type = NLA_U8 }, [IFLA_VXLAN_VNIFILTER] = { .type = NLA_U8 }, [IFLA_VXLAN_LOCALBYPASS] = NLA_POLICY_MAX(NLA_U8, 1), [IFLA_VXLAN_LABEL_POLICY] = NLA_POLICY_MAX(NLA_U32, VXLAN_LABEL_MAX), }; static int vxlan_validate(struct nlattr *tb[], struct nlattr *data[], struct netlink_ext_ack *extack) { if (tb[IFLA_ADDRESS]) { if (nla_len(tb[IFLA_ADDRESS]) != ETH_ALEN) { NL_SET_ERR_MSG_ATTR(extack, tb[IFLA_ADDRESS], "Provided link layer address is not Ethernet"); return -EINVAL; } if (!is_valid_ether_addr(nla_data(tb[IFLA_ADDRESS]))) { NL_SET_ERR_MSG_ATTR(extack, tb[IFLA_ADDRESS], "Provided Ethernet address is not unicast"); return -EADDRNOTAVAIL; } } if (tb[IFLA_MTU]) { u32 mtu = nla_get_u32(tb[IFLA_MTU]); if (mtu < ETH_MIN_MTU || mtu > ETH_MAX_MTU) { NL_SET_ERR_MSG_ATTR(extack, tb[IFLA_MTU], "MTU must be between 68 and 65535"); return -EINVAL; } } if (!data) { NL_SET_ERR_MSG(extack, "Required attributes not provided to perform the operation"); return -EINVAL; } if (data[IFLA_VXLAN_ID]) { u32 id = nla_get_u32(data[IFLA_VXLAN_ID]); if (id >= VXLAN_N_VID) { NL_SET_ERR_MSG_ATTR(extack, data[IFLA_VXLAN_ID], "VXLAN ID must be lower than 16777216"); return -ERANGE; } } if (data[IFLA_VXLAN_PORT_RANGE]) { const struct ifla_vxlan_port_range *p = nla_data(data[IFLA_VXLAN_PORT_RANGE]); if (ntohs(p->high) < ntohs(p->low)) { NL_SET_ERR_MSG_ATTR(extack, data[IFLA_VXLAN_PORT_RANGE], "Invalid source port range"); return -EINVAL; } } if (data[IFLA_VXLAN_DF]) { enum ifla_vxlan_df df = nla_get_u8(data[IFLA_VXLAN_DF]); if (df < 0 || df > VXLAN_DF_MAX) { NL_SET_ERR_MSG_ATTR(extack, data[IFLA_VXLAN_DF], "Invalid DF attribute"); return -EINVAL; } } return 0; } static void vxlan_get_drvinfo(struct net_device *netdev, struct ethtool_drvinfo *drvinfo) { strscpy(drvinfo->version, VXLAN_VERSION, sizeof(drvinfo->version)); strscpy(drvinfo->driver, "vxlan", sizeof(drvinfo->driver)); } static int vxlan_get_link_ksettings(struct net_device *dev, struct ethtool_link_ksettings *cmd) { struct vxlan_dev *vxlan = netdev_priv(dev); struct vxlan_rdst *dst = &vxlan->default_dst; struct net_device *lowerdev = __dev_get_by_index(vxlan->net, dst->remote_ifindex); if (!lowerdev) { cmd->base.duplex = DUPLEX_UNKNOWN; cmd->base.port = PORT_OTHER; cmd->base.speed = SPEED_UNKNOWN; return 0; } return __ethtool_get_link_ksettings(lowerdev, cmd); } static const struct ethtool_ops vxlan_ethtool_ops = { .get_drvinfo = vxlan_get_drvinfo, .get_link = ethtool_op_get_link, .get_link_ksettings = vxlan_get_link_ksettings, }; static struct socket *vxlan_create_sock(struct net *net, bool ipv6, __be16 port, u32 flags, int ifindex) { struct socket *sock; struct udp_port_cfg udp_conf; int err; memset(&udp_conf, 0, sizeof(udp_conf)); if (ipv6) { udp_conf.family = AF_INET6; udp_conf.use_udp6_rx_checksums = !(flags & VXLAN_F_UDP_ZERO_CSUM6_RX); udp_conf.ipv6_v6only = 1; } else { udp_conf.family = AF_INET; } udp_conf.local_udp_port = port; udp_conf.bind_ifindex = ifindex; /* Open UDP socket */ err = udp_sock_create(net, &udp_conf, &sock); if (err < 0) return ERR_PTR(err); udp_allow_gso(sock->sk); return sock; } /* Create new listen socket if needed */ static struct vxlan_sock *vxlan_socket_create(struct net *net, bool ipv6, __be16 port, u32 flags, int ifindex) { struct vxlan_net *vn = net_generic(net, vxlan_net_id); struct vxlan_sock *vs; struct socket *sock; unsigned int h; struct udp_tunnel_sock_cfg tunnel_cfg; vs = kzalloc(sizeof(*vs), GFP_KERNEL); if (!vs) return ERR_PTR(-ENOMEM); for (h = 0; h < VNI_HASH_SIZE; ++h) INIT_HLIST_HEAD(&vs->vni_list[h]); sock = vxlan_create_sock(net, ipv6, port, flags, ifindex); if (IS_ERR(sock)) { kfree(vs); return ERR_CAST(sock); } vs->sock = sock; refcount_set(&vs->refcnt, 1); vs->flags = (flags & VXLAN_F_RCV_FLAGS); spin_lock(&vn->sock_lock); hlist_add_head_rcu(&vs->hlist, vs_head(net, port)); udp_tunnel_notify_add_rx_port(sock, (vs->flags & VXLAN_F_GPE) ? UDP_TUNNEL_TYPE_VXLAN_GPE : UDP_TUNNEL_TYPE_VXLAN); spin_unlock(&vn->sock_lock); /* Mark socket as an encapsulation socket. */ memset(&tunnel_cfg, 0, sizeof(tunnel_cfg)); tunnel_cfg.sk_user_data = vs; tunnel_cfg.encap_type = 1; tunnel_cfg.encap_rcv = vxlan_rcv; tunnel_cfg.encap_err_lookup = vxlan_err_lookup; tunnel_cfg.encap_destroy = NULL; if (vs->flags & VXLAN_F_GPE) { tunnel_cfg.gro_receive = vxlan_gpe_gro_receive; tunnel_cfg.gro_complete = vxlan_gpe_gro_complete; } else { tunnel_cfg.gro_receive = vxlan_gro_receive; tunnel_cfg.gro_complete = vxlan_gro_complete; } setup_udp_tunnel_sock(net, sock, &tunnel_cfg); return vs; } static int __vxlan_sock_add(struct vxlan_dev *vxlan, bool ipv6) { struct vxlan_net *vn = net_generic(vxlan->net, vxlan_net_id); bool metadata = vxlan->cfg.flags & VXLAN_F_COLLECT_METADATA; struct vxlan_sock *vs = NULL; struct vxlan_dev_node *node; int l3mdev_index = 0; if (vxlan->cfg.remote_ifindex) l3mdev_index = l3mdev_master_upper_ifindex_by_index( vxlan->net, vxlan->cfg.remote_ifindex); if (!vxlan->cfg.no_share) { spin_lock(&vn->sock_lock); vs = vxlan_find_sock(vxlan->net, ipv6 ? AF_INET6 : AF_INET, vxlan->cfg.dst_port, vxlan->cfg.flags, l3mdev_index); if (vs && !refcount_inc_not_zero(&vs->refcnt)) { spin_unlock(&vn->sock_lock); return -EBUSY; } spin_unlock(&vn->sock_lock); } if (!vs) vs = vxlan_socket_create(vxlan->net, ipv6, vxlan->cfg.dst_port, vxlan->cfg.flags, l3mdev_index); if (IS_ERR(vs)) return PTR_ERR(vs); #if IS_ENABLED(CONFIG_IPV6) if (ipv6) { rcu_assign_pointer(vxlan->vn6_sock, vs); node = &vxlan->hlist6; } else #endif { rcu_assign_pointer(vxlan->vn4_sock, vs); node = &vxlan->hlist4; } if (metadata && (vxlan->cfg.flags & VXLAN_F_VNIFILTER)) vxlan_vs_add_vnigrp(vxlan, vs, ipv6); else vxlan_vs_add_dev(vs, vxlan, node); return 0; } static int vxlan_sock_add(struct vxlan_dev *vxlan) { bool metadata = vxlan->cfg.flags & VXLAN_F_COLLECT_METADATA; bool ipv6 = vxlan->cfg.flags & VXLAN_F_IPV6 || metadata; bool ipv4 = !ipv6 || metadata; int ret = 0; RCU_INIT_POINTER(vxlan->vn4_sock, NULL); #if IS_ENABLED(CONFIG_IPV6) RCU_INIT_POINTER(vxlan->vn6_sock, NULL); if (ipv6) { ret = __vxlan_sock_add(vxlan, true); if (ret < 0 && ret != -EAFNOSUPPORT) ipv4 = false; } #endif if (ipv4) ret = __vxlan_sock_add(vxlan, false); if (ret < 0) vxlan_sock_release(vxlan); return ret; } int vxlan_vni_in_use(struct net *src_net, struct vxlan_dev *vxlan, struct vxlan_config *conf, __be32 vni) { struct vxlan_net *vn = net_generic(src_net, vxlan_net_id); struct vxlan_dev *tmp; list_for_each_entry(tmp, &vn->vxlan_list, next) { if (tmp == vxlan) continue; if (tmp->cfg.flags & VXLAN_F_VNIFILTER) { if (!vxlan_vnifilter_lookup(tmp, vni)) continue; } else if (tmp->cfg.vni != vni) { continue; } if (tmp->cfg.dst_port != conf->dst_port) continue; if ((tmp->cfg.flags & (VXLAN_F_RCV_FLAGS | VXLAN_F_IPV6)) != (conf->flags & (VXLAN_F_RCV_FLAGS | VXLAN_F_IPV6))) continue; if ((conf->flags & VXLAN_F_IPV6_LINKLOCAL) && tmp->cfg.remote_ifindex != conf->remote_ifindex) continue; return -EEXIST; } return 0; } static int vxlan_config_validate(struct net *src_net, struct vxlan_config *conf, struct net_device **lower, struct vxlan_dev *old, struct netlink_ext_ack *extack) { bool use_ipv6 = false; if (conf->flags & VXLAN_F_GPE) { /* For now, allow GPE only together with * COLLECT_METADATA. This can be relaxed later; in such * case, the other side of the PtP link will have to be * provided. */ if ((conf->flags & ~VXLAN_F_ALLOWED_GPE) || !(conf->flags & VXLAN_F_COLLECT_METADATA)) { NL_SET_ERR_MSG(extack, "VXLAN GPE does not support this combination of attributes"); return -EINVAL; } } if (!conf->remote_ip.sa.sa_family && !conf->saddr.sa.sa_family) { /* Unless IPv6 is explicitly requested, assume IPv4 */ conf->remote_ip.sa.sa_family = AF_INET; conf->saddr.sa.sa_family = AF_INET; } else if (!conf->remote_ip.sa.sa_family) { conf->remote_ip.sa.sa_family = conf->saddr.sa.sa_family; } else if (!conf->saddr.sa.sa_family) { conf->saddr.sa.sa_family = conf->remote_ip.sa.sa_family; } if (conf->saddr.sa.sa_family != conf->remote_ip.sa.sa_family) { NL_SET_ERR_MSG(extack, "Local and remote address must be from the same family"); return -EINVAL; } if (vxlan_addr_multicast(&conf->saddr)) { NL_SET_ERR_MSG(extack, "Local address cannot be multicast"); return -EINVAL; } if (conf->saddr.sa.sa_family == AF_INET6) { if (!IS_ENABLED(CONFIG_IPV6)) { NL_SET_ERR_MSG(extack, "IPv6 support not enabled in the kernel"); return -EPFNOSUPPORT; } use_ipv6 = true; conf->flags |= VXLAN_F_IPV6; if (!(conf->flags & VXLAN_F_COLLECT_METADATA)) { int local_type = ipv6_addr_type(&conf->saddr.sin6.sin6_addr); int remote_type = ipv6_addr_type(&conf->remote_ip.sin6.sin6_addr); if (local_type & IPV6_ADDR_LINKLOCAL) { if (!(remote_type & IPV6_ADDR_LINKLOCAL) && (remote_type != IPV6_ADDR_ANY)) { NL_SET_ERR_MSG(extack, "Invalid combination of local and remote address scopes"); return -EINVAL; } conf->flags |= VXLAN_F_IPV6_LINKLOCAL; } else { if (remote_type == (IPV6_ADDR_UNICAST | IPV6_ADDR_LINKLOCAL)) { NL_SET_ERR_MSG(extack, "Invalid combination of local and remote address scopes"); return -EINVAL; } conf->flags &= ~VXLAN_F_IPV6_LINKLOCAL; } } } if (conf->label && !use_ipv6) { NL_SET_ERR_MSG(extack, "Label attribute only applies to IPv6 VXLAN devices"); return -EINVAL; } if (conf->label_policy && !use_ipv6) { NL_SET_ERR_MSG(extack, "Label policy only applies to IPv6 VXLAN devices"); return -EINVAL; } if (conf->remote_ifindex) { struct net_device *lowerdev; lowerdev = __dev_get_by_index(src_net, conf->remote_ifindex); if (!lowerdev) { NL_SET_ERR_MSG(extack, "Invalid local interface, device not found"); return -ENODEV; } #if IS_ENABLED(CONFIG_IPV6) if (use_ipv6) { struct inet6_dev *idev = __in6_dev_get(lowerdev); if (idev && idev->cnf.disable_ipv6) { NL_SET_ERR_MSG(extack, "IPv6 support disabled by administrator"); return -EPERM; } } #endif *lower = lowerdev; } else { if (vxlan_addr_multicast(&conf->remote_ip)) { NL_SET_ERR_MSG(extack, "Local interface required for multicast remote destination"); return -EINVAL; } #if IS_ENABLED(CONFIG_IPV6) if (conf->flags & VXLAN_F_IPV6_LINKLOCAL) { NL_SET_ERR_MSG(extack, "Local interface required for link-local local/remote addresses"); return -EINVAL; } #endif *lower = NULL; } if (!conf->dst_port) { if (conf->flags & VXLAN_F_GPE) conf->dst_port = htons(IANA_VXLAN_GPE_UDP_PORT); else conf->dst_port = htons(vxlan_port); } if (!conf->age_interval) conf->age_interval = FDB_AGE_DEFAULT; if (vxlan_vni_in_use(src_net, old, conf, conf->vni)) { NL_SET_ERR_MSG(extack, "A VXLAN device with the specified VNI already exists"); return -EEXIST; } return 0; } static void vxlan_config_apply(struct net_device *dev, struct vxlan_config *conf, struct net_device *lowerdev, struct net *src_net, bool changelink) { struct vxlan_dev *vxlan = netdev_priv(dev); struct vxlan_rdst *dst = &vxlan->default_dst; unsigned short needed_headroom = ETH_HLEN; int max_mtu = ETH_MAX_MTU; u32 flags = conf->flags; if (!changelink) { if (flags & VXLAN_F_GPE) vxlan_raw_setup(dev); else vxlan_ether_setup(dev); if (conf->mtu) dev->mtu = conf->mtu; vxlan->net = src_net; } dst->remote_vni = conf->vni; memcpy(&dst->remote_ip, &conf->remote_ip, sizeof(conf->remote_ip)); if (lowerdev) { dst->remote_ifindex = conf->remote_ifindex; netif_inherit_tso_max(dev, lowerdev); needed_headroom = lowerdev->hard_header_len; needed_headroom += lowerdev->needed_headroom; dev->needed_tailroom = lowerdev->needed_tailroom; max_mtu = lowerdev->mtu - vxlan_headroom(flags); if (max_mtu < ETH_MIN_MTU) max_mtu = ETH_MIN_MTU; if (!changelink && !conf->mtu) dev->mtu = max_mtu; } if (dev->mtu > max_mtu) dev->mtu = max_mtu; if (flags & VXLAN_F_COLLECT_METADATA) flags |= VXLAN_F_IPV6; needed_headroom += vxlan_headroom(flags); dev->needed_headroom = needed_headroom; memcpy(&vxlan->cfg, conf, sizeof(*conf)); } static int vxlan_dev_configure(struct net *src_net, struct net_device *dev, struct vxlan_config *conf, bool changelink, struct netlink_ext_ack *extack) { struct vxlan_dev *vxlan = netdev_priv(dev); struct net_device *lowerdev; int ret; ret = vxlan_config_validate(src_net, conf, &lowerdev, vxlan, extack); if (ret) return ret; vxlan_config_apply(dev, conf, lowerdev, src_net, changelink); return 0; } static int __vxlan_dev_create(struct net *net, struct net_device *dev, struct vxlan_config *conf, struct netlink_ext_ack *extack) { struct vxlan_net *vn = net_generic(net, vxlan_net_id); struct vxlan_dev *vxlan = netdev_priv(dev); struct net_device *remote_dev = NULL; struct vxlan_fdb *f = NULL; bool unregister = false; struct vxlan_rdst *dst; int err; dst = &vxlan->default_dst; err = vxlan_dev_configure(net, dev, conf, false, extack); if (err) return err; dev->ethtool_ops = &vxlan_ethtool_ops; /* create an fdb entry for a valid default destination */ if (!vxlan_addr_any(&dst->remote_ip)) { err = vxlan_fdb_create(vxlan, all_zeros_mac, &dst->remote_ip, NUD_REACHABLE | NUD_PERMANENT, vxlan->cfg.dst_port, dst->remote_vni, dst->remote_vni, dst->remote_ifindex, NTF_SELF, 0, &f, extack); if (err) return err; } err = register_netdevice(dev); if (err) goto errout; unregister = true; if (dst->remote_ifindex) { remote_dev = __dev_get_by_index(net, dst->remote_ifindex); if (!remote_dev) { err = -ENODEV; goto errout; } err = netdev_upper_dev_link(remote_dev, dev, extack); if (err) goto errout; } err = rtnl_configure_link(dev, NULL, 0, NULL); if (err < 0) goto unlink; if (f) { vxlan_fdb_insert(vxlan, all_zeros_mac, dst->remote_vni, f); /* notify default fdb entry */ err = vxlan_fdb_notify(vxlan, f, first_remote_rtnl(f), RTM_NEWNEIGH, true, extack); if (err) { vxlan_fdb_destroy(vxlan, f, false, false); if (remote_dev) netdev_upper_dev_unlink(remote_dev, dev); goto unregister; } } list_add(&vxlan->next, &vn->vxlan_list); if (remote_dev) dst->remote_dev = remote_dev; return 0; unlink: if (remote_dev) netdev_upper_dev_unlink(remote_dev, dev); errout: /* unregister_netdevice() destroys the default FDB entry with deletion * notification. But the addition notification was not sent yet, so * destroy the entry by hand here. */ if (f) __vxlan_fdb_free(f); unregister: if (unregister) unregister_netdevice(dev); return err; } /* Set/clear flags based on attribute */ static int vxlan_nl2flag(struct vxlan_config *conf, struct nlattr *tb[], int attrtype, unsigned long mask, bool changelink, bool changelink_supported, struct netlink_ext_ack *extack) { unsigned long flags; if (!tb[attrtype]) return 0; if (changelink && !changelink_supported) { vxlan_flag_attr_error(attrtype, extack); return -EOPNOTSUPP; } if (vxlan_policy[attrtype].type == NLA_FLAG) flags = conf->flags | mask; else if (nla_get_u8(tb[attrtype])) flags = conf->flags | mask; else flags = conf->flags & ~mask; conf->flags = flags; return 0; } static int vxlan_nl2conf(struct nlattr *tb[], struct nlattr *data[], struct net_device *dev, struct vxlan_config *conf, bool changelink, struct netlink_ext_ack *extack) { struct vxlan_dev *vxlan = netdev_priv(dev); int err = 0; memset(conf, 0, sizeof(*conf)); /* if changelink operation, start with old existing cfg */ if (changelink) memcpy(conf, &vxlan->cfg, sizeof(*conf)); if (data[IFLA_VXLAN_ID]) { __be32 vni = cpu_to_be32(nla_get_u32(data[IFLA_VXLAN_ID])); if (changelink && (vni != conf->vni)) { NL_SET_ERR_MSG_ATTR(extack, tb[IFLA_VXLAN_ID], "Cannot change VNI"); return -EOPNOTSUPP; } conf->vni = cpu_to_be32(nla_get_u32(data[IFLA_VXLAN_ID])); } if (data[IFLA_VXLAN_GROUP]) { if (changelink && (conf->remote_ip.sa.sa_family != AF_INET)) { NL_SET_ERR_MSG_ATTR(extack, tb[IFLA_VXLAN_GROUP], "New group address family does not match old group"); return -EOPNOTSUPP; } conf->remote_ip.sin.sin_addr.s_addr = nla_get_in_addr(data[IFLA_VXLAN_GROUP]); conf->remote_ip.sa.sa_family = AF_INET; } else if (data[IFLA_VXLAN_GROUP6]) { if (!IS_ENABLED(CONFIG_IPV6)) { NL_SET_ERR_MSG_ATTR(extack, tb[IFLA_VXLAN_GROUP6], "IPv6 support not enabled in the kernel"); return -EPFNOSUPPORT; } if (changelink && (conf->remote_ip.sa.sa_family != AF_INET6)) { NL_SET_ERR_MSG_ATTR(extack, tb[IFLA_VXLAN_GROUP6], "New group address family does not match old group"); return -EOPNOTSUPP; } conf->remote_ip.sin6.sin6_addr = nla_get_in6_addr(data[IFLA_VXLAN_GROUP6]); conf->remote_ip.sa.sa_family = AF_INET6; } if (data[IFLA_VXLAN_LOCAL]) { if (changelink && (conf->saddr.sa.sa_family != AF_INET)) { NL_SET_ERR_MSG_ATTR(extack, tb[IFLA_VXLAN_LOCAL], "New local address family does not match old"); return -EOPNOTSUPP; } conf->saddr.sin.sin_addr.s_addr = nla_get_in_addr(data[IFLA_VXLAN_LOCAL]); conf->saddr.sa.sa_family = AF_INET; } else if (data[IFLA_VXLAN_LOCAL6]) { if (!IS_ENABLED(CONFIG_IPV6)) { NL_SET_ERR_MSG_ATTR(extack, tb[IFLA_VXLAN_LOCAL6], "IPv6 support not enabled in the kernel"); return -EPFNOSUPPORT; } if (changelink && (conf->saddr.sa.sa_family != AF_INET6)) { NL_SET_ERR_MSG_ATTR(extack, tb[IFLA_VXLAN_LOCAL6], "New local address family does not match old"); return -EOPNOTSUPP; } /* TODO: respect scope id */ conf->saddr.sin6.sin6_addr = nla_get_in6_addr(data[IFLA_VXLAN_LOCAL6]); conf->saddr.sa.sa_family = AF_INET6; } if (data[IFLA_VXLAN_LINK]) conf->remote_ifindex = nla_get_u32(data[IFLA_VXLAN_LINK]); if (data[IFLA_VXLAN_TOS]) conf->tos = nla_get_u8(data[IFLA_VXLAN_TOS]); if (data[IFLA_VXLAN_TTL]) conf->ttl = nla_get_u8(data[IFLA_VXLAN_TTL]); if (data[IFLA_VXLAN_TTL_INHERIT]) { err = vxlan_nl2flag(conf, data, IFLA_VXLAN_TTL_INHERIT, VXLAN_F_TTL_INHERIT, changelink, false, extack); if (err) return err; } if (data[IFLA_VXLAN_LABEL]) conf->label = nla_get_be32(data[IFLA_VXLAN_LABEL]) & IPV6_FLOWLABEL_MASK; if (data[IFLA_VXLAN_LABEL_POLICY]) conf->label_policy = nla_get_u32(data[IFLA_VXLAN_LABEL_POLICY]); if (data[IFLA_VXLAN_LEARNING]) { err = vxlan_nl2flag(conf, data, IFLA_VXLAN_LEARNING, VXLAN_F_LEARN, changelink, true, extack); if (err) return err; } else if (!changelink) { /* default to learn on a new device */ conf->flags |= VXLAN_F_LEARN; } if (data[IFLA_VXLAN_AGEING]) conf->age_interval = nla_get_u32(data[IFLA_VXLAN_AGEING]); if (data[IFLA_VXLAN_PROXY]) { err = vxlan_nl2flag(conf, data, IFLA_VXLAN_PROXY, VXLAN_F_PROXY, changelink, false, extack); if (err) return err; } if (data[IFLA_VXLAN_RSC]) { err = vxlan_nl2flag(conf, data, IFLA_VXLAN_RSC, VXLAN_F_RSC, changelink, false, extack); if (err) return err; } if (data[IFLA_VXLAN_L2MISS]) { err = vxlan_nl2flag(conf, data, IFLA_VXLAN_L2MISS, VXLAN_F_L2MISS, changelink, false, extack); if (err) return err; } if (data[IFLA_VXLAN_L3MISS]) { err = vxlan_nl2flag(conf, data, IFLA_VXLAN_L3MISS, VXLAN_F_L3MISS, changelink, false, extack); if (err) return err; } if (data[IFLA_VXLAN_LIMIT]) { if (changelink) { NL_SET_ERR_MSG_ATTR(extack, tb[IFLA_VXLAN_LIMIT], "Cannot change limit"); return -EOPNOTSUPP; } conf->addrmax = nla_get_u32(data[IFLA_VXLAN_LIMIT]); } if (data[IFLA_VXLAN_COLLECT_METADATA]) { err = vxlan_nl2flag(conf, data, IFLA_VXLAN_COLLECT_METADATA, VXLAN_F_COLLECT_METADATA, changelink, false, extack); if (err) return err; } if (data[IFLA_VXLAN_PORT_RANGE]) { if (!changelink) { const struct ifla_vxlan_port_range *p = nla_data(data[IFLA_VXLAN_PORT_RANGE]); conf->port_min = ntohs(p->low); conf->port_max = ntohs(p->high); } else { NL_SET_ERR_MSG_ATTR(extack, tb[IFLA_VXLAN_PORT_RANGE], "Cannot change port range"); return -EOPNOTSUPP; } } if (data[IFLA_VXLAN_PORT]) { if (changelink) { NL_SET_ERR_MSG_ATTR(extack, tb[IFLA_VXLAN_PORT], "Cannot change port"); return -EOPNOTSUPP; } conf->dst_port = nla_get_be16(data[IFLA_VXLAN_PORT]); } if (data[IFLA_VXLAN_UDP_CSUM]) { if (changelink) { NL_SET_ERR_MSG_ATTR(extack, tb[IFLA_VXLAN_UDP_CSUM], "Cannot change UDP_CSUM flag"); return -EOPNOTSUPP; } if (!nla_get_u8(data[IFLA_VXLAN_UDP_CSUM])) conf->flags |= VXLAN_F_UDP_ZERO_CSUM_TX; } if (data[IFLA_VXLAN_LOCALBYPASS]) { err = vxlan_nl2flag(conf, data, IFLA_VXLAN_LOCALBYPASS, VXLAN_F_LOCALBYPASS, changelink, true, extack); if (err) return err; } else if (!changelink) { /* default to local bypass on a new device */ conf->flags |= VXLAN_F_LOCALBYPASS; } if (data[IFLA_VXLAN_UDP_ZERO_CSUM6_TX]) { err = vxlan_nl2flag(conf, data, IFLA_VXLAN_UDP_ZERO_CSUM6_TX, VXLAN_F_UDP_ZERO_CSUM6_TX, changelink, false, extack); if (err) return err; } if (data[IFLA_VXLAN_UDP_ZERO_CSUM6_RX]) { err = vxlan_nl2flag(conf, data, IFLA_VXLAN_UDP_ZERO_CSUM6_RX, VXLAN_F_UDP_ZERO_CSUM6_RX, changelink, false, extack); if (err) return err; } if (data[IFLA_VXLAN_REMCSUM_TX]) { err = vxlan_nl2flag(conf, data, IFLA_VXLAN_REMCSUM_TX, VXLAN_F_REMCSUM_TX, changelink, false, extack); if (err) return err; } if (data[IFLA_VXLAN_REMCSUM_RX]) { err = vxlan_nl2flag(conf, data, IFLA_VXLAN_REMCSUM_RX, VXLAN_F_REMCSUM_RX, changelink, false, extack); if (err) return err; } if (data[IFLA_VXLAN_GBP]) { err = vxlan_nl2flag(conf, data, IFLA_VXLAN_GBP, VXLAN_F_GBP, changelink, false, extack); if (err) return err; } if (data[IFLA_VXLAN_GPE]) { err = vxlan_nl2flag(conf, data, IFLA_VXLAN_GPE, VXLAN_F_GPE, changelink, false, extack); if (err) return err; } if (data[IFLA_VXLAN_REMCSUM_NOPARTIAL]) { err = vxlan_nl2flag(conf, data, IFLA_VXLAN_REMCSUM_NOPARTIAL, VXLAN_F_REMCSUM_NOPARTIAL, changelink, false, extack); if (err) return err; } if (tb[IFLA_MTU]) { if (changelink) { NL_SET_ERR_MSG_ATTR(extack, tb[IFLA_MTU], "Cannot change mtu"); return -EOPNOTSUPP; } conf->mtu = nla_get_u32(tb[IFLA_MTU]); } if (data[IFLA_VXLAN_DF]) conf->df = nla_get_u8(data[IFLA_VXLAN_DF]); if (data[IFLA_VXLAN_VNIFILTER]) { err = vxlan_nl2flag(conf, data, IFLA_VXLAN_VNIFILTER, VXLAN_F_VNIFILTER, changelink, false, extack); if (err) return err; if ((conf->flags & VXLAN_F_VNIFILTER) && !(conf->flags & VXLAN_F_COLLECT_METADATA)) { NL_SET_ERR_MSG_ATTR(extack, data[IFLA_VXLAN_VNIFILTER], "vxlan vnifilter only valid in collect metadata mode"); return -EINVAL; } } return 0; } static int vxlan_newlink(struct net *src_net, struct net_device *dev, struct nlattr *tb[], struct nlattr *data[], struct netlink_ext_ack *extack) { struct vxlan_config conf; int err; err = vxlan_nl2conf(tb, data, dev, &conf, false, extack); if (err) return err; return __vxlan_dev_create(src_net, dev, &conf, extack); } static int vxlan_changelink(struct net_device *dev, struct nlattr *tb[], struct nlattr *data[], struct netlink_ext_ack *extack) { struct vxlan_dev *vxlan = netdev_priv(dev); struct net_device *lowerdev; struct vxlan_config conf; struct vxlan_rdst *dst; int err; dst = &vxlan->default_dst; err = vxlan_nl2conf(tb, data, dev, &conf, true, extack); if (err) return err; err = vxlan_config_validate(vxlan->net, &conf, &lowerdev, vxlan, extack); if (err) return err; if (dst->remote_dev == lowerdev) lowerdev = NULL; err = netdev_adjacent_change_prepare(dst->remote_dev, lowerdev, dev, extack); if (err) return err; /* handle default dst entry */ if (!vxlan_addr_equal(&conf.remote_ip, &dst->remote_ip)) { u32 hash_index = fdb_head_index(vxlan, all_zeros_mac, conf.vni); spin_lock_bh(&vxlan->hash_lock[hash_index]); if (!vxlan_addr_any(&conf.remote_ip)) { err = vxlan_fdb_update(vxlan, all_zeros_mac, &conf.remote_ip, NUD_REACHABLE | NUD_PERMANENT, NLM_F_APPEND | NLM_F_CREATE, vxlan->cfg.dst_port, conf.vni, conf.vni, conf.remote_ifindex, NTF_SELF, 0, true, extack); if (err) { spin_unlock_bh(&vxlan->hash_lock[hash_index]); netdev_adjacent_change_abort(dst->remote_dev, lowerdev, dev); return err; } } if (!vxlan_addr_any(&dst->remote_ip)) __vxlan_fdb_delete(vxlan, all_zeros_mac, dst->remote_ip, vxlan->cfg.dst_port, dst->remote_vni, dst->remote_vni, dst->remote_ifindex, true); spin_unlock_bh(&vxlan->hash_lock[hash_index]); /* If vni filtering device, also update fdb entries of * all vnis that were using default remote ip */ if (vxlan->cfg.flags & VXLAN_F_VNIFILTER) { err = vxlan_vnilist_update_group(vxlan, &dst->remote_ip, &conf.remote_ip, extack); if (err) { netdev_adjacent_change_abort(dst->remote_dev, lowerdev, dev); return err; } } } if (conf.age_interval != vxlan->cfg.age_interval) mod_timer(&vxlan->age_timer, jiffies); netdev_adjacent_change_commit(dst->remote_dev, lowerdev, dev); if (lowerdev && lowerdev != dst->remote_dev) dst->remote_dev = lowerdev; vxlan_config_apply(dev, &conf, lowerdev, vxlan->net, true); return 0; } static void vxlan_dellink(struct net_device *dev, struct list_head *head) { struct vxlan_dev *vxlan = netdev_priv(dev); struct vxlan_fdb_flush_desc desc = { /* Default entry is deleted at vxlan_uninit. */ .ignore_default_entry = true, }; vxlan_flush(vxlan, &desc); list_del(&vxlan->next); unregister_netdevice_queue(dev, head); if (vxlan->default_dst.remote_dev) netdev_upper_dev_unlink(vxlan->default_dst.remote_dev, dev); } static size_t vxlan_get_size(const struct net_device *dev) { return nla_total_size(sizeof(__u32)) + /* IFLA_VXLAN_ID */ nla_total_size(sizeof(struct in6_addr)) + /* IFLA_VXLAN_GROUP{6} */ nla_total_size(sizeof(__u32)) + /* IFLA_VXLAN_LINK */ nla_total_size(sizeof(struct in6_addr)) + /* IFLA_VXLAN_LOCAL{6} */ nla_total_size(sizeof(__u8)) + /* IFLA_VXLAN_TTL */ nla_total_size(sizeof(__u8)) + /* IFLA_VXLAN_TTL_INHERIT */ nla_total_size(sizeof(__u8)) + /* IFLA_VXLAN_TOS */ nla_total_size(sizeof(__u8)) + /* IFLA_VXLAN_DF */ nla_total_size(sizeof(__be32)) + /* IFLA_VXLAN_LABEL */ nla_total_size(sizeof(__u32)) + /* IFLA_VXLAN_LABEL_POLICY */ nla_total_size(sizeof(__u8)) + /* IFLA_VXLAN_LEARNING */ nla_total_size(sizeof(__u8)) + /* IFLA_VXLAN_PROXY */ nla_total_size(sizeof(__u8)) + /* IFLA_VXLAN_RSC */ nla_total_size(sizeof(__u8)) + /* IFLA_VXLAN_L2MISS */ nla_total_size(sizeof(__u8)) + /* IFLA_VXLAN_L3MISS */ nla_total_size(sizeof(__u8)) + /* IFLA_VXLAN_COLLECT_METADATA */ nla_total_size(sizeof(__u32)) + /* IFLA_VXLAN_AGEING */ nla_total_size(sizeof(__u32)) + /* IFLA_VXLAN_LIMIT */ nla_total_size(sizeof(__be16)) + /* IFLA_VXLAN_PORT */ nla_total_size(sizeof(__u8)) + /* IFLA_VXLAN_UDP_CSUM */ nla_total_size(sizeof(__u8)) + /* IFLA_VXLAN_UDP_ZERO_CSUM6_TX */ nla_total_size(sizeof(__u8)) + /* IFLA_VXLAN_UDP_ZERO_CSUM6_RX */ nla_total_size(sizeof(__u8)) + /* IFLA_VXLAN_REMCSUM_TX */ nla_total_size(sizeof(__u8)) + /* IFLA_VXLAN_REMCSUM_RX */ nla_total_size(sizeof(__u8)) + /* IFLA_VXLAN_LOCALBYPASS */ /* IFLA_VXLAN_PORT_RANGE */ nla_total_size(sizeof(struct ifla_vxlan_port_range)) + nla_total_size(0) + /* IFLA_VXLAN_GBP */ nla_total_size(0) + /* IFLA_VXLAN_GPE */ nla_total_size(0) + /* IFLA_VXLAN_REMCSUM_NOPARTIAL */ nla_total_size(sizeof(__u8)) + /* IFLA_VXLAN_VNIFILTER */ 0; } static int vxlan_fill_info(struct sk_buff *skb, const struct net_device *dev) { const struct vxlan_dev *vxlan = netdev_priv(dev); const struct vxlan_rdst *dst = &vxlan->default_dst; struct ifla_vxlan_port_range ports = { .low = htons(vxlan->cfg.port_min), .high = htons(vxlan->cfg.port_max), }; if (nla_put_u32(skb, IFLA_VXLAN_ID, be32_to_cpu(dst->remote_vni))) goto nla_put_failure; if (!vxlan_addr_any(&dst->remote_ip)) { if (dst->remote_ip.sa.sa_family == AF_INET) { if (nla_put_in_addr(skb, IFLA_VXLAN_GROUP, dst->remote_ip.sin.sin_addr.s_addr)) goto nla_put_failure; #if IS_ENABLED(CONFIG_IPV6) } else { if (nla_put_in6_addr(skb, IFLA_VXLAN_GROUP6, &dst->remote_ip.sin6.sin6_addr)) goto nla_put_failure; #endif } } if (dst->remote_ifindex && nla_put_u32(skb, IFLA_VXLAN_LINK, dst->remote_ifindex)) goto nla_put_failure; if (!vxlan_addr_any(&vxlan->cfg.saddr)) { if (vxlan->cfg.saddr.sa.sa_family == AF_INET) { if (nla_put_in_addr(skb, IFLA_VXLAN_LOCAL, vxlan->cfg.saddr.sin.sin_addr.s_addr)) goto nla_put_failure; #if IS_ENABLED(CONFIG_IPV6) } else { if (nla_put_in6_addr(skb, IFLA_VXLAN_LOCAL6, &vxlan->cfg.saddr.sin6.sin6_addr)) goto nla_put_failure; #endif } } if (nla_put_u8(skb, IFLA_VXLAN_TTL, vxlan->cfg.ttl) || nla_put_u8(skb, IFLA_VXLAN_TTL_INHERIT, !!(vxlan->cfg.flags & VXLAN_F_TTL_INHERIT)) || nla_put_u8(skb, IFLA_VXLAN_TOS, vxlan->cfg.tos) || nla_put_u8(skb, IFLA_VXLAN_DF, vxlan->cfg.df) || nla_put_be32(skb, IFLA_VXLAN_LABEL, vxlan->cfg.label) || nla_put_u32(skb, IFLA_VXLAN_LABEL_POLICY, vxlan->cfg.label_policy) || nla_put_u8(skb, IFLA_VXLAN_LEARNING, !!(vxlan->cfg.flags & VXLAN_F_LEARN)) || nla_put_u8(skb, IFLA_VXLAN_PROXY, !!(vxlan->cfg.flags & VXLAN_F_PROXY)) || nla_put_u8(skb, IFLA_VXLAN_RSC, !!(vxlan->cfg.flags & VXLAN_F_RSC)) || nla_put_u8(skb, IFLA_VXLAN_L2MISS, !!(vxlan->cfg.flags & VXLAN_F_L2MISS)) || nla_put_u8(skb, IFLA_VXLAN_L3MISS, !!(vxlan->cfg.flags & VXLAN_F_L3MISS)) || nla_put_u8(skb, IFLA_VXLAN_COLLECT_METADATA, !!(vxlan->cfg.flags & VXLAN_F_COLLECT_METADATA)) || nla_put_u32(skb, IFLA_VXLAN_AGEING, vxlan->cfg.age_interval) || nla_put_u32(skb, IFLA_VXLAN_LIMIT, vxlan->cfg.addrmax) || nla_put_be16(skb, IFLA_VXLAN_PORT, vxlan->cfg.dst_port) || nla_put_u8(skb, IFLA_VXLAN_UDP_CSUM, !(vxlan->cfg.flags & VXLAN_F_UDP_ZERO_CSUM_TX)) || nla_put_u8(skb, IFLA_VXLAN_UDP_ZERO_CSUM6_TX, !!(vxlan->cfg.flags & VXLAN_F_UDP_ZERO_CSUM6_TX)) || nla_put_u8(skb, IFLA_VXLAN_UDP_ZERO_CSUM6_RX, !!(vxlan->cfg.flags & VXLAN_F_UDP_ZERO_CSUM6_RX)) || nla_put_u8(skb, IFLA_VXLAN_REMCSUM_TX, !!(vxlan->cfg.flags & VXLAN_F_REMCSUM_TX)) || nla_put_u8(skb, IFLA_VXLAN_REMCSUM_RX, !!(vxlan->cfg.flags & VXLAN_F_REMCSUM_RX)) || nla_put_u8(skb, IFLA_VXLAN_LOCALBYPASS, !!(vxlan->cfg.flags & VXLAN_F_LOCALBYPASS))) goto nla_put_failure; if (nla_put(skb, IFLA_VXLAN_PORT_RANGE, sizeof(ports), &ports)) goto nla_put_failure; if (vxlan->cfg.flags & VXLAN_F_GBP && nla_put_flag(skb, IFLA_VXLAN_GBP)) goto nla_put_failure; if (vxlan->cfg.flags & VXLAN_F_GPE && nla_put_flag(skb, IFLA_VXLAN_GPE)) goto nla_put_failure; if (vxlan->cfg.flags & VXLAN_F_REMCSUM_NOPARTIAL && nla_put_flag(skb, IFLA_VXLAN_REMCSUM_NOPARTIAL)) goto nla_put_failure; if (vxlan->cfg.flags & VXLAN_F_VNIFILTER && nla_put_u8(skb, IFLA_VXLAN_VNIFILTER, !!(vxlan->cfg.flags & VXLAN_F_VNIFILTER))) goto nla_put_failure; return 0; nla_put_failure: return -EMSGSIZE; } static struct net *vxlan_get_link_net(const struct net_device *dev) { struct vxlan_dev *vxlan = netdev_priv(dev); return READ_ONCE(vxlan->net); } static struct rtnl_link_ops vxlan_link_ops __read_mostly = { .kind = "vxlan", .maxtype = IFLA_VXLAN_MAX, .policy = vxlan_policy, .priv_size = sizeof(struct vxlan_dev), .setup = vxlan_setup, .validate = vxlan_validate, .newlink = vxlan_newlink, .changelink = vxlan_changelink, .dellink = vxlan_dellink, .get_size = vxlan_get_size, .fill_info = vxlan_fill_info, .get_link_net = vxlan_get_link_net, }; struct net_device *vxlan_dev_create(struct net *net, const char *name, u8 name_assign_type, struct vxlan_config *conf) { struct nlattr *tb[IFLA_MAX + 1]; struct net_device *dev; int err; memset(&tb, 0, sizeof(tb)); dev = rtnl_create_link(net, name, name_assign_type, &vxlan_link_ops, tb, NULL); if (IS_ERR(dev)) return dev; err = __vxlan_dev_create(net, dev, conf, NULL); if (err < 0) { free_netdev(dev); return ERR_PTR(err); } err = rtnl_configure_link(dev, NULL, 0, NULL); if (err < 0) { LIST_HEAD(list_kill); vxlan_dellink(dev, &list_kill); unregister_netdevice_many(&list_kill); return ERR_PTR(err); } return dev; } EXPORT_SYMBOL_GPL(vxlan_dev_create); static void vxlan_handle_lowerdev_unregister(struct vxlan_net *vn, struct net_device *dev) { struct vxlan_dev *vxlan, *next; LIST_HEAD(list_kill); list_for_each_entry_safe(vxlan, next, &vn->vxlan_list, next) { struct vxlan_rdst *dst = &vxlan->default_dst; /* In case we created vxlan device with carrier * and we loose the carrier due to module unload * we also need to remove vxlan device. In other * cases, it's not necessary and remote_ifindex * is 0 here, so no matches. */ if (dst->remote_ifindex == dev->ifindex) vxlan_dellink(vxlan->dev, &list_kill); } unregister_netdevice_many(&list_kill); } static int vxlan_netdevice_event(struct notifier_block *unused, unsigned long event, void *ptr) { struct net_device *dev = netdev_notifier_info_to_dev(ptr); struct vxlan_net *vn = net_generic(dev_net(dev), vxlan_net_id); if (event == NETDEV_UNREGISTER) vxlan_handle_lowerdev_unregister(vn, dev); else if (event == NETDEV_UDP_TUNNEL_PUSH_INFO) vxlan_offload_rx_ports(dev, true); else if (event == NETDEV_UDP_TUNNEL_DROP_INFO) vxlan_offload_rx_ports(dev, false); return NOTIFY_DONE; } static struct notifier_block vxlan_notifier_block __read_mostly = { .notifier_call = vxlan_netdevice_event, }; static void vxlan_fdb_offloaded_set(struct net_device *dev, struct switchdev_notifier_vxlan_fdb_info *fdb_info) { struct vxlan_dev *vxlan = netdev_priv(dev); struct vxlan_rdst *rdst; struct vxlan_fdb *f; u32 hash_index; hash_index = fdb_head_index(vxlan, fdb_info->eth_addr, fdb_info->vni); spin_lock_bh(&vxlan->hash_lock[hash_index]); f = vxlan_find_mac(vxlan, fdb_info->eth_addr, fdb_info->vni); if (!f) goto out; rdst = vxlan_fdb_find_rdst(f, &fdb_info->remote_ip, fdb_info->remote_port, fdb_info->remote_vni, fdb_info->remote_ifindex); if (!rdst) goto out; rdst->offloaded = fdb_info->offloaded; out: spin_unlock_bh(&vxlan->hash_lock[hash_index]); } static int vxlan_fdb_external_learn_add(struct net_device *dev, struct switchdev_notifier_vxlan_fdb_info *fdb_info) { struct vxlan_dev *vxlan = netdev_priv(dev); struct netlink_ext_ack *extack; u32 hash_index; int err; hash_index = fdb_head_index(vxlan, fdb_info->eth_addr, fdb_info->vni); extack = switchdev_notifier_info_to_extack(&fdb_info->info); spin_lock_bh(&vxlan->hash_lock[hash_index]); err = vxlan_fdb_update(vxlan, fdb_info->eth_addr, &fdb_info->remote_ip, NUD_REACHABLE, NLM_F_CREATE | NLM_F_REPLACE, fdb_info->remote_port, fdb_info->vni, fdb_info->remote_vni, fdb_info->remote_ifindex, NTF_USE | NTF_SELF | NTF_EXT_LEARNED, 0, false, extack); spin_unlock_bh(&vxlan->hash_lock[hash_index]); return err; } static int vxlan_fdb_external_learn_del(struct net_device *dev, struct switchdev_notifier_vxlan_fdb_info *fdb_info) { struct vxlan_dev *vxlan = netdev_priv(dev); struct vxlan_fdb *f; u32 hash_index; int err = 0; hash_index = fdb_head_index(vxlan, fdb_info->eth_addr, fdb_info->vni); spin_lock_bh(&vxlan->hash_lock[hash_index]); f = vxlan_find_mac(vxlan, fdb_info->eth_addr, fdb_info->vni); if (!f) err = -ENOENT; else if (f->flags & NTF_EXT_LEARNED) err = __vxlan_fdb_delete(vxlan, fdb_info->eth_addr, fdb_info->remote_ip, fdb_info->remote_port, fdb_info->vni, fdb_info->remote_vni, fdb_info->remote_ifindex, false); spin_unlock_bh(&vxlan->hash_lock[hash_index]); return err; } static int vxlan_switchdev_event(struct notifier_block *unused, unsigned long event, void *ptr) { struct net_device *dev = switchdev_notifier_info_to_dev(ptr); struct switchdev_notifier_vxlan_fdb_info *fdb_info; int err = 0; switch (event) { case SWITCHDEV_VXLAN_FDB_OFFLOADED: vxlan_fdb_offloaded_set(dev, ptr); break; case SWITCHDEV_VXLAN_FDB_ADD_TO_BRIDGE: fdb_info = ptr; err = vxlan_fdb_external_learn_add(dev, fdb_info); if (err) { err = notifier_from_errno(err); break; } fdb_info->offloaded = true; vxlan_fdb_offloaded_set(dev, fdb_info); break; case SWITCHDEV_VXLAN_FDB_DEL_TO_BRIDGE: fdb_info = ptr; err = vxlan_fdb_external_learn_del(dev, fdb_info); if (err) { err = notifier_from_errno(err); break; } fdb_info->offloaded = false; vxlan_fdb_offloaded_set(dev, fdb_info); break; } return err; } static struct notifier_block vxlan_switchdev_notifier_block __read_mostly = { .notifier_call = vxlan_switchdev_event, }; static void vxlan_fdb_nh_flush(struct nexthop *nh) { struct vxlan_fdb *fdb; struct vxlan_dev *vxlan; u32 hash_index; rcu_read_lock(); list_for_each_entry_rcu(fdb, &nh->fdb_list, nh_list) { vxlan = rcu_dereference(fdb->vdev); WARN_ON(!vxlan); hash_index = fdb_head_index(vxlan, fdb->eth_addr, vxlan->default_dst.remote_vni); spin_lock_bh(&vxlan->hash_lock[hash_index]); if (!hlist_unhashed(&fdb->hlist)) vxlan_fdb_destroy(vxlan, fdb, false, false); spin_unlock_bh(&vxlan->hash_lock[hash_index]); } rcu_read_unlock(); } static int vxlan_nexthop_event(struct notifier_block *nb, unsigned long event, void *ptr) { struct nh_notifier_info *info = ptr; struct nexthop *nh; if (event != NEXTHOP_EVENT_DEL) return NOTIFY_DONE; nh = nexthop_find_by_id(info->net, info->id); if (!nh) return NOTIFY_DONE; vxlan_fdb_nh_flush(nh); return NOTIFY_DONE; } static __net_init int vxlan_init_net(struct net *net) { struct vxlan_net *vn = net_generic(net, vxlan_net_id); unsigned int h; INIT_LIST_HEAD(&vn->vxlan_list); spin_lock_init(&vn->sock_lock); vn->nexthop_notifier_block.notifier_call = vxlan_nexthop_event; for (h = 0; h < PORT_HASH_SIZE; ++h) INIT_HLIST_HEAD(&vn->sock_list[h]); return register_nexthop_notifier(net, &vn->nexthop_notifier_block, NULL); } static void __net_exit vxlan_destroy_tunnels(struct vxlan_net *vn, struct list_head *dev_to_kill) { struct vxlan_dev *vxlan, *next; list_for_each_entry_safe(vxlan, next, &vn->vxlan_list, next) vxlan_dellink(vxlan->dev, dev_to_kill); } static void __net_exit vxlan_exit_batch_rtnl(struct list_head *net_list, struct list_head *dev_to_kill) { struct net *net; ASSERT_RTNL(); list_for_each_entry(net, net_list, exit_list) { struct vxlan_net *vn = net_generic(net, vxlan_net_id); __unregister_nexthop_notifier(net, &vn->nexthop_notifier_block); vxlan_destroy_tunnels(vn, dev_to_kill); } } static void __net_exit vxlan_exit_net(struct net *net) { struct vxlan_net *vn = net_generic(net, vxlan_net_id); unsigned int h; for (h = 0; h < PORT_HASH_SIZE; ++h) WARN_ON_ONCE(!hlist_empty(&vn->sock_list[h])); } static struct pernet_operations vxlan_net_ops = { .init = vxlan_init_net, .exit_batch_rtnl = vxlan_exit_batch_rtnl, .exit = vxlan_exit_net, .id = &vxlan_net_id, .size = sizeof(struct vxlan_net), }; static int __init vxlan_init_module(void) { int rc; get_random_bytes(&vxlan_salt, sizeof(vxlan_salt)); rc = register_pernet_subsys(&vxlan_net_ops); if (rc) goto out1; rc = register_netdevice_notifier(&vxlan_notifier_block); if (rc) goto out2; rc = register_switchdev_notifier(&vxlan_switchdev_notifier_block); if (rc) goto out3; rc = rtnl_link_register(&vxlan_link_ops); if (rc) goto out4; rc = vxlan_vnifilter_init(); if (rc) goto out5; return 0; out5: rtnl_link_unregister(&vxlan_link_ops); out4: unregister_switchdev_notifier(&vxlan_switchdev_notifier_block); out3: unregister_netdevice_notifier(&vxlan_notifier_block); out2: unregister_pernet_subsys(&vxlan_net_ops); out1: return rc; } late_initcall(vxlan_init_module); static void __exit vxlan_cleanup_module(void) { vxlan_vnifilter_uninit(); rtnl_link_unregister(&vxlan_link_ops); unregister_switchdev_notifier(&vxlan_switchdev_notifier_block); unregister_netdevice_notifier(&vxlan_notifier_block); unregister_pernet_subsys(&vxlan_net_ops); /* rcu_barrier() is called by netns */ } module_exit(vxlan_cleanup_module); MODULE_LICENSE("GPL"); MODULE_VERSION(VXLAN_VERSION); MODULE_AUTHOR("Stephen Hemminger <stephen@networkplumber.org>"); MODULE_DESCRIPTION("Driver for VXLAN encapsulated traffic"); MODULE_ALIAS_RTNL_LINK("vxlan"); |
| 2 4 39 2 33 4 2 2 3 1 2 32 32 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 | // SPDX-License-Identifier: GPL-2.0-only /* * Copyright (C) 2015, 2016 ARM Ltd. */ #include <linux/kvm.h> #include <linux/kvm_host.h> #include <trace/events/kvm.h> #include <kvm/arm_vgic.h> #include "vgic.h" /* * vgic_irqfd_set_irq: inject the IRQ corresponding to the * irqchip routing entry * * This is the entry point for irqfd IRQ injection */ static int vgic_irqfd_set_irq(struct kvm_kernel_irq_routing_entry *e, struct kvm *kvm, int irq_source_id, int level, bool line_status) { unsigned int spi_id = e->irqchip.pin + VGIC_NR_PRIVATE_IRQS; if (!vgic_valid_spi(kvm, spi_id)) return -EINVAL; return kvm_vgic_inject_irq(kvm, NULL, spi_id, level, NULL); } /** * kvm_set_routing_entry: populate a kvm routing entry * from a user routing entry * * @kvm: the VM this entry is applied to * @e: kvm kernel routing entry handle * @ue: user api routing entry handle * return 0 on success, -EINVAL on errors. */ int kvm_set_routing_entry(struct kvm *kvm, struct kvm_kernel_irq_routing_entry *e, const struct kvm_irq_routing_entry *ue) { int r = -EINVAL; switch (ue->type) { case KVM_IRQ_ROUTING_IRQCHIP: e->set = vgic_irqfd_set_irq; e->irqchip.irqchip = ue->u.irqchip.irqchip; e->irqchip.pin = ue->u.irqchip.pin; if ((e->irqchip.pin >= KVM_IRQCHIP_NUM_PINS) || (e->irqchip.irqchip >= KVM_NR_IRQCHIPS)) goto out; break; case KVM_IRQ_ROUTING_MSI: e->set = kvm_set_msi; e->msi.address_lo = ue->u.msi.address_lo; e->msi.address_hi = ue->u.msi.address_hi; e->msi.data = ue->u.msi.data; e->msi.flags = ue->flags; e->msi.devid = ue->u.msi.devid; break; default: goto out; } r = 0; out: return r; } static void kvm_populate_msi(struct kvm_kernel_irq_routing_entry *e, struct kvm_msi *msi) { msi->address_lo = e->msi.address_lo; msi->address_hi = e->msi.address_hi; msi->data = e->msi.data; msi->flags = e->msi.flags; msi->devid = e->msi.devid; } /* * kvm_set_msi: inject the MSI corresponding to the * MSI routing entry * * This is the entry point for irqfd MSI injection * and userspace MSI injection. */ int kvm_set_msi(struct kvm_kernel_irq_routing_entry *e, struct kvm *kvm, int irq_source_id, int level, bool line_status) { struct kvm_msi msi; if (!vgic_has_its(kvm)) return -ENODEV; if (!level) return -1; kvm_populate_msi(e, &msi); return vgic_its_inject_msi(kvm, &msi); } /* * kvm_arch_set_irq_inatomic: fast-path for irqfd injection */ int kvm_arch_set_irq_inatomic(struct kvm_kernel_irq_routing_entry *e, struct kvm *kvm, int irq_source_id, int level, bool line_status) { if (!level) return -EWOULDBLOCK; switch (e->type) { case KVM_IRQ_ROUTING_MSI: { struct kvm_msi msi; if (!vgic_has_its(kvm)) break; kvm_populate_msi(e, &msi); return vgic_its_inject_cached_translation(kvm, &msi); } case KVM_IRQ_ROUTING_IRQCHIP: /* * Injecting SPIs is always possible in atomic context * as long as the damn vgic is initialized. */ if (unlikely(!vgic_initialized(kvm))) break; return vgic_irqfd_set_irq(e, kvm, irq_source_id, 1, line_status); } return -EWOULDBLOCK; } int kvm_vgic_setup_default_irq_routing(struct kvm *kvm) { struct kvm_irq_routing_entry *entries; struct vgic_dist *dist = &kvm->arch.vgic; u32 nr = dist->nr_spis; int i, ret; entries = kcalloc(nr, sizeof(*entries), GFP_KERNEL_ACCOUNT); if (!entries) return -ENOMEM; for (i = 0; i < nr; i++) { entries[i].gsi = i; entries[i].type = KVM_IRQ_ROUTING_IRQCHIP; entries[i].u.irqchip.irqchip = 0; entries[i].u.irqchip.pin = i; } ret = kvm_set_irq_routing(kvm, entries, nr, 0); kfree(entries); return ret; } |
| 333 332 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _LINUX_MMAN_H #define _LINUX_MMAN_H #include <linux/fs.h> #include <linux/mm.h> #include <linux/percpu_counter.h> #include <linux/atomic.h> #include <uapi/linux/mman.h> /* * Arrange for legacy / undefined architecture specific flags to be * ignored by mmap handling code. */ #ifndef MAP_32BIT #define MAP_32BIT 0 #endif #ifndef MAP_ABOVE4G #define MAP_ABOVE4G 0 #endif #ifndef MAP_HUGE_2MB #define MAP_HUGE_2MB 0 #endif #ifndef MAP_HUGE_1GB #define MAP_HUGE_1GB 0 #endif #ifndef MAP_UNINITIALIZED #define MAP_UNINITIALIZED 0 #endif #ifndef MAP_SYNC #define MAP_SYNC 0 #endif /* * The historical set of flags that all mmap implementations implicitly * support when a ->mmap_validate() op is not provided in file_operations. * * MAP_EXECUTABLE and MAP_DENYWRITE are completely ignored throughout the * kernel. */ #define LEGACY_MAP_MASK (MAP_SHARED \ | MAP_PRIVATE \ | MAP_FIXED \ | MAP_ANONYMOUS \ | MAP_DENYWRITE \ | MAP_EXECUTABLE \ | MAP_UNINITIALIZED \ | MAP_GROWSDOWN \ | MAP_LOCKED \ | MAP_NORESERVE \ | MAP_POPULATE \ | MAP_NONBLOCK \ | MAP_STACK \ | MAP_HUGETLB \ | MAP_32BIT \ | MAP_ABOVE4G \ | MAP_HUGE_2MB \ | MAP_HUGE_1GB) extern int sysctl_overcommit_memory; extern int sysctl_overcommit_ratio; extern unsigned long sysctl_overcommit_kbytes; extern struct percpu_counter vm_committed_as; #ifdef CONFIG_SMP extern s32 vm_committed_as_batch; extern void mm_compute_batch(int overcommit_policy); #else #define vm_committed_as_batch 0 static inline void mm_compute_batch(int overcommit_policy) { } #endif unsigned long vm_memory_committed(void); static inline void vm_acct_memory(long pages) { percpu_counter_add_batch(&vm_committed_as, pages, vm_committed_as_batch); } static inline void vm_unacct_memory(long pages) { vm_acct_memory(-pages); } /* * Allow architectures to handle additional protection and flag bits. The * overriding macros must be defined in the arch-specific asm/mman.h file. */ #ifndef arch_calc_vm_prot_bits #define arch_calc_vm_prot_bits(prot, pkey) 0 #endif #ifndef arch_calc_vm_flag_bits #define arch_calc_vm_flag_bits(file, flags) 0 #endif #ifndef arch_validate_prot /* * This is called from mprotect(). PROT_GROWSDOWN and PROT_GROWSUP have * already been masked out. * * Returns true if the prot flags are valid */ static inline bool arch_validate_prot(unsigned long prot, unsigned long addr) { return (prot & ~(PROT_READ | PROT_WRITE | PROT_EXEC | PROT_SEM)) == 0; } #define arch_validate_prot arch_validate_prot #endif #ifndef arch_validate_flags /* * This is called from mmap() and mprotect() with the updated vma->vm_flags. * * Returns true if the VM_* flags are valid. */ static inline bool arch_validate_flags(unsigned long flags) { return true; } #define arch_validate_flags arch_validate_flags #endif /* * Optimisation macro. It is equivalent to: * (x & bit1) ? bit2 : 0 * but this version is faster. * ("bit1" and "bit2" must be single bits) */ #define _calc_vm_trans(x, bit1, bit2) \ ((!(bit1) || !(bit2)) ? 0 : \ ((bit1) <= (bit2) ? ((x) & (bit1)) * ((bit2) / (bit1)) \ : ((x) & (bit1)) / ((bit1) / (bit2)))) /* * Combine the mmap "prot" argument into "vm_flags" used internally. */ static inline unsigned long calc_vm_prot_bits(unsigned long prot, unsigned long pkey) { return _calc_vm_trans(prot, PROT_READ, VM_READ ) | _calc_vm_trans(prot, PROT_WRITE, VM_WRITE) | _calc_vm_trans(prot, PROT_EXEC, VM_EXEC) | arch_calc_vm_prot_bits(prot, pkey); } /* * Combine the mmap "flags" argument into "vm_flags" used internally. */ static inline unsigned long calc_vm_flag_bits(struct file *file, unsigned long flags) { return _calc_vm_trans(flags, MAP_GROWSDOWN, VM_GROWSDOWN ) | _calc_vm_trans(flags, MAP_LOCKED, VM_LOCKED ) | _calc_vm_trans(flags, MAP_SYNC, VM_SYNC ) | _calc_vm_trans(flags, MAP_STACK, VM_NOHUGEPAGE) | arch_calc_vm_flag_bits(file, flags); } unsigned long vm_commit_limit(void); #ifndef arch_memory_deny_write_exec_supported static inline bool arch_memory_deny_write_exec_supported(void) { return true; } #define arch_memory_deny_write_exec_supported arch_memory_deny_write_exec_supported #endif /* * Denies creating a writable executable mapping or gaining executable permissions. * * This denies the following: * * a) mmap(PROT_WRITE | PROT_EXEC) * * b) mmap(PROT_WRITE) * mprotect(PROT_EXEC) * * c) mmap(PROT_WRITE) * mprotect(PROT_READ) * mprotect(PROT_EXEC) * * But allows the following: * * d) mmap(PROT_READ | PROT_EXEC) * mmap(PROT_READ | PROT_EXEC | PROT_BTI) * * This is only applicable if the user has set the Memory-Deny-Write-Execute * (MDWE) protection mask for the current process. * * @old specifies the VMA flags the VMA originally possessed, and @new the ones * we propose to set. * * Return: false if proposed change is OK, true if not ok and should be denied. */ static inline bool map_deny_write_exec(unsigned long old, unsigned long new) { /* If MDWE is disabled, we have nothing to deny. */ if (!test_bit(MMF_HAS_MDWE, ¤t->mm->flags)) return false; /* If the new VMA is not executable, we have nothing to deny. */ if (!(new & VM_EXEC)) return false; /* Under MDWE we do not accept newly writably executable VMAs... */ if (new & VM_WRITE) return true; /* ...nor previously non-executable VMAs becoming executable. */ if (!(old & VM_EXEC)) return true; return false; } #endif /* _LINUX_MMAN_H */ |
| 88 88 88 88 87 88 88 88 88 88 93 93 93 92 93 93 93 91 93 93 78 79 79 79 79 79 79 78 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 | // SPDX-License-Identifier: GPL-2.0-only /* * Copyright (C) 2012-2015 - ARM Ltd * Author: Marc Zyngier <marc.zyngier@arm.com> */ #include <hyp/sysreg-sr.h> #include <linux/compiler.h> #include <linux/kvm_host.h> #include <asm/kprobes.h> #include <asm/kvm_asm.h> #include <asm/kvm_emulate.h> #include <asm/kvm_hyp.h> #include <asm/kvm_nested.h> static void __sysreg_save_vel2_state(struct kvm_vcpu *vcpu) { /* These registers are common with EL1 */ __vcpu_sys_reg(vcpu, PAR_EL1) = read_sysreg(par_el1); __vcpu_sys_reg(vcpu, TPIDR_EL1) = read_sysreg(tpidr_el1); __vcpu_sys_reg(vcpu, ESR_EL2) = read_sysreg_el1(SYS_ESR); __vcpu_sys_reg(vcpu, AFSR0_EL2) = read_sysreg_el1(SYS_AFSR0); __vcpu_sys_reg(vcpu, AFSR1_EL2) = read_sysreg_el1(SYS_AFSR1); __vcpu_sys_reg(vcpu, FAR_EL2) = read_sysreg_el1(SYS_FAR); __vcpu_sys_reg(vcpu, MAIR_EL2) = read_sysreg_el1(SYS_MAIR); __vcpu_sys_reg(vcpu, VBAR_EL2) = read_sysreg_el1(SYS_VBAR); __vcpu_sys_reg(vcpu, CONTEXTIDR_EL2) = read_sysreg_el1(SYS_CONTEXTIDR); __vcpu_sys_reg(vcpu, AMAIR_EL2) = read_sysreg_el1(SYS_AMAIR); /* * In VHE mode those registers are compatible between EL1 and EL2, * and the guest uses the _EL1 versions on the CPU naturally. * So we save them into their _EL2 versions here. * For nVHE mode we trap accesses to those registers, so our * _EL2 copy in sys_regs[] is always up-to-date and we don't need * to save anything here. */ if (vcpu_el2_e2h_is_set(vcpu)) { u64 val; /* * We don't save CPTR_EL2, as accesses to CPACR_EL1 * are always trapped, ensuring that the in-memory * copy is always up-to-date. A small blessing... */ __vcpu_sys_reg(vcpu, SCTLR_EL2) = read_sysreg_el1(SYS_SCTLR); __vcpu_sys_reg(vcpu, TTBR0_EL2) = read_sysreg_el1(SYS_TTBR0); __vcpu_sys_reg(vcpu, TTBR1_EL2) = read_sysreg_el1(SYS_TTBR1); __vcpu_sys_reg(vcpu, TCR_EL2) = read_sysreg_el1(SYS_TCR); if (ctxt_has_tcrx(&vcpu->arch.ctxt)) { __vcpu_sys_reg(vcpu, TCR2_EL2) = read_sysreg_el1(SYS_TCR2); if (ctxt_has_s1pie(&vcpu->arch.ctxt)) { __vcpu_sys_reg(vcpu, PIRE0_EL2) = read_sysreg_el1(SYS_PIRE0); __vcpu_sys_reg(vcpu, PIR_EL2) = read_sysreg_el1(SYS_PIR); } if (ctxt_has_s1poe(&vcpu->arch.ctxt)) __vcpu_sys_reg(vcpu, POR_EL2) = read_sysreg_el1(SYS_POR); } /* * The EL1 view of CNTKCTL_EL1 has a bunch of RES0 bits where * the interesting CNTHCTL_EL2 bits live. So preserve these * bits when reading back the guest-visible value. */ val = read_sysreg_el1(SYS_CNTKCTL); val &= CNTKCTL_VALID_BITS; __vcpu_sys_reg(vcpu, CNTHCTL_EL2) &= ~CNTKCTL_VALID_BITS; __vcpu_sys_reg(vcpu, CNTHCTL_EL2) |= val; } __vcpu_sys_reg(vcpu, SP_EL2) = read_sysreg(sp_el1); __vcpu_sys_reg(vcpu, ELR_EL2) = read_sysreg_el1(SYS_ELR); __vcpu_sys_reg(vcpu, SPSR_EL2) = read_sysreg_el1(SYS_SPSR); } static void __sysreg_restore_vel2_state(struct kvm_vcpu *vcpu) { u64 val; /* These registers are common with EL1 */ write_sysreg(__vcpu_sys_reg(vcpu, PAR_EL1), par_el1); write_sysreg(__vcpu_sys_reg(vcpu, TPIDR_EL1), tpidr_el1); write_sysreg(__vcpu_sys_reg(vcpu, MPIDR_EL1), vmpidr_el2); write_sysreg_el1(__vcpu_sys_reg(vcpu, MAIR_EL2), SYS_MAIR); write_sysreg_el1(__vcpu_sys_reg(vcpu, VBAR_EL2), SYS_VBAR); write_sysreg_el1(__vcpu_sys_reg(vcpu, CONTEXTIDR_EL2), SYS_CONTEXTIDR); write_sysreg_el1(__vcpu_sys_reg(vcpu, AMAIR_EL2), SYS_AMAIR); if (vcpu_el2_e2h_is_set(vcpu)) { /* * In VHE mode those registers are compatible between * EL1 and EL2. */ write_sysreg_el1(__vcpu_sys_reg(vcpu, SCTLR_EL2), SYS_SCTLR); write_sysreg_el1(__vcpu_sys_reg(vcpu, CPTR_EL2), SYS_CPACR); write_sysreg_el1(__vcpu_sys_reg(vcpu, TTBR0_EL2), SYS_TTBR0); write_sysreg_el1(__vcpu_sys_reg(vcpu, TTBR1_EL2), SYS_TTBR1); write_sysreg_el1(__vcpu_sys_reg(vcpu, TCR_EL2), SYS_TCR); write_sysreg_el1(__vcpu_sys_reg(vcpu, CNTHCTL_EL2), SYS_CNTKCTL); } else { /* * CNTHCTL_EL2 only affects EL1 when running nVHE, so * no need to restore it. */ val = translate_sctlr_el2_to_sctlr_el1(__vcpu_sys_reg(vcpu, SCTLR_EL2)); write_sysreg_el1(val, SYS_SCTLR); val = translate_cptr_el2_to_cpacr_el1(__vcpu_sys_reg(vcpu, CPTR_EL2)); write_sysreg_el1(val, SYS_CPACR); val = translate_ttbr0_el2_to_ttbr0_el1(__vcpu_sys_reg(vcpu, TTBR0_EL2)); write_sysreg_el1(val, SYS_TTBR0); val = translate_tcr_el2_to_tcr_el1(__vcpu_sys_reg(vcpu, TCR_EL2)); write_sysreg_el1(val, SYS_TCR); } if (ctxt_has_tcrx(&vcpu->arch.ctxt)) { write_sysreg_el1(__vcpu_sys_reg(vcpu, TCR2_EL2), SYS_TCR2); if (ctxt_has_s1pie(&vcpu->arch.ctxt)) { write_sysreg_el1(__vcpu_sys_reg(vcpu, PIR_EL2), SYS_PIR); write_sysreg_el1(__vcpu_sys_reg(vcpu, PIRE0_EL2), SYS_PIRE0); } if (ctxt_has_s1poe(&vcpu->arch.ctxt)) write_sysreg_el1(__vcpu_sys_reg(vcpu, POR_EL2), SYS_POR); } write_sysreg_el1(__vcpu_sys_reg(vcpu, ESR_EL2), SYS_ESR); write_sysreg_el1(__vcpu_sys_reg(vcpu, AFSR0_EL2), SYS_AFSR0); write_sysreg_el1(__vcpu_sys_reg(vcpu, AFSR1_EL2), SYS_AFSR1); write_sysreg_el1(__vcpu_sys_reg(vcpu, FAR_EL2), SYS_FAR); write_sysreg(__vcpu_sys_reg(vcpu, SP_EL2), sp_el1); write_sysreg_el1(__vcpu_sys_reg(vcpu, ELR_EL2), SYS_ELR); write_sysreg_el1(__vcpu_sys_reg(vcpu, SPSR_EL2), SYS_SPSR); } /* * VHE: Host and guest must save mdscr_el1 and sp_el0 (and the PC and * pstate, which are handled as part of the el2 return state) on every * switch (sp_el0 is being dealt with in the assembly code). * tpidr_el0 and tpidrro_el0 only need to be switched when going * to host userspace or a different VCPU. EL1 registers only need to be * switched when potentially going to run a different VCPU. The latter two * classes are handled as part of kvm_arch_vcpu_load and kvm_arch_vcpu_put. */ void sysreg_save_host_state_vhe(struct kvm_cpu_context *ctxt) { __sysreg_save_common_state(ctxt); } NOKPROBE_SYMBOL(sysreg_save_host_state_vhe); void sysreg_save_guest_state_vhe(struct kvm_cpu_context *ctxt) { __sysreg_save_common_state(ctxt); __sysreg_save_el2_return_state(ctxt); } NOKPROBE_SYMBOL(sysreg_save_guest_state_vhe); void sysreg_restore_host_state_vhe(struct kvm_cpu_context *ctxt) { __sysreg_restore_common_state(ctxt); } NOKPROBE_SYMBOL(sysreg_restore_host_state_vhe); void sysreg_restore_guest_state_vhe(struct kvm_cpu_context *ctxt) { __sysreg_restore_common_state(ctxt); __sysreg_restore_el2_return_state(ctxt); } NOKPROBE_SYMBOL(sysreg_restore_guest_state_vhe); /** * __vcpu_load_switch_sysregs - Load guest system registers to the physical CPU * * @vcpu: The VCPU pointer * * Load system registers that do not affect the host's execution, for * example EL1 system registers on a VHE system where the host kernel * runs at EL2. This function is called from KVM's vcpu_load() function * and loading system register state early avoids having to load them on * every entry to the VM. */ void __vcpu_load_switch_sysregs(struct kvm_vcpu *vcpu) { struct kvm_cpu_context *guest_ctxt = &vcpu->arch.ctxt; struct kvm_cpu_context *host_ctxt; u64 mpidr; host_ctxt = host_data_ptr(host_ctxt); __sysreg_save_user_state(host_ctxt); /* * When running a normal EL1 guest, we only load a new vcpu * after a context switch, which imvolves a DSB, so all * speculative EL1&0 walks will have already completed. * If running NV, the vcpu may transition between vEL1 and * vEL2 without a context switch, so make sure we complete * those walks before loading a new context. */ if (vcpu_has_nv(vcpu)) dsb(nsh); /* * Load guest EL1 and user state * * We must restore the 32-bit state before the sysregs, thanks * to erratum #852523 (Cortex-A57) or #853709 (Cortex-A72). */ __sysreg32_restore_state(vcpu); __sysreg_restore_user_state(guest_ctxt); if (unlikely(__is_hyp_ctxt(guest_ctxt))) { __sysreg_restore_vel2_state(vcpu); } else { if (vcpu_has_nv(vcpu)) { /* * Use the guest hypervisor's VPIDR_EL2 when in a * nested state. The hardware value of MIDR_EL1 gets * restored on put. */ write_sysreg(ctxt_sys_reg(guest_ctxt, VPIDR_EL2), vpidr_el2); /* * As we're restoring a nested guest, set the value * provided by the guest hypervisor. */ mpidr = ctxt_sys_reg(guest_ctxt, VMPIDR_EL2); } else { mpidr = ctxt_sys_reg(guest_ctxt, MPIDR_EL1); } __sysreg_restore_el1_state(guest_ctxt, mpidr); } vcpu_set_flag(vcpu, SYSREGS_ON_CPU); } /** * __vcpu_put_switch_sysregs - Restore host system registers to the physical CPU * * @vcpu: The VCPU pointer * * Save guest system registers that do not affect the host's execution, for * example EL1 system registers on a VHE system where the host kernel * runs at EL2. This function is called from KVM's vcpu_put() function * and deferring saving system register state until we're no longer running the * VCPU avoids having to save them on every exit from the VM. */ void __vcpu_put_switch_sysregs(struct kvm_vcpu *vcpu) { struct kvm_cpu_context *guest_ctxt = &vcpu->arch.ctxt; struct kvm_cpu_context *host_ctxt; host_ctxt = host_data_ptr(host_ctxt); if (unlikely(__is_hyp_ctxt(guest_ctxt))) __sysreg_save_vel2_state(vcpu); else __sysreg_save_el1_state(guest_ctxt); __sysreg_save_user_state(guest_ctxt); __sysreg32_save_state(vcpu); /* Restore host user state */ __sysreg_restore_user_state(host_ctxt); /* If leaving a nesting guest, restore MIDR_EL1 default view */ if (vcpu_has_nv(vcpu)) write_sysreg(read_cpuid_id(), vpidr_el2); vcpu_clear_flag(vcpu, SYSREGS_ON_CPU); } |
| 7 5 7 7 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 | // SPDX-License-Identifier: GPL-2.0-or-later #include <linux/syscalls.h> #include <linux/time_namespace.h> #include "futex.h" /* * Support for robust futexes: the kernel cleans up held futexes at * thread exit time. * * Implementation: user-space maintains a per-thread list of locks it * is holding. Upon do_exit(), the kernel carefully walks this list, * and marks all locks that are owned by this thread with the * FUTEX_OWNER_DIED bit, and wakes up a waiter (if any). The list is * always manipulated with the lock held, so the list is private and * per-thread. Userspace also maintains a per-thread 'list_op_pending' * field, to allow the kernel to clean up if the thread dies after * acquiring the lock, but just before it could have added itself to * the list. There can only be one such pending lock. */ /** * sys_set_robust_list() - Set the robust-futex list head of a task * @head: pointer to the list-head * @len: length of the list-head, as userspace expects */ SYSCALL_DEFINE2(set_robust_list, struct robust_list_head __user *, head, size_t, len) { /* * The kernel knows only one size for now: */ if (unlikely(len != sizeof(*head))) return -EINVAL; current->robust_list = head; return 0; } /** * sys_get_robust_list() - Get the robust-futex list head of a task * @pid: pid of the process [zero for current task] * @head_ptr: pointer to a list-head pointer, the kernel fills it in * @len_ptr: pointer to a length field, the kernel fills in the header size */ SYSCALL_DEFINE3(get_robust_list, int, pid, struct robust_list_head __user * __user *, head_ptr, size_t __user *, len_ptr) { struct robust_list_head __user *head; unsigned long ret; struct task_struct *p; rcu_read_lock(); ret = -ESRCH; if (!pid) p = current; else { p = find_task_by_vpid(pid); if (!p) goto err_unlock; } ret = -EPERM; if (!ptrace_may_access(p, PTRACE_MODE_READ_REALCREDS)) goto err_unlock; head = p->robust_list; rcu_read_unlock(); if (put_user(sizeof(*head), len_ptr)) return -EFAULT; return put_user(head, head_ptr); err_unlock: rcu_read_unlock(); return ret; } long do_futex(u32 __user *uaddr, int op, u32 val, ktime_t *timeout, u32 __user *uaddr2, u32 val2, u32 val3) { unsigned int flags = futex_to_flags(op); int cmd = op & FUTEX_CMD_MASK; if (flags & FLAGS_CLOCKRT) { if (cmd != FUTEX_WAIT_BITSET && cmd != FUTEX_WAIT_REQUEUE_PI && cmd != FUTEX_LOCK_PI2) return -ENOSYS; } switch (cmd) { case FUTEX_WAIT: val3 = FUTEX_BITSET_MATCH_ANY; fallthrough; case FUTEX_WAIT_BITSET: return futex_wait(uaddr, flags, val, timeout, val3); case FUTEX_WAKE: val3 = FUTEX_BITSET_MATCH_ANY; fallthrough; case FUTEX_WAKE_BITSET: return futex_wake(uaddr, flags, val, val3); case FUTEX_REQUEUE: return futex_requeue(uaddr, flags, uaddr2, flags, val, val2, NULL, 0); case FUTEX_CMP_REQUEUE: return futex_requeue(uaddr, flags, uaddr2, flags, val, val2, &val3, 0); case FUTEX_WAKE_OP: return futex_wake_op(uaddr, flags, uaddr2, val, val2, val3); case FUTEX_LOCK_PI: flags |= FLAGS_CLOCKRT; fallthrough; case FUTEX_LOCK_PI2: return futex_lock_pi(uaddr, flags, timeout, 0); case FUTEX_UNLOCK_PI: return futex_unlock_pi(uaddr, flags); case FUTEX_TRYLOCK_PI: return futex_lock_pi(uaddr, flags, NULL, 1); case FUTEX_WAIT_REQUEUE_PI: val3 = FUTEX_BITSET_MATCH_ANY; return futex_wait_requeue_pi(uaddr, flags, val, timeout, val3, uaddr2); case FUTEX_CMP_REQUEUE_PI: return futex_requeue(uaddr, flags, uaddr2, flags, val, val2, &val3, 1); } return -ENOSYS; } static __always_inline bool futex_cmd_has_timeout(u32 cmd) { switch (cmd) { case FUTEX_WAIT: case FUTEX_LOCK_PI: case FUTEX_LOCK_PI2: case FUTEX_WAIT_BITSET: case FUTEX_WAIT_REQUEUE_PI: return true; } return false; } static __always_inline int futex_init_timeout(u32 cmd, u32 op, struct timespec64 *ts, ktime_t *t) { if (!timespec64_valid(ts)) return -EINVAL; *t = timespec64_to_ktime(*ts); if (cmd == FUTEX_WAIT) *t = ktime_add_safe(ktime_get(), *t); else if (cmd != FUTEX_LOCK_PI && !(op & FUTEX_CLOCK_REALTIME)) *t = timens_ktime_to_host(CLOCK_MONOTONIC, *t); return 0; } SYSCALL_DEFINE6(futex, u32 __user *, uaddr, int, op, u32, val, const struct __kernel_timespec __user *, utime, u32 __user *, uaddr2, u32, val3) { int ret, cmd = op & FUTEX_CMD_MASK; ktime_t t, *tp = NULL; struct timespec64 ts; if (utime && futex_cmd_has_timeout(cmd)) { if (unlikely(should_fail_futex(!(op & FUTEX_PRIVATE_FLAG)))) return -EFAULT; if (get_timespec64(&ts, utime)) return -EFAULT; ret = futex_init_timeout(cmd, op, &ts, &t); if (ret) return ret; tp = &t; } return do_futex(uaddr, op, val, tp, uaddr2, (unsigned long)utime, val3); } /** * futex_parse_waitv - Parse a waitv array from userspace * @futexv: Kernel side list of waiters to be filled * @uwaitv: Userspace list to be parsed * @nr_futexes: Length of futexv * @wake: Wake to call when futex is woken * @wake_data: Data for the wake handler * * Return: Error code on failure, 0 on success */ int futex_parse_waitv(struct futex_vector *futexv, struct futex_waitv __user *uwaitv, unsigned int nr_futexes, futex_wake_fn *wake, void *wake_data) { struct futex_waitv aux; unsigned int i; for (i = 0; i < nr_futexes; i++) { unsigned int flags; if (copy_from_user(&aux, &uwaitv[i], sizeof(aux))) return -EFAULT; if ((aux.flags & ~FUTEX2_VALID_MASK) || aux.__reserved) return -EINVAL; flags = futex2_to_flags(aux.flags); if (!futex_flags_valid(flags)) return -EINVAL; if (!futex_validate_input(flags, aux.val)) return -EINVAL; futexv[i].w.flags = flags; futexv[i].w.val = aux.val; futexv[i].w.uaddr = aux.uaddr; futexv[i].q = futex_q_init; futexv[i].q.wake = wake; futexv[i].q.wake_data = wake_data; } return 0; } static int futex2_setup_timeout(struct __kernel_timespec __user *timeout, clockid_t clockid, struct hrtimer_sleeper *to) { int flag_clkid = 0, flag_init = 0; struct timespec64 ts; ktime_t time; int ret; if (!timeout) return 0; if (clockid == CLOCK_REALTIME) { flag_clkid = FLAGS_CLOCKRT; flag_init = FUTEX_CLOCK_REALTIME; } if (clockid != CLOCK_REALTIME && clockid != CLOCK_MONOTONIC) return -EINVAL; if (get_timespec64(&ts, timeout)) return -EFAULT; /* * Since there's no opcode for futex_waitv, use * FUTEX_WAIT_BITSET that uses absolute timeout as well */ ret = futex_init_timeout(FUTEX_WAIT_BITSET, flag_init, &ts, &time); if (ret) return ret; futex_setup_timer(&time, to, flag_clkid, 0); return 0; } static inline void futex2_destroy_timeout(struct hrtimer_sleeper *to) { hrtimer_cancel(&to->timer); destroy_hrtimer_on_stack(&to->timer); } /** * sys_futex_waitv - Wait on a list of futexes * @waiters: List of futexes to wait on * @nr_futexes: Length of futexv * @flags: Flag for timeout (monotonic/realtime) * @timeout: Optional absolute timeout. * @clockid: Clock to be used for the timeout, realtime or monotonic. * * Given an array of `struct futex_waitv`, wait on each uaddr. The thread wakes * if a futex_wake() is performed at any uaddr. The syscall returns immediately * if any waiter has *uaddr != val. *timeout is an optional timeout value for * the operation. Each waiter has individual flags. The `flags` argument for * the syscall should be used solely for specifying the timeout as realtime, if * needed. Flags for private futexes, sizes, etc. should be used on the * individual flags of each waiter. * * Returns the array index of one of the woken futexes. No further information * is provided: any number of other futexes may also have been woken by the * same event, and if more than one futex was woken, the retrned index may * refer to any one of them. (It is not necessaryily the futex with the * smallest index, nor the one most recently woken, nor...) */ SYSCALL_DEFINE5(futex_waitv, struct futex_waitv __user *, waiters, unsigned int, nr_futexes, unsigned int, flags, struct __kernel_timespec __user *, timeout, clockid_t, clockid) { struct hrtimer_sleeper to; struct futex_vector *futexv; int ret; /* This syscall supports no flags for now */ if (flags) return -EINVAL; if (!nr_futexes || nr_futexes > FUTEX_WAITV_MAX || !waiters) return -EINVAL; if (timeout && (ret = futex2_setup_timeout(timeout, clockid, &to))) return ret; futexv = kcalloc(nr_futexes, sizeof(*futexv), GFP_KERNEL); if (!futexv) { ret = -ENOMEM; goto destroy_timer; } ret = futex_parse_waitv(futexv, waiters, nr_futexes, futex_wake_mark, NULL); if (!ret) ret = futex_wait_multiple(futexv, nr_futexes, timeout ? &to : NULL); kfree(futexv); destroy_timer: if (timeout) futex2_destroy_timeout(&to); return ret; } /* * sys_futex_wake - Wake a number of futexes * @uaddr: Address of the futex(es) to wake * @mask: bitmask * @nr: Number of the futexes to wake * @flags: FUTEX2 flags * * Identical to the traditional FUTEX_WAKE_BITSET op, except it is part of the * futex2 family of calls. */ SYSCALL_DEFINE4(futex_wake, void __user *, uaddr, unsigned long, mask, int, nr, unsigned int, flags) { if (flags & ~FUTEX2_VALID_MASK) return -EINVAL; flags = futex2_to_flags(flags); if (!futex_flags_valid(flags)) return -EINVAL; if (!futex_validate_input(flags, mask)) return -EINVAL; return futex_wake(uaddr, FLAGS_STRICT | flags, nr, mask); } /* * sys_futex_wait - Wait on a futex * @uaddr: Address of the futex to wait on * @val: Value of @uaddr * @mask: bitmask * @flags: FUTEX2 flags * @timeout: Optional absolute timeout * @clockid: Clock to be used for the timeout, realtime or monotonic * * Identical to the traditional FUTEX_WAIT_BITSET op, except it is part of the * futex2 familiy of calls. */ SYSCALL_DEFINE6(futex_wait, void __user *, uaddr, unsigned long, val, unsigned long, mask, unsigned int, flags, struct __kernel_timespec __user *, timeout, clockid_t, clockid) { struct hrtimer_sleeper to; int ret; if (flags & ~FUTEX2_VALID_MASK) return -EINVAL; flags = futex2_to_flags(flags); if (!futex_flags_valid(flags)) return -EINVAL; if (!futex_validate_input(flags, val) || !futex_validate_input(flags, mask)) return -EINVAL; if (timeout && (ret = futex2_setup_timeout(timeout, clockid, &to))) return ret; ret = __futex_wait(uaddr, flags, val, timeout ? &to : NULL, mask); if (timeout) futex2_destroy_timeout(&to); return ret; } /* * sys_futex_requeue - Requeue a waiter from one futex to another * @waiters: array describing the source and destination futex * @flags: unused * @nr_wake: number of futexes to wake * @nr_requeue: number of futexes to requeue * * Identical to the traditional FUTEX_CMP_REQUEUE op, except it is part of the * futex2 family of calls. */ SYSCALL_DEFINE4(futex_requeue, struct futex_waitv __user *, waiters, unsigned int, flags, int, nr_wake, int, nr_requeue) { struct futex_vector futexes[2]; u32 cmpval; int ret; if (flags) return -EINVAL; if (!waiters) return -EINVAL; ret = futex_parse_waitv(futexes, waiters, 2, futex_wake_mark, NULL); if (ret) return ret; cmpval = futexes[0].w.val; return futex_requeue(u64_to_user_ptr(futexes[0].w.uaddr), futexes[0].w.flags, u64_to_user_ptr(futexes[1].w.uaddr), futexes[1].w.flags, nr_wake, nr_requeue, &cmpval, 0); } #ifdef CONFIG_COMPAT COMPAT_SYSCALL_DEFINE2(set_robust_list, struct compat_robust_list_head __user *, head, compat_size_t, len) { if (unlikely(len != sizeof(*head))) return -EINVAL; current->compat_robust_list = head; return 0; } COMPAT_SYSCALL_DEFINE3(get_robust_list, int, pid, compat_uptr_t __user *, head_ptr, compat_size_t __user *, len_ptr) { struct compat_robust_list_head __user *head; unsigned long ret; struct task_struct *p; rcu_read_lock(); ret = -ESRCH; if (!pid) p = current; else { p = find_task_by_vpid(pid); if (!p) goto err_unlock; } ret = -EPERM; if (!ptrace_may_access(p, PTRACE_MODE_READ_REALCREDS)) goto err_unlock; head = p->compat_robust_list; rcu_read_unlock(); if (put_user(sizeof(*head), len_ptr)) return -EFAULT; return put_user(ptr_to_compat(head), head_ptr); err_unlock: rcu_read_unlock(); return ret; } #endif /* CONFIG_COMPAT */ #ifdef CONFIG_COMPAT_32BIT_TIME SYSCALL_DEFINE6(futex_time32, u32 __user *, uaddr, int, op, u32, val, const struct old_timespec32 __user *, utime, u32 __user *, uaddr2, u32, val3) { int ret, cmd = op & FUTEX_CMD_MASK; ktime_t t, *tp = NULL; struct timespec64 ts; if (utime && futex_cmd_has_timeout(cmd)) { if (get_old_timespec32(&ts, utime)) return -EFAULT; ret = futex_init_timeout(cmd, op, &ts, &t); if (ret) return ret; tp = &t; } return do_futex(uaddr, op, val, tp, uaddr2, (unsigned long)utime, val3); } #endif /* CONFIG_COMPAT_32BIT_TIME */ |
| 161 163 163 163 610 616 615 615 617 615 498 39 475 499 2 492 8 498 2 498 498 498 149 149 148 146 2 118 33 145 4 149 148 148 116 1118 1127 16 116 37 37 37 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 | // SPDX-License-Identifier: GPL-2.0-only /* * linux/fs/file_table.c * * Copyright (C) 1991, 1992 Linus Torvalds * Copyright (C) 1997 David S. Miller (davem@caip.rutgers.edu) */ #include <linux/string.h> #include <linux/slab.h> #include <linux/file.h> #include <linux/init.h> #include <linux/module.h> #include <linux/fs.h> #include <linux/filelock.h> #include <linux/security.h> #include <linux/cred.h> #include <linux/eventpoll.h> #include <linux/rcupdate.h> #include <linux/mount.h> #include <linux/capability.h> #include <linux/cdev.h> #include <linux/fsnotify.h> #include <linux/sysctl.h> #include <linux/percpu_counter.h> #include <linux/percpu.h> #include <linux/task_work.h> #include <linux/swap.h> #include <linux/kmemleak.h> #include <linux/atomic.h> #include "internal.h" /* sysctl tunables... */ static struct files_stat_struct files_stat = { .max_files = NR_FILE }; /* SLAB cache for file structures */ static struct kmem_cache *filp_cachep __ro_after_init; static struct kmem_cache *bfilp_cachep __ro_after_init; static struct percpu_counter nr_files __cacheline_aligned_in_smp; /* Container for backing file with optional user path */ struct backing_file { struct file file; union { struct path user_path; freeptr_t bf_freeptr; }; }; static inline struct backing_file *backing_file(struct file *f) { return container_of(f, struct backing_file, file); } struct path *backing_file_user_path(struct file *f) { return &backing_file(f)->user_path; } EXPORT_SYMBOL_GPL(backing_file_user_path); static inline void file_free(struct file *f) { security_file_free(f); if (likely(!(f->f_mode & FMODE_NOACCOUNT))) percpu_counter_dec(&nr_files); put_cred(f->f_cred); if (unlikely(f->f_mode & FMODE_BACKING)) { path_put(backing_file_user_path(f)); kmem_cache_free(bfilp_cachep, backing_file(f)); } else { kmem_cache_free(filp_cachep, f); } } /* * Return the total number of open files in the system */ static long get_nr_files(void) { return percpu_counter_read_positive(&nr_files); } /* * Return the maximum number of open files in the system */ unsigned long get_max_files(void) { return files_stat.max_files; } EXPORT_SYMBOL_GPL(get_max_files); #if defined(CONFIG_SYSCTL) && defined(CONFIG_PROC_FS) /* * Handle nr_files sysctl */ static int proc_nr_files(const struct ctl_table *table, int write, void *buffer, size_t *lenp, loff_t *ppos) { files_stat.nr_files = get_nr_files(); return proc_doulongvec_minmax(table, write, buffer, lenp, ppos); } static struct ctl_table fs_stat_sysctls[] = { { .procname = "file-nr", .data = &files_stat, .maxlen = sizeof(files_stat), .mode = 0444, .proc_handler = proc_nr_files, }, { .procname = "file-max", .data = &files_stat.max_files, .maxlen = sizeof(files_stat.max_files), .mode = 0644, .proc_handler = proc_doulongvec_minmax, .extra1 = SYSCTL_LONG_ZERO, .extra2 = SYSCTL_LONG_MAX, }, { .procname = "nr_open", .data = &sysctl_nr_open, .maxlen = sizeof(unsigned int), .mode = 0644, .proc_handler = proc_dointvec_minmax, .extra1 = &sysctl_nr_open_min, .extra2 = &sysctl_nr_open_max, }, }; static int __init init_fs_stat_sysctls(void) { register_sysctl_init("fs", fs_stat_sysctls); if (IS_ENABLED(CONFIG_BINFMT_MISC)) { struct ctl_table_header *hdr; hdr = register_sysctl_mount_point("fs/binfmt_misc"); kmemleak_not_leak(hdr); } return 0; } fs_initcall(init_fs_stat_sysctls); #endif static int init_file(struct file *f, int flags, const struct cred *cred) { int error; f->f_cred = get_cred(cred); error = security_file_alloc(f); if (unlikely(error)) { put_cred(f->f_cred); return error; } spin_lock_init(&f->f_lock); /* * Note that f_pos_lock is only used for files raising * FMODE_ATOMIC_POS and directories. Other files such as pipes * don't need it and since f_pos_lock is in a union may reuse * the space for other purposes. They are expected to initialize * the respective member when opening the file. */ mutex_init(&f->f_pos_lock); memset(&f->f_path, 0, sizeof(f->f_path)); memset(&f->f_ra, 0, sizeof(f->f_ra)); f->f_flags = flags; f->f_mode = OPEN_FMODE(flags); f->f_op = NULL; f->f_mapping = NULL; f->private_data = NULL; f->f_inode = NULL; f->f_owner = NULL; #ifdef CONFIG_EPOLL f->f_ep = NULL; #endif f->f_iocb_flags = 0; f->f_pos = 0; f->f_wb_err = 0; f->f_sb_err = 0; /* * We're SLAB_TYPESAFE_BY_RCU so initialize f_count last. While * fget-rcu pattern users need to be able to handle spurious * refcount bumps we should reinitialize the reused file first. */ file_ref_init(&f->f_ref, 1); return 0; } /* Find an unused file structure and return a pointer to it. * Returns an error pointer if some error happend e.g. we over file * structures limit, run out of memory or operation is not permitted. * * Be very careful using this. You are responsible for * getting write access to any mount that you might assign * to this filp, if it is opened for write. If this is not * done, you will imbalance int the mount's writer count * and a warning at __fput() time. */ struct file *alloc_empty_file(int flags, const struct cred *cred) { static long old_max; struct file *f; int error; /* * Privileged users can go above max_files */ if (get_nr_files() >= files_stat.max_files && !capable(CAP_SYS_ADMIN)) { /* * percpu_counters are inaccurate. Do an expensive check before * we go and fail. */ if (percpu_counter_sum_positive(&nr_files) >= files_stat.max_files) goto over; } f = kmem_cache_alloc(filp_cachep, GFP_KERNEL); if (unlikely(!f)) return ERR_PTR(-ENOMEM); error = init_file(f, flags, cred); if (unlikely(error)) { kmem_cache_free(filp_cachep, f); return ERR_PTR(error); } percpu_counter_inc(&nr_files); return f; over: /* Ran out of filps - report that */ if (get_nr_files() > old_max) { pr_info("VFS: file-max limit %lu reached\n", get_max_files()); old_max = get_nr_files(); } return ERR_PTR(-ENFILE); } /* * Variant of alloc_empty_file() that doesn't check and modify nr_files. * * This is only for kernel internal use, and the allocate file must not be * installed into file tables or such. */ struct file *alloc_empty_file_noaccount(int flags, const struct cred *cred) { struct file *f; int error; f = kmem_cache_alloc(filp_cachep, GFP_KERNEL); if (unlikely(!f)) return ERR_PTR(-ENOMEM); error = init_file(f, flags, cred); if (unlikely(error)) { kmem_cache_free(filp_cachep, f); return ERR_PTR(error); } f->f_mode |= FMODE_NOACCOUNT; return f; } /* * Variant of alloc_empty_file() that allocates a backing_file container * and doesn't check and modify nr_files. * * This is only for kernel internal use, and the allocate file must not be * installed into file tables or such. */ struct file *alloc_empty_backing_file(int flags, const struct cred *cred) { struct backing_file *ff; int error; ff = kmem_cache_alloc(bfilp_cachep, GFP_KERNEL); if (unlikely(!ff)) return ERR_PTR(-ENOMEM); error = init_file(&ff->file, flags, cred); if (unlikely(error)) { kmem_cache_free(bfilp_cachep, ff); return ERR_PTR(error); } ff->file.f_mode |= FMODE_BACKING | FMODE_NOACCOUNT; return &ff->file; } /** * file_init_path - initialize a 'struct file' based on path * * @file: the file to set up * @path: the (dentry, vfsmount) pair for the new file * @fop: the 'struct file_operations' for the new file */ static void file_init_path(struct file *file, const struct path *path, const struct file_operations *fop) { file->f_path = *path; file->f_inode = path->dentry->d_inode; file->f_mapping = path->dentry->d_inode->i_mapping; file->f_wb_err = filemap_sample_wb_err(file->f_mapping); file->f_sb_err = file_sample_sb_err(file); if (fop->llseek) file->f_mode |= FMODE_LSEEK; if ((file->f_mode & FMODE_READ) && likely(fop->read || fop->read_iter)) file->f_mode |= FMODE_CAN_READ; if ((file->f_mode & FMODE_WRITE) && likely(fop->write || fop->write_iter)) file->f_mode |= FMODE_CAN_WRITE; file->f_iocb_flags = iocb_flags(file); file->f_mode |= FMODE_OPENED; file->f_op = fop; if ((file->f_mode & (FMODE_READ | FMODE_WRITE)) == FMODE_READ) i_readcount_inc(path->dentry->d_inode); } /** * alloc_file - allocate and initialize a 'struct file' * * @path: the (dentry, vfsmount) pair for the new file * @flags: O_... flags with which the new file will be opened * @fop: the 'struct file_operations' for the new file */ static struct file *alloc_file(const struct path *path, int flags, const struct file_operations *fop) { struct file *file; file = alloc_empty_file(flags, current_cred()); if (!IS_ERR(file)) file_init_path(file, path, fop); return file; } static inline int alloc_path_pseudo(const char *name, struct inode *inode, struct vfsmount *mnt, struct path *path) { struct qstr this = QSTR_INIT(name, strlen(name)); path->dentry = d_alloc_pseudo(mnt->mnt_sb, &this); if (!path->dentry) return -ENOMEM; path->mnt = mntget(mnt); d_instantiate(path->dentry, inode); return 0; } struct file *alloc_file_pseudo(struct inode *inode, struct vfsmount *mnt, const char *name, int flags, const struct file_operations *fops) { int ret; struct path path; struct file *file; ret = alloc_path_pseudo(name, inode, mnt, &path); if (ret) return ERR_PTR(ret); file = alloc_file(&path, flags, fops); if (IS_ERR(file)) { ihold(inode); path_put(&path); } return file; } EXPORT_SYMBOL(alloc_file_pseudo); struct file *alloc_file_pseudo_noaccount(struct inode *inode, struct vfsmount *mnt, const char *name, int flags, const struct file_operations *fops) { int ret; struct path path; struct file *file; ret = alloc_path_pseudo(name, inode, mnt, &path); if (ret) return ERR_PTR(ret); file = alloc_empty_file_noaccount(flags, current_cred()); if (IS_ERR(file)) { ihold(inode); path_put(&path); return file; } file_init_path(file, &path, fops); return file; } EXPORT_SYMBOL_GPL(alloc_file_pseudo_noaccount); struct file *alloc_file_clone(struct file *base, int flags, const struct file_operations *fops) { struct file *f; f = alloc_file(&base->f_path, flags, fops); if (!IS_ERR(f)) { path_get(&f->f_path); f->f_mapping = base->f_mapping; } return f; } /* the real guts of fput() - releasing the last reference to file */ static void __fput(struct file *file) { struct dentry *dentry = file->f_path.dentry; struct vfsmount *mnt = file->f_path.mnt; struct inode *inode = file->f_inode; fmode_t mode = file->f_mode; if (unlikely(!(file->f_mode & FMODE_OPENED))) goto out; might_sleep(); fsnotify_close(file); /* * The function eventpoll_release() should be the first called * in the file cleanup chain. */ eventpoll_release(file); locks_remove_file(file); security_file_release(file); if (unlikely(file->f_flags & FASYNC)) { if (file->f_op->fasync) file->f_op->fasync(-1, file, 0); } if (file->f_op->release) file->f_op->release(inode, file); if (unlikely(S_ISCHR(inode->i_mode) && inode->i_cdev != NULL && !(mode & FMODE_PATH))) { cdev_put(inode->i_cdev); } fops_put(file->f_op); file_f_owner_release(file); put_file_access(file); dput(dentry); if (unlikely(mode & FMODE_NEED_UNMOUNT)) dissolve_on_fput(mnt); mntput(mnt); out: file_free(file); } static LLIST_HEAD(delayed_fput_list); static void delayed_fput(struct work_struct *unused) { struct llist_node *node = llist_del_all(&delayed_fput_list); struct file *f, *t; llist_for_each_entry_safe(f, t, node, f_llist) __fput(f); } static void ____fput(struct callback_head *work) { __fput(container_of(work, struct file, f_task_work)); } /* * If kernel thread really needs to have the final fput() it has done * to complete, call this. The only user right now is the boot - we * *do* need to make sure our writes to binaries on initramfs has * not left us with opened struct file waiting for __fput() - execve() * won't work without that. Please, don't add more callers without * very good reasons; in particular, never call that with locks * held and never call that from a thread that might need to do * some work on any kind of umount. */ void flush_delayed_fput(void) { delayed_fput(NULL); } EXPORT_SYMBOL_GPL(flush_delayed_fput); static DECLARE_DELAYED_WORK(delayed_fput_work, delayed_fput); void fput(struct file *file) { if (file_ref_put(&file->f_ref)) { struct task_struct *task = current; if (unlikely(!(file->f_mode & (FMODE_BACKING | FMODE_OPENED)))) { file_free(file); return; } if (likely(!in_interrupt() && !(task->flags & PF_KTHREAD))) { init_task_work(&file->f_task_work, ____fput); if (!task_work_add(task, &file->f_task_work, TWA_RESUME)) return; /* * After this task has run exit_task_work(), * task_work_add() will fail. Fall through to delayed * fput to avoid leaking *file. */ } if (llist_add(&file->f_llist, &delayed_fput_list)) schedule_delayed_work(&delayed_fput_work, 1); } } /* * synchronous analog of fput(); for kernel threads that might be needed * in some umount() (and thus can't use flush_delayed_fput() without * risking deadlocks), need to wait for completion of __fput() and know * for this specific struct file it won't involve anything that would * need them. Use only if you really need it - at the very least, * don't blindly convert fput() by kernel thread to that. */ void __fput_sync(struct file *file) { if (file_ref_put(&file->f_ref)) __fput(file); } EXPORT_SYMBOL(fput); EXPORT_SYMBOL(__fput_sync); void __init files_init(void) { struct kmem_cache_args args = { .use_freeptr_offset = true, .freeptr_offset = offsetof(struct file, f_freeptr), }; filp_cachep = kmem_cache_create("filp", sizeof(struct file), &args, SLAB_HWCACHE_ALIGN | SLAB_PANIC | SLAB_ACCOUNT | SLAB_TYPESAFE_BY_RCU); args.freeptr_offset = offsetof(struct backing_file, bf_freeptr); bfilp_cachep = kmem_cache_create("bfilp", sizeof(struct backing_file), &args, SLAB_HWCACHE_ALIGN | SLAB_PANIC | SLAB_ACCOUNT | SLAB_TYPESAFE_BY_RCU); percpu_counter_init(&nr_files, 0, GFP_KERNEL); } /* * One file with associated inode and dcache is very roughly 1K. Per default * do not use more than 10% of our memory for files. */ void __init files_maxfiles_init(void) { unsigned long n; unsigned long nr_pages = totalram_pages(); unsigned long memreserve = (nr_pages - nr_free_pages()) * 3/2; memreserve = min(memreserve, nr_pages - 1); n = ((nr_pages - memreserve) * (PAGE_SIZE / 1024)) / 10; files_stat.max_files = max_t(unsigned long, n, NR_FILE); } |
| 84 84 139 194 37 873 798 1 194 887 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 | /* SPDX-License-Identifier: GPL-2.0-only */ /* * Based on arch/arm/include/asm/cmpxchg.h * * Copyright (C) 2012 ARM Ltd. */ #ifndef __ASM_CMPXCHG_H #define __ASM_CMPXCHG_H #include <linux/build_bug.h> #include <linux/compiler.h> #include <asm/barrier.h> #include <asm/lse.h> /* * We need separate acquire parameters for ll/sc and lse, since the full * barrier case is generated as release+dmb for the former and * acquire+release for the latter. */ #define __XCHG_CASE(w, sfx, name, sz, mb, nop_lse, acq, acq_lse, rel, cl) \ static inline u##sz __xchg_case_##name##sz(u##sz x, volatile void *ptr) \ { \ u##sz ret; \ unsigned long tmp; \ \ asm volatile(ARM64_LSE_ATOMIC_INSN( \ /* LL/SC */ \ " prfm pstl1strm, %2\n" \ "1: ld" #acq "xr" #sfx "\t%" #w "0, %2\n" \ " st" #rel "xr" #sfx "\t%w1, %" #w "3, %2\n" \ " cbnz %w1, 1b\n" \ " " #mb, \ /* LSE atomics */ \ " swp" #acq_lse #rel #sfx "\t%" #w "3, %" #w "0, %2\n" \ __nops(3) \ " " #nop_lse) \ : "=&r" (ret), "=&r" (tmp), "+Q" (*(u##sz *)ptr) \ : "r" (x) \ : cl); \ \ return ret; \ } __XCHG_CASE(w, b, , 8, , , , , , ) __XCHG_CASE(w, h, , 16, , , , , , ) __XCHG_CASE(w, , , 32, , , , , , ) __XCHG_CASE( , , , 64, , , , , , ) __XCHG_CASE(w, b, acq_, 8, , , a, a, , "memory") __XCHG_CASE(w, h, acq_, 16, , , a, a, , "memory") __XCHG_CASE(w, , acq_, 32, , , a, a, , "memory") __XCHG_CASE( , , acq_, 64, , , a, a, , "memory") __XCHG_CASE(w, b, rel_, 8, , , , , l, "memory") __XCHG_CASE(w, h, rel_, 16, , , , , l, "memory") __XCHG_CASE(w, , rel_, 32, , , , , l, "memory") __XCHG_CASE( , , rel_, 64, , , , , l, "memory") __XCHG_CASE(w, b, mb_, 8, dmb ish, nop, , a, l, "memory") __XCHG_CASE(w, h, mb_, 16, dmb ish, nop, , a, l, "memory") __XCHG_CASE(w, , mb_, 32, dmb ish, nop, , a, l, "memory") __XCHG_CASE( , , mb_, 64, dmb ish, nop, , a, l, "memory") #undef __XCHG_CASE #define __XCHG_GEN(sfx) \ static __always_inline unsigned long \ __arch_xchg##sfx(unsigned long x, volatile void *ptr, int size) \ { \ switch (size) { \ case 1: \ return __xchg_case##sfx##_8(x, ptr); \ case 2: \ return __xchg_case##sfx##_16(x, ptr); \ case 4: \ return __xchg_case##sfx##_32(x, ptr); \ case 8: \ return __xchg_case##sfx##_64(x, ptr); \ default: \ BUILD_BUG(); \ } \ \ unreachable(); \ } __XCHG_GEN() __XCHG_GEN(_acq) __XCHG_GEN(_rel) __XCHG_GEN(_mb) #undef __XCHG_GEN #define __xchg_wrapper(sfx, ptr, x) \ ({ \ __typeof__(*(ptr)) __ret; \ __ret = (__typeof__(*(ptr))) \ __arch_xchg##sfx((unsigned long)(x), (ptr), sizeof(*(ptr))); \ __ret; \ }) /* xchg */ #define arch_xchg_relaxed(...) __xchg_wrapper( , __VA_ARGS__) #define arch_xchg_acquire(...) __xchg_wrapper(_acq, __VA_ARGS__) #define arch_xchg_release(...) __xchg_wrapper(_rel, __VA_ARGS__) #define arch_xchg(...) __xchg_wrapper( _mb, __VA_ARGS__) #define __CMPXCHG_CASE(name, sz) \ static inline u##sz __cmpxchg_case_##name##sz(volatile void *ptr, \ u##sz old, \ u##sz new) \ { \ return __lse_ll_sc_body(_cmpxchg_case_##name##sz, \ ptr, old, new); \ } __CMPXCHG_CASE( , 8) __CMPXCHG_CASE( , 16) __CMPXCHG_CASE( , 32) __CMPXCHG_CASE( , 64) __CMPXCHG_CASE(acq_, 8) __CMPXCHG_CASE(acq_, 16) __CMPXCHG_CASE(acq_, 32) __CMPXCHG_CASE(acq_, 64) __CMPXCHG_CASE(rel_, 8) __CMPXCHG_CASE(rel_, 16) __CMPXCHG_CASE(rel_, 32) __CMPXCHG_CASE(rel_, 64) __CMPXCHG_CASE(mb_, 8) __CMPXCHG_CASE(mb_, 16) __CMPXCHG_CASE(mb_, 32) __CMPXCHG_CASE(mb_, 64) #undef __CMPXCHG_CASE #define __CMPXCHG128(name) \ static inline u128 __cmpxchg128##name(volatile u128 *ptr, \ u128 old, u128 new) \ { \ return __lse_ll_sc_body(_cmpxchg128##name, \ ptr, old, new); \ } __CMPXCHG128( ) __CMPXCHG128(_mb) #undef __CMPXCHG128 #define __CMPXCHG_GEN(sfx) \ static __always_inline unsigned long __cmpxchg##sfx(volatile void *ptr, \ unsigned long old, \ unsigned long new, \ int size) \ { \ switch (size) { \ case 1: \ return __cmpxchg_case##sfx##_8(ptr, old, new); \ case 2: \ return __cmpxchg_case##sfx##_16(ptr, old, new); \ case 4: \ return __cmpxchg_case##sfx##_32(ptr, old, new); \ case 8: \ return __cmpxchg_case##sfx##_64(ptr, old, new); \ default: \ BUILD_BUG(); \ } \ \ unreachable(); \ } __CMPXCHG_GEN() __CMPXCHG_GEN(_acq) __CMPXCHG_GEN(_rel) __CMPXCHG_GEN(_mb) #undef __CMPXCHG_GEN #define __cmpxchg_wrapper(sfx, ptr, o, n) \ ({ \ __typeof__(*(ptr)) __ret; \ __ret = (__typeof__(*(ptr))) \ __cmpxchg##sfx((ptr), (unsigned long)(o), \ (unsigned long)(n), sizeof(*(ptr))); \ __ret; \ }) /* cmpxchg */ #define arch_cmpxchg_relaxed(...) __cmpxchg_wrapper( , __VA_ARGS__) #define arch_cmpxchg_acquire(...) __cmpxchg_wrapper(_acq, __VA_ARGS__) #define arch_cmpxchg_release(...) __cmpxchg_wrapper(_rel, __VA_ARGS__) #define arch_cmpxchg(...) __cmpxchg_wrapper( _mb, __VA_ARGS__) #define arch_cmpxchg_local arch_cmpxchg_relaxed /* cmpxchg64 */ #define arch_cmpxchg64_relaxed arch_cmpxchg_relaxed #define arch_cmpxchg64_acquire arch_cmpxchg_acquire #define arch_cmpxchg64_release arch_cmpxchg_release #define arch_cmpxchg64 arch_cmpxchg #define arch_cmpxchg64_local arch_cmpxchg_local /* cmpxchg128 */ #define system_has_cmpxchg128() 1 #define arch_cmpxchg128(ptr, o, n) \ ({ \ __cmpxchg128_mb((ptr), (o), (n)); \ }) #define arch_cmpxchg128_local(ptr, o, n) \ ({ \ __cmpxchg128((ptr), (o), (n)); \ }) #define __CMPWAIT_CASE(w, sfx, sz) \ static inline void __cmpwait_case_##sz(volatile void *ptr, \ unsigned long val) \ { \ unsigned long tmp; \ \ asm volatile( \ " sevl\n" \ " wfe\n" \ " ldxr" #sfx "\t%" #w "[tmp], %[v]\n" \ " eor %" #w "[tmp], %" #w "[tmp], %" #w "[val]\n" \ " cbnz %" #w "[tmp], 1f\n" \ " wfe\n" \ "1:" \ : [tmp] "=&r" (tmp), [v] "+Q" (*(u##sz *)ptr) \ : [val] "r" (val)); \ } __CMPWAIT_CASE(w, b, 8); __CMPWAIT_CASE(w, h, 16); __CMPWAIT_CASE(w, , 32); __CMPWAIT_CASE( , , 64); #undef __CMPWAIT_CASE #define __CMPWAIT_GEN(sfx) \ static __always_inline void __cmpwait##sfx(volatile void *ptr, \ unsigned long val, \ int size) \ { \ switch (size) { \ case 1: \ return __cmpwait_case##sfx##_8(ptr, (u8)val); \ case 2: \ return __cmpwait_case##sfx##_16(ptr, (u16)val); \ case 4: \ return __cmpwait_case##sfx##_32(ptr, val); \ case 8: \ return __cmpwait_case##sfx##_64(ptr, val); \ default: \ BUILD_BUG(); \ } \ \ unreachable(); \ } __CMPWAIT_GEN() #undef __CMPWAIT_GEN #define __cmpwait_relaxed(ptr, val) \ __cmpwait((ptr), (unsigned long)(val), sizeof(*(ptr))) #endif /* __ASM_CMPXCHG_H */ |
| 762 290 290 225 225 80 80 80 80 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 | // SPDX-License-Identifier: GPL-2.0-only /* * fs/anon_inodes.c * * Copyright (C) 2007 Davide Libenzi <davidel@xmailserver.org> * * Thanks to Arnd Bergmann for code review and suggestions. * More changes for Thomas Gleixner suggestions. * */ #include <linux/cred.h> #include <linux/file.h> #include <linux/poll.h> #include <linux/sched.h> #include <linux/init.h> #include <linux/fs.h> #include <linux/mount.h> #include <linux/module.h> #include <linux/kernel.h> #include <linux/magic.h> #include <linux/anon_inodes.h> #include <linux/pseudo_fs.h> #include <linux/uaccess.h> static struct vfsmount *anon_inode_mnt __ro_after_init; static struct inode *anon_inode_inode __ro_after_init; /* * anon_inodefs_dname() is called from d_path(). */ static char *anon_inodefs_dname(struct dentry *dentry, char *buffer, int buflen) { return dynamic_dname(buffer, buflen, "anon_inode:%s", dentry->d_name.name); } static const struct dentry_operations anon_inodefs_dentry_operations = { .d_dname = anon_inodefs_dname, }; static int anon_inodefs_init_fs_context(struct fs_context *fc) { struct pseudo_fs_context *ctx = init_pseudo(fc, ANON_INODE_FS_MAGIC); if (!ctx) return -ENOMEM; ctx->dops = &anon_inodefs_dentry_operations; return 0; } static struct file_system_type anon_inode_fs_type = { .name = "anon_inodefs", .init_fs_context = anon_inodefs_init_fs_context, .kill_sb = kill_anon_super, }; static struct inode *anon_inode_make_secure_inode( const char *name, const struct inode *context_inode) { struct inode *inode; const struct qstr qname = QSTR_INIT(name, strlen(name)); int error; inode = alloc_anon_inode(anon_inode_mnt->mnt_sb); if (IS_ERR(inode)) return inode; inode->i_flags &= ~S_PRIVATE; error = security_inode_init_security_anon(inode, &qname, context_inode); if (error) { iput(inode); return ERR_PTR(error); } return inode; } static struct file *__anon_inode_getfile(const char *name, const struct file_operations *fops, void *priv, int flags, const struct inode *context_inode, bool make_inode) { struct inode *inode; struct file *file; if (fops->owner && !try_module_get(fops->owner)) return ERR_PTR(-ENOENT); if (make_inode) { inode = anon_inode_make_secure_inode(name, context_inode); if (IS_ERR(inode)) { file = ERR_CAST(inode); goto err; } } else { inode = anon_inode_inode; if (IS_ERR(inode)) { file = ERR_PTR(-ENODEV); goto err; } /* * We know the anon_inode inode count is always * greater than zero, so ihold() is safe. */ ihold(inode); } file = alloc_file_pseudo(inode, anon_inode_mnt, name, flags & (O_ACCMODE | O_NONBLOCK), fops); if (IS_ERR(file)) goto err_iput; file->f_mapping = inode->i_mapping; file->private_data = priv; return file; err_iput: iput(inode); err: module_put(fops->owner); return file; } /** * anon_inode_getfile - creates a new file instance by hooking it up to an * anonymous inode, and a dentry that describe the "class" * of the file * * @name: [in] name of the "class" of the new file * @fops: [in] file operations for the new file * @priv: [in] private data for the new file (will be file's private_data) * @flags: [in] flags * * Creates a new file by hooking it on a single inode. This is useful for files * that do not need to have a full-fledged inode in order to operate correctly. * All the files created with anon_inode_getfile() will share a single inode, * hence saving memory and avoiding code duplication for the file/inode/dentry * setup. Returns the newly created file* or an error pointer. */ struct file *anon_inode_getfile(const char *name, const struct file_operations *fops, void *priv, int flags) { return __anon_inode_getfile(name, fops, priv, flags, NULL, false); } EXPORT_SYMBOL_GPL(anon_inode_getfile); /** * anon_inode_getfile_fmode - creates a new file instance by hooking it up to an * anonymous inode, and a dentry that describe the "class" * of the file * * @name: [in] name of the "class" of the new file * @fops: [in] file operations for the new file * @priv: [in] private data for the new file (will be file's private_data) * @flags: [in] flags * @f_mode: [in] fmode * * Creates a new file by hooking it on a single inode. This is useful for files * that do not need to have a full-fledged inode in order to operate correctly. * All the files created with anon_inode_getfile() will share a single inode, * hence saving memory and avoiding code duplication for the file/inode/dentry * setup. Allows setting the fmode. Returns the newly created file* or an error * pointer. */ struct file *anon_inode_getfile_fmode(const char *name, const struct file_operations *fops, void *priv, int flags, fmode_t f_mode) { struct file *file; file = __anon_inode_getfile(name, fops, priv, flags, NULL, false); if (!IS_ERR(file)) file->f_mode |= f_mode; return file; } EXPORT_SYMBOL_GPL(anon_inode_getfile_fmode); /** * anon_inode_create_getfile - Like anon_inode_getfile(), but creates a new * !S_PRIVATE anon inode rather than reuse the * singleton anon inode and calls the * inode_init_security_anon() LSM hook. * * @name: [in] name of the "class" of the new file * @fops: [in] file operations for the new file * @priv: [in] private data for the new file (will be file's private_data) * @flags: [in] flags * @context_inode: * [in] the logical relationship with the new inode (optional) * * Create a new anonymous inode and file pair. This can be done for two * reasons: * * - for the inode to have its own security context, so that LSMs can enforce * policy on the inode's creation; * * - if the caller needs a unique inode, for example in order to customize * the size returned by fstat() * * The LSM may use @context_inode in inode_init_security_anon(), but a * reference to it is not held. * * Returns the newly created file* or an error pointer. */ struct file *anon_inode_create_getfile(const char *name, const struct file_operations *fops, void *priv, int flags, const struct inode *context_inode) { return __anon_inode_getfile(name, fops, priv, flags, context_inode, true); } EXPORT_SYMBOL_GPL(anon_inode_create_getfile); static int __anon_inode_getfd(const char *name, const struct file_operations *fops, void *priv, int flags, const struct inode *context_inode, bool make_inode) { int error, fd; struct file *file; error = get_unused_fd_flags(flags); if (error < 0) return error; fd = error; file = __anon_inode_getfile(name, fops, priv, flags, context_inode, make_inode); if (IS_ERR(file)) { error = PTR_ERR(file); goto err_put_unused_fd; } fd_install(fd, file); return fd; err_put_unused_fd: put_unused_fd(fd); return error; } /** * anon_inode_getfd - creates a new file instance by hooking it up to * an anonymous inode and a dentry that describe * the "class" of the file * * @name: [in] name of the "class" of the new file * @fops: [in] file operations for the new file * @priv: [in] private data for the new file (will be file's private_data) * @flags: [in] flags * * Creates a new file by hooking it on a single inode. This is * useful for files that do not need to have a full-fledged inode in * order to operate correctly. All the files created with * anon_inode_getfd() will use the same singleton inode, reducing * memory use and avoiding code duplication for the file/inode/dentry * setup. Returns a newly created file descriptor or an error code. */ int anon_inode_getfd(const char *name, const struct file_operations *fops, void *priv, int flags) { return __anon_inode_getfd(name, fops, priv, flags, NULL, false); } EXPORT_SYMBOL_GPL(anon_inode_getfd); /** * anon_inode_create_getfd - Like anon_inode_getfd(), but creates a new * !S_PRIVATE anon inode rather than reuse the singleton anon inode, and calls * the inode_init_security_anon() LSM hook. * * @name: [in] name of the "class" of the new file * @fops: [in] file operations for the new file * @priv: [in] private data for the new file (will be file's private_data) * @flags: [in] flags * @context_inode: * [in] the logical relationship with the new inode (optional) * * Create a new anonymous inode and file pair. This can be done for two * reasons: * * - for the inode to have its own security context, so that LSMs can enforce * policy on the inode's creation; * * - if the caller needs a unique inode, for example in order to customize * the size returned by fstat() * * The LSM may use @context_inode in inode_init_security_anon(), but a * reference to it is not held. * * Returns a newly created file descriptor or an error code. */ int anon_inode_create_getfd(const char *name, const struct file_operations *fops, void *priv, int flags, const struct inode *context_inode) { return __anon_inode_getfd(name, fops, priv, flags, context_inode, true); } static int __init anon_inode_init(void) { anon_inode_mnt = kern_mount(&anon_inode_fs_type); if (IS_ERR(anon_inode_mnt)) panic("anon_inode_init() kernel mount failed (%ld)\n", PTR_ERR(anon_inode_mnt)); anon_inode_inode = alloc_anon_inode(anon_inode_mnt->mnt_sb); if (IS_ERR(anon_inode_inode)) panic("anon_inode_init() inode allocation failed (%ld)\n", PTR_ERR(anon_inode_inode)); return 0; } fs_initcall(anon_inode_init); |
| 3 2 3 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 | // SPDX-License-Identifier: GPL-2.0-only /* * net/core/fib_rules.c Generic Routing Rules * * Authors: Thomas Graf <tgraf@suug.ch> */ #include <linux/types.h> #include <linux/kernel.h> #include <linux/slab.h> #include <linux/list.h> #include <linux/module.h> #include <net/net_namespace.h> #include <net/inet_dscp.h> #include <net/sock.h> #include <net/fib_rules.h> #include <net/ip_tunnels.h> #include <linux/indirect_call_wrapper.h> #if defined(CONFIG_IPV6) && defined(CONFIG_IPV6_MULTIPLE_TABLES) #ifdef CONFIG_IP_MULTIPLE_TABLES #define INDIRECT_CALL_MT(f, f2, f1, ...) \ INDIRECT_CALL_INET(f, f2, f1, __VA_ARGS__) #else #define INDIRECT_CALL_MT(f, f2, f1, ...) INDIRECT_CALL_1(f, f2, __VA_ARGS__) #endif #elif defined(CONFIG_IP_MULTIPLE_TABLES) #define INDIRECT_CALL_MT(f, f2, f1, ...) INDIRECT_CALL_1(f, f1, __VA_ARGS__) #else #define INDIRECT_CALL_MT(f, f2, f1, ...) f(__VA_ARGS__) #endif static const struct fib_kuid_range fib_kuid_range_unset = { KUIDT_INIT(0), KUIDT_INIT(~0), }; bool fib_rule_matchall(const struct fib_rule *rule) { if (rule->iifindex || rule->oifindex || rule->mark || rule->tun_id || rule->flags) return false; if (rule->suppress_ifgroup != -1 || rule->suppress_prefixlen != -1) return false; if (!uid_eq(rule->uid_range.start, fib_kuid_range_unset.start) || !uid_eq(rule->uid_range.end, fib_kuid_range_unset.end)) return false; if (fib_rule_port_range_set(&rule->sport_range)) return false; if (fib_rule_port_range_set(&rule->dport_range)) return false; return true; } EXPORT_SYMBOL_GPL(fib_rule_matchall); int fib_default_rule_add(struct fib_rules_ops *ops, u32 pref, u32 table) { struct fib_rule *r; r = kzalloc(ops->rule_size, GFP_KERNEL_ACCOUNT); if (r == NULL) return -ENOMEM; refcount_set(&r->refcnt, 1); r->action = FR_ACT_TO_TBL; r->pref = pref; r->table = table; r->proto = RTPROT_KERNEL; r->fr_net = ops->fro_net; r->uid_range = fib_kuid_range_unset; r->suppress_prefixlen = -1; r->suppress_ifgroup = -1; /* The lock is not required here, the list in unreachable * at the moment this function is called */ list_add_tail(&r->list, &ops->rules_list); return 0; } EXPORT_SYMBOL(fib_default_rule_add); static u32 fib_default_rule_pref(struct fib_rules_ops *ops) { struct list_head *pos; struct fib_rule *rule; if (!list_empty(&ops->rules_list)) { pos = ops->rules_list.next; if (pos->next != &ops->rules_list) { rule = list_entry(pos->next, struct fib_rule, list); if (rule->pref) return rule->pref - 1; } } return 0; } static void notify_rule_change(int event, struct fib_rule *rule, struct fib_rules_ops *ops, struct nlmsghdr *nlh, u32 pid); static struct fib_rules_ops *lookup_rules_ops(const struct net *net, int family) { struct fib_rules_ops *ops; rcu_read_lock(); list_for_each_entry_rcu(ops, &net->rules_ops, list) { if (ops->family == family) { if (!try_module_get(ops->owner)) ops = NULL; rcu_read_unlock(); return ops; } } rcu_read_unlock(); return NULL; } static void rules_ops_put(struct fib_rules_ops *ops) { if (ops) module_put(ops->owner); } static void flush_route_cache(struct fib_rules_ops *ops) { if (ops->flush_cache) ops->flush_cache(ops); } static int __fib_rules_register(struct fib_rules_ops *ops) { int err = -EEXIST; struct fib_rules_ops *o; struct net *net; net = ops->fro_net; if (ops->rule_size < sizeof(struct fib_rule)) return -EINVAL; if (ops->match == NULL || ops->configure == NULL || ops->compare == NULL || ops->fill == NULL || ops->action == NULL) return -EINVAL; spin_lock(&net->rules_mod_lock); list_for_each_entry(o, &net->rules_ops, list) if (ops->family == o->family) goto errout; list_add_tail_rcu(&ops->list, &net->rules_ops); err = 0; errout: spin_unlock(&net->rules_mod_lock); return err; } struct fib_rules_ops * fib_rules_register(const struct fib_rules_ops *tmpl, struct net *net) { struct fib_rules_ops *ops; int err; ops = kmemdup(tmpl, sizeof(*ops), GFP_KERNEL); if (ops == NULL) return ERR_PTR(-ENOMEM); INIT_LIST_HEAD(&ops->rules_list); ops->fro_net = net; err = __fib_rules_register(ops); if (err) { kfree(ops); ops = ERR_PTR(err); } return ops; } EXPORT_SYMBOL_GPL(fib_rules_register); static void fib_rules_cleanup_ops(struct fib_rules_ops *ops) { struct fib_rule *rule, *tmp; list_for_each_entry_safe(rule, tmp, &ops->rules_list, list) { list_del_rcu(&rule->list); if (ops->delete) ops->delete(rule); fib_rule_put(rule); } } void fib_rules_unregister(struct fib_rules_ops *ops) { struct net *net = ops->fro_net; spin_lock(&net->rules_mod_lock); list_del_rcu(&ops->list); spin_unlock(&net->rules_mod_lock); fib_rules_cleanup_ops(ops); kfree_rcu(ops, rcu); } EXPORT_SYMBOL_GPL(fib_rules_unregister); static int uid_range_set(struct fib_kuid_range *range) { return uid_valid(range->start) && uid_valid(range->end); } static struct fib_kuid_range nla_get_kuid_range(struct nlattr **tb) { struct fib_rule_uid_range *in; struct fib_kuid_range out; in = (struct fib_rule_uid_range *)nla_data(tb[FRA_UID_RANGE]); out.start = make_kuid(current_user_ns(), in->start); out.end = make_kuid(current_user_ns(), in->end); return out; } static int nla_put_uid_range(struct sk_buff *skb, struct fib_kuid_range *range) { struct fib_rule_uid_range out = { from_kuid_munged(current_user_ns(), range->start), from_kuid_munged(current_user_ns(), range->end) }; return nla_put(skb, FRA_UID_RANGE, sizeof(out), &out); } static int nla_get_port_range(struct nlattr *pattr, struct fib_rule_port_range *port_range) { const struct fib_rule_port_range *pr = nla_data(pattr); if (!fib_rule_port_range_valid(pr)) return -EINVAL; port_range->start = pr->start; port_range->end = pr->end; return 0; } static int nla_put_port_range(struct sk_buff *skb, int attrtype, struct fib_rule_port_range *range) { return nla_put(skb, attrtype, sizeof(*range), range); } static int fib_rule_match(struct fib_rule *rule, struct fib_rules_ops *ops, struct flowi *fl, int flags, struct fib_lookup_arg *arg) { int ret = 0; if (rule->iifindex && (rule->iifindex != fl->flowi_iif)) goto out; if (rule->oifindex && (rule->oifindex != fl->flowi_oif)) goto out; if ((rule->mark ^ fl->flowi_mark) & rule->mark_mask) goto out; if (rule->tun_id && (rule->tun_id != fl->flowi_tun_key.tun_id)) goto out; if (rule->l3mdev && !l3mdev_fib_rule_match(rule->fr_net, fl, arg)) goto out; if (uid_lt(fl->flowi_uid, rule->uid_range.start) || uid_gt(fl->flowi_uid, rule->uid_range.end)) goto out; ret = INDIRECT_CALL_MT(ops->match, fib6_rule_match, fib4_rule_match, rule, fl, flags); out: return (rule->flags & FIB_RULE_INVERT) ? !ret : ret; } int fib_rules_lookup(struct fib_rules_ops *ops, struct flowi *fl, int flags, struct fib_lookup_arg *arg) { struct fib_rule *rule; int err; rcu_read_lock(); list_for_each_entry_rcu(rule, &ops->rules_list, list) { jumped: if (!fib_rule_match(rule, ops, fl, flags, arg)) continue; if (rule->action == FR_ACT_GOTO) { struct fib_rule *target; target = rcu_dereference(rule->ctarget); if (target == NULL) { continue; } else { rule = target; goto jumped; } } else if (rule->action == FR_ACT_NOP) continue; else err = INDIRECT_CALL_MT(ops->action, fib6_rule_action, fib4_rule_action, rule, fl, flags, arg); if (!err && ops->suppress && INDIRECT_CALL_MT(ops->suppress, fib6_rule_suppress, fib4_rule_suppress, rule, flags, arg)) continue; if (err != -EAGAIN) { if ((arg->flags & FIB_LOOKUP_NOREF) || likely(refcount_inc_not_zero(&rule->refcnt))) { arg->rule = rule; goto out; } break; } } err = -ESRCH; out: rcu_read_unlock(); return err; } EXPORT_SYMBOL_GPL(fib_rules_lookup); static int call_fib_rule_notifier(struct notifier_block *nb, enum fib_event_type event_type, struct fib_rule *rule, int family, struct netlink_ext_ack *extack) { struct fib_rule_notifier_info info = { .info.family = family, .info.extack = extack, .rule = rule, }; return call_fib_notifier(nb, event_type, &info.info); } static int call_fib_rule_notifiers(struct net *net, enum fib_event_type event_type, struct fib_rule *rule, struct fib_rules_ops *ops, struct netlink_ext_ack *extack) { struct fib_rule_notifier_info info = { .info.family = ops->family, .info.extack = extack, .rule = rule, }; ASSERT_RTNL(); /* Paired with READ_ONCE() in fib_rules_seq() */ WRITE_ONCE(ops->fib_rules_seq, ops->fib_rules_seq + 1); return call_fib_notifiers(net, event_type, &info.info); } /* Called with rcu_read_lock() */ int fib_rules_dump(struct net *net, struct notifier_block *nb, int family, struct netlink_ext_ack *extack) { struct fib_rules_ops *ops; struct fib_rule *rule; int err = 0; ops = lookup_rules_ops(net, family); if (!ops) return -EAFNOSUPPORT; list_for_each_entry_rcu(rule, &ops->rules_list, list) { err = call_fib_rule_notifier(nb, FIB_EVENT_RULE_ADD, rule, family, extack); if (err) break; } rules_ops_put(ops); return err; } EXPORT_SYMBOL_GPL(fib_rules_dump); unsigned int fib_rules_seq_read(const struct net *net, int family) { unsigned int fib_rules_seq; struct fib_rules_ops *ops; ops = lookup_rules_ops(net, family); if (!ops) return 0; /* Paired with WRITE_ONCE() in call_fib_rule_notifiers() */ fib_rules_seq = READ_ONCE(ops->fib_rules_seq); rules_ops_put(ops); return fib_rules_seq; } EXPORT_SYMBOL_GPL(fib_rules_seq_read); static struct fib_rule *rule_find(struct fib_rules_ops *ops, struct fib_rule_hdr *frh, struct nlattr **tb, struct fib_rule *rule, bool user_priority) { struct fib_rule *r; list_for_each_entry(r, &ops->rules_list, list) { if (rule->action && r->action != rule->action) continue; if (rule->table && r->table != rule->table) continue; if (user_priority && r->pref != rule->pref) continue; if (rule->iifname[0] && memcmp(r->iifname, rule->iifname, IFNAMSIZ)) continue; if (rule->oifname[0] && memcmp(r->oifname, rule->oifname, IFNAMSIZ)) continue; if (rule->mark && r->mark != rule->mark) continue; if (rule->suppress_ifgroup != -1 && r->suppress_ifgroup != rule->suppress_ifgroup) continue; if (rule->suppress_prefixlen != -1 && r->suppress_prefixlen != rule->suppress_prefixlen) continue; if (rule->mark_mask && r->mark_mask != rule->mark_mask) continue; if (rule->tun_id && r->tun_id != rule->tun_id) continue; if (r->fr_net != rule->fr_net) continue; if (rule->l3mdev && r->l3mdev != rule->l3mdev) continue; if (uid_range_set(&rule->uid_range) && (!uid_eq(r->uid_range.start, rule->uid_range.start) || !uid_eq(r->uid_range.end, rule->uid_range.end))) continue; if (rule->ip_proto && r->ip_proto != rule->ip_proto) continue; if (rule->proto && r->proto != rule->proto) continue; if (fib_rule_port_range_set(&rule->sport_range) && !fib_rule_port_range_compare(&r->sport_range, &rule->sport_range)) continue; if (fib_rule_port_range_set(&rule->dport_range) && !fib_rule_port_range_compare(&r->dport_range, &rule->dport_range)) continue; if (!ops->compare(r, frh, tb)) continue; return r; } return NULL; } #ifdef CONFIG_NET_L3_MASTER_DEV static int fib_nl2rule_l3mdev(struct nlattr *nla, struct fib_rule *nlrule, struct netlink_ext_ack *extack) { nlrule->l3mdev = nla_get_u8(nla); if (nlrule->l3mdev != 1) { NL_SET_ERR_MSG(extack, "Invalid l3mdev attribute"); return -1; } return 0; } #else static int fib_nl2rule_l3mdev(struct nlattr *nla, struct fib_rule *nlrule, struct netlink_ext_ack *extack) { NL_SET_ERR_MSG(extack, "l3mdev support is not enabled in kernel"); return -1; } #endif static int fib_nl2rule(struct sk_buff *skb, struct nlmsghdr *nlh, struct netlink_ext_ack *extack, struct fib_rules_ops *ops, struct nlattr *tb[], struct fib_rule **rule, bool *user_priority) { struct net *net = sock_net(skb->sk); struct fib_rule_hdr *frh = nlmsg_data(nlh); struct fib_rule *nlrule = NULL; int err = -EINVAL; if (frh->src_len) if (!tb[FRA_SRC] || frh->src_len > (ops->addr_size * 8) || nla_len(tb[FRA_SRC]) != ops->addr_size) { NL_SET_ERR_MSG(extack, "Invalid source address"); goto errout; } if (frh->dst_len) if (!tb[FRA_DST] || frh->dst_len > (ops->addr_size * 8) || nla_len(tb[FRA_DST]) != ops->addr_size) { NL_SET_ERR_MSG(extack, "Invalid dst address"); goto errout; } nlrule = kzalloc(ops->rule_size, GFP_KERNEL_ACCOUNT); if (!nlrule) { err = -ENOMEM; goto errout; } refcount_set(&nlrule->refcnt, 1); nlrule->fr_net = net; if (tb[FRA_PRIORITY]) { nlrule->pref = nla_get_u32(tb[FRA_PRIORITY]); *user_priority = true; } else { nlrule->pref = fib_default_rule_pref(ops); } nlrule->proto = nla_get_u8_default(tb[FRA_PROTOCOL], RTPROT_UNSPEC); if (tb[FRA_IIFNAME]) { struct net_device *dev; nlrule->iifindex = -1; nla_strscpy(nlrule->iifname, tb[FRA_IIFNAME], IFNAMSIZ); dev = __dev_get_by_name(net, nlrule->iifname); if (dev) nlrule->iifindex = dev->ifindex; } if (tb[FRA_OIFNAME]) { struct net_device *dev; nlrule->oifindex = -1; nla_strscpy(nlrule->oifname, tb[FRA_OIFNAME], IFNAMSIZ); dev = __dev_get_by_name(net, nlrule->oifname); if (dev) nlrule->oifindex = dev->ifindex; } if (tb[FRA_FWMARK]) { nlrule->mark = nla_get_u32(tb[FRA_FWMARK]); if (nlrule->mark) /* compatibility: if the mark value is non-zero all bits * are compared unless a mask is explicitly specified. */ nlrule->mark_mask = 0xFFFFFFFF; } if (tb[FRA_FWMASK]) nlrule->mark_mask = nla_get_u32(tb[FRA_FWMASK]); if (tb[FRA_TUN_ID]) nlrule->tun_id = nla_get_be64(tb[FRA_TUN_ID]); if (tb[FRA_L3MDEV] && fib_nl2rule_l3mdev(tb[FRA_L3MDEV], nlrule, extack) < 0) goto errout_free; nlrule->action = frh->action; nlrule->flags = frh->flags; nlrule->table = frh_get_table(frh, tb); if (tb[FRA_SUPPRESS_PREFIXLEN]) nlrule->suppress_prefixlen = nla_get_u32(tb[FRA_SUPPRESS_PREFIXLEN]); else nlrule->suppress_prefixlen = -1; if (tb[FRA_SUPPRESS_IFGROUP]) nlrule->suppress_ifgroup = nla_get_u32(tb[FRA_SUPPRESS_IFGROUP]); else nlrule->suppress_ifgroup = -1; if (tb[FRA_GOTO]) { if (nlrule->action != FR_ACT_GOTO) { NL_SET_ERR_MSG(extack, "Unexpected goto"); goto errout_free; } nlrule->target = nla_get_u32(tb[FRA_GOTO]); /* Backward jumps are prohibited to avoid endless loops */ if (nlrule->target <= nlrule->pref) { NL_SET_ERR_MSG(extack, "Backward goto not supported"); goto errout_free; } } else if (nlrule->action == FR_ACT_GOTO) { NL_SET_ERR_MSG(extack, "Missing goto target for action goto"); goto errout_free; } if (nlrule->l3mdev && nlrule->table) { NL_SET_ERR_MSG(extack, "l3mdev and table are mutually exclusive"); goto errout_free; } if (tb[FRA_UID_RANGE]) { if (current_user_ns() != net->user_ns) { err = -EPERM; NL_SET_ERR_MSG(extack, "No permission to set uid"); goto errout_free; } nlrule->uid_range = nla_get_kuid_range(tb); if (!uid_range_set(&nlrule->uid_range) || !uid_lte(nlrule->uid_range.start, nlrule->uid_range.end)) { NL_SET_ERR_MSG(extack, "Invalid uid range"); goto errout_free; } } else { nlrule->uid_range = fib_kuid_range_unset; } if (tb[FRA_IP_PROTO]) nlrule->ip_proto = nla_get_u8(tb[FRA_IP_PROTO]); if (tb[FRA_SPORT_RANGE]) { err = nla_get_port_range(tb[FRA_SPORT_RANGE], &nlrule->sport_range); if (err) { NL_SET_ERR_MSG(extack, "Invalid sport range"); goto errout_free; } } if (tb[FRA_DPORT_RANGE]) { err = nla_get_port_range(tb[FRA_DPORT_RANGE], &nlrule->dport_range); if (err) { NL_SET_ERR_MSG(extack, "Invalid dport range"); goto errout_free; } } *rule = nlrule; return 0; errout_free: kfree(nlrule); errout: return err; } static int rule_exists(struct fib_rules_ops *ops, struct fib_rule_hdr *frh, struct nlattr **tb, struct fib_rule *rule) { struct fib_rule *r; list_for_each_entry(r, &ops->rules_list, list) { if (r->action != rule->action) continue; if (r->table != rule->table) continue; if (r->pref != rule->pref) continue; if (memcmp(r->iifname, rule->iifname, IFNAMSIZ)) continue; if (memcmp(r->oifname, rule->oifname, IFNAMSIZ)) continue; if (r->mark != rule->mark) continue; if (r->suppress_ifgroup != rule->suppress_ifgroup) continue; if (r->suppress_prefixlen != rule->suppress_prefixlen) continue; if (r->mark_mask != rule->mark_mask) continue; if (r->tun_id != rule->tun_id) continue; if (r->fr_net != rule->fr_net) continue; if (r->l3mdev != rule->l3mdev) continue; if (!uid_eq(r->uid_range.start, rule->uid_range.start) || !uid_eq(r->uid_range.end, rule->uid_range.end)) continue; if (r->ip_proto != rule->ip_proto) continue; if (r->proto != rule->proto) continue; if (!fib_rule_port_range_compare(&r->sport_range, &rule->sport_range)) continue; if (!fib_rule_port_range_compare(&r->dport_range, &rule->dport_range)) continue; if (!ops->compare(r, frh, tb)) continue; return 1; } return 0; } static const struct nla_policy fib_rule_policy[FRA_MAX + 1] = { [FRA_UNSPEC] = { .strict_start_type = FRA_DPORT_RANGE + 1 }, [FRA_IIFNAME] = { .type = NLA_STRING, .len = IFNAMSIZ - 1 }, [FRA_OIFNAME] = { .type = NLA_STRING, .len = IFNAMSIZ - 1 }, [FRA_PRIORITY] = { .type = NLA_U32 }, [FRA_FWMARK] = { .type = NLA_U32 }, [FRA_FLOW] = { .type = NLA_U32 }, [FRA_TUN_ID] = { .type = NLA_U64 }, [FRA_FWMASK] = { .type = NLA_U32 }, [FRA_TABLE] = { .type = NLA_U32 }, [FRA_SUPPRESS_PREFIXLEN] = { .type = NLA_U32 }, [FRA_SUPPRESS_IFGROUP] = { .type = NLA_U32 }, [FRA_GOTO] = { .type = NLA_U32 }, [FRA_L3MDEV] = { .type = NLA_U8 }, [FRA_UID_RANGE] = { .len = sizeof(struct fib_rule_uid_range) }, [FRA_PROTOCOL] = { .type = NLA_U8 }, [FRA_IP_PROTO] = { .type = NLA_U8 }, [FRA_SPORT_RANGE] = { .len = sizeof(struct fib_rule_port_range) }, [FRA_DPORT_RANGE] = { .len = sizeof(struct fib_rule_port_range) }, [FRA_DSCP] = NLA_POLICY_MAX(NLA_U8, INET_DSCP_MASK >> 2), }; int fib_nl_newrule(struct sk_buff *skb, struct nlmsghdr *nlh, struct netlink_ext_ack *extack) { struct net *net = sock_net(skb->sk); struct fib_rule_hdr *frh = nlmsg_data(nlh); struct fib_rules_ops *ops = NULL; struct fib_rule *rule = NULL, *r, *last = NULL; struct nlattr *tb[FRA_MAX + 1]; int err = -EINVAL, unresolved = 0; bool user_priority = false; if (nlh->nlmsg_len < nlmsg_msg_size(sizeof(*frh))) { NL_SET_ERR_MSG(extack, "Invalid msg length"); goto errout; } ops = lookup_rules_ops(net, frh->family); if (!ops) { err = -EAFNOSUPPORT; NL_SET_ERR_MSG(extack, "Rule family not supported"); goto errout; } err = nlmsg_parse_deprecated(nlh, sizeof(*frh), tb, FRA_MAX, fib_rule_policy, extack); if (err < 0) { NL_SET_ERR_MSG(extack, "Error parsing msg"); goto errout; } err = fib_nl2rule(skb, nlh, extack, ops, tb, &rule, &user_priority); if (err) goto errout; if ((nlh->nlmsg_flags & NLM_F_EXCL) && rule_exists(ops, frh, tb, rule)) { err = -EEXIST; goto errout_free; } err = ops->configure(rule, skb, frh, tb, extack); if (err < 0) goto errout_free; err = call_fib_rule_notifiers(net, FIB_EVENT_RULE_ADD, rule, ops, extack); if (err < 0) goto errout_free; list_for_each_entry(r, &ops->rules_list, list) { if (r->pref == rule->target) { RCU_INIT_POINTER(rule->ctarget, r); break; } } if (rcu_dereference_protected(rule->ctarget, 1) == NULL) unresolved = 1; list_for_each_entry(r, &ops->rules_list, list) { if (r->pref > rule->pref) break; last = r; } if (last) list_add_rcu(&rule->list, &last->list); else list_add_rcu(&rule->list, &ops->rules_list); if (ops->unresolved_rules) { /* * There are unresolved goto rules in the list, check if * any of them are pointing to this new rule. */ list_for_each_entry(r, &ops->rules_list, list) { if (r->action == FR_ACT_GOTO && r->target == rule->pref && rtnl_dereference(r->ctarget) == NULL) { rcu_assign_pointer(r->ctarget, rule); if (--ops->unresolved_rules == 0) break; } } } if (rule->action == FR_ACT_GOTO) ops->nr_goto_rules++; if (unresolved) ops->unresolved_rules++; if (rule->tun_id) ip_tunnel_need_metadata(); notify_rule_change(RTM_NEWRULE, rule, ops, nlh, NETLINK_CB(skb).portid); flush_route_cache(ops); rules_ops_put(ops); return 0; errout_free: kfree(rule); errout: rules_ops_put(ops); return err; } EXPORT_SYMBOL_GPL(fib_nl_newrule); int fib_nl_delrule(struct sk_buff *skb, struct nlmsghdr *nlh, struct netlink_ext_ack *extack) { struct net *net = sock_net(skb->sk); struct fib_rule_hdr *frh = nlmsg_data(nlh); struct fib_rules_ops *ops = NULL; struct fib_rule *rule = NULL, *r, *nlrule = NULL; struct nlattr *tb[FRA_MAX+1]; int err = -EINVAL; bool user_priority = false; if (nlh->nlmsg_len < nlmsg_msg_size(sizeof(*frh))) { NL_SET_ERR_MSG(extack, "Invalid msg length"); goto errout; } ops = lookup_rules_ops(net, frh->family); if (ops == NULL) { err = -EAFNOSUPPORT; NL_SET_ERR_MSG(extack, "Rule family not supported"); goto errout; } err = nlmsg_parse_deprecated(nlh, sizeof(*frh), tb, FRA_MAX, fib_rule_policy, extack); if (err < 0) { NL_SET_ERR_MSG(extack, "Error parsing msg"); goto errout; } err = fib_nl2rule(skb, nlh, extack, ops, tb, &nlrule, &user_priority); if (err) goto errout; rule = rule_find(ops, frh, tb, nlrule, user_priority); if (!rule) { err = -ENOENT; goto errout; } if (rule->flags & FIB_RULE_PERMANENT) { err = -EPERM; goto errout; } if (ops->delete) { err = ops->delete(rule); if (err) goto errout; } if (rule->tun_id) ip_tunnel_unneed_metadata(); list_del_rcu(&rule->list); if (rule->action == FR_ACT_GOTO) { ops->nr_goto_rules--; if (rtnl_dereference(rule->ctarget) == NULL) ops->unresolved_rules--; } /* * Check if this rule is a target to any of them. If so, * adjust to the next one with the same preference or * disable them. As this operation is eventually very * expensive, it is only performed if goto rules, except * current if it is goto rule, have actually been added. */ if (ops->nr_goto_rules > 0) { struct fib_rule *n; n = list_next_entry(rule, list); if (&n->list == &ops->rules_list || n->pref != rule->pref) n = NULL; list_for_each_entry(r, &ops->rules_list, list) { if (rtnl_dereference(r->ctarget) != rule) continue; rcu_assign_pointer(r->ctarget, n); if (!n) ops->unresolved_rules++; } } call_fib_rule_notifiers(net, FIB_EVENT_RULE_DEL, rule, ops, NULL); notify_rule_change(RTM_DELRULE, rule, ops, nlh, NETLINK_CB(skb).portid); fib_rule_put(rule); flush_route_cache(ops); rules_ops_put(ops); kfree(nlrule); return 0; errout: kfree(nlrule); rules_ops_put(ops); return err; } EXPORT_SYMBOL_GPL(fib_nl_delrule); static inline size_t fib_rule_nlmsg_size(struct fib_rules_ops *ops, struct fib_rule *rule) { size_t payload = NLMSG_ALIGN(sizeof(struct fib_rule_hdr)) + nla_total_size(IFNAMSIZ) /* FRA_IIFNAME */ + nla_total_size(IFNAMSIZ) /* FRA_OIFNAME */ + nla_total_size(4) /* FRA_PRIORITY */ + nla_total_size(4) /* FRA_TABLE */ + nla_total_size(4) /* FRA_SUPPRESS_PREFIXLEN */ + nla_total_size(4) /* FRA_SUPPRESS_IFGROUP */ + nla_total_size(4) /* FRA_FWMARK */ + nla_total_size(4) /* FRA_FWMASK */ + nla_total_size_64bit(8) /* FRA_TUN_ID */ + nla_total_size(sizeof(struct fib_kuid_range)) + nla_total_size(1) /* FRA_PROTOCOL */ + nla_total_size(1) /* FRA_IP_PROTO */ + nla_total_size(sizeof(struct fib_rule_port_range)) /* FRA_SPORT_RANGE */ + nla_total_size(sizeof(struct fib_rule_port_range)); /* FRA_DPORT_RANGE */ if (ops->nlmsg_payload) payload += ops->nlmsg_payload(rule); return payload; } static int fib_nl_fill_rule(struct sk_buff *skb, struct fib_rule *rule, u32 pid, u32 seq, int type, int flags, struct fib_rules_ops *ops) { struct nlmsghdr *nlh; struct fib_rule_hdr *frh; nlh = nlmsg_put(skb, pid, seq, type, sizeof(*frh), flags); if (nlh == NULL) return -EMSGSIZE; frh = nlmsg_data(nlh); frh->family = ops->family; frh->table = rule->table < 256 ? rule->table : RT_TABLE_COMPAT; if (nla_put_u32(skb, FRA_TABLE, rule->table)) goto nla_put_failure; if (nla_put_u32(skb, FRA_SUPPRESS_PREFIXLEN, rule->suppress_prefixlen)) goto nla_put_failure; frh->res1 = 0; frh->res2 = 0; frh->action = rule->action; frh->flags = rule->flags; if (nla_put_u8(skb, FRA_PROTOCOL, rule->proto)) goto nla_put_failure; if (rule->action == FR_ACT_GOTO && rcu_access_pointer(rule->ctarget) == NULL) frh->flags |= FIB_RULE_UNRESOLVED; if (rule->iifname[0]) { if (nla_put_string(skb, FRA_IIFNAME, rule->iifname)) goto nla_put_failure; if (rule->iifindex == -1) frh->flags |= FIB_RULE_IIF_DETACHED; } if (rule->oifname[0]) { if (nla_put_string(skb, FRA_OIFNAME, rule->oifname)) goto nla_put_failure; if (rule->oifindex == -1) frh->flags |= FIB_RULE_OIF_DETACHED; } if ((rule->pref && nla_put_u32(skb, FRA_PRIORITY, rule->pref)) || (rule->mark && nla_put_u32(skb, FRA_FWMARK, rule->mark)) || ((rule->mark_mask || rule->mark) && nla_put_u32(skb, FRA_FWMASK, rule->mark_mask)) || (rule->target && nla_put_u32(skb, FRA_GOTO, rule->target)) || (rule->tun_id && nla_put_be64(skb, FRA_TUN_ID, rule->tun_id, FRA_PAD)) || (rule->l3mdev && nla_put_u8(skb, FRA_L3MDEV, rule->l3mdev)) || (uid_range_set(&rule->uid_range) && nla_put_uid_range(skb, &rule->uid_range)) || (fib_rule_port_range_set(&rule->sport_range) && nla_put_port_range(skb, FRA_SPORT_RANGE, &rule->sport_range)) || (fib_rule_port_range_set(&rule->dport_range) && nla_put_port_range(skb, FRA_DPORT_RANGE, &rule->dport_range)) || (rule->ip_proto && nla_put_u8(skb, FRA_IP_PROTO, rule->ip_proto))) goto nla_put_failure; if (rule->suppress_ifgroup != -1) { if (nla_put_u32(skb, FRA_SUPPRESS_IFGROUP, rule->suppress_ifgroup)) goto nla_put_failure; } if (ops->fill(rule, skb, frh) < 0) goto nla_put_failure; nlmsg_end(skb, nlh); return 0; nla_put_failure: nlmsg_cancel(skb, nlh); return -EMSGSIZE; } static int dump_rules(struct sk_buff *skb, struct netlink_callback *cb, struct fib_rules_ops *ops) { int idx = 0; struct fib_rule *rule; int err = 0; rcu_read_lock(); list_for_each_entry_rcu(rule, &ops->rules_list, list) { if (idx < cb->args[1]) goto skip; err = fib_nl_fill_rule(skb, rule, NETLINK_CB(cb->skb).portid, cb->nlh->nlmsg_seq, RTM_NEWRULE, NLM_F_MULTI, ops); if (err) break; skip: idx++; } rcu_read_unlock(); cb->args[1] = idx; rules_ops_put(ops); return err; } static int fib_valid_dumprule_req(const struct nlmsghdr *nlh, struct netlink_ext_ack *extack) { struct fib_rule_hdr *frh; if (nlh->nlmsg_len < nlmsg_msg_size(sizeof(*frh))) { NL_SET_ERR_MSG(extack, "Invalid header for fib rule dump request"); return -EINVAL; } frh = nlmsg_data(nlh); if (frh->dst_len || frh->src_len || frh->tos || frh->table || frh->res1 || frh->res2 || frh->action || frh->flags) { NL_SET_ERR_MSG(extack, "Invalid values in header for fib rule dump request"); return -EINVAL; } if (nlmsg_attrlen(nlh, sizeof(*frh))) { NL_SET_ERR_MSG(extack, "Invalid data after header in fib rule dump request"); return -EINVAL; } return 0; } static int fib_nl_dumprule(struct sk_buff *skb, struct netlink_callback *cb) { const struct nlmsghdr *nlh = cb->nlh; struct net *net = sock_net(skb->sk); struct fib_rules_ops *ops; int err, idx = 0, family; if (cb->strict_check) { err = fib_valid_dumprule_req(nlh, cb->extack); if (err < 0) return err; } family = rtnl_msg_family(nlh); if (family != AF_UNSPEC) { /* Protocol specific dump request */ ops = lookup_rules_ops(net, family); if (ops == NULL) return -EAFNOSUPPORT; return dump_rules(skb, cb, ops); } err = 0; rcu_read_lock(); list_for_each_entry_rcu(ops, &net->rules_ops, list) { if (idx < cb->args[0] || !try_module_get(ops->owner)) goto skip; err = dump_rules(skb, cb, ops); if (err < 0) break; cb->args[1] = 0; skip: idx++; } rcu_read_unlock(); cb->args[0] = idx; return err; } static void notify_rule_change(int event, struct fib_rule *rule, struct fib_rules_ops *ops, struct nlmsghdr *nlh, u32 pid) { struct net *net; struct sk_buff *skb; int err = -ENOMEM; net = ops->fro_net; skb = nlmsg_new(fib_rule_nlmsg_size(ops, rule), GFP_KERNEL); if (skb == NULL) goto errout; err = fib_nl_fill_rule(skb, rule, pid, nlh->nlmsg_seq, event, 0, ops); if (err < 0) { /* -EMSGSIZE implies BUG in fib_rule_nlmsg_size() */ WARN_ON(err == -EMSGSIZE); kfree_skb(skb); goto errout; } rtnl_notify(skb, net, pid, ops->nlgroup, nlh, GFP_KERNEL); return; errout: rtnl_set_sk_err(net, ops->nlgroup, err); } static void attach_rules(struct list_head *rules, struct net_device *dev) { struct fib_rule *rule; list_for_each_entry(rule, rules, list) { if (rule->iifindex == -1 && strcmp(dev->name, rule->iifname) == 0) rule->iifindex = dev->ifindex; if (rule->oifindex == -1 && strcmp(dev->name, rule->oifname) == 0) rule->oifindex = dev->ifindex; } } static void detach_rules(struct list_head *rules, struct net_device *dev) { struct fib_rule *rule; list_for_each_entry(rule, rules, list) { if (rule->iifindex == dev->ifindex) rule->iifindex = -1; if (rule->oifindex == dev->ifindex) rule->oifindex = -1; } } static int fib_rules_event(struct notifier_block *this, unsigned long event, void *ptr) { struct net_device *dev = netdev_notifier_info_to_dev(ptr); struct net *net = dev_net(dev); struct fib_rules_ops *ops; ASSERT_RTNL(); switch (event) { case NETDEV_REGISTER: list_for_each_entry(ops, &net->rules_ops, list) attach_rules(&ops->rules_list, dev); break; case NETDEV_CHANGENAME: list_for_each_entry(ops, &net->rules_ops, list) { detach_rules(&ops->rules_list, dev); attach_rules(&ops->rules_list, dev); } break; case NETDEV_UNREGISTER: list_for_each_entry(ops, &net->rules_ops, list) detach_rules(&ops->rules_list, dev); break; } return NOTIFY_DONE; } static struct notifier_block fib_rules_notifier = { .notifier_call = fib_rules_event, }; static int __net_init fib_rules_net_init(struct net *net) { INIT_LIST_HEAD(&net->rules_ops); spin_lock_init(&net->rules_mod_lock); return 0; } static void __net_exit fib_rules_net_exit(struct net *net) { WARN_ON_ONCE(!list_empty(&net->rules_ops)); } static struct pernet_operations fib_rules_net_ops = { .init = fib_rules_net_init, .exit = fib_rules_net_exit, }; static const struct rtnl_msg_handler fib_rules_rtnl_msg_handlers[] __initconst = { {.msgtype = RTM_NEWRULE, .doit = fib_nl_newrule}, {.msgtype = RTM_DELRULE, .doit = fib_nl_delrule}, {.msgtype = RTM_GETRULE, .dumpit = fib_nl_dumprule, .flags = RTNL_FLAG_DUMP_UNLOCKED}, }; static int __init fib_rules_init(void) { int err; rtnl_register_many(fib_rules_rtnl_msg_handlers); err = register_pernet_subsys(&fib_rules_net_ops); if (err < 0) goto fail; err = register_netdevice_notifier(&fib_rules_notifier); if (err < 0) goto fail_unregister; return 0; fail_unregister: unregister_pernet_subsys(&fib_rules_net_ops); fail: rtnl_unregister_many(fib_rules_rtnl_msg_handlers); return err; } subsys_initcall(fib_rules_init); |
| 3 3 3 3 3 3 3 3 3 3 3 3 3 3 3 3 3 3 3 3 3 3 3 3 3 3 3 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 1522 1523 1524 1525 1526 1527 1528 1529 1530 1531 1532 1533 1534 1535 1536 1537 1538 1539 1540 1541 1542 1543 1544 1545 1546 1547 1548 1549 1550 1551 1552 1553 1554 1555 1556 1557 1558 1559 1560 1561 1562 1563 1564 1565 1566 1567 1568 1569 1570 1571 1572 1573 1574 1575 1576 1577 1578 1579 1580 1581 1582 1583 1584 1585 1586 1587 1588 1589 1590 1591 1592 1593 1594 1595 1596 1597 1598 1599 1600 1601 1602 1603 1604 1605 1606 1607 1608 1609 1610 1611 1612 1613 1614 1615 1616 1617 1618 1619 1620 1621 1622 1623 1624 1625 1626 1627 1628 1629 1630 1631 1632 1633 1634 1635 1636 1637 1638 1639 1640 1641 1642 1643 1644 1645 1646 1647 1648 1649 1650 1651 1652 1653 1654 1655 1656 1657 1658 1659 1660 1661 1662 1663 1664 1665 1666 1667 1668 1669 1670 1671 1672 1673 1674 1675 1676 1677 1678 1679 1680 1681 1682 1683 1684 1685 1686 1687 1688 1689 1690 1691 1692 1693 1694 1695 1696 1697 1698 1699 1700 1701 1702 1703 1704 1705 1706 1707 1708 1709 1710 1711 1712 1713 1714 1715 1716 1717 1718 1719 1720 1721 1722 1723 1724 1725 1726 1727 1728 1729 1730 1731 1732 1733 1734 1735 1736 1737 1738 1739 1740 1741 1742 1743 1744 1745 1746 1747 1748 1749 1750 1751 1752 1753 1754 1755 1756 1757 1758 1759 1760 1761 1762 1763 1764 1765 1766 1767 1768 1769 1770 1771 1772 1773 1774 1775 1776 1777 1778 1779 1780 1781 1782 1783 1784 1785 1786 1787 1788 1789 1790 1791 1792 1793 1794 1795 1796 1797 1798 1799 1800 1801 1802 1803 1804 1805 1806 1807 1808 1809 1810 1811 1812 1813 1814 1815 1816 1817 1818 1819 1820 1821 1822 1823 1824 1825 1826 1827 1828 1829 1830 1831 1832 1833 1834 1835 1836 1837 1838 1839 1840 1841 1842 1843 1844 1845 1846 1847 1848 1849 1850 1851 1852 1853 1854 1855 1856 1857 1858 1859 1860 1861 1862 1863 1864 1865 1866 1867 1868 1869 1870 1871 1872 1873 1874 1875 1876 1877 1878 1879 1880 1881 1882 1883 1884 1885 1886 1887 1888 1889 1890 1891 1892 1893 1894 1895 1896 1897 1898 1899 1900 1901 1902 1903 1904 1905 1906 1907 1908 1909 1910 1911 1912 1913 1914 1915 1916 1917 1918 1919 1920 1921 1922 1923 1924 1925 1926 1927 1928 1929 1930 1931 1932 1933 1934 1935 1936 1937 1938 1939 1940 1941 1942 1943 1944 1945 1946 1947 1948 1949 1950 1951 1952 1953 1954 1955 1956 1957 1958 1959 1960 1961 1962 1963 1964 1965 1966 1967 1968 1969 1970 1971 1972 1973 1974 1975 1976 1977 1978 1979 1980 1981 1982 1983 1984 1985 1986 1987 1988 1989 1990 1991 1992 1993 1994 1995 1996 1997 1998 1999 2000 2001 2002 2003 2004 2005 2006 2007 2008 2009 2010 2011 2012 2013 2014 2015 2016 2017 2018 2019 2020 2021 2022 2023 2024 2025 2026 2027 2028 2029 2030 2031 2032 2033 2034 2035 2036 2037 2038 2039 2040 2041 2042 2043 2044 2045 2046 2047 2048 2049 2050 2051 2052 2053 2054 2055 2056 2057 2058 2059 2060 2061 2062 2063 2064 2065 2066 2067 2068 2069 2070 2071 2072 2073 2074 2075 2076 2077 2078 2079 2080 2081 2082 2083 2084 2085 2086 2087 2088 2089 2090 2091 2092 2093 2094 2095 2096 2097 2098 2099 2100 2101 2102 2103 2104 2105 2106 2107 2108 2109 2110 2111 2112 2113 2114 2115 2116 2117 2118 2119 2120 2121 2122 2123 2124 2125 2126 2127 2128 2129 2130 2131 2132 2133 2134 2135 2136 2137 2138 2139 2140 2141 2142 2143 2144 2145 2146 2147 2148 2149 2150 2151 2152 2153 2154 2155 2156 2157 2158 2159 2160 2161 2162 2163 2164 2165 2166 2167 2168 2169 2170 2171 2172 2173 2174 2175 2176 2177 2178 2179 2180 2181 2182 2183 2184 2185 2186 2187 2188 2189 2190 2191 2192 2193 2194 2195 2196 2197 2198 2199 2200 2201 2202 2203 2204 2205 2206 2207 2208 2209 2210 2211 2212 2213 2214 2215 2216 2217 2218 2219 2220 2221 2222 2223 2224 2225 2226 2227 2228 2229 2230 2231 2232 2233 2234 2235 2236 2237 2238 2239 2240 2241 2242 2243 2244 2245 2246 2247 2248 2249 2250 2251 2252 2253 2254 2255 2256 2257 2258 2259 2260 2261 2262 2263 2264 2265 2266 2267 2268 2269 2270 2271 2272 2273 2274 2275 2276 2277 2278 2279 2280 2281 2282 2283 2284 2285 2286 2287 2288 2289 2290 2291 2292 2293 2294 2295 2296 2297 2298 2299 2300 2301 2302 2303 2304 2305 2306 2307 2308 2309 2310 2311 2312 2313 2314 2315 2316 2317 2318 2319 2320 2321 2322 2323 2324 2325 2326 2327 2328 2329 2330 2331 2332 2333 2334 2335 2336 2337 2338 2339 2340 2341 2342 2343 2344 2345 2346 2347 2348 2349 2350 2351 2352 2353 2354 2355 2356 2357 2358 2359 2360 2361 2362 2363 2364 2365 2366 2367 2368 2369 2370 2371 2372 2373 2374 2375 2376 2377 2378 2379 2380 2381 2382 2383 2384 2385 2386 2387 2388 2389 2390 2391 2392 2393 2394 2395 2396 2397 2398 2399 2400 2401 2402 2403 2404 2405 2406 2407 2408 2409 2410 2411 2412 2413 2414 2415 2416 2417 2418 2419 2420 2421 2422 2423 2424 2425 2426 2427 2428 2429 2430 2431 2432 2433 2434 2435 2436 2437 2438 2439 2440 2441 2442 2443 2444 2445 2446 2447 2448 2449 2450 2451 2452 2453 2454 2455 2456 2457 2458 2459 2460 2461 2462 2463 2464 2465 2466 2467 2468 2469 2470 2471 2472 2473 2474 2475 2476 2477 2478 2479 2480 2481 2482 2483 2484 2485 2486 2487 2488 2489 2490 2491 2492 2493 2494 2495 2496 2497 2498 2499 2500 2501 2502 2503 2504 2505 2506 2507 2508 2509 2510 2511 2512 2513 2514 2515 2516 2517 2518 2519 2520 2521 2522 2523 2524 2525 2526 2527 2528 2529 2530 2531 2532 2533 2534 2535 2536 2537 2538 2539 2540 2541 2542 2543 2544 2545 2546 2547 2548 2549 2550 2551 2552 2553 2554 2555 2556 2557 2558 2559 2560 2561 2562 2563 2564 2565 2566 2567 2568 2569 2570 2571 2572 2573 2574 2575 2576 2577 2578 2579 2580 2581 2582 2583 2584 2585 2586 2587 2588 2589 2590 2591 2592 2593 2594 2595 2596 2597 2598 2599 2600 2601 2602 2603 2604 2605 2606 2607 2608 2609 2610 2611 2612 2613 2614 2615 2616 2617 2618 2619 2620 2621 2622 2623 2624 2625 2626 2627 2628 2629 2630 2631 2632 2633 2634 2635 2636 2637 2638 2639 2640 2641 2642 2643 2644 2645 2646 2647 2648 2649 2650 2651 2652 2653 2654 2655 2656 2657 2658 2659 2660 2661 2662 2663 2664 2665 2666 2667 2668 2669 2670 2671 2672 2673 2674 2675 2676 2677 2678 2679 2680 2681 2682 2683 2684 2685 2686 2687 2688 2689 2690 2691 2692 2693 2694 2695 2696 2697 2698 2699 2700 2701 2702 2703 2704 2705 2706 2707 2708 2709 2710 2711 2712 2713 2714 2715 2716 2717 2718 2719 2720 2721 2722 2723 2724 2725 2726 2727 2728 2729 2730 2731 2732 2733 2734 2735 2736 2737 2738 2739 2740 2741 2742 2743 2744 2745 2746 2747 2748 2749 2750 2751 2752 2753 2754 2755 2756 2757 2758 2759 2760 2761 2762 2763 2764 2765 2766 2767 2768 2769 2770 2771 2772 2773 2774 2775 2776 2777 2778 2779 2780 2781 2782 2783 2784 2785 2786 2787 2788 2789 2790 2791 2792 2793 2794 2795 2796 2797 2798 2799 2800 2801 2802 2803 2804 2805 2806 2807 2808 2809 2810 2811 2812 2813 2814 2815 2816 2817 2818 2819 2820 2821 2822 2823 2824 2825 2826 2827 2828 2829 2830 2831 2832 2833 2834 2835 2836 2837 2838 2839 2840 2841 2842 2843 2844 2845 2846 2847 2848 2849 2850 2851 2852 2853 2854 2855 2856 2857 2858 2859 2860 2861 2862 2863 2864 2865 2866 2867 2868 2869 2870 2871 2872 2873 2874 2875 2876 2877 2878 2879 2880 2881 2882 2883 2884 2885 2886 2887 2888 2889 2890 2891 2892 2893 2894 2895 2896 2897 2898 2899 2900 2901 2902 2903 2904 2905 2906 2907 2908 2909 2910 2911 2912 2913 2914 2915 2916 2917 2918 2919 2920 2921 2922 2923 2924 2925 2926 2927 2928 2929 2930 2931 2932 2933 2934 2935 2936 2937 2938 2939 2940 2941 2942 2943 2944 2945 2946 2947 2948 2949 2950 2951 2952 2953 2954 2955 2956 2957 2958 2959 2960 2961 2962 2963 2964 2965 2966 2967 2968 2969 2970 2971 2972 2973 2974 2975 2976 2977 2978 2979 2980 2981 2982 2983 2984 2985 2986 2987 2988 2989 2990 2991 2992 2993 2994 2995 2996 2997 2998 2999 3000 3001 3002 3003 3004 3005 3006 3007 3008 3009 3010 3011 3012 3013 3014 3015 3016 3017 3018 3019 3020 3021 3022 3023 3024 3025 3026 3027 3028 3029 3030 3031 3032 3033 3034 3035 3036 3037 3038 3039 3040 3041 3042 3043 3044 3045 3046 3047 3048 3049 3050 3051 3052 3053 3054 3055 3056 3057 3058 3059 3060 3061 3062 3063 3064 3065 3066 3067 3068 3069 3070 3071 3072 3073 3074 3075 3076 3077 3078 3079 3080 3081 3082 3083 3084 3085 3086 3087 3088 3089 3090 3091 3092 3093 3094 3095 3096 3097 3098 3099 3100 3101 3102 3103 3104 3105 3106 3107 3108 3109 3110 3111 3112 3113 3114 3115 3116 3117 3118 3119 3120 3121 3122 3123 3124 3125 3126 3127 3128 3129 3130 3131 3132 3133 3134 3135 3136 3137 3138 3139 3140 3141 3142 3143 3144 3145 3146 3147 3148 3149 3150 3151 3152 3153 3154 3155 3156 3157 3158 3159 3160 3161 3162 3163 3164 3165 3166 3167 3168 3169 3170 3171 3172 3173 3174 3175 3176 3177 3178 3179 3180 3181 3182 3183 3184 3185 3186 3187 3188 3189 3190 3191 3192 3193 3194 3195 3196 3197 3198 3199 3200 3201 3202 3203 3204 3205 3206 3207 | // SPDX-License-Identifier: GPL-2.0-or-later /* * Multicast support for IPv6 * Linux INET6 implementation * * Authors: * Pedro Roque <roque@di.fc.ul.pt> * * Based on linux/ipv4/igmp.c and linux/ipv4/ip_sockglue.c */ /* Changes: * * yoshfuji : fix format of router-alert option * YOSHIFUJI Hideaki @USAGI: * Fixed source address for MLD message based on * <draft-ietf-magma-mld-source-05.txt>. * YOSHIFUJI Hideaki @USAGI: * - Ignore Queries for invalid addresses. * - MLD for link-local addresses. * David L Stevens <dlstevens@us.ibm.com>: * - MLDv2 support */ #include <linux/module.h> #include <linux/errno.h> #include <linux/types.h> #include <linux/string.h> #include <linux/socket.h> #include <linux/sockios.h> #include <linux/jiffies.h> #include <linux/net.h> #include <linux/in.h> #include <linux/in6.h> #include <linux/netdevice.h> #include <linux/if_arp.h> #include <linux/route.h> #include <linux/init.h> #include <linux/proc_fs.h> #include <linux/seq_file.h> #include <linux/slab.h> #include <linux/pkt_sched.h> #include <net/mld.h> #include <linux/workqueue.h> #include <linux/netfilter.h> #include <linux/netfilter_ipv6.h> #include <net/net_namespace.h> #include <net/sock.h> #include <net/snmp.h> #include <net/ipv6.h> #include <net/protocol.h> #include <net/if_inet6.h> #include <net/ndisc.h> #include <net/addrconf.h> #include <net/ip6_route.h> #include <net/inet_common.h> #include <net/ip6_checksum.h> /* Ensure that we have struct in6_addr aligned on 32bit word. */ static int __mld2_query_bugs[] __attribute__((__unused__)) = { BUILD_BUG_ON_ZERO(offsetof(struct mld2_query, mld2q_srcs) % 4), BUILD_BUG_ON_ZERO(offsetof(struct mld2_report, mld2r_grec) % 4), BUILD_BUG_ON_ZERO(offsetof(struct mld2_grec, grec_mca) % 4) }; static struct workqueue_struct *mld_wq; static struct in6_addr mld2_all_mcr = MLD2_ALL_MCR_INIT; static void igmp6_join_group(struct ifmcaddr6 *ma); static void igmp6_leave_group(struct ifmcaddr6 *ma); static void mld_mca_work(struct work_struct *work); static void mld_ifc_event(struct inet6_dev *idev); static bool mld_in_v1_mode(const struct inet6_dev *idev); static int sf_setstate(struct ifmcaddr6 *pmc); static void sf_markstate(struct ifmcaddr6 *pmc); static void ip6_mc_clear_src(struct ifmcaddr6 *pmc); static int ip6_mc_del_src(struct inet6_dev *idev, const struct in6_addr *pmca, int sfmode, int sfcount, const struct in6_addr *psfsrc, int delta); static int ip6_mc_add_src(struct inet6_dev *idev, const struct in6_addr *pmca, int sfmode, int sfcount, const struct in6_addr *psfsrc, int delta); static int ip6_mc_leave_src(struct sock *sk, struct ipv6_mc_socklist *iml, struct inet6_dev *idev); static int __ipv6_dev_mc_inc(struct net_device *dev, const struct in6_addr *addr, unsigned int mode); #define MLD_QRV_DEFAULT 2 /* RFC3810, 9.2. Query Interval */ #define MLD_QI_DEFAULT (125 * HZ) /* RFC3810, 9.3. Query Response Interval */ #define MLD_QRI_DEFAULT (10 * HZ) /* RFC3810, 8.1 Query Version Distinctions */ #define MLD_V1_QUERY_LEN 24 #define MLD_V2_QUERY_LEN_MIN 28 #define IPV6_MLD_MAX_MSF 64 int sysctl_mld_max_msf __read_mostly = IPV6_MLD_MAX_MSF; int sysctl_mld_qrv __read_mostly = MLD_QRV_DEFAULT; /* * socket join on multicast group */ #define mc_dereference(e, idev) \ rcu_dereference_protected(e, lockdep_is_held(&(idev)->mc_lock)) #define sock_dereference(e, sk) \ rcu_dereference_protected(e, lockdep_sock_is_held(sk)) #define for_each_pmc_socklock(np, sk, pmc) \ for (pmc = sock_dereference((np)->ipv6_mc_list, sk); \ pmc; \ pmc = sock_dereference(pmc->next, sk)) #define for_each_pmc_rcu(np, pmc) \ for (pmc = rcu_dereference((np)->ipv6_mc_list); \ pmc; \ pmc = rcu_dereference(pmc->next)) #define for_each_psf_mclock(mc, psf) \ for (psf = mc_dereference((mc)->mca_sources, mc->idev); \ psf; \ psf = mc_dereference(psf->sf_next, mc->idev)) #define for_each_psf_rcu(mc, psf) \ for (psf = rcu_dereference((mc)->mca_sources); \ psf; \ psf = rcu_dereference(psf->sf_next)) #define for_each_psf_tomb(mc, psf) \ for (psf = mc_dereference((mc)->mca_tomb, mc->idev); \ psf; \ psf = mc_dereference(psf->sf_next, mc->idev)) #define for_each_mc_mclock(idev, mc) \ for (mc = mc_dereference((idev)->mc_list, idev); \ mc; \ mc = mc_dereference(mc->next, idev)) #define for_each_mc_rcu(idev, mc) \ for (mc = rcu_dereference((idev)->mc_list); \ mc; \ mc = rcu_dereference(mc->next)) #define for_each_mc_tomb(idev, mc) \ for (mc = mc_dereference((idev)->mc_tomb, idev); \ mc; \ mc = mc_dereference(mc->next, idev)) static int unsolicited_report_interval(struct inet6_dev *idev) { int iv; if (mld_in_v1_mode(idev)) iv = READ_ONCE(idev->cnf.mldv1_unsolicited_report_interval); else iv = READ_ONCE(idev->cnf.mldv2_unsolicited_report_interval); return iv > 0 ? iv : 1; } static int __ipv6_sock_mc_join(struct sock *sk, int ifindex, const struct in6_addr *addr, unsigned int mode) { struct net_device *dev = NULL; struct ipv6_mc_socklist *mc_lst; struct ipv6_pinfo *np = inet6_sk(sk); struct net *net = sock_net(sk); int err; ASSERT_RTNL(); if (!ipv6_addr_is_multicast(addr)) return -EINVAL; for_each_pmc_socklock(np, sk, mc_lst) { if ((ifindex == 0 || mc_lst->ifindex == ifindex) && ipv6_addr_equal(&mc_lst->addr, addr)) return -EADDRINUSE; } mc_lst = sock_kmalloc(sk, sizeof(struct ipv6_mc_socklist), GFP_KERNEL); if (!mc_lst) return -ENOMEM; mc_lst->next = NULL; mc_lst->addr = *addr; if (ifindex == 0) { struct rt6_info *rt; rt = rt6_lookup(net, addr, NULL, 0, NULL, 0); if (rt) { dev = rt->dst.dev; ip6_rt_put(rt); } } else dev = __dev_get_by_index(net, ifindex); if (!dev) { sock_kfree_s(sk, mc_lst, sizeof(*mc_lst)); return -ENODEV; } mc_lst->ifindex = dev->ifindex; mc_lst->sfmode = mode; RCU_INIT_POINTER(mc_lst->sflist, NULL); /* * now add/increase the group membership on the device */ err = __ipv6_dev_mc_inc(dev, addr, mode); if (err) { sock_kfree_s(sk, mc_lst, sizeof(*mc_lst)); return err; } mc_lst->next = np->ipv6_mc_list; rcu_assign_pointer(np->ipv6_mc_list, mc_lst); return 0; } int ipv6_sock_mc_join(struct sock *sk, int ifindex, const struct in6_addr *addr) { return __ipv6_sock_mc_join(sk, ifindex, addr, MCAST_EXCLUDE); } EXPORT_SYMBOL(ipv6_sock_mc_join); int ipv6_sock_mc_join_ssm(struct sock *sk, int ifindex, const struct in6_addr *addr, unsigned int mode) { return __ipv6_sock_mc_join(sk, ifindex, addr, mode); } /* * socket leave on multicast group */ int ipv6_sock_mc_drop(struct sock *sk, int ifindex, const struct in6_addr *addr) { struct ipv6_pinfo *np = inet6_sk(sk); struct ipv6_mc_socklist *mc_lst; struct ipv6_mc_socklist __rcu **lnk; struct net *net = sock_net(sk); ASSERT_RTNL(); if (!ipv6_addr_is_multicast(addr)) return -EINVAL; for (lnk = &np->ipv6_mc_list; (mc_lst = sock_dereference(*lnk, sk)) != NULL; lnk = &mc_lst->next) { if ((ifindex == 0 || mc_lst->ifindex == ifindex) && ipv6_addr_equal(&mc_lst->addr, addr)) { struct net_device *dev; *lnk = mc_lst->next; dev = __dev_get_by_index(net, mc_lst->ifindex); if (dev) { struct inet6_dev *idev = __in6_dev_get(dev); ip6_mc_leave_src(sk, mc_lst, idev); if (idev) __ipv6_dev_mc_dec(idev, &mc_lst->addr); } else { ip6_mc_leave_src(sk, mc_lst, NULL); } atomic_sub(sizeof(*mc_lst), &sk->sk_omem_alloc); kfree_rcu(mc_lst, rcu); return 0; } } return -EADDRNOTAVAIL; } EXPORT_SYMBOL(ipv6_sock_mc_drop); static struct inet6_dev *ip6_mc_find_dev_rtnl(struct net *net, const struct in6_addr *group, int ifindex) { struct net_device *dev = NULL; struct inet6_dev *idev = NULL; if (ifindex == 0) { struct rt6_info *rt = rt6_lookup(net, group, NULL, 0, NULL, 0); if (rt) { dev = rt->dst.dev; ip6_rt_put(rt); } } else { dev = __dev_get_by_index(net, ifindex); } if (!dev) return NULL; idev = __in6_dev_get(dev); if (!idev) return NULL; if (idev->dead) return NULL; return idev; } void __ipv6_sock_mc_close(struct sock *sk) { struct ipv6_pinfo *np = inet6_sk(sk); struct ipv6_mc_socklist *mc_lst; struct net *net = sock_net(sk); ASSERT_RTNL(); while ((mc_lst = sock_dereference(np->ipv6_mc_list, sk)) != NULL) { struct net_device *dev; np->ipv6_mc_list = mc_lst->next; dev = __dev_get_by_index(net, mc_lst->ifindex); if (dev) { struct inet6_dev *idev = __in6_dev_get(dev); ip6_mc_leave_src(sk, mc_lst, idev); if (idev) __ipv6_dev_mc_dec(idev, &mc_lst->addr); } else { ip6_mc_leave_src(sk, mc_lst, NULL); } atomic_sub(sizeof(*mc_lst), &sk->sk_omem_alloc); kfree_rcu(mc_lst, rcu); } } void ipv6_sock_mc_close(struct sock *sk) { struct ipv6_pinfo *np = inet6_sk(sk); if (!rcu_access_pointer(np->ipv6_mc_list)) return; rtnl_lock(); lock_sock(sk); __ipv6_sock_mc_close(sk); release_sock(sk); rtnl_unlock(); } int ip6_mc_source(int add, int omode, struct sock *sk, struct group_source_req *pgsr) { struct in6_addr *source, *group; struct ipv6_mc_socklist *pmc; struct inet6_dev *idev; struct ipv6_pinfo *inet6 = inet6_sk(sk); struct ip6_sf_socklist *psl; struct net *net = sock_net(sk); int i, j, rv; int leavegroup = 0; int err; source = &((struct sockaddr_in6 *)&pgsr->gsr_source)->sin6_addr; group = &((struct sockaddr_in6 *)&pgsr->gsr_group)->sin6_addr; if (!ipv6_addr_is_multicast(group)) return -EINVAL; idev = ip6_mc_find_dev_rtnl(net, group, pgsr->gsr_interface); if (!idev) return -ENODEV; err = -EADDRNOTAVAIL; mutex_lock(&idev->mc_lock); for_each_pmc_socklock(inet6, sk, pmc) { if (pgsr->gsr_interface && pmc->ifindex != pgsr->gsr_interface) continue; if (ipv6_addr_equal(&pmc->addr, group)) break; } if (!pmc) { /* must have a prior join */ err = -EINVAL; goto done; } /* if a source filter was set, must be the same mode as before */ if (rcu_access_pointer(pmc->sflist)) { if (pmc->sfmode != omode) { err = -EINVAL; goto done; } } else if (pmc->sfmode != omode) { /* allow mode switches for empty-set filters */ ip6_mc_add_src(idev, group, omode, 0, NULL, 0); ip6_mc_del_src(idev, group, pmc->sfmode, 0, NULL, 0); pmc->sfmode = omode; } psl = sock_dereference(pmc->sflist, sk); if (!add) { if (!psl) goto done; /* err = -EADDRNOTAVAIL */ rv = !0; for (i = 0; i < psl->sl_count; i++) { rv = !ipv6_addr_equal(&psl->sl_addr[i], source); if (rv == 0) break; } if (rv) /* source not found */ goto done; /* err = -EADDRNOTAVAIL */ /* special case - (INCLUDE, empty) == LEAVE_GROUP */ if (psl->sl_count == 1 && omode == MCAST_INCLUDE) { leavegroup = 1; goto done; } /* update the interface filter */ ip6_mc_del_src(idev, group, omode, 1, source, 1); for (j = i+1; j < psl->sl_count; j++) psl->sl_addr[j-1] = psl->sl_addr[j]; psl->sl_count--; err = 0; goto done; } /* else, add a new source to the filter */ if (psl && psl->sl_count >= sysctl_mld_max_msf) { err = -ENOBUFS; goto done; } if (!psl || psl->sl_count == psl->sl_max) { struct ip6_sf_socklist *newpsl; int count = IP6_SFBLOCK; if (psl) count += psl->sl_max; newpsl = sock_kmalloc(sk, struct_size(newpsl, sl_addr, count), GFP_KERNEL); if (!newpsl) { err = -ENOBUFS; goto done; } newpsl->sl_max = count; newpsl->sl_count = count - IP6_SFBLOCK; if (psl) { for (i = 0; i < psl->sl_count; i++) newpsl->sl_addr[i] = psl->sl_addr[i]; atomic_sub(struct_size(psl, sl_addr, psl->sl_max), &sk->sk_omem_alloc); } rcu_assign_pointer(pmc->sflist, newpsl); kfree_rcu(psl, rcu); psl = newpsl; } rv = 1; /* > 0 for insert logic below if sl_count is 0 */ for (i = 0; i < psl->sl_count; i++) { rv = !ipv6_addr_equal(&psl->sl_addr[i], source); if (rv == 0) /* There is an error in the address. */ goto done; } for (j = psl->sl_count-1; j >= i; j--) psl->sl_addr[j+1] = psl->sl_addr[j]; psl->sl_addr[i] = *source; psl->sl_count++; err = 0; /* update the interface list */ ip6_mc_add_src(idev, group, omode, 1, source, 1); done: mutex_unlock(&idev->mc_lock); if (leavegroup) err = ipv6_sock_mc_drop(sk, pgsr->gsr_interface, group); return err; } int ip6_mc_msfilter(struct sock *sk, struct group_filter *gsf, struct sockaddr_storage *list) { const struct in6_addr *group; struct ipv6_mc_socklist *pmc; struct inet6_dev *idev; struct ipv6_pinfo *inet6 = inet6_sk(sk); struct ip6_sf_socklist *newpsl, *psl; struct net *net = sock_net(sk); int leavegroup = 0; int i, err; group = &((struct sockaddr_in6 *)&gsf->gf_group)->sin6_addr; if (!ipv6_addr_is_multicast(group)) return -EINVAL; if (gsf->gf_fmode != MCAST_INCLUDE && gsf->gf_fmode != MCAST_EXCLUDE) return -EINVAL; idev = ip6_mc_find_dev_rtnl(net, group, gsf->gf_interface); if (!idev) return -ENODEV; err = 0; if (gsf->gf_fmode == MCAST_INCLUDE && gsf->gf_numsrc == 0) { leavegroup = 1; goto done; } for_each_pmc_socklock(inet6, sk, pmc) { if (pmc->ifindex != gsf->gf_interface) continue; if (ipv6_addr_equal(&pmc->addr, group)) break; } if (!pmc) { /* must have a prior join */ err = -EINVAL; goto done; } if (gsf->gf_numsrc) { newpsl = sock_kmalloc(sk, struct_size(newpsl, sl_addr, gsf->gf_numsrc), GFP_KERNEL); if (!newpsl) { err = -ENOBUFS; goto done; } newpsl->sl_max = newpsl->sl_count = gsf->gf_numsrc; for (i = 0; i < newpsl->sl_count; ++i, ++list) { struct sockaddr_in6 *psin6; psin6 = (struct sockaddr_in6 *)list; newpsl->sl_addr[i] = psin6->sin6_addr; } mutex_lock(&idev->mc_lock); err = ip6_mc_add_src(idev, group, gsf->gf_fmode, newpsl->sl_count, newpsl->sl_addr, 0); if (err) { mutex_unlock(&idev->mc_lock); sock_kfree_s(sk, newpsl, struct_size(newpsl, sl_addr, newpsl->sl_max)); goto done; } mutex_unlock(&idev->mc_lock); } else { newpsl = NULL; mutex_lock(&idev->mc_lock); ip6_mc_add_src(idev, group, gsf->gf_fmode, 0, NULL, 0); mutex_unlock(&idev->mc_lock); } mutex_lock(&idev->mc_lock); psl = sock_dereference(pmc->sflist, sk); if (psl) { ip6_mc_del_src(idev, group, pmc->sfmode, psl->sl_count, psl->sl_addr, 0); atomic_sub(struct_size(psl, sl_addr, psl->sl_max), &sk->sk_omem_alloc); } else { ip6_mc_del_src(idev, group, pmc->sfmode, 0, NULL, 0); } rcu_assign_pointer(pmc->sflist, newpsl); mutex_unlock(&idev->mc_lock); kfree_rcu(psl, rcu); pmc->sfmode = gsf->gf_fmode; err = 0; done: if (leavegroup) err = ipv6_sock_mc_drop(sk, gsf->gf_interface, group); return err; } int ip6_mc_msfget(struct sock *sk, struct group_filter *gsf, sockptr_t optval, size_t ss_offset) { struct ipv6_pinfo *inet6 = inet6_sk(sk); const struct in6_addr *group; struct ipv6_mc_socklist *pmc; struct ip6_sf_socklist *psl; unsigned int count; int i, copycount; group = &((struct sockaddr_in6 *)&gsf->gf_group)->sin6_addr; if (!ipv6_addr_is_multicast(group)) return -EINVAL; /* changes to the ipv6_mc_list require the socket lock and * rtnl lock. We have the socket lock, so reading the list is safe. */ for_each_pmc_socklock(inet6, sk, pmc) { if (pmc->ifindex != gsf->gf_interface) continue; if (ipv6_addr_equal(group, &pmc->addr)) break; } if (!pmc) /* must have a prior join */ return -EADDRNOTAVAIL; gsf->gf_fmode = pmc->sfmode; psl = sock_dereference(pmc->sflist, sk); count = psl ? psl->sl_count : 0; copycount = min(count, gsf->gf_numsrc); gsf->gf_numsrc = count; for (i = 0; i < copycount; i++) { struct sockaddr_in6 *psin6; struct sockaddr_storage ss; psin6 = (struct sockaddr_in6 *)&ss; memset(&ss, 0, sizeof(ss)); psin6->sin6_family = AF_INET6; psin6->sin6_addr = psl->sl_addr[i]; if (copy_to_sockptr_offset(optval, ss_offset, &ss, sizeof(ss))) return -EFAULT; ss_offset += sizeof(ss); } return 0; } bool inet6_mc_check(const struct sock *sk, const struct in6_addr *mc_addr, const struct in6_addr *src_addr) { const struct ipv6_pinfo *np = inet6_sk(sk); const struct ipv6_mc_socklist *mc; const struct ip6_sf_socklist *psl; bool rv = true; rcu_read_lock(); for_each_pmc_rcu(np, mc) { if (ipv6_addr_equal(&mc->addr, mc_addr)) break; } if (!mc) { rcu_read_unlock(); return inet6_test_bit(MC6_ALL, sk); } psl = rcu_dereference(mc->sflist); if (!psl) { rv = mc->sfmode == MCAST_EXCLUDE; } else { int i; for (i = 0; i < psl->sl_count; i++) { if (ipv6_addr_equal(&psl->sl_addr[i], src_addr)) break; } if (mc->sfmode == MCAST_INCLUDE && i >= psl->sl_count) rv = false; if (mc->sfmode == MCAST_EXCLUDE && i < psl->sl_count) rv = false; } rcu_read_unlock(); return rv; } /* called with mc_lock */ static void igmp6_group_added(struct ifmcaddr6 *mc) { struct net_device *dev = mc->idev->dev; char buf[MAX_ADDR_LEN]; if (IPV6_ADDR_MC_SCOPE(&mc->mca_addr) < IPV6_ADDR_SCOPE_LINKLOCAL) return; if (!(mc->mca_flags&MAF_LOADED)) { mc->mca_flags |= MAF_LOADED; if (ndisc_mc_map(&mc->mca_addr, buf, dev, 0) == 0) dev_mc_add(dev, buf); } if (!(dev->flags & IFF_UP) || (mc->mca_flags & MAF_NOREPORT)) return; if (mld_in_v1_mode(mc->idev)) { igmp6_join_group(mc); return; } /* else v2 */ /* Based on RFC3810 6.1, for newly added INCLUDE SSM, we * should not send filter-mode change record as the mode * should be from IN() to IN(A). */ if (mc->mca_sfmode == MCAST_EXCLUDE) mc->mca_crcount = mc->idev->mc_qrv; mld_ifc_event(mc->idev); } /* called with mc_lock */ static void igmp6_group_dropped(struct ifmcaddr6 *mc) { struct net_device *dev = mc->idev->dev; char buf[MAX_ADDR_LEN]; if (IPV6_ADDR_MC_SCOPE(&mc->mca_addr) < IPV6_ADDR_SCOPE_LINKLOCAL) return; if (mc->mca_flags&MAF_LOADED) { mc->mca_flags &= ~MAF_LOADED; if (ndisc_mc_map(&mc->mca_addr, buf, dev, 0) == 0) dev_mc_del(dev, buf); } if (mc->mca_flags & MAF_NOREPORT) return; if (!mc->idev->dead) igmp6_leave_group(mc); if (cancel_delayed_work(&mc->mca_work)) refcount_dec(&mc->mca_refcnt); } /* * deleted ifmcaddr6 manipulation * called with mc_lock */ static void mld_add_delrec(struct inet6_dev *idev, struct ifmcaddr6 *im) { struct ifmcaddr6 *pmc; /* this is an "ifmcaddr6" for convenience; only the fields below * are actually used. In particular, the refcnt and users are not * used for management of the delete list. Using the same structure * for deleted items allows change reports to use common code with * non-deleted or query-response MCA's. */ pmc = kzalloc(sizeof(*pmc), GFP_KERNEL); if (!pmc) return; pmc->idev = im->idev; in6_dev_hold(idev); pmc->mca_addr = im->mca_addr; pmc->mca_crcount = idev->mc_qrv; pmc->mca_sfmode = im->mca_sfmode; if (pmc->mca_sfmode == MCAST_INCLUDE) { struct ip6_sf_list *psf; rcu_assign_pointer(pmc->mca_tomb, mc_dereference(im->mca_tomb, idev)); rcu_assign_pointer(pmc->mca_sources, mc_dereference(im->mca_sources, idev)); RCU_INIT_POINTER(im->mca_tomb, NULL); RCU_INIT_POINTER(im->mca_sources, NULL); for_each_psf_mclock(pmc, psf) psf->sf_crcount = pmc->mca_crcount; } rcu_assign_pointer(pmc->next, idev->mc_tomb); rcu_assign_pointer(idev->mc_tomb, pmc); } /* called with mc_lock */ static void mld_del_delrec(struct inet6_dev *idev, struct ifmcaddr6 *im) { struct ip6_sf_list *psf, *sources, *tomb; struct in6_addr *pmca = &im->mca_addr; struct ifmcaddr6 *pmc, *pmc_prev; pmc_prev = NULL; for_each_mc_tomb(idev, pmc) { if (ipv6_addr_equal(&pmc->mca_addr, pmca)) break; pmc_prev = pmc; } if (pmc) { if (pmc_prev) rcu_assign_pointer(pmc_prev->next, pmc->next); else rcu_assign_pointer(idev->mc_tomb, pmc->next); } if (pmc) { im->idev = pmc->idev; if (im->mca_sfmode == MCAST_INCLUDE) { tomb = rcu_replace_pointer(im->mca_tomb, mc_dereference(pmc->mca_tomb, pmc->idev), lockdep_is_held(&im->idev->mc_lock)); rcu_assign_pointer(pmc->mca_tomb, tomb); sources = rcu_replace_pointer(im->mca_sources, mc_dereference(pmc->mca_sources, pmc->idev), lockdep_is_held(&im->idev->mc_lock)); rcu_assign_pointer(pmc->mca_sources, sources); for_each_psf_mclock(im, psf) psf->sf_crcount = idev->mc_qrv; } else { im->mca_crcount = idev->mc_qrv; } in6_dev_put(pmc->idev); ip6_mc_clear_src(pmc); kfree_rcu(pmc, rcu); } } /* called with mc_lock */ static void mld_clear_delrec(struct inet6_dev *idev) { struct ifmcaddr6 *pmc, *nextpmc; pmc = mc_dereference(idev->mc_tomb, idev); RCU_INIT_POINTER(idev->mc_tomb, NULL); for (; pmc; pmc = nextpmc) { nextpmc = mc_dereference(pmc->next, idev); ip6_mc_clear_src(pmc); in6_dev_put(pmc->idev); kfree_rcu(pmc, rcu); } /* clear dead sources, too */ for_each_mc_mclock(idev, pmc) { struct ip6_sf_list *psf, *psf_next; psf = mc_dereference(pmc->mca_tomb, idev); RCU_INIT_POINTER(pmc->mca_tomb, NULL); for (; psf; psf = psf_next) { psf_next = mc_dereference(psf->sf_next, idev); kfree_rcu(psf, rcu); } } } static void mld_clear_query(struct inet6_dev *idev) { struct sk_buff *skb; spin_lock_bh(&idev->mc_query_lock); while ((skb = __skb_dequeue(&idev->mc_query_queue))) kfree_skb(skb); spin_unlock_bh(&idev->mc_query_lock); } static void mld_clear_report(struct inet6_dev *idev) { struct sk_buff *skb; spin_lock_bh(&idev->mc_report_lock); while ((skb = __skb_dequeue(&idev->mc_report_queue))) kfree_skb(skb); spin_unlock_bh(&idev->mc_report_lock); } static void mca_get(struct ifmcaddr6 *mc) { refcount_inc(&mc->mca_refcnt); } static void ma_put(struct ifmcaddr6 *mc) { if (refcount_dec_and_test(&mc->mca_refcnt)) { in6_dev_put(mc->idev); kfree_rcu(mc, rcu); } } /* called with mc_lock */ static struct ifmcaddr6 *mca_alloc(struct inet6_dev *idev, const struct in6_addr *addr, unsigned int mode) { struct ifmcaddr6 *mc; mc = kzalloc(sizeof(*mc), GFP_KERNEL); if (!mc) return NULL; INIT_DELAYED_WORK(&mc->mca_work, mld_mca_work); mc->mca_addr = *addr; mc->idev = idev; /* reference taken by caller */ mc->mca_users = 1; /* mca_stamp should be updated upon changes */ mc->mca_cstamp = mc->mca_tstamp = jiffies; refcount_set(&mc->mca_refcnt, 1); mc->mca_sfmode = mode; mc->mca_sfcount[mode] = 1; if (ipv6_addr_is_ll_all_nodes(&mc->mca_addr) || IPV6_ADDR_MC_SCOPE(&mc->mca_addr) < IPV6_ADDR_SCOPE_LINKLOCAL) mc->mca_flags |= MAF_NOREPORT; return mc; } /* * device multicast group inc (add if not found) */ static int __ipv6_dev_mc_inc(struct net_device *dev, const struct in6_addr *addr, unsigned int mode) { struct ifmcaddr6 *mc; struct inet6_dev *idev; ASSERT_RTNL(); /* we need to take a reference on idev */ idev = in6_dev_get(dev); if (!idev) return -EINVAL; if (idev->dead) { in6_dev_put(idev); return -ENODEV; } mutex_lock(&idev->mc_lock); for_each_mc_mclock(idev, mc) { if (ipv6_addr_equal(&mc->mca_addr, addr)) { mc->mca_users++; ip6_mc_add_src(idev, &mc->mca_addr, mode, 0, NULL, 0); mutex_unlock(&idev->mc_lock); in6_dev_put(idev); return 0; } } mc = mca_alloc(idev, addr, mode); if (!mc) { mutex_unlock(&idev->mc_lock); in6_dev_put(idev); return -ENOMEM; } rcu_assign_pointer(mc->next, idev->mc_list); rcu_assign_pointer(idev->mc_list, mc); mca_get(mc); mld_del_delrec(idev, mc); igmp6_group_added(mc); mutex_unlock(&idev->mc_lock); ma_put(mc); return 0; } int ipv6_dev_mc_inc(struct net_device *dev, const struct in6_addr *addr) { return __ipv6_dev_mc_inc(dev, addr, MCAST_EXCLUDE); } EXPORT_SYMBOL(ipv6_dev_mc_inc); /* * device multicast group del */ int __ipv6_dev_mc_dec(struct inet6_dev *idev, const struct in6_addr *addr) { struct ifmcaddr6 *ma, __rcu **map; ASSERT_RTNL(); mutex_lock(&idev->mc_lock); for (map = &idev->mc_list; (ma = mc_dereference(*map, idev)); map = &ma->next) { if (ipv6_addr_equal(&ma->mca_addr, addr)) { if (--ma->mca_users == 0) { *map = ma->next; igmp6_group_dropped(ma); ip6_mc_clear_src(ma); mutex_unlock(&idev->mc_lock); ma_put(ma); return 0; } mutex_unlock(&idev->mc_lock); return 0; } } mutex_unlock(&idev->mc_lock); return -ENOENT; } int ipv6_dev_mc_dec(struct net_device *dev, const struct in6_addr *addr) { struct inet6_dev *idev; int err; ASSERT_RTNL(); idev = __in6_dev_get(dev); if (!idev) err = -ENODEV; else err = __ipv6_dev_mc_dec(idev, addr); return err; } EXPORT_SYMBOL(ipv6_dev_mc_dec); /* * check if the interface/address pair is valid */ bool ipv6_chk_mcast_addr(struct net_device *dev, const struct in6_addr *group, const struct in6_addr *src_addr) { struct inet6_dev *idev; struct ifmcaddr6 *mc; bool rv = false; rcu_read_lock(); idev = __in6_dev_get(dev); if (idev) { for_each_mc_rcu(idev, mc) { if (ipv6_addr_equal(&mc->mca_addr, group)) break; } if (mc) { if (src_addr && !ipv6_addr_any(src_addr)) { struct ip6_sf_list *psf; for_each_psf_rcu(mc, psf) { if (ipv6_addr_equal(&psf->sf_addr, src_addr)) break; } if (psf) rv = psf->sf_count[MCAST_INCLUDE] || psf->sf_count[MCAST_EXCLUDE] != mc->mca_sfcount[MCAST_EXCLUDE]; else rv = mc->mca_sfcount[MCAST_EXCLUDE] != 0; } else rv = true; /* don't filter unspecified source */ } } rcu_read_unlock(); return rv; } /* called with mc_lock */ static void mld_gq_start_work(struct inet6_dev *idev) { unsigned long tv = get_random_u32_below(idev->mc_maxdelay); idev->mc_gq_running = 1; if (!mod_delayed_work(mld_wq, &idev->mc_gq_work, tv + 2)) in6_dev_hold(idev); } /* called with mc_lock */ static void mld_gq_stop_work(struct inet6_dev *idev) { idev->mc_gq_running = 0; if (cancel_delayed_work(&idev->mc_gq_work)) __in6_dev_put(idev); } /* called with mc_lock */ static void mld_ifc_start_work(struct inet6_dev *idev, unsigned long delay) { unsigned long tv = get_random_u32_below(delay); if (!mod_delayed_work(mld_wq, &idev->mc_ifc_work, tv + 2)) in6_dev_hold(idev); } /* called with mc_lock */ static void mld_ifc_stop_work(struct inet6_dev *idev) { idev->mc_ifc_count = 0; if (cancel_delayed_work(&idev->mc_ifc_work)) __in6_dev_put(idev); } /* called with mc_lock */ static void mld_dad_start_work(struct inet6_dev *idev, unsigned long delay) { unsigned long tv = get_random_u32_below(delay); if (!mod_delayed_work(mld_wq, &idev->mc_dad_work, tv + 2)) in6_dev_hold(idev); } static void mld_dad_stop_work(struct inet6_dev *idev) { if (cancel_delayed_work(&idev->mc_dad_work)) __in6_dev_put(idev); } static void mld_query_stop_work(struct inet6_dev *idev) { spin_lock_bh(&idev->mc_query_lock); if (cancel_delayed_work(&idev->mc_query_work)) __in6_dev_put(idev); spin_unlock_bh(&idev->mc_query_lock); } static void mld_report_stop_work(struct inet6_dev *idev) { if (cancel_delayed_work_sync(&idev->mc_report_work)) __in6_dev_put(idev); } /* * IGMP handling (alias multicast ICMPv6 messages) * called with mc_lock */ static void igmp6_group_queried(struct ifmcaddr6 *ma, unsigned long resptime) { unsigned long delay = resptime; /* Do not start work for these addresses */ if (ipv6_addr_is_ll_all_nodes(&ma->mca_addr) || IPV6_ADDR_MC_SCOPE(&ma->mca_addr) < IPV6_ADDR_SCOPE_LINKLOCAL) return; if (cancel_delayed_work(&ma->mca_work)) { refcount_dec(&ma->mca_refcnt); delay = ma->mca_work.timer.expires - jiffies; } if (delay >= resptime) delay = get_random_u32_below(resptime); if (!mod_delayed_work(mld_wq, &ma->mca_work, delay)) refcount_inc(&ma->mca_refcnt); ma->mca_flags |= MAF_TIMER_RUNNING; } /* mark EXCLUDE-mode sources * called with mc_lock */ static bool mld_xmarksources(struct ifmcaddr6 *pmc, int nsrcs, const struct in6_addr *srcs) { struct ip6_sf_list *psf; int i, scount; scount = 0; for_each_psf_mclock(pmc, psf) { if (scount == nsrcs) break; for (i = 0; i < nsrcs; i++) { /* skip inactive filters */ if (psf->sf_count[MCAST_INCLUDE] || pmc->mca_sfcount[MCAST_EXCLUDE] != psf->sf_count[MCAST_EXCLUDE]) break; if (ipv6_addr_equal(&srcs[i], &psf->sf_addr)) { scount++; break; } } } pmc->mca_flags &= ~MAF_GSQUERY; if (scount == nsrcs) /* all sources excluded */ return false; return true; } /* called with mc_lock */ static bool mld_marksources(struct ifmcaddr6 *pmc, int nsrcs, const struct in6_addr *srcs) { struct ip6_sf_list *psf; int i, scount; if (pmc->mca_sfmode == MCAST_EXCLUDE) return mld_xmarksources(pmc, nsrcs, srcs); /* mark INCLUDE-mode sources */ scount = 0; for_each_psf_mclock(pmc, psf) { if (scount == nsrcs) break; for (i = 0; i < nsrcs; i++) { if (ipv6_addr_equal(&srcs[i], &psf->sf_addr)) { psf->sf_gsresp = 1; scount++; break; } } } if (!scount) { pmc->mca_flags &= ~MAF_GSQUERY; return false; } pmc->mca_flags |= MAF_GSQUERY; return true; } static int mld_force_mld_version(const struct inet6_dev *idev) { const struct net *net = dev_net(idev->dev); int all_force; all_force = READ_ONCE(net->ipv6.devconf_all->force_mld_version); /* Normally, both are 0 here. If enforcement to a particular is * being used, individual device enforcement will have a lower * precedence over 'all' device (.../conf/all/force_mld_version). */ return all_force ?: READ_ONCE(idev->cnf.force_mld_version); } static bool mld_in_v2_mode_only(const struct inet6_dev *idev) { return mld_force_mld_version(idev) == 2; } static bool mld_in_v1_mode_only(const struct inet6_dev *idev) { return mld_force_mld_version(idev) == 1; } static bool mld_in_v1_mode(const struct inet6_dev *idev) { if (mld_in_v2_mode_only(idev)) return false; if (mld_in_v1_mode_only(idev)) return true; if (idev->mc_v1_seen && time_before(jiffies, idev->mc_v1_seen)) return true; return false; } static void mld_set_v1_mode(struct inet6_dev *idev) { /* RFC3810, relevant sections: * - 9.1. Robustness Variable * - 9.2. Query Interval * - 9.3. Query Response Interval * - 9.12. Older Version Querier Present Timeout */ unsigned long switchback; switchback = (idev->mc_qrv * idev->mc_qi) + idev->mc_qri; idev->mc_v1_seen = jiffies + switchback; } static void mld_update_qrv(struct inet6_dev *idev, const struct mld2_query *mlh2) { /* RFC3810, relevant sections: * - 5.1.8. QRV (Querier's Robustness Variable) * - 9.1. Robustness Variable */ /* The value of the Robustness Variable MUST NOT be zero, * and SHOULD NOT be one. Catch this here if we ever run * into such a case in future. */ const int min_qrv = min(MLD_QRV_DEFAULT, sysctl_mld_qrv); WARN_ON(idev->mc_qrv == 0); if (mlh2->mld2q_qrv > 0) idev->mc_qrv = mlh2->mld2q_qrv; if (unlikely(idev->mc_qrv < min_qrv)) { net_warn_ratelimited("IPv6: MLD: clamping QRV from %u to %u!\n", idev->mc_qrv, min_qrv); idev->mc_qrv = min_qrv; } } static void mld_update_qi(struct inet6_dev *idev, const struct mld2_query *mlh2) { /* RFC3810, relevant sections: * - 5.1.9. QQIC (Querier's Query Interval Code) * - 9.2. Query Interval * - 9.12. Older Version Querier Present Timeout * (the [Query Interval] in the last Query received) */ unsigned long mc_qqi; if (mlh2->mld2q_qqic < 128) { mc_qqi = mlh2->mld2q_qqic; } else { unsigned long mc_man, mc_exp; mc_exp = MLDV2_QQIC_EXP(mlh2->mld2q_qqic); mc_man = MLDV2_QQIC_MAN(mlh2->mld2q_qqic); mc_qqi = (mc_man | 0x10) << (mc_exp + 3); } idev->mc_qi = mc_qqi * HZ; } static void mld_update_qri(struct inet6_dev *idev, const struct mld2_query *mlh2) { /* RFC3810, relevant sections: * - 5.1.3. Maximum Response Code * - 9.3. Query Response Interval */ idev->mc_qri = msecs_to_jiffies(mldv2_mrc(mlh2)); } static int mld_process_v1(struct inet6_dev *idev, struct mld_msg *mld, unsigned long *max_delay, bool v1_query) { unsigned long mldv1_md; /* Ignore v1 queries */ if (mld_in_v2_mode_only(idev)) return -EINVAL; mldv1_md = ntohs(mld->mld_maxdelay); /* When in MLDv1 fallback and a MLDv2 router start-up being * unaware of current MLDv1 operation, the MRC == MRD mapping * only works when the exponential algorithm is not being * used (as MLDv1 is unaware of such things). * * According to the RFC author, the MLDv2 implementations * he's aware of all use a MRC < 32768 on start up queries. * * Thus, should we *ever* encounter something else larger * than that, just assume the maximum possible within our * reach. */ if (!v1_query) mldv1_md = min(mldv1_md, MLDV1_MRD_MAX_COMPAT); *max_delay = max(msecs_to_jiffies(mldv1_md), 1UL); /* MLDv1 router present: we need to go into v1 mode *only* * when an MLDv1 query is received as per section 9.12. of * RFC3810! And we know from RFC2710 section 3.7 that MLDv1 * queries MUST be of exactly 24 octets. */ if (v1_query) mld_set_v1_mode(idev); /* cancel MLDv2 report work */ mld_gq_stop_work(idev); /* cancel the interface change work */ mld_ifc_stop_work(idev); /* clear deleted report items */ mld_clear_delrec(idev); return 0; } static void mld_process_v2(struct inet6_dev *idev, struct mld2_query *mld, unsigned long *max_delay) { *max_delay = max(msecs_to_jiffies(mldv2_mrc(mld)), 1UL); mld_update_qrv(idev, mld); mld_update_qi(idev, mld); mld_update_qri(idev, mld); idev->mc_maxdelay = *max_delay; return; } /* called with rcu_read_lock() */ void igmp6_event_query(struct sk_buff *skb) { struct inet6_dev *idev = __in6_dev_get(skb->dev); if (!idev || idev->dead) goto out; spin_lock_bh(&idev->mc_query_lock); if (skb_queue_len(&idev->mc_query_queue) < MLD_MAX_SKBS) { __skb_queue_tail(&idev->mc_query_queue, skb); if (!mod_delayed_work(mld_wq, &idev->mc_query_work, 0)) in6_dev_hold(idev); skb = NULL; } spin_unlock_bh(&idev->mc_query_lock); out: kfree_skb(skb); } static void __mld_query_work(struct sk_buff *skb) { struct mld2_query *mlh2 = NULL; const struct in6_addr *group; unsigned long max_delay; struct inet6_dev *idev; struct ifmcaddr6 *ma; struct mld_msg *mld; int group_type; int mark = 0; int len, err; if (!pskb_may_pull(skb, sizeof(struct in6_addr))) goto kfree_skb; /* compute payload length excluding extension headers */ len = ntohs(ipv6_hdr(skb)->payload_len) + sizeof(struct ipv6hdr); len -= skb_network_header_len(skb); /* RFC3810 6.2 * Upon reception of an MLD message that contains a Query, the node * checks if the source address of the message is a valid link-local * address, if the Hop Limit is set to 1, and if the Router Alert * option is present in the Hop-By-Hop Options header of the IPv6 * packet. If any of these checks fails, the packet is dropped. */ if (!(ipv6_addr_type(&ipv6_hdr(skb)->saddr) & IPV6_ADDR_LINKLOCAL) || ipv6_hdr(skb)->hop_limit != 1 || !(IP6CB(skb)->flags & IP6SKB_ROUTERALERT) || IP6CB(skb)->ra != htons(IPV6_OPT_ROUTERALERT_MLD)) goto kfree_skb; idev = in6_dev_get(skb->dev); if (!idev) goto kfree_skb; mld = (struct mld_msg *)icmp6_hdr(skb); group = &mld->mld_mca; group_type = ipv6_addr_type(group); if (group_type != IPV6_ADDR_ANY && !(group_type&IPV6_ADDR_MULTICAST)) goto out; if (len < MLD_V1_QUERY_LEN) { goto out; } else if (len == MLD_V1_QUERY_LEN || mld_in_v1_mode(idev)) { err = mld_process_v1(idev, mld, &max_delay, len == MLD_V1_QUERY_LEN); if (err < 0) goto out; } else if (len >= MLD_V2_QUERY_LEN_MIN) { int srcs_offset = sizeof(struct mld2_query) - sizeof(struct icmp6hdr); if (!pskb_may_pull(skb, srcs_offset)) goto out; mlh2 = (struct mld2_query *)skb_transport_header(skb); mld_process_v2(idev, mlh2, &max_delay); if (group_type == IPV6_ADDR_ANY) { /* general query */ if (mlh2->mld2q_nsrcs) goto out; /* no sources allowed */ mld_gq_start_work(idev); goto out; } /* mark sources to include, if group & source-specific */ if (mlh2->mld2q_nsrcs != 0) { if (!pskb_may_pull(skb, srcs_offset + ntohs(mlh2->mld2q_nsrcs) * sizeof(struct in6_addr))) goto out; mlh2 = (struct mld2_query *)skb_transport_header(skb); mark = 1; } } else { goto out; } if (group_type == IPV6_ADDR_ANY) { for_each_mc_mclock(idev, ma) { igmp6_group_queried(ma, max_delay); } } else { for_each_mc_mclock(idev, ma) { if (!ipv6_addr_equal(group, &ma->mca_addr)) continue; if (ma->mca_flags & MAF_TIMER_RUNNING) { /* gsquery <- gsquery && mark */ if (!mark) ma->mca_flags &= ~MAF_GSQUERY; } else { /* gsquery <- mark */ if (mark) ma->mca_flags |= MAF_GSQUERY; else ma->mca_flags &= ~MAF_GSQUERY; } if (!(ma->mca_flags & MAF_GSQUERY) || mld_marksources(ma, ntohs(mlh2->mld2q_nsrcs), mlh2->mld2q_srcs)) igmp6_group_queried(ma, max_delay); break; } } out: in6_dev_put(idev); kfree_skb: consume_skb(skb); } static void mld_query_work(struct work_struct *work) { struct inet6_dev *idev = container_of(to_delayed_work(work), struct inet6_dev, mc_query_work); struct sk_buff_head q; struct sk_buff *skb; bool rework = false; int cnt = 0; skb_queue_head_init(&q); spin_lock_bh(&idev->mc_query_lock); while ((skb = __skb_dequeue(&idev->mc_query_queue))) { __skb_queue_tail(&q, skb); if (++cnt >= MLD_MAX_QUEUE) { rework = true; break; } } spin_unlock_bh(&idev->mc_query_lock); mutex_lock(&idev->mc_lock); while ((skb = __skb_dequeue(&q))) __mld_query_work(skb); mutex_unlock(&idev->mc_lock); if (rework && queue_delayed_work(mld_wq, &idev->mc_query_work, 0)) return; in6_dev_put(idev); } /* called with rcu_read_lock() */ void igmp6_event_report(struct sk_buff *skb) { struct inet6_dev *idev = __in6_dev_get(skb->dev); if (!idev || idev->dead) goto out; spin_lock_bh(&idev->mc_report_lock); if (skb_queue_len(&idev->mc_report_queue) < MLD_MAX_SKBS) { __skb_queue_tail(&idev->mc_report_queue, skb); if (!mod_delayed_work(mld_wq, &idev->mc_report_work, 0)) in6_dev_hold(idev); skb = NULL; } spin_unlock_bh(&idev->mc_report_lock); out: kfree_skb(skb); } static void __mld_report_work(struct sk_buff *skb) { struct inet6_dev *idev; struct ifmcaddr6 *ma; struct mld_msg *mld; int addr_type; /* Our own report looped back. Ignore it. */ if (skb->pkt_type == PACKET_LOOPBACK) goto kfree_skb; /* send our report if the MC router may not have heard this report */ if (skb->pkt_type != PACKET_MULTICAST && skb->pkt_type != PACKET_BROADCAST) goto kfree_skb; if (!pskb_may_pull(skb, sizeof(*mld) - sizeof(struct icmp6hdr))) goto kfree_skb; mld = (struct mld_msg *)icmp6_hdr(skb); /* Drop reports with not link local source */ addr_type = ipv6_addr_type(&ipv6_hdr(skb)->saddr); if (addr_type != IPV6_ADDR_ANY && !(addr_type&IPV6_ADDR_LINKLOCAL)) goto kfree_skb; idev = in6_dev_get(skb->dev); if (!idev) goto kfree_skb; /* * Cancel the work for this group */ for_each_mc_mclock(idev, ma) { if (ipv6_addr_equal(&ma->mca_addr, &mld->mld_mca)) { if (cancel_delayed_work(&ma->mca_work)) refcount_dec(&ma->mca_refcnt); ma->mca_flags &= ~(MAF_LAST_REPORTER | MAF_TIMER_RUNNING); break; } } in6_dev_put(idev); kfree_skb: consume_skb(skb); } static void mld_report_work(struct work_struct *work) { struct inet6_dev *idev = container_of(to_delayed_work(work), struct inet6_dev, mc_report_work); struct sk_buff_head q; struct sk_buff *skb; bool rework = false; int cnt = 0; skb_queue_head_init(&q); spin_lock_bh(&idev->mc_report_lock); while ((skb = __skb_dequeue(&idev->mc_report_queue))) { __skb_queue_tail(&q, skb); if (++cnt >= MLD_MAX_QUEUE) { rework = true; break; } } spin_unlock_bh(&idev->mc_report_lock); mutex_lock(&idev->mc_lock); while ((skb = __skb_dequeue(&q))) __mld_report_work(skb); mutex_unlock(&idev->mc_lock); if (rework && queue_delayed_work(mld_wq, &idev->mc_report_work, 0)) return; in6_dev_put(idev); } static bool is_in(struct ifmcaddr6 *pmc, struct ip6_sf_list *psf, int type, int gdeleted, int sdeleted) { switch (type) { case MLD2_MODE_IS_INCLUDE: case MLD2_MODE_IS_EXCLUDE: if (gdeleted || sdeleted) return false; if (!((pmc->mca_flags & MAF_GSQUERY) && !psf->sf_gsresp)) { if (pmc->mca_sfmode == MCAST_INCLUDE) return true; /* don't include if this source is excluded * in all filters */ if (psf->sf_count[MCAST_INCLUDE]) return type == MLD2_MODE_IS_INCLUDE; return pmc->mca_sfcount[MCAST_EXCLUDE] == psf->sf_count[MCAST_EXCLUDE]; } return false; case MLD2_CHANGE_TO_INCLUDE: if (gdeleted || sdeleted) return false; return psf->sf_count[MCAST_INCLUDE] != 0; case MLD2_CHANGE_TO_EXCLUDE: if (gdeleted || sdeleted) return false; if (pmc->mca_sfcount[MCAST_EXCLUDE] == 0 || psf->sf_count[MCAST_INCLUDE]) return false; return pmc->mca_sfcount[MCAST_EXCLUDE] == psf->sf_count[MCAST_EXCLUDE]; case MLD2_ALLOW_NEW_SOURCES: if (gdeleted || !psf->sf_crcount) return false; return (pmc->mca_sfmode == MCAST_INCLUDE) ^ sdeleted; case MLD2_BLOCK_OLD_SOURCES: if (pmc->mca_sfmode == MCAST_INCLUDE) return gdeleted || (psf->sf_crcount && sdeleted); return psf->sf_crcount && !gdeleted && !sdeleted; } return false; } static int mld_scount(struct ifmcaddr6 *pmc, int type, int gdeleted, int sdeleted) { struct ip6_sf_list *psf; int scount = 0; for_each_psf_mclock(pmc, psf) { if (!is_in(pmc, psf, type, gdeleted, sdeleted)) continue; scount++; } return scount; } static void ip6_mc_hdr(const struct sock *sk, struct sk_buff *skb, struct net_device *dev, const struct in6_addr *saddr, const struct in6_addr *daddr, int proto, int len) { struct ipv6hdr *hdr; skb->protocol = htons(ETH_P_IPV6); skb->dev = dev; skb_reset_network_header(skb); skb_put(skb, sizeof(struct ipv6hdr)); hdr = ipv6_hdr(skb); ip6_flow_hdr(hdr, 0, 0); hdr->payload_len = htons(len); hdr->nexthdr = proto; hdr->hop_limit = READ_ONCE(inet6_sk(sk)->hop_limit); hdr->saddr = *saddr; hdr->daddr = *daddr; } static struct sk_buff *mld_newpack(struct inet6_dev *idev, unsigned int mtu) { u8 ra[8] = { IPPROTO_ICMPV6, 0, IPV6_TLV_ROUTERALERT, 2, 0, 0, IPV6_TLV_PADN, 0 }; struct net_device *dev = idev->dev; int hlen = LL_RESERVED_SPACE(dev); int tlen = dev->needed_tailroom; struct net *net = dev_net(dev); const struct in6_addr *saddr; struct in6_addr addr_buf; struct mld2_report *pmr; struct sk_buff *skb; unsigned int size; struct sock *sk; int err; sk = net->ipv6.igmp_sk; /* we assume size > sizeof(ra) here * Also try to not allocate high-order pages for big MTU */ size = min_t(int, mtu, PAGE_SIZE / 2) + hlen + tlen; skb = sock_alloc_send_skb(sk, size, 1, &err); if (!skb) return NULL; skb->priority = TC_PRIO_CONTROL; skb_reserve(skb, hlen); skb_tailroom_reserve(skb, mtu, tlen); if (ipv6_get_lladdr(dev, &addr_buf, IFA_F_TENTATIVE)) { /* <draft-ietf-magma-mld-source-05.txt>: * use unspecified address as the source address * when a valid link-local address is not available. */ saddr = &in6addr_any; } else saddr = &addr_buf; ip6_mc_hdr(sk, skb, dev, saddr, &mld2_all_mcr, NEXTHDR_HOP, 0); skb_put_data(skb, ra, sizeof(ra)); skb_set_transport_header(skb, skb_tail_pointer(skb) - skb->data); skb_put(skb, sizeof(*pmr)); pmr = (struct mld2_report *)skb_transport_header(skb); pmr->mld2r_type = ICMPV6_MLD2_REPORT; pmr->mld2r_resv1 = 0; pmr->mld2r_cksum = 0; pmr->mld2r_resv2 = 0; pmr->mld2r_ngrec = 0; return skb; } static void mld_sendpack(struct sk_buff *skb) { struct ipv6hdr *pip6 = ipv6_hdr(skb); struct mld2_report *pmr = (struct mld2_report *)skb_transport_header(skb); int payload_len, mldlen; struct inet6_dev *idev; struct net *net = dev_net(skb->dev); int err; struct flowi6 fl6; struct dst_entry *dst; rcu_read_lock(); idev = __in6_dev_get(skb->dev); IP6_INC_STATS(net, idev, IPSTATS_MIB_OUTREQUESTS); payload_len = (skb_tail_pointer(skb) - skb_network_header(skb)) - sizeof(*pip6); mldlen = skb_tail_pointer(skb) - skb_transport_header(skb); pip6->payload_len = htons(payload_len); pmr->mld2r_cksum = csum_ipv6_magic(&pip6->saddr, &pip6->daddr, mldlen, IPPROTO_ICMPV6, csum_partial(skb_transport_header(skb), mldlen, 0)); icmpv6_flow_init(net->ipv6.igmp_sk, &fl6, ICMPV6_MLD2_REPORT, &ipv6_hdr(skb)->saddr, &ipv6_hdr(skb)->daddr, skb->dev->ifindex); dst = icmp6_dst_alloc(skb->dev, &fl6); err = 0; if (IS_ERR(dst)) { err = PTR_ERR(dst); dst = NULL; } skb_dst_set(skb, dst); if (err) goto err_out; err = NF_HOOK(NFPROTO_IPV6, NF_INET_LOCAL_OUT, net, net->ipv6.igmp_sk, skb, NULL, skb->dev, dst_output); out: if (!err) { ICMP6MSGOUT_INC_STATS(net, idev, ICMPV6_MLD2_REPORT); ICMP6_INC_STATS(net, idev, ICMP6_MIB_OUTMSGS); } else { IP6_INC_STATS(net, idev, IPSTATS_MIB_OUTDISCARDS); } rcu_read_unlock(); return; err_out: kfree_skb(skb); goto out; } static int grec_size(struct ifmcaddr6 *pmc, int type, int gdel, int sdel) { return sizeof(struct mld2_grec) + 16 * mld_scount(pmc,type,gdel,sdel); } static struct sk_buff *add_grhead(struct sk_buff *skb, struct ifmcaddr6 *pmc, int type, struct mld2_grec **ppgr, unsigned int mtu) { struct mld2_report *pmr; struct mld2_grec *pgr; if (!skb) { skb = mld_newpack(pmc->idev, mtu); if (!skb) return NULL; } pgr = skb_put(skb, sizeof(struct mld2_grec)); pgr->grec_type = type; pgr->grec_auxwords = 0; pgr->grec_nsrcs = 0; pgr->grec_mca = pmc->mca_addr; /* structure copy */ pmr = (struct mld2_report *)skb_transport_header(skb); pmr->mld2r_ngrec = htons(ntohs(pmr->mld2r_ngrec)+1); *ppgr = pgr; return skb; } #define AVAILABLE(skb) ((skb) ? skb_availroom(skb) : 0) /* called with mc_lock */ static struct sk_buff *add_grec(struct sk_buff *skb, struct ifmcaddr6 *pmc, int type, int gdeleted, int sdeleted, int crsend) { struct ip6_sf_list *psf, *psf_prev, *psf_next; int scount, stotal, first, isquery, truncate; struct ip6_sf_list __rcu **psf_list; struct inet6_dev *idev = pmc->idev; struct net_device *dev = idev->dev; struct mld2_grec *pgr = NULL; struct mld2_report *pmr; unsigned int mtu; if (pmc->mca_flags & MAF_NOREPORT) return skb; mtu = READ_ONCE(dev->mtu); if (mtu < IPV6_MIN_MTU) return skb; isquery = type == MLD2_MODE_IS_INCLUDE || type == MLD2_MODE_IS_EXCLUDE; truncate = type == MLD2_MODE_IS_EXCLUDE || type == MLD2_CHANGE_TO_EXCLUDE; stotal = scount = 0; psf_list = sdeleted ? &pmc->mca_tomb : &pmc->mca_sources; if (!rcu_access_pointer(*psf_list)) goto empty_source; pmr = skb ? (struct mld2_report *)skb_transport_header(skb) : NULL; /* EX and TO_EX get a fresh packet, if needed */ if (truncate) { if (pmr && pmr->mld2r_ngrec && AVAILABLE(skb) < grec_size(pmc, type, gdeleted, sdeleted)) { if (skb) mld_sendpack(skb); skb = mld_newpack(idev, mtu); } } first = 1; psf_prev = NULL; for (psf = mc_dereference(*psf_list, idev); psf; psf = psf_next) { struct in6_addr *psrc; psf_next = mc_dereference(psf->sf_next, idev); if (!is_in(pmc, psf, type, gdeleted, sdeleted) && !crsend) { psf_prev = psf; continue; } /* Based on RFC3810 6.1. Should not send source-list change * records when there is a filter mode change. */ if (((gdeleted && pmc->mca_sfmode == MCAST_EXCLUDE) || (!gdeleted && pmc->mca_crcount)) && (type == MLD2_ALLOW_NEW_SOURCES || type == MLD2_BLOCK_OLD_SOURCES) && psf->sf_crcount) goto decrease_sf_crcount; /* clear marks on query responses */ if (isquery) psf->sf_gsresp = 0; if (AVAILABLE(skb) < sizeof(*psrc) + first*sizeof(struct mld2_grec)) { if (truncate && !first) break; /* truncate these */ if (pgr) pgr->grec_nsrcs = htons(scount); if (skb) mld_sendpack(skb); skb = mld_newpack(idev, mtu); first = 1; scount = 0; } if (first) { skb = add_grhead(skb, pmc, type, &pgr, mtu); first = 0; } if (!skb) return NULL; psrc = skb_put(skb, sizeof(*psrc)); *psrc = psf->sf_addr; scount++; stotal++; if ((type == MLD2_ALLOW_NEW_SOURCES || type == MLD2_BLOCK_OLD_SOURCES) && psf->sf_crcount) { decrease_sf_crcount: psf->sf_crcount--; if ((sdeleted || gdeleted) && psf->sf_crcount == 0) { if (psf_prev) rcu_assign_pointer(psf_prev->sf_next, mc_dereference(psf->sf_next, idev)); else rcu_assign_pointer(*psf_list, mc_dereference(psf->sf_next, idev)); kfree_rcu(psf, rcu); continue; } } psf_prev = psf; } empty_source: if (!stotal) { if (type == MLD2_ALLOW_NEW_SOURCES || type == MLD2_BLOCK_OLD_SOURCES) return skb; if (pmc->mca_crcount || isquery || crsend) { /* make sure we have room for group header */ if (skb && AVAILABLE(skb) < sizeof(struct mld2_grec)) { mld_sendpack(skb); skb = NULL; /* add_grhead will get a new one */ } skb = add_grhead(skb, pmc, type, &pgr, mtu); } } if (pgr) pgr->grec_nsrcs = htons(scount); if (isquery) pmc->mca_flags &= ~MAF_GSQUERY; /* clear query state */ return skb; } /* called with mc_lock */ static void mld_send_report(struct inet6_dev *idev, struct ifmcaddr6 *pmc) { struct sk_buff *skb = NULL; int type; if (!pmc) { for_each_mc_mclock(idev, pmc) { if (pmc->mca_flags & MAF_NOREPORT) continue; if (pmc->mca_sfcount[MCAST_EXCLUDE]) type = MLD2_MODE_IS_EXCLUDE; else type = MLD2_MODE_IS_INCLUDE; skb = add_grec(skb, pmc, type, 0, 0, 0); } } else { if (pmc->mca_sfcount[MCAST_EXCLUDE]) type = MLD2_MODE_IS_EXCLUDE; else type = MLD2_MODE_IS_INCLUDE; skb = add_grec(skb, pmc, type, 0, 0, 0); } if (skb) mld_sendpack(skb); } /* * remove zero-count source records from a source filter list * called with mc_lock */ static void mld_clear_zeros(struct ip6_sf_list __rcu **ppsf, struct inet6_dev *idev) { struct ip6_sf_list *psf_prev, *psf_next, *psf; psf_prev = NULL; for (psf = mc_dereference(*ppsf, idev); psf; psf = psf_next) { psf_next = mc_dereference(psf->sf_next, idev); if (psf->sf_crcount == 0) { if (psf_prev) rcu_assign_pointer(psf_prev->sf_next, mc_dereference(psf->sf_next, idev)); else rcu_assign_pointer(*ppsf, mc_dereference(psf->sf_next, idev)); kfree_rcu(psf, rcu); } else { psf_prev = psf; } } } /* called with mc_lock */ static void mld_send_cr(struct inet6_dev *idev) { struct ifmcaddr6 *pmc, *pmc_prev, *pmc_next; struct sk_buff *skb = NULL; int type, dtype; /* deleted MCA's */ pmc_prev = NULL; for (pmc = mc_dereference(idev->mc_tomb, idev); pmc; pmc = pmc_next) { pmc_next = mc_dereference(pmc->next, idev); if (pmc->mca_sfmode == MCAST_INCLUDE) { type = MLD2_BLOCK_OLD_SOURCES; dtype = MLD2_BLOCK_OLD_SOURCES; skb = add_grec(skb, pmc, type, 1, 0, 0); skb = add_grec(skb, pmc, dtype, 1, 1, 0); } if (pmc->mca_crcount) { if (pmc->mca_sfmode == MCAST_EXCLUDE) { type = MLD2_CHANGE_TO_INCLUDE; skb = add_grec(skb, pmc, type, 1, 0, 0); } pmc->mca_crcount--; if (pmc->mca_crcount == 0) { mld_clear_zeros(&pmc->mca_tomb, idev); mld_clear_zeros(&pmc->mca_sources, idev); } } if (pmc->mca_crcount == 0 && !rcu_access_pointer(pmc->mca_tomb) && !rcu_access_pointer(pmc->mca_sources)) { if (pmc_prev) rcu_assign_pointer(pmc_prev->next, pmc_next); else rcu_assign_pointer(idev->mc_tomb, pmc_next); in6_dev_put(pmc->idev); kfree_rcu(pmc, rcu); } else pmc_prev = pmc; } /* change recs */ for_each_mc_mclock(idev, pmc) { if (pmc->mca_sfcount[MCAST_EXCLUDE]) { type = MLD2_BLOCK_OLD_SOURCES; dtype = MLD2_ALLOW_NEW_SOURCES; } else { type = MLD2_ALLOW_NEW_SOURCES; dtype = MLD2_BLOCK_OLD_SOURCES; } skb = add_grec(skb, pmc, type, 0, 0, 0); skb = add_grec(skb, pmc, dtype, 0, 1, 0); /* deleted sources */ /* filter mode changes */ if (pmc->mca_crcount) { if (pmc->mca_sfmode == MCAST_EXCLUDE) type = MLD2_CHANGE_TO_EXCLUDE; else type = MLD2_CHANGE_TO_INCLUDE; skb = add_grec(skb, pmc, type, 0, 0, 0); pmc->mca_crcount--; } } if (!skb) return; (void) mld_sendpack(skb); } static void igmp6_send(struct in6_addr *addr, struct net_device *dev, int type) { struct net *net = dev_net(dev); struct sock *sk = net->ipv6.igmp_sk; struct inet6_dev *idev; struct sk_buff *skb; struct mld_msg *hdr; const struct in6_addr *snd_addr, *saddr; struct in6_addr addr_buf; int hlen = LL_RESERVED_SPACE(dev); int tlen = dev->needed_tailroom; int err, len, payload_len, full_len; u8 ra[8] = { IPPROTO_ICMPV6, 0, IPV6_TLV_ROUTERALERT, 2, 0, 0, IPV6_TLV_PADN, 0 }; struct flowi6 fl6; struct dst_entry *dst; if (type == ICMPV6_MGM_REDUCTION) snd_addr = &in6addr_linklocal_allrouters; else snd_addr = addr; len = sizeof(struct icmp6hdr) + sizeof(struct in6_addr); payload_len = len + sizeof(ra); full_len = sizeof(struct ipv6hdr) + payload_len; rcu_read_lock(); IP6_INC_STATS(net, __in6_dev_get(dev), IPSTATS_MIB_OUTREQUESTS); rcu_read_unlock(); skb = sock_alloc_send_skb(sk, hlen + tlen + full_len, 1, &err); if (!skb) { rcu_read_lock(); IP6_INC_STATS(net, __in6_dev_get(dev), IPSTATS_MIB_OUTDISCARDS); rcu_read_unlock(); return; } skb->priority = TC_PRIO_CONTROL; skb_reserve(skb, hlen); if (ipv6_get_lladdr(dev, &addr_buf, IFA_F_TENTATIVE)) { /* <draft-ietf-magma-mld-source-05.txt>: * use unspecified address as the source address * when a valid link-local address is not available. */ saddr = &in6addr_any; } else saddr = &addr_buf; ip6_mc_hdr(sk, skb, dev, saddr, snd_addr, NEXTHDR_HOP, payload_len); skb_put_data(skb, ra, sizeof(ra)); hdr = skb_put_zero(skb, sizeof(struct mld_msg)); hdr->mld_type = type; hdr->mld_mca = *addr; hdr->mld_cksum = csum_ipv6_magic(saddr, snd_addr, len, IPPROTO_ICMPV6, csum_partial(hdr, len, 0)); rcu_read_lock(); idev = __in6_dev_get(skb->dev); icmpv6_flow_init(sk, &fl6, type, &ipv6_hdr(skb)->saddr, &ipv6_hdr(skb)->daddr, skb->dev->ifindex); dst = icmp6_dst_alloc(skb->dev, &fl6); if (IS_ERR(dst)) { err = PTR_ERR(dst); goto err_out; } skb_dst_set(skb, dst); err = NF_HOOK(NFPROTO_IPV6, NF_INET_LOCAL_OUT, net, sk, skb, NULL, skb->dev, dst_output); out: if (!err) { ICMP6MSGOUT_INC_STATS(net, idev, type); ICMP6_INC_STATS(net, idev, ICMP6_MIB_OUTMSGS); } else IP6_INC_STATS(net, idev, IPSTATS_MIB_OUTDISCARDS); rcu_read_unlock(); return; err_out: kfree_skb(skb); goto out; } /* called with mc_lock */ static void mld_send_initial_cr(struct inet6_dev *idev) { struct sk_buff *skb; struct ifmcaddr6 *pmc; int type; if (mld_in_v1_mode(idev)) return; skb = NULL; for_each_mc_mclock(idev, pmc) { if (pmc->mca_sfcount[MCAST_EXCLUDE]) type = MLD2_CHANGE_TO_EXCLUDE; else type = MLD2_ALLOW_NEW_SOURCES; skb = add_grec(skb, pmc, type, 0, 0, 1); } if (skb) mld_sendpack(skb); } void ipv6_mc_dad_complete(struct inet6_dev *idev) { mutex_lock(&idev->mc_lock); idev->mc_dad_count = idev->mc_qrv; if (idev->mc_dad_count) { mld_send_initial_cr(idev); idev->mc_dad_count--; if (idev->mc_dad_count) mld_dad_start_work(idev, unsolicited_report_interval(idev)); } mutex_unlock(&idev->mc_lock); } static void mld_dad_work(struct work_struct *work) { struct inet6_dev *idev = container_of(to_delayed_work(work), struct inet6_dev, mc_dad_work); mutex_lock(&idev->mc_lock); mld_send_initial_cr(idev); if (idev->mc_dad_count) { idev->mc_dad_count--; if (idev->mc_dad_count) mld_dad_start_work(idev, unsolicited_report_interval(idev)); } mutex_unlock(&idev->mc_lock); in6_dev_put(idev); } /* called with mc_lock */ static int ip6_mc_del1_src(struct ifmcaddr6 *pmc, int sfmode, const struct in6_addr *psfsrc) { struct ip6_sf_list *psf, *psf_prev; int rv = 0; psf_prev = NULL; for_each_psf_mclock(pmc, psf) { if (ipv6_addr_equal(&psf->sf_addr, psfsrc)) break; psf_prev = psf; } if (!psf || psf->sf_count[sfmode] == 0) { /* source filter not found, or count wrong => bug */ return -ESRCH; } psf->sf_count[sfmode]--; if (!psf->sf_count[MCAST_INCLUDE] && !psf->sf_count[MCAST_EXCLUDE]) { struct inet6_dev *idev = pmc->idev; /* no more filters for this source */ if (psf_prev) rcu_assign_pointer(psf_prev->sf_next, mc_dereference(psf->sf_next, idev)); else rcu_assign_pointer(pmc->mca_sources, mc_dereference(psf->sf_next, idev)); if (psf->sf_oldin && !(pmc->mca_flags & MAF_NOREPORT) && !mld_in_v1_mode(idev)) { psf->sf_crcount = idev->mc_qrv; rcu_assign_pointer(psf->sf_next, mc_dereference(pmc->mca_tomb, idev)); rcu_assign_pointer(pmc->mca_tomb, psf); rv = 1; } else { kfree_rcu(psf, rcu); } } return rv; } /* called with mc_lock */ static int ip6_mc_del_src(struct inet6_dev *idev, const struct in6_addr *pmca, int sfmode, int sfcount, const struct in6_addr *psfsrc, int delta) { struct ifmcaddr6 *pmc; int changerec = 0; int i, err; if (!idev) return -ENODEV; for_each_mc_mclock(idev, pmc) { if (ipv6_addr_equal(pmca, &pmc->mca_addr)) break; } if (!pmc) return -ESRCH; sf_markstate(pmc); if (!delta) { if (!pmc->mca_sfcount[sfmode]) return -EINVAL; pmc->mca_sfcount[sfmode]--; } err = 0; for (i = 0; i < sfcount; i++) { int rv = ip6_mc_del1_src(pmc, sfmode, &psfsrc[i]); changerec |= rv > 0; if (!err && rv < 0) err = rv; } if (pmc->mca_sfmode == MCAST_EXCLUDE && pmc->mca_sfcount[MCAST_EXCLUDE] == 0 && pmc->mca_sfcount[MCAST_INCLUDE]) { struct ip6_sf_list *psf; /* filter mode change */ pmc->mca_sfmode = MCAST_INCLUDE; pmc->mca_crcount = idev->mc_qrv; idev->mc_ifc_count = pmc->mca_crcount; for_each_psf_mclock(pmc, psf) psf->sf_crcount = 0; mld_ifc_event(pmc->idev); } else if (sf_setstate(pmc) || changerec) { mld_ifc_event(pmc->idev); } return err; } /* * Add multicast single-source filter to the interface list * called with mc_lock */ static int ip6_mc_add1_src(struct ifmcaddr6 *pmc, int sfmode, const struct in6_addr *psfsrc) { struct ip6_sf_list *psf, *psf_prev; psf_prev = NULL; for_each_psf_mclock(pmc, psf) { if (ipv6_addr_equal(&psf->sf_addr, psfsrc)) break; psf_prev = psf; } if (!psf) { psf = kzalloc(sizeof(*psf), GFP_KERNEL); if (!psf) return -ENOBUFS; psf->sf_addr = *psfsrc; if (psf_prev) { rcu_assign_pointer(psf_prev->sf_next, psf); } else { rcu_assign_pointer(pmc->mca_sources, psf); } } psf->sf_count[sfmode]++; return 0; } /* called with mc_lock */ static void sf_markstate(struct ifmcaddr6 *pmc) { struct ip6_sf_list *psf; int mca_xcount = pmc->mca_sfcount[MCAST_EXCLUDE]; for_each_psf_mclock(pmc, psf) { if (pmc->mca_sfcount[MCAST_EXCLUDE]) { psf->sf_oldin = mca_xcount == psf->sf_count[MCAST_EXCLUDE] && !psf->sf_count[MCAST_INCLUDE]; } else { psf->sf_oldin = psf->sf_count[MCAST_INCLUDE] != 0; } } } /* called with mc_lock */ static int sf_setstate(struct ifmcaddr6 *pmc) { struct ip6_sf_list *psf, *dpsf; int mca_xcount = pmc->mca_sfcount[MCAST_EXCLUDE]; int qrv = pmc->idev->mc_qrv; int new_in, rv; rv = 0; for_each_psf_mclock(pmc, psf) { if (pmc->mca_sfcount[MCAST_EXCLUDE]) { new_in = mca_xcount == psf->sf_count[MCAST_EXCLUDE] && !psf->sf_count[MCAST_INCLUDE]; } else new_in = psf->sf_count[MCAST_INCLUDE] != 0; if (new_in) { if (!psf->sf_oldin) { struct ip6_sf_list *prev = NULL; for_each_psf_tomb(pmc, dpsf) { if (ipv6_addr_equal(&dpsf->sf_addr, &psf->sf_addr)) break; prev = dpsf; } if (dpsf) { if (prev) rcu_assign_pointer(prev->sf_next, mc_dereference(dpsf->sf_next, pmc->idev)); else rcu_assign_pointer(pmc->mca_tomb, mc_dereference(dpsf->sf_next, pmc->idev)); kfree_rcu(dpsf, rcu); } psf->sf_crcount = qrv; rv++; } } else if (psf->sf_oldin) { psf->sf_crcount = 0; /* * add or update "delete" records if an active filter * is now inactive */ for_each_psf_tomb(pmc, dpsf) if (ipv6_addr_equal(&dpsf->sf_addr, &psf->sf_addr)) break; if (!dpsf) { dpsf = kmalloc(sizeof(*dpsf), GFP_KERNEL); if (!dpsf) continue; *dpsf = *psf; rcu_assign_pointer(dpsf->sf_next, mc_dereference(pmc->mca_tomb, pmc->idev)); rcu_assign_pointer(pmc->mca_tomb, dpsf); } dpsf->sf_crcount = qrv; rv++; } } return rv; } /* * Add multicast source filter list to the interface list * called with mc_lock */ static int ip6_mc_add_src(struct inet6_dev *idev, const struct in6_addr *pmca, int sfmode, int sfcount, const struct in6_addr *psfsrc, int delta) { struct ifmcaddr6 *pmc; int isexclude; int i, err; if (!idev) return -ENODEV; for_each_mc_mclock(idev, pmc) { if (ipv6_addr_equal(pmca, &pmc->mca_addr)) break; } if (!pmc) return -ESRCH; sf_markstate(pmc); isexclude = pmc->mca_sfmode == MCAST_EXCLUDE; if (!delta) pmc->mca_sfcount[sfmode]++; err = 0; for (i = 0; i < sfcount; i++) { err = ip6_mc_add1_src(pmc, sfmode, &psfsrc[i]); if (err) break; } if (err) { int j; if (!delta) pmc->mca_sfcount[sfmode]--; for (j = 0; j < i; j++) ip6_mc_del1_src(pmc, sfmode, &psfsrc[j]); } else if (isexclude != (pmc->mca_sfcount[MCAST_EXCLUDE] != 0)) { struct ip6_sf_list *psf; /* filter mode change */ if (pmc->mca_sfcount[MCAST_EXCLUDE]) pmc->mca_sfmode = MCAST_EXCLUDE; else if (pmc->mca_sfcount[MCAST_INCLUDE]) pmc->mca_sfmode = MCAST_INCLUDE; /* else no filters; keep old mode for reports */ pmc->mca_crcount = idev->mc_qrv; idev->mc_ifc_count = pmc->mca_crcount; for_each_psf_mclock(pmc, psf) psf->sf_crcount = 0; mld_ifc_event(idev); } else if (sf_setstate(pmc)) { mld_ifc_event(idev); } return err; } /* called with mc_lock */ static void ip6_mc_clear_src(struct ifmcaddr6 *pmc) { struct ip6_sf_list *psf, *nextpsf; for (psf = mc_dereference(pmc->mca_tomb, pmc->idev); psf; psf = nextpsf) { nextpsf = mc_dereference(psf->sf_next, pmc->idev); kfree_rcu(psf, rcu); } RCU_INIT_POINTER(pmc->mca_tomb, NULL); for (psf = mc_dereference(pmc->mca_sources, pmc->idev); psf; psf = nextpsf) { nextpsf = mc_dereference(psf->sf_next, pmc->idev); kfree_rcu(psf, rcu); } RCU_INIT_POINTER(pmc->mca_sources, NULL); pmc->mca_sfmode = MCAST_EXCLUDE; pmc->mca_sfcount[MCAST_INCLUDE] = 0; pmc->mca_sfcount[MCAST_EXCLUDE] = 1; } /* called with mc_lock */ static void igmp6_join_group(struct ifmcaddr6 *ma) { unsigned long delay; if (ma->mca_flags & MAF_NOREPORT) return; igmp6_send(&ma->mca_addr, ma->idev->dev, ICMPV6_MGM_REPORT); delay = get_random_u32_below(unsolicited_report_interval(ma->idev)); if (cancel_delayed_work(&ma->mca_work)) { refcount_dec(&ma->mca_refcnt); delay = ma->mca_work.timer.expires - jiffies; } if (!mod_delayed_work(mld_wq, &ma->mca_work, delay)) refcount_inc(&ma->mca_refcnt); ma->mca_flags |= MAF_TIMER_RUNNING | MAF_LAST_REPORTER; } static int ip6_mc_leave_src(struct sock *sk, struct ipv6_mc_socklist *iml, struct inet6_dev *idev) { struct ip6_sf_socklist *psl; int err; psl = sock_dereference(iml->sflist, sk); if (idev) mutex_lock(&idev->mc_lock); if (!psl) { /* any-source empty exclude case */ err = ip6_mc_del_src(idev, &iml->addr, iml->sfmode, 0, NULL, 0); } else { err = ip6_mc_del_src(idev, &iml->addr, iml->sfmode, psl->sl_count, psl->sl_addr, 0); RCU_INIT_POINTER(iml->sflist, NULL); atomic_sub(struct_size(psl, sl_addr, psl->sl_max), &sk->sk_omem_alloc); kfree_rcu(psl, rcu); } if (idev) mutex_unlock(&idev->mc_lock); return err; } /* called with mc_lock */ static void igmp6_leave_group(struct ifmcaddr6 *ma) { if (mld_in_v1_mode(ma->idev)) { if (ma->mca_flags & MAF_LAST_REPORTER) { igmp6_send(&ma->mca_addr, ma->idev->dev, ICMPV6_MGM_REDUCTION); } } else { mld_add_delrec(ma->idev, ma); mld_ifc_event(ma->idev); } } static void mld_gq_work(struct work_struct *work) { struct inet6_dev *idev = container_of(to_delayed_work(work), struct inet6_dev, mc_gq_work); mutex_lock(&idev->mc_lock); mld_send_report(idev, NULL); idev->mc_gq_running = 0; mutex_unlock(&idev->mc_lock); in6_dev_put(idev); } static void mld_ifc_work(struct work_struct *work) { struct inet6_dev *idev = container_of(to_delayed_work(work), struct inet6_dev, mc_ifc_work); mutex_lock(&idev->mc_lock); mld_send_cr(idev); if (idev->mc_ifc_count) { idev->mc_ifc_count--; if (idev->mc_ifc_count) mld_ifc_start_work(idev, unsolicited_report_interval(idev)); } mutex_unlock(&idev->mc_lock); in6_dev_put(idev); } /* called with mc_lock */ static void mld_ifc_event(struct inet6_dev *idev) { if (mld_in_v1_mode(idev)) return; idev->mc_ifc_count = idev->mc_qrv; mld_ifc_start_work(idev, 1); } static void mld_mca_work(struct work_struct *work) { struct ifmcaddr6 *ma = container_of(to_delayed_work(work), struct ifmcaddr6, mca_work); mutex_lock(&ma->idev->mc_lock); if (mld_in_v1_mode(ma->idev)) igmp6_send(&ma->mca_addr, ma->idev->dev, ICMPV6_MGM_REPORT); else mld_send_report(ma->idev, ma); ma->mca_flags |= MAF_LAST_REPORTER; ma->mca_flags &= ~MAF_TIMER_RUNNING; mutex_unlock(&ma->idev->mc_lock); ma_put(ma); } /* Device changing type */ void ipv6_mc_unmap(struct inet6_dev *idev) { struct ifmcaddr6 *i; /* Install multicast list, except for all-nodes (already installed) */ mutex_lock(&idev->mc_lock); for_each_mc_mclock(idev, i) igmp6_group_dropped(i); mutex_unlock(&idev->mc_lock); } void ipv6_mc_remap(struct inet6_dev *idev) { ipv6_mc_up(idev); } /* Device going down */ void ipv6_mc_down(struct inet6_dev *idev) { struct ifmcaddr6 *i; mutex_lock(&idev->mc_lock); /* Withdraw multicast list */ for_each_mc_mclock(idev, i) igmp6_group_dropped(i); mutex_unlock(&idev->mc_lock); /* Should stop work after group drop. or we will * start work again in mld_ifc_event() */ mld_query_stop_work(idev); mld_report_stop_work(idev); mutex_lock(&idev->mc_lock); mld_ifc_stop_work(idev); mld_gq_stop_work(idev); mutex_unlock(&idev->mc_lock); mld_dad_stop_work(idev); } static void ipv6_mc_reset(struct inet6_dev *idev) { idev->mc_qrv = sysctl_mld_qrv; idev->mc_qi = MLD_QI_DEFAULT; idev->mc_qri = MLD_QRI_DEFAULT; idev->mc_v1_seen = 0; idev->mc_maxdelay = unsolicited_report_interval(idev); } /* Device going up */ void ipv6_mc_up(struct inet6_dev *idev) { struct ifmcaddr6 *i; /* Install multicast list, except for all-nodes (already installed) */ ipv6_mc_reset(idev); mutex_lock(&idev->mc_lock); for_each_mc_mclock(idev, i) { mld_del_delrec(idev, i); igmp6_group_added(i); } mutex_unlock(&idev->mc_lock); } /* IPv6 device initialization. */ void ipv6_mc_init_dev(struct inet6_dev *idev) { idev->mc_gq_running = 0; INIT_DELAYED_WORK(&idev->mc_gq_work, mld_gq_work); RCU_INIT_POINTER(idev->mc_tomb, NULL); idev->mc_ifc_count = 0; INIT_DELAYED_WORK(&idev->mc_ifc_work, mld_ifc_work); INIT_DELAYED_WORK(&idev->mc_dad_work, mld_dad_work); INIT_DELAYED_WORK(&idev->mc_query_work, mld_query_work); INIT_DELAYED_WORK(&idev->mc_report_work, mld_report_work); skb_queue_head_init(&idev->mc_query_queue); skb_queue_head_init(&idev->mc_report_queue); spin_lock_init(&idev->mc_query_lock); spin_lock_init(&idev->mc_report_lock); mutex_init(&idev->mc_lock); ipv6_mc_reset(idev); } /* * Device is about to be destroyed: clean up. */ void ipv6_mc_destroy_dev(struct inet6_dev *idev) { struct ifmcaddr6 *i; /* Deactivate works */ ipv6_mc_down(idev); mutex_lock(&idev->mc_lock); mld_clear_delrec(idev); mutex_unlock(&idev->mc_lock); mld_clear_query(idev); mld_clear_report(idev); /* Delete all-nodes address. */ /* We cannot call ipv6_dev_mc_dec() directly, our caller in * addrconf.c has NULL'd out dev->ip6_ptr so in6_dev_get() will * fail. */ __ipv6_dev_mc_dec(idev, &in6addr_linklocal_allnodes); if (idev->cnf.forwarding) __ipv6_dev_mc_dec(idev, &in6addr_linklocal_allrouters); mutex_lock(&idev->mc_lock); while ((i = mc_dereference(idev->mc_list, idev))) { rcu_assign_pointer(idev->mc_list, mc_dereference(i->next, idev)); ip6_mc_clear_src(i); ma_put(i); } mutex_unlock(&idev->mc_lock); } static void ipv6_mc_rejoin_groups(struct inet6_dev *idev) { struct ifmcaddr6 *pmc; ASSERT_RTNL(); mutex_lock(&idev->mc_lock); if (mld_in_v1_mode(idev)) { for_each_mc_mclock(idev, pmc) igmp6_join_group(pmc); } else { mld_send_report(idev, NULL); } mutex_unlock(&idev->mc_lock); } static int ipv6_mc_netdev_event(struct notifier_block *this, unsigned long event, void *ptr) { struct net_device *dev = netdev_notifier_info_to_dev(ptr); struct inet6_dev *idev = __in6_dev_get(dev); switch (event) { case NETDEV_RESEND_IGMP: if (idev) ipv6_mc_rejoin_groups(idev); break; default: break; } return NOTIFY_DONE; } static struct notifier_block igmp6_netdev_notifier = { .notifier_call = ipv6_mc_netdev_event, }; #ifdef CONFIG_PROC_FS struct igmp6_mc_iter_state { struct seq_net_private p; struct net_device *dev; struct inet6_dev *idev; }; #define igmp6_mc_seq_private(seq) ((struct igmp6_mc_iter_state *)(seq)->private) static inline struct ifmcaddr6 *igmp6_mc_get_first(struct seq_file *seq) { struct ifmcaddr6 *im = NULL; struct igmp6_mc_iter_state *state = igmp6_mc_seq_private(seq); struct net *net = seq_file_net(seq); state->idev = NULL; for_each_netdev_rcu(net, state->dev) { struct inet6_dev *idev; idev = __in6_dev_get(state->dev); if (!idev) continue; im = rcu_dereference(idev->mc_list); if (im) { state->idev = idev; break; } } return im; } static struct ifmcaddr6 *igmp6_mc_get_next(struct seq_file *seq, struct ifmcaddr6 *im) { struct igmp6_mc_iter_state *state = igmp6_mc_seq_private(seq); im = rcu_dereference(im->next); while (!im) { state->dev = next_net_device_rcu(state->dev); if (!state->dev) { state->idev = NULL; break; } state->idev = __in6_dev_get(state->dev); if (!state->idev) continue; im = rcu_dereference(state->idev->mc_list); } return im; } static struct ifmcaddr6 *igmp6_mc_get_idx(struct seq_file *seq, loff_t pos) { struct ifmcaddr6 *im = igmp6_mc_get_first(seq); if (im) while (pos && (im = igmp6_mc_get_next(seq, im)) != NULL) --pos; return pos ? NULL : im; } static void *igmp6_mc_seq_start(struct seq_file *seq, loff_t *pos) __acquires(RCU) { rcu_read_lock(); return igmp6_mc_get_idx(seq, *pos); } static void *igmp6_mc_seq_next(struct seq_file *seq, void *v, loff_t *pos) { struct ifmcaddr6 *im = igmp6_mc_get_next(seq, v); ++*pos; return im; } static void igmp6_mc_seq_stop(struct seq_file *seq, void *v) __releases(RCU) { struct igmp6_mc_iter_state *state = igmp6_mc_seq_private(seq); if (likely(state->idev)) state->idev = NULL; state->dev = NULL; rcu_read_unlock(); } static int igmp6_mc_seq_show(struct seq_file *seq, void *v) { struct ifmcaddr6 *im = (struct ifmcaddr6 *)v; struct igmp6_mc_iter_state *state = igmp6_mc_seq_private(seq); seq_printf(seq, "%-4d %-15s %pi6 %5d %08X %ld\n", state->dev->ifindex, state->dev->name, &im->mca_addr, im->mca_users, im->mca_flags, (im->mca_flags & MAF_TIMER_RUNNING) ? jiffies_to_clock_t(im->mca_work.timer.expires - jiffies) : 0); return 0; } static const struct seq_operations igmp6_mc_seq_ops = { .start = igmp6_mc_seq_start, .next = igmp6_mc_seq_next, .stop = igmp6_mc_seq_stop, .show = igmp6_mc_seq_show, }; struct igmp6_mcf_iter_state { struct seq_net_private p; struct net_device *dev; struct inet6_dev *idev; struct ifmcaddr6 *im; }; #define igmp6_mcf_seq_private(seq) ((struct igmp6_mcf_iter_state *)(seq)->private) static inline struct ip6_sf_list *igmp6_mcf_get_first(struct seq_file *seq) { struct ip6_sf_list *psf = NULL; struct ifmcaddr6 *im = NULL; struct igmp6_mcf_iter_state *state = igmp6_mcf_seq_private(seq); struct net *net = seq_file_net(seq); state->idev = NULL; state->im = NULL; for_each_netdev_rcu(net, state->dev) { struct inet6_dev *idev; idev = __in6_dev_get(state->dev); if (unlikely(idev == NULL)) continue; im = rcu_dereference(idev->mc_list); if (likely(im)) { psf = rcu_dereference(im->mca_sources); if (likely(psf)) { state->im = im; state->idev = idev; break; } } } return psf; } static struct ip6_sf_list *igmp6_mcf_get_next(struct seq_file *seq, struct ip6_sf_list *psf) { struct igmp6_mcf_iter_state *state = igmp6_mcf_seq_private(seq); psf = rcu_dereference(psf->sf_next); while (!psf) { state->im = rcu_dereference(state->im->next); while (!state->im) { state->dev = next_net_device_rcu(state->dev); if (!state->dev) { state->idev = NULL; goto out; } state->idev = __in6_dev_get(state->dev); if (!state->idev) continue; state->im = rcu_dereference(state->idev->mc_list); } psf = rcu_dereference(state->im->mca_sources); } out: return psf; } static struct ip6_sf_list *igmp6_mcf_get_idx(struct seq_file *seq, loff_t pos) { struct ip6_sf_list *psf = igmp6_mcf_get_first(seq); if (psf) while (pos && (psf = igmp6_mcf_get_next(seq, psf)) != NULL) --pos; return pos ? NULL : psf; } static void *igmp6_mcf_seq_start(struct seq_file *seq, loff_t *pos) __acquires(RCU) { rcu_read_lock(); return *pos ? igmp6_mcf_get_idx(seq, *pos - 1) : SEQ_START_TOKEN; } static void *igmp6_mcf_seq_next(struct seq_file *seq, void *v, loff_t *pos) { struct ip6_sf_list *psf; if (v == SEQ_START_TOKEN) psf = igmp6_mcf_get_first(seq); else psf = igmp6_mcf_get_next(seq, v); ++*pos; return psf; } static void igmp6_mcf_seq_stop(struct seq_file *seq, void *v) __releases(RCU) { struct igmp6_mcf_iter_state *state = igmp6_mcf_seq_private(seq); if (likely(state->im)) state->im = NULL; if (likely(state->idev)) state->idev = NULL; state->dev = NULL; rcu_read_unlock(); } static int igmp6_mcf_seq_show(struct seq_file *seq, void *v) { struct ip6_sf_list *psf = (struct ip6_sf_list *)v; struct igmp6_mcf_iter_state *state = igmp6_mcf_seq_private(seq); if (v == SEQ_START_TOKEN) { seq_puts(seq, "Idx Device Multicast Address Source Address INC EXC\n"); } else { seq_printf(seq, "%3d %6.6s %pi6 %pi6 %6lu %6lu\n", state->dev->ifindex, state->dev->name, &state->im->mca_addr, &psf->sf_addr, psf->sf_count[MCAST_INCLUDE], psf->sf_count[MCAST_EXCLUDE]); } return 0; } static const struct seq_operations igmp6_mcf_seq_ops = { .start = igmp6_mcf_seq_start, .next = igmp6_mcf_seq_next, .stop = igmp6_mcf_seq_stop, .show = igmp6_mcf_seq_show, }; static int __net_init igmp6_proc_init(struct net *net) { int err; err = -ENOMEM; if (!proc_create_net("igmp6", 0444, net->proc_net, &igmp6_mc_seq_ops, sizeof(struct igmp6_mc_iter_state))) goto out; if (!proc_create_net("mcfilter6", 0444, net->proc_net, &igmp6_mcf_seq_ops, sizeof(struct igmp6_mcf_iter_state))) goto out_proc_net_igmp6; err = 0; out: return err; out_proc_net_igmp6: remove_proc_entry("igmp6", net->proc_net); goto out; } static void __net_exit igmp6_proc_exit(struct net *net) { remove_proc_entry("mcfilter6", net->proc_net); remove_proc_entry("igmp6", net->proc_net); } #else static inline int igmp6_proc_init(struct net *net) { return 0; } static inline void igmp6_proc_exit(struct net *net) { } #endif static int __net_init igmp6_net_init(struct net *net) { int err; err = inet_ctl_sock_create(&net->ipv6.igmp_sk, PF_INET6, SOCK_RAW, IPPROTO_ICMPV6, net); if (err < 0) { pr_err("Failed to initialize the IGMP6 control socket (err %d)\n", err); goto out; } inet6_sk(net->ipv6.igmp_sk)->hop_limit = 1; net->ipv6.igmp_sk->sk_allocation = GFP_KERNEL; err = inet_ctl_sock_create(&net->ipv6.mc_autojoin_sk, PF_INET6, SOCK_RAW, IPPROTO_ICMPV6, net); if (err < 0) { pr_err("Failed to initialize the IGMP6 autojoin socket (err %d)\n", err); goto out_sock_create; } err = igmp6_proc_init(net); if (err) goto out_sock_create_autojoin; return 0; out_sock_create_autojoin: inet_ctl_sock_destroy(net->ipv6.mc_autojoin_sk); out_sock_create: inet_ctl_sock_destroy(net->ipv6.igmp_sk); out: return err; } static void __net_exit igmp6_net_exit(struct net *net) { inet_ctl_sock_destroy(net->ipv6.igmp_sk); inet_ctl_sock_destroy(net->ipv6.mc_autojoin_sk); igmp6_proc_exit(net); } static struct pernet_operations igmp6_net_ops = { .init = igmp6_net_init, .exit = igmp6_net_exit, }; int __init igmp6_init(void) { int err; err = register_pernet_subsys(&igmp6_net_ops); if (err) return err; mld_wq = create_workqueue("mld"); if (!mld_wq) { unregister_pernet_subsys(&igmp6_net_ops); return -ENOMEM; } return err; } int __init igmp6_late_init(void) { return register_netdevice_notifier(&igmp6_netdev_notifier); } void igmp6_cleanup(void) { unregister_pernet_subsys(&igmp6_net_ops); destroy_workqueue(mld_wq); } void igmp6_late_cleanup(void) { unregister_netdevice_notifier(&igmp6_netdev_notifier); } |
| 417 417 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 | /* SPDX-License-Identifier: GPL-2.0 */ #undef TRACE_SYSTEM #define TRACE_SYSTEM cgroup #if !defined(_TRACE_CGROUP_H) || defined(TRACE_HEADER_MULTI_READ) #define _TRACE_CGROUP_H #include <linux/cgroup.h> #include <linux/tracepoint.h> DECLARE_EVENT_CLASS(cgroup_root, TP_PROTO(struct cgroup_root *root), TP_ARGS(root), TP_STRUCT__entry( __field( int, root ) __field( u16, ss_mask ) __string( name, root->name ) ), TP_fast_assign( __entry->root = root->hierarchy_id; __entry->ss_mask = root->subsys_mask; __assign_str(name); ), TP_printk("root=%d ss_mask=%#x name=%s", __entry->root, __entry->ss_mask, __get_str(name)) ); DEFINE_EVENT(cgroup_root, cgroup_setup_root, TP_PROTO(struct cgroup_root *root), TP_ARGS(root) ); DEFINE_EVENT(cgroup_root, cgroup_destroy_root, TP_PROTO(struct cgroup_root *root), TP_ARGS(root) ); DEFINE_EVENT(cgroup_root, cgroup_remount, TP_PROTO(struct cgroup_root *root), TP_ARGS(root) ); DECLARE_EVENT_CLASS(cgroup, TP_PROTO(struct cgroup *cgrp, const char *path), TP_ARGS(cgrp, path), TP_STRUCT__entry( __field( int, root ) __field( int, level ) __field( u64, id ) __string( path, path ) ), TP_fast_assign( __entry->root = cgrp->root->hierarchy_id; __entry->id = cgroup_id(cgrp); __entry->level = cgrp->level; __assign_str(path); ), TP_printk("root=%d id=%llu level=%d path=%s", __entry->root, __entry->id, __entry->level, __get_str(path)) ); DEFINE_EVENT(cgroup, cgroup_mkdir, TP_PROTO(struct cgroup *cgrp, const char *path), TP_ARGS(cgrp, path) ); DEFINE_EVENT(cgroup, cgroup_rmdir, TP_PROTO(struct cgroup *cgrp, const char *path), TP_ARGS(cgrp, path) ); DEFINE_EVENT(cgroup, cgroup_release, TP_PROTO(struct cgroup *cgrp, const char *path), TP_ARGS(cgrp, path) ); DEFINE_EVENT(cgroup, cgroup_rename, TP_PROTO(struct cgroup *cgrp, const char *path), TP_ARGS(cgrp, path) ); DEFINE_EVENT(cgroup, cgroup_freeze, TP_PROTO(struct cgroup *cgrp, const char *path), TP_ARGS(cgrp, path) ); DEFINE_EVENT(cgroup, cgroup_unfreeze, TP_PROTO(struct cgroup *cgrp, const char *path), TP_ARGS(cgrp, path) ); DECLARE_EVENT_CLASS(cgroup_migrate, TP_PROTO(struct cgroup *dst_cgrp, const char *path, struct task_struct *task, bool threadgroup), TP_ARGS(dst_cgrp, path, task, threadgroup), TP_STRUCT__entry( __field( int, dst_root ) __field( int, dst_level ) __field( u64, dst_id ) __field( int, pid ) __string( dst_path, path ) __string( comm, task->comm ) ), TP_fast_assign( __entry->dst_root = dst_cgrp->root->hierarchy_id; __entry->dst_id = cgroup_id(dst_cgrp); __entry->dst_level = dst_cgrp->level; __assign_str(dst_path); __entry->pid = task->pid; __assign_str(comm); ), TP_printk("dst_root=%d dst_id=%llu dst_level=%d dst_path=%s pid=%d comm=%s", __entry->dst_root, __entry->dst_id, __entry->dst_level, __get_str(dst_path), __entry->pid, __get_str(comm)) ); DEFINE_EVENT(cgroup_migrate, cgroup_attach_task, TP_PROTO(struct cgroup *dst_cgrp, const char *path, struct task_struct *task, bool threadgroup), TP_ARGS(dst_cgrp, path, task, threadgroup) ); DEFINE_EVENT(cgroup_migrate, cgroup_transfer_tasks, TP_PROTO(struct cgroup *dst_cgrp, const char *path, struct task_struct *task, bool threadgroup), TP_ARGS(dst_cgrp, path, task, threadgroup) ); DECLARE_EVENT_CLASS(cgroup_event, TP_PROTO(struct cgroup *cgrp, const char *path, int val), TP_ARGS(cgrp, path, val), TP_STRUCT__entry( __field( int, root ) __field( int, level ) __field( u64, id ) __string( path, path ) __field( int, val ) ), TP_fast_assign( __entry->root = cgrp->root->hierarchy_id; __entry->id = cgroup_id(cgrp); __entry->level = cgrp->level; __assign_str(path); __entry->val = val; ), TP_printk("root=%d id=%llu level=%d path=%s val=%d", __entry->root, __entry->id, __entry->level, __get_str(path), __entry->val) ); DEFINE_EVENT(cgroup_event, cgroup_notify_populated, TP_PROTO(struct cgroup *cgrp, const char *path, int val), TP_ARGS(cgrp, path, val) ); DEFINE_EVENT(cgroup_event, cgroup_notify_frozen, TP_PROTO(struct cgroup *cgrp, const char *path, int val), TP_ARGS(cgrp, path, val) ); DECLARE_EVENT_CLASS(cgroup_rstat, TP_PROTO(struct cgroup *cgrp, int cpu, bool contended), TP_ARGS(cgrp, cpu, contended), TP_STRUCT__entry( __field( int, root ) __field( int, level ) __field( u64, id ) __field( int, cpu ) __field( bool, contended ) ), TP_fast_assign( __entry->root = cgrp->root->hierarchy_id; __entry->id = cgroup_id(cgrp); __entry->level = cgrp->level; __entry->cpu = cpu; __entry->contended = contended; ), TP_printk("root=%d id=%llu level=%d cpu=%d lock contended:%d", __entry->root, __entry->id, __entry->level, __entry->cpu, __entry->contended) ); /* Related to global: cgroup_rstat_lock */ DEFINE_EVENT(cgroup_rstat, cgroup_rstat_lock_contended, TP_PROTO(struct cgroup *cgrp, int cpu, bool contended), TP_ARGS(cgrp, cpu, contended) ); DEFINE_EVENT(cgroup_rstat, cgroup_rstat_locked, TP_PROTO(struct cgroup *cgrp, int cpu, bool contended), TP_ARGS(cgrp, cpu, contended) ); DEFINE_EVENT(cgroup_rstat, cgroup_rstat_unlock, TP_PROTO(struct cgroup *cgrp, int cpu, bool contended), TP_ARGS(cgrp, cpu, contended) ); /* Related to per CPU: cgroup_rstat_cpu_lock */ DEFINE_EVENT(cgroup_rstat, cgroup_rstat_cpu_lock_contended, TP_PROTO(struct cgroup *cgrp, int cpu, bool contended), TP_ARGS(cgrp, cpu, contended) ); DEFINE_EVENT(cgroup_rstat, cgroup_rstat_cpu_lock_contended_fastpath, TP_PROTO(struct cgroup *cgrp, int cpu, bool contended), TP_ARGS(cgrp, cpu, contended) ); DEFINE_EVENT(cgroup_rstat, cgroup_rstat_cpu_locked, TP_PROTO(struct cgroup *cgrp, int cpu, bool contended), TP_ARGS(cgrp, cpu, contended) ); DEFINE_EVENT(cgroup_rstat, cgroup_rstat_cpu_locked_fastpath, TP_PROTO(struct cgroup *cgrp, int cpu, bool contended), TP_ARGS(cgrp, cpu, contended) ); DEFINE_EVENT(cgroup_rstat, cgroup_rstat_cpu_unlock, TP_PROTO(struct cgroup *cgrp, int cpu, bool contended), TP_ARGS(cgrp, cpu, contended) ); DEFINE_EVENT(cgroup_rstat, cgroup_rstat_cpu_unlock_fastpath, TP_PROTO(struct cgroup *cgrp, int cpu, bool contended), TP_ARGS(cgrp, cpu, contended) ); #endif /* _TRACE_CGROUP_H */ /* This part must be outside protection */ #include <trace/define_trace.h> |
| 3 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _LINUX_INETDEVICE_H #define _LINUX_INETDEVICE_H #ifdef __KERNEL__ #include <linux/bitmap.h> #include <linux/if.h> #include <linux/ip.h> #include <linux/netdevice.h> #include <linux/rcupdate.h> #include <linux/timer.h> #include <linux/sysctl.h> #include <linux/rtnetlink.h> #include <linux/refcount.h> struct ipv4_devconf { void *sysctl; int data[IPV4_DEVCONF_MAX]; DECLARE_BITMAP(state, IPV4_DEVCONF_MAX); }; #define MC_HASH_SZ_LOG 9 struct in_device { struct net_device *dev; netdevice_tracker dev_tracker; refcount_t refcnt; int dead; struct in_ifaddr __rcu *ifa_list;/* IP ifaddr chain */ struct ip_mc_list __rcu *mc_list; /* IP multicast filter chain */ struct ip_mc_list __rcu * __rcu *mc_hash; int mc_count; /* Number of installed mcasts */ spinlock_t mc_tomb_lock; struct ip_mc_list *mc_tomb; unsigned long mr_v1_seen; unsigned long mr_v2_seen; unsigned long mr_maxdelay; unsigned long mr_qi; /* Query Interval */ unsigned long mr_qri; /* Query Response Interval */ unsigned char mr_qrv; /* Query Robustness Variable */ unsigned char mr_gq_running; u32 mr_ifc_count; struct timer_list mr_gq_timer; /* general query timer */ struct timer_list mr_ifc_timer; /* interface change timer */ struct neigh_parms *arp_parms; struct ipv4_devconf cnf; struct rcu_head rcu_head; }; #define IPV4_DEVCONF(cnf, attr) ((cnf).data[IPV4_DEVCONF_ ## attr - 1]) #define IPV4_DEVCONF_RO(cnf, attr) READ_ONCE(IPV4_DEVCONF(cnf, attr)) #define IPV4_DEVCONF_ALL(net, attr) \ IPV4_DEVCONF((*(net)->ipv4.devconf_all), attr) #define IPV4_DEVCONF_ALL_RO(net, attr) READ_ONCE(IPV4_DEVCONF_ALL(net, attr)) static inline int ipv4_devconf_get(const struct in_device *in_dev, int index) { index--; return READ_ONCE(in_dev->cnf.data[index]); } static inline void ipv4_devconf_set(struct in_device *in_dev, int index, int val) { index--; set_bit(index, in_dev->cnf.state); WRITE_ONCE(in_dev->cnf.data[index], val); } static inline void ipv4_devconf_setall(struct in_device *in_dev) { bitmap_fill(in_dev->cnf.state, IPV4_DEVCONF_MAX); } #define IN_DEV_CONF_GET(in_dev, attr) \ ipv4_devconf_get((in_dev), IPV4_DEVCONF_ ## attr) #define IN_DEV_CONF_SET(in_dev, attr, val) \ ipv4_devconf_set((in_dev), IPV4_DEVCONF_ ## attr, (val)) #define IN_DEV_ANDCONF(in_dev, attr) \ (IPV4_DEVCONF_ALL_RO(dev_net(in_dev->dev), attr) && \ IN_DEV_CONF_GET((in_dev), attr)) #define IN_DEV_NET_ORCONF(in_dev, net, attr) \ (IPV4_DEVCONF_ALL_RO(net, attr) || \ IN_DEV_CONF_GET((in_dev), attr)) #define IN_DEV_ORCONF(in_dev, attr) \ IN_DEV_NET_ORCONF(in_dev, dev_net(in_dev->dev), attr) #define IN_DEV_MAXCONF(in_dev, attr) \ (max(IPV4_DEVCONF_ALL_RO(dev_net(in_dev->dev), attr), \ IN_DEV_CONF_GET((in_dev), attr))) #define IN_DEV_FORWARD(in_dev) IN_DEV_CONF_GET((in_dev), FORWARDING) #define IN_DEV_MFORWARD(in_dev) IN_DEV_ANDCONF((in_dev), MC_FORWARDING) #define IN_DEV_BFORWARD(in_dev) IN_DEV_ANDCONF((in_dev), BC_FORWARDING) #define IN_DEV_RPFILTER(in_dev) IN_DEV_MAXCONF((in_dev), RP_FILTER) #define IN_DEV_SRC_VMARK(in_dev) IN_DEV_ORCONF((in_dev), SRC_VMARK) #define IN_DEV_SOURCE_ROUTE(in_dev) IN_DEV_ANDCONF((in_dev), \ ACCEPT_SOURCE_ROUTE) #define IN_DEV_ACCEPT_LOCAL(in_dev) IN_DEV_ORCONF((in_dev), ACCEPT_LOCAL) #define IN_DEV_BOOTP_RELAY(in_dev) IN_DEV_ANDCONF((in_dev), BOOTP_RELAY) #define IN_DEV_LOG_MARTIANS(in_dev) IN_DEV_ORCONF((in_dev), LOG_MARTIANS) #define IN_DEV_PROXY_ARP(in_dev) IN_DEV_ORCONF((in_dev), PROXY_ARP) #define IN_DEV_PROXY_ARP_PVLAN(in_dev) IN_DEV_ORCONF((in_dev), PROXY_ARP_PVLAN) #define IN_DEV_SHARED_MEDIA(in_dev) IN_DEV_ORCONF((in_dev), SHARED_MEDIA) #define IN_DEV_TX_REDIRECTS(in_dev) IN_DEV_ORCONF((in_dev), SEND_REDIRECTS) #define IN_DEV_SEC_REDIRECTS(in_dev) IN_DEV_ORCONF((in_dev), \ SECURE_REDIRECTS) #define IN_DEV_IDTAG(in_dev) IN_DEV_CONF_GET(in_dev, TAG) #define IN_DEV_MEDIUM_ID(in_dev) IN_DEV_CONF_GET(in_dev, MEDIUM_ID) #define IN_DEV_PROMOTE_SECONDARIES(in_dev) \ IN_DEV_ORCONF((in_dev), \ PROMOTE_SECONDARIES) #define IN_DEV_ROUTE_LOCALNET(in_dev) IN_DEV_ORCONF(in_dev, ROUTE_LOCALNET) #define IN_DEV_NET_ROUTE_LOCALNET(in_dev, net) \ IN_DEV_NET_ORCONF(in_dev, net, ROUTE_LOCALNET) #define IN_DEV_RX_REDIRECTS(in_dev) \ ((IN_DEV_FORWARD(in_dev) && \ IN_DEV_ANDCONF((in_dev), ACCEPT_REDIRECTS)) \ || (!IN_DEV_FORWARD(in_dev) && \ IN_DEV_ORCONF((in_dev), ACCEPT_REDIRECTS))) #define IN_DEV_IGNORE_ROUTES_WITH_LINKDOWN(in_dev) \ IN_DEV_ORCONF((in_dev), IGNORE_ROUTES_WITH_LINKDOWN) #define IN_DEV_ARPFILTER(in_dev) IN_DEV_ORCONF((in_dev), ARPFILTER) #define IN_DEV_ARP_ACCEPT(in_dev) IN_DEV_MAXCONF((in_dev), ARP_ACCEPT) #define IN_DEV_ARP_ANNOUNCE(in_dev) IN_DEV_MAXCONF((in_dev), ARP_ANNOUNCE) #define IN_DEV_ARP_IGNORE(in_dev) IN_DEV_MAXCONF((in_dev), ARP_IGNORE) #define IN_DEV_ARP_NOTIFY(in_dev) IN_DEV_MAXCONF((in_dev), ARP_NOTIFY) #define IN_DEV_ARP_EVICT_NOCARRIER(in_dev) IN_DEV_ANDCONF((in_dev), \ ARP_EVICT_NOCARRIER) struct in_ifaddr { struct hlist_node addr_lst; struct in_ifaddr __rcu *ifa_next; struct in_device *ifa_dev; struct rcu_head rcu_head; __be32 ifa_local; __be32 ifa_address; __be32 ifa_mask; __u32 ifa_rt_priority; __be32 ifa_broadcast; unsigned char ifa_scope; unsigned char ifa_prefixlen; unsigned char ifa_proto; __u32 ifa_flags; char ifa_label[IFNAMSIZ]; /* In seconds, relative to tstamp. Expiry is at tstamp + HZ * lft. */ __u32 ifa_valid_lft; __u32 ifa_preferred_lft; unsigned long ifa_cstamp; /* created timestamp */ unsigned long ifa_tstamp; /* updated timestamp */ }; struct in_validator_info { __be32 ivi_addr; struct in_device *ivi_dev; struct netlink_ext_ack *extack; }; int register_inetaddr_notifier(struct notifier_block *nb); int unregister_inetaddr_notifier(struct notifier_block *nb); int register_inetaddr_validator_notifier(struct notifier_block *nb); int unregister_inetaddr_validator_notifier(struct notifier_block *nb); void inet_netconf_notify_devconf(struct net *net, int event, int type, int ifindex, struct ipv4_devconf *devconf); struct net_device *__ip_dev_find(struct net *net, __be32 addr, bool devref); static inline struct net_device *ip_dev_find(struct net *net, __be32 addr) { return __ip_dev_find(net, addr, true); } int inet_addr_onlink(struct in_device *in_dev, __be32 a, __be32 b); int devinet_ioctl(struct net *net, unsigned int cmd, struct ifreq *); #ifdef CONFIG_INET int inet_gifconf(struct net_device *dev, char __user *buf, int len, int size); #else static inline int inet_gifconf(struct net_device *dev, char __user *buf, int len, int size) { return 0; } #endif void devinet_init(void); struct in_device *inetdev_by_index(struct net *, int); __be32 inet_select_addr(const struct net_device *dev, __be32 dst, int scope); __be32 inet_confirm_addr(struct net *net, struct in_device *in_dev, __be32 dst, __be32 local, int scope); struct in_ifaddr *inet_ifa_byprefix(struct in_device *in_dev, __be32 prefix, __be32 mask); struct in_ifaddr *inet_lookup_ifaddr_rcu(struct net *net, __be32 addr); static inline bool inet_ifa_match(__be32 addr, const struct in_ifaddr *ifa) { return !((addr^ifa->ifa_address)&ifa->ifa_mask); } /* * Check if a mask is acceptable. */ static __inline__ bool bad_mask(__be32 mask, __be32 addr) { __u32 hmask; if (addr & (mask = ~mask)) return true; hmask = ntohl(mask); if (hmask & (hmask+1)) return true; return false; } #define in_dev_for_each_ifa_rtnl(ifa, in_dev) \ for (ifa = rtnl_dereference((in_dev)->ifa_list); ifa; \ ifa = rtnl_dereference(ifa->ifa_next)) #define in_dev_for_each_ifa_rtnl_net(net, ifa, in_dev) \ for (ifa = rtnl_net_dereference(net, (in_dev)->ifa_list); ifa; \ ifa = rtnl_net_dereference(net, ifa->ifa_next)) #define in_dev_for_each_ifa_rcu(ifa, in_dev) \ for (ifa = rcu_dereference((in_dev)->ifa_list); ifa; \ ifa = rcu_dereference(ifa->ifa_next)) static inline struct in_device *__in_dev_get_rcu(const struct net_device *dev) { return rcu_dereference(dev->ip_ptr); } static inline struct in_device *in_dev_get(const struct net_device *dev) { struct in_device *in_dev; rcu_read_lock(); in_dev = __in_dev_get_rcu(dev); if (in_dev) refcount_inc(&in_dev->refcnt); rcu_read_unlock(); return in_dev; } static inline struct in_device *__in_dev_get_rtnl(const struct net_device *dev) { return rtnl_dereference(dev->ip_ptr); } static inline struct in_device *__in_dev_get_rtnl_net(const struct net_device *dev) { return rtnl_net_dereference(dev_net(dev), dev->ip_ptr); } /* called with rcu_read_lock or rtnl held */ static inline bool ip_ignore_linkdown(const struct net_device *dev) { struct in_device *in_dev; bool rc = false; in_dev = rcu_dereference_rtnl(dev->ip_ptr); if (in_dev && IN_DEV_IGNORE_ROUTES_WITH_LINKDOWN(in_dev)) rc = true; return rc; } static inline struct neigh_parms *__in_dev_arp_parms_get_rcu(const struct net_device *dev) { struct in_device *in_dev = __in_dev_get_rcu(dev); return in_dev ? in_dev->arp_parms : NULL; } void in_dev_finish_destroy(struct in_device *idev); static inline void in_dev_put(struct in_device *idev) { if (refcount_dec_and_test(&idev->refcnt)) in_dev_finish_destroy(idev); } #define __in_dev_put(idev) refcount_dec(&(idev)->refcnt) #define in_dev_hold(idev) refcount_inc(&(idev)->refcnt) #endif /* __KERNEL__ */ static __inline__ __be32 inet_make_mask(int logmask) { if (logmask) return htonl(~((1U<<(32-logmask))-1)); return 0; } static __inline__ int inet_mask_len(__be32 mask) { __u32 hmask = ntohl(mask); if (!hmask) return 0; return 32 - ffz(~hmask); } #endif /* _LINUX_INETDEVICE_H */ |
| 179 76 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 | /* SPDX-License-Identifier: GPL-2.0 */ #undef TRACE_SYSTEM #define TRACE_SYSTEM hugetlbfs #if !defined(_TRACE_HUGETLBFS_H) || defined(TRACE_HEADER_MULTI_READ) #define _TRACE_HUGETLBFS_H #include <linux/tracepoint.h> TRACE_EVENT(hugetlbfs_alloc_inode, TP_PROTO(struct inode *inode, struct inode *dir, int mode), TP_ARGS(inode, dir, mode), TP_STRUCT__entry( __field(dev_t, dev) __field(ino_t, ino) __field(ino_t, dir) __field(__u16, mode) ), TP_fast_assign( __entry->dev = inode->i_sb->s_dev; __entry->ino = inode->i_ino; __entry->dir = dir->i_ino; __entry->mode = mode; ), TP_printk("dev %d,%d ino %lu dir %lu mode 0%o", MAJOR(__entry->dev), MINOR(__entry->dev), (unsigned long) __entry->ino, (unsigned long) __entry->dir, __entry->mode) ); DECLARE_EVENT_CLASS(hugetlbfs__inode, TP_PROTO(struct inode *inode), TP_ARGS(inode), TP_STRUCT__entry( __field(dev_t, dev) __field(ino_t, ino) __field(__u16, mode) __field(loff_t, size) __field(unsigned int, nlink) __field(unsigned int, seals) __field(blkcnt_t, blocks) ), TP_fast_assign( __entry->dev = inode->i_sb->s_dev; __entry->ino = inode->i_ino; __entry->mode = inode->i_mode; __entry->size = inode->i_size; __entry->nlink = inode->i_nlink; __entry->seals = HUGETLBFS_I(inode)->seals; __entry->blocks = inode->i_blocks; ), TP_printk("dev %d,%d ino %lu mode 0%o size %lld nlink %u seals %u blocks %llu", MAJOR(__entry->dev), MINOR(__entry->dev), (unsigned long) __entry->ino, __entry->mode, __entry->size, __entry->nlink, __entry->seals, (unsigned long long)__entry->blocks) ); DEFINE_EVENT(hugetlbfs__inode, hugetlbfs_evict_inode, TP_PROTO(struct inode *inode), TP_ARGS(inode) ); DEFINE_EVENT(hugetlbfs__inode, hugetlbfs_free_inode, TP_PROTO(struct inode *inode), TP_ARGS(inode) ); TRACE_EVENT(hugetlbfs_setattr, TP_PROTO(struct inode *inode, struct dentry *dentry, struct iattr *attr), TP_ARGS(inode, dentry, attr), TP_STRUCT__entry( __field(dev_t, dev) __field(ino_t, ino) __field(unsigned int, d_len) __string(d_name, dentry->d_name.name) __field(unsigned int, ia_valid) __field(unsigned int, ia_mode) __field(loff_t, old_size) __field(loff_t, ia_size) ), TP_fast_assign( __entry->dev = inode->i_sb->s_dev; __entry->ino = inode->i_ino; __entry->d_len = dentry->d_name.len; __assign_str(d_name); __entry->ia_valid = attr->ia_valid; __entry->ia_mode = attr->ia_mode; __entry->old_size = inode->i_size; __entry->ia_size = attr->ia_size; ), TP_printk("dev %d,%d ino %lu name %.*s valid %#x mode 0%o old_size %lld size %lld", MAJOR(__entry->dev), MINOR(__entry->dev), (unsigned long)__entry->ino, __entry->d_len, __get_str(d_name), __entry->ia_valid, __entry->ia_mode, __entry->old_size, __entry->ia_size) ); TRACE_EVENT(hugetlbfs_fallocate, TP_PROTO(struct inode *inode, int mode, loff_t offset, loff_t len, int ret), TP_ARGS(inode, mode, offset, len, ret), TP_STRUCT__entry( __field(dev_t, dev) __field(ino_t, ino) __field(int, mode) __field(loff_t, offset) __field(loff_t, len) __field(loff_t, size) __field(int, ret) ), TP_fast_assign( __entry->dev = inode->i_sb->s_dev; __entry->ino = inode->i_ino; __entry->mode = mode; __entry->offset = offset; __entry->len = len; __entry->size = inode->i_size; __entry->ret = ret; ), TP_printk("dev %d,%d ino %lu mode 0%o offset %lld len %lld size %lld ret %d", MAJOR(__entry->dev), MINOR(__entry->dev), (unsigned long)__entry->ino, __entry->mode, (unsigned long long)__entry->offset, (unsigned long long)__entry->len, (unsigned long long)__entry->size, __entry->ret) ); #endif /* _TRACE_HUGETLBFS_H */ /* This part must be outside protection */ #include <trace/define_trace.h> |
| 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 | /* * Copyright IBM Corporation, 2012 * Author Aneesh Kumar K.V <aneesh.kumar@linux.vnet.ibm.com> * * This program is free software; you can redistribute it and/or modify it * under the terms of version 2.1 of the GNU Lesser General Public License * as published by the Free Software Foundation. * * This program is distributed in the hope that it would be useful, but * WITHOUT ANY WARRANTY; without even the implied warranty of * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. * */ #ifndef _LINUX_HUGETLB_CGROUP_H #define _LINUX_HUGETLB_CGROUP_H #include <linux/mmdebug.h> struct hugetlb_cgroup; struct resv_map; struct file_region; #ifdef CONFIG_CGROUP_HUGETLB enum hugetlb_memory_event { HUGETLB_MAX, HUGETLB_NR_MEMORY_EVENTS, }; struct hugetlb_cgroup_per_node { /* hugetlb usage in pages over all hstates. */ unsigned long usage[HUGE_MAX_HSTATE]; }; struct hugetlb_cgroup { struct cgroup_subsys_state css; /* * the counter to account for hugepages from hugetlb. */ struct page_counter hugepage[HUGE_MAX_HSTATE]; /* * the counter to account for hugepage reservations from hugetlb. */ struct page_counter rsvd_hugepage[HUGE_MAX_HSTATE]; atomic_long_t events[HUGE_MAX_HSTATE][HUGETLB_NR_MEMORY_EVENTS]; atomic_long_t events_local[HUGE_MAX_HSTATE][HUGETLB_NR_MEMORY_EVENTS]; /* Handle for "hugetlb.events" */ struct cgroup_file events_file[HUGE_MAX_HSTATE]; /* Handle for "hugetlb.events.local" */ struct cgroup_file events_local_file[HUGE_MAX_HSTATE]; struct hugetlb_cgroup_per_node *nodeinfo[]; }; static inline struct hugetlb_cgroup * __hugetlb_cgroup_from_folio(struct folio *folio, bool rsvd) { VM_BUG_ON_FOLIO(!folio_test_hugetlb(folio), folio); if (rsvd) return folio->_hugetlb_cgroup_rsvd; else return folio->_hugetlb_cgroup; } static inline struct hugetlb_cgroup *hugetlb_cgroup_from_folio(struct folio *folio) { return __hugetlb_cgroup_from_folio(folio, false); } static inline struct hugetlb_cgroup * hugetlb_cgroup_from_folio_rsvd(struct folio *folio) { return __hugetlb_cgroup_from_folio(folio, true); } static inline void __set_hugetlb_cgroup(struct folio *folio, struct hugetlb_cgroup *h_cg, bool rsvd) { VM_BUG_ON_FOLIO(!folio_test_hugetlb(folio), folio); if (rsvd) folio->_hugetlb_cgroup_rsvd = h_cg; else folio->_hugetlb_cgroup = h_cg; } static inline void set_hugetlb_cgroup(struct folio *folio, struct hugetlb_cgroup *h_cg) { __set_hugetlb_cgroup(folio, h_cg, false); } static inline void set_hugetlb_cgroup_rsvd(struct folio *folio, struct hugetlb_cgroup *h_cg) { __set_hugetlb_cgroup(folio, h_cg, true); } static inline bool hugetlb_cgroup_disabled(void) { return !cgroup_subsys_enabled(hugetlb_cgrp_subsys); } static inline void hugetlb_cgroup_put_rsvd_cgroup(struct hugetlb_cgroup *h_cg) { css_put(&h_cg->css); } static inline void resv_map_dup_hugetlb_cgroup_uncharge_info( struct resv_map *resv_map) { if (resv_map->css) css_get(resv_map->css); } static inline void resv_map_put_hugetlb_cgroup_uncharge_info( struct resv_map *resv_map) { if (resv_map->css) css_put(resv_map->css); } extern int hugetlb_cgroup_charge_cgroup(int idx, unsigned long nr_pages, struct hugetlb_cgroup **ptr); extern int hugetlb_cgroup_charge_cgroup_rsvd(int idx, unsigned long nr_pages, struct hugetlb_cgroup **ptr); extern void hugetlb_cgroup_commit_charge(int idx, unsigned long nr_pages, struct hugetlb_cgroup *h_cg, struct folio *folio); extern void hugetlb_cgroup_commit_charge_rsvd(int idx, unsigned long nr_pages, struct hugetlb_cgroup *h_cg, struct folio *folio); extern void hugetlb_cgroup_uncharge_folio(int idx, unsigned long nr_pages, struct folio *folio); extern void hugetlb_cgroup_uncharge_folio_rsvd(int idx, unsigned long nr_pages, struct folio *folio); extern void hugetlb_cgroup_uncharge_cgroup(int idx, unsigned long nr_pages, struct hugetlb_cgroup *h_cg); extern void hugetlb_cgroup_uncharge_cgroup_rsvd(int idx, unsigned long nr_pages, struct hugetlb_cgroup *h_cg); extern void hugetlb_cgroup_uncharge_counter(struct resv_map *resv, unsigned long start, unsigned long end); extern void hugetlb_cgroup_uncharge_file_region(struct resv_map *resv, struct file_region *rg, unsigned long nr_pages, bool region_del); extern void hugetlb_cgroup_file_init(void) __init; extern void hugetlb_cgroup_migrate(struct folio *old_folio, struct folio *new_folio); #else static inline void hugetlb_cgroup_uncharge_file_region(struct resv_map *resv, struct file_region *rg, unsigned long nr_pages, bool region_del) { } static inline struct hugetlb_cgroup *hugetlb_cgroup_from_folio(struct folio *folio) { return NULL; } static inline struct hugetlb_cgroup * hugetlb_cgroup_from_folio_rsvd(struct folio *folio) { return NULL; } static inline void set_hugetlb_cgroup(struct folio *folio, struct hugetlb_cgroup *h_cg) { } static inline void set_hugetlb_cgroup_rsvd(struct folio *folio, struct hugetlb_cgroup *h_cg) { } static inline bool hugetlb_cgroup_disabled(void) { return true; } static inline void hugetlb_cgroup_put_rsvd_cgroup(struct hugetlb_cgroup *h_cg) { } static inline void resv_map_dup_hugetlb_cgroup_uncharge_info( struct resv_map *resv_map) { } static inline void resv_map_put_hugetlb_cgroup_uncharge_info( struct resv_map *resv_map) { } static inline int hugetlb_cgroup_charge_cgroup(int idx, unsigned long nr_pages, struct hugetlb_cgroup **ptr) { return 0; } static inline int hugetlb_cgroup_charge_cgroup_rsvd(int idx, unsigned long nr_pages, struct hugetlb_cgroup **ptr) { return 0; } static inline void hugetlb_cgroup_commit_charge(int idx, unsigned long nr_pages, struct hugetlb_cgroup *h_cg, struct folio *folio) { } static inline void hugetlb_cgroup_commit_charge_rsvd(int idx, unsigned long nr_pages, struct hugetlb_cgroup *h_cg, struct folio *folio) { } static inline void hugetlb_cgroup_uncharge_folio(int idx, unsigned long nr_pages, struct folio *folio) { } static inline void hugetlb_cgroup_uncharge_folio_rsvd(int idx, unsigned long nr_pages, struct folio *folio) { } static inline void hugetlb_cgroup_uncharge_cgroup(int idx, unsigned long nr_pages, struct hugetlb_cgroup *h_cg) { } static inline void hugetlb_cgroup_uncharge_cgroup_rsvd(int idx, unsigned long nr_pages, struct hugetlb_cgroup *h_cg) { } static inline void hugetlb_cgroup_uncharge_counter(struct resv_map *resv, unsigned long start, unsigned long end) { } static inline void hugetlb_cgroup_file_init(void) { } static inline void hugetlb_cgroup_migrate(struct folio *old_folio, struct folio *new_folio) { } #endif /* CONFIG_MEM_RES_CTLR_HUGETLB */ #endif |
| 92 93 92 93 4 4 4 93 93 92 93 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 1522 1523 1524 1525 1526 1527 1528 1529 1530 1531 1532 1533 1534 1535 1536 1537 1538 1539 1540 1541 1542 1543 1544 1545 1546 1547 1548 1549 1550 1551 1552 1553 1554 1555 1556 1557 1558 1559 1560 1561 1562 1563 1564 1565 1566 1567 1568 1569 1570 1571 1572 1573 1574 1575 1576 1577 1578 1579 1580 1581 1582 1583 1584 1585 1586 1587 1588 1589 1590 1591 1592 1593 1594 1595 1596 1597 1598 1599 1600 1601 1602 1603 1604 1605 1606 1607 1608 1609 1610 1611 1612 1613 1614 1615 1616 1617 1618 1619 1620 1621 1622 1623 1624 1625 1626 1627 1628 1629 1630 1631 1632 1633 1634 1635 1636 1637 1638 1639 1640 1641 1642 1643 1644 1645 1646 1647 1648 1649 1650 1651 1652 1653 1654 1655 1656 1657 1658 1659 1660 1661 1662 1663 1664 1665 1666 1667 1668 1669 1670 1671 1672 1673 1674 1675 1676 1677 1678 1679 1680 1681 1682 1683 1684 1685 1686 1687 1688 1689 1690 1691 1692 1693 1694 1695 1696 1697 1698 1699 1700 1701 1702 1703 1704 1705 1706 1707 1708 1709 1710 1711 1712 1713 1714 1715 1716 1717 1718 1719 1720 1721 1722 1723 1724 1725 1726 1727 1728 1729 1730 1731 1732 1733 1734 1735 1736 1737 1738 1739 1740 1741 1742 1743 1744 1745 1746 1747 1748 1749 1750 1751 1752 1753 1754 1755 1756 1757 1758 1759 1760 1761 1762 1763 1764 1765 1766 1767 1768 1769 1770 1771 1772 1773 1774 1775 1776 1777 1778 1779 1780 1781 1782 1783 1784 1785 1786 1787 1788 1789 1790 1791 1792 1793 1794 1795 1796 1797 1798 1799 1800 1801 1802 1803 1804 1805 1806 1807 1808 1809 1810 1811 1812 1813 1814 1815 1816 1817 1818 1819 1820 1821 1822 1823 1824 1825 1826 1827 1828 1829 1830 1831 1832 1833 1834 1835 1836 1837 1838 1839 1840 1841 1842 1843 1844 1845 1846 1847 1848 1849 1850 1851 1852 1853 1854 1855 1856 1857 1858 1859 1860 1861 1862 1863 1864 1865 1866 1867 1868 1869 1870 1871 1872 1873 1874 1875 1876 1877 1878 1879 1880 1881 1882 1883 1884 1885 1886 1887 1888 1889 1890 1891 1892 1893 1894 1895 1896 1897 1898 1899 1900 1901 1902 1903 1904 1905 1906 1907 1908 1909 1910 1911 1912 1913 1914 1915 1916 1917 1918 1919 1920 1921 1922 1923 1924 1925 1926 1927 1928 1929 1930 1931 1932 1933 1934 1935 1936 1937 1938 1939 1940 1941 1942 1943 1944 1945 1946 1947 1948 1949 1950 1951 1952 1953 1954 1955 1956 1957 1958 1959 1960 1961 1962 1963 1964 1965 1966 1967 1968 1969 1970 1971 1972 1973 1974 1975 1976 1977 1978 1979 1980 1981 1982 1983 1984 1985 1986 1987 1988 1989 1990 1991 1992 1993 1994 1995 1996 1997 1998 1999 2000 2001 2002 2003 2004 2005 2006 2007 2008 2009 2010 2011 2012 2013 2014 2015 2016 2017 2018 2019 2020 2021 2022 2023 2024 2025 2026 2027 2028 2029 2030 2031 2032 2033 2034 2035 2036 2037 2038 2039 2040 2041 2042 2043 2044 2045 2046 2047 2048 2049 2050 2051 2052 2053 2054 2055 2056 2057 2058 2059 2060 2061 2062 2063 2064 2065 2066 2067 2068 2069 2070 2071 2072 2073 2074 2075 2076 2077 2078 2079 2080 2081 2082 2083 2084 2085 2086 2087 2088 2089 2090 2091 2092 2093 2094 2095 2096 2097 2098 2099 2100 2101 2102 2103 2104 2105 2106 2107 2108 2109 2110 2111 2112 2113 2114 2115 2116 2117 2118 2119 2120 2121 2122 2123 2124 2125 2126 2127 2128 2129 2130 2131 2132 2133 2134 2135 2136 2137 2138 2139 2140 2141 2142 2143 2144 2145 2146 2147 2148 2149 2150 2151 2152 2153 2154 2155 2156 2157 2158 2159 2160 2161 2162 2163 2164 2165 2166 2167 2168 2169 2170 2171 2172 2173 2174 2175 2176 2177 2178 2179 2180 2181 2182 2183 2184 2185 2186 2187 2188 2189 2190 2191 2192 2193 2194 2195 2196 2197 2198 2199 2200 2201 2202 2203 2204 2205 2206 2207 2208 2209 2210 2211 2212 2213 2214 2215 2216 2217 2218 2219 2220 2221 2222 2223 2224 2225 2226 2227 2228 2229 2230 2231 2232 2233 2234 2235 2236 2237 2238 2239 2240 2241 2242 2243 2244 2245 2246 2247 2248 2249 2250 2251 2252 2253 2254 2255 2256 2257 2258 2259 2260 2261 2262 2263 2264 2265 2266 2267 2268 2269 2270 2271 2272 2273 2274 2275 2276 2277 2278 2279 2280 2281 2282 2283 2284 2285 2286 2287 2288 2289 2290 2291 2292 2293 2294 2295 2296 2297 2298 2299 2300 2301 2302 2303 2304 2305 2306 2307 2308 2309 2310 2311 2312 2313 2314 2315 2316 2317 2318 2319 2320 2321 2322 2323 2324 2325 2326 2327 2328 2329 2330 2331 2332 2333 2334 2335 2336 2337 2338 2339 2340 2341 2342 2343 2344 2345 2346 2347 2348 2349 2350 2351 2352 2353 2354 2355 2356 2357 2358 2359 2360 2361 2362 2363 2364 2365 2366 2367 2368 2369 2370 2371 2372 2373 2374 2375 2376 2377 2378 2379 2380 2381 2382 2383 2384 2385 2386 2387 2388 2389 2390 2391 2392 2393 2394 2395 2396 2397 2398 2399 2400 2401 2402 2403 2404 2405 2406 2407 2408 2409 2410 2411 2412 2413 2414 2415 2416 2417 2418 2419 2420 2421 2422 2423 2424 2425 2426 2427 2428 2429 2430 2431 2432 2433 2434 2435 2436 2437 2438 2439 2440 2441 2442 2443 2444 2445 2446 2447 2448 2449 2450 2451 2452 2453 2454 2455 2456 2457 2458 2459 2460 2461 2462 2463 2464 2465 2466 2467 2468 2469 2470 2471 2472 2473 2474 2475 2476 2477 2478 2479 2480 2481 2482 2483 2484 2485 2486 2487 2488 2489 2490 2491 2492 2493 2494 2495 2496 2497 2498 2499 2500 2501 2502 2503 2504 2505 2506 2507 2508 2509 2510 2511 2512 2513 2514 2515 2516 2517 2518 2519 2520 2521 2522 2523 2524 2525 2526 2527 2528 2529 2530 2531 2532 2533 2534 2535 2536 2537 2538 2539 2540 2541 2542 2543 2544 2545 2546 2547 2548 2549 2550 2551 2552 2553 2554 2555 2556 2557 2558 2559 2560 2561 2562 2563 2564 2565 2566 2567 2568 2569 2570 2571 2572 2573 2574 2575 2576 2577 2578 2579 2580 2581 2582 2583 2584 2585 2586 2587 2588 2589 2590 2591 2592 2593 2594 2595 2596 2597 2598 2599 2600 2601 2602 2603 2604 2605 2606 2607 2608 2609 2610 2611 2612 2613 2614 2615 2616 2617 2618 2619 2620 2621 2622 2623 2624 2625 2626 2627 2628 2629 2630 2631 2632 2633 2634 2635 2636 2637 2638 2639 2640 2641 2642 2643 2644 2645 2646 2647 2648 2649 2650 2651 2652 2653 2654 2655 2656 2657 2658 2659 2660 2661 2662 2663 2664 2665 2666 2667 2668 2669 2670 2671 2672 2673 2674 2675 2676 2677 2678 2679 2680 2681 2682 2683 2684 2685 2686 2687 2688 2689 2690 2691 2692 2693 2694 2695 2696 2697 | // SPDX-License-Identifier: GPL-2.0-only /* * Copyright (C) 2013-2017 ARM Limited, All Rights Reserved. * Author: Marc Zyngier <marc.zyngier@arm.com> */ #define pr_fmt(fmt) "GICv3: " fmt #include <linux/acpi.h> #include <linux/cpu.h> #include <linux/cpu_pm.h> #include <linux/delay.h> #include <linux/interrupt.h> #include <linux/irqdomain.h> #include <linux/kernel.h> #include <linux/kstrtox.h> #include <linux/of.h> #include <linux/of_address.h> #include <linux/of_irq.h> #include <linux/percpu.h> #include <linux/refcount.h> #include <linux/slab.h> #include <linux/iopoll.h> #include <linux/irqchip.h> #include <linux/irqchip/arm-gic-common.h> #include <linux/irqchip/arm-gic-v3.h> #include <linux/irqchip/arm-gic-v3-prio.h> #include <linux/irqchip/irq-partition-percpu.h> #include <linux/bitfield.h> #include <linux/bits.h> #include <linux/arm-smccc.h> #include <asm/cputype.h> #include <asm/exception.h> #include <asm/smp_plat.h> #include <asm/virt.h> #include "irq-gic-common.h" static u8 dist_prio_irq __ro_after_init = GICV3_PRIO_IRQ; static u8 dist_prio_nmi __ro_after_init = GICV3_PRIO_NMI; #define FLAGS_WORKAROUND_GICR_WAKER_MSM8996 (1ULL << 0) #define FLAGS_WORKAROUND_CAVIUM_ERRATUM_38539 (1ULL << 1) #define FLAGS_WORKAROUND_ASR_ERRATUM_8601001 (1ULL << 2) #define GIC_IRQ_TYPE_PARTITION (GIC_IRQ_TYPE_LPI + 1) static struct cpumask broken_rdists __read_mostly __maybe_unused; struct redist_region { void __iomem *redist_base; phys_addr_t phys_base; bool single_redist; }; struct gic_chip_data { struct fwnode_handle *fwnode; phys_addr_t dist_phys_base; void __iomem *dist_base; struct redist_region *redist_regions; struct rdists rdists; struct irq_domain *domain; u64 redist_stride; u32 nr_redist_regions; u64 flags; bool has_rss; unsigned int ppi_nr; struct partition_desc **ppi_descs; }; #define T241_CHIPS_MAX 4 static void __iomem *t241_dist_base_alias[T241_CHIPS_MAX] __read_mostly; static DEFINE_STATIC_KEY_FALSE(gic_nvidia_t241_erratum); static DEFINE_STATIC_KEY_FALSE(gic_arm64_2941627_erratum); static struct gic_chip_data gic_data __read_mostly; static DEFINE_STATIC_KEY_TRUE(supports_deactivate_key); #define GIC_ID_NR (1U << GICD_TYPER_ID_BITS(gic_data.rdists.gicd_typer)) #define GIC_LINE_NR min(GICD_TYPER_SPIS(gic_data.rdists.gicd_typer), 1020U) #define GIC_ESPI_NR GICD_TYPER_ESPIS(gic_data.rdists.gicd_typer) /* * There are 16 SGIs, though we only actually use 8 in Linux. The other 8 SGIs * are potentially stolen by the secure side. Some code, especially code dealing * with hwirq IDs, is simplified by accounting for all 16. */ #define SGI_NR 16 /* * The behaviours of RPR and PMR registers differ depending on the value of * SCR_EL3.FIQ, and the behaviour of non-secure priority registers of the * distributor and redistributors depends on whether security is enabled in the * GIC. * * When security is enabled, non-secure priority values from the (re)distributor * are presented to the GIC CPUIF as follow: * (GIC_(R)DIST_PRI[irq] >> 1) | 0x80; * * If SCR_EL3.FIQ == 1, the values written to/read from PMR and RPR at non-secure * EL1 are subject to a similar operation thus matching the priorities presented * from the (re)distributor when security is enabled. When SCR_EL3.FIQ == 0, * these values are unchanged by the GIC. * * see GICv3/GICv4 Architecture Specification (IHI0069D): * - section 4.8.1 Non-secure accesses to register fields for Secure interrupt * priorities. * - Figure 4-7 Secure read of the priority field for a Non-secure Group 1 * interrupt. */ static DEFINE_STATIC_KEY_FALSE(supports_pseudo_nmis); static u32 gic_get_pribits(void) { u32 pribits; pribits = gic_read_ctlr(); pribits &= ICC_CTLR_EL1_PRI_BITS_MASK; pribits >>= ICC_CTLR_EL1_PRI_BITS_SHIFT; pribits++; return pribits; } static bool gic_has_group0(void) { u32 val; u32 old_pmr; old_pmr = gic_read_pmr(); /* * Let's find out if Group0 is under control of EL3 or not by * setting the highest possible, non-zero priority in PMR. * * If SCR_EL3.FIQ is set, the priority gets shifted down in * order for the CPU interface to set bit 7, and keep the * actual priority in the non-secure range. In the process, it * looses the least significant bit and the actual priority * becomes 0x80. Reading it back returns 0, indicating that * we're don't have access to Group0. */ gic_write_pmr(BIT(8 - gic_get_pribits())); val = gic_read_pmr(); gic_write_pmr(old_pmr); return val != 0; } static inline bool gic_dist_security_disabled(void) { return readl_relaxed(gic_data.dist_base + GICD_CTLR) & GICD_CTLR_DS; } static bool cpus_have_security_disabled __ro_after_init; static bool cpus_have_group0 __ro_after_init; static void __init gic_prio_init(void) { bool ds; ds = gic_dist_security_disabled(); if (!ds) { u32 val; val = readl_relaxed(gic_data.dist_base + GICD_CTLR); val |= GICD_CTLR_DS; writel_relaxed(val, gic_data.dist_base + GICD_CTLR); ds = gic_dist_security_disabled(); if (ds) pr_warn("Broken GIC integration, security disabled"); } cpus_have_security_disabled = ds; cpus_have_group0 = gic_has_group0(); /* * How priority values are used by the GIC depends on two things: * the security state of the GIC (controlled by the GICD_CTRL.DS bit) * and if Group 0 interrupts can be delivered to Linux in the non-secure * world as FIQs (controlled by the SCR_EL3.FIQ bit). These affect the * way priorities are presented in ICC_PMR_EL1 and in the distributor: * * GICD_CTRL.DS | SCR_EL3.FIQ | ICC_PMR_EL1 | Distributor * ------------------------------------------------------- * 1 | - | unchanged | unchanged * ------------------------------------------------------- * 0 | 1 | non-secure | non-secure * ------------------------------------------------------- * 0 | 0 | unchanged | non-secure * * In the non-secure view reads and writes are modified: * * - A value written is right-shifted by one and the MSB is set, * forcing the priority into the non-secure range. * * - A value read is left-shifted by one. * * In the first two cases, where ICC_PMR_EL1 and the interrupt priority * are both either modified or unchanged, we can use the same set of * priorities. * * In the last case, where only the interrupt priorities are modified to * be in the non-secure range, we program the non-secure values into * the distributor to match the PMR values we want. */ if (cpus_have_group0 & !cpus_have_security_disabled) { dist_prio_irq = __gicv3_prio_to_ns(dist_prio_irq); dist_prio_nmi = __gicv3_prio_to_ns(dist_prio_nmi); } pr_info("GICD_CTRL.DS=%d, SCR_EL3.FIQ=%d\n", cpus_have_security_disabled, !cpus_have_group0); } /* rdist_nmi_refs[n] == number of cpus having the rdist interrupt n set as NMI */ static refcount_t *rdist_nmi_refs; static struct gic_kvm_info gic_v3_kvm_info __initdata; static DEFINE_PER_CPU(bool, has_rss); #define MPIDR_RS(mpidr) (((mpidr) & 0xF0UL) >> 4) #define gic_data_rdist() (this_cpu_ptr(gic_data.rdists.rdist)) #define gic_data_rdist_rd_base() (gic_data_rdist()->rd_base) #define gic_data_rdist_sgi_base() (gic_data_rdist_rd_base() + SZ_64K) /* Our default, arbitrary priority value. Linux only uses one anyway. */ #define DEFAULT_PMR_VALUE 0xf0 enum gic_intid_range { SGI_RANGE, PPI_RANGE, SPI_RANGE, EPPI_RANGE, ESPI_RANGE, LPI_RANGE, __INVALID_RANGE__ }; static enum gic_intid_range __get_intid_range(irq_hw_number_t hwirq) { switch (hwirq) { case 0 ... 15: return SGI_RANGE; case 16 ... 31: return PPI_RANGE; case 32 ... 1019: return SPI_RANGE; case EPPI_BASE_INTID ... (EPPI_BASE_INTID + 63): return EPPI_RANGE; case ESPI_BASE_INTID ... (ESPI_BASE_INTID + 1023): return ESPI_RANGE; case 8192 ... GENMASK(23, 0): return LPI_RANGE; default: return __INVALID_RANGE__; } } static enum gic_intid_range get_intid_range(struct irq_data *d) { return __get_intid_range(d->hwirq); } static inline bool gic_irq_in_rdist(struct irq_data *d) { switch (get_intid_range(d)) { case SGI_RANGE: case PPI_RANGE: case EPPI_RANGE: return true; default: return false; } } static inline void __iomem *gic_dist_base_alias(struct irq_data *d) { if (static_branch_unlikely(&gic_nvidia_t241_erratum)) { irq_hw_number_t hwirq = irqd_to_hwirq(d); u32 chip; /* * For the erratum T241-FABRIC-4, read accesses to GICD_In{E} * registers are directed to the chip that owns the SPI. The * the alias region can also be used for writes to the * GICD_In{E} except GICD_ICENABLERn. Each chip has support * for 320 {E}SPIs. Mappings for all 4 chips: * Chip0 = 32-351 * Chip1 = 352-671 * Chip2 = 672-991 * Chip3 = 4096-4415 */ switch (__get_intid_range(hwirq)) { case SPI_RANGE: chip = (hwirq - 32) / 320; break; case ESPI_RANGE: chip = 3; break; default: unreachable(); } return t241_dist_base_alias[chip]; } return gic_data.dist_base; } static inline void __iomem *gic_dist_base(struct irq_data *d) { switch (get_intid_range(d)) { case SGI_RANGE: case PPI_RANGE: case EPPI_RANGE: /* SGI+PPI -> SGI_base for this CPU */ return gic_data_rdist_sgi_base(); case SPI_RANGE: case ESPI_RANGE: /* SPI -> dist_base */ return gic_data.dist_base; default: return NULL; } } static void gic_do_wait_for_rwp(void __iomem *base, u32 bit) { u32 val; int ret; ret = readl_relaxed_poll_timeout_atomic(base + GICD_CTLR, val, !(val & bit), 1, USEC_PER_SEC); if (ret == -ETIMEDOUT) pr_err_ratelimited("RWP timeout, gone fishing\n"); } /* Wait for completion of a distributor change */ static void gic_dist_wait_for_rwp(void) { gic_do_wait_for_rwp(gic_data.dist_base, GICD_CTLR_RWP); } /* Wait for completion of a redistributor change */ static void gic_redist_wait_for_rwp(void) { gic_do_wait_for_rwp(gic_data_rdist_rd_base(), GICR_CTLR_RWP); } static void gic_enable_redist(bool enable) { void __iomem *rbase; u32 val; int ret; if (gic_data.flags & FLAGS_WORKAROUND_GICR_WAKER_MSM8996) return; rbase = gic_data_rdist_rd_base(); val = readl_relaxed(rbase + GICR_WAKER); if (enable) /* Wake up this CPU redistributor */ val &= ~GICR_WAKER_ProcessorSleep; else val |= GICR_WAKER_ProcessorSleep; writel_relaxed(val, rbase + GICR_WAKER); if (!enable) { /* Check that GICR_WAKER is writeable */ val = readl_relaxed(rbase + GICR_WAKER); if (!(val & GICR_WAKER_ProcessorSleep)) return; /* No PM support in this redistributor */ } ret = readl_relaxed_poll_timeout_atomic(rbase + GICR_WAKER, val, enable ^ (bool)(val & GICR_WAKER_ChildrenAsleep), 1, USEC_PER_SEC); if (ret == -ETIMEDOUT) { pr_err_ratelimited("redistributor failed to %s...\n", enable ? "wakeup" : "sleep"); } } /* * Routines to disable, enable, EOI and route interrupts */ static u32 convert_offset_index(struct irq_data *d, u32 offset, u32 *index) { switch (get_intid_range(d)) { case SGI_RANGE: case PPI_RANGE: case SPI_RANGE: *index = d->hwirq; return offset; case EPPI_RANGE: /* * Contrary to the ESPI range, the EPPI range is contiguous * to the PPI range in the registers, so let's adjust the * displacement accordingly. Consistency is overrated. */ *index = d->hwirq - EPPI_BASE_INTID + 32; return offset; case ESPI_RANGE: *index = d->hwirq - ESPI_BASE_INTID; switch (offset) { case GICD_ISENABLER: return GICD_ISENABLERnE; case GICD_ICENABLER: return GICD_ICENABLERnE; case GICD_ISPENDR: return GICD_ISPENDRnE; case GICD_ICPENDR: return GICD_ICPENDRnE; case GICD_ISACTIVER: return GICD_ISACTIVERnE; case GICD_ICACTIVER: return GICD_ICACTIVERnE; case GICD_IPRIORITYR: return GICD_IPRIORITYRnE; case GICD_ICFGR: return GICD_ICFGRnE; case GICD_IROUTER: return GICD_IROUTERnE; default: break; } break; default: break; } WARN_ON(1); *index = d->hwirq; return offset; } static int gic_peek_irq(struct irq_data *d, u32 offset) { void __iomem *base; u32 index, mask; offset = convert_offset_index(d, offset, &index); mask = 1 << (index % 32); if (gic_irq_in_rdist(d)) base = gic_data_rdist_sgi_base(); else base = gic_dist_base_alias(d); return !!(readl_relaxed(base + offset + (index / 32) * 4) & mask); } static void gic_poke_irq(struct irq_data *d, u32 offset) { void __iomem *base; u32 index, mask; offset = convert_offset_index(d, offset, &index); mask = 1 << (index % 32); if (gic_irq_in_rdist(d)) base = gic_data_rdist_sgi_base(); else base = gic_data.dist_base; writel_relaxed(mask, base + offset + (index / 32) * 4); } static void gic_mask_irq(struct irq_data *d) { gic_poke_irq(d, GICD_ICENABLER); if (gic_irq_in_rdist(d)) gic_redist_wait_for_rwp(); else gic_dist_wait_for_rwp(); } static void gic_eoimode1_mask_irq(struct irq_data *d) { gic_mask_irq(d); /* * When masking a forwarded interrupt, make sure it is * deactivated as well. * * This ensures that an interrupt that is getting * disabled/masked will not get "stuck", because there is * noone to deactivate it (guest is being terminated). */ if (irqd_is_forwarded_to_vcpu(d)) gic_poke_irq(d, GICD_ICACTIVER); } static void gic_unmask_irq(struct irq_data *d) { gic_poke_irq(d, GICD_ISENABLER); } static inline bool gic_supports_nmi(void) { return IS_ENABLED(CONFIG_ARM64_PSEUDO_NMI) && static_branch_likely(&supports_pseudo_nmis); } static int gic_irq_set_irqchip_state(struct irq_data *d, enum irqchip_irq_state which, bool val) { u32 reg; if (d->hwirq >= 8192) /* SGI/PPI/SPI only */ return -EINVAL; switch (which) { case IRQCHIP_STATE_PENDING: reg = val ? GICD_ISPENDR : GICD_ICPENDR; break; case IRQCHIP_STATE_ACTIVE: reg = val ? GICD_ISACTIVER : GICD_ICACTIVER; break; case IRQCHIP_STATE_MASKED: if (val) { gic_mask_irq(d); return 0; } reg = GICD_ISENABLER; break; default: return -EINVAL; } gic_poke_irq(d, reg); /* * Force read-back to guarantee that the active state has taken * effect, and won't race with a guest-driven deactivation. */ if (reg == GICD_ISACTIVER) gic_peek_irq(d, reg); return 0; } static int gic_irq_get_irqchip_state(struct irq_data *d, enum irqchip_irq_state which, bool *val) { if (d->hwirq >= 8192) /* PPI/SPI only */ return -EINVAL; switch (which) { case IRQCHIP_STATE_PENDING: *val = gic_peek_irq(d, GICD_ISPENDR); break; case IRQCHIP_STATE_ACTIVE: *val = gic_peek_irq(d, GICD_ISACTIVER); break; case IRQCHIP_STATE_MASKED: *val = !gic_peek_irq(d, GICD_ISENABLER); break; default: return -EINVAL; } return 0; } static void gic_irq_set_prio(struct irq_data *d, u8 prio) { void __iomem *base = gic_dist_base(d); u32 offset, index; offset = convert_offset_index(d, GICD_IPRIORITYR, &index); writeb_relaxed(prio, base + offset + index); } static u32 __gic_get_ppi_index(irq_hw_number_t hwirq) { switch (__get_intid_range(hwirq)) { case PPI_RANGE: return hwirq - 16; case EPPI_RANGE: return hwirq - EPPI_BASE_INTID + 16; default: unreachable(); } } static u32 __gic_get_rdist_index(irq_hw_number_t hwirq) { switch (__get_intid_range(hwirq)) { case SGI_RANGE: case PPI_RANGE: return hwirq; case EPPI_RANGE: return hwirq - EPPI_BASE_INTID + 32; default: unreachable(); } } static u32 gic_get_rdist_index(struct irq_data *d) { return __gic_get_rdist_index(d->hwirq); } static int gic_irq_nmi_setup(struct irq_data *d) { struct irq_desc *desc = irq_to_desc(d->irq); if (!gic_supports_nmi()) return -EINVAL; if (gic_peek_irq(d, GICD_ISENABLER)) { pr_err("Cannot set NMI property of enabled IRQ %u\n", d->irq); return -EINVAL; } /* * A secondary irq_chip should be in charge of LPI request, * it should not be possible to get there */ if (WARN_ON(irqd_to_hwirq(d) >= 8192)) return -EINVAL; /* desc lock should already be held */ if (gic_irq_in_rdist(d)) { u32 idx = gic_get_rdist_index(d); /* * Setting up a percpu interrupt as NMI, only switch handler * for first NMI */ if (!refcount_inc_not_zero(&rdist_nmi_refs[idx])) { refcount_set(&rdist_nmi_refs[idx], 1); desc->handle_irq = handle_percpu_devid_fasteoi_nmi; } } else { desc->handle_irq = handle_fasteoi_nmi; } gic_irq_set_prio(d, dist_prio_nmi); return 0; } static void gic_irq_nmi_teardown(struct irq_data *d) { struct irq_desc *desc = irq_to_desc(d->irq); if (WARN_ON(!gic_supports_nmi())) return; if (gic_peek_irq(d, GICD_ISENABLER)) { pr_err("Cannot set NMI property of enabled IRQ %u\n", d->irq); return; } /* * A secondary irq_chip should be in charge of LPI request, * it should not be possible to get there */ if (WARN_ON(irqd_to_hwirq(d) >= 8192)) return; /* desc lock should already be held */ if (gic_irq_in_rdist(d)) { u32 idx = gic_get_rdist_index(d); /* Tearing down NMI, only switch handler for last NMI */ if (refcount_dec_and_test(&rdist_nmi_refs[idx])) desc->handle_irq = handle_percpu_devid_irq; } else { desc->handle_irq = handle_fasteoi_irq; } gic_irq_set_prio(d, dist_prio_irq); } static bool gic_arm64_erratum_2941627_needed(struct irq_data *d) { enum gic_intid_range range; if (!static_branch_unlikely(&gic_arm64_2941627_erratum)) return false; range = get_intid_range(d); /* * The workaround is needed if the IRQ is an SPI and * the target cpu is different from the one we are * executing on. */ return (range == SPI_RANGE || range == ESPI_RANGE) && !cpumask_test_cpu(raw_smp_processor_id(), irq_data_get_effective_affinity_mask(d)); } static void gic_eoi_irq(struct irq_data *d) { write_gicreg(irqd_to_hwirq(d), ICC_EOIR1_EL1); isb(); if (gic_arm64_erratum_2941627_needed(d)) { /* * Make sure the GIC stream deactivate packet * issued by ICC_EOIR1_EL1 has completed before * deactivating through GICD_IACTIVER. */ dsb(sy); gic_poke_irq(d, GICD_ICACTIVER); } } static void gic_eoimode1_eoi_irq(struct irq_data *d) { /* * No need to deactivate an LPI, or an interrupt that * is is getting forwarded to a vcpu. */ if (irqd_to_hwirq(d) >= 8192 || irqd_is_forwarded_to_vcpu(d)) return; if (!gic_arm64_erratum_2941627_needed(d)) gic_write_dir(irqd_to_hwirq(d)); else gic_poke_irq(d, GICD_ICACTIVER); } static int gic_set_type(struct irq_data *d, unsigned int type) { irq_hw_number_t irq = irqd_to_hwirq(d); enum gic_intid_range range; void __iomem *base; u32 offset, index; int ret; range = get_intid_range(d); /* Interrupt configuration for SGIs can't be changed */ if (range == SGI_RANGE) return type != IRQ_TYPE_EDGE_RISING ? -EINVAL : 0; /* SPIs have restrictions on the supported types */ if ((range == SPI_RANGE || range == ESPI_RANGE) && type != IRQ_TYPE_LEVEL_HIGH && type != IRQ_TYPE_EDGE_RISING) return -EINVAL; if (gic_irq_in_rdist(d)) base = gic_data_rdist_sgi_base(); else base = gic_dist_base_alias(d); offset = convert_offset_index(d, GICD_ICFGR, &index); ret = gic_configure_irq(index, type, base + offset); if (ret && (range == PPI_RANGE || range == EPPI_RANGE)) { /* Misconfigured PPIs are usually not fatal */ pr_warn("GIC: PPI INTID%ld is secure or misconfigured\n", irq); ret = 0; } return ret; } static int gic_irq_set_vcpu_affinity(struct irq_data *d, void *vcpu) { if (get_intid_range(d) == SGI_RANGE) return -EINVAL; if (vcpu) irqd_set_forwarded_to_vcpu(d); else irqd_clr_forwarded_to_vcpu(d); return 0; } static u64 gic_cpu_to_affinity(int cpu) { u64 mpidr = cpu_logical_map(cpu); u64 aff; /* ASR8601 needs to have its affinities shifted down... */ if (unlikely(gic_data.flags & FLAGS_WORKAROUND_ASR_ERRATUM_8601001)) mpidr = (MPIDR_AFFINITY_LEVEL(mpidr, 1) | (MPIDR_AFFINITY_LEVEL(mpidr, 2) << 8)); aff = ((u64)MPIDR_AFFINITY_LEVEL(mpidr, 3) << 32 | MPIDR_AFFINITY_LEVEL(mpidr, 2) << 16 | MPIDR_AFFINITY_LEVEL(mpidr, 1) << 8 | MPIDR_AFFINITY_LEVEL(mpidr, 0)); return aff; } static void gic_deactivate_unhandled(u32 irqnr) { if (static_branch_likely(&supports_deactivate_key)) { if (irqnr < 8192) gic_write_dir(irqnr); } else { write_gicreg(irqnr, ICC_EOIR1_EL1); isb(); } } /* * Follow a read of the IAR with any HW maintenance that needs to happen prior * to invoking the relevant IRQ handler. We must do two things: * * (1) Ensure instruction ordering between a read of IAR and subsequent * instructions in the IRQ handler using an ISB. * * It is possible for the IAR to report an IRQ which was signalled *after* * the CPU took an IRQ exception as multiple interrupts can race to be * recognized by the GIC, earlier interrupts could be withdrawn, and/or * later interrupts could be prioritized by the GIC. * * For devices which are tightly coupled to the CPU, such as PMUs, a * context synchronization event is necessary to ensure that system * register state is not stale, as these may have been indirectly written * *after* exception entry. * * (2) Execute an interrupt priority drop when EOI mode 1 is in use. */ static inline void gic_complete_ack(u32 irqnr) { if (static_branch_likely(&supports_deactivate_key)) write_gicreg(irqnr, ICC_EOIR1_EL1); isb(); } static bool gic_rpr_is_nmi_prio(void) { if (!gic_supports_nmi()) return false; return unlikely(gic_read_rpr() == GICV3_PRIO_NMI); } static bool gic_irqnr_is_special(u32 irqnr) { return irqnr >= 1020 && irqnr <= 1023; } static void __gic_handle_irq(u32 irqnr, struct pt_regs *regs) { if (gic_irqnr_is_special(irqnr)) return; gic_complete_ack(irqnr); if (generic_handle_domain_irq(gic_data.domain, irqnr)) { WARN_ONCE(true, "Unexpected interrupt (irqnr %u)\n", irqnr); gic_deactivate_unhandled(irqnr); } } static void __gic_handle_nmi(u32 irqnr, struct pt_regs *regs) { if (gic_irqnr_is_special(irqnr)) return; gic_complete_ack(irqnr); if (generic_handle_domain_nmi(gic_data.domain, irqnr)) { WARN_ONCE(true, "Unexpected pseudo-NMI (irqnr %u)\n", irqnr); gic_deactivate_unhandled(irqnr); } } /* * An exception has been taken from a context with IRQs enabled, and this could * be an IRQ or an NMI. * * The entry code called us with DAIF.IF set to keep NMIs masked. We must clear * DAIF.IF (and update ICC_PMR_EL1 to mask regular IRQs) prior to returning, * after handling any NMI but before handling any IRQ. * * The entry code has performed IRQ entry, and if an NMI is detected we must * perform NMI entry/exit around invoking the handler. */ static void __gic_handle_irq_from_irqson(struct pt_regs *regs) { bool is_nmi; u32 irqnr; irqnr = gic_read_iar(); is_nmi = gic_rpr_is_nmi_prio(); if (is_nmi) { nmi_enter(); __gic_handle_nmi(irqnr, regs); nmi_exit(); } if (gic_prio_masking_enabled()) { gic_pmr_mask_irqs(); gic_arch_enable_irqs(); } if (!is_nmi) __gic_handle_irq(irqnr, regs); } /* * An exception has been taken from a context with IRQs disabled, which can only * be an NMI. * * The entry code called us with DAIF.IF set to keep NMIs masked. We must leave * DAIF.IF (and ICC_PMR_EL1) unchanged. * * The entry code has performed NMI entry. */ static void __gic_handle_irq_from_irqsoff(struct pt_regs *regs) { u64 pmr; u32 irqnr; /* * We were in a context with IRQs disabled. However, the * entry code has set PMR to a value that allows any * interrupt to be acknowledged, and not just NMIs. This can * lead to surprising effects if the NMI has been retired in * the meantime, and that there is an IRQ pending. The IRQ * would then be taken in NMI context, something that nobody * wants to debug twice. * * Until we sort this, drop PMR again to a level that will * actually only allow NMIs before reading IAR, and then * restore it to what it was. */ pmr = gic_read_pmr(); gic_pmr_mask_irqs(); isb(); irqnr = gic_read_iar(); gic_write_pmr(pmr); __gic_handle_nmi(irqnr, regs); } static void __exception_irq_entry gic_handle_irq(struct pt_regs *regs) { if (unlikely(gic_supports_nmi() && !interrupts_enabled(regs))) __gic_handle_irq_from_irqsoff(regs); else __gic_handle_irq_from_irqson(regs); } static void __init gic_dist_init(void) { unsigned int i; u64 affinity; void __iomem *base = gic_data.dist_base; u32 val; /* Disable the distributor */ writel_relaxed(0, base + GICD_CTLR); gic_dist_wait_for_rwp(); /* * Configure SPIs as non-secure Group-1. This will only matter * if the GIC only has a single security state. This will not * do the right thing if the kernel is running in secure mode, * but that's not the intended use case anyway. */ for (i = 32; i < GIC_LINE_NR; i += 32) writel_relaxed(~0, base + GICD_IGROUPR + i / 8); /* Extended SPI range, not handled by the GICv2/GICv3 common code */ for (i = 0; i < GIC_ESPI_NR; i += 32) { writel_relaxed(~0U, base + GICD_ICENABLERnE + i / 8); writel_relaxed(~0U, base + GICD_ICACTIVERnE + i / 8); } for (i = 0; i < GIC_ESPI_NR; i += 32) writel_relaxed(~0U, base + GICD_IGROUPRnE + i / 8); for (i = 0; i < GIC_ESPI_NR; i += 16) writel_relaxed(0, base + GICD_ICFGRnE + i / 4); for (i = 0; i < GIC_ESPI_NR; i += 4) writel_relaxed(REPEAT_BYTE_U32(dist_prio_irq), base + GICD_IPRIORITYRnE + i); /* Now do the common stuff */ gic_dist_config(base, GIC_LINE_NR, dist_prio_irq); val = GICD_CTLR_ARE_NS | GICD_CTLR_ENABLE_G1A | GICD_CTLR_ENABLE_G1; if (gic_data.rdists.gicd_typer2 & GICD_TYPER2_nASSGIcap) { pr_info("Enabling SGIs without active state\n"); val |= GICD_CTLR_nASSGIreq; } /* Enable distributor with ARE, Group1, and wait for it to drain */ writel_relaxed(val, base + GICD_CTLR); gic_dist_wait_for_rwp(); /* * Set all global interrupts to the boot CPU only. ARE must be * enabled. */ affinity = gic_cpu_to_affinity(smp_processor_id()); for (i = 32; i < GIC_LINE_NR; i++) gic_write_irouter(affinity, base + GICD_IROUTER + i * 8); for (i = 0; i < GIC_ESPI_NR; i++) gic_write_irouter(affinity, base + GICD_IROUTERnE + i * 8); } static int gic_iterate_rdists(int (*fn)(struct redist_region *, void __iomem *)) { int ret = -ENODEV; int i; for (i = 0; i < gic_data.nr_redist_regions; i++) { void __iomem *ptr = gic_data.redist_regions[i].redist_base; u64 typer; u32 reg; reg = readl_relaxed(ptr + GICR_PIDR2) & GIC_PIDR2_ARCH_MASK; if (reg != GIC_PIDR2_ARCH_GICv3 && reg != GIC_PIDR2_ARCH_GICv4) { /* We're in trouble... */ pr_warn("No redistributor present @%p\n", ptr); break; } do { typer = gic_read_typer(ptr + GICR_TYPER); ret = fn(gic_data.redist_regions + i, ptr); if (!ret) return 0; if (gic_data.redist_regions[i].single_redist) break; if (gic_data.redist_stride) { ptr += gic_data.redist_stride; } else { ptr += SZ_64K * 2; /* Skip RD_base + SGI_base */ if (typer & GICR_TYPER_VLPIS) ptr += SZ_64K * 2; /* Skip VLPI_base + reserved page */ } } while (!(typer & GICR_TYPER_LAST)); } return ret ? -ENODEV : 0; } static int __gic_populate_rdist(struct redist_region *region, void __iomem *ptr) { unsigned long mpidr; u64 typer; u32 aff; /* * Convert affinity to a 32bit value that can be matched to * GICR_TYPER bits [63:32]. */ mpidr = gic_cpu_to_affinity(smp_processor_id()); aff = (MPIDR_AFFINITY_LEVEL(mpidr, 3) << 24 | MPIDR_AFFINITY_LEVEL(mpidr, 2) << 16 | MPIDR_AFFINITY_LEVEL(mpidr, 1) << 8 | MPIDR_AFFINITY_LEVEL(mpidr, 0)); typer = gic_read_typer(ptr + GICR_TYPER); if ((typer >> 32) == aff) { u64 offset = ptr - region->redist_base; raw_spin_lock_init(&gic_data_rdist()->rd_lock); gic_data_rdist_rd_base() = ptr; gic_data_rdist()->phys_base = region->phys_base + offset; pr_info("CPU%d: found redistributor %lx region %d:%pa\n", smp_processor_id(), mpidr, (int)(region - gic_data.redist_regions), &gic_data_rdist()->phys_base); return 0; } /* Try next one */ return 1; } static int gic_populate_rdist(void) { if (gic_iterate_rdists(__gic_populate_rdist) == 0) return 0; /* We couldn't even deal with ourselves... */ WARN(true, "CPU%d: mpidr %lx has no re-distributor!\n", smp_processor_id(), (unsigned long)cpu_logical_map(smp_processor_id())); return -ENODEV; } static int __gic_update_rdist_properties(struct redist_region *region, void __iomem *ptr) { u64 typer = gic_read_typer(ptr + GICR_TYPER); u32 ctlr = readl_relaxed(ptr + GICR_CTLR); /* Boot-time cleanup */ if ((typer & GICR_TYPER_VLPIS) && (typer & GICR_TYPER_RVPEID)) { u64 val; /* Deactivate any present vPE */ val = gicr_read_vpendbaser(ptr + SZ_128K + GICR_VPENDBASER); if (val & GICR_VPENDBASER_Valid) gicr_write_vpendbaser(GICR_VPENDBASER_PendingLast, ptr + SZ_128K + GICR_VPENDBASER); /* Mark the VPE table as invalid */ val = gicr_read_vpropbaser(ptr + SZ_128K + GICR_VPROPBASER); val &= ~GICR_VPROPBASER_4_1_VALID; gicr_write_vpropbaser(val, ptr + SZ_128K + GICR_VPROPBASER); } gic_data.rdists.has_vlpis &= !!(typer & GICR_TYPER_VLPIS); /* * TYPER.RVPEID implies some form of DirectLPI, no matter what the * doc says... :-/ And CTLR.IR implies another subset of DirectLPI * that the ITS driver can make use of for LPIs (and not VLPIs). * * These are 3 different ways to express the same thing, depending * on the revision of the architecture and its relaxations over * time. Just group them under the 'direct_lpi' banner. */ gic_data.rdists.has_rvpeid &= !!(typer & GICR_TYPER_RVPEID); gic_data.rdists.has_direct_lpi &= (!!(typer & GICR_TYPER_DirectLPIS) | !!(ctlr & GICR_CTLR_IR) | gic_data.rdists.has_rvpeid); gic_data.rdists.has_vpend_valid_dirty &= !!(typer & GICR_TYPER_DIRTY); /* Detect non-sensical configurations */ if (WARN_ON_ONCE(gic_data.rdists.has_rvpeid && !gic_data.rdists.has_vlpis)) { gic_data.rdists.has_direct_lpi = false; gic_data.rdists.has_vlpis = false; gic_data.rdists.has_rvpeid = false; } gic_data.ppi_nr = min(GICR_TYPER_NR_PPIS(typer), gic_data.ppi_nr); return 1; } static void gic_update_rdist_properties(void) { gic_data.ppi_nr = UINT_MAX; gic_iterate_rdists(__gic_update_rdist_properties); if (WARN_ON(gic_data.ppi_nr == UINT_MAX)) gic_data.ppi_nr = 0; pr_info("GICv3 features: %d PPIs%s%s\n", gic_data.ppi_nr, gic_data.has_rss ? ", RSS" : "", gic_data.rdists.has_direct_lpi ? ", DirectLPI" : ""); if (gic_data.rdists.has_vlpis) pr_info("GICv4 features: %s%s%s\n", gic_data.rdists.has_direct_lpi ? "DirectLPI " : "", gic_data.rdists.has_rvpeid ? "RVPEID " : "", gic_data.rdists.has_vpend_valid_dirty ? "Valid+Dirty " : ""); } static void gic_cpu_sys_reg_enable(void) { /* * Need to check that the SRE bit has actually been set. If * not, it means that SRE is disabled at EL2. We're going to * die painfully, and there is nothing we can do about it. * * Kindly inform the luser. */ if (!gic_enable_sre()) pr_err("GIC: unable to set SRE (disabled at EL2), panic ahead\n"); } static void gic_cpu_sys_reg_init(void) { int i, cpu = smp_processor_id(); u64 mpidr = gic_cpu_to_affinity(cpu); u64 need_rss = MPIDR_RS(mpidr); bool group0; u32 pribits; pribits = gic_get_pribits(); group0 = gic_has_group0(); /* Set priority mask register */ if (!gic_prio_masking_enabled()) { write_gicreg(DEFAULT_PMR_VALUE, ICC_PMR_EL1); } else if (gic_supports_nmi()) { /* * Check that all CPUs use the same priority space. * * If there's a mismatch with the boot CPU, the system is * likely to die as interrupt masking will not work properly on * all CPUs. */ WARN_ON(group0 != cpus_have_group0); WARN_ON(gic_dist_security_disabled() != cpus_have_security_disabled); } /* * Some firmwares hand over to the kernel with the BPR changed from * its reset value (and with a value large enough to prevent * any pre-emptive interrupts from working at all). Writing a zero * to BPR restores is reset value. */ gic_write_bpr1(0); if (static_branch_likely(&supports_deactivate_key)) { /* EOI drops priority only (mode 1) */ gic_write_ctlr(ICC_CTLR_EL1_EOImode_drop); } else { /* EOI deactivates interrupt too (mode 0) */ gic_write_ctlr(ICC_CTLR_EL1_EOImode_drop_dir); } /* Always whack Group0 before Group1 */ if (group0) { switch(pribits) { case 8: case 7: write_gicreg(0, ICC_AP0R3_EL1); write_gicreg(0, ICC_AP0R2_EL1); fallthrough; case 6: write_gicreg(0, ICC_AP0R1_EL1); fallthrough; case 5: case 4: write_gicreg(0, ICC_AP0R0_EL1); } isb(); } switch(pribits) { case 8: case 7: write_gicreg(0, ICC_AP1R3_EL1); write_gicreg(0, ICC_AP1R2_EL1); fallthrough; case 6: write_gicreg(0, ICC_AP1R1_EL1); fallthrough; case 5: case 4: write_gicreg(0, ICC_AP1R0_EL1); } isb(); /* ... and let's hit the road... */ gic_write_grpen1(1); /* Keep the RSS capability status in per_cpu variable */ per_cpu(has_rss, cpu) = !!(gic_read_ctlr() & ICC_CTLR_EL1_RSS); /* Check all the CPUs have capable of sending SGIs to other CPUs */ for_each_online_cpu(i) { bool have_rss = per_cpu(has_rss, i) && per_cpu(has_rss, cpu); need_rss |= MPIDR_RS(gic_cpu_to_affinity(i)); if (need_rss && (!have_rss)) pr_crit("CPU%d (%lx) can't SGI CPU%d (%lx), no RSS\n", cpu, (unsigned long)mpidr, i, (unsigned long)gic_cpu_to_affinity(i)); } /** * GIC spec says, when ICC_CTLR_EL1.RSS==1 and GICD_TYPER.RSS==0, * writing ICC_ASGI1R_EL1 register with RS != 0 is a CONSTRAINED * UNPREDICTABLE choice of : * - The write is ignored. * - The RS field is treated as 0. */ if (need_rss && (!gic_data.has_rss)) pr_crit_once("RSS is required but GICD doesn't support it\n"); } static bool gicv3_nolpi; static int __init gicv3_nolpi_cfg(char *buf) { return kstrtobool(buf, &gicv3_nolpi); } early_param("irqchip.gicv3_nolpi", gicv3_nolpi_cfg); static int gic_dist_supports_lpis(void) { return (IS_ENABLED(CONFIG_ARM_GIC_V3_ITS) && !!(readl_relaxed(gic_data.dist_base + GICD_TYPER) & GICD_TYPER_LPIS) && !gicv3_nolpi); } static void gic_cpu_init(void) { void __iomem *rbase; int i; /* Register ourselves with the rest of the world */ if (gic_populate_rdist()) return; gic_enable_redist(true); WARN((gic_data.ppi_nr > 16 || GIC_ESPI_NR != 0) && !(gic_read_ctlr() & ICC_CTLR_EL1_ExtRange), "Distributor has extended ranges, but CPU%d doesn't\n", smp_processor_id()); rbase = gic_data_rdist_sgi_base(); /* Configure SGIs/PPIs as non-secure Group-1 */ for (i = 0; i < gic_data.ppi_nr + SGI_NR; i += 32) writel_relaxed(~0, rbase + GICR_IGROUPR0 + i / 8); gic_cpu_config(rbase, gic_data.ppi_nr + SGI_NR, dist_prio_irq); gic_redist_wait_for_rwp(); /* initialise system registers */ gic_cpu_sys_reg_init(); } #ifdef CONFIG_SMP #define MPIDR_TO_SGI_RS(mpidr) (MPIDR_RS(mpidr) << ICC_SGI1R_RS_SHIFT) #define MPIDR_TO_SGI_CLUSTER_ID(mpidr) ((mpidr) & ~0xFUL) /* * gic_starting_cpu() is called after the last point where cpuhp is allowed * to fail. So pre check for problems earlier. */ static int gic_check_rdist(unsigned int cpu) { if (cpumask_test_cpu(cpu, &broken_rdists)) return -EINVAL; return 0; } static int gic_starting_cpu(unsigned int cpu) { gic_cpu_sys_reg_enable(); gic_cpu_init(); if (gic_dist_supports_lpis()) its_cpu_init(); return 0; } static u16 gic_compute_target_list(int *base_cpu, const struct cpumask *mask, unsigned long cluster_id) { int next_cpu, cpu = *base_cpu; unsigned long mpidr; u16 tlist = 0; mpidr = gic_cpu_to_affinity(cpu); while (cpu < nr_cpu_ids) { tlist |= 1 << (mpidr & 0xf); next_cpu = cpumask_next(cpu, mask); if (next_cpu >= nr_cpu_ids) goto out; cpu = next_cpu; mpidr = gic_cpu_to_affinity(cpu); if (cluster_id != MPIDR_TO_SGI_CLUSTER_ID(mpidr)) { cpu--; goto out; } } out: *base_cpu = cpu; return tlist; } #define MPIDR_TO_SGI_AFFINITY(cluster_id, level) \ (MPIDR_AFFINITY_LEVEL(cluster_id, level) \ << ICC_SGI1R_AFFINITY_## level ##_SHIFT) static void gic_send_sgi(u64 cluster_id, u16 tlist, unsigned int irq) { u64 val; val = (MPIDR_TO_SGI_AFFINITY(cluster_id, 3) | MPIDR_TO_SGI_AFFINITY(cluster_id, 2) | irq << ICC_SGI1R_SGI_ID_SHIFT | MPIDR_TO_SGI_AFFINITY(cluster_id, 1) | MPIDR_TO_SGI_RS(cluster_id) | tlist << ICC_SGI1R_TARGET_LIST_SHIFT); pr_devel("CPU%d: ICC_SGI1R_EL1 %llx\n", smp_processor_id(), val); gic_write_sgi1r(val); } static void gic_ipi_send_mask(struct irq_data *d, const struct cpumask *mask) { int cpu; if (WARN_ON(d->hwirq >= 16)) return; /* * Ensure that stores to Normal memory are visible to the * other CPUs before issuing the IPI. */ dsb(ishst); for_each_cpu(cpu, mask) { u64 cluster_id = MPIDR_TO_SGI_CLUSTER_ID(gic_cpu_to_affinity(cpu)); u16 tlist; tlist = gic_compute_target_list(&cpu, mask, cluster_id); gic_send_sgi(cluster_id, tlist, d->hwirq); } /* Force the above writes to ICC_SGI1R_EL1 to be executed */ isb(); } static void __init gic_smp_init(void) { struct irq_fwspec sgi_fwspec = { .fwnode = gic_data.fwnode, .param_count = 1, }; int base_sgi; cpuhp_setup_state_nocalls(CPUHP_BP_PREPARE_DYN, "irqchip/arm/gicv3:checkrdist", gic_check_rdist, NULL); cpuhp_setup_state_nocalls(CPUHP_AP_IRQ_GIC_STARTING, "irqchip/arm/gicv3:starting", gic_starting_cpu, NULL); /* Register all 8 non-secure SGIs */ base_sgi = irq_domain_alloc_irqs(gic_data.domain, 8, NUMA_NO_NODE, &sgi_fwspec); if (WARN_ON(base_sgi <= 0)) return; set_smp_ipi_range(base_sgi, 8); } static int gic_set_affinity(struct irq_data *d, const struct cpumask *mask_val, bool force) { unsigned int cpu; u32 offset, index; void __iomem *reg; int enabled; u64 val; if (force) cpu = cpumask_first(mask_val); else cpu = cpumask_any_and(mask_val, cpu_online_mask); if (cpu >= nr_cpu_ids) return -EINVAL; if (gic_irq_in_rdist(d)) return -EINVAL; /* If interrupt was enabled, disable it first */ enabled = gic_peek_irq(d, GICD_ISENABLER); if (enabled) gic_mask_irq(d); offset = convert_offset_index(d, GICD_IROUTER, &index); reg = gic_dist_base(d) + offset + (index * 8); val = gic_cpu_to_affinity(cpu); gic_write_irouter(val, reg); /* * If the interrupt was enabled, enabled it again. Otherwise, * just wait for the distributor to have digested our changes. */ if (enabled) gic_unmask_irq(d); irq_data_update_effective_affinity(d, cpumask_of(cpu)); return IRQ_SET_MASK_OK_DONE; } #else #define gic_set_affinity NULL #define gic_ipi_send_mask NULL #define gic_smp_init() do { } while(0) #endif static int gic_retrigger(struct irq_data *data) { return !gic_irq_set_irqchip_state(data, IRQCHIP_STATE_PENDING, true); } #ifdef CONFIG_CPU_PM static int gic_cpu_pm_notifier(struct notifier_block *self, unsigned long cmd, void *v) { if (cmd == CPU_PM_EXIT) { if (gic_dist_security_disabled()) gic_enable_redist(true); gic_cpu_sys_reg_enable(); gic_cpu_sys_reg_init(); } else if (cmd == CPU_PM_ENTER && gic_dist_security_disabled()) { gic_write_grpen1(0); gic_enable_redist(false); } return NOTIFY_OK; } static struct notifier_block gic_cpu_pm_notifier_block = { .notifier_call = gic_cpu_pm_notifier, }; static void gic_cpu_pm_init(void) { cpu_pm_register_notifier(&gic_cpu_pm_notifier_block); } #else static inline void gic_cpu_pm_init(void) { } #endif /* CONFIG_CPU_PM */ static struct irq_chip gic_chip = { .name = "GICv3", .irq_mask = gic_mask_irq, .irq_unmask = gic_unmask_irq, .irq_eoi = gic_eoi_irq, .irq_set_type = gic_set_type, .irq_set_affinity = gic_set_affinity, .irq_retrigger = gic_retrigger, .irq_get_irqchip_state = gic_irq_get_irqchip_state, .irq_set_irqchip_state = gic_irq_set_irqchip_state, .irq_nmi_setup = gic_irq_nmi_setup, .irq_nmi_teardown = gic_irq_nmi_teardown, .ipi_send_mask = gic_ipi_send_mask, .flags = IRQCHIP_SET_TYPE_MASKED | IRQCHIP_SKIP_SET_WAKE | IRQCHIP_MASK_ON_SUSPEND, }; static struct irq_chip gic_eoimode1_chip = { .name = "GICv3", .irq_mask = gic_eoimode1_mask_irq, .irq_unmask = gic_unmask_irq, .irq_eoi = gic_eoimode1_eoi_irq, .irq_set_type = gic_set_type, .irq_set_affinity = gic_set_affinity, .irq_retrigger = gic_retrigger, .irq_get_irqchip_state = gic_irq_get_irqchip_state, .irq_set_irqchip_state = gic_irq_set_irqchip_state, .irq_set_vcpu_affinity = gic_irq_set_vcpu_affinity, .irq_nmi_setup = gic_irq_nmi_setup, .irq_nmi_teardown = gic_irq_nmi_teardown, .ipi_send_mask = gic_ipi_send_mask, .flags = IRQCHIP_SET_TYPE_MASKED | IRQCHIP_SKIP_SET_WAKE | IRQCHIP_MASK_ON_SUSPEND, }; static int gic_irq_domain_map(struct irq_domain *d, unsigned int irq, irq_hw_number_t hw) { struct irq_chip *chip = &gic_chip; struct irq_data *irqd = irq_desc_get_irq_data(irq_to_desc(irq)); if (static_branch_likely(&supports_deactivate_key)) chip = &gic_eoimode1_chip; switch (__get_intid_range(hw)) { case SGI_RANGE: case PPI_RANGE: case EPPI_RANGE: irq_set_percpu_devid(irq); irq_domain_set_info(d, irq, hw, chip, d->host_data, handle_percpu_devid_irq, NULL, NULL); break; case SPI_RANGE: case ESPI_RANGE: irq_domain_set_info(d, irq, hw, chip, d->host_data, handle_fasteoi_irq, NULL, NULL); irq_set_probe(irq); irqd_set_single_target(irqd); break; case LPI_RANGE: if (!gic_dist_supports_lpis()) return -EPERM; irq_domain_set_info(d, irq, hw, chip, d->host_data, handle_fasteoi_irq, NULL, NULL); break; default: return -EPERM; } /* Prevents SW retriggers which mess up the ACK/EOI ordering */ irqd_set_handle_enforce_irqctx(irqd); return 0; } static int gic_irq_domain_translate(struct irq_domain *d, struct irq_fwspec *fwspec, unsigned long *hwirq, unsigned int *type) { if (fwspec->param_count == 1 && fwspec->param[0] < 16) { *hwirq = fwspec->param[0]; *type = IRQ_TYPE_EDGE_RISING; return 0; } if (is_of_node(fwspec->fwnode)) { if (fwspec->param_count < 3) return -EINVAL; switch (fwspec->param[0]) { case 0: /* SPI */ *hwirq = fwspec->param[1] + 32; break; case 1: /* PPI */ *hwirq = fwspec->param[1] + 16; break; case 2: /* ESPI */ *hwirq = fwspec->param[1] + ESPI_BASE_INTID; break; case 3: /* EPPI */ *hwirq = fwspec->param[1] + EPPI_BASE_INTID; break; case GIC_IRQ_TYPE_LPI: /* LPI */ *hwirq = fwspec->param[1]; break; case GIC_IRQ_TYPE_PARTITION: *hwirq = fwspec->param[1]; if (fwspec->param[1] >= 16) *hwirq += EPPI_BASE_INTID - 16; else *hwirq += 16; break; default: return -EINVAL; } *type = fwspec->param[2] & IRQ_TYPE_SENSE_MASK; /* * Make it clear that broken DTs are... broken. * Partitioned PPIs are an unfortunate exception. */ WARN_ON(*type == IRQ_TYPE_NONE && fwspec->param[0] != GIC_IRQ_TYPE_PARTITION); return 0; } if (is_fwnode_irqchip(fwspec->fwnode)) { if(fwspec->param_count != 2) return -EINVAL; if (fwspec->param[0] < 16) { pr_err(FW_BUG "Illegal GSI%d translation request\n", fwspec->param[0]); return -EINVAL; } *hwirq = fwspec->param[0]; *type = fwspec->param[1]; WARN_ON(*type == IRQ_TYPE_NONE); return 0; } return -EINVAL; } static int gic_irq_domain_alloc(struct irq_domain *domain, unsigned int virq, unsigned int nr_irqs, void *arg) { int i, ret; irq_hw_number_t hwirq; unsigned int type = IRQ_TYPE_NONE; struct irq_fwspec *fwspec = arg; ret = gic_irq_domain_translate(domain, fwspec, &hwirq, &type); if (ret) return ret; for (i = 0; i < nr_irqs; i++) { ret = gic_irq_domain_map(domain, virq + i, hwirq + i); if (ret) return ret; } return 0; } static void gic_irq_domain_free(struct irq_domain *domain, unsigned int virq, unsigned int nr_irqs) { int i; for (i = 0; i < nr_irqs; i++) { struct irq_data *d = irq_domain_get_irq_data(domain, virq + i); irq_set_handler(virq + i, NULL); irq_domain_reset_irq_data(d); } } static bool fwspec_is_partitioned_ppi(struct irq_fwspec *fwspec, irq_hw_number_t hwirq) { enum gic_intid_range range; if (!gic_data.ppi_descs) return false; if (!is_of_node(fwspec->fwnode)) return false; if (fwspec->param_count < 4 || !fwspec->param[3]) return false; range = __get_intid_range(hwirq); if (range != PPI_RANGE && range != EPPI_RANGE) return false; return true; } static int gic_irq_domain_select(struct irq_domain *d, struct irq_fwspec *fwspec, enum irq_domain_bus_token bus_token) { unsigned int type, ret, ppi_idx; irq_hw_number_t hwirq; /* Not for us */ if (fwspec->fwnode != d->fwnode) return 0; /* Handle pure domain searches */ if (!fwspec->param_count) return d->bus_token == bus_token; /* If this is not DT, then we have a single domain */ if (!is_of_node(fwspec->fwnode)) return 1; ret = gic_irq_domain_translate(d, fwspec, &hwirq, &type); if (WARN_ON_ONCE(ret)) return 0; if (!fwspec_is_partitioned_ppi(fwspec, hwirq)) return d == gic_data.domain; /* * If this is a PPI and we have a 4th (non-null) parameter, * then we need to match the partition domain. */ ppi_idx = __gic_get_ppi_index(hwirq); return d == partition_get_domain(gic_data.ppi_descs[ppi_idx]); } static const struct irq_domain_ops gic_irq_domain_ops = { .translate = gic_irq_domain_translate, .alloc = gic_irq_domain_alloc, .free = gic_irq_domain_free, .select = gic_irq_domain_select, }; static int partition_domain_translate(struct irq_domain *d, struct irq_fwspec *fwspec, unsigned long *hwirq, unsigned int *type) { unsigned long ppi_intid; struct device_node *np; unsigned int ppi_idx; int ret; if (!gic_data.ppi_descs) return -ENOMEM; np = of_find_node_by_phandle(fwspec->param[3]); if (WARN_ON(!np)) return -EINVAL; ret = gic_irq_domain_translate(d, fwspec, &ppi_intid, type); if (WARN_ON_ONCE(ret)) return 0; ppi_idx = __gic_get_ppi_index(ppi_intid); ret = partition_translate_id(gic_data.ppi_descs[ppi_idx], of_node_to_fwnode(np)); if (ret < 0) return ret; *hwirq = ret; *type = fwspec->param[2] & IRQ_TYPE_SENSE_MASK; return 0; } static const struct irq_domain_ops partition_domain_ops = { .translate = partition_domain_translate, .select = gic_irq_domain_select, }; static bool gic_enable_quirk_msm8996(void *data) { struct gic_chip_data *d = data; d->flags |= FLAGS_WORKAROUND_GICR_WAKER_MSM8996; return true; } static bool gic_enable_quirk_cavium_38539(void *data) { struct gic_chip_data *d = data; d->flags |= FLAGS_WORKAROUND_CAVIUM_ERRATUM_38539; return true; } static bool gic_enable_quirk_hip06_07(void *data) { struct gic_chip_data *d = data; /* * HIP06 GICD_IIDR clashes with GIC-600 product number (despite * not being an actual ARM implementation). The saving grace is * that GIC-600 doesn't have ESPI, so nothing to do in that case. * HIP07 doesn't even have a proper IIDR, and still pretends to * have ESPI. In both cases, put them right. */ if (d->rdists.gicd_typer & GICD_TYPER_ESPI) { /* Zero both ESPI and the RES0 field next to it... */ d->rdists.gicd_typer &= ~GENMASK(9, 8); return true; } return false; } #define T241_CHIPN_MASK GENMASK_ULL(45, 44) #define T241_CHIP_GICDA_OFFSET 0x1580000 #define SMCCC_SOC_ID_T241 0x036b0241 static bool gic_enable_quirk_nvidia_t241(void *data) { s32 soc_id = arm_smccc_get_soc_id_version(); unsigned long chip_bmask = 0; phys_addr_t phys; u32 i; /* Check JEP106 code for NVIDIA T241 chip (036b:0241) */ if ((soc_id < 0) || (soc_id != SMCCC_SOC_ID_T241)) return false; /* Find the chips based on GICR regions PHYS addr */ for (i = 0; i < gic_data.nr_redist_regions; i++) { chip_bmask |= BIT(FIELD_GET(T241_CHIPN_MASK, (u64)gic_data.redist_regions[i].phys_base)); } if (hweight32(chip_bmask) < 3) return false; /* Setup GICD alias regions */ for (i = 0; i < ARRAY_SIZE(t241_dist_base_alias); i++) { if (chip_bmask & BIT(i)) { phys = gic_data.dist_phys_base + T241_CHIP_GICDA_OFFSET; phys |= FIELD_PREP(T241_CHIPN_MASK, i); t241_dist_base_alias[i] = ioremap(phys, SZ_64K); WARN_ON_ONCE(!t241_dist_base_alias[i]); } } static_branch_enable(&gic_nvidia_t241_erratum); return true; } static bool gic_enable_quirk_asr8601(void *data) { struct gic_chip_data *d = data; d->flags |= FLAGS_WORKAROUND_ASR_ERRATUM_8601001; return true; } static bool gic_enable_quirk_arm64_2941627(void *data) { static_branch_enable(&gic_arm64_2941627_erratum); return true; } static bool rd_set_non_coherent(void *data) { struct gic_chip_data *d = data; d->rdists.flags |= RDIST_FLAGS_FORCE_NON_SHAREABLE; return true; } static const struct gic_quirk gic_quirks[] = { { .desc = "GICv3: Qualcomm MSM8996 broken firmware", .compatible = "qcom,msm8996-gic-v3", .init = gic_enable_quirk_msm8996, }, { .desc = "GICv3: ASR erratum 8601001", .compatible = "asr,asr8601-gic-v3", .init = gic_enable_quirk_asr8601, }, { .desc = "GICv3: HIP06 erratum 161010803", .iidr = 0x0204043b, .mask = 0xffffffff, .init = gic_enable_quirk_hip06_07, }, { .desc = "GICv3: HIP07 erratum 161010803", .iidr = 0x00000000, .mask = 0xffffffff, .init = gic_enable_quirk_hip06_07, }, { /* * Reserved register accesses generate a Synchronous * External Abort. This erratum applies to: * - ThunderX: CN88xx * - OCTEON TX: CN83xx, CN81xx * - OCTEON TX2: CN93xx, CN96xx, CN98xx, CNF95xx* */ .desc = "GICv3: Cavium erratum 38539", .iidr = 0xa000034c, .mask = 0xe8f00fff, .init = gic_enable_quirk_cavium_38539, }, { .desc = "GICv3: NVIDIA erratum T241-FABRIC-4", .iidr = 0x0402043b, .mask = 0xffffffff, .init = gic_enable_quirk_nvidia_t241, }, { /* * GIC-700: 2941627 workaround - IP variant [0,1] * */ .desc = "GICv3: ARM64 erratum 2941627", .iidr = 0x0400043b, .mask = 0xff0e0fff, .init = gic_enable_quirk_arm64_2941627, }, { /* * GIC-700: 2941627 workaround - IP variant [2] */ .desc = "GICv3: ARM64 erratum 2941627", .iidr = 0x0402043b, .mask = 0xff0f0fff, .init = gic_enable_quirk_arm64_2941627, }, { .desc = "GICv3: non-coherent attribute", .property = "dma-noncoherent", .init = rd_set_non_coherent, }, { } }; static void gic_enable_nmi_support(void) { int i; if (!gic_prio_masking_enabled()) return; rdist_nmi_refs = kcalloc(gic_data.ppi_nr + SGI_NR, sizeof(*rdist_nmi_refs), GFP_KERNEL); if (!rdist_nmi_refs) return; for (i = 0; i < gic_data.ppi_nr + SGI_NR; i++) refcount_set(&rdist_nmi_refs[i], 0); pr_info("Pseudo-NMIs enabled using %s ICC_PMR_EL1 synchronisation\n", gic_has_relaxed_pmr_sync() ? "relaxed" : "forced"); static_branch_enable(&supports_pseudo_nmis); if (static_branch_likely(&supports_deactivate_key)) gic_eoimode1_chip.flags |= IRQCHIP_SUPPORTS_NMI; else gic_chip.flags |= IRQCHIP_SUPPORTS_NMI; } static int __init gic_init_bases(phys_addr_t dist_phys_base, void __iomem *dist_base, struct redist_region *rdist_regs, u32 nr_redist_regions, u64 redist_stride, struct fwnode_handle *handle) { u32 typer; int err; if (!is_hyp_mode_available()) static_branch_disable(&supports_deactivate_key); if (static_branch_likely(&supports_deactivate_key)) pr_info("GIC: Using split EOI/Deactivate mode\n"); gic_data.fwnode = handle; gic_data.dist_phys_base = dist_phys_base; gic_data.dist_base = dist_base; gic_data.redist_regions = rdist_regs; gic_data.nr_redist_regions = nr_redist_regions; gic_data.redist_stride = redist_stride; /* * Find out how many interrupts are supported. */ typer = readl_relaxed(gic_data.dist_base + GICD_TYPER); gic_data.rdists.gicd_typer = typer; gic_enable_quirks(readl_relaxed(gic_data.dist_base + GICD_IIDR), gic_quirks, &gic_data); pr_info("%d SPIs implemented\n", GIC_LINE_NR - 32); pr_info("%d Extended SPIs implemented\n", GIC_ESPI_NR); /* * ThunderX1 explodes on reading GICD_TYPER2, in violation of the * architecture spec (which says that reserved registers are RES0). */ if (!(gic_data.flags & FLAGS_WORKAROUND_CAVIUM_ERRATUM_38539)) gic_data.rdists.gicd_typer2 = readl_relaxed(gic_data.dist_base + GICD_TYPER2); gic_data.domain = irq_domain_create_tree(handle, &gic_irq_domain_ops, &gic_data); gic_data.rdists.rdist = alloc_percpu(typeof(*gic_data.rdists.rdist)); if (!static_branch_unlikely(&gic_nvidia_t241_erratum)) { /* Disable GICv4.x features for the erratum T241-FABRIC-4 */ gic_data.rdists.has_rvpeid = true; gic_data.rdists.has_vlpis = true; gic_data.rdists.has_direct_lpi = true; gic_data.rdists.has_vpend_valid_dirty = true; } if (WARN_ON(!gic_data.domain) || WARN_ON(!gic_data.rdists.rdist)) { err = -ENOMEM; goto out_free; } irq_domain_update_bus_token(gic_data.domain, DOMAIN_BUS_WIRED); gic_data.has_rss = !!(typer & GICD_TYPER_RSS); if (typer & GICD_TYPER_MBIS) { err = mbi_init(handle, gic_data.domain); if (err) pr_err("Failed to initialize MBIs\n"); } set_handle_irq(gic_handle_irq); gic_update_rdist_properties(); gic_cpu_sys_reg_enable(); gic_prio_init(); gic_dist_init(); gic_cpu_init(); gic_enable_nmi_support(); gic_smp_init(); gic_cpu_pm_init(); if (gic_dist_supports_lpis()) { its_init(handle, &gic_data.rdists, gic_data.domain, dist_prio_irq); its_cpu_init(); its_lpi_memreserve_init(); } else { if (IS_ENABLED(CONFIG_ARM_GIC_V2M)) gicv2m_init(handle, gic_data.domain); } return 0; out_free: if (gic_data.domain) irq_domain_remove(gic_data.domain); free_percpu(gic_data.rdists.rdist); return err; } static int __init gic_validate_dist_version(void __iomem *dist_base) { u32 reg = readl_relaxed(dist_base + GICD_PIDR2) & GIC_PIDR2_ARCH_MASK; if (reg != GIC_PIDR2_ARCH_GICv3 && reg != GIC_PIDR2_ARCH_GICv4) return -ENODEV; return 0; } /* Create all possible partitions at boot time */ static void __init gic_populate_ppi_partitions(struct device_node *gic_node) { struct device_node *parts_node, *child_part; int part_idx = 0, i; int nr_parts; struct partition_affinity *parts; parts_node = of_get_child_by_name(gic_node, "ppi-partitions"); if (!parts_node) return; gic_data.ppi_descs = kcalloc(gic_data.ppi_nr, sizeof(*gic_data.ppi_descs), GFP_KERNEL); if (!gic_data.ppi_descs) goto out_put_node; nr_parts = of_get_child_count(parts_node); if (!nr_parts) goto out_put_node; parts = kcalloc(nr_parts, sizeof(*parts), GFP_KERNEL); if (WARN_ON(!parts)) goto out_put_node; for_each_child_of_node(parts_node, child_part) { struct partition_affinity *part; int n; part = &parts[part_idx]; part->partition_id = of_node_to_fwnode(child_part); pr_info("GIC: PPI partition %pOFn[%d] { ", child_part, part_idx); n = of_property_count_elems_of_size(child_part, "affinity", sizeof(u32)); WARN_ON(n <= 0); for (i = 0; i < n; i++) { int err, cpu; u32 cpu_phandle; struct device_node *cpu_node; err = of_property_read_u32_index(child_part, "affinity", i, &cpu_phandle); if (WARN_ON(err)) continue; cpu_node = of_find_node_by_phandle(cpu_phandle); if (WARN_ON(!cpu_node)) continue; cpu = of_cpu_node_to_id(cpu_node); if (WARN_ON(cpu < 0)) { of_node_put(cpu_node); continue; } pr_cont("%pOF[%d] ", cpu_node, cpu); cpumask_set_cpu(cpu, &part->mask); of_node_put(cpu_node); } pr_cont("}\n"); part_idx++; } for (i = 0; i < gic_data.ppi_nr; i++) { unsigned int irq; struct partition_desc *desc; struct irq_fwspec ppi_fwspec = { .fwnode = gic_data.fwnode, .param_count = 3, .param = { [0] = GIC_IRQ_TYPE_PARTITION, [1] = i, [2] = IRQ_TYPE_NONE, }, }; irq = irq_create_fwspec_mapping(&ppi_fwspec); if (WARN_ON(!irq)) continue; desc = partition_create_desc(gic_data.fwnode, parts, nr_parts, irq, &partition_domain_ops); if (WARN_ON(!desc)) continue; gic_data.ppi_descs[i] = desc; } out_put_node: of_node_put(parts_node); } static void __init gic_of_setup_kvm_info(struct device_node *node, u32 nr_redist_regions) { int ret; struct resource r; gic_v3_kvm_info.type = GIC_V3; gic_v3_kvm_info.maint_irq = irq_of_parse_and_map(node, 0); if (!gic_v3_kvm_info.maint_irq) return; /* Also skip GICD, GICC, GICH */ ret = of_address_to_resource(node, nr_redist_regions + 3, &r); if (!ret) gic_v3_kvm_info.vcpu = r; gic_v3_kvm_info.has_v4 = gic_data.rdists.has_vlpis; gic_v3_kvm_info.has_v4_1 = gic_data.rdists.has_rvpeid; vgic_set_kvm_info(&gic_v3_kvm_info); } static void gic_request_region(resource_size_t base, resource_size_t size, const char *name) { if (!request_mem_region(base, size, name)) pr_warn_once(FW_BUG "%s region %pa has overlapping address\n", name, &base); } static void __iomem *gic_of_iomap(struct device_node *node, int idx, const char *name, struct resource *res) { void __iomem *base; int ret; ret = of_address_to_resource(node, idx, res); if (ret) return IOMEM_ERR_PTR(ret); gic_request_region(res->start, resource_size(res), name); base = of_iomap(node, idx); return base ?: IOMEM_ERR_PTR(-ENOMEM); } static int __init gic_of_init(struct device_node *node, struct device_node *parent) { phys_addr_t dist_phys_base; void __iomem *dist_base; struct redist_region *rdist_regs; struct resource res; u64 redist_stride; u32 nr_redist_regions; int err, i; dist_base = gic_of_iomap(node, 0, "GICD", &res); if (IS_ERR(dist_base)) { pr_err("%pOF: unable to map gic dist registers\n", node); return PTR_ERR(dist_base); } dist_phys_base = res.start; err = gic_validate_dist_version(dist_base); if (err) { pr_err("%pOF: no distributor detected, giving up\n", node); goto out_unmap_dist; } if (of_property_read_u32(node, "#redistributor-regions", &nr_redist_regions)) nr_redist_regions = 1; rdist_regs = kcalloc(nr_redist_regions, sizeof(*rdist_regs), GFP_KERNEL); if (!rdist_regs) { err = -ENOMEM; goto out_unmap_dist; } for (i = 0; i < nr_redist_regions; i++) { rdist_regs[i].redist_base = gic_of_iomap(node, 1 + i, "GICR", &res); if (IS_ERR(rdist_regs[i].redist_base)) { pr_err("%pOF: couldn't map region %d\n", node, i); err = -ENODEV; goto out_unmap_rdist; } rdist_regs[i].phys_base = res.start; } if (of_property_read_u64(node, "redistributor-stride", &redist_stride)) redist_stride = 0; gic_enable_of_quirks(node, gic_quirks, &gic_data); err = gic_init_bases(dist_phys_base, dist_base, rdist_regs, nr_redist_regions, redist_stride, &node->fwnode); if (err) goto out_unmap_rdist; gic_populate_ppi_partitions(node); if (static_branch_likely(&supports_deactivate_key)) gic_of_setup_kvm_info(node, nr_redist_regions); return 0; out_unmap_rdist: for (i = 0; i < nr_redist_regions; i++) if (rdist_regs[i].redist_base && !IS_ERR(rdist_regs[i].redist_base)) iounmap(rdist_regs[i].redist_base); kfree(rdist_regs); out_unmap_dist: iounmap(dist_base); return err; } IRQCHIP_DECLARE(gic_v3, "arm,gic-v3", gic_of_init); #ifdef CONFIG_ACPI static struct { void __iomem *dist_base; struct redist_region *redist_regs; u32 nr_redist_regions; bool single_redist; int enabled_rdists; u32 maint_irq; int maint_irq_mode; phys_addr_t vcpu_base; } acpi_data __initdata; static void __init gic_acpi_register_redist(phys_addr_t phys_base, void __iomem *redist_base) { static int count = 0; acpi_data.redist_regs[count].phys_base = phys_base; acpi_data.redist_regs[count].redist_base = redist_base; acpi_data.redist_regs[count].single_redist = acpi_data.single_redist; count++; } static int __init gic_acpi_parse_madt_redist(union acpi_subtable_headers *header, const unsigned long end) { struct acpi_madt_generic_redistributor *redist = (struct acpi_madt_generic_redistributor *)header; void __iomem *redist_base; redist_base = ioremap(redist->base_address, redist->length); if (!redist_base) { pr_err("Couldn't map GICR region @%llx\n", redist->base_address); return -ENOMEM; } if (acpi_get_madt_revision() >= 7 && (redist->flags & ACPI_MADT_GICR_NON_COHERENT)) gic_data.rdists.flags |= RDIST_FLAGS_FORCE_NON_SHAREABLE; gic_request_region(redist->base_address, redist->length, "GICR"); gic_acpi_register_redist(redist->base_address, redist_base); return 0; } static int __init gic_acpi_parse_madt_gicc(union acpi_subtable_headers *header, const unsigned long end) { struct acpi_madt_generic_interrupt *gicc = (struct acpi_madt_generic_interrupt *)header; u32 reg = readl_relaxed(acpi_data.dist_base + GICD_PIDR2) & GIC_PIDR2_ARCH_MASK; u32 size = reg == GIC_PIDR2_ARCH_GICv4 ? SZ_64K * 4 : SZ_64K * 2; void __iomem *redist_base; /* Neither enabled or online capable means it doesn't exist, skip it */ if (!(gicc->flags & (ACPI_MADT_ENABLED | ACPI_MADT_GICC_ONLINE_CAPABLE))) return 0; /* * Capable but disabled CPUs can be brought online later. What about * the redistributor? ACPI doesn't want to say! * Virtual hotplug systems can use the MADT's "always-on" GICR entries. * Otherwise, prevent such CPUs from being brought online. */ if (!(gicc->flags & ACPI_MADT_ENABLED)) { int cpu = get_cpu_for_acpi_id(gicc->uid); pr_warn("CPU %u's redistributor is inaccessible: this CPU can't be brought online\n", cpu); if (cpu >= 0) cpumask_set_cpu(cpu, &broken_rdists); return 0; } redist_base = ioremap(gicc->gicr_base_address, size); if (!redist_base) return -ENOMEM; gic_request_region(gicc->gicr_base_address, size, "GICR"); if (acpi_get_madt_revision() >= 7 && (gicc->flags & ACPI_MADT_GICC_NON_COHERENT)) gic_data.rdists.flags |= RDIST_FLAGS_FORCE_NON_SHAREABLE; gic_acpi_register_redist(gicc->gicr_base_address, redist_base); return 0; } static int __init gic_acpi_collect_gicr_base(void) { acpi_tbl_entry_handler redist_parser; enum acpi_madt_type type; if (acpi_data.single_redist) { type = ACPI_MADT_TYPE_GENERIC_INTERRUPT; redist_parser = gic_acpi_parse_madt_gicc; } else { type = ACPI_MADT_TYPE_GENERIC_REDISTRIBUTOR; redist_parser = gic_acpi_parse_madt_redist; } /* Collect redistributor base addresses in GICR entries */ if (acpi_table_parse_madt(type, redist_parser, 0) > 0) return 0; pr_info("No valid GICR entries exist\n"); return -ENODEV; } static int __init gic_acpi_match_gicr(union acpi_subtable_headers *header, const unsigned long end) { /* Subtable presence means that redist exists, that's it */ return 0; } static int __init gic_acpi_match_gicc(union acpi_subtable_headers *header, const unsigned long end) { struct acpi_madt_generic_interrupt *gicc = (struct acpi_madt_generic_interrupt *)header; /* * If GICC is enabled and has valid gicr base address, then it means * GICR base is presented via GICC. The redistributor is only known to * be accessible if the GICC is marked as enabled. If this bit is not * set, we'd need to add the redistributor at runtime, which isn't * supported. */ if (gicc->flags & ACPI_MADT_ENABLED && gicc->gicr_base_address) acpi_data.enabled_rdists++; return 0; } static int __init gic_acpi_count_gicr_regions(void) { int count; /* * Count how many redistributor regions we have. It is not allowed * to mix redistributor description, GICR and GICC subtables have to be * mutually exclusive. */ count = acpi_table_parse_madt(ACPI_MADT_TYPE_GENERIC_REDISTRIBUTOR, gic_acpi_match_gicr, 0); if (count > 0) { acpi_data.single_redist = false; return count; } count = acpi_table_parse_madt(ACPI_MADT_TYPE_GENERIC_INTERRUPT, gic_acpi_match_gicc, 0); if (count > 0) { acpi_data.single_redist = true; count = acpi_data.enabled_rdists; } return count; } static bool __init acpi_validate_gic_table(struct acpi_subtable_header *header, struct acpi_probe_entry *ape) { struct acpi_madt_generic_distributor *dist; int count; dist = (struct acpi_madt_generic_distributor *)header; if (dist->version != ape->driver_data) return false; /* We need to do that exercise anyway, the sooner the better */ count = gic_acpi_count_gicr_regions(); if (count <= 0) return false; acpi_data.nr_redist_regions = count; return true; } static int __init gic_acpi_parse_virt_madt_gicc(union acpi_subtable_headers *header, const unsigned long end) { struct acpi_madt_generic_interrupt *gicc = (struct acpi_madt_generic_interrupt *)header; int maint_irq_mode; static int first_madt = true; if (!(gicc->flags & (ACPI_MADT_ENABLED | ACPI_MADT_GICC_ONLINE_CAPABLE))) return 0; maint_irq_mode = (gicc->flags & ACPI_MADT_VGIC_IRQ_MODE) ? ACPI_EDGE_SENSITIVE : ACPI_LEVEL_SENSITIVE; if (first_madt) { first_madt = false; acpi_data.maint_irq = gicc->vgic_interrupt; acpi_data.maint_irq_mode = maint_irq_mode; acpi_data.vcpu_base = gicc->gicv_base_address; return 0; } /* * The maintenance interrupt and GICV should be the same for every CPU */ if ((acpi_data.maint_irq != gicc->vgic_interrupt) || (acpi_data.maint_irq_mode != maint_irq_mode) || (acpi_data.vcpu_base != gicc->gicv_base_address)) return -EINVAL; return 0; } static bool __init gic_acpi_collect_virt_info(void) { int count; count = acpi_table_parse_madt(ACPI_MADT_TYPE_GENERIC_INTERRUPT, gic_acpi_parse_virt_madt_gicc, 0); return (count > 0); } #define ACPI_GICV3_DIST_MEM_SIZE (SZ_64K) #define ACPI_GICV2_VCTRL_MEM_SIZE (SZ_4K) #define ACPI_GICV2_VCPU_MEM_SIZE (SZ_8K) static void __init gic_acpi_setup_kvm_info(void) { int irq; if (!gic_acpi_collect_virt_info()) { pr_warn("Unable to get hardware information used for virtualization\n"); return; } gic_v3_kvm_info.type = GIC_V3; irq = acpi_register_gsi(NULL, acpi_data.maint_irq, acpi_data.maint_irq_mode, ACPI_ACTIVE_HIGH); if (irq <= 0) return; gic_v3_kvm_info.maint_irq = irq; if (acpi_data.vcpu_base) { struct resource *vcpu = &gic_v3_kvm_info.vcpu; vcpu->flags = IORESOURCE_MEM; vcpu->start = acpi_data.vcpu_base; vcpu->end = vcpu->start + ACPI_GICV2_VCPU_MEM_SIZE - 1; } gic_v3_kvm_info.has_v4 = gic_data.rdists.has_vlpis; gic_v3_kvm_info.has_v4_1 = gic_data.rdists.has_rvpeid; vgic_set_kvm_info(&gic_v3_kvm_info); } static struct fwnode_handle *gsi_domain_handle; static struct fwnode_handle *gic_v3_get_gsi_domain_id(u32 gsi) { return gsi_domain_handle; } static int __init gic_acpi_init(union acpi_subtable_headers *header, const unsigned long end) { struct acpi_madt_generic_distributor *dist; size_t size; int i, err; /* Get distributor base address */ dist = (struct acpi_madt_generic_distributor *)header; acpi_data.dist_base = ioremap(dist->base_address, ACPI_GICV3_DIST_MEM_SIZE); if (!acpi_data.dist_base) { pr_err("Unable to map GICD registers\n"); return -ENOMEM; } gic_request_region(dist->base_address, ACPI_GICV3_DIST_MEM_SIZE, "GICD"); err = gic_validate_dist_version(acpi_data.dist_base); if (err) { pr_err("No distributor detected at @%p, giving up\n", acpi_data.dist_base); goto out_dist_unmap; } size = sizeof(*acpi_data.redist_regs) * acpi_data.nr_redist_regions; acpi_data.redist_regs = kzalloc(size, GFP_KERNEL); if (!acpi_data.redist_regs) { err = -ENOMEM; goto out_dist_unmap; } err = gic_acpi_collect_gicr_base(); if (err) goto out_redist_unmap; gsi_domain_handle = irq_domain_alloc_fwnode(&dist->base_address); if (!gsi_domain_handle) { err = -ENOMEM; goto out_redist_unmap; } err = gic_init_bases(dist->base_address, acpi_data.dist_base, acpi_data.redist_regs, acpi_data.nr_redist_regions, 0, gsi_domain_handle); if (err) goto out_fwhandle_free; acpi_set_irq_model(ACPI_IRQ_MODEL_GIC, gic_v3_get_gsi_domain_id); if (static_branch_likely(&supports_deactivate_key)) gic_acpi_setup_kvm_info(); return 0; out_fwhandle_free: irq_domain_free_fwnode(gsi_domain_handle); out_redist_unmap: for (i = 0; i < acpi_data.nr_redist_regions; i++) if (acpi_data.redist_regs[i].redist_base) iounmap(acpi_data.redist_regs[i].redist_base); kfree(acpi_data.redist_regs); out_dist_unmap: iounmap(acpi_data.dist_base); return err; } IRQCHIP_ACPI_DECLARE(gic_v3, ACPI_MADT_TYPE_GENERIC_DISTRIBUTOR, acpi_validate_gic_table, ACPI_MADT_GIC_VERSION_V3, gic_acpi_init); IRQCHIP_ACPI_DECLARE(gic_v4, ACPI_MADT_TYPE_GENERIC_DISTRIBUTOR, acpi_validate_gic_table, ACPI_MADT_GIC_VERSION_V4, gic_acpi_init); IRQCHIP_ACPI_DECLARE(gic_v3_or_v4, ACPI_MADT_TYPE_GENERIC_DISTRIBUTOR, acpi_validate_gic_table, ACPI_MADT_GIC_VERSION_NONE, gic_acpi_init); #endif |
| 22 219 236 236 134 220 209 218 110 109 110 75 220 187 220 69 2 1 186 220 187 235 236 236 219 220 69 236 236 8 231 232 183 224 169 78 20 3 68 164 115 54 116 109 97 52 110 220 214 203 220 219 219 219 219 137 219 14 8 219 12 61 58 69 220 66 220 128 220 106 21 18 19 20 22 6 22 4 6 22 220 220 220 220 116 180 220 220 219 220 220 116 219 217 219 217 21 22 22 22 22 22 22 220 220 220 22 219 220 219 220 219 219 220 220 220 220 220 220 219 220 22 22 22 22 22 30 29 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 1522 1523 1524 1525 1526 1527 1528 1529 1530 1531 1532 1533 1534 1535 1536 1537 1538 1539 1540 1541 1542 1543 1544 1545 1546 1547 1548 1549 1550 1551 1552 1553 1554 1555 1556 1557 1558 1559 1560 1561 1562 1563 1564 1565 1566 1567 1568 1569 1570 1571 1572 1573 1574 1575 1576 1577 1578 1579 1580 1581 1582 1583 1584 1585 1586 1587 1588 1589 1590 1591 1592 1593 1594 1595 1596 1597 1598 1599 1600 1601 1602 1603 1604 1605 1606 1607 1608 1609 1610 1611 1612 1613 1614 1615 1616 1617 1618 1619 1620 1621 1622 1623 1624 1625 1626 1627 1628 1629 1630 1631 1632 1633 1634 1635 1636 1637 1638 1639 1640 1641 1642 1643 1644 1645 1646 1647 1648 1649 1650 1651 1652 1653 1654 1655 1656 1657 1658 1659 1660 1661 1662 1663 1664 1665 1666 1667 1668 1669 1670 1671 1672 1673 1674 1675 1676 1677 1678 1679 1680 1681 1682 1683 1684 1685 1686 1687 1688 1689 1690 1691 1692 1693 1694 1695 1696 1697 1698 1699 1700 1701 1702 1703 1704 1705 1706 1707 1708 1709 1710 1711 1712 1713 1714 1715 1716 1717 1718 1719 1720 1721 1722 1723 1724 1725 1726 1727 1728 1729 1730 1731 1732 1733 1734 1735 1736 1737 1738 1739 1740 1741 1742 1743 1744 1745 1746 1747 1748 1749 1750 1751 1752 1753 1754 1755 1756 1757 1758 1759 1760 1761 1762 1763 1764 1765 1766 1767 1768 1769 1770 1771 1772 1773 1774 1775 1776 1777 1778 1779 1780 1781 1782 1783 1784 1785 1786 1787 1788 1789 1790 1791 1792 1793 1794 1795 1796 1797 1798 1799 1800 1801 1802 1803 1804 1805 1806 1807 1808 1809 1810 1811 1812 1813 1814 1815 1816 1817 1818 1819 1820 1821 1822 1823 1824 1825 1826 1827 1828 1829 1830 1831 1832 1833 1834 1835 1836 1837 1838 1839 1840 1841 1842 1843 1844 1845 1846 1847 1848 1849 1850 1851 1852 1853 1854 1855 1856 1857 1858 1859 1860 1861 1862 1863 1864 1865 1866 1867 1868 1869 1870 1871 1872 1873 1874 1875 1876 1877 1878 1879 1880 1881 1882 1883 1884 1885 1886 1887 1888 1889 1890 1891 1892 1893 1894 1895 1896 1897 1898 1899 1900 1901 1902 1903 1904 1905 1906 1907 1908 1909 1910 1911 1912 1913 1914 1915 1916 1917 1918 1919 1920 1921 1922 1923 1924 1925 1926 1927 1928 1929 1930 1931 1932 1933 1934 1935 1936 1937 1938 1939 1940 1941 1942 1943 1944 1945 1946 1947 1948 1949 1950 1951 1952 1953 1954 1955 1956 1957 1958 1959 1960 1961 1962 1963 1964 1965 1966 1967 1968 1969 1970 1971 1972 1973 1974 1975 1976 1977 1978 1979 1980 1981 1982 1983 1984 1985 1986 1987 1988 1989 1990 1991 1992 1993 1994 1995 1996 1997 1998 1999 2000 2001 2002 2003 2004 2005 2006 2007 2008 2009 2010 2011 2012 2013 2014 2015 2016 2017 2018 2019 2020 2021 2022 2023 2024 2025 2026 2027 2028 2029 2030 2031 2032 2033 2034 2035 2036 2037 2038 2039 2040 2041 2042 2043 2044 2045 2046 2047 2048 2049 2050 2051 2052 2053 2054 2055 2056 2057 2058 2059 2060 2061 2062 2063 2064 2065 2066 2067 2068 2069 2070 2071 2072 2073 2074 2075 2076 2077 2078 2079 2080 2081 2082 2083 2084 2085 2086 2087 2088 2089 2090 2091 2092 2093 2094 2095 2096 2097 2098 2099 2100 2101 2102 2103 2104 2105 2106 2107 2108 2109 2110 2111 2112 2113 2114 2115 2116 2117 2118 2119 2120 2121 2122 2123 2124 2125 2126 2127 2128 2129 2130 2131 2132 2133 2134 2135 2136 2137 2138 2139 2140 2141 2142 2143 2144 2145 2146 2147 2148 2149 2150 2151 2152 2153 2154 2155 2156 2157 2158 2159 2160 2161 2162 2163 2164 2165 2166 2167 2168 2169 2170 2171 2172 2173 2174 2175 2176 2177 2178 2179 2180 2181 2182 2183 2184 2185 2186 2187 2188 2189 2190 2191 2192 2193 2194 2195 2196 2197 2198 2199 2200 2201 2202 2203 2204 2205 2206 2207 2208 2209 2210 2211 2212 2213 2214 2215 2216 2217 2218 2219 2220 2221 2222 2223 2224 2225 2226 2227 2228 2229 2230 2231 2232 2233 2234 2235 2236 2237 2238 2239 2240 2241 2242 2243 2244 2245 2246 2247 2248 2249 2250 2251 2252 2253 2254 2255 2256 2257 2258 2259 2260 2261 2262 2263 2264 2265 2266 2267 2268 2269 2270 2271 2272 2273 2274 2275 2276 2277 2278 2279 2280 2281 2282 2283 2284 2285 2286 2287 2288 2289 2290 2291 2292 2293 2294 2295 2296 2297 2298 2299 2300 2301 2302 2303 2304 2305 2306 2307 2308 2309 2310 2311 2312 2313 2314 2315 2316 2317 2318 2319 2320 2321 2322 2323 2324 2325 2326 2327 2328 2329 2330 2331 2332 2333 2334 2335 2336 2337 2338 2339 2340 2341 2342 2343 2344 2345 2346 2347 2348 2349 2350 2351 2352 2353 2354 2355 2356 2357 2358 2359 2360 2361 2362 2363 2364 2365 2366 2367 2368 2369 2370 2371 2372 2373 2374 2375 2376 2377 2378 2379 2380 2381 2382 2383 2384 2385 2386 2387 2388 2389 2390 2391 2392 2393 2394 2395 2396 2397 2398 2399 2400 2401 2402 2403 2404 2405 2406 2407 2408 2409 2410 2411 2412 2413 2414 2415 2416 2417 2418 2419 2420 2421 2422 2423 2424 2425 2426 2427 2428 2429 2430 2431 2432 2433 2434 2435 2436 2437 2438 2439 2440 2441 2442 2443 2444 2445 2446 2447 2448 2449 2450 2451 2452 2453 2454 2455 2456 2457 2458 2459 2460 2461 2462 2463 2464 2465 2466 2467 2468 2469 2470 2471 2472 2473 2474 2475 2476 2477 2478 2479 2480 2481 2482 2483 2484 2485 2486 2487 2488 2489 2490 2491 2492 2493 2494 2495 2496 2497 2498 2499 2500 2501 2502 2503 2504 2505 2506 2507 2508 2509 2510 2511 2512 2513 2514 2515 2516 2517 2518 2519 2520 2521 2522 2523 2524 2525 2526 2527 2528 2529 2530 2531 2532 2533 2534 2535 2536 2537 2538 2539 2540 2541 2542 2543 2544 2545 2546 2547 2548 2549 2550 2551 2552 2553 2554 2555 2556 2557 2558 2559 2560 2561 2562 2563 2564 2565 2566 2567 2568 2569 2570 2571 2572 2573 2574 2575 2576 2577 2578 2579 2580 2581 2582 2583 2584 2585 2586 2587 2588 2589 2590 2591 2592 2593 2594 2595 2596 2597 2598 2599 2600 2601 2602 2603 2604 2605 2606 2607 2608 2609 2610 2611 2612 2613 2614 2615 2616 2617 2618 2619 2620 2621 2622 2623 2624 2625 2626 2627 2628 2629 2630 2631 2632 2633 2634 2635 2636 2637 2638 2639 2640 2641 2642 2643 2644 2645 2646 2647 2648 2649 2650 2651 2652 2653 2654 2655 2656 2657 2658 2659 2660 2661 2662 2663 2664 2665 2666 2667 2668 2669 2670 2671 2672 2673 2674 2675 2676 2677 2678 2679 2680 2681 2682 2683 2684 2685 2686 2687 2688 2689 2690 2691 2692 2693 2694 2695 2696 2697 2698 2699 2700 2701 2702 2703 2704 2705 2706 2707 2708 2709 2710 2711 2712 2713 2714 2715 2716 2717 2718 2719 2720 2721 2722 2723 2724 2725 2726 2727 2728 2729 2730 2731 2732 2733 2734 2735 2736 2737 2738 2739 2740 2741 2742 2743 2744 2745 2746 2747 2748 2749 2750 2751 2752 2753 2754 2755 2756 2757 2758 2759 2760 2761 2762 2763 2764 2765 2766 2767 2768 2769 2770 2771 2772 2773 2774 2775 2776 2777 2778 2779 2780 2781 2782 2783 2784 2785 2786 2787 2788 2789 2790 2791 2792 2793 2794 2795 2796 2797 2798 2799 2800 2801 2802 2803 2804 2805 2806 2807 2808 2809 2810 2811 2812 2813 2814 2815 2816 2817 2818 2819 2820 2821 2822 2823 2824 2825 2826 2827 2828 2829 2830 2831 2832 2833 2834 2835 2836 2837 2838 2839 2840 2841 2842 2843 2844 2845 2846 2847 2848 2849 2850 2851 2852 2853 2854 2855 2856 2857 2858 2859 2860 2861 2862 2863 2864 2865 2866 2867 2868 2869 2870 2871 2872 2873 2874 2875 2876 2877 2878 2879 2880 2881 2882 2883 2884 2885 2886 2887 2888 2889 2890 2891 2892 2893 2894 2895 2896 2897 2898 2899 2900 2901 2902 2903 2904 2905 2906 2907 2908 2909 2910 2911 2912 2913 2914 2915 2916 2917 2918 2919 2920 2921 2922 2923 2924 2925 2926 2927 2928 2929 2930 2931 2932 2933 2934 2935 2936 2937 2938 2939 2940 2941 2942 2943 2944 2945 2946 2947 2948 2949 2950 2951 2952 2953 2954 2955 2956 2957 2958 2959 2960 2961 2962 2963 2964 2965 2966 2967 2968 2969 2970 2971 2972 2973 2974 2975 2976 2977 2978 2979 2980 2981 2982 2983 2984 2985 2986 2987 2988 2989 2990 2991 2992 2993 2994 2995 2996 2997 2998 2999 3000 3001 3002 3003 3004 3005 3006 3007 3008 3009 3010 3011 3012 3013 3014 3015 3016 3017 3018 3019 3020 3021 3022 3023 3024 3025 3026 3027 3028 3029 3030 3031 3032 3033 3034 3035 3036 3037 3038 3039 3040 3041 3042 3043 3044 3045 3046 3047 3048 3049 3050 3051 3052 3053 3054 3055 3056 3057 3058 3059 3060 3061 3062 3063 3064 3065 3066 3067 3068 3069 3070 3071 3072 3073 3074 3075 3076 3077 3078 3079 3080 3081 3082 3083 3084 3085 3086 3087 3088 3089 3090 3091 3092 3093 3094 3095 3096 3097 3098 3099 3100 3101 3102 3103 3104 3105 3106 3107 3108 3109 3110 3111 3112 3113 3114 3115 3116 3117 3118 3119 3120 3121 3122 3123 3124 3125 3126 3127 3128 3129 3130 3131 3132 3133 3134 3135 3136 3137 3138 3139 3140 3141 3142 3143 3144 3145 3146 3147 3148 3149 3150 3151 3152 3153 3154 3155 3156 3157 3158 3159 3160 3161 3162 3163 3164 3165 3166 3167 3168 3169 3170 3171 3172 3173 3174 3175 3176 3177 3178 3179 3180 3181 3182 3183 3184 3185 3186 3187 3188 3189 3190 3191 3192 3193 3194 3195 3196 3197 3198 3199 3200 3201 3202 3203 3204 3205 3206 3207 3208 3209 3210 3211 3212 3213 3214 3215 3216 3217 3218 3219 3220 3221 3222 3223 3224 3225 3226 3227 3228 3229 3230 3231 3232 3233 3234 3235 3236 3237 3238 3239 3240 3241 3242 3243 3244 3245 3246 3247 3248 3249 3250 3251 3252 3253 3254 3255 3256 3257 3258 3259 3260 3261 3262 3263 3264 3265 3266 3267 3268 3269 3270 3271 3272 3273 3274 3275 3276 3277 3278 3279 3280 3281 3282 3283 3284 3285 3286 3287 3288 3289 3290 3291 3292 3293 3294 3295 3296 3297 3298 3299 3300 3301 3302 3303 3304 3305 3306 3307 3308 3309 3310 3311 3312 3313 3314 3315 3316 3317 3318 3319 3320 3321 3322 3323 3324 3325 3326 3327 3328 3329 3330 3331 3332 3333 3334 3335 3336 3337 3338 3339 3340 3341 3342 3343 3344 3345 3346 3347 3348 3349 3350 3351 3352 3353 3354 3355 3356 3357 3358 3359 3360 3361 3362 3363 3364 3365 3366 3367 3368 3369 3370 3371 3372 3373 3374 3375 3376 3377 3378 3379 3380 3381 3382 3383 3384 3385 3386 3387 3388 3389 3390 3391 3392 3393 3394 3395 3396 3397 3398 3399 3400 3401 3402 3403 3404 3405 3406 3407 | // SPDX-License-Identifier: GPL-2.0-only /* * mm/percpu.c - percpu memory allocator * * Copyright (C) 2009 SUSE Linux Products GmbH * Copyright (C) 2009 Tejun Heo <tj@kernel.org> * * Copyright (C) 2017 Facebook Inc. * Copyright (C) 2017 Dennis Zhou <dennis@kernel.org> * * The percpu allocator handles both static and dynamic areas. Percpu * areas are allocated in chunks which are divided into units. There is * a 1-to-1 mapping for units to possible cpus. These units are grouped * based on NUMA properties of the machine. * * c0 c1 c2 * ------------------- ------------------- ------------ * | u0 | u1 | u2 | u3 | | u0 | u1 | u2 | u3 | | u0 | u1 | u * ------------------- ...... ------------------- .... ------------ * * Allocation is done by offsets into a unit's address space. Ie., an * area of 512 bytes at 6k in c1 occupies 512 bytes at 6k in c1:u0, * c1:u1, c1:u2, etc. On NUMA machines, the mapping may be non-linear * and even sparse. Access is handled by configuring percpu base * registers according to the cpu to unit mappings and offsetting the * base address using pcpu_unit_size. * * There is special consideration for the first chunk which must handle * the static percpu variables in the kernel image as allocation services * are not online yet. In short, the first chunk is structured like so: * * <Static | [Reserved] | Dynamic> * * The static data is copied from the original section managed by the * linker. The reserved section, if non-zero, primarily manages static * percpu variables from kernel modules. Finally, the dynamic section * takes care of normal allocations. * * The allocator organizes chunks into lists according to free size and * memcg-awareness. To make a percpu allocation memcg-aware the __GFP_ACCOUNT * flag should be passed. All memcg-aware allocations are sharing one set * of chunks and all unaccounted allocations and allocations performed * by processes belonging to the root memory cgroup are using the second set. * * The allocator tries to allocate from the fullest chunk first. Each chunk * is managed by a bitmap with metadata blocks. The allocation map is updated * on every allocation and free to reflect the current state while the boundary * map is only updated on allocation. Each metadata block contains * information to help mitigate the need to iterate over large portions * of the bitmap. The reverse mapping from page to chunk is stored in * the page's index. Lastly, units are lazily backed and grow in unison. * * There is a unique conversion that goes on here between bytes and bits. * Each bit represents a fragment of size PCPU_MIN_ALLOC_SIZE. The chunk * tracks the number of pages it is responsible for in nr_pages. Helper * functions are used to convert from between the bytes, bits, and blocks. * All hints are managed in bits unless explicitly stated. * * To use this allocator, arch code should do the following: * * - define __addr_to_pcpu_ptr() and __pcpu_ptr_to_addr() to translate * regular address to percpu pointer and back if they need to be * different from the default * * - use pcpu_setup_first_chunk() during percpu area initialization to * setup the first chunk containing the kernel static percpu area */ #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt #include <linux/bitmap.h> #include <linux/cpumask.h> #include <linux/memblock.h> #include <linux/err.h> #include <linux/list.h> #include <linux/log2.h> #include <linux/mm.h> #include <linux/module.h> #include <linux/mutex.h> #include <linux/percpu.h> #include <linux/pfn.h> #include <linux/slab.h> #include <linux/spinlock.h> #include <linux/vmalloc.h> #include <linux/workqueue.h> #include <linux/kmemleak.h> #include <linux/sched.h> #include <linux/sched/mm.h> #include <linux/memcontrol.h> #include <asm/cacheflush.h> #include <asm/sections.h> #include <asm/tlbflush.h> #include <asm/io.h> #define CREATE_TRACE_POINTS #include <trace/events/percpu.h> #include "percpu-internal.h" /* * The slots are sorted by the size of the biggest continuous free area. * 1-31 bytes share the same slot. */ #define PCPU_SLOT_BASE_SHIFT 5 /* chunks in slots below this are subject to being sidelined on failed alloc */ #define PCPU_SLOT_FAIL_THRESHOLD 3 #define PCPU_EMPTY_POP_PAGES_LOW 2 #define PCPU_EMPTY_POP_PAGES_HIGH 4 #ifdef CONFIG_SMP /* default addr <-> pcpu_ptr mapping, override in asm/percpu.h if necessary */ #ifndef __addr_to_pcpu_ptr #define __addr_to_pcpu_ptr(addr) \ (void __percpu *)((unsigned long)(addr) - \ (unsigned long)pcpu_base_addr + \ (unsigned long)__per_cpu_start) #endif #ifndef __pcpu_ptr_to_addr #define __pcpu_ptr_to_addr(ptr) \ (void __force *)((unsigned long)(ptr) + \ (unsigned long)pcpu_base_addr - \ (unsigned long)__per_cpu_start) #endif #else /* CONFIG_SMP */ /* on UP, it's always identity mapped */ #define __addr_to_pcpu_ptr(addr) (void __percpu *)(addr) #define __pcpu_ptr_to_addr(ptr) (void __force *)(ptr) #endif /* CONFIG_SMP */ static int pcpu_unit_pages __ro_after_init; static int pcpu_unit_size __ro_after_init; static int pcpu_nr_units __ro_after_init; static int pcpu_atom_size __ro_after_init; int pcpu_nr_slots __ro_after_init; static int pcpu_free_slot __ro_after_init; int pcpu_sidelined_slot __ro_after_init; int pcpu_to_depopulate_slot __ro_after_init; static size_t pcpu_chunk_struct_size __ro_after_init; /* cpus with the lowest and highest unit addresses */ static unsigned int pcpu_low_unit_cpu __ro_after_init; static unsigned int pcpu_high_unit_cpu __ro_after_init; /* the address of the first chunk which starts with the kernel static area */ void *pcpu_base_addr __ro_after_init; static const int *pcpu_unit_map __ro_after_init; /* cpu -> unit */ const unsigned long *pcpu_unit_offsets __ro_after_init; /* cpu -> unit offset */ /* group information, used for vm allocation */ static int pcpu_nr_groups __ro_after_init; static const unsigned long *pcpu_group_offsets __ro_after_init; static const size_t *pcpu_group_sizes __ro_after_init; /* * The first chunk which always exists. Note that unlike other * chunks, this one can be allocated and mapped in several different * ways and thus often doesn't live in the vmalloc area. */ struct pcpu_chunk *pcpu_first_chunk __ro_after_init; /* * Optional reserved chunk. This chunk reserves part of the first * chunk and serves it for reserved allocations. When the reserved * region doesn't exist, the following variable is NULL. */ struct pcpu_chunk *pcpu_reserved_chunk __ro_after_init; DEFINE_SPINLOCK(pcpu_lock); /* all internal data structures */ static DEFINE_MUTEX(pcpu_alloc_mutex); /* chunk create/destroy, [de]pop, map ext */ struct list_head *pcpu_chunk_lists __ro_after_init; /* chunk list slots */ /* * The number of empty populated pages, protected by pcpu_lock. * The reserved chunk doesn't contribute to the count. */ int pcpu_nr_empty_pop_pages; /* * The number of populated pages in use by the allocator, protected by * pcpu_lock. This number is kept per a unit per chunk (i.e. when a page gets * allocated/deallocated, it is allocated/deallocated in all units of a chunk * and increments/decrements this count by 1). */ static unsigned long pcpu_nr_populated; /* * Balance work is used to populate or destroy chunks asynchronously. We * try to keep the number of populated free pages between * PCPU_EMPTY_POP_PAGES_LOW and HIGH for atomic allocations and at most one * empty chunk. */ static void pcpu_balance_workfn(struct work_struct *work); static DECLARE_WORK(pcpu_balance_work, pcpu_balance_workfn); static bool pcpu_async_enabled __read_mostly; static bool pcpu_atomic_alloc_failed; static void pcpu_schedule_balance_work(void) { if (pcpu_async_enabled) schedule_work(&pcpu_balance_work); } /** * pcpu_addr_in_chunk - check if the address is served from this chunk * @chunk: chunk of interest * @addr: percpu address * * RETURNS: * True if the address is served from this chunk. */ static bool pcpu_addr_in_chunk(struct pcpu_chunk *chunk, void *addr) { void *start_addr, *end_addr; if (!chunk) return false; start_addr = chunk->base_addr + chunk->start_offset; end_addr = chunk->base_addr + chunk->nr_pages * PAGE_SIZE - chunk->end_offset; return addr >= start_addr && addr < end_addr; } static int __pcpu_size_to_slot(int size) { int highbit = fls(size); /* size is in bytes */ return max(highbit - PCPU_SLOT_BASE_SHIFT + 2, 1); } static int pcpu_size_to_slot(int size) { if (size == pcpu_unit_size) return pcpu_free_slot; return __pcpu_size_to_slot(size); } static int pcpu_chunk_slot(const struct pcpu_chunk *chunk) { const struct pcpu_block_md *chunk_md = &chunk->chunk_md; if (chunk->free_bytes < PCPU_MIN_ALLOC_SIZE || chunk_md->contig_hint == 0) return 0; return pcpu_size_to_slot(chunk_md->contig_hint * PCPU_MIN_ALLOC_SIZE); } /* set the pointer to a chunk in a page struct */ static void pcpu_set_page_chunk(struct page *page, struct pcpu_chunk *pcpu) { page->private = (unsigned long)pcpu; } /* obtain pointer to a chunk from a page struct */ static struct pcpu_chunk *pcpu_get_page_chunk(struct page *page) { return (struct pcpu_chunk *)page->private; } static int __maybe_unused pcpu_page_idx(unsigned int cpu, int page_idx) { return pcpu_unit_map[cpu] * pcpu_unit_pages + page_idx; } static unsigned long pcpu_unit_page_offset(unsigned int cpu, int page_idx) { return pcpu_unit_offsets[cpu] + (page_idx << PAGE_SHIFT); } static unsigned long pcpu_chunk_addr(struct pcpu_chunk *chunk, unsigned int cpu, int page_idx) { return (unsigned long)chunk->base_addr + pcpu_unit_page_offset(cpu, page_idx); } /* * The following are helper functions to help access bitmaps and convert * between bitmap offsets to address offsets. */ static unsigned long *pcpu_index_alloc_map(struct pcpu_chunk *chunk, int index) { return chunk->alloc_map + (index * PCPU_BITMAP_BLOCK_BITS / BITS_PER_LONG); } static unsigned long pcpu_off_to_block_index(int off) { return off / PCPU_BITMAP_BLOCK_BITS; } static unsigned long pcpu_off_to_block_off(int off) { return off & (PCPU_BITMAP_BLOCK_BITS - 1); } static unsigned long pcpu_block_off_to_off(int index, int off) { return index * PCPU_BITMAP_BLOCK_BITS + off; } /** * pcpu_check_block_hint - check against the contig hint * @block: block of interest * @bits: size of allocation * @align: alignment of area (max PAGE_SIZE) * * Check to see if the allocation can fit in the block's contig hint. * Note, a chunk uses the same hints as a block so this can also check against * the chunk's contig hint. */ static bool pcpu_check_block_hint(struct pcpu_block_md *block, int bits, size_t align) { int bit_off = ALIGN(block->contig_hint_start, align) - block->contig_hint_start; return bit_off + bits <= block->contig_hint; } /* * pcpu_next_hint - determine which hint to use * @block: block of interest * @alloc_bits: size of allocation * * This determines if we should scan based on the scan_hint or first_free. * In general, we want to scan from first_free to fulfill allocations by * first fit. However, if we know a scan_hint at position scan_hint_start * cannot fulfill an allocation, we can begin scanning from there knowing * the contig_hint will be our fallback. */ static int pcpu_next_hint(struct pcpu_block_md *block, int alloc_bits) { /* * The three conditions below determine if we can skip past the * scan_hint. First, does the scan hint exist. Second, is the * contig_hint after the scan_hint (possibly not true iff * contig_hint == scan_hint). Third, is the allocation request * larger than the scan_hint. */ if (block->scan_hint && block->contig_hint_start > block->scan_hint_start && alloc_bits > block->scan_hint) return block->scan_hint_start + block->scan_hint; return block->first_free; } /** * pcpu_next_md_free_region - finds the next hint free area * @chunk: chunk of interest * @bit_off: chunk offset * @bits: size of free area * * Helper function for pcpu_for_each_md_free_region. It checks * block->contig_hint and performs aggregation across blocks to find the * next hint. It modifies bit_off and bits in-place to be consumed in the * loop. */ static void pcpu_next_md_free_region(struct pcpu_chunk *chunk, int *bit_off, int *bits) { int i = pcpu_off_to_block_index(*bit_off); int block_off = pcpu_off_to_block_off(*bit_off); struct pcpu_block_md *block; *bits = 0; for (block = chunk->md_blocks + i; i < pcpu_chunk_nr_blocks(chunk); block++, i++) { /* handles contig area across blocks */ if (*bits) { *bits += block->left_free; if (block->left_free == PCPU_BITMAP_BLOCK_BITS) continue; return; } /* * This checks three things. First is there a contig_hint to * check. Second, have we checked this hint before by * comparing the block_off. Third, is this the same as the * right contig hint. In the last case, it spills over into * the next block and should be handled by the contig area * across blocks code. */ *bits = block->contig_hint; if (*bits && block->contig_hint_start >= block_off && *bits + block->contig_hint_start < PCPU_BITMAP_BLOCK_BITS) { *bit_off = pcpu_block_off_to_off(i, block->contig_hint_start); return; } /* reset to satisfy the second predicate above */ block_off = 0; *bits = block->right_free; *bit_off = (i + 1) * PCPU_BITMAP_BLOCK_BITS - block->right_free; } } /** * pcpu_next_fit_region - finds fit areas for a given allocation request * @chunk: chunk of interest * @alloc_bits: size of allocation * @align: alignment of area (max PAGE_SIZE) * @bit_off: chunk offset * @bits: size of free area * * Finds the next free region that is viable for use with a given size and * alignment. This only returns if there is a valid area to be used for this * allocation. block->first_free is returned if the allocation request fits * within the block to see if the request can be fulfilled prior to the contig * hint. */ static void pcpu_next_fit_region(struct pcpu_chunk *chunk, int alloc_bits, int align, int *bit_off, int *bits) { int i = pcpu_off_to_block_index(*bit_off); int block_off = pcpu_off_to_block_off(*bit_off); struct pcpu_block_md *block; *bits = 0; for (block = chunk->md_blocks + i; i < pcpu_chunk_nr_blocks(chunk); block++, i++) { /* handles contig area across blocks */ if (*bits) { *bits += block->left_free; if (*bits >= alloc_bits) return; if (block->left_free == PCPU_BITMAP_BLOCK_BITS) continue; } /* check block->contig_hint */ *bits = ALIGN(block->contig_hint_start, align) - block->contig_hint_start; /* * This uses the block offset to determine if this has been * checked in the prior iteration. */ if (block->contig_hint && block->contig_hint_start >= block_off && block->contig_hint >= *bits + alloc_bits) { int start = pcpu_next_hint(block, alloc_bits); *bits += alloc_bits + block->contig_hint_start - start; *bit_off = pcpu_block_off_to_off(i, start); return; } /* reset to satisfy the second predicate above */ block_off = 0; *bit_off = ALIGN(PCPU_BITMAP_BLOCK_BITS - block->right_free, align); *bits = PCPU_BITMAP_BLOCK_BITS - *bit_off; *bit_off = pcpu_block_off_to_off(i, *bit_off); if (*bits >= alloc_bits) return; } /* no valid offsets were found - fail condition */ *bit_off = pcpu_chunk_map_bits(chunk); } /* * Metadata free area iterators. These perform aggregation of free areas * based on the metadata blocks and return the offset @bit_off and size in * bits of the free area @bits. pcpu_for_each_fit_region only returns when * a fit is found for the allocation request. */ #define pcpu_for_each_md_free_region(chunk, bit_off, bits) \ for (pcpu_next_md_free_region((chunk), &(bit_off), &(bits)); \ (bit_off) < pcpu_chunk_map_bits((chunk)); \ (bit_off) += (bits) + 1, \ pcpu_next_md_free_region((chunk), &(bit_off), &(bits))) #define pcpu_for_each_fit_region(chunk, alloc_bits, align, bit_off, bits) \ for (pcpu_next_fit_region((chunk), (alloc_bits), (align), &(bit_off), \ &(bits)); \ (bit_off) < pcpu_chunk_map_bits((chunk)); \ (bit_off) += (bits), \ pcpu_next_fit_region((chunk), (alloc_bits), (align), &(bit_off), \ &(bits))) /** * pcpu_mem_zalloc - allocate memory * @size: bytes to allocate * @gfp: allocation flags * * Allocate @size bytes. If @size is smaller than PAGE_SIZE, * kzalloc() is used; otherwise, the equivalent of vzalloc() is used. * This is to facilitate passing through whitelisted flags. The * returned memory is always zeroed. * * RETURNS: * Pointer to the allocated area on success, NULL on failure. */ static void *pcpu_mem_zalloc(size_t size, gfp_t gfp) { if (WARN_ON_ONCE(!slab_is_available())) return NULL; if (size <= PAGE_SIZE) return kzalloc(size, gfp); else return __vmalloc(size, gfp | __GFP_ZERO); } /** * pcpu_mem_free - free memory * @ptr: memory to free * * Free @ptr. @ptr should have been allocated using pcpu_mem_zalloc(). */ static void pcpu_mem_free(void *ptr) { kvfree(ptr); } static void __pcpu_chunk_move(struct pcpu_chunk *chunk, int slot, bool move_front) { if (chunk != pcpu_reserved_chunk) { if (move_front) list_move(&chunk->list, &pcpu_chunk_lists[slot]); else list_move_tail(&chunk->list, &pcpu_chunk_lists[slot]); } } static void pcpu_chunk_move(struct pcpu_chunk *chunk, int slot) { __pcpu_chunk_move(chunk, slot, true); } /** * pcpu_chunk_relocate - put chunk in the appropriate chunk slot * @chunk: chunk of interest * @oslot: the previous slot it was on * * This function is called after an allocation or free changed @chunk. * New slot according to the changed state is determined and @chunk is * moved to the slot. Note that the reserved chunk is never put on * chunk slots. * * CONTEXT: * pcpu_lock. */ static void pcpu_chunk_relocate(struct pcpu_chunk *chunk, int oslot) { int nslot = pcpu_chunk_slot(chunk); /* leave isolated chunks in-place */ if (chunk->isolated) return; if (oslot != nslot) __pcpu_chunk_move(chunk, nslot, oslot < nslot); } static void pcpu_isolate_chunk(struct pcpu_chunk *chunk) { lockdep_assert_held(&pcpu_lock); if (!chunk->isolated) { chunk->isolated = true; pcpu_nr_empty_pop_pages -= chunk->nr_empty_pop_pages; } list_move(&chunk->list, &pcpu_chunk_lists[pcpu_to_depopulate_slot]); } static void pcpu_reintegrate_chunk(struct pcpu_chunk *chunk) { lockdep_assert_held(&pcpu_lock); if (chunk->isolated) { chunk->isolated = false; pcpu_nr_empty_pop_pages += chunk->nr_empty_pop_pages; pcpu_chunk_relocate(chunk, -1); } } /* * pcpu_update_empty_pages - update empty page counters * @chunk: chunk of interest * @nr: nr of empty pages * * This is used to keep track of the empty pages now based on the premise * a md_block covers a page. The hint update functions recognize if a block * is made full or broken to calculate deltas for keeping track of free pages. */ static inline void pcpu_update_empty_pages(struct pcpu_chunk *chunk, int nr) { chunk->nr_empty_pop_pages += nr; if (chunk != pcpu_reserved_chunk && !chunk->isolated) pcpu_nr_empty_pop_pages += nr; } /* * pcpu_region_overlap - determines if two regions overlap * @a: start of first region, inclusive * @b: end of first region, exclusive * @x: start of second region, inclusive * @y: end of second region, exclusive * * This is used to determine if the hint region [a, b) overlaps with the * allocated region [x, y). */ static inline bool pcpu_region_overlap(int a, int b, int x, int y) { return (a < y) && (x < b); } /** * pcpu_block_update - updates a block given a free area * @block: block of interest * @start: start offset in block * @end: end offset in block * * Updates a block given a known free area. The region [start, end) is * expected to be the entirety of the free area within a block. Chooses * the best starting offset if the contig hints are equal. */ static void pcpu_block_update(struct pcpu_block_md *block, int start, int end) { int contig = end - start; block->first_free = min(block->first_free, start); if (start == 0) block->left_free = contig; if (end == block->nr_bits) block->right_free = contig; if (contig > block->contig_hint) { /* promote the old contig_hint to be the new scan_hint */ if (start > block->contig_hint_start) { if (block->contig_hint > block->scan_hint) { block->scan_hint_start = block->contig_hint_start; block->scan_hint = block->contig_hint; } else if (start < block->scan_hint_start) { /* * The old contig_hint == scan_hint. But, the * new contig is larger so hold the invariant * scan_hint_start < contig_hint_start. */ block->scan_hint = 0; } } else { block->scan_hint = 0; } block->contig_hint_start = start; block->contig_hint = contig; } else if (contig == block->contig_hint) { if (block->contig_hint_start && (!start || __ffs(start) > __ffs(block->contig_hint_start))) { /* start has a better alignment so use it */ block->contig_hint_start = start; if (start < block->scan_hint_start && block->contig_hint > block->scan_hint) block->scan_hint = 0; } else if (start > block->scan_hint_start || block->contig_hint > block->scan_hint) { /* * Knowing contig == contig_hint, update the scan_hint * if it is farther than or larger than the current * scan_hint. */ block->scan_hint_start = start; block->scan_hint = contig; } } else { /* * The region is smaller than the contig_hint. So only update * the scan_hint if it is larger than or equal and farther than * the current scan_hint. */ if ((start < block->contig_hint_start && (contig > block->scan_hint || (contig == block->scan_hint && start > block->scan_hint_start)))) { block->scan_hint_start = start; block->scan_hint = contig; } } } /* * pcpu_block_update_scan - update a block given a free area from a scan * @chunk: chunk of interest * @bit_off: chunk offset * @bits: size of free area * * Finding the final allocation spot first goes through pcpu_find_block_fit() * to find a block that can hold the allocation and then pcpu_alloc_area() * where a scan is used. When allocations require specific alignments, * we can inadvertently create holes which will not be seen in the alloc * or free paths. * * This takes a given free area hole and updates a block as it may change the * scan_hint. We need to scan backwards to ensure we don't miss free bits * from alignment. */ static void pcpu_block_update_scan(struct pcpu_chunk *chunk, int bit_off, int bits) { int s_off = pcpu_off_to_block_off(bit_off); int e_off = s_off + bits; int s_index, l_bit; struct pcpu_block_md *block; if (e_off > PCPU_BITMAP_BLOCK_BITS) return; s_index = pcpu_off_to_block_index(bit_off); block = chunk->md_blocks + s_index; /* scan backwards in case of alignment skipping free bits */ l_bit = find_last_bit(pcpu_index_alloc_map(chunk, s_index), s_off); s_off = (s_off == l_bit) ? 0 : l_bit + 1; pcpu_block_update(block, s_off, e_off); } /** * pcpu_chunk_refresh_hint - updates metadata about a chunk * @chunk: chunk of interest * @full_scan: if we should scan from the beginning * * Iterates over the metadata blocks to find the largest contig area. * A full scan can be avoided on the allocation path as this is triggered * if we broke the contig_hint. In doing so, the scan_hint will be before * the contig_hint or after if the scan_hint == contig_hint. This cannot * be prevented on freeing as we want to find the largest area possibly * spanning blocks. */ static void pcpu_chunk_refresh_hint(struct pcpu_chunk *chunk, bool full_scan) { struct pcpu_block_md *chunk_md = &chunk->chunk_md; int bit_off, bits; /* promote scan_hint to contig_hint */ if (!full_scan && chunk_md->scan_hint) { bit_off = chunk_md->scan_hint_start + chunk_md->scan_hint; chunk_md->contig_hint_start = chunk_md->scan_hint_start; chunk_md->contig_hint = chunk_md->scan_hint; chunk_md->scan_hint = 0; } else { bit_off = chunk_md->first_free; chunk_md->contig_hint = 0; } bits = 0; pcpu_for_each_md_free_region(chunk, bit_off, bits) pcpu_block_update(chunk_md, bit_off, bit_off + bits); } /** * pcpu_block_refresh_hint * @chunk: chunk of interest * @index: index of the metadata block * * Scans over the block beginning at first_free and updates the block * metadata accordingly. */ static void pcpu_block_refresh_hint(struct pcpu_chunk *chunk, int index) { struct pcpu_block_md *block = chunk->md_blocks + index; unsigned long *alloc_map = pcpu_index_alloc_map(chunk, index); unsigned int start, end; /* region start, region end */ /* promote scan_hint to contig_hint */ if (block->scan_hint) { start = block->scan_hint_start + block->scan_hint; block->contig_hint_start = block->scan_hint_start; block->contig_hint = block->scan_hint; block->scan_hint = 0; } else { start = block->first_free; block->contig_hint = 0; } block->right_free = 0; /* iterate over free areas and update the contig hints */ for_each_clear_bitrange_from(start, end, alloc_map, PCPU_BITMAP_BLOCK_BITS) pcpu_block_update(block, start, end); } /** * pcpu_block_update_hint_alloc - update hint on allocation path * @chunk: chunk of interest * @bit_off: chunk offset * @bits: size of request * * Updates metadata for the allocation path. The metadata only has to be * refreshed by a full scan iff the chunk's contig hint is broken. Block level * scans are required if the block's contig hint is broken. */ static void pcpu_block_update_hint_alloc(struct pcpu_chunk *chunk, int bit_off, int bits) { struct pcpu_block_md *chunk_md = &chunk->chunk_md; int nr_empty_pages = 0; struct pcpu_block_md *s_block, *e_block, *block; int s_index, e_index; /* block indexes of the freed allocation */ int s_off, e_off; /* block offsets of the freed allocation */ /* * Calculate per block offsets. * The calculation uses an inclusive range, but the resulting offsets * are [start, end). e_index always points to the last block in the * range. */ s_index = pcpu_off_to_block_index(bit_off); e_index = pcpu_off_to_block_index(bit_off + bits - 1); s_off = pcpu_off_to_block_off(bit_off); e_off = pcpu_off_to_block_off(bit_off + bits - 1) + 1; s_block = chunk->md_blocks + s_index; e_block = chunk->md_blocks + e_index; /* * Update s_block. */ if (s_block->contig_hint == PCPU_BITMAP_BLOCK_BITS) nr_empty_pages++; /* * block->first_free must be updated if the allocation takes its place. * If the allocation breaks the contig_hint, a scan is required to * restore this hint. */ if (s_off == s_block->first_free) s_block->first_free = find_next_zero_bit( pcpu_index_alloc_map(chunk, s_index), PCPU_BITMAP_BLOCK_BITS, s_off + bits); if (pcpu_region_overlap(s_block->scan_hint_start, s_block->scan_hint_start + s_block->scan_hint, s_off, s_off + bits)) s_block->scan_hint = 0; if (pcpu_region_overlap(s_block->contig_hint_start, s_block->contig_hint_start + s_block->contig_hint, s_off, s_off + bits)) { /* block contig hint is broken - scan to fix it */ if (!s_off) s_block->left_free = 0; pcpu_block_refresh_hint(chunk, s_index); } else { /* update left and right contig manually */ s_block->left_free = min(s_block->left_free, s_off); if (s_index == e_index) s_block->right_free = min_t(int, s_block->right_free, PCPU_BITMAP_BLOCK_BITS - e_off); else s_block->right_free = 0; } /* * Update e_block. */ if (s_index != e_index) { if (e_block->contig_hint == PCPU_BITMAP_BLOCK_BITS) nr_empty_pages++; /* * When the allocation is across blocks, the end is along * the left part of the e_block. */ e_block->first_free = find_next_zero_bit( pcpu_index_alloc_map(chunk, e_index), PCPU_BITMAP_BLOCK_BITS, e_off); if (e_off == PCPU_BITMAP_BLOCK_BITS) { /* reset the block */ e_block++; } else { if (e_off > e_block->scan_hint_start) e_block->scan_hint = 0; e_block->left_free = 0; if (e_off > e_block->contig_hint_start) { /* contig hint is broken - scan to fix it */ pcpu_block_refresh_hint(chunk, e_index); } else { e_block->right_free = min_t(int, e_block->right_free, PCPU_BITMAP_BLOCK_BITS - e_off); } } /* update in-between md_blocks */ nr_empty_pages += (e_index - s_index - 1); for (block = s_block + 1; block < e_block; block++) { block->scan_hint = 0; block->contig_hint = 0; block->left_free = 0; block->right_free = 0; } } /* * If the allocation is not atomic, some blocks may not be * populated with pages, while we account it here. The number * of pages will be added back with pcpu_chunk_populated() * when populating pages. */ if (nr_empty_pages) pcpu_update_empty_pages(chunk, -nr_empty_pages); if (pcpu_region_overlap(chunk_md->scan_hint_start, chunk_md->scan_hint_start + chunk_md->scan_hint, bit_off, bit_off + bits)) chunk_md->scan_hint = 0; /* * The only time a full chunk scan is required is if the chunk * contig hint is broken. Otherwise, it means a smaller space * was used and therefore the chunk contig hint is still correct. */ if (pcpu_region_overlap(chunk_md->contig_hint_start, chunk_md->contig_hint_start + chunk_md->contig_hint, bit_off, bit_off + bits)) pcpu_chunk_refresh_hint(chunk, false); } /** * pcpu_block_update_hint_free - updates the block hints on the free path * @chunk: chunk of interest * @bit_off: chunk offset * @bits: size of request * * Updates metadata for the allocation path. This avoids a blind block * refresh by making use of the block contig hints. If this fails, it scans * forward and backward to determine the extent of the free area. This is * capped at the boundary of blocks. * * A chunk update is triggered if a page becomes free, a block becomes free, * or the free spans across blocks. This tradeoff is to minimize iterating * over the block metadata to update chunk_md->contig_hint. * chunk_md->contig_hint may be off by up to a page, but it will never be more * than the available space. If the contig hint is contained in one block, it * will be accurate. */ static void pcpu_block_update_hint_free(struct pcpu_chunk *chunk, int bit_off, int bits) { int nr_empty_pages = 0; struct pcpu_block_md *s_block, *e_block, *block; int s_index, e_index; /* block indexes of the freed allocation */ int s_off, e_off; /* block offsets of the freed allocation */ int start, end; /* start and end of the whole free area */ /* * Calculate per block offsets. * The calculation uses an inclusive range, but the resulting offsets * are [start, end). e_index always points to the last block in the * range. */ s_index = pcpu_off_to_block_index(bit_off); e_index = pcpu_off_to_block_index(bit_off + bits - 1); s_off = pcpu_off_to_block_off(bit_off); e_off = pcpu_off_to_block_off(bit_off + bits - 1) + 1; s_block = chunk->md_blocks + s_index; e_block = chunk->md_blocks + e_index; /* * Check if the freed area aligns with the block->contig_hint. * If it does, then the scan to find the beginning/end of the * larger free area can be avoided. * * start and end refer to beginning and end of the free area * within each their respective blocks. This is not necessarily * the entire free area as it may span blocks past the beginning * or end of the block. */ start = s_off; if (s_off == s_block->contig_hint + s_block->contig_hint_start) { start = s_block->contig_hint_start; } else { /* * Scan backwards to find the extent of the free area. * find_last_bit returns the starting bit, so if the start bit * is returned, that means there was no last bit and the * remainder of the chunk is free. */ int l_bit = find_last_bit(pcpu_index_alloc_map(chunk, s_index), start); start = (start == l_bit) ? 0 : l_bit + 1; } end = e_off; if (e_off == e_block->contig_hint_start) end = e_block->contig_hint_start + e_block->contig_hint; else end = find_next_bit(pcpu_index_alloc_map(chunk, e_index), PCPU_BITMAP_BLOCK_BITS, end); /* update s_block */ e_off = (s_index == e_index) ? end : PCPU_BITMAP_BLOCK_BITS; if (!start && e_off == PCPU_BITMAP_BLOCK_BITS) nr_empty_pages++; pcpu_block_update(s_block, start, e_off); /* freeing in the same block */ if (s_index != e_index) { /* update e_block */ if (end == PCPU_BITMAP_BLOCK_BITS) nr_empty_pages++; pcpu_block_update(e_block, 0, end); /* reset md_blocks in the middle */ nr_empty_pages += (e_index - s_index - 1); for (block = s_block + 1; block < e_block; block++) { block->first_free = 0; block->scan_hint = 0; block->contig_hint_start = 0; block->contig_hint = PCPU_BITMAP_BLOCK_BITS; block->left_free = PCPU_BITMAP_BLOCK_BITS; block->right_free = PCPU_BITMAP_BLOCK_BITS; } } if (nr_empty_pages) pcpu_update_empty_pages(chunk, nr_empty_pages); /* * Refresh chunk metadata when the free makes a block free or spans * across blocks. The contig_hint may be off by up to a page, but if * the contig_hint is contained in a block, it will be accurate with * the else condition below. */ if (((end - start) >= PCPU_BITMAP_BLOCK_BITS) || s_index != e_index) pcpu_chunk_refresh_hint(chunk, true); else pcpu_block_update(&chunk->chunk_md, pcpu_block_off_to_off(s_index, start), end); } /** * pcpu_is_populated - determines if the region is populated * @chunk: chunk of interest * @bit_off: chunk offset * @bits: size of area * @next_off: return value for the next offset to start searching * * For atomic allocations, check if the backing pages are populated. * * RETURNS: * Bool if the backing pages are populated. * next_index is to skip over unpopulated blocks in pcpu_find_block_fit. */ static bool pcpu_is_populated(struct pcpu_chunk *chunk, int bit_off, int bits, int *next_off) { unsigned int start, end; start = PFN_DOWN(bit_off * PCPU_MIN_ALLOC_SIZE); end = PFN_UP((bit_off + bits) * PCPU_MIN_ALLOC_SIZE); start = find_next_zero_bit(chunk->populated, end, start); if (start >= end) return true; end = find_next_bit(chunk->populated, end, start + 1); *next_off = end * PAGE_SIZE / PCPU_MIN_ALLOC_SIZE; return false; } /** * pcpu_find_block_fit - finds the block index to start searching * @chunk: chunk of interest * @alloc_bits: size of request in allocation units * @align: alignment of area (max PAGE_SIZE bytes) * @pop_only: use populated regions only * * Given a chunk and an allocation spec, find the offset to begin searching * for a free region. This iterates over the bitmap metadata blocks to * find an offset that will be guaranteed to fit the requirements. It is * not quite first fit as if the allocation does not fit in the contig hint * of a block or chunk, it is skipped. This errs on the side of caution * to prevent excess iteration. Poor alignment can cause the allocator to * skip over blocks and chunks that have valid free areas. * * RETURNS: * The offset in the bitmap to begin searching. * -1 if no offset is found. */ static int pcpu_find_block_fit(struct pcpu_chunk *chunk, int alloc_bits, size_t align, bool pop_only) { struct pcpu_block_md *chunk_md = &chunk->chunk_md; int bit_off, bits, next_off; /* * This is an optimization to prevent scanning by assuming if the * allocation cannot fit in the global hint, there is memory pressure * and creating a new chunk would happen soon. */ if (!pcpu_check_block_hint(chunk_md, alloc_bits, align)) return -1; bit_off = pcpu_next_hint(chunk_md, alloc_bits); bits = 0; pcpu_for_each_fit_region(chunk, alloc_bits, align, bit_off, bits) { if (!pop_only || pcpu_is_populated(chunk, bit_off, bits, &next_off)) break; bit_off = next_off; bits = 0; } if (bit_off == pcpu_chunk_map_bits(chunk)) return -1; return bit_off; } /* * pcpu_find_zero_area - modified from bitmap_find_next_zero_area_off() * @map: the address to base the search on * @size: the bitmap size in bits * @start: the bitnumber to start searching at * @nr: the number of zeroed bits we're looking for * @align_mask: alignment mask for zero area * @largest_off: offset of the largest area skipped * @largest_bits: size of the largest area skipped * * The @align_mask should be one less than a power of 2. * * This is a modified version of bitmap_find_next_zero_area_off() to remember * the largest area that was skipped. This is imperfect, but in general is * good enough. The largest remembered region is the largest failed region * seen. This does not include anything we possibly skipped due to alignment. * pcpu_block_update_scan() does scan backwards to try and recover what was * lost to alignment. While this can cause scanning to miss earlier possible * free areas, smaller allocations will eventually fill those holes. */ static unsigned long pcpu_find_zero_area(unsigned long *map, unsigned long size, unsigned long start, unsigned long nr, unsigned long align_mask, unsigned long *largest_off, unsigned long *largest_bits) { unsigned long index, end, i, area_off, area_bits; again: index = find_next_zero_bit(map, size, start); /* Align allocation */ index = __ALIGN_MASK(index, align_mask); area_off = index; end = index + nr; if (end > size) return end; i = find_next_bit(map, end, index); if (i < end) { area_bits = i - area_off; /* remember largest unused area with best alignment */ if (area_bits > *largest_bits || (area_bits == *largest_bits && *largest_off && (!area_off || __ffs(area_off) > __ffs(*largest_off)))) { *largest_off = area_off; *largest_bits = area_bits; } start = i + 1; goto again; } return index; } /** * pcpu_alloc_area - allocates an area from a pcpu_chunk * @chunk: chunk of interest * @alloc_bits: size of request in allocation units * @align: alignment of area (max PAGE_SIZE) * @start: bit_off to start searching * * This function takes in a @start offset to begin searching to fit an * allocation of @alloc_bits with alignment @align. It needs to scan * the allocation map because if it fits within the block's contig hint, * @start will be block->first_free. This is an attempt to fill the * allocation prior to breaking the contig hint. The allocation and * boundary maps are updated accordingly if it confirms a valid * free area. * * RETURNS: * Allocated addr offset in @chunk on success. * -1 if no matching area is found. */ static int pcpu_alloc_area(struct pcpu_chunk *chunk, int alloc_bits, size_t align, int start) { struct pcpu_block_md *chunk_md = &chunk->chunk_md; size_t align_mask = (align) ? (align - 1) : 0; unsigned long area_off = 0, area_bits = 0; int bit_off, end, oslot; lockdep_assert_held(&pcpu_lock); oslot = pcpu_chunk_slot(chunk); /* * Search to find a fit. */ end = min_t(int, start + alloc_bits + PCPU_BITMAP_BLOCK_BITS, pcpu_chunk_map_bits(chunk)); bit_off = pcpu_find_zero_area(chunk->alloc_map, end, start, alloc_bits, align_mask, &area_off, &area_bits); if (bit_off >= end) return -1; if (area_bits) pcpu_block_update_scan(chunk, area_off, area_bits); /* update alloc map */ bitmap_set(chunk->alloc_map, bit_off, alloc_bits); /* update boundary map */ set_bit(bit_off, chunk->bound_map); bitmap_clear(chunk->bound_map, bit_off + 1, alloc_bits - 1); set_bit(bit_off + alloc_bits, chunk->bound_map); chunk->free_bytes -= alloc_bits * PCPU_MIN_ALLOC_SIZE; /* update first free bit */ if (bit_off == chunk_md->first_free) chunk_md->first_free = find_next_zero_bit( chunk->alloc_map, pcpu_chunk_map_bits(chunk), bit_off + alloc_bits); pcpu_block_update_hint_alloc(chunk, bit_off, alloc_bits); pcpu_chunk_relocate(chunk, oslot); return bit_off * PCPU_MIN_ALLOC_SIZE; } /** * pcpu_free_area - frees the corresponding offset * @chunk: chunk of interest * @off: addr offset into chunk * * This function determines the size of an allocation to free using * the boundary bitmap and clears the allocation map. * * RETURNS: * Number of freed bytes. */ static int pcpu_free_area(struct pcpu_chunk *chunk, int off) { struct pcpu_block_md *chunk_md = &chunk->chunk_md; int bit_off, bits, end, oslot, freed; lockdep_assert_held(&pcpu_lock); pcpu_stats_area_dealloc(chunk); oslot = pcpu_chunk_slot(chunk); bit_off = off / PCPU_MIN_ALLOC_SIZE; /* find end index */ end = find_next_bit(chunk->bound_map, pcpu_chunk_map_bits(chunk), bit_off + 1); bits = end - bit_off; bitmap_clear(chunk->alloc_map, bit_off, bits); freed = bits * PCPU_MIN_ALLOC_SIZE; /* update metadata */ chunk->free_bytes += freed; /* update first free bit */ chunk_md->first_free = min(chunk_md->first_free, bit_off); pcpu_block_update_hint_free(chunk, bit_off, bits); pcpu_chunk_relocate(chunk, oslot); return freed; } static void pcpu_init_md_block(struct pcpu_block_md *block, int nr_bits) { block->scan_hint = 0; block->contig_hint = nr_bits; block->left_free = nr_bits; block->right_free = nr_bits; block->first_free = 0; block->nr_bits = nr_bits; } static void pcpu_init_md_blocks(struct pcpu_chunk *chunk) { struct pcpu_block_md *md_block; /* init the chunk's block */ pcpu_init_md_block(&chunk->chunk_md, pcpu_chunk_map_bits(chunk)); for (md_block = chunk->md_blocks; md_block != chunk->md_blocks + pcpu_chunk_nr_blocks(chunk); md_block++) pcpu_init_md_block(md_block, PCPU_BITMAP_BLOCK_BITS); } /** * pcpu_alloc_first_chunk - creates chunks that serve the first chunk * @tmp_addr: the start of the region served * @map_size: size of the region served * * This is responsible for creating the chunks that serve the first chunk. The * base_addr is page aligned down of @tmp_addr while the region end is page * aligned up. Offsets are kept track of to determine the region served. All * this is done to appease the bitmap allocator in avoiding partial blocks. * * RETURNS: * Chunk serving the region at @tmp_addr of @map_size. */ static struct pcpu_chunk * __init pcpu_alloc_first_chunk(unsigned long tmp_addr, int map_size) { struct pcpu_chunk *chunk; unsigned long aligned_addr; int start_offset, offset_bits, region_size, region_bits; size_t alloc_size; /* region calculations */ aligned_addr = tmp_addr & PAGE_MASK; start_offset = tmp_addr - aligned_addr; region_size = ALIGN(start_offset + map_size, PAGE_SIZE); /* allocate chunk */ alloc_size = struct_size(chunk, populated, BITS_TO_LONGS(region_size >> PAGE_SHIFT)); chunk = memblock_alloc(alloc_size, SMP_CACHE_BYTES); if (!chunk) panic("%s: Failed to allocate %zu bytes\n", __func__, alloc_size); INIT_LIST_HEAD(&chunk->list); chunk->base_addr = (void *)aligned_addr; chunk->start_offset = start_offset; chunk->end_offset = region_size - chunk->start_offset - map_size; chunk->nr_pages = region_size >> PAGE_SHIFT; region_bits = pcpu_chunk_map_bits(chunk); alloc_size = BITS_TO_LONGS(region_bits) * sizeof(chunk->alloc_map[0]); chunk->alloc_map = memblock_alloc(alloc_size, SMP_CACHE_BYTES); if (!chunk->alloc_map) panic("%s: Failed to allocate %zu bytes\n", __func__, alloc_size); alloc_size = BITS_TO_LONGS(region_bits + 1) * sizeof(chunk->bound_map[0]); chunk->bound_map = memblock_alloc(alloc_size, SMP_CACHE_BYTES); if (!chunk->bound_map) panic("%s: Failed to allocate %zu bytes\n", __func__, alloc_size); alloc_size = pcpu_chunk_nr_blocks(chunk) * sizeof(chunk->md_blocks[0]); chunk->md_blocks = memblock_alloc(alloc_size, SMP_CACHE_BYTES); if (!chunk->md_blocks) panic("%s: Failed to allocate %zu bytes\n", __func__, alloc_size); #ifdef NEED_PCPUOBJ_EXT /* first chunk is free to use */ chunk->obj_exts = NULL; #endif pcpu_init_md_blocks(chunk); /* manage populated page bitmap */ chunk->immutable = true; bitmap_fill(chunk->populated, chunk->nr_pages); chunk->nr_populated = chunk->nr_pages; chunk->nr_empty_pop_pages = chunk->nr_pages; chunk->free_bytes = map_size; if (chunk->start_offset) { /* hide the beginning of the bitmap */ offset_bits = chunk->start_offset / PCPU_MIN_ALLOC_SIZE; bitmap_set(chunk->alloc_map, 0, offset_bits); set_bit(0, chunk->bound_map); set_bit(offset_bits, chunk->bound_map); chunk->chunk_md.first_free = offset_bits; pcpu_block_update_hint_alloc(chunk, 0, offset_bits); } if (chunk->end_offset) { /* hide the end of the bitmap */ offset_bits = chunk->end_offset / PCPU_MIN_ALLOC_SIZE; bitmap_set(chunk->alloc_map, pcpu_chunk_map_bits(chunk) - offset_bits, offset_bits); set_bit((start_offset + map_size) / PCPU_MIN_ALLOC_SIZE, chunk->bound_map); set_bit(region_bits, chunk->bound_map); pcpu_block_update_hint_alloc(chunk, pcpu_chunk_map_bits(chunk) - offset_bits, offset_bits); } return chunk; } static struct pcpu_chunk *pcpu_alloc_chunk(gfp_t gfp) { struct pcpu_chunk *chunk; int region_bits; chunk = pcpu_mem_zalloc(pcpu_chunk_struct_size, gfp); if (!chunk) return NULL; INIT_LIST_HEAD(&chunk->list); chunk->nr_pages = pcpu_unit_pages; region_bits = pcpu_chunk_map_bits(chunk); chunk->alloc_map = pcpu_mem_zalloc(BITS_TO_LONGS(region_bits) * sizeof(chunk->alloc_map[0]), gfp); if (!chunk->alloc_map) goto alloc_map_fail; chunk->bound_map = pcpu_mem_zalloc(BITS_TO_LONGS(region_bits + 1) * sizeof(chunk->bound_map[0]), gfp); if (!chunk->bound_map) goto bound_map_fail; chunk->md_blocks = pcpu_mem_zalloc(pcpu_chunk_nr_blocks(chunk) * sizeof(chunk->md_blocks[0]), gfp); if (!chunk->md_blocks) goto md_blocks_fail; #ifdef NEED_PCPUOBJ_EXT if (need_pcpuobj_ext()) { chunk->obj_exts = pcpu_mem_zalloc(pcpu_chunk_map_bits(chunk) * sizeof(struct pcpuobj_ext), gfp); if (!chunk->obj_exts) goto objcg_fail; } #endif pcpu_init_md_blocks(chunk); /* init metadata */ chunk->free_bytes = chunk->nr_pages * PAGE_SIZE; return chunk; #ifdef NEED_PCPUOBJ_EXT objcg_fail: pcpu_mem_free(chunk->md_blocks); #endif md_blocks_fail: pcpu_mem_free(chunk->bound_map); bound_map_fail: pcpu_mem_free(chunk->alloc_map); alloc_map_fail: pcpu_mem_free(chunk); return NULL; } static void pcpu_free_chunk(struct pcpu_chunk *chunk) { if (!chunk) return; #ifdef NEED_PCPUOBJ_EXT pcpu_mem_free(chunk->obj_exts); #endif pcpu_mem_free(chunk->md_blocks); pcpu_mem_free(chunk->bound_map); pcpu_mem_free(chunk->alloc_map); pcpu_mem_free(chunk); } /** * pcpu_chunk_populated - post-population bookkeeping * @chunk: pcpu_chunk which got populated * @page_start: the start page * @page_end: the end page * * Pages in [@page_start,@page_end) have been populated to @chunk. Update * the bookkeeping information accordingly. Must be called after each * successful population. */ static void pcpu_chunk_populated(struct pcpu_chunk *chunk, int page_start, int page_end) { int nr = page_end - page_start; lockdep_assert_held(&pcpu_lock); bitmap_set(chunk->populated, page_start, nr); chunk->nr_populated += nr; pcpu_nr_populated += nr; pcpu_update_empty_pages(chunk, nr); } /** * pcpu_chunk_depopulated - post-depopulation bookkeeping * @chunk: pcpu_chunk which got depopulated * @page_start: the start page * @page_end: the end page * * Pages in [@page_start,@page_end) have been depopulated from @chunk. * Update the bookkeeping information accordingly. Must be called after * each successful depopulation. */ static void pcpu_chunk_depopulated(struct pcpu_chunk *chunk, int page_start, int page_end) { int nr = page_end - page_start; lockdep_assert_held(&pcpu_lock); bitmap_clear(chunk->populated, page_start, nr); chunk->nr_populated -= nr; pcpu_nr_populated -= nr; pcpu_update_empty_pages(chunk, -nr); } /* * Chunk management implementation. * * To allow different implementations, chunk alloc/free and * [de]population are implemented in a separate file which is pulled * into this file and compiled together. The following functions * should be implemented. * * pcpu_populate_chunk - populate the specified range of a chunk * pcpu_depopulate_chunk - depopulate the specified range of a chunk * pcpu_post_unmap_tlb_flush - flush tlb for the specified range of a chunk * pcpu_create_chunk - create a new chunk * pcpu_destroy_chunk - destroy a chunk, always preceded by full depop * pcpu_addr_to_page - translate address to physical address * pcpu_verify_alloc_info - check alloc_info is acceptable during init */ static int pcpu_populate_chunk(struct pcpu_chunk *chunk, int page_start, int page_end, gfp_t gfp); static void pcpu_depopulate_chunk(struct pcpu_chunk *chunk, int page_start, int page_end); static void pcpu_post_unmap_tlb_flush(struct pcpu_chunk *chunk, int page_start, int page_end); static struct pcpu_chunk *pcpu_create_chunk(gfp_t gfp); static void pcpu_destroy_chunk(struct pcpu_chunk *chunk); static struct page *pcpu_addr_to_page(void *addr); static int __init pcpu_verify_alloc_info(const struct pcpu_alloc_info *ai); #ifdef CONFIG_NEED_PER_CPU_KM #include "percpu-km.c" #else #include "percpu-vm.c" #endif /** * pcpu_chunk_addr_search - determine chunk containing specified address * @addr: address for which the chunk needs to be determined. * * This is an internal function that handles all but static allocations. * Static percpu address values should never be passed into the allocator. * * RETURNS: * The address of the found chunk. */ static struct pcpu_chunk *pcpu_chunk_addr_search(void *addr) { /* is it in the dynamic region (first chunk)? */ if (pcpu_addr_in_chunk(pcpu_first_chunk, addr)) return pcpu_first_chunk; /* is it in the reserved region? */ if (pcpu_addr_in_chunk(pcpu_reserved_chunk, addr)) return pcpu_reserved_chunk; /* * The address is relative to unit0 which might be unused and * thus unmapped. Offset the address to the unit space of the * current processor before looking it up in the vmalloc * space. Note that any possible cpu id can be used here, so * there's no need to worry about preemption or cpu hotplug. */ addr += pcpu_unit_offsets[raw_smp_processor_id()]; return pcpu_get_page_chunk(pcpu_addr_to_page(addr)); } #ifdef CONFIG_MEMCG static bool pcpu_memcg_pre_alloc_hook(size_t size, gfp_t gfp, struct obj_cgroup **objcgp) { struct obj_cgroup *objcg; if (!memcg_kmem_online() || !(gfp & __GFP_ACCOUNT)) return true; objcg = current_obj_cgroup(); if (!objcg) return true; if (obj_cgroup_charge(objcg, gfp, pcpu_obj_full_size(size))) return false; *objcgp = objcg; return true; } static void pcpu_memcg_post_alloc_hook(struct obj_cgroup *objcg, struct pcpu_chunk *chunk, int off, size_t size) { if (!objcg) return; if (likely(chunk && chunk->obj_exts)) { obj_cgroup_get(objcg); chunk->obj_exts[off >> PCPU_MIN_ALLOC_SHIFT].cgroup = objcg; rcu_read_lock(); mod_memcg_state(obj_cgroup_memcg(objcg), MEMCG_PERCPU_B, pcpu_obj_full_size(size)); rcu_read_unlock(); } else { obj_cgroup_uncharge(objcg, pcpu_obj_full_size(size)); } } static void pcpu_memcg_free_hook(struct pcpu_chunk *chunk, int off, size_t size) { struct obj_cgroup *objcg; if (unlikely(!chunk->obj_exts)) return; objcg = chunk->obj_exts[off >> PCPU_MIN_ALLOC_SHIFT].cgroup; if (!objcg) return; chunk->obj_exts[off >> PCPU_MIN_ALLOC_SHIFT].cgroup = NULL; obj_cgroup_uncharge(objcg, pcpu_obj_full_size(size)); rcu_read_lock(); mod_memcg_state(obj_cgroup_memcg(objcg), MEMCG_PERCPU_B, -pcpu_obj_full_size(size)); rcu_read_unlock(); obj_cgroup_put(objcg); } #else /* CONFIG_MEMCG */ static bool pcpu_memcg_pre_alloc_hook(size_t size, gfp_t gfp, struct obj_cgroup **objcgp) { return true; } static void pcpu_memcg_post_alloc_hook(struct obj_cgroup *objcg, struct pcpu_chunk *chunk, int off, size_t size) { } static void pcpu_memcg_free_hook(struct pcpu_chunk *chunk, int off, size_t size) { } #endif /* CONFIG_MEMCG */ #ifdef CONFIG_MEM_ALLOC_PROFILING static void pcpu_alloc_tag_alloc_hook(struct pcpu_chunk *chunk, int off, size_t size) { if (mem_alloc_profiling_enabled() && likely(chunk->obj_exts)) { alloc_tag_add(&chunk->obj_exts[off >> PCPU_MIN_ALLOC_SHIFT].tag, current->alloc_tag, size); } } static void pcpu_alloc_tag_free_hook(struct pcpu_chunk *chunk, int off, size_t size) { if (mem_alloc_profiling_enabled() && likely(chunk->obj_exts)) alloc_tag_sub(&chunk->obj_exts[off >> PCPU_MIN_ALLOC_SHIFT].tag, size); } #else static void pcpu_alloc_tag_alloc_hook(struct pcpu_chunk *chunk, int off, size_t size) { } static void pcpu_alloc_tag_free_hook(struct pcpu_chunk *chunk, int off, size_t size) { } #endif /** * pcpu_alloc - the percpu allocator * @size: size of area to allocate in bytes * @align: alignment of area (max PAGE_SIZE) * @reserved: allocate from the reserved chunk if available * @gfp: allocation flags * * Allocate percpu area of @size bytes aligned at @align. If @gfp doesn't * contain %GFP_KERNEL, the allocation is atomic. If @gfp has __GFP_NOWARN * then no warning will be triggered on invalid or failed allocation * requests. * * RETURNS: * Percpu pointer to the allocated area on success, NULL on failure. */ void __percpu *pcpu_alloc_noprof(size_t size, size_t align, bool reserved, gfp_t gfp) { gfp_t pcpu_gfp; bool is_atomic; bool do_warn; struct obj_cgroup *objcg = NULL; static int warn_limit = 10; struct pcpu_chunk *chunk, *next; const char *err; int slot, off, cpu, ret; unsigned long flags; void __percpu *ptr; size_t bits, bit_align; gfp = current_gfp_context(gfp); /* whitelisted flags that can be passed to the backing allocators */ pcpu_gfp = gfp & (GFP_KERNEL | __GFP_NORETRY | __GFP_NOWARN); is_atomic = (gfp & GFP_KERNEL) != GFP_KERNEL; do_warn = !(gfp & __GFP_NOWARN); /* * There is now a minimum allocation size of PCPU_MIN_ALLOC_SIZE, * therefore alignment must be a minimum of that many bytes. * An allocation may have internal fragmentation from rounding up * of up to PCPU_MIN_ALLOC_SIZE - 1 bytes. */ if (unlikely(align < PCPU_MIN_ALLOC_SIZE)) align = PCPU_MIN_ALLOC_SIZE; size = ALIGN(size, PCPU_MIN_ALLOC_SIZE); bits = size >> PCPU_MIN_ALLOC_SHIFT; bit_align = align >> PCPU_MIN_ALLOC_SHIFT; if (unlikely(!size || size > PCPU_MIN_UNIT_SIZE || align > PAGE_SIZE || !is_power_of_2(align))) { WARN(do_warn, "illegal size (%zu) or align (%zu) for percpu allocation\n", size, align); return NULL; } if (unlikely(!pcpu_memcg_pre_alloc_hook(size, gfp, &objcg))) return NULL; if (!is_atomic) { /* * pcpu_balance_workfn() allocates memory under this mutex, * and it may wait for memory reclaim. Allow current task * to become OOM victim, in case of memory pressure. */ if (gfp & __GFP_NOFAIL) { mutex_lock(&pcpu_alloc_mutex); } else if (mutex_lock_killable(&pcpu_alloc_mutex)) { pcpu_memcg_post_alloc_hook(objcg, NULL, 0, size); return NULL; } } spin_lock_irqsave(&pcpu_lock, flags); /* serve reserved allocations from the reserved chunk if available */ if (reserved && pcpu_reserved_chunk) { chunk = pcpu_reserved_chunk; off = pcpu_find_block_fit(chunk, bits, bit_align, is_atomic); if (off < 0) { err = "alloc from reserved chunk failed"; goto fail_unlock; } off = pcpu_alloc_area(chunk, bits, bit_align, off); if (off >= 0) goto area_found; err = "alloc from reserved chunk failed"; goto fail_unlock; } restart: /* search through normal chunks */ for (slot = pcpu_size_to_slot(size); slot <= pcpu_free_slot; slot++) { list_for_each_entry_safe(chunk, next, &pcpu_chunk_lists[slot], list) { off = pcpu_find_block_fit(chunk, bits, bit_align, is_atomic); if (off < 0) { if (slot < PCPU_SLOT_FAIL_THRESHOLD) pcpu_chunk_move(chunk, 0); continue; } off = pcpu_alloc_area(chunk, bits, bit_align, off); if (off >= 0) { pcpu_reintegrate_chunk(chunk); goto area_found; } } } spin_unlock_irqrestore(&pcpu_lock, flags); if (is_atomic) { err = "atomic alloc failed, no space left"; goto fail; } /* No space left. Create a new chunk. */ if (list_empty(&pcpu_chunk_lists[pcpu_free_slot])) { chunk = pcpu_create_chunk(pcpu_gfp); if (!chunk) { err = "failed to allocate new chunk"; goto fail; } spin_lock_irqsave(&pcpu_lock, flags); pcpu_chunk_relocate(chunk, -1); } else { spin_lock_irqsave(&pcpu_lock, flags); } goto restart; area_found: pcpu_stats_area_alloc(chunk, size); if (pcpu_nr_empty_pop_pages < PCPU_EMPTY_POP_PAGES_LOW) pcpu_schedule_balance_work(); spin_unlock_irqrestore(&pcpu_lock, flags); /* populate if not all pages are already there */ if (!is_atomic) { unsigned int page_end, rs, re; rs = PFN_DOWN(off); page_end = PFN_UP(off + size); for_each_clear_bitrange_from(rs, re, chunk->populated, page_end) { WARN_ON(chunk->immutable); ret = pcpu_populate_chunk(chunk, rs, re, pcpu_gfp); spin_lock_irqsave(&pcpu_lock, flags); if (ret) { pcpu_free_area(chunk, off); err = "failed to populate"; goto fail_unlock; } pcpu_chunk_populated(chunk, rs, re); spin_unlock_irqrestore(&pcpu_lock, flags); } mutex_unlock(&pcpu_alloc_mutex); } /* clear the areas and return address relative to base address */ for_each_possible_cpu(cpu) memset((void *)pcpu_chunk_addr(chunk, cpu, 0) + off, 0, size); ptr = __addr_to_pcpu_ptr(chunk->base_addr + off); kmemleak_alloc_percpu(ptr, size, gfp); trace_percpu_alloc_percpu(_RET_IP_, reserved, is_atomic, size, align, chunk->base_addr, off, ptr, pcpu_obj_full_size(size), gfp); pcpu_memcg_post_alloc_hook(objcg, chunk, off, size); pcpu_alloc_tag_alloc_hook(chunk, off, size); return ptr; fail_unlock: spin_unlock_irqrestore(&pcpu_lock, flags); fail: trace_percpu_alloc_percpu_fail(reserved, is_atomic, size, align); if (do_warn && warn_limit) { pr_warn("allocation failed, size=%zu align=%zu atomic=%d, %s\n", size, align, is_atomic, err); if (!is_atomic) dump_stack(); if (!--warn_limit) pr_info("limit reached, disable warning\n"); } if (is_atomic) { /* see the flag handling in pcpu_balance_workfn() */ pcpu_atomic_alloc_failed = true; pcpu_schedule_balance_work(); } else { mutex_unlock(&pcpu_alloc_mutex); } pcpu_memcg_post_alloc_hook(objcg, NULL, 0, size); return NULL; } EXPORT_SYMBOL_GPL(pcpu_alloc_noprof); /** * pcpu_balance_free - manage the amount of free chunks * @empty_only: free chunks only if there are no populated pages * * If empty_only is %false, reclaim all fully free chunks regardless of the * number of populated pages. Otherwise, only reclaim chunks that have no * populated pages. * * CONTEXT: * pcpu_lock (can be dropped temporarily) */ static void pcpu_balance_free(bool empty_only) { LIST_HEAD(to_free); struct list_head *free_head = &pcpu_chunk_lists[pcpu_free_slot]; struct pcpu_chunk *chunk, *next; lockdep_assert_held(&pcpu_lock); /* * There's no reason to keep around multiple unused chunks and VM * areas can be scarce. Destroy all free chunks except for one. */ list_for_each_entry_safe(chunk, next, free_head, list) { WARN_ON(chunk->immutable); /* spare the first one */ if (chunk == list_first_entry(free_head, struct pcpu_chunk, list)) continue; if (!empty_only || chunk->nr_empty_pop_pages == 0) list_move(&chunk->list, &to_free); } if (list_empty(&to_free)) return; spin_unlock_irq(&pcpu_lock); list_for_each_entry_safe(chunk, next, &to_free, list) { unsigned int rs, re; for_each_set_bitrange(rs, re, chunk->populated, chunk->nr_pages) { pcpu_depopulate_chunk(chunk, rs, re); spin_lock_irq(&pcpu_lock); pcpu_chunk_depopulated(chunk, rs, re); spin_unlock_irq(&pcpu_lock); } pcpu_destroy_chunk(chunk); cond_resched(); } spin_lock_irq(&pcpu_lock); } /** * pcpu_balance_populated - manage the amount of populated pages * * Maintain a certain amount of populated pages to satisfy atomic allocations. * It is possible that this is called when physical memory is scarce causing * OOM killer to be triggered. We should avoid doing so until an actual * allocation causes the failure as it is possible that requests can be * serviced from already backed regions. * * CONTEXT: * pcpu_lock (can be dropped temporarily) */ static void pcpu_balance_populated(void) { /* gfp flags passed to underlying allocators */ const gfp_t gfp = GFP_KERNEL | __GFP_NORETRY | __GFP_NOWARN; struct pcpu_chunk *chunk; int slot, nr_to_pop, ret; lockdep_assert_held(&pcpu_lock); /* * Ensure there are certain number of free populated pages for * atomic allocs. Fill up from the most packed so that atomic * allocs don't increase fragmentation. If atomic allocation * failed previously, always populate the maximum amount. This * should prevent atomic allocs larger than PAGE_SIZE from keeping * failing indefinitely; however, large atomic allocs are not * something we support properly and can be highly unreliable and * inefficient. */ retry_pop: if (pcpu_atomic_alloc_failed) { nr_to_pop = PCPU_EMPTY_POP_PAGES_HIGH; /* best effort anyway, don't worry about synchronization */ pcpu_atomic_alloc_failed = false; } else { nr_to_pop = clamp(PCPU_EMPTY_POP_PAGES_HIGH - pcpu_nr_empty_pop_pages, 0, PCPU_EMPTY_POP_PAGES_HIGH); } for (slot = pcpu_size_to_slot(PAGE_SIZE); slot <= pcpu_free_slot; slot++) { unsigned int nr_unpop = 0, rs, re; if (!nr_to_pop) break; list_for_each_entry(chunk, &pcpu_chunk_lists[slot], list) { nr_unpop = chunk->nr_pages - chunk->nr_populated; if (nr_unpop) break; } if (!nr_unpop) continue; /* @chunk can't go away while pcpu_alloc_mutex is held */ for_each_clear_bitrange(rs, re, chunk->populated, chunk->nr_pages) { int nr = min_t(int, re - rs, nr_to_pop); spin_unlock_irq(&pcpu_lock); ret = pcpu_populate_chunk(chunk, rs, rs + nr, gfp); cond_resched(); spin_lock_irq(&pcpu_lock); if (!ret) { nr_to_pop -= nr; pcpu_chunk_populated(chunk, rs, rs + nr); } else { nr_to_pop = 0; } if (!nr_to_pop) break; } } if (nr_to_pop) { /* ran out of chunks to populate, create a new one and retry */ spin_unlock_irq(&pcpu_lock); chunk = pcpu_create_chunk(gfp); cond_resched(); spin_lock_irq(&pcpu_lock); if (chunk) { pcpu_chunk_relocate(chunk, -1); goto retry_pop; } } } /** * pcpu_reclaim_populated - scan over to_depopulate chunks and free empty pages * * Scan over chunks in the depopulate list and try to release unused populated * pages back to the system. Depopulated chunks are sidelined to prevent * repopulating these pages unless required. Fully free chunks are reintegrated * and freed accordingly (1 is kept around). If we drop below the empty * populated pages threshold, reintegrate the chunk if it has empty free pages. * Each chunk is scanned in the reverse order to keep populated pages close to * the beginning of the chunk. * * CONTEXT: * pcpu_lock (can be dropped temporarily) * */ static void pcpu_reclaim_populated(void) { struct pcpu_chunk *chunk; struct pcpu_block_md *block; int freed_page_start, freed_page_end; int i, end; bool reintegrate; lockdep_assert_held(&pcpu_lock); /* * Once a chunk is isolated to the to_depopulate list, the chunk is no * longer discoverable to allocations whom may populate pages. The only * other accessor is the free path which only returns area back to the * allocator not touching the populated bitmap. */ while ((chunk = list_first_entry_or_null( &pcpu_chunk_lists[pcpu_to_depopulate_slot], struct pcpu_chunk, list))) { WARN_ON(chunk->immutable); /* * Scan chunk's pages in the reverse order to keep populated * pages close to the beginning of the chunk. */ freed_page_start = chunk->nr_pages; freed_page_end = 0; reintegrate = false; for (i = chunk->nr_pages - 1, end = -1; i >= 0; i--) { /* no more work to do */ if (chunk->nr_empty_pop_pages == 0) break; /* reintegrate chunk to prevent atomic alloc failures */ if (pcpu_nr_empty_pop_pages < PCPU_EMPTY_POP_PAGES_HIGH) { reintegrate = true; break; } /* * If the page is empty and populated, start or * extend the (i, end) range. If i == 0, decrease * i and perform the depopulation to cover the last * (first) page in the chunk. */ block = chunk->md_blocks + i; if (block->contig_hint == PCPU_BITMAP_BLOCK_BITS && test_bit(i, chunk->populated)) { if (end == -1) end = i; if (i > 0) continue; i--; } /* depopulate if there is an active range */ if (end == -1) continue; spin_unlock_irq(&pcpu_lock); pcpu_depopulate_chunk(chunk, i + 1, end + 1); cond_resched(); spin_lock_irq(&pcpu_lock); pcpu_chunk_depopulated(chunk, i + 1, end + 1); freed_page_start = min(freed_page_start, i + 1); freed_page_end = max(freed_page_end, end + 1); /* reset the range and continue */ end = -1; } /* batch tlb flush per chunk to amortize cost */ if (freed_page_start < freed_page_end) { spin_unlock_irq(&pcpu_lock); pcpu_post_unmap_tlb_flush(chunk, freed_page_start, freed_page_end); cond_resched(); spin_lock_irq(&pcpu_lock); } if (reintegrate || chunk->free_bytes == pcpu_unit_size) pcpu_reintegrate_chunk(chunk); else list_move_tail(&chunk->list, &pcpu_chunk_lists[pcpu_sidelined_slot]); } } /** * pcpu_balance_workfn - manage the amount of free chunks and populated pages * @work: unused * * For each chunk type, manage the number of fully free chunks and the number of * populated pages. An important thing to consider is when pages are freed and * how they contribute to the global counts. */ static void pcpu_balance_workfn(struct work_struct *work) { /* * pcpu_balance_free() is called twice because the first time we may * trim pages in the active pcpu_nr_empty_pop_pages which may cause us * to grow other chunks. This then gives pcpu_reclaim_populated() time * to move fully free chunks to the active list to be freed if * appropriate. */ mutex_lock(&pcpu_alloc_mutex); spin_lock_irq(&pcpu_lock); pcpu_balance_free(false); pcpu_reclaim_populated(); pcpu_balance_populated(); pcpu_balance_free(true); spin_unlock_irq(&pcpu_lock); mutex_unlock(&pcpu_alloc_mutex); } /** * free_percpu - free percpu area * @ptr: pointer to area to free * * Free percpu area @ptr. * * CONTEXT: * Can be called from atomic context. */ void free_percpu(void __percpu *ptr) { void *addr; struct pcpu_chunk *chunk; unsigned long flags; int size, off; bool need_balance = false; if (!ptr) return; kmemleak_free_percpu(ptr); addr = __pcpu_ptr_to_addr(ptr); chunk = pcpu_chunk_addr_search(addr); off = addr - chunk->base_addr; spin_lock_irqsave(&pcpu_lock, flags); size = pcpu_free_area(chunk, off); pcpu_alloc_tag_free_hook(chunk, off, size); pcpu_memcg_free_hook(chunk, off, size); /* * If there are more than one fully free chunks, wake up grim reaper. * If the chunk is isolated, it may be in the process of being * reclaimed. Let reclaim manage cleaning up of that chunk. */ if (!chunk->isolated && chunk->free_bytes == pcpu_unit_size) { struct pcpu_chunk *pos; list_for_each_entry(pos, &pcpu_chunk_lists[pcpu_free_slot], list) if (pos != chunk) { need_balance = true; break; } } else if (pcpu_should_reclaim_chunk(chunk)) { pcpu_isolate_chunk(chunk); need_balance = true; } trace_percpu_free_percpu(chunk->base_addr, off, ptr); spin_unlock_irqrestore(&pcpu_lock, flags); if (need_balance) pcpu_schedule_balance_work(); } EXPORT_SYMBOL_GPL(free_percpu); bool __is_kernel_percpu_address(unsigned long addr, unsigned long *can_addr) { #ifdef CONFIG_SMP const size_t static_size = __per_cpu_end - __per_cpu_start; void __percpu *base = __addr_to_pcpu_ptr(pcpu_base_addr); unsigned int cpu; for_each_possible_cpu(cpu) { void *start = per_cpu_ptr(base, cpu); void *va = (void *)addr; if (va >= start && va < start + static_size) { if (can_addr) { *can_addr = (unsigned long) (va - start); *can_addr += (unsigned long) per_cpu_ptr(base, get_boot_cpu_id()); } return true; } } #endif /* on UP, can't distinguish from other static vars, always false */ return false; } /** * is_kernel_percpu_address - test whether address is from static percpu area * @addr: address to test * * Test whether @addr belongs to in-kernel static percpu area. Module * static percpu areas are not considered. For those, use * is_module_percpu_address(). * * RETURNS: * %true if @addr is from in-kernel static percpu area, %false otherwise. */ bool is_kernel_percpu_address(unsigned long addr) { return __is_kernel_percpu_address(addr, NULL); } /** * per_cpu_ptr_to_phys - convert translated percpu address to physical address * @addr: the address to be converted to physical address * * Given @addr which is dereferenceable address obtained via one of * percpu access macros, this function translates it into its physical * address. The caller is responsible for ensuring @addr stays valid * until this function finishes. * * percpu allocator has special setup for the first chunk, which currently * supports either embedding in linear address space or vmalloc mapping, * and, from the second one, the backing allocator (currently either vm or * km) provides translation. * * The addr can be translated simply without checking if it falls into the * first chunk. But the current code reflects better how percpu allocator * actually works, and the verification can discover both bugs in percpu * allocator itself and per_cpu_ptr_to_phys() callers. So we keep current * code. * * RETURNS: * The physical address for @addr. */ phys_addr_t per_cpu_ptr_to_phys(void *addr) { void __percpu *base = __addr_to_pcpu_ptr(pcpu_base_addr); bool in_first_chunk = false; unsigned long first_low, first_high; unsigned int cpu; /* * The following test on unit_low/high isn't strictly * necessary but will speed up lookups of addresses which * aren't in the first chunk. * * The address check is against full chunk sizes. pcpu_base_addr * points to the beginning of the first chunk including the * static region. Assumes good intent as the first chunk may * not be full (ie. < pcpu_unit_pages in size). */ first_low = (unsigned long)pcpu_base_addr + pcpu_unit_page_offset(pcpu_low_unit_cpu, 0); first_high = (unsigned long)pcpu_base_addr + pcpu_unit_page_offset(pcpu_high_unit_cpu, pcpu_unit_pages); if ((unsigned long)addr >= first_low && (unsigned long)addr < first_high) { for_each_possible_cpu(cpu) { void *start = per_cpu_ptr(base, cpu); if (addr >= start && addr < start + pcpu_unit_size) { in_first_chunk = true; break; } } } if (in_first_chunk) { if (!is_vmalloc_addr(addr)) return __pa(addr); else return page_to_phys(vmalloc_to_page(addr)) + offset_in_page(addr); } else return page_to_phys(pcpu_addr_to_page(addr)) + offset_in_page(addr); } /** * pcpu_alloc_alloc_info - allocate percpu allocation info * @nr_groups: the number of groups * @nr_units: the number of units * * Allocate ai which is large enough for @nr_groups groups containing * @nr_units units. The returned ai's groups[0].cpu_map points to the * cpu_map array which is long enough for @nr_units and filled with * NR_CPUS. It's the caller's responsibility to initialize cpu_map * pointer of other groups. * * RETURNS: * Pointer to the allocated pcpu_alloc_info on success, NULL on * failure. */ struct pcpu_alloc_info * __init pcpu_alloc_alloc_info(int nr_groups, int nr_units) { struct pcpu_alloc_info *ai; size_t base_size, ai_size; void *ptr; int unit; base_size = ALIGN(struct_size(ai, groups, nr_groups), __alignof__(ai->groups[0].cpu_map[0])); ai_size = base_size + nr_units * sizeof(ai->groups[0].cpu_map[0]); ptr = memblock_alloc(PFN_ALIGN(ai_size), PAGE_SIZE); if (!ptr) return NULL; ai = ptr; ptr += base_size; ai->groups[0].cpu_map = ptr; for (unit = 0; unit < nr_units; unit++) ai->groups[0].cpu_map[unit] = NR_CPUS; ai->nr_groups = nr_groups; ai->__ai_size = PFN_ALIGN(ai_size); return ai; } /** * pcpu_free_alloc_info - free percpu allocation info * @ai: pcpu_alloc_info to free * * Free @ai which was allocated by pcpu_alloc_alloc_info(). */ void __init pcpu_free_alloc_info(struct pcpu_alloc_info *ai) { memblock_free(ai, ai->__ai_size); } /** * pcpu_dump_alloc_info - print out information about pcpu_alloc_info * @lvl: loglevel * @ai: allocation info to dump * * Print out information about @ai using loglevel @lvl. */ static void pcpu_dump_alloc_info(const char *lvl, const struct pcpu_alloc_info *ai) { int group_width = 1, cpu_width = 1, width; char empty_str[] = "--------"; int alloc = 0, alloc_end = 0; int group, v; int upa, apl; /* units per alloc, allocs per line */ v = ai->nr_groups; while (v /= 10) group_width++; v = num_possible_cpus(); while (v /= 10) cpu_width++; empty_str[min_t(int, cpu_width, sizeof(empty_str) - 1)] = '\0'; upa = ai->alloc_size / ai->unit_size; width = upa * (cpu_width + 1) + group_width + 3; apl = rounddown_pow_of_two(max(60 / width, 1)); printk("%spcpu-alloc: s%zu r%zu d%zu u%zu alloc=%zu*%zu", lvl, ai->static_size, ai->reserved_size, ai->dyn_size, ai->unit_size, ai->alloc_size / ai->atom_size, ai->atom_size); for (group = 0; group < ai->nr_groups; group++) { const struct pcpu_group_info *gi = &ai->groups[group]; int unit = 0, unit_end = 0; BUG_ON(gi->nr_units % upa); for (alloc_end += gi->nr_units / upa; alloc < alloc_end; alloc++) { if (!(alloc % apl)) { pr_cont("\n"); printk("%spcpu-alloc: ", lvl); } pr_cont("[%0*d] ", group_width, group); for (unit_end += upa; unit < unit_end; unit++) if (gi->cpu_map[unit] != NR_CPUS) pr_cont("%0*d ", cpu_width, gi->cpu_map[unit]); else pr_cont("%s ", empty_str); } } pr_cont("\n"); } /** * pcpu_setup_first_chunk - initialize the first percpu chunk * @ai: pcpu_alloc_info describing how to percpu area is shaped * @base_addr: mapped address * * Initialize the first percpu chunk which contains the kernel static * percpu area. This function is to be called from arch percpu area * setup path. * * @ai contains all information necessary to initialize the first * chunk and prime the dynamic percpu allocator. * * @ai->static_size is the size of static percpu area. * * @ai->reserved_size, if non-zero, specifies the amount of bytes to * reserve after the static area in the first chunk. This reserves * the first chunk such that it's available only through reserved * percpu allocation. This is primarily used to serve module percpu * static areas on architectures where the addressing model has * limited offset range for symbol relocations to guarantee module * percpu symbols fall inside the relocatable range. * * @ai->dyn_size determines the number of bytes available for dynamic * allocation in the first chunk. The area between @ai->static_size + * @ai->reserved_size + @ai->dyn_size and @ai->unit_size is unused. * * @ai->unit_size specifies unit size and must be aligned to PAGE_SIZE * and equal to or larger than @ai->static_size + @ai->reserved_size + * @ai->dyn_size. * * @ai->atom_size is the allocation atom size and used as alignment * for vm areas. * * @ai->alloc_size is the allocation size and always multiple of * @ai->atom_size. This is larger than @ai->atom_size if * @ai->unit_size is larger than @ai->atom_size. * * @ai->nr_groups and @ai->groups describe virtual memory layout of * percpu areas. Units which should be colocated are put into the * same group. Dynamic VM areas will be allocated according to these * groupings. If @ai->nr_groups is zero, a single group containing * all units is assumed. * * The caller should have mapped the first chunk at @base_addr and * copied static data to each unit. * * The first chunk will always contain a static and a dynamic region. * However, the static region is not managed by any chunk. If the first * chunk also contains a reserved region, it is served by two chunks - * one for the reserved region and one for the dynamic region. They * share the same vm, but use offset regions in the area allocation map. * The chunk serving the dynamic region is circulated in the chunk slots * and available for dynamic allocation like any other chunk. */ void __init pcpu_setup_first_chunk(const struct pcpu_alloc_info *ai, void *base_addr) { size_t size_sum = ai->static_size + ai->reserved_size + ai->dyn_size; size_t static_size, dyn_size; unsigned long *group_offsets; size_t *group_sizes; unsigned long *unit_off; unsigned int cpu; int *unit_map; int group, unit, i; unsigned long tmp_addr; size_t alloc_size; #define PCPU_SETUP_BUG_ON(cond) do { \ if (unlikely(cond)) { \ pr_emerg("failed to initialize, %s\n", #cond); \ pr_emerg("cpu_possible_mask=%*pb\n", \ cpumask_pr_args(cpu_possible_mask)); \ pcpu_dump_alloc_info(KERN_EMERG, ai); \ BUG(); \ } \ } while (0) /* sanity checks */ PCPU_SETUP_BUG_ON(ai->nr_groups <= 0); #ifdef CONFIG_SMP PCPU_SETUP_BUG_ON(!ai->static_size); PCPU_SETUP_BUG_ON(offset_in_page(__per_cpu_start)); #endif PCPU_SETUP_BUG_ON(!base_addr); PCPU_SETUP_BUG_ON(offset_in_page(base_addr)); PCPU_SETUP_BUG_ON(ai->unit_size < size_sum); PCPU_SETUP_BUG_ON(offset_in_page(ai->unit_size)); PCPU_SETUP_BUG_ON(ai->unit_size < PCPU_MIN_UNIT_SIZE); PCPU_SETUP_BUG_ON(!IS_ALIGNED(ai->unit_size, PCPU_BITMAP_BLOCK_SIZE)); PCPU_SETUP_BUG_ON(ai->dyn_size < PERCPU_DYNAMIC_EARLY_SIZE); PCPU_SETUP_BUG_ON(!IS_ALIGNED(ai->reserved_size, PCPU_MIN_ALLOC_SIZE)); PCPU_SETUP_BUG_ON(!(IS_ALIGNED(PCPU_BITMAP_BLOCK_SIZE, PAGE_SIZE) || IS_ALIGNED(PAGE_SIZE, PCPU_BITMAP_BLOCK_SIZE))); PCPU_SETUP_BUG_ON(pcpu_verify_alloc_info(ai) < 0); /* process group information and build config tables accordingly */ alloc_size = ai->nr_groups * sizeof(group_offsets[0]); group_offsets = memblock_alloc(alloc_size, SMP_CACHE_BYTES); if (!group_offsets) panic("%s: Failed to allocate %zu bytes\n", __func__, alloc_size); alloc_size = ai->nr_groups * sizeof(group_sizes[0]); group_sizes = memblock_alloc(alloc_size, SMP_CACHE_BYTES); if (!group_sizes) panic("%s: Failed to allocate %zu bytes\n", __func__, alloc_size); alloc_size = nr_cpu_ids * sizeof(unit_map[0]); unit_map = memblock_alloc(alloc_size, SMP_CACHE_BYTES); if (!unit_map) panic("%s: Failed to allocate %zu bytes\n", __func__, alloc_size); alloc_size = nr_cpu_ids * sizeof(unit_off[0]); unit_off = memblock_alloc(alloc_size, SMP_CACHE_BYTES); if (!unit_off) panic("%s: Failed to allocate %zu bytes\n", __func__, alloc_size); for (cpu = 0; cpu < nr_cpu_ids; cpu++) unit_map[cpu] = UINT_MAX; pcpu_low_unit_cpu = NR_CPUS; pcpu_high_unit_cpu = NR_CPUS; for (group = 0, unit = 0; group < ai->nr_groups; group++, unit += i) { const struct pcpu_group_info *gi = &ai->groups[group]; group_offsets[group] = gi->base_offset; group_sizes[group] = gi->nr_units * ai->unit_size; for (i = 0; i < gi->nr_units; i++) { cpu = gi->cpu_map[i]; if (cpu == NR_CPUS) continue; PCPU_SETUP_BUG_ON(cpu >= nr_cpu_ids); PCPU_SETUP_BUG_ON(!cpu_possible(cpu)); PCPU_SETUP_BUG_ON(unit_map[cpu] != UINT_MAX); unit_map[cpu] = unit + i; unit_off[cpu] = gi->base_offset + i * ai->unit_size; /* determine low/high unit_cpu */ if (pcpu_low_unit_cpu == NR_CPUS || unit_off[cpu] < unit_off[pcpu_low_unit_cpu]) pcpu_low_unit_cpu = cpu; if (pcpu_high_unit_cpu == NR_CPUS || unit_off[cpu] > unit_off[pcpu_high_unit_cpu]) pcpu_high_unit_cpu = cpu; } } pcpu_nr_units = unit; for_each_possible_cpu(cpu) PCPU_SETUP_BUG_ON(unit_map[cpu] == UINT_MAX); /* we're done parsing the input, undefine BUG macro and dump config */ #undef PCPU_SETUP_BUG_ON pcpu_dump_alloc_info(KERN_DEBUG, ai); pcpu_nr_groups = ai->nr_groups; pcpu_group_offsets = group_offsets; pcpu_group_sizes = group_sizes; pcpu_unit_map = unit_map; pcpu_unit_offsets = unit_off; /* determine basic parameters */ pcpu_unit_pages = ai->unit_size >> PAGE_SHIFT; pcpu_unit_size = pcpu_unit_pages << PAGE_SHIFT; pcpu_atom_size = ai->atom_size; pcpu_chunk_struct_size = struct_size((struct pcpu_chunk *)0, populated, BITS_TO_LONGS(pcpu_unit_pages)); pcpu_stats_save_ai(ai); /* * Allocate chunk slots. The slots after the active slots are: * sidelined_slot - isolated, depopulated chunks * free_slot - fully free chunks * to_depopulate_slot - isolated, chunks to depopulate */ pcpu_sidelined_slot = __pcpu_size_to_slot(pcpu_unit_size) + 1; pcpu_free_slot = pcpu_sidelined_slot + 1; pcpu_to_depopulate_slot = pcpu_free_slot + 1; pcpu_nr_slots = pcpu_to_depopulate_slot + 1; pcpu_chunk_lists = memblock_alloc(pcpu_nr_slots * sizeof(pcpu_chunk_lists[0]), SMP_CACHE_BYTES); if (!pcpu_chunk_lists) panic("%s: Failed to allocate %zu bytes\n", __func__, pcpu_nr_slots * sizeof(pcpu_chunk_lists[0])); for (i = 0; i < pcpu_nr_slots; i++) INIT_LIST_HEAD(&pcpu_chunk_lists[i]); /* * The end of the static region needs to be aligned with the * minimum allocation size as this offsets the reserved and * dynamic region. The first chunk ends page aligned by * expanding the dynamic region, therefore the dynamic region * can be shrunk to compensate while still staying above the * configured sizes. */ static_size = ALIGN(ai->static_size, PCPU_MIN_ALLOC_SIZE); dyn_size = ai->dyn_size - (static_size - ai->static_size); /* * Initialize first chunk: * This chunk is broken up into 3 parts: * < static | [reserved] | dynamic > * - static - there is no backing chunk because these allocations can * never be freed. * - reserved (pcpu_reserved_chunk) - exists primarily to serve * allocations from module load. * - dynamic (pcpu_first_chunk) - serves the dynamic part of the first * chunk. */ tmp_addr = (unsigned long)base_addr + static_size; if (ai->reserved_size) pcpu_reserved_chunk = pcpu_alloc_first_chunk(tmp_addr, ai->reserved_size); tmp_addr = (unsigned long)base_addr + static_size + ai->reserved_size; pcpu_first_chunk = pcpu_alloc_first_chunk(tmp_addr, dyn_size); pcpu_nr_empty_pop_pages = pcpu_first_chunk->nr_empty_pop_pages; pcpu_chunk_relocate(pcpu_first_chunk, -1); /* include all regions of the first chunk */ pcpu_nr_populated += PFN_DOWN(size_sum); pcpu_stats_chunk_alloc(); trace_percpu_create_chunk(base_addr); /* we're done */ pcpu_base_addr = base_addr; } #ifdef CONFIG_SMP const char * const pcpu_fc_names[PCPU_FC_NR] __initconst = { [PCPU_FC_AUTO] = "auto", [PCPU_FC_EMBED] = "embed", [PCPU_FC_PAGE] = "page", }; enum pcpu_fc pcpu_chosen_fc __initdata = PCPU_FC_AUTO; static int __init percpu_alloc_setup(char *str) { if (!str) return -EINVAL; if (0) /* nada */; #ifdef CONFIG_NEED_PER_CPU_EMBED_FIRST_CHUNK else if (!strcmp(str, "embed")) pcpu_chosen_fc = PCPU_FC_EMBED; #endif #ifdef CONFIG_NEED_PER_CPU_PAGE_FIRST_CHUNK else if (!strcmp(str, "page")) pcpu_chosen_fc = PCPU_FC_PAGE; #endif else pr_warn("unknown allocator %s specified\n", str); return 0; } early_param("percpu_alloc", percpu_alloc_setup); /* * pcpu_embed_first_chunk() is used by the generic percpu setup. * Build it if needed by the arch config or the generic setup is going * to be used. */ #if defined(CONFIG_NEED_PER_CPU_EMBED_FIRST_CHUNK) || \ !defined(CONFIG_HAVE_SETUP_PER_CPU_AREA) #define BUILD_EMBED_FIRST_CHUNK #endif /* build pcpu_page_first_chunk() iff needed by the arch config */ #if defined(CONFIG_NEED_PER_CPU_PAGE_FIRST_CHUNK) #define BUILD_PAGE_FIRST_CHUNK #endif /* pcpu_build_alloc_info() is used by both embed and page first chunk */ #if defined(BUILD_EMBED_FIRST_CHUNK) || defined(BUILD_PAGE_FIRST_CHUNK) /** * pcpu_build_alloc_info - build alloc_info considering distances between CPUs * @reserved_size: the size of reserved percpu area in bytes * @dyn_size: minimum free size for dynamic allocation in bytes * @atom_size: allocation atom size * @cpu_distance_fn: callback to determine distance between cpus, optional * * This function determines grouping of units, their mappings to cpus * and other parameters considering needed percpu size, allocation * atom size and distances between CPUs. * * Groups are always multiples of atom size and CPUs which are of * LOCAL_DISTANCE both ways are grouped together and share space for * units in the same group. The returned configuration is guaranteed * to have CPUs on different nodes on different groups and >=75% usage * of allocated virtual address space. * * RETURNS: * On success, pointer to the new allocation_info is returned. On * failure, ERR_PTR value is returned. */ static struct pcpu_alloc_info * __init __flatten pcpu_build_alloc_info( size_t reserved_size, size_t dyn_size, size_t atom_size, pcpu_fc_cpu_distance_fn_t cpu_distance_fn) { static int group_map[NR_CPUS] __initdata; static int group_cnt[NR_CPUS] __initdata; static struct cpumask mask __initdata; const size_t static_size = __per_cpu_end - __per_cpu_start; int nr_groups = 1, nr_units = 0; size_t size_sum, min_unit_size, alloc_size; int upa, max_upa, best_upa; /* units_per_alloc */ int last_allocs, group, unit; unsigned int cpu, tcpu; struct pcpu_alloc_info *ai; unsigned int *cpu_map; /* this function may be called multiple times */ memset(group_map, 0, sizeof(group_map)); memset(group_cnt, 0, sizeof(group_cnt)); cpumask_clear(&mask); /* calculate size_sum and ensure dyn_size is enough for early alloc */ size_sum = PFN_ALIGN(static_size + reserved_size + max_t(size_t, dyn_size, PERCPU_DYNAMIC_EARLY_SIZE)); dyn_size = size_sum - static_size - reserved_size; /* * Determine min_unit_size, alloc_size and max_upa such that * alloc_size is multiple of atom_size and is the smallest * which can accommodate 4k aligned segments which are equal to * or larger than min_unit_size. */ min_unit_size = max_t(size_t, size_sum, PCPU_MIN_UNIT_SIZE); /* determine the maximum # of units that can fit in an allocation */ alloc_size = roundup(min_unit_size, atom_size); upa = alloc_size / min_unit_size; while (alloc_size % upa || (offset_in_page(alloc_size / upa))) upa--; max_upa = upa; cpumask_copy(&mask, cpu_possible_mask); /* group cpus according to their proximity */ for (group = 0; !cpumask_empty(&mask); group++) { /* pop the group's first cpu */ cpu = cpumask_first(&mask); group_map[cpu] = group; group_cnt[group]++; cpumask_clear_cpu(cpu, &mask); for_each_cpu(tcpu, &mask) { if (!cpu_distance_fn || (cpu_distance_fn(cpu, tcpu) == LOCAL_DISTANCE && cpu_distance_fn(tcpu, cpu) == LOCAL_DISTANCE)) { group_map[tcpu] = group; group_cnt[group]++; cpumask_clear_cpu(tcpu, &mask); } } } nr_groups = group; /* * Wasted space is caused by a ratio imbalance of upa to group_cnt. * Expand the unit_size until we use >= 75% of the units allocated. * Related to atom_size, which could be much larger than the unit_size. */ last_allocs = INT_MAX; best_upa = 0; for (upa = max_upa; upa; upa--) { int allocs = 0, wasted = 0; if (alloc_size % upa || (offset_in_page(alloc_size / upa))) continue; for (group = 0; group < nr_groups; group++) { int this_allocs = DIV_ROUND_UP(group_cnt[group], upa); allocs += this_allocs; wasted += this_allocs * upa - group_cnt[group]; } /* * Don't accept if wastage is over 1/3. The * greater-than comparison ensures upa==1 always * passes the following check. */ if (wasted > num_possible_cpus() / 3) continue; /* and then don't consume more memory */ if (allocs > last_allocs) break; last_allocs = allocs; best_upa = upa; } BUG_ON(!best_upa); upa = best_upa; /* allocate and fill alloc_info */ for (group = 0; group < nr_groups; group++) nr_units += roundup(group_cnt[group], upa); ai = pcpu_alloc_alloc_info(nr_groups, nr_units); if (!ai) return ERR_PTR(-ENOMEM); cpu_map = ai->groups[0].cpu_map; for (group = 0; group < nr_groups; group++) { ai->groups[group].cpu_map = cpu_map; cpu_map += roundup(group_cnt[group], upa); } ai->static_size = static_size; ai->reserved_size = reserved_size; ai->dyn_size = dyn_size; ai->unit_size = alloc_size / upa; ai->atom_size = atom_size; ai->alloc_size = alloc_size; for (group = 0, unit = 0; group < nr_groups; group++) { struct pcpu_group_info *gi = &ai->groups[group]; /* * Initialize base_offset as if all groups are located * back-to-back. The caller should update this to * reflect actual allocation. */ gi->base_offset = unit * ai->unit_size; for_each_possible_cpu(cpu) if (group_map[cpu] == group) gi->cpu_map[gi->nr_units++] = cpu; gi->nr_units = roundup(gi->nr_units, upa); unit += gi->nr_units; } BUG_ON(unit != nr_units); return ai; } static void * __init pcpu_fc_alloc(unsigned int cpu, size_t size, size_t align, pcpu_fc_cpu_to_node_fn_t cpu_to_nd_fn) { const unsigned long goal = __pa(MAX_DMA_ADDRESS); #ifdef CONFIG_NUMA int node = NUMA_NO_NODE; void *ptr; if (cpu_to_nd_fn) node = cpu_to_nd_fn(cpu); if (node == NUMA_NO_NODE || !node_online(node) || !NODE_DATA(node)) { ptr = memblock_alloc_from(size, align, goal); pr_info("cpu %d has no node %d or node-local memory\n", cpu, node); pr_debug("per cpu data for cpu%d %zu bytes at 0x%llx\n", cpu, size, (u64)__pa(ptr)); } else { ptr = memblock_alloc_try_nid(size, align, goal, MEMBLOCK_ALLOC_ACCESSIBLE, node); pr_debug("per cpu data for cpu%d %zu bytes on node%d at 0x%llx\n", cpu, size, node, (u64)__pa(ptr)); } return ptr; #else return memblock_alloc_from(size, align, goal); #endif } static void __init pcpu_fc_free(void *ptr, size_t size) { memblock_free(ptr, size); } #endif /* BUILD_EMBED_FIRST_CHUNK || BUILD_PAGE_FIRST_CHUNK */ #if defined(BUILD_EMBED_FIRST_CHUNK) /** * pcpu_embed_first_chunk - embed the first percpu chunk into bootmem * @reserved_size: the size of reserved percpu area in bytes * @dyn_size: minimum free size for dynamic allocation in bytes * @atom_size: allocation atom size * @cpu_distance_fn: callback to determine distance between cpus, optional * @cpu_to_nd_fn: callback to convert cpu to it's node, optional * * This is a helper to ease setting up embedded first percpu chunk and * can be called where pcpu_setup_first_chunk() is expected. * * If this function is used to setup the first chunk, it is allocated * by calling pcpu_fc_alloc and used as-is without being mapped into * vmalloc area. Allocations are always whole multiples of @atom_size * aligned to @atom_size. * * This enables the first chunk to piggy back on the linear physical * mapping which often uses larger page size. Please note that this * can result in very sparse cpu->unit mapping on NUMA machines thus * requiring large vmalloc address space. Don't use this allocator if * vmalloc space is not orders of magnitude larger than distances * between node memory addresses (ie. 32bit NUMA machines). * * @dyn_size specifies the minimum dynamic area size. * * If the needed size is smaller than the minimum or specified unit * size, the leftover is returned using pcpu_fc_free. * * RETURNS: * 0 on success, -errno on failure. */ int __init pcpu_embed_first_chunk(size_t reserved_size, size_t dyn_size, size_t atom_size, pcpu_fc_cpu_distance_fn_t cpu_distance_fn, pcpu_fc_cpu_to_node_fn_t cpu_to_nd_fn) { void *base = (void *)ULONG_MAX; void **areas = NULL; struct pcpu_alloc_info *ai; size_t size_sum, areas_size; unsigned long max_distance; int group, i, highest_group, rc = 0; ai = pcpu_build_alloc_info(reserved_size, dyn_size, atom_size, cpu_distance_fn); if (IS_ERR(ai)) return PTR_ERR(ai); size_sum = ai->static_size + ai->reserved_size + ai->dyn_size; areas_size = PFN_ALIGN(ai->nr_groups * sizeof(void *)); areas = memblock_alloc(areas_size, SMP_CACHE_BYTES); if (!areas) { rc = -ENOMEM; goto out_free; } /* allocate, copy and determine base address & max_distance */ highest_group = 0; for (group = 0; group < ai->nr_groups; group++) { struct pcpu_group_info *gi = &ai->groups[group]; unsigned int cpu = NR_CPUS; void *ptr; for (i = 0; i < gi->nr_units && cpu == NR_CPUS; i++) cpu = gi->cpu_map[i]; BUG_ON(cpu == NR_CPUS); /* allocate space for the whole group */ ptr = pcpu_fc_alloc(cpu, gi->nr_units * ai->unit_size, atom_size, cpu_to_nd_fn); if (!ptr) { rc = -ENOMEM; goto out_free_areas; } /* kmemleak tracks the percpu allocations separately */ kmemleak_ignore_phys(__pa(ptr)); areas[group] = ptr; base = min(ptr, base); if (ptr > areas[highest_group]) highest_group = group; } max_distance = areas[highest_group] - base; max_distance += ai->unit_size * ai->groups[highest_group].nr_units; /* warn if maximum distance is further than 75% of vmalloc space */ if (max_distance > VMALLOC_TOTAL * 3 / 4) { pr_warn("max_distance=0x%lx too large for vmalloc space 0x%lx\n", max_distance, VMALLOC_TOTAL); #ifdef CONFIG_NEED_PER_CPU_PAGE_FIRST_CHUNK /* and fail if we have fallback */ rc = -EINVAL; goto out_free_areas; #endif } /* * Copy data and free unused parts. This should happen after all * allocations are complete; otherwise, we may end up with * overlapping groups. */ for (group = 0; group < ai->nr_groups; group++) { struct pcpu_group_info *gi = &ai->groups[group]; void *ptr = areas[group]; for (i = 0; i < gi->nr_units; i++, ptr += ai->unit_size) { if (gi->cpu_map[i] == NR_CPUS) { /* unused unit, free whole */ pcpu_fc_free(ptr, ai->unit_size); continue; } /* copy and return the unused part */ memcpy(ptr, __per_cpu_load, ai->static_size); pcpu_fc_free(ptr + size_sum, ai->unit_size - size_sum); } } /* base address is now known, determine group base offsets */ for (group = 0; group < ai->nr_groups; group++) { ai->groups[group].base_offset = areas[group] - base; } pr_info("Embedded %zu pages/cpu s%zu r%zu d%zu u%zu\n", PFN_DOWN(size_sum), ai->static_size, ai->reserved_size, ai->dyn_size, ai->unit_size); pcpu_setup_first_chunk(ai, base); goto out_free; out_free_areas: for (group = 0; group < ai->nr_groups; group++) if (areas[group]) pcpu_fc_free(areas[group], ai->groups[group].nr_units * ai->unit_size); out_free: pcpu_free_alloc_info(ai); if (areas) memblock_free(areas, areas_size); return rc; } #endif /* BUILD_EMBED_FIRST_CHUNK */ #ifdef BUILD_PAGE_FIRST_CHUNK #include <asm/pgalloc.h> #ifndef P4D_TABLE_SIZE #define P4D_TABLE_SIZE PAGE_SIZE #endif #ifndef PUD_TABLE_SIZE #define PUD_TABLE_SIZE PAGE_SIZE #endif #ifndef PMD_TABLE_SIZE #define PMD_TABLE_SIZE PAGE_SIZE #endif #ifndef PTE_TABLE_SIZE #define PTE_TABLE_SIZE PAGE_SIZE #endif void __init __weak pcpu_populate_pte(unsigned long addr) { pgd_t *pgd = pgd_offset_k(addr); p4d_t *p4d; pud_t *pud; pmd_t *pmd; if (pgd_none(*pgd)) { p4d = memblock_alloc(P4D_TABLE_SIZE, P4D_TABLE_SIZE); if (!p4d) goto err_alloc; pgd_populate(&init_mm, pgd, p4d); } p4d = p4d_offset(pgd, addr); if (p4d_none(*p4d)) { pud = memblock_alloc(PUD_TABLE_SIZE, PUD_TABLE_SIZE); if (!pud) goto err_alloc; p4d_populate(&init_mm, p4d, pud); } pud = pud_offset(p4d, addr); if (pud_none(*pud)) { pmd = memblock_alloc(PMD_TABLE_SIZE, PMD_TABLE_SIZE); if (!pmd) goto err_alloc; pud_populate(&init_mm, pud, pmd); } pmd = pmd_offset(pud, addr); if (!pmd_present(*pmd)) { pte_t *new; new = memblock_alloc(PTE_TABLE_SIZE, PTE_TABLE_SIZE); if (!new) goto err_alloc; pmd_populate_kernel(&init_mm, pmd, new); } return; err_alloc: panic("%s: Failed to allocate memory\n", __func__); } /** * pcpu_page_first_chunk - map the first chunk using PAGE_SIZE pages * @reserved_size: the size of reserved percpu area in bytes * @cpu_to_nd_fn: callback to convert cpu to it's node, optional * * This is a helper to ease setting up page-remapped first percpu * chunk and can be called where pcpu_setup_first_chunk() is expected. * * This is the basic allocator. Static percpu area is allocated * page-by-page into vmalloc area. * * RETURNS: * 0 on success, -errno on failure. */ int __init pcpu_page_first_chunk(size_t reserved_size, pcpu_fc_cpu_to_node_fn_t cpu_to_nd_fn) { static struct vm_struct vm; struct pcpu_alloc_info *ai; char psize_str[16]; int unit_pages; size_t pages_size; struct page **pages; int unit, i, j, rc = 0; int upa; int nr_g0_units; snprintf(psize_str, sizeof(psize_str), "%luK", PAGE_SIZE >> 10); ai = pcpu_build_alloc_info(reserved_size, 0, PAGE_SIZE, NULL); if (IS_ERR(ai)) return PTR_ERR(ai); BUG_ON(ai->nr_groups != 1); upa = ai->alloc_size/ai->unit_size; nr_g0_units = roundup(num_possible_cpus(), upa); if (WARN_ON(ai->groups[0].nr_units != nr_g0_units)) { pcpu_free_alloc_info(ai); return -EINVAL; } unit_pages = ai->unit_size >> PAGE_SHIFT; /* unaligned allocations can't be freed, round up to page size */ pages_size = PFN_ALIGN(unit_pages * num_possible_cpus() * sizeof(pages[0])); pages = memblock_alloc(pages_size, SMP_CACHE_BYTES); if (!pages) panic("%s: Failed to allocate %zu bytes\n", __func__, pages_size); /* allocate pages */ j = 0; for (unit = 0; unit < num_possible_cpus(); unit++) { unsigned int cpu = ai->groups[0].cpu_map[unit]; for (i = 0; i < unit_pages; i++) { void *ptr; ptr = pcpu_fc_alloc(cpu, PAGE_SIZE, PAGE_SIZE, cpu_to_nd_fn); if (!ptr) { pr_warn("failed to allocate %s page for cpu%u\n", psize_str, cpu); goto enomem; } /* kmemleak tracks the percpu allocations separately */ kmemleak_ignore_phys(__pa(ptr)); pages[j++] = virt_to_page(ptr); } } /* allocate vm area, map the pages and copy static data */ vm.flags = VM_ALLOC; vm.size = num_possible_cpus() * ai->unit_size; vm_area_register_early(&vm, PAGE_SIZE); for (unit = 0; unit < num_possible_cpus(); unit++) { unsigned long unit_addr = (unsigned long)vm.addr + unit * ai->unit_size; for (i = 0; i < unit_pages; i++) pcpu_populate_pte(unit_addr + (i << PAGE_SHIFT)); /* pte already populated, the following shouldn't fail */ rc = __pcpu_map_pages(unit_addr, &pages[unit * unit_pages], unit_pages); if (rc < 0) panic("failed to map percpu area, err=%d\n", rc); flush_cache_vmap_early(unit_addr, unit_addr + ai->unit_size); /* copy static data */ memcpy((void *)unit_addr, __per_cpu_load, ai->static_size); } /* we're ready, commit */ pr_info("%d %s pages/cpu s%zu r%zu d%zu\n", unit_pages, psize_str, ai->static_size, ai->reserved_size, ai->dyn_size); pcpu_setup_first_chunk(ai, vm.addr); goto out_free_ar; enomem: while (--j >= 0) pcpu_fc_free(page_address(pages[j]), PAGE_SIZE); rc = -ENOMEM; out_free_ar: memblock_free(pages, pages_size); pcpu_free_alloc_info(ai); return rc; } #endif /* BUILD_PAGE_FIRST_CHUNK */ #ifndef CONFIG_HAVE_SETUP_PER_CPU_AREA /* * Generic SMP percpu area setup. * * The embedding helper is used because its behavior closely resembles * the original non-dynamic generic percpu area setup. This is * important because many archs have addressing restrictions and might * fail if the percpu area is located far away from the previous * location. As an added bonus, in non-NUMA cases, embedding is * generally a good idea TLB-wise because percpu area can piggy back * on the physical linear memory mapping which uses large page * mappings on applicable archs. */ unsigned long __per_cpu_offset[NR_CPUS] __read_mostly; EXPORT_SYMBOL(__per_cpu_offset); void __init setup_per_cpu_areas(void) { unsigned long delta; unsigned int cpu; int rc; /* * Always reserve area for module percpu variables. That's * what the legacy allocator did. */ rc = pcpu_embed_first_chunk(PERCPU_MODULE_RESERVE, PERCPU_DYNAMIC_RESERVE, PAGE_SIZE, NULL, NULL); if (rc < 0) panic("Failed to initialize percpu areas."); delta = (unsigned long)pcpu_base_addr - (unsigned long)__per_cpu_start; for_each_possible_cpu(cpu) __per_cpu_offset[cpu] = delta + pcpu_unit_offsets[cpu]; } #endif /* CONFIG_HAVE_SETUP_PER_CPU_AREA */ #else /* CONFIG_SMP */ /* * UP percpu area setup. * * UP always uses km-based percpu allocator with identity mapping. * Static percpu variables are indistinguishable from the usual static * variables and don't require any special preparation. */ void __init setup_per_cpu_areas(void) { const size_t unit_size = roundup_pow_of_two(max_t(size_t, PCPU_MIN_UNIT_SIZE, PERCPU_DYNAMIC_RESERVE)); struct pcpu_alloc_info *ai; void *fc; ai = pcpu_alloc_alloc_info(1, 1); fc = memblock_alloc_from(unit_size, PAGE_SIZE, __pa(MAX_DMA_ADDRESS)); if (!ai || !fc) panic("Failed to allocate memory for percpu areas."); /* kmemleak tracks the percpu allocations separately */ kmemleak_ignore_phys(__pa(fc)); ai->dyn_size = unit_size; ai->unit_size = unit_size; ai->atom_size = unit_size; ai->alloc_size = unit_size; ai->groups[0].nr_units = 1; ai->groups[0].cpu_map[0] = 0; pcpu_setup_first_chunk(ai, fc); pcpu_free_alloc_info(ai); } #endif /* CONFIG_SMP */ /* * pcpu_nr_pages - calculate total number of populated backing pages * * This reflects the number of pages populated to back chunks. Metadata is * excluded in the number exposed in meminfo as the number of backing pages * scales with the number of cpus and can quickly outweigh the memory used for * metadata. It also keeps this calculation nice and simple. * * RETURNS: * Total number of populated backing pages in use by the allocator. */ unsigned long pcpu_nr_pages(void) { return pcpu_nr_populated * pcpu_nr_units; } /* * Percpu allocator is initialized early during boot when neither slab or * workqueue is available. Plug async management until everything is up * and running. */ static int __init percpu_enable_async(void) { pcpu_async_enabled = true; return 0; } subsys_initcall(percpu_enable_async); |
| 19 23 1 20 2 3 1 2 21 19 22 20 21 11 20 19 17 19 14 14 5 14 13 12 2 8 8 1 14 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 1522 | // SPDX-License-Identifier: GPL-2.0 /* * linux/fs/pipe.c * * Copyright (C) 1991, 1992, 1999 Linus Torvalds */ #include <linux/mm.h> #include <linux/file.h> #include <linux/poll.h> #include <linux/slab.h> #include <linux/module.h> #include <linux/init.h> #include <linux/fs.h> #include <linux/log2.h> #include <linux/mount.h> #include <linux/pseudo_fs.h> #include <linux/magic.h> #include <linux/pipe_fs_i.h> #include <linux/uio.h> #include <linux/highmem.h> #include <linux/pagemap.h> #include <linux/audit.h> #include <linux/syscalls.h> #include <linux/fcntl.h> #include <linux/memcontrol.h> #include <linux/watch_queue.h> #include <linux/sysctl.h> #include <linux/uaccess.h> #include <asm/ioctls.h> #include "internal.h" /* * New pipe buffers will be restricted to this size while the user is exceeding * their pipe buffer quota. The general pipe use case needs at least two * buffers: one for data yet to be read, and one for new data. If this is less * than two, then a write to a non-empty pipe may block even if the pipe is not * full. This can occur with GNU make jobserver or similar uses of pipes as * semaphores: multiple processes may be waiting to write tokens back to the * pipe before reading tokens: https://lore.kernel.org/lkml/1628086770.5rn8p04n6j.none@localhost/. * * Users can reduce their pipe buffers with F_SETPIPE_SZ below this at their * own risk, namely: pipe writes to non-full pipes may block until the pipe is * emptied. */ #define PIPE_MIN_DEF_BUFFERS 2 /* * The max size that a non-root user is allowed to grow the pipe. Can * be set by root in /proc/sys/fs/pipe-max-size */ static unsigned int pipe_max_size = 1048576; /* Maximum allocatable pages per user. Hard limit is unset by default, soft * matches default values. */ static unsigned long pipe_user_pages_hard; static unsigned long pipe_user_pages_soft = PIPE_DEF_BUFFERS * INR_OPEN_CUR; /* * We use head and tail indices that aren't masked off, except at the point of * dereference, but rather they're allowed to wrap naturally. This means there * isn't a dead spot in the buffer, but the ring has to be a power of two and * <= 2^31. * -- David Howells 2019-09-23. * * Reads with count = 0 should always return 0. * -- Julian Bradfield 1999-06-07. * * FIFOs and Pipes now generate SIGIO for both readers and writers. * -- Jeremy Elson <jelson@circlemud.org> 2001-08-16 * * pipe_read & write cleanup * -- Manfred Spraul <manfred@colorfullife.com> 2002-05-09 */ #define cmp_int(l, r) ((l > r) - (l < r)) #ifdef CONFIG_PROVE_LOCKING static int pipe_lock_cmp_fn(const struct lockdep_map *a, const struct lockdep_map *b) { return cmp_int((unsigned long) a, (unsigned long) b); } #endif void pipe_lock(struct pipe_inode_info *pipe) { if (pipe->files) mutex_lock(&pipe->mutex); } EXPORT_SYMBOL(pipe_lock); void pipe_unlock(struct pipe_inode_info *pipe) { if (pipe->files) mutex_unlock(&pipe->mutex); } EXPORT_SYMBOL(pipe_unlock); void pipe_double_lock(struct pipe_inode_info *pipe1, struct pipe_inode_info *pipe2) { BUG_ON(pipe1 == pipe2); if (pipe1 > pipe2) swap(pipe1, pipe2); pipe_lock(pipe1); pipe_lock(pipe2); } static void anon_pipe_buf_release(struct pipe_inode_info *pipe, struct pipe_buffer *buf) { struct page *page = buf->page; /* * If nobody else uses this page, and we don't already have a * temporary page, let's keep track of it as a one-deep * allocation cache. (Otherwise just release our reference to it) */ if (page_count(page) == 1 && !pipe->tmp_page) pipe->tmp_page = page; else put_page(page); } static bool anon_pipe_buf_try_steal(struct pipe_inode_info *pipe, struct pipe_buffer *buf) { struct page *page = buf->page; if (page_count(page) != 1) return false; memcg_kmem_uncharge_page(page, 0); __SetPageLocked(page); return true; } /** * generic_pipe_buf_try_steal - attempt to take ownership of a &pipe_buffer * @pipe: the pipe that the buffer belongs to * @buf: the buffer to attempt to steal * * Description: * This function attempts to steal the &struct page attached to * @buf. If successful, this function returns 0 and returns with * the page locked. The caller may then reuse the page for whatever * he wishes; the typical use is insertion into a different file * page cache. */ bool generic_pipe_buf_try_steal(struct pipe_inode_info *pipe, struct pipe_buffer *buf) { struct page *page = buf->page; /* * A reference of one is golden, that means that the owner of this * page is the only one holding a reference to it. lock the page * and return OK. */ if (page_count(page) == 1) { lock_page(page); return true; } return false; } EXPORT_SYMBOL(generic_pipe_buf_try_steal); /** * generic_pipe_buf_get - get a reference to a &struct pipe_buffer * @pipe: the pipe that the buffer belongs to * @buf: the buffer to get a reference to * * Description: * This function grabs an extra reference to @buf. It's used in * the tee() system call, when we duplicate the buffers in one * pipe into another. */ bool generic_pipe_buf_get(struct pipe_inode_info *pipe, struct pipe_buffer *buf) { return try_get_page(buf->page); } EXPORT_SYMBOL(generic_pipe_buf_get); /** * generic_pipe_buf_release - put a reference to a &struct pipe_buffer * @pipe: the pipe that the buffer belongs to * @buf: the buffer to put a reference to * * Description: * This function releases a reference to @buf. */ void generic_pipe_buf_release(struct pipe_inode_info *pipe, struct pipe_buffer *buf) { put_page(buf->page); } EXPORT_SYMBOL(generic_pipe_buf_release); static const struct pipe_buf_operations anon_pipe_buf_ops = { .release = anon_pipe_buf_release, .try_steal = anon_pipe_buf_try_steal, .get = generic_pipe_buf_get, }; /* Done while waiting without holding the pipe lock - thus the READ_ONCE() */ static inline bool pipe_readable(const struct pipe_inode_info *pipe) { unsigned int head = READ_ONCE(pipe->head); unsigned int tail = READ_ONCE(pipe->tail); unsigned int writers = READ_ONCE(pipe->writers); return !pipe_empty(head, tail) || !writers; } static inline unsigned int pipe_update_tail(struct pipe_inode_info *pipe, struct pipe_buffer *buf, unsigned int tail) { pipe_buf_release(pipe, buf); /* * If the pipe has a watch_queue, we need additional protection * by the spinlock because notifications get posted with only * this spinlock, no mutex */ if (pipe_has_watch_queue(pipe)) { spin_lock_irq(&pipe->rd_wait.lock); #ifdef CONFIG_WATCH_QUEUE if (buf->flags & PIPE_BUF_FLAG_LOSS) pipe->note_loss = true; #endif pipe->tail = ++tail; spin_unlock_irq(&pipe->rd_wait.lock); return tail; } /* * Without a watch_queue, we can simply increment the tail * without the spinlock - the mutex is enough. */ pipe->tail = ++tail; return tail; } static ssize_t pipe_read(struct kiocb *iocb, struct iov_iter *to) { size_t total_len = iov_iter_count(to); struct file *filp = iocb->ki_filp; struct pipe_inode_info *pipe = filp->private_data; bool was_full, wake_next_reader = false; ssize_t ret; /* Null read succeeds. */ if (unlikely(total_len == 0)) return 0; ret = 0; mutex_lock(&pipe->mutex); /* * We only wake up writers if the pipe was full when we started * reading in order to avoid unnecessary wakeups. * * But when we do wake up writers, we do so using a sync wakeup * (WF_SYNC), because we want them to get going and generate more * data for us. */ was_full = pipe_full(pipe->head, pipe->tail, pipe->max_usage); for (;;) { /* Read ->head with a barrier vs post_one_notification() */ unsigned int head = smp_load_acquire(&pipe->head); unsigned int tail = pipe->tail; unsigned int mask = pipe->ring_size - 1; #ifdef CONFIG_WATCH_QUEUE if (pipe->note_loss) { struct watch_notification n; if (total_len < 8) { if (ret == 0) ret = -ENOBUFS; break; } n.type = WATCH_TYPE_META; n.subtype = WATCH_META_LOSS_NOTIFICATION; n.info = watch_sizeof(n); if (copy_to_iter(&n, sizeof(n), to) != sizeof(n)) { if (ret == 0) ret = -EFAULT; break; } ret += sizeof(n); total_len -= sizeof(n); pipe->note_loss = false; } #endif if (!pipe_empty(head, tail)) { struct pipe_buffer *buf = &pipe->bufs[tail & mask]; size_t chars = buf->len; size_t written; int error; if (chars > total_len) { if (buf->flags & PIPE_BUF_FLAG_WHOLE) { if (ret == 0) ret = -ENOBUFS; break; } chars = total_len; } error = pipe_buf_confirm(pipe, buf); if (error) { if (!ret) ret = error; break; } written = copy_page_to_iter(buf->page, buf->offset, chars, to); if (unlikely(written < chars)) { if (!ret) ret = -EFAULT; break; } ret += chars; buf->offset += chars; buf->len -= chars; /* Was it a packet buffer? Clean up and exit */ if (buf->flags & PIPE_BUF_FLAG_PACKET) { total_len = chars; buf->len = 0; } if (!buf->len) tail = pipe_update_tail(pipe, buf, tail); total_len -= chars; if (!total_len) break; /* common path: read succeeded */ if (!pipe_empty(head, tail)) /* More to do? */ continue; } if (!pipe->writers) break; if (ret) break; if ((filp->f_flags & O_NONBLOCK) || (iocb->ki_flags & IOCB_NOWAIT)) { ret = -EAGAIN; break; } mutex_unlock(&pipe->mutex); /* * We only get here if we didn't actually read anything. * * However, we could have seen (and removed) a zero-sized * pipe buffer, and might have made space in the buffers * that way. * * You can't make zero-sized pipe buffers by doing an empty * write (not even in packet mode), but they can happen if * the writer gets an EFAULT when trying to fill a buffer * that already got allocated and inserted in the buffer * array. * * So we still need to wake up any pending writers in the * _very_ unlikely case that the pipe was full, but we got * no data. */ if (unlikely(was_full)) wake_up_interruptible_sync_poll(&pipe->wr_wait, EPOLLOUT | EPOLLWRNORM); kill_fasync(&pipe->fasync_writers, SIGIO, POLL_OUT); /* * But because we didn't read anything, at this point we can * just return directly with -ERESTARTSYS if we're interrupted, * since we've done any required wakeups and there's no need * to mark anything accessed. And we've dropped the lock. */ if (wait_event_interruptible_exclusive(pipe->rd_wait, pipe_readable(pipe)) < 0) return -ERESTARTSYS; mutex_lock(&pipe->mutex); was_full = pipe_full(pipe->head, pipe->tail, pipe->max_usage); wake_next_reader = true; } if (pipe_empty(pipe->head, pipe->tail)) wake_next_reader = false; mutex_unlock(&pipe->mutex); if (was_full) wake_up_interruptible_sync_poll(&pipe->wr_wait, EPOLLOUT | EPOLLWRNORM); if (wake_next_reader) wake_up_interruptible_sync_poll(&pipe->rd_wait, EPOLLIN | EPOLLRDNORM); kill_fasync(&pipe->fasync_writers, SIGIO, POLL_OUT); if (ret > 0) file_accessed(filp); return ret; } static inline int is_packetized(struct file *file) { return (file->f_flags & O_DIRECT) != 0; } /* Done while waiting without holding the pipe lock - thus the READ_ONCE() */ static inline bool pipe_writable(const struct pipe_inode_info *pipe) { unsigned int head = READ_ONCE(pipe->head); unsigned int tail = READ_ONCE(pipe->tail); unsigned int max_usage = READ_ONCE(pipe->max_usage); return !pipe_full(head, tail, max_usage) || !READ_ONCE(pipe->readers); } static ssize_t pipe_write(struct kiocb *iocb, struct iov_iter *from) { struct file *filp = iocb->ki_filp; struct pipe_inode_info *pipe = filp->private_data; unsigned int head; ssize_t ret = 0; size_t total_len = iov_iter_count(from); ssize_t chars; bool was_empty = false; bool wake_next_writer = false; /* * Reject writing to watch queue pipes before the point where we lock * the pipe. * Otherwise, lockdep would be unhappy if the caller already has another * pipe locked. * If we had to support locking a normal pipe and a notification pipe at * the same time, we could set up lockdep annotations for that, but * since we don't actually need that, it's simpler to just bail here. */ if (pipe_has_watch_queue(pipe)) return -EXDEV; /* Null write succeeds. */ if (unlikely(total_len == 0)) return 0; mutex_lock(&pipe->mutex); if (!pipe->readers) { send_sig(SIGPIPE, current, 0); ret = -EPIPE; goto out; } /* * If it wasn't empty we try to merge new data into * the last buffer. * * That naturally merges small writes, but it also * page-aligns the rest of the writes for large writes * spanning multiple pages. */ head = pipe->head; was_empty = pipe_empty(head, pipe->tail); chars = total_len & (PAGE_SIZE-1); if (chars && !was_empty) { unsigned int mask = pipe->ring_size - 1; struct pipe_buffer *buf = &pipe->bufs[(head - 1) & mask]; int offset = buf->offset + buf->len; if ((buf->flags & PIPE_BUF_FLAG_CAN_MERGE) && offset + chars <= PAGE_SIZE) { ret = pipe_buf_confirm(pipe, buf); if (ret) goto out; ret = copy_page_from_iter(buf->page, offset, chars, from); if (unlikely(ret < chars)) { ret = -EFAULT; goto out; } buf->len += ret; if (!iov_iter_count(from)) goto out; } } for (;;) { if (!pipe->readers) { send_sig(SIGPIPE, current, 0); if (!ret) ret = -EPIPE; break; } head = pipe->head; if (!pipe_full(head, pipe->tail, pipe->max_usage)) { unsigned int mask = pipe->ring_size - 1; struct pipe_buffer *buf; struct page *page = pipe->tmp_page; int copied; if (!page) { page = alloc_page(GFP_HIGHUSER | __GFP_ACCOUNT); if (unlikely(!page)) { ret = ret ? : -ENOMEM; break; } pipe->tmp_page = page; } /* Allocate a slot in the ring in advance and attach an * empty buffer. If we fault or otherwise fail to use * it, either the reader will consume it or it'll still * be there for the next write. */ pipe->head = head + 1; /* Insert it into the buffer array */ buf = &pipe->bufs[head & mask]; buf->page = page; buf->ops = &anon_pipe_buf_ops; buf->offset = 0; buf->len = 0; if (is_packetized(filp)) buf->flags = PIPE_BUF_FLAG_PACKET; else buf->flags = PIPE_BUF_FLAG_CAN_MERGE; pipe->tmp_page = NULL; copied = copy_page_from_iter(page, 0, PAGE_SIZE, from); if (unlikely(copied < PAGE_SIZE && iov_iter_count(from))) { if (!ret) ret = -EFAULT; break; } ret += copied; buf->len = copied; if (!iov_iter_count(from)) break; } if (!pipe_full(head, pipe->tail, pipe->max_usage)) continue; /* Wait for buffer space to become available. */ if ((filp->f_flags & O_NONBLOCK) || (iocb->ki_flags & IOCB_NOWAIT)) { if (!ret) ret = -EAGAIN; break; } if (signal_pending(current)) { if (!ret) ret = -ERESTARTSYS; break; } /* * We're going to release the pipe lock and wait for more * space. We wake up any readers if necessary, and then * after waiting we need to re-check whether the pipe * become empty while we dropped the lock. */ mutex_unlock(&pipe->mutex); if (was_empty) wake_up_interruptible_sync_poll(&pipe->rd_wait, EPOLLIN | EPOLLRDNORM); kill_fasync(&pipe->fasync_readers, SIGIO, POLL_IN); wait_event_interruptible_exclusive(pipe->wr_wait, pipe_writable(pipe)); mutex_lock(&pipe->mutex); was_empty = pipe_empty(pipe->head, pipe->tail); wake_next_writer = true; } out: if (pipe_full(pipe->head, pipe->tail, pipe->max_usage)) wake_next_writer = false; mutex_unlock(&pipe->mutex); /* * If we do do a wakeup event, we do a 'sync' wakeup, because we * want the reader to start processing things asap, rather than * leave the data pending. * * This is particularly important for small writes, because of * how (for example) the GNU make jobserver uses small writes to * wake up pending jobs * * Epoll nonsensically wants a wakeup whether the pipe * was already empty or not. */ if (was_empty || pipe->poll_usage) wake_up_interruptible_sync_poll(&pipe->rd_wait, EPOLLIN | EPOLLRDNORM); kill_fasync(&pipe->fasync_readers, SIGIO, POLL_IN); if (wake_next_writer) wake_up_interruptible_sync_poll(&pipe->wr_wait, EPOLLOUT | EPOLLWRNORM); if (ret > 0 && sb_start_write_trylock(file_inode(filp)->i_sb)) { int err = file_update_time(filp); if (err) ret = err; sb_end_write(file_inode(filp)->i_sb); } return ret; } static long pipe_ioctl(struct file *filp, unsigned int cmd, unsigned long arg) { struct pipe_inode_info *pipe = filp->private_data; unsigned int count, head, tail, mask; switch (cmd) { case FIONREAD: mutex_lock(&pipe->mutex); count = 0; head = pipe->head; tail = pipe->tail; mask = pipe->ring_size - 1; while (tail != head) { count += pipe->bufs[tail & mask].len; tail++; } mutex_unlock(&pipe->mutex); return put_user(count, (int __user *)arg); #ifdef CONFIG_WATCH_QUEUE case IOC_WATCH_QUEUE_SET_SIZE: { int ret; mutex_lock(&pipe->mutex); ret = watch_queue_set_size(pipe, arg); mutex_unlock(&pipe->mutex); return ret; } case IOC_WATCH_QUEUE_SET_FILTER: return watch_queue_set_filter( pipe, (struct watch_notification_filter __user *)arg); #endif default: return -ENOIOCTLCMD; } } /* No kernel lock held - fine */ static __poll_t pipe_poll(struct file *filp, poll_table *wait) { __poll_t mask; struct pipe_inode_info *pipe = filp->private_data; unsigned int head, tail; /* Epoll has some historical nasty semantics, this enables them */ WRITE_ONCE(pipe->poll_usage, true); /* * Reading pipe state only -- no need for acquiring the semaphore. * * But because this is racy, the code has to add the * entry to the poll table _first_ .. */ if (filp->f_mode & FMODE_READ) poll_wait(filp, &pipe->rd_wait, wait); if (filp->f_mode & FMODE_WRITE) poll_wait(filp, &pipe->wr_wait, wait); /* * .. and only then can you do the racy tests. That way, * if something changes and you got it wrong, the poll * table entry will wake you up and fix it. */ head = READ_ONCE(pipe->head); tail = READ_ONCE(pipe->tail); mask = 0; if (filp->f_mode & FMODE_READ) { if (!pipe_empty(head, tail)) mask |= EPOLLIN | EPOLLRDNORM; if (!pipe->writers && filp->f_pipe != pipe->w_counter) mask |= EPOLLHUP; } if (filp->f_mode & FMODE_WRITE) { if (!pipe_full(head, tail, pipe->max_usage)) mask |= EPOLLOUT | EPOLLWRNORM; /* * Most Unices do not set EPOLLERR for FIFOs but on Linux they * behave exactly like pipes for poll(). */ if (!pipe->readers) mask |= EPOLLERR; } return mask; } static void put_pipe_info(struct inode *inode, struct pipe_inode_info *pipe) { int kill = 0; spin_lock(&inode->i_lock); if (!--pipe->files) { inode->i_pipe = NULL; kill = 1; } spin_unlock(&inode->i_lock); if (kill) free_pipe_info(pipe); } static int pipe_release(struct inode *inode, struct file *file) { struct pipe_inode_info *pipe = file->private_data; mutex_lock(&pipe->mutex); if (file->f_mode & FMODE_READ) pipe->readers--; if (file->f_mode & FMODE_WRITE) pipe->writers--; /* Was that the last reader or writer, but not the other side? */ if (!pipe->readers != !pipe->writers) { wake_up_interruptible_all(&pipe->rd_wait); wake_up_interruptible_all(&pipe->wr_wait); kill_fasync(&pipe->fasync_readers, SIGIO, POLL_IN); kill_fasync(&pipe->fasync_writers, SIGIO, POLL_OUT); } mutex_unlock(&pipe->mutex); put_pipe_info(inode, pipe); return 0; } static int pipe_fasync(int fd, struct file *filp, int on) { struct pipe_inode_info *pipe = filp->private_data; int retval = 0; mutex_lock(&pipe->mutex); if (filp->f_mode & FMODE_READ) retval = fasync_helper(fd, filp, on, &pipe->fasync_readers); if ((filp->f_mode & FMODE_WRITE) && retval >= 0) { retval = fasync_helper(fd, filp, on, &pipe->fasync_writers); if (retval < 0 && (filp->f_mode & FMODE_READ)) /* this can happen only if on == T */ fasync_helper(-1, filp, 0, &pipe->fasync_readers); } mutex_unlock(&pipe->mutex); return retval; } unsigned long account_pipe_buffers(struct user_struct *user, unsigned long old, unsigned long new) { return atomic_long_add_return(new - old, &user->pipe_bufs); } bool too_many_pipe_buffers_soft(unsigned long user_bufs) { unsigned long soft_limit = READ_ONCE(pipe_user_pages_soft); return soft_limit && user_bufs > soft_limit; } bool too_many_pipe_buffers_hard(unsigned long user_bufs) { unsigned long hard_limit = READ_ONCE(pipe_user_pages_hard); return hard_limit && user_bufs > hard_limit; } bool pipe_is_unprivileged_user(void) { return !capable(CAP_SYS_RESOURCE) && !capable(CAP_SYS_ADMIN); } struct pipe_inode_info *alloc_pipe_info(void) { struct pipe_inode_info *pipe; unsigned long pipe_bufs = PIPE_DEF_BUFFERS; struct user_struct *user = get_current_user(); unsigned long user_bufs; unsigned int max_size = READ_ONCE(pipe_max_size); pipe = kzalloc(sizeof(struct pipe_inode_info), GFP_KERNEL_ACCOUNT); if (pipe == NULL) goto out_free_uid; if (pipe_bufs * PAGE_SIZE > max_size && !capable(CAP_SYS_RESOURCE)) pipe_bufs = max_size >> PAGE_SHIFT; user_bufs = account_pipe_buffers(user, 0, pipe_bufs); if (too_many_pipe_buffers_soft(user_bufs) && pipe_is_unprivileged_user()) { user_bufs = account_pipe_buffers(user, pipe_bufs, PIPE_MIN_DEF_BUFFERS); pipe_bufs = PIPE_MIN_DEF_BUFFERS; } if (too_many_pipe_buffers_hard(user_bufs) && pipe_is_unprivileged_user()) goto out_revert_acct; pipe->bufs = kcalloc(pipe_bufs, sizeof(struct pipe_buffer), GFP_KERNEL_ACCOUNT); if (pipe->bufs) { init_waitqueue_head(&pipe->rd_wait); init_waitqueue_head(&pipe->wr_wait); pipe->r_counter = pipe->w_counter = 1; pipe->max_usage = pipe_bufs; pipe->ring_size = pipe_bufs; pipe->nr_accounted = pipe_bufs; pipe->user = user; mutex_init(&pipe->mutex); lock_set_cmp_fn(&pipe->mutex, pipe_lock_cmp_fn, NULL); return pipe; } out_revert_acct: (void) account_pipe_buffers(user, pipe_bufs, 0); kfree(pipe); out_free_uid: free_uid(user); return NULL; } void free_pipe_info(struct pipe_inode_info *pipe) { unsigned int i; #ifdef CONFIG_WATCH_QUEUE if (pipe->watch_queue) watch_queue_clear(pipe->watch_queue); #endif (void) account_pipe_buffers(pipe->user, pipe->nr_accounted, 0); free_uid(pipe->user); for (i = 0; i < pipe->ring_size; i++) { struct pipe_buffer *buf = pipe->bufs + i; if (buf->ops) pipe_buf_release(pipe, buf); } #ifdef CONFIG_WATCH_QUEUE if (pipe->watch_queue) put_watch_queue(pipe->watch_queue); #endif if (pipe->tmp_page) __free_page(pipe->tmp_page); kfree(pipe->bufs); kfree(pipe); } static struct vfsmount *pipe_mnt __ro_after_init; /* * pipefs_dname() is called from d_path(). */ static char *pipefs_dname(struct dentry *dentry, char *buffer, int buflen) { return dynamic_dname(buffer, buflen, "pipe:[%lu]", d_inode(dentry)->i_ino); } static const struct dentry_operations pipefs_dentry_operations = { .d_dname = pipefs_dname, }; static struct inode * get_pipe_inode(void) { struct inode *inode = new_inode_pseudo(pipe_mnt->mnt_sb); struct pipe_inode_info *pipe; if (!inode) goto fail_inode; inode->i_ino = get_next_ino(); pipe = alloc_pipe_info(); if (!pipe) goto fail_iput; inode->i_pipe = pipe; pipe->files = 2; pipe->readers = pipe->writers = 1; inode->i_fop = &pipefifo_fops; /* * Mark the inode dirty from the very beginning, * that way it will never be moved to the dirty * list because "mark_inode_dirty()" will think * that it already _is_ on the dirty list. */ inode->i_state = I_DIRTY; inode->i_mode = S_IFIFO | S_IRUSR | S_IWUSR; inode->i_uid = current_fsuid(); inode->i_gid = current_fsgid(); simple_inode_init_ts(inode); return inode; fail_iput: iput(inode); fail_inode: return NULL; } int create_pipe_files(struct file **res, int flags) { struct inode *inode = get_pipe_inode(); struct file *f; int error; if (!inode) return -ENFILE; if (flags & O_NOTIFICATION_PIPE) { error = watch_queue_init(inode->i_pipe); if (error) { free_pipe_info(inode->i_pipe); iput(inode); return error; } } f = alloc_file_pseudo(inode, pipe_mnt, "", O_WRONLY | (flags & (O_NONBLOCK | O_DIRECT)), &pipefifo_fops); if (IS_ERR(f)) { free_pipe_info(inode->i_pipe); iput(inode); return PTR_ERR(f); } f->private_data = inode->i_pipe; f->f_pipe = 0; res[0] = alloc_file_clone(f, O_RDONLY | (flags & O_NONBLOCK), &pipefifo_fops); if (IS_ERR(res[0])) { put_pipe_info(inode, inode->i_pipe); fput(f); return PTR_ERR(res[0]); } res[0]->private_data = inode->i_pipe; res[0]->f_pipe = 0; res[1] = f; stream_open(inode, res[0]); stream_open(inode, res[1]); return 0; } static int __do_pipe_flags(int *fd, struct file **files, int flags) { int error; int fdw, fdr; if (flags & ~(O_CLOEXEC | O_NONBLOCK | O_DIRECT | O_NOTIFICATION_PIPE)) return -EINVAL; error = create_pipe_files(files, flags); if (error) return error; error = get_unused_fd_flags(flags); if (error < 0) goto err_read_pipe; fdr = error; error = get_unused_fd_flags(flags); if (error < 0) goto err_fdr; fdw = error; audit_fd_pair(fdr, fdw); fd[0] = fdr; fd[1] = fdw; /* pipe groks IOCB_NOWAIT */ files[0]->f_mode |= FMODE_NOWAIT; files[1]->f_mode |= FMODE_NOWAIT; return 0; err_fdr: put_unused_fd(fdr); err_read_pipe: fput(files[0]); fput(files[1]); return error; } int do_pipe_flags(int *fd, int flags) { struct file *files[2]; int error = __do_pipe_flags(fd, files, flags); if (!error) { fd_install(fd[0], files[0]); fd_install(fd[1], files[1]); } return error; } /* * sys_pipe() is the normal C calling standard for creating * a pipe. It's not the way Unix traditionally does this, though. */ static int do_pipe2(int __user *fildes, int flags) { struct file *files[2]; int fd[2]; int error; error = __do_pipe_flags(fd, files, flags); if (!error) { if (unlikely(copy_to_user(fildes, fd, sizeof(fd)))) { fput(files[0]); fput(files[1]); put_unused_fd(fd[0]); put_unused_fd(fd[1]); error = -EFAULT; } else { fd_install(fd[0], files[0]); fd_install(fd[1], files[1]); } } return error; } SYSCALL_DEFINE2(pipe2, int __user *, fildes, int, flags) { return do_pipe2(fildes, flags); } SYSCALL_DEFINE1(pipe, int __user *, fildes) { return do_pipe2(fildes, 0); } /* * This is the stupid "wait for pipe to be readable or writable" * model. * * See pipe_read/write() for the proper kind of exclusive wait, * but that requires that we wake up any other readers/writers * if we then do not end up reading everything (ie the whole * "wake_next_reader/writer" logic in pipe_read/write()). */ void pipe_wait_readable(struct pipe_inode_info *pipe) { pipe_unlock(pipe); wait_event_interruptible(pipe->rd_wait, pipe_readable(pipe)); pipe_lock(pipe); } void pipe_wait_writable(struct pipe_inode_info *pipe) { pipe_unlock(pipe); wait_event_interruptible(pipe->wr_wait, pipe_writable(pipe)); pipe_lock(pipe); } /* * This depends on both the wait (here) and the wakeup (wake_up_partner) * holding the pipe lock, so "*cnt" is stable and we know a wakeup cannot * race with the count check and waitqueue prep. * * Normally in order to avoid races, you'd do the prepare_to_wait() first, * then check the condition you're waiting for, and only then sleep. But * because of the pipe lock, we can check the condition before being on * the wait queue. * * We use the 'rd_wait' waitqueue for pipe partner waiting. */ static int wait_for_partner(struct pipe_inode_info *pipe, unsigned int *cnt) { DEFINE_WAIT(rdwait); int cur = *cnt; while (cur == *cnt) { prepare_to_wait(&pipe->rd_wait, &rdwait, TASK_INTERRUPTIBLE); pipe_unlock(pipe); schedule(); finish_wait(&pipe->rd_wait, &rdwait); pipe_lock(pipe); if (signal_pending(current)) break; } return cur == *cnt ? -ERESTARTSYS : 0; } static void wake_up_partner(struct pipe_inode_info *pipe) { wake_up_interruptible_all(&pipe->rd_wait); } static int fifo_open(struct inode *inode, struct file *filp) { struct pipe_inode_info *pipe; bool is_pipe = inode->i_sb->s_magic == PIPEFS_MAGIC; int ret; filp->f_pipe = 0; spin_lock(&inode->i_lock); if (inode->i_pipe) { pipe = inode->i_pipe; pipe->files++; spin_unlock(&inode->i_lock); } else { spin_unlock(&inode->i_lock); pipe = alloc_pipe_info(); if (!pipe) return -ENOMEM; pipe->files = 1; spin_lock(&inode->i_lock); if (unlikely(inode->i_pipe)) { inode->i_pipe->files++; spin_unlock(&inode->i_lock); free_pipe_info(pipe); pipe = inode->i_pipe; } else { inode->i_pipe = pipe; spin_unlock(&inode->i_lock); } } filp->private_data = pipe; /* OK, we have a pipe and it's pinned down */ mutex_lock(&pipe->mutex); /* We can only do regular read/write on fifos */ stream_open(inode, filp); switch (filp->f_mode & (FMODE_READ | FMODE_WRITE)) { case FMODE_READ: /* * O_RDONLY * POSIX.1 says that O_NONBLOCK means return with the FIFO * opened, even when there is no process writing the FIFO. */ pipe->r_counter++; if (pipe->readers++ == 0) wake_up_partner(pipe); if (!is_pipe && !pipe->writers) { if ((filp->f_flags & O_NONBLOCK)) { /* suppress EPOLLHUP until we have * seen a writer */ filp->f_pipe = pipe->w_counter; } else { if (wait_for_partner(pipe, &pipe->w_counter)) goto err_rd; } } break; case FMODE_WRITE: /* * O_WRONLY * POSIX.1 says that O_NONBLOCK means return -1 with * errno=ENXIO when there is no process reading the FIFO. */ ret = -ENXIO; if (!is_pipe && (filp->f_flags & O_NONBLOCK) && !pipe->readers) goto err; pipe->w_counter++; if (!pipe->writers++) wake_up_partner(pipe); if (!is_pipe && !pipe->readers) { if (wait_for_partner(pipe, &pipe->r_counter)) goto err_wr; } break; case FMODE_READ | FMODE_WRITE: /* * O_RDWR * POSIX.1 leaves this case "undefined" when O_NONBLOCK is set. * This implementation will NEVER block on a O_RDWR open, since * the process can at least talk to itself. */ pipe->readers++; pipe->writers++; pipe->r_counter++; pipe->w_counter++; if (pipe->readers == 1 || pipe->writers == 1) wake_up_partner(pipe); break; default: ret = -EINVAL; goto err; } /* Ok! */ mutex_unlock(&pipe->mutex); return 0; err_rd: if (!--pipe->readers) wake_up_interruptible(&pipe->wr_wait); ret = -ERESTARTSYS; goto err; err_wr: if (!--pipe->writers) wake_up_interruptible_all(&pipe->rd_wait); ret = -ERESTARTSYS; goto err; err: mutex_unlock(&pipe->mutex); put_pipe_info(inode, pipe); return ret; } const struct file_operations pipefifo_fops = { .open = fifo_open, .read_iter = pipe_read, .write_iter = pipe_write, .poll = pipe_poll, .unlocked_ioctl = pipe_ioctl, .release = pipe_release, .fasync = pipe_fasync, .splice_write = iter_file_splice_write, }; /* * Currently we rely on the pipe array holding a power-of-2 number * of pages. Returns 0 on error. */ unsigned int round_pipe_size(unsigned int size) { if (size > (1U << 31)) return 0; /* Minimum pipe size, as required by POSIX */ if (size < PAGE_SIZE) return PAGE_SIZE; return roundup_pow_of_two(size); } /* * Resize the pipe ring to a number of slots. * * Note the pipe can be reduced in capacity, but only if the current * occupancy doesn't exceed nr_slots; if it does, EBUSY will be * returned instead. */ int pipe_resize_ring(struct pipe_inode_info *pipe, unsigned int nr_slots) { struct pipe_buffer *bufs; unsigned int head, tail, mask, n; bufs = kcalloc(nr_slots, sizeof(*bufs), GFP_KERNEL_ACCOUNT | __GFP_NOWARN); if (unlikely(!bufs)) return -ENOMEM; spin_lock_irq(&pipe->rd_wait.lock); mask = pipe->ring_size - 1; head = pipe->head; tail = pipe->tail; n = pipe_occupancy(head, tail); if (nr_slots < n) { spin_unlock_irq(&pipe->rd_wait.lock); kfree(bufs); return -EBUSY; } /* * The pipe array wraps around, so just start the new one at zero * and adjust the indices. */ if (n > 0) { unsigned int h = head & mask; unsigned int t = tail & mask; if (h > t) { memcpy(bufs, pipe->bufs + t, n * sizeof(struct pipe_buffer)); } else { unsigned int tsize = pipe->ring_size - t; if (h > 0) memcpy(bufs + tsize, pipe->bufs, h * sizeof(struct pipe_buffer)); memcpy(bufs, pipe->bufs + t, tsize * sizeof(struct pipe_buffer)); } } head = n; tail = 0; kfree(pipe->bufs); pipe->bufs = bufs; pipe->ring_size = nr_slots; if (pipe->max_usage > nr_slots) pipe->max_usage = nr_slots; pipe->tail = tail; pipe->head = head; if (!pipe_has_watch_queue(pipe)) { pipe->max_usage = nr_slots; pipe->nr_accounted = nr_slots; } spin_unlock_irq(&pipe->rd_wait.lock); /* This might have made more room for writers */ wake_up_interruptible(&pipe->wr_wait); return 0; } /* * Allocate a new array of pipe buffers and copy the info over. Returns the * pipe size if successful, or return -ERROR on error. */ static long pipe_set_size(struct pipe_inode_info *pipe, unsigned int arg) { unsigned long user_bufs; unsigned int nr_slots, size; long ret = 0; if (pipe_has_watch_queue(pipe)) return -EBUSY; size = round_pipe_size(arg); nr_slots = size >> PAGE_SHIFT; if (!nr_slots) return -EINVAL; /* * If trying to increase the pipe capacity, check that an * unprivileged user is not trying to exceed various limits * (soft limit check here, hard limit check just below). * Decreasing the pipe capacity is always permitted, even * if the user is currently over a limit. */ if (nr_slots > pipe->max_usage && size > pipe_max_size && !capable(CAP_SYS_RESOURCE)) return -EPERM; user_bufs = account_pipe_buffers(pipe->user, pipe->nr_accounted, nr_slots); if (nr_slots > pipe->max_usage && (too_many_pipe_buffers_hard(user_bufs) || too_many_pipe_buffers_soft(user_bufs)) && pipe_is_unprivileged_user()) { ret = -EPERM; goto out_revert_acct; } ret = pipe_resize_ring(pipe, nr_slots); if (ret < 0) goto out_revert_acct; return pipe->max_usage * PAGE_SIZE; out_revert_acct: (void) account_pipe_buffers(pipe->user, nr_slots, pipe->nr_accounted); return ret; } /* * Note that i_pipe and i_cdev share the same location, so checking ->i_pipe is * not enough to verify that this is a pipe. */ struct pipe_inode_info *get_pipe_info(struct file *file, bool for_splice) { struct pipe_inode_info *pipe = file->private_data; if (file->f_op != &pipefifo_fops || !pipe) return NULL; if (for_splice && pipe_has_watch_queue(pipe)) return NULL; return pipe; } long pipe_fcntl(struct file *file, unsigned int cmd, unsigned int arg) { struct pipe_inode_info *pipe; long ret; pipe = get_pipe_info(file, false); if (!pipe) return -EBADF; mutex_lock(&pipe->mutex); switch (cmd) { case F_SETPIPE_SZ: ret = pipe_set_size(pipe, arg); break; case F_GETPIPE_SZ: ret = pipe->max_usage * PAGE_SIZE; break; default: ret = -EINVAL; break; } mutex_unlock(&pipe->mutex); return ret; } static const struct super_operations pipefs_ops = { .destroy_inode = free_inode_nonrcu, .statfs = simple_statfs, }; /* * pipefs should _never_ be mounted by userland - too much of security hassle, * no real gain from having the whole file system mounted. So we don't need * any operations on the root directory. However, we need a non-trivial * d_name - pipe: will go nicely and kill the special-casing in procfs. */ static int pipefs_init_fs_context(struct fs_context *fc) { struct pseudo_fs_context *ctx = init_pseudo(fc, PIPEFS_MAGIC); if (!ctx) return -ENOMEM; ctx->ops = &pipefs_ops; ctx->dops = &pipefs_dentry_operations; return 0; } static struct file_system_type pipe_fs_type = { .name = "pipefs", .init_fs_context = pipefs_init_fs_context, .kill_sb = kill_anon_super, }; #ifdef CONFIG_SYSCTL static int do_proc_dopipe_max_size_conv(unsigned long *lvalp, unsigned int *valp, int write, void *data) { if (write) { unsigned int val; val = round_pipe_size(*lvalp); if (val == 0) return -EINVAL; *valp = val; } else { unsigned int val = *valp; *lvalp = (unsigned long) val; } return 0; } static int proc_dopipe_max_size(const struct ctl_table *table, int write, void *buffer, size_t *lenp, loff_t *ppos) { return do_proc_douintvec(table, write, buffer, lenp, ppos, do_proc_dopipe_max_size_conv, NULL); } static struct ctl_table fs_pipe_sysctls[] = { { .procname = "pipe-max-size", .data = &pipe_max_size, .maxlen = sizeof(pipe_max_size), .mode = 0644, .proc_handler = proc_dopipe_max_size, }, { .procname = "pipe-user-pages-hard", .data = &pipe_user_pages_hard, .maxlen = sizeof(pipe_user_pages_hard), .mode = 0644, .proc_handler = proc_doulongvec_minmax, }, { .procname = "pipe-user-pages-soft", .data = &pipe_user_pages_soft, .maxlen = sizeof(pipe_user_pages_soft), .mode = 0644, .proc_handler = proc_doulongvec_minmax, }, }; #endif static int __init init_pipe_fs(void) { int err = register_filesystem(&pipe_fs_type); if (!err) { pipe_mnt = kern_mount(&pipe_fs_type); if (IS_ERR(pipe_mnt)) { err = PTR_ERR(pipe_mnt); unregister_filesystem(&pipe_fs_type); } } #ifdef CONFIG_SYSCTL register_sysctl_init("fs", fs_pipe_sysctls); #endif return err; } fs_initcall(init_pipe_fs); |
| 1086 1087 1088 1088 1084 36 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 | /* SPDX-License-Identifier: GPL-2.0+ */ /* * Sleepable Read-Copy Update mechanism for mutual exclusion * * Copyright (C) IBM Corporation, 2006 * Copyright (C) Fujitsu, 2012 * * Author: Paul McKenney <paulmck@linux.ibm.com> * Lai Jiangshan <laijs@cn.fujitsu.com> * * For detailed explanation of Read-Copy Update mechanism see - * Documentation/RCU/ *.txt * */ #ifndef _LINUX_SRCU_H #define _LINUX_SRCU_H #include <linux/mutex.h> #include <linux/rcupdate.h> #include <linux/workqueue.h> #include <linux/rcu_segcblist.h> struct srcu_struct; #ifdef CONFIG_DEBUG_LOCK_ALLOC int __init_srcu_struct(struct srcu_struct *ssp, const char *name, struct lock_class_key *key); #define init_srcu_struct(ssp) \ ({ \ static struct lock_class_key __srcu_key; \ \ __init_srcu_struct((ssp), #ssp, &__srcu_key); \ }) #define __SRCU_DEP_MAP_INIT(srcu_name) .dep_map = { .name = #srcu_name }, #else /* #ifdef CONFIG_DEBUG_LOCK_ALLOC */ int init_srcu_struct(struct srcu_struct *ssp); #define __SRCU_DEP_MAP_INIT(srcu_name) #endif /* #else #ifdef CONFIG_DEBUG_LOCK_ALLOC */ #ifdef CONFIG_TINY_SRCU #include <linux/srcutiny.h> #elif defined(CONFIG_TREE_SRCU) #include <linux/srcutree.h> #else #error "Unknown SRCU implementation specified to kernel configuration" #endif void call_srcu(struct srcu_struct *ssp, struct rcu_head *head, void (*func)(struct rcu_head *head)); void cleanup_srcu_struct(struct srcu_struct *ssp); int __srcu_read_lock(struct srcu_struct *ssp) __acquires(ssp); void __srcu_read_unlock(struct srcu_struct *ssp, int idx) __releases(ssp); #ifdef CONFIG_TINY_SRCU #define __srcu_read_lock_lite __srcu_read_lock #define __srcu_read_unlock_lite __srcu_read_unlock #else // #ifdef CONFIG_TINY_SRCU int __srcu_read_lock_lite(struct srcu_struct *ssp) __acquires(ssp); void __srcu_read_unlock_lite(struct srcu_struct *ssp, int idx) __releases(ssp); #endif // #else // #ifdef CONFIG_TINY_SRCU void synchronize_srcu(struct srcu_struct *ssp); #define SRCU_GET_STATE_COMPLETED 0x1 /** * get_completed_synchronize_srcu - Return a pre-completed polled state cookie * * Returns a value that poll_state_synchronize_srcu() will always treat * as a cookie whose grace period has already completed. */ static inline unsigned long get_completed_synchronize_srcu(void) { return SRCU_GET_STATE_COMPLETED; } unsigned long get_state_synchronize_srcu(struct srcu_struct *ssp); unsigned long start_poll_synchronize_srcu(struct srcu_struct *ssp); bool poll_state_synchronize_srcu(struct srcu_struct *ssp, unsigned long cookie); // Maximum number of unsigned long values corresponding to // not-yet-completed SRCU grace periods. #define NUM_ACTIVE_SRCU_POLL_OLDSTATE 2 /** * same_state_synchronize_srcu - Are two old-state values identical? * @oldstate1: First old-state value. * @oldstate2: Second old-state value. * * The two old-state values must have been obtained from either * get_state_synchronize_srcu(), start_poll_synchronize_srcu(), or * get_completed_synchronize_srcu(). Returns @true if the two values are * identical and @false otherwise. This allows structures whose lifetimes * are tracked by old-state values to push these values to a list header, * allowing those structures to be slightly smaller. */ static inline bool same_state_synchronize_srcu(unsigned long oldstate1, unsigned long oldstate2) { return oldstate1 == oldstate2; } #ifdef CONFIG_NEED_SRCU_NMI_SAFE int __srcu_read_lock_nmisafe(struct srcu_struct *ssp) __acquires(ssp); void __srcu_read_unlock_nmisafe(struct srcu_struct *ssp, int idx) __releases(ssp); #else static inline int __srcu_read_lock_nmisafe(struct srcu_struct *ssp) { return __srcu_read_lock(ssp); } static inline void __srcu_read_unlock_nmisafe(struct srcu_struct *ssp, int idx) { __srcu_read_unlock(ssp, idx); } #endif /* CONFIG_NEED_SRCU_NMI_SAFE */ void srcu_init(void); #ifdef CONFIG_DEBUG_LOCK_ALLOC /** * srcu_read_lock_held - might we be in SRCU read-side critical section? * @ssp: The srcu_struct structure to check * * If CONFIG_DEBUG_LOCK_ALLOC is selected, returns nonzero iff in an SRCU * read-side critical section. In absence of CONFIG_DEBUG_LOCK_ALLOC, * this assumes we are in an SRCU read-side critical section unless it can * prove otherwise. * * Checks debug_lockdep_rcu_enabled() to prevent false positives during boot * and while lockdep is disabled. * * Note that SRCU is based on its own statemachine and it doesn't * relies on normal RCU, it can be called from the CPU which * is in the idle loop from an RCU point of view or offline. */ static inline int srcu_read_lock_held(const struct srcu_struct *ssp) { if (!debug_lockdep_rcu_enabled()) return 1; return lock_is_held(&ssp->dep_map); } /* * Annotations provide deadlock detection for SRCU. * * Similar to other lockdep annotations, except there is an additional * srcu_lock_sync(), which is basically an empty *write*-side critical section, * see lock_sync() for more information. */ /* Annotates a srcu_read_lock() */ static inline void srcu_lock_acquire(struct lockdep_map *map) { lock_map_acquire_read(map); } /* Annotates a srcu_read_lock() */ static inline void srcu_lock_release(struct lockdep_map *map) { lock_map_release(map); } /* Annotates a synchronize_srcu() */ static inline void srcu_lock_sync(struct lockdep_map *map) { lock_map_sync(map); } #else /* #ifdef CONFIG_DEBUG_LOCK_ALLOC */ static inline int srcu_read_lock_held(const struct srcu_struct *ssp) { return 1; } #define srcu_lock_acquire(m) do { } while (0) #define srcu_lock_release(m) do { } while (0) #define srcu_lock_sync(m) do { } while (0) #endif /* #else #ifdef CONFIG_DEBUG_LOCK_ALLOC */ /** * srcu_dereference_check - fetch SRCU-protected pointer for later dereferencing * @p: the pointer to fetch and protect for later dereferencing * @ssp: pointer to the srcu_struct, which is used to check that we * really are in an SRCU read-side critical section. * @c: condition to check for update-side use * * If PROVE_RCU is enabled, invoking this outside of an RCU read-side * critical section will result in an RCU-lockdep splat, unless @c evaluates * to 1. The @c argument will normally be a logical expression containing * lockdep_is_held() calls. */ #define srcu_dereference_check(p, ssp, c) \ __rcu_dereference_check((p), __UNIQUE_ID(rcu), \ (c) || srcu_read_lock_held(ssp), __rcu) /** * srcu_dereference - fetch SRCU-protected pointer for later dereferencing * @p: the pointer to fetch and protect for later dereferencing * @ssp: pointer to the srcu_struct, which is used to check that we * really are in an SRCU read-side critical section. * * Makes rcu_dereference_check() do the dirty work. If PROVE_RCU * is enabled, invoking this outside of an RCU read-side critical * section will result in an RCU-lockdep splat. */ #define srcu_dereference(p, ssp) srcu_dereference_check((p), (ssp), 0) /** * srcu_dereference_notrace - no tracing and no lockdep calls from here * @p: the pointer to fetch and protect for later dereferencing * @ssp: pointer to the srcu_struct, which is used to check that we * really are in an SRCU read-side critical section. */ #define srcu_dereference_notrace(p, ssp) srcu_dereference_check((p), (ssp), 1) /** * srcu_read_lock - register a new reader for an SRCU-protected structure. * @ssp: srcu_struct in which to register the new reader. * * Enter an SRCU read-side critical section. Note that SRCU read-side * critical sections may be nested. However, it is illegal to * call anything that waits on an SRCU grace period for the same * srcu_struct, whether directly or indirectly. Please note that * one way to indirectly wait on an SRCU grace period is to acquire * a mutex that is held elsewhere while calling synchronize_srcu() or * synchronize_srcu_expedited(). * * The return value from srcu_read_lock() must be passed unaltered * to the matching srcu_read_unlock(). Note that srcu_read_lock() and * the matching srcu_read_unlock() must occur in the same context, for * example, it is illegal to invoke srcu_read_unlock() in an irq handler * if the matching srcu_read_lock() was invoked in process context. Or, * for that matter to invoke srcu_read_unlock() from one task and the * matching srcu_read_lock() from another. */ static inline int srcu_read_lock(struct srcu_struct *ssp) __acquires(ssp) { int retval; srcu_check_read_flavor(ssp, SRCU_READ_FLAVOR_NORMAL); retval = __srcu_read_lock(ssp); srcu_lock_acquire(&ssp->dep_map); return retval; } /** * srcu_read_lock_lite - register a new reader for an SRCU-protected structure. * @ssp: srcu_struct in which to register the new reader. * * Enter an SRCU read-side critical section, but for a light-weight * smp_mb()-free reader. See srcu_read_lock() for more information. * * If srcu_read_lock_lite() is ever used on an srcu_struct structure, * then none of the other flavors may be used, whether before, during, * or after. Note that grace-period auto-expediting is disabled for _lite * srcu_struct structures because auto-expedited grace periods invoke * synchronize_rcu_expedited(), IPIs and all. * * Note that srcu_read_lock_lite() can be invoked only from those contexts * where RCU is watching, that is, from contexts where it would be legal * to invoke rcu_read_lock(). Otherwise, lockdep will complain. */ static inline int srcu_read_lock_lite(struct srcu_struct *ssp) __acquires(ssp) { int retval; srcu_check_read_flavor_lite(ssp); retval = __srcu_read_lock_lite(ssp); rcu_try_lock_acquire(&ssp->dep_map); return retval; } /** * srcu_read_lock_nmisafe - register a new reader for an SRCU-protected structure. * @ssp: srcu_struct in which to register the new reader. * * Enter an SRCU read-side critical section, but in an NMI-safe manner. * See srcu_read_lock() for more information. * * If srcu_read_lock_nmisafe() is ever used on an srcu_struct structure, * then none of the other flavors may be used, whether before, during, * or after. */ static inline int srcu_read_lock_nmisafe(struct srcu_struct *ssp) __acquires(ssp) { int retval; srcu_check_read_flavor(ssp, SRCU_READ_FLAVOR_NMI); retval = __srcu_read_lock_nmisafe(ssp); rcu_try_lock_acquire(&ssp->dep_map); return retval; } /* Used by tracing, cannot be traced and cannot invoke lockdep. */ static inline notrace int srcu_read_lock_notrace(struct srcu_struct *ssp) __acquires(ssp) { int retval; srcu_check_read_flavor(ssp, SRCU_READ_FLAVOR_NORMAL); retval = __srcu_read_lock(ssp); return retval; } /** * srcu_down_read - register a new reader for an SRCU-protected structure. * @ssp: srcu_struct in which to register the new reader. * * Enter a semaphore-like SRCU read-side critical section. Note that * SRCU read-side critical sections may be nested. However, it is * illegal to call anything that waits on an SRCU grace period for the * same srcu_struct, whether directly or indirectly. Please note that * one way to indirectly wait on an SRCU grace period is to acquire * a mutex that is held elsewhere while calling synchronize_srcu() or * synchronize_srcu_expedited(). But if you want lockdep to help you * keep this stuff straight, you should instead use srcu_read_lock(). * * The semaphore-like nature of srcu_down_read() means that the matching * srcu_up_read() can be invoked from some other context, for example, * from some other task or from an irq handler. However, neither * srcu_down_read() nor srcu_up_read() may be invoked from an NMI handler. * * Calls to srcu_down_read() may be nested, similar to the manner in * which calls to down_read() may be nested. */ static inline int srcu_down_read(struct srcu_struct *ssp) __acquires(ssp) { WARN_ON_ONCE(in_nmi()); srcu_check_read_flavor(ssp, SRCU_READ_FLAVOR_NORMAL); return __srcu_read_lock(ssp); } /** * srcu_read_unlock - unregister a old reader from an SRCU-protected structure. * @ssp: srcu_struct in which to unregister the old reader. * @idx: return value from corresponding srcu_read_lock(). * * Exit an SRCU read-side critical section. */ static inline void srcu_read_unlock(struct srcu_struct *ssp, int idx) __releases(ssp) { WARN_ON_ONCE(idx & ~0x1); srcu_check_read_flavor(ssp, SRCU_READ_FLAVOR_NORMAL); srcu_lock_release(&ssp->dep_map); __srcu_read_unlock(ssp, idx); } /** * srcu_read_unlock_lite - unregister a old reader from an SRCU-protected structure. * @ssp: srcu_struct in which to unregister the old reader. * @idx: return value from corresponding srcu_read_lock(). * * Exit a light-weight SRCU read-side critical section. */ static inline void srcu_read_unlock_lite(struct srcu_struct *ssp, int idx) __releases(ssp) { WARN_ON_ONCE(idx & ~0x1); srcu_check_read_flavor(ssp, SRCU_READ_FLAVOR_LITE); srcu_lock_release(&ssp->dep_map); __srcu_read_unlock_lite(ssp, idx); } /** * srcu_read_unlock_nmisafe - unregister a old reader from an SRCU-protected structure. * @ssp: srcu_struct in which to unregister the old reader. * @idx: return value from corresponding srcu_read_lock(). * * Exit an SRCU read-side critical section, but in an NMI-safe manner. */ static inline void srcu_read_unlock_nmisafe(struct srcu_struct *ssp, int idx) __releases(ssp) { WARN_ON_ONCE(idx & ~0x1); srcu_check_read_flavor(ssp, SRCU_READ_FLAVOR_NMI); rcu_lock_release(&ssp->dep_map); __srcu_read_unlock_nmisafe(ssp, idx); } /* Used by tracing, cannot be traced and cannot call lockdep. */ static inline notrace void srcu_read_unlock_notrace(struct srcu_struct *ssp, int idx) __releases(ssp) { srcu_check_read_flavor(ssp, SRCU_READ_FLAVOR_NORMAL); __srcu_read_unlock(ssp, idx); } /** * srcu_up_read - unregister a old reader from an SRCU-protected structure. * @ssp: srcu_struct in which to unregister the old reader. * @idx: return value from corresponding srcu_read_lock(). * * Exit an SRCU read-side critical section, but not necessarily from * the same context as the maching srcu_down_read(). */ static inline void srcu_up_read(struct srcu_struct *ssp, int idx) __releases(ssp) { WARN_ON_ONCE(idx & ~0x1); WARN_ON_ONCE(in_nmi()); srcu_check_read_flavor(ssp, SRCU_READ_FLAVOR_NORMAL); __srcu_read_unlock(ssp, idx); } /** * smp_mb__after_srcu_read_unlock - ensure full ordering after srcu_read_unlock * * Converts the preceding srcu_read_unlock into a two-way memory barrier. * * Call this after srcu_read_unlock, to guarantee that all memory operations * that occur after smp_mb__after_srcu_read_unlock will appear to happen after * the preceding srcu_read_unlock. */ static inline void smp_mb__after_srcu_read_unlock(void) { /* __srcu_read_unlock has smp_mb() internally so nothing to do here. */ } /** * smp_mb__after_srcu_read_lock - ensure full ordering after srcu_read_lock * * Converts the preceding srcu_read_lock into a two-way memory barrier. * * Call this after srcu_read_lock, to guarantee that all memory operations * that occur after smp_mb__after_srcu_read_lock will appear to happen after * the preceding srcu_read_lock. */ static inline void smp_mb__after_srcu_read_lock(void) { /* __srcu_read_lock has smp_mb() internally so nothing to do here. */ } DEFINE_LOCK_GUARD_1(srcu, struct srcu_struct, _T->idx = srcu_read_lock(_T->lock), srcu_read_unlock(_T->lock, _T->idx), int idx) #endif |
| 14 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 | /* SPDX-License-Identifier: GPL-2.0 */ /* * Statically sized hash table implementation * (C) 2012 Sasha Levin <levinsasha928@gmail.com> */ #ifndef _LINUX_HASHTABLE_H #define _LINUX_HASHTABLE_H #include <linux/list.h> #include <linux/types.h> #include <linux/kernel.h> #include <linux/hash.h> #include <linux/rculist.h> #define DEFINE_HASHTABLE(name, bits) \ struct hlist_head name[1 << (bits)] = \ { [0 ... ((1 << (bits)) - 1)] = HLIST_HEAD_INIT } #define DEFINE_READ_MOSTLY_HASHTABLE(name, bits) \ struct hlist_head name[1 << (bits)] __read_mostly = \ { [0 ... ((1 << (bits)) - 1)] = HLIST_HEAD_INIT } #define DECLARE_HASHTABLE(name, bits) \ struct hlist_head name[1 << (bits)] #define HASH_SIZE(name) (ARRAY_SIZE(name)) #define HASH_BITS(name) ilog2(HASH_SIZE(name)) /* Use hash_32 when possible to allow for fast 32bit hashing in 64bit kernels. */ #define hash_min(val, bits) \ (sizeof(val) <= 4 ? hash_32(val, bits) : hash_long(val, bits)) static inline void __hash_init(struct hlist_head *ht, unsigned int sz) { unsigned int i; for (i = 0; i < sz; i++) INIT_HLIST_HEAD(&ht[i]); } /** * hash_init - initialize a hash table * @hashtable: hashtable to be initialized * * Calculates the size of the hashtable from the given parameter, otherwise * same as hash_init_size. * * This has to be a macro since HASH_BITS() will not work on pointers since * it calculates the size during preprocessing. */ #define hash_init(hashtable) __hash_init(hashtable, HASH_SIZE(hashtable)) /** * hash_add - add an object to a hashtable * @hashtable: hashtable to add to * @node: the &struct hlist_node of the object to be added * @key: the key of the object to be added */ #define hash_add(hashtable, node, key) \ hlist_add_head(node, &hashtable[hash_min(key, HASH_BITS(hashtable))]) /** * hash_add_rcu - add an object to a rcu enabled hashtable * @hashtable: hashtable to add to * @node: the &struct hlist_node of the object to be added * @key: the key of the object to be added */ #define hash_add_rcu(hashtable, node, key) \ hlist_add_head_rcu(node, &hashtable[hash_min(key, HASH_BITS(hashtable))]) /** * hash_hashed - check whether an object is in any hashtable * @node: the &struct hlist_node of the object to be checked */ static inline bool hash_hashed(struct hlist_node *node) { return !hlist_unhashed(node); } static inline bool __hash_empty(struct hlist_head *ht, unsigned int sz) { unsigned int i; for (i = 0; i < sz; i++) if (!hlist_empty(&ht[i])) return false; return true; } /** * hash_empty - check whether a hashtable is empty * @hashtable: hashtable to check * * This has to be a macro since HASH_BITS() will not work on pointers since * it calculates the size during preprocessing. */ #define hash_empty(hashtable) __hash_empty(hashtable, HASH_SIZE(hashtable)) /** * hash_del - remove an object from a hashtable * @node: &struct hlist_node of the object to remove */ static inline void hash_del(struct hlist_node *node) { hlist_del_init(node); } /** * hash_del_rcu - remove an object from a rcu enabled hashtable * @node: &struct hlist_node of the object to remove */ static inline void hash_del_rcu(struct hlist_node *node) { hlist_del_init_rcu(node); } /** * hash_for_each - iterate over a hashtable * @name: hashtable to iterate * @bkt: integer to use as bucket loop cursor * @obj: the type * to use as a loop cursor for each entry * @member: the name of the hlist_node within the struct */ #define hash_for_each(name, bkt, obj, member) \ for ((bkt) = 0, obj = NULL; obj == NULL && (bkt) < HASH_SIZE(name);\ (bkt)++)\ hlist_for_each_entry(obj, &name[bkt], member) /** * hash_for_each_rcu - iterate over a rcu enabled hashtable * @name: hashtable to iterate * @bkt: integer to use as bucket loop cursor * @obj: the type * to use as a loop cursor for each entry * @member: the name of the hlist_node within the struct */ #define hash_for_each_rcu(name, bkt, obj, member) \ for ((bkt) = 0, obj = NULL; obj == NULL && (bkt) < HASH_SIZE(name);\ (bkt)++)\ hlist_for_each_entry_rcu(obj, &name[bkt], member) /** * hash_for_each_safe - iterate over a hashtable safe against removal of * hash entry * @name: hashtable to iterate * @bkt: integer to use as bucket loop cursor * @tmp: a &struct hlist_node used for temporary storage * @obj: the type * to use as a loop cursor for each entry * @member: the name of the hlist_node within the struct */ #define hash_for_each_safe(name, bkt, tmp, obj, member) \ for ((bkt) = 0, obj = NULL; obj == NULL && (bkt) < HASH_SIZE(name);\ (bkt)++)\ hlist_for_each_entry_safe(obj, tmp, &name[bkt], member) /** * hash_for_each_possible - iterate over all possible objects hashing to the * same bucket * @name: hashtable to iterate * @obj: the type * to use as a loop cursor for each entry * @member: the name of the hlist_node within the struct * @key: the key of the objects to iterate over */ #define hash_for_each_possible(name, obj, member, key) \ hlist_for_each_entry(obj, &name[hash_min(key, HASH_BITS(name))], member) /** * hash_for_each_possible_rcu - iterate over all possible objects hashing to the * same bucket in an rcu enabled hashtable * @name: hashtable to iterate * @obj: the type * to use as a loop cursor for each entry * @member: the name of the hlist_node within the struct * @key: the key of the objects to iterate over */ #define hash_for_each_possible_rcu(name, obj, member, key, cond...) \ hlist_for_each_entry_rcu(obj, &name[hash_min(key, HASH_BITS(name))],\ member, ## cond) /** * hash_for_each_possible_rcu_notrace - iterate over all possible objects hashing * to the same bucket in an rcu enabled hashtable in a rcu enabled hashtable * @name: hashtable to iterate * @obj: the type * to use as a loop cursor for each entry * @member: the name of the hlist_node within the struct * @key: the key of the objects to iterate over * * This is the same as hash_for_each_possible_rcu() except that it does * not do any RCU debugging or tracing. */ #define hash_for_each_possible_rcu_notrace(name, obj, member, key) \ hlist_for_each_entry_rcu_notrace(obj, \ &name[hash_min(key, HASH_BITS(name))], member) /** * hash_for_each_possible_safe - iterate over all possible objects hashing to the * same bucket safe against removals * @name: hashtable to iterate * @obj: the type * to use as a loop cursor for each entry * @tmp: a &struct hlist_node used for temporary storage * @member: the name of the hlist_node within the struct * @key: the key of the objects to iterate over */ #define hash_for_each_possible_safe(name, obj, tmp, member, key) \ hlist_for_each_entry_safe(obj, tmp,\ &name[hash_min(key, HASH_BITS(name))], member) #endif |
| 484 8 8 4 1 485 64 64 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 1522 1523 1524 1525 1526 1527 1528 1529 1530 1531 1532 1533 1534 1535 1536 1537 1538 1539 1540 1541 1542 1543 1544 1545 1546 1547 1548 1549 1550 1551 1552 1553 1554 1555 1556 1557 1558 1559 1560 1561 1562 1563 1564 1565 1566 1567 1568 1569 1570 1571 1572 1573 1574 1575 1576 1577 1578 1579 1580 1581 1582 1583 1584 1585 1586 1587 1588 1589 1590 1591 1592 1593 1594 1595 1596 1597 1598 1599 1600 1601 1602 1603 1604 1605 1606 1607 1608 1609 1610 1611 1612 1613 1614 1615 1616 1617 1618 1619 1620 1621 1622 1623 1624 1625 1626 1627 1628 1629 1630 1631 1632 1633 1634 1635 1636 1637 1638 1639 1640 1641 1642 1643 1644 1645 1646 1647 1648 1649 1650 1651 1652 1653 1654 1655 1656 1657 1658 1659 1660 1661 1662 1663 1664 1665 1666 1667 1668 1669 1670 1671 1672 1673 1674 1675 1676 1677 1678 1679 1680 1681 1682 1683 1684 1685 1686 1687 1688 1689 1690 1691 1692 1693 1694 1695 1696 1697 1698 1699 1700 1701 1702 1703 1704 1705 1706 1707 1708 1709 1710 1711 1712 1713 1714 1715 1716 1717 1718 1719 1720 1721 1722 1723 1724 1725 1726 1727 1728 1729 1730 1731 1732 1733 1734 1735 1736 1737 1738 1739 1740 1741 1742 1743 1744 1745 1746 1747 1748 1749 1750 1751 1752 1753 1754 1755 1756 1757 1758 1759 1760 1761 1762 1763 1764 1765 1766 1767 1768 1769 1770 1771 1772 1773 1774 1775 1776 1777 1778 1779 1780 1781 1782 1783 1784 1785 1786 1787 1788 1789 1790 1791 1792 1793 1794 1795 1796 1797 1798 1799 1800 1801 1802 1803 1804 1805 1806 1807 1808 1809 1810 1811 1812 1813 1814 1815 1816 1817 1818 1819 1820 1821 1822 1823 1824 1825 1826 1827 1828 1829 1830 1831 1832 1833 1834 1835 1836 1837 1838 1839 1840 1841 1842 1843 1844 1845 1846 1847 1848 1849 1850 1851 1852 1853 1854 1855 1856 1857 1858 1859 1860 1861 1862 1863 1864 1865 1866 1867 1868 1869 1870 1871 1872 1873 1874 1875 1876 1877 1878 1879 1880 1881 1882 1883 1884 1885 1886 1887 1888 1889 1890 1891 1892 1893 1894 1895 1896 1897 1898 1899 1900 1901 1902 1903 1904 1905 1906 1907 1908 1909 1910 1911 1912 1913 1914 1915 1916 1917 1918 1919 1920 1921 1922 1923 1924 1925 1926 1927 1928 1929 1930 1931 1932 1933 1934 1935 1936 1937 1938 1939 1940 1941 1942 1943 1944 1945 1946 1947 1948 1949 1950 1951 1952 1953 1954 1955 1956 1957 1958 1959 1960 1961 1962 1963 1964 1965 1966 1967 1968 1969 1970 1971 1972 1973 1974 1975 1976 1977 1978 1979 1980 1981 1982 1983 1984 1985 1986 1987 1988 1989 1990 1991 1992 1993 1994 1995 1996 1997 1998 1999 2000 2001 2002 2003 2004 2005 2006 2007 2008 2009 2010 2011 2012 2013 2014 2015 2016 2017 2018 2019 2020 2021 2022 2023 2024 2025 2026 2027 2028 2029 2030 2031 2032 2033 2034 2035 2036 2037 2038 2039 2040 2041 2042 2043 2044 2045 2046 2047 2048 2049 2050 2051 2052 2053 2054 2055 2056 2057 2058 2059 2060 2061 2062 2063 2064 2065 2066 2067 2068 2069 2070 2071 2072 2073 2074 2075 2076 2077 2078 2079 2080 2081 2082 2083 2084 2085 2086 2087 2088 2089 2090 2091 2092 2093 2094 2095 2096 2097 2098 2099 2100 2101 2102 2103 2104 2105 2106 2107 2108 2109 2110 2111 2112 2113 2114 2115 2116 2117 2118 2119 2120 2121 2122 2123 2124 2125 2126 2127 2128 2129 2130 2131 2132 2133 2134 2135 2136 2137 2138 2139 2140 2141 2142 2143 2144 2145 2146 2147 2148 2149 2150 2151 2152 2153 2154 2155 2156 2157 2158 2159 2160 2161 2162 2163 2164 2165 2166 2167 2168 2169 2170 2171 2172 2173 2174 2175 2176 2177 2178 2179 2180 2181 2182 2183 2184 2185 2186 2187 2188 2189 2190 2191 2192 2193 2194 2195 2196 2197 2198 2199 2200 2201 2202 2203 2204 2205 2206 2207 2208 2209 2210 2211 2212 2213 2214 2215 2216 2217 2218 2219 2220 2221 2222 2223 2224 2225 2226 2227 2228 2229 2230 2231 2232 2233 2234 2235 2236 2237 2238 2239 2240 2241 2242 2243 2244 2245 2246 2247 2248 2249 2250 2251 2252 2253 2254 2255 2256 2257 2258 2259 2260 2261 2262 2263 2264 2265 2266 2267 2268 2269 2270 2271 2272 2273 2274 2275 2276 2277 2278 2279 2280 2281 2282 2283 2284 2285 2286 2287 2288 2289 2290 2291 2292 2293 2294 2295 2296 2297 2298 2299 2300 2301 2302 2303 2304 2305 2306 2307 2308 2309 2310 2311 2312 2313 2314 2315 2316 2317 2318 2319 2320 2321 2322 2323 2324 2325 2326 2327 2328 2329 2330 2331 2332 2333 2334 2335 2336 2337 2338 2339 2340 2341 2342 2343 2344 2345 2346 2347 2348 2349 2350 2351 2352 2353 2354 2355 2356 2357 2358 2359 2360 2361 2362 2363 2364 2365 2366 2367 2368 2369 2370 2371 2372 2373 2374 2375 2376 2377 2378 2379 2380 2381 2382 2383 2384 2385 2386 2387 2388 2389 2390 2391 2392 2393 2394 2395 2396 2397 2398 2399 2400 2401 2402 2403 2404 2405 2406 2407 2408 2409 2410 2411 2412 2413 2414 2415 2416 2417 2418 2419 2420 2421 2422 2423 2424 2425 2426 2427 2428 2429 2430 2431 2432 2433 2434 2435 2436 2437 2438 2439 2440 2441 2442 2443 2444 2445 2446 2447 2448 2449 2450 2451 2452 2453 2454 2455 2456 2457 2458 2459 2460 2461 2462 2463 2464 2465 2466 2467 2468 2469 2470 2471 2472 2473 2474 2475 2476 2477 2478 2479 2480 2481 2482 2483 2484 2485 2486 2487 2488 2489 2490 2491 2492 2493 2494 2495 2496 2497 2498 2499 2500 2501 2502 2503 2504 2505 2506 2507 2508 2509 2510 2511 2512 2513 2514 2515 2516 2517 2518 2519 2520 2521 2522 2523 2524 2525 2526 2527 2528 2529 2530 2531 2532 2533 2534 2535 2536 2537 2538 2539 2540 2541 2542 2543 2544 2545 2546 2547 2548 2549 2550 2551 2552 2553 2554 2555 2556 2557 2558 2559 2560 2561 2562 2563 2564 2565 2566 2567 2568 2569 2570 2571 2572 2573 2574 2575 2576 2577 2578 2579 2580 2581 2582 2583 2584 2585 2586 2587 2588 2589 2590 2591 2592 2593 2594 2595 2596 2597 2598 2599 2600 2601 2602 2603 2604 2605 2606 2607 2608 2609 2610 2611 2612 2613 2614 2615 2616 2617 2618 2619 2620 2621 2622 2623 2624 2625 2626 2627 2628 2629 2630 2631 2632 2633 2634 2635 2636 2637 2638 2639 2640 2641 2642 2643 2644 2645 2646 2647 2648 2649 2650 2651 2652 2653 2654 2655 2656 2657 2658 2659 2660 2661 2662 2663 2664 2665 2666 2667 2668 2669 2670 2671 2672 2673 2674 2675 2676 2677 2678 2679 2680 2681 2682 2683 2684 2685 2686 2687 2688 2689 2690 2691 2692 2693 2694 2695 2696 2697 2698 2699 2700 2701 2702 2703 2704 2705 2706 2707 2708 2709 2710 2711 2712 2713 2714 2715 2716 2717 2718 2719 2720 2721 2722 2723 2724 2725 2726 2727 2728 2729 2730 2731 2732 2733 2734 2735 2736 2737 2738 2739 2740 2741 2742 2743 2744 2745 2746 2747 2748 2749 2750 2751 2752 2753 2754 2755 2756 2757 2758 2759 2760 2761 2762 2763 2764 2765 2766 2767 2768 2769 2770 2771 2772 2773 2774 2775 2776 2777 2778 2779 2780 2781 2782 2783 2784 2785 2786 2787 2788 2789 2790 2791 2792 2793 2794 2795 2796 2797 2798 2799 2800 2801 2802 2803 2804 2805 2806 2807 2808 2809 2810 2811 2812 2813 2814 2815 2816 2817 2818 2819 2820 2821 2822 2823 2824 2825 2826 2827 2828 2829 2830 2831 2832 2833 2834 2835 2836 2837 2838 2839 2840 2841 2842 2843 2844 2845 2846 2847 2848 2849 2850 2851 2852 2853 2854 2855 2856 2857 2858 2859 2860 2861 2862 2863 2864 2865 2866 2867 2868 2869 2870 2871 2872 2873 2874 2875 2876 2877 2878 2879 2880 2881 2882 2883 2884 2885 2886 2887 2888 2889 2890 2891 2892 2893 2894 2895 2896 2897 2898 2899 2900 2901 2902 2903 2904 2905 2906 2907 2908 2909 2910 2911 2912 2913 2914 2915 2916 2917 2918 2919 2920 2921 2922 2923 2924 2925 2926 2927 2928 2929 2930 2931 2932 2933 2934 2935 2936 2937 2938 2939 2940 2941 2942 2943 2944 2945 2946 2947 2948 2949 2950 2951 2952 2953 2954 2955 2956 2957 2958 2959 2960 2961 2962 2963 2964 2965 2966 2967 2968 2969 2970 2971 2972 2973 2974 2975 2976 2977 2978 2979 2980 2981 2982 2983 2984 2985 2986 2987 2988 2989 2990 2991 2992 2993 2994 2995 2996 2997 2998 2999 3000 3001 3002 3003 3004 3005 3006 3007 3008 3009 3010 3011 3012 3013 3014 3015 3016 3017 3018 3019 3020 3021 3022 3023 3024 3025 3026 3027 3028 3029 3030 3031 3032 3033 3034 3035 3036 3037 3038 3039 3040 3041 3042 3043 3044 3045 3046 3047 3048 3049 3050 3051 3052 3053 3054 3055 3056 3057 3058 3059 3060 3061 3062 3063 3064 3065 3066 3067 3068 3069 3070 3071 3072 3073 3074 3075 3076 3077 3078 3079 3080 3081 3082 3083 3084 3085 3086 3087 3088 3089 3090 3091 3092 3093 3094 3095 3096 3097 3098 3099 3100 3101 3102 3103 3104 3105 3106 3107 3108 3109 3110 3111 3112 3113 3114 3115 3116 3117 3118 3119 3120 3121 3122 3123 3124 3125 3126 3127 3128 3129 3130 3131 3132 3133 3134 3135 3136 3137 3138 3139 3140 3141 3142 3143 3144 3145 3146 3147 3148 3149 3150 3151 3152 3153 3154 3155 3156 3157 3158 3159 3160 3161 3162 3163 3164 3165 3166 3167 3168 3169 3170 3171 3172 3173 3174 3175 3176 3177 3178 3179 3180 3181 3182 3183 3184 3185 3186 3187 3188 3189 3190 3191 3192 3193 3194 3195 3196 3197 3198 3199 3200 3201 3202 3203 3204 3205 3206 3207 3208 3209 3210 3211 3212 3213 3214 3215 3216 3217 3218 3219 3220 3221 3222 3223 3224 3225 3226 3227 3228 3229 3230 3231 3232 3233 3234 3235 3236 3237 3238 3239 3240 3241 3242 3243 3244 3245 3246 3247 3248 3249 3250 3251 3252 3253 3254 3255 3256 3257 3258 3259 3260 3261 3262 3263 3264 3265 3266 3267 3268 3269 3270 3271 3272 3273 3274 3275 3276 3277 3278 3279 3280 3281 3282 3283 3284 3285 3286 3287 3288 3289 3290 3291 3292 3293 3294 3295 3296 3297 3298 3299 3300 3301 3302 3303 3304 3305 3306 3307 3308 3309 3310 3311 3312 3313 3314 3315 3316 3317 3318 3319 3320 3321 3322 3323 3324 3325 3326 3327 3328 3329 3330 3331 3332 3333 3334 3335 3336 3337 3338 3339 3340 3341 3342 3343 3344 3345 3346 3347 3348 3349 3350 3351 3352 3353 3354 3355 3356 3357 3358 3359 3360 3361 3362 3363 3364 3365 3366 3367 3368 3369 3370 3371 3372 3373 3374 3375 3376 3377 3378 3379 3380 3381 3382 3383 3384 3385 3386 3387 3388 3389 3390 3391 3392 3393 3394 3395 3396 3397 3398 3399 3400 3401 3402 3403 3404 3405 3406 3407 3408 3409 3410 3411 3412 3413 3414 3415 3416 3417 3418 3419 3420 3421 3422 3423 3424 3425 3426 3427 3428 3429 3430 3431 3432 3433 3434 3435 3436 3437 3438 3439 3440 3441 3442 3443 3444 3445 3446 3447 3448 3449 3450 3451 3452 3453 3454 3455 3456 3457 3458 3459 3460 3461 3462 3463 3464 3465 3466 3467 3468 3469 3470 3471 3472 3473 3474 3475 3476 3477 3478 3479 3480 3481 3482 3483 3484 3485 3486 3487 3488 3489 3490 3491 3492 3493 3494 3495 3496 3497 3498 3499 3500 3501 3502 3503 3504 3505 3506 3507 3508 3509 3510 3511 3512 3513 3514 3515 3516 3517 3518 3519 3520 3521 3522 3523 3524 3525 3526 3527 3528 3529 3530 3531 3532 3533 3534 3535 3536 3537 3538 3539 3540 3541 3542 3543 3544 3545 3546 3547 3548 3549 3550 3551 3552 3553 3554 3555 3556 3557 3558 3559 3560 3561 3562 3563 3564 3565 3566 3567 3568 3569 3570 3571 3572 3573 3574 3575 3576 3577 3578 3579 3580 3581 3582 3583 3584 3585 3586 3587 3588 3589 3590 3591 3592 3593 3594 3595 3596 3597 3598 3599 3600 3601 3602 3603 3604 3605 3606 3607 3608 3609 3610 3611 3612 3613 3614 3615 3616 3617 3618 3619 3620 3621 3622 3623 3624 3625 3626 3627 3628 3629 3630 3631 3632 3633 3634 3635 3636 3637 3638 3639 3640 3641 3642 3643 3644 3645 3646 3647 3648 3649 3650 3651 3652 3653 3654 3655 3656 3657 3658 3659 3660 3661 3662 3663 3664 3665 3666 3667 3668 3669 3670 3671 3672 3673 3674 3675 3676 3677 3678 3679 3680 3681 3682 3683 3684 3685 3686 3687 3688 3689 3690 3691 3692 3693 3694 3695 3696 3697 3698 3699 3700 3701 3702 3703 3704 3705 3706 3707 3708 3709 3710 3711 3712 3713 3714 3715 3716 3717 3718 3719 3720 3721 3722 3723 3724 3725 3726 3727 3728 3729 3730 3731 3732 3733 3734 3735 3736 3737 3738 3739 3740 3741 3742 3743 3744 3745 3746 3747 3748 3749 3750 3751 3752 3753 3754 3755 3756 3757 3758 3759 3760 3761 3762 3763 3764 3765 3766 3767 3768 3769 3770 3771 3772 3773 3774 3775 3776 3777 3778 3779 3780 3781 3782 3783 3784 3785 3786 3787 3788 3789 3790 3791 3792 3793 3794 3795 3796 3797 3798 3799 3800 3801 3802 3803 3804 3805 3806 3807 3808 3809 3810 3811 3812 3813 3814 3815 3816 3817 3818 3819 3820 3821 3822 3823 3824 3825 3826 3827 3828 3829 3830 3831 3832 3833 3834 3835 3836 3837 3838 3839 3840 3841 3842 3843 3844 3845 3846 3847 3848 3849 3850 3851 3852 3853 3854 3855 3856 3857 3858 3859 3860 3861 3862 3863 3864 3865 3866 3867 3868 3869 3870 3871 3872 3873 3874 3875 3876 3877 3878 3879 3880 3881 3882 3883 3884 3885 3886 3887 3888 3889 3890 3891 3892 3893 3894 3895 3896 3897 3898 3899 3900 3901 3902 3903 3904 3905 | // SPDX-License-Identifier: GPL-2.0-only /* * Contains CPU feature definitions * * Copyright (C) 2015 ARM Ltd. * * A note for the weary kernel hacker: the code here is confusing and hard to * follow! That's partly because it's solving a nasty problem, but also because * there's a little bit of over-abstraction that tends to obscure what's going * on behind a maze of helper functions and macros. * * The basic problem is that hardware folks have started gluing together CPUs * with distinct architectural features; in some cases even creating SoCs where * user-visible instructions are available only on a subset of the available * cores. We try to address this by snapshotting the feature registers of the * boot CPU and comparing these with the feature registers of each secondary * CPU when bringing them up. If there is a mismatch, then we update the * snapshot state to indicate the lowest-common denominator of the feature, * known as the "safe" value. This snapshot state can be queried to view the * "sanitised" value of a feature register. * * The sanitised register values are used to decide which capabilities we * have in the system. These may be in the form of traditional "hwcaps" * advertised to userspace or internal "cpucaps" which are used to configure * things like alternative patching and static keys. While a feature mismatch * may result in a TAINT_CPU_OUT_OF_SPEC kernel taint, a capability mismatch * may prevent a CPU from being onlined at all. * * Some implementation details worth remembering: * * - Mismatched features are *always* sanitised to a "safe" value, which * usually indicates that the feature is not supported. * * - A mismatched feature marked with FTR_STRICT will cause a "SANITY CHECK" * warning when onlining an offending CPU and the kernel will be tainted * with TAINT_CPU_OUT_OF_SPEC. * * - Features marked as FTR_VISIBLE have their sanitised value visible to * userspace. FTR_VISIBLE features in registers that are only visible * to EL0 by trapping *must* have a corresponding HWCAP so that late * onlining of CPUs cannot lead to features disappearing at runtime. * * - A "feature" is typically a 4-bit register field. A "capability" is the * high-level description derived from the sanitised field value. * * - Read the Arm ARM (DDI 0487F.a) section D13.1.3 ("Principles of the ID * scheme for fields in ID registers") to understand when feature fields * may be signed or unsigned (FTR_SIGNED and FTR_UNSIGNED accordingly). * * - KVM exposes its own view of the feature registers to guest operating * systems regardless of FTR_VISIBLE. This is typically driven from the * sanitised register values to allow virtual CPUs to be migrated between * arbitrary physical CPUs, but some features not present on the host are * also advertised and emulated. Look at sys_reg_descs[] for the gory * details. * * - If the arm64_ftr_bits[] for a register has a missing field, then this * field is treated as STRICT RES0, including for read_sanitised_ftr_reg(). * This is stronger than FTR_HIDDEN and can be used to hide features from * KVM guests. */ #define pr_fmt(fmt) "CPU features: " fmt #include <linux/bsearch.h> #include <linux/cpumask.h> #include <linux/crash_dump.h> #include <linux/kstrtox.h> #include <linux/sort.h> #include <linux/stop_machine.h> #include <linux/sysfs.h> #include <linux/types.h> #include <linux/minmax.h> #include <linux/mm.h> #include <linux/cpu.h> #include <linux/kasan.h> #include <linux/percpu.h> #include <asm/cpu.h> #include <asm/cpufeature.h> #include <asm/cpu_ops.h> #include <asm/fpsimd.h> #include <asm/hwcap.h> #include <asm/insn.h> #include <asm/kvm_host.h> #include <asm/mmu_context.h> #include <asm/mte.h> #include <asm/processor.h> #include <asm/smp.h> #include <asm/sysreg.h> #include <asm/traps.h> #include <asm/vectors.h> #include <asm/virt.h> /* Kernel representation of AT_HWCAP and AT_HWCAP2 */ static DECLARE_BITMAP(elf_hwcap, MAX_CPU_FEATURES) __read_mostly; #ifdef CONFIG_COMPAT #define COMPAT_ELF_HWCAP_DEFAULT \ (COMPAT_HWCAP_HALF|COMPAT_HWCAP_THUMB|\ COMPAT_HWCAP_FAST_MULT|COMPAT_HWCAP_EDSP|\ COMPAT_HWCAP_TLS|COMPAT_HWCAP_IDIV|\ COMPAT_HWCAP_LPAE) unsigned int compat_elf_hwcap __read_mostly = COMPAT_ELF_HWCAP_DEFAULT; unsigned int compat_elf_hwcap2 __read_mostly; unsigned int compat_elf_hwcap3 __read_mostly; #endif DECLARE_BITMAP(system_cpucaps, ARM64_NCAPS); EXPORT_SYMBOL(system_cpucaps); static struct arm64_cpu_capabilities const __ro_after_init *cpucap_ptrs[ARM64_NCAPS]; DECLARE_BITMAP(boot_cpucaps, ARM64_NCAPS); bool arm64_use_ng_mappings = false; EXPORT_SYMBOL(arm64_use_ng_mappings); DEFINE_PER_CPU_READ_MOSTLY(const char *, this_cpu_vector) = vectors; /* * Permit PER_LINUX32 and execve() of 32-bit binaries even if not all CPUs * support it? */ static bool __read_mostly allow_mismatched_32bit_el0; /* * Static branch enabled only if allow_mismatched_32bit_el0 is set and we have * seen at least one CPU capable of 32-bit EL0. */ DEFINE_STATIC_KEY_FALSE(arm64_mismatched_32bit_el0); /* * Mask of CPUs supporting 32-bit EL0. * Only valid if arm64_mismatched_32bit_el0 is enabled. */ static cpumask_var_t cpu_32bit_el0_mask __cpumask_var_read_mostly; void dump_cpu_features(void) { /* file-wide pr_fmt adds "CPU features: " prefix */ pr_emerg("0x%*pb\n", ARM64_NCAPS, &system_cpucaps); } #define __ARM64_MAX_POSITIVE(reg, field) \ ((reg##_##field##_SIGNED ? \ BIT(reg##_##field##_WIDTH - 1) : \ BIT(reg##_##field##_WIDTH)) - 1) #define __ARM64_MIN_NEGATIVE(reg, field) BIT(reg##_##field##_WIDTH - 1) #define __ARM64_CPUID_FIELDS(reg, field, min_value, max_value) \ .sys_reg = SYS_##reg, \ .field_pos = reg##_##field##_SHIFT, \ .field_width = reg##_##field##_WIDTH, \ .sign = reg##_##field##_SIGNED, \ .min_field_value = min_value, \ .max_field_value = max_value, /* * ARM64_CPUID_FIELDS() encodes a field with a range from min_value to * an implicit maximum that depends on the sign-ess of the field. * * An unsigned field will be capped at all ones, while a signed field * will be limited to the positive half only. */ #define ARM64_CPUID_FIELDS(reg, field, min_value) \ __ARM64_CPUID_FIELDS(reg, field, \ SYS_FIELD_VALUE(reg, field, min_value), \ __ARM64_MAX_POSITIVE(reg, field)) /* * ARM64_CPUID_FIELDS_NEG() encodes a field with a range from an * implicit minimal value to max_value. This should be used when * matching a non-implemented property. */ #define ARM64_CPUID_FIELDS_NEG(reg, field, max_value) \ __ARM64_CPUID_FIELDS(reg, field, \ __ARM64_MIN_NEGATIVE(reg, field), \ SYS_FIELD_VALUE(reg, field, max_value)) #define __ARM64_FTR_BITS(SIGNED, VISIBLE, STRICT, TYPE, SHIFT, WIDTH, SAFE_VAL) \ { \ .sign = SIGNED, \ .visible = VISIBLE, \ .strict = STRICT, \ .type = TYPE, \ .shift = SHIFT, \ .width = WIDTH, \ .safe_val = SAFE_VAL, \ } /* Define a feature with unsigned values */ #define ARM64_FTR_BITS(VISIBLE, STRICT, TYPE, SHIFT, WIDTH, SAFE_VAL) \ __ARM64_FTR_BITS(FTR_UNSIGNED, VISIBLE, STRICT, TYPE, SHIFT, WIDTH, SAFE_VAL) /* Define a feature with a signed value */ #define S_ARM64_FTR_BITS(VISIBLE, STRICT, TYPE, SHIFT, WIDTH, SAFE_VAL) \ __ARM64_FTR_BITS(FTR_SIGNED, VISIBLE, STRICT, TYPE, SHIFT, WIDTH, SAFE_VAL) #define ARM64_FTR_END \ { \ .width = 0, \ } static void cpu_enable_cnp(struct arm64_cpu_capabilities const *cap); static bool __system_matches_cap(unsigned int n); /* * NOTE: Any changes to the visibility of features should be kept in * sync with the documentation of the CPU feature register ABI. */ static const struct arm64_ftr_bits ftr_id_aa64isar0[] = { ARM64_FTR_BITS(FTR_VISIBLE, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64ISAR0_EL1_RNDR_SHIFT, 4, 0), ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64ISAR0_EL1_TLB_SHIFT, 4, 0), ARM64_FTR_BITS(FTR_VISIBLE, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64ISAR0_EL1_TS_SHIFT, 4, 0), ARM64_FTR_BITS(FTR_VISIBLE, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64ISAR0_EL1_FHM_SHIFT, 4, 0), ARM64_FTR_BITS(FTR_VISIBLE, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64ISAR0_EL1_DP_SHIFT, 4, 0), ARM64_FTR_BITS(FTR_VISIBLE, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64ISAR0_EL1_SM4_SHIFT, 4, 0), ARM64_FTR_BITS(FTR_VISIBLE, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64ISAR0_EL1_SM3_SHIFT, 4, 0), ARM64_FTR_BITS(FTR_VISIBLE, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64ISAR0_EL1_SHA3_SHIFT, 4, 0), ARM64_FTR_BITS(FTR_VISIBLE, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64ISAR0_EL1_RDM_SHIFT, 4, 0), ARM64_FTR_BITS(FTR_VISIBLE, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64ISAR0_EL1_ATOMIC_SHIFT, 4, 0), ARM64_FTR_BITS(FTR_VISIBLE, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64ISAR0_EL1_CRC32_SHIFT, 4, 0), ARM64_FTR_BITS(FTR_VISIBLE, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64ISAR0_EL1_SHA2_SHIFT, 4, 0), ARM64_FTR_BITS(FTR_VISIBLE, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64ISAR0_EL1_SHA1_SHIFT, 4, 0), ARM64_FTR_BITS(FTR_VISIBLE, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64ISAR0_EL1_AES_SHIFT, 4, 0), ARM64_FTR_END, }; static const struct arm64_ftr_bits ftr_id_aa64isar1[] = { ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64ISAR1_EL1_XS_SHIFT, 4, 0), ARM64_FTR_BITS(FTR_VISIBLE, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64ISAR1_EL1_I8MM_SHIFT, 4, 0), ARM64_FTR_BITS(FTR_VISIBLE, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64ISAR1_EL1_DGH_SHIFT, 4, 0), ARM64_FTR_BITS(FTR_VISIBLE, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64ISAR1_EL1_BF16_SHIFT, 4, 0), ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64ISAR1_EL1_SPECRES_SHIFT, 4, 0), ARM64_FTR_BITS(FTR_VISIBLE, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64ISAR1_EL1_SB_SHIFT, 4, 0), ARM64_FTR_BITS(FTR_VISIBLE, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64ISAR1_EL1_FRINTTS_SHIFT, 4, 0), ARM64_FTR_BITS(FTR_VISIBLE_IF_IS_ENABLED(CONFIG_ARM64_PTR_AUTH), FTR_STRICT, FTR_LOWER_SAFE, ID_AA64ISAR1_EL1_GPI_SHIFT, 4, 0), ARM64_FTR_BITS(FTR_VISIBLE_IF_IS_ENABLED(CONFIG_ARM64_PTR_AUTH), FTR_STRICT, FTR_LOWER_SAFE, ID_AA64ISAR1_EL1_GPA_SHIFT, 4, 0), ARM64_FTR_BITS(FTR_VISIBLE, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64ISAR1_EL1_LRCPC_SHIFT, 4, 0), ARM64_FTR_BITS(FTR_VISIBLE, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64ISAR1_EL1_FCMA_SHIFT, 4, 0), ARM64_FTR_BITS(FTR_VISIBLE, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64ISAR1_EL1_JSCVT_SHIFT, 4, 0), ARM64_FTR_BITS(FTR_VISIBLE_IF_IS_ENABLED(CONFIG_ARM64_PTR_AUTH), FTR_STRICT, FTR_EXACT, ID_AA64ISAR1_EL1_API_SHIFT, 4, 0), ARM64_FTR_BITS(FTR_VISIBLE_IF_IS_ENABLED(CONFIG_ARM64_PTR_AUTH), FTR_STRICT, FTR_EXACT, ID_AA64ISAR1_EL1_APA_SHIFT, 4, 0), ARM64_FTR_BITS(FTR_VISIBLE, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64ISAR1_EL1_DPB_SHIFT, 4, 0), ARM64_FTR_END, }; static const struct arm64_ftr_bits ftr_id_aa64isar2[] = { ARM64_FTR_BITS(FTR_VISIBLE, FTR_NONSTRICT, FTR_LOWER_SAFE, ID_AA64ISAR2_EL1_LUT_SHIFT, 4, 0), ARM64_FTR_BITS(FTR_VISIBLE, FTR_NONSTRICT, FTR_LOWER_SAFE, ID_AA64ISAR2_EL1_CSSC_SHIFT, 4, 0), ARM64_FTR_BITS(FTR_VISIBLE, FTR_NONSTRICT, FTR_LOWER_SAFE, ID_AA64ISAR2_EL1_RPRFM_SHIFT, 4, 0), ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64ISAR2_EL1_CLRBHB_SHIFT, 4, 0), ARM64_FTR_BITS(FTR_VISIBLE, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64ISAR2_EL1_BC_SHIFT, 4, 0), ARM64_FTR_BITS(FTR_VISIBLE, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64ISAR2_EL1_MOPS_SHIFT, 4, 0), ARM64_FTR_BITS(FTR_VISIBLE_IF_IS_ENABLED(CONFIG_ARM64_PTR_AUTH), FTR_STRICT, FTR_EXACT, ID_AA64ISAR2_EL1_APA3_SHIFT, 4, 0), ARM64_FTR_BITS(FTR_VISIBLE_IF_IS_ENABLED(CONFIG_ARM64_PTR_AUTH), FTR_STRICT, FTR_LOWER_SAFE, ID_AA64ISAR2_EL1_GPA3_SHIFT, 4, 0), ARM64_FTR_BITS(FTR_VISIBLE, FTR_NONSTRICT, FTR_LOWER_SAFE, ID_AA64ISAR2_EL1_RPRES_SHIFT, 4, 0), ARM64_FTR_BITS(FTR_VISIBLE, FTR_NONSTRICT, FTR_LOWER_SAFE, ID_AA64ISAR2_EL1_WFxT_SHIFT, 4, 0), ARM64_FTR_END, }; static const struct arm64_ftr_bits ftr_id_aa64isar3[] = { ARM64_FTR_BITS(FTR_VISIBLE, FTR_NONSTRICT, FTR_LOWER_SAFE, ID_AA64ISAR3_EL1_FAMINMAX_SHIFT, 4, 0), ARM64_FTR_END, }; static const struct arm64_ftr_bits ftr_id_aa64pfr0[] = { ARM64_FTR_BITS(FTR_HIDDEN, FTR_NONSTRICT, FTR_LOWER_SAFE, ID_AA64PFR0_EL1_CSV3_SHIFT, 4, 0), ARM64_FTR_BITS(FTR_HIDDEN, FTR_NONSTRICT, FTR_LOWER_SAFE, ID_AA64PFR0_EL1_CSV2_SHIFT, 4, 0), ARM64_FTR_BITS(FTR_VISIBLE, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64PFR0_EL1_DIT_SHIFT, 4, 0), ARM64_FTR_BITS(FTR_HIDDEN, FTR_NONSTRICT, FTR_LOWER_SAFE, ID_AA64PFR0_EL1_AMU_SHIFT, 4, 0), ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64PFR0_EL1_MPAM_SHIFT, 4, 0), ARM64_FTR_BITS(FTR_HIDDEN, FTR_NONSTRICT, FTR_LOWER_SAFE, ID_AA64PFR0_EL1_SEL2_SHIFT, 4, 0), ARM64_FTR_BITS(FTR_VISIBLE_IF_IS_ENABLED(CONFIG_ARM64_SVE), FTR_STRICT, FTR_LOWER_SAFE, ID_AA64PFR0_EL1_SVE_SHIFT, 4, 0), ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64PFR0_EL1_RAS_SHIFT, 4, 0), ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64PFR0_EL1_GIC_SHIFT, 4, 0), S_ARM64_FTR_BITS(FTR_VISIBLE, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64PFR0_EL1_AdvSIMD_SHIFT, 4, ID_AA64PFR0_EL1_AdvSIMD_NI), S_ARM64_FTR_BITS(FTR_VISIBLE, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64PFR0_EL1_FP_SHIFT, 4, ID_AA64PFR0_EL1_FP_NI), ARM64_FTR_BITS(FTR_HIDDEN, FTR_NONSTRICT, FTR_LOWER_SAFE, ID_AA64PFR0_EL1_EL3_SHIFT, 4, 0), ARM64_FTR_BITS(FTR_HIDDEN, FTR_NONSTRICT, FTR_LOWER_SAFE, ID_AA64PFR0_EL1_EL2_SHIFT, 4, 0), ARM64_FTR_BITS(FTR_HIDDEN, FTR_NONSTRICT, FTR_LOWER_SAFE, ID_AA64PFR0_EL1_EL1_SHIFT, 4, ID_AA64PFR0_EL1_EL1_IMP), ARM64_FTR_BITS(FTR_HIDDEN, FTR_NONSTRICT, FTR_LOWER_SAFE, ID_AA64PFR0_EL1_EL0_SHIFT, 4, ID_AA64PFR0_EL1_EL0_IMP), ARM64_FTR_END, }; static const struct arm64_ftr_bits ftr_id_aa64pfr1[] = { ARM64_FTR_BITS(FTR_VISIBLE_IF_IS_ENABLED(CONFIG_ARM64_GCS), FTR_STRICT, FTR_LOWER_SAFE, ID_AA64PFR1_EL1_GCS_SHIFT, 4, 0), ARM64_FTR_BITS(FTR_VISIBLE_IF_IS_ENABLED(CONFIG_ARM64_SME), FTR_STRICT, FTR_LOWER_SAFE, ID_AA64PFR1_EL1_SME_SHIFT, 4, 0), ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64PFR1_EL1_MPAM_frac_SHIFT, 4, 0), ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64PFR1_EL1_RAS_frac_SHIFT, 4, 0), ARM64_FTR_BITS(FTR_VISIBLE_IF_IS_ENABLED(CONFIG_ARM64_MTE), FTR_STRICT, FTR_LOWER_SAFE, ID_AA64PFR1_EL1_MTE_SHIFT, 4, ID_AA64PFR1_EL1_MTE_NI), ARM64_FTR_BITS(FTR_VISIBLE, FTR_NONSTRICT, FTR_LOWER_SAFE, ID_AA64PFR1_EL1_SSBS_SHIFT, 4, ID_AA64PFR1_EL1_SSBS_NI), ARM64_FTR_BITS(FTR_VISIBLE_IF_IS_ENABLED(CONFIG_ARM64_BTI), FTR_STRICT, FTR_LOWER_SAFE, ID_AA64PFR1_EL1_BT_SHIFT, 4, 0), ARM64_FTR_END, }; static const struct arm64_ftr_bits ftr_id_aa64pfr2[] = { ARM64_FTR_BITS(FTR_VISIBLE, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64PFR2_EL1_FPMR_SHIFT, 4, 0), ARM64_FTR_END, }; static const struct arm64_ftr_bits ftr_id_aa64zfr0[] = { ARM64_FTR_BITS(FTR_VISIBLE_IF_IS_ENABLED(CONFIG_ARM64_SVE), FTR_STRICT, FTR_LOWER_SAFE, ID_AA64ZFR0_EL1_F64MM_SHIFT, 4, 0), ARM64_FTR_BITS(FTR_VISIBLE_IF_IS_ENABLED(CONFIG_ARM64_SVE), FTR_STRICT, FTR_LOWER_SAFE, ID_AA64ZFR0_EL1_F32MM_SHIFT, 4, 0), ARM64_FTR_BITS(FTR_VISIBLE_IF_IS_ENABLED(CONFIG_ARM64_SVE), FTR_STRICT, FTR_LOWER_SAFE, ID_AA64ZFR0_EL1_I8MM_SHIFT, 4, 0), ARM64_FTR_BITS(FTR_VISIBLE_IF_IS_ENABLED(CONFIG_ARM64_SVE), FTR_STRICT, FTR_LOWER_SAFE, ID_AA64ZFR0_EL1_SM4_SHIFT, 4, 0), ARM64_FTR_BITS(FTR_VISIBLE_IF_IS_ENABLED(CONFIG_ARM64_SVE), FTR_STRICT, FTR_LOWER_SAFE, ID_AA64ZFR0_EL1_SHA3_SHIFT, 4, 0), ARM64_FTR_BITS(FTR_VISIBLE_IF_IS_ENABLED(CONFIG_ARM64_SVE), FTR_STRICT, FTR_LOWER_SAFE, ID_AA64ZFR0_EL1_B16B16_SHIFT, 4, 0), ARM64_FTR_BITS(FTR_VISIBLE_IF_IS_ENABLED(CONFIG_ARM64_SVE), FTR_STRICT, FTR_LOWER_SAFE, ID_AA64ZFR0_EL1_BF16_SHIFT, 4, 0), ARM64_FTR_BITS(FTR_VISIBLE_IF_IS_ENABLED(CONFIG_ARM64_SVE), FTR_STRICT, FTR_LOWER_SAFE, ID_AA64ZFR0_EL1_BitPerm_SHIFT, 4, 0), ARM64_FTR_BITS(FTR_VISIBLE_IF_IS_ENABLED(CONFIG_ARM64_SVE), FTR_STRICT, FTR_LOWER_SAFE, ID_AA64ZFR0_EL1_AES_SHIFT, 4, 0), ARM64_FTR_BITS(FTR_VISIBLE_IF_IS_ENABLED(CONFIG_ARM64_SVE), FTR_STRICT, FTR_LOWER_SAFE, ID_AA64ZFR0_EL1_SVEver_SHIFT, 4, 0), ARM64_FTR_END, }; static const struct arm64_ftr_bits ftr_id_aa64smfr0[] = { ARM64_FTR_BITS(FTR_VISIBLE_IF_IS_ENABLED(CONFIG_ARM64_SME), FTR_STRICT, FTR_EXACT, ID_AA64SMFR0_EL1_FA64_SHIFT, 1, 0), ARM64_FTR_BITS(FTR_VISIBLE_IF_IS_ENABLED(CONFIG_ARM64_SME), FTR_STRICT, FTR_EXACT, ID_AA64SMFR0_EL1_LUTv2_SHIFT, 1, 0), ARM64_FTR_BITS(FTR_VISIBLE_IF_IS_ENABLED(CONFIG_ARM64_SME), FTR_STRICT, FTR_EXACT, ID_AA64SMFR0_EL1_SMEver_SHIFT, 4, 0), ARM64_FTR_BITS(FTR_VISIBLE_IF_IS_ENABLED(CONFIG_ARM64_SME), FTR_STRICT, FTR_EXACT, ID_AA64SMFR0_EL1_I16I64_SHIFT, 4, 0), ARM64_FTR_BITS(FTR_VISIBLE_IF_IS_ENABLED(CONFIG_ARM64_SME), FTR_STRICT, FTR_EXACT, ID_AA64SMFR0_EL1_F64F64_SHIFT, 1, 0), ARM64_FTR_BITS(FTR_VISIBLE_IF_IS_ENABLED(CONFIG_ARM64_SME), FTR_STRICT, FTR_EXACT, ID_AA64SMFR0_EL1_I16I32_SHIFT, 4, 0), ARM64_FTR_BITS(FTR_VISIBLE_IF_IS_ENABLED(CONFIG_ARM64_SME), FTR_STRICT, FTR_EXACT, ID_AA64SMFR0_EL1_B16B16_SHIFT, 1, 0), ARM64_FTR_BITS(FTR_VISIBLE_IF_IS_ENABLED(CONFIG_ARM64_SME), FTR_STRICT, FTR_EXACT, ID_AA64SMFR0_EL1_F16F16_SHIFT, 1, 0), ARM64_FTR_BITS(FTR_VISIBLE_IF_IS_ENABLED(CONFIG_ARM64_SME), FTR_STRICT, FTR_EXACT, ID_AA64SMFR0_EL1_F8F16_SHIFT, 1, 0), ARM64_FTR_BITS(FTR_VISIBLE_IF_IS_ENABLED(CONFIG_ARM64_SME), FTR_STRICT, FTR_EXACT, ID_AA64SMFR0_EL1_F8F32_SHIFT, 1, 0), ARM64_FTR_BITS(FTR_VISIBLE_IF_IS_ENABLED(CONFIG_ARM64_SME), FTR_STRICT, FTR_EXACT, ID_AA64SMFR0_EL1_I8I32_SHIFT, 4, 0), ARM64_FTR_BITS(FTR_VISIBLE_IF_IS_ENABLED(CONFIG_ARM64_SME), FTR_STRICT, FTR_EXACT, ID_AA64SMFR0_EL1_F16F32_SHIFT, 1, 0), ARM64_FTR_BITS(FTR_VISIBLE_IF_IS_ENABLED(CONFIG_ARM64_SME), FTR_STRICT, FTR_EXACT, ID_AA64SMFR0_EL1_B16F32_SHIFT, 1, 0), ARM64_FTR_BITS(FTR_VISIBLE_IF_IS_ENABLED(CONFIG_ARM64_SME), FTR_STRICT, FTR_EXACT, ID_AA64SMFR0_EL1_BI32I32_SHIFT, 1, 0), ARM64_FTR_BITS(FTR_VISIBLE_IF_IS_ENABLED(CONFIG_ARM64_SME), FTR_STRICT, FTR_EXACT, ID_AA64SMFR0_EL1_F32F32_SHIFT, 1, 0), ARM64_FTR_BITS(FTR_VISIBLE_IF_IS_ENABLED(CONFIG_ARM64_SME), FTR_STRICT, FTR_EXACT, ID_AA64SMFR0_EL1_SF8FMA_SHIFT, 1, 0), ARM64_FTR_BITS(FTR_VISIBLE_IF_IS_ENABLED(CONFIG_ARM64_SME), FTR_STRICT, FTR_EXACT, ID_AA64SMFR0_EL1_SF8DP4_SHIFT, 1, 0), ARM64_FTR_BITS(FTR_VISIBLE_IF_IS_ENABLED(CONFIG_ARM64_SME), FTR_STRICT, FTR_EXACT, ID_AA64SMFR0_EL1_SF8DP2_SHIFT, 1, 0), ARM64_FTR_END, }; static const struct arm64_ftr_bits ftr_id_aa64fpfr0[] = { ARM64_FTR_BITS(FTR_VISIBLE, FTR_STRICT, FTR_EXACT, ID_AA64FPFR0_EL1_F8CVT_SHIFT, 1, 0), ARM64_FTR_BITS(FTR_VISIBLE, FTR_STRICT, FTR_EXACT, ID_AA64FPFR0_EL1_F8FMA_SHIFT, 1, 0), ARM64_FTR_BITS(FTR_VISIBLE, FTR_STRICT, FTR_EXACT, ID_AA64FPFR0_EL1_F8DP4_SHIFT, 1, 0), ARM64_FTR_BITS(FTR_VISIBLE, FTR_STRICT, FTR_EXACT, ID_AA64FPFR0_EL1_F8DP2_SHIFT, 1, 0), ARM64_FTR_BITS(FTR_VISIBLE, FTR_STRICT, FTR_EXACT, ID_AA64FPFR0_EL1_F8E4M3_SHIFT, 1, 0), ARM64_FTR_BITS(FTR_VISIBLE, FTR_STRICT, FTR_EXACT, ID_AA64FPFR0_EL1_F8E5M2_SHIFT, 1, 0), ARM64_FTR_END, }; static const struct arm64_ftr_bits ftr_id_aa64mmfr0[] = { ARM64_FTR_BITS(FTR_VISIBLE, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64MMFR0_EL1_ECV_SHIFT, 4, 0), ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64MMFR0_EL1_FGT_SHIFT, 4, 0), ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64MMFR0_EL1_EXS_SHIFT, 4, 0), /* * Page size not being supported at Stage-2 is not fatal. You * just give up KVM if PAGE_SIZE isn't supported there. Go fix * your favourite nesting hypervisor. * * There is a small corner case where the hypervisor explicitly * advertises a given granule size at Stage-2 (value 2) on some * vCPUs, and uses the fallback to Stage-1 (value 0) for other * vCPUs. Although this is not forbidden by the architecture, it * indicates that the hypervisor is being silly (or buggy). * * We make no effort to cope with this and pretend that if these * fields are inconsistent across vCPUs, then it isn't worth * trying to bring KVM up. */ ARM64_FTR_BITS(FTR_HIDDEN, FTR_NONSTRICT, FTR_EXACT, ID_AA64MMFR0_EL1_TGRAN4_2_SHIFT, 4, 1), ARM64_FTR_BITS(FTR_HIDDEN, FTR_NONSTRICT, FTR_EXACT, ID_AA64MMFR0_EL1_TGRAN64_2_SHIFT, 4, 1), ARM64_FTR_BITS(FTR_HIDDEN, FTR_NONSTRICT, FTR_EXACT, ID_AA64MMFR0_EL1_TGRAN16_2_SHIFT, 4, 1), /* * We already refuse to boot CPUs that don't support our configured * page size, so we can only detect mismatches for a page size other * than the one we're currently using. Unfortunately, SoCs like this * exist in the wild so, even though we don't like it, we'll have to go * along with it and treat them as non-strict. */ S_ARM64_FTR_BITS(FTR_HIDDEN, FTR_NONSTRICT, FTR_LOWER_SAFE, ID_AA64MMFR0_EL1_TGRAN4_SHIFT, 4, ID_AA64MMFR0_EL1_TGRAN4_NI), S_ARM64_FTR_BITS(FTR_HIDDEN, FTR_NONSTRICT, FTR_LOWER_SAFE, ID_AA64MMFR0_EL1_TGRAN64_SHIFT, 4, ID_AA64MMFR0_EL1_TGRAN64_NI), ARM64_FTR_BITS(FTR_HIDDEN, FTR_NONSTRICT, FTR_LOWER_SAFE, ID_AA64MMFR0_EL1_TGRAN16_SHIFT, 4, ID_AA64MMFR0_EL1_TGRAN16_NI), ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64MMFR0_EL1_BIGENDEL0_SHIFT, 4, 0), /* Linux shouldn't care about secure memory */ ARM64_FTR_BITS(FTR_HIDDEN, FTR_NONSTRICT, FTR_LOWER_SAFE, ID_AA64MMFR0_EL1_SNSMEM_SHIFT, 4, 0), ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64MMFR0_EL1_BIGEND_SHIFT, 4, 0), ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64MMFR0_EL1_ASIDBITS_SHIFT, 4, 0), /* * Differing PARange is fine as long as all peripherals and memory are mapped * within the minimum PARange of all CPUs */ ARM64_FTR_BITS(FTR_HIDDEN, FTR_NONSTRICT, FTR_LOWER_SAFE, ID_AA64MMFR0_EL1_PARANGE_SHIFT, 4, 0), ARM64_FTR_END, }; static const struct arm64_ftr_bits ftr_id_aa64mmfr1[] = { ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64MMFR1_EL1_ECBHB_SHIFT, 4, 0), ARM64_FTR_BITS(FTR_HIDDEN, FTR_NONSTRICT, FTR_LOWER_SAFE, ID_AA64MMFR1_EL1_TIDCP1_SHIFT, 4, 0), ARM64_FTR_BITS(FTR_VISIBLE, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64MMFR1_EL1_AFP_SHIFT, 4, 0), ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64MMFR1_EL1_HCX_SHIFT, 4, 0), ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64MMFR1_EL1_ETS_SHIFT, 4, 0), ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64MMFR1_EL1_TWED_SHIFT, 4, 0), ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64MMFR1_EL1_XNX_SHIFT, 4, 0), ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_HIGHER_SAFE, ID_AA64MMFR1_EL1_SpecSEI_SHIFT, 4, 0), ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64MMFR1_EL1_PAN_SHIFT, 4, 0), ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64MMFR1_EL1_LO_SHIFT, 4, 0), ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64MMFR1_EL1_HPDS_SHIFT, 4, 0), ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64MMFR1_EL1_VH_SHIFT, 4, 0), ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64MMFR1_EL1_VMIDBits_SHIFT, 4, 0), ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64MMFR1_EL1_HAFDBS_SHIFT, 4, 0), ARM64_FTR_END, }; static const struct arm64_ftr_bits ftr_id_aa64mmfr2[] = { ARM64_FTR_BITS(FTR_HIDDEN, FTR_NONSTRICT, FTR_LOWER_SAFE, ID_AA64MMFR2_EL1_E0PD_SHIFT, 4, 0), ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64MMFR2_EL1_EVT_SHIFT, 4, 0), ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64MMFR2_EL1_BBM_SHIFT, 4, 0), ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64MMFR2_EL1_TTL_SHIFT, 4, 0), ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64MMFR2_EL1_FWB_SHIFT, 4, 0), ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64MMFR2_EL1_IDS_SHIFT, 4, 0), ARM64_FTR_BITS(FTR_VISIBLE, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64MMFR2_EL1_AT_SHIFT, 4, 0), ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64MMFR2_EL1_ST_SHIFT, 4, 0), ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64MMFR2_EL1_NV_SHIFT, 4, 0), ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64MMFR2_EL1_CCIDX_SHIFT, 4, 0), ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64MMFR2_EL1_VARange_SHIFT, 4, 0), ARM64_FTR_BITS(FTR_HIDDEN, FTR_NONSTRICT, FTR_LOWER_SAFE, ID_AA64MMFR2_EL1_IESB_SHIFT, 4, 0), ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64MMFR2_EL1_LSM_SHIFT, 4, 0), ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64MMFR2_EL1_UAO_SHIFT, 4, 0), ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64MMFR2_EL1_CnP_SHIFT, 4, 0), ARM64_FTR_END, }; static const struct arm64_ftr_bits ftr_id_aa64mmfr3[] = { ARM64_FTR_BITS(FTR_VISIBLE_IF_IS_ENABLED(CONFIG_ARM64_POE), FTR_NONSTRICT, FTR_LOWER_SAFE, ID_AA64MMFR3_EL1_S1POE_SHIFT, 4, 0), ARM64_FTR_BITS(FTR_HIDDEN, FTR_NONSTRICT, FTR_LOWER_SAFE, ID_AA64MMFR3_EL1_S1PIE_SHIFT, 4, 0), ARM64_FTR_BITS(FTR_HIDDEN, FTR_NONSTRICT, FTR_LOWER_SAFE, ID_AA64MMFR3_EL1_TCRX_SHIFT, 4, 0), ARM64_FTR_END, }; static const struct arm64_ftr_bits ftr_id_aa64mmfr4[] = { S_ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64MMFR4_EL1_E2H0_SHIFT, 4, 0), ARM64_FTR_END, }; static const struct arm64_ftr_bits ftr_ctr[] = { ARM64_FTR_BITS(FTR_VISIBLE, FTR_STRICT, FTR_EXACT, 31, 1, 1), /* RES1 */ ARM64_FTR_BITS(FTR_VISIBLE, FTR_STRICT, FTR_LOWER_SAFE, CTR_EL0_DIC_SHIFT, 1, 1), ARM64_FTR_BITS(FTR_VISIBLE, FTR_STRICT, FTR_LOWER_SAFE, CTR_EL0_IDC_SHIFT, 1, 1), ARM64_FTR_BITS(FTR_VISIBLE, FTR_STRICT, FTR_HIGHER_OR_ZERO_SAFE, CTR_EL0_CWG_SHIFT, 4, 0), ARM64_FTR_BITS(FTR_VISIBLE, FTR_STRICT, FTR_HIGHER_OR_ZERO_SAFE, CTR_EL0_ERG_SHIFT, 4, 0), ARM64_FTR_BITS(FTR_VISIBLE, FTR_STRICT, FTR_LOWER_SAFE, CTR_EL0_DminLine_SHIFT, 4, 1), /* * Linux can handle differing I-cache policies. Userspace JITs will * make use of *minLine. * If we have differing I-cache policies, report it as the weakest - VIPT. */ ARM64_FTR_BITS(FTR_VISIBLE, FTR_NONSTRICT, FTR_EXACT, CTR_EL0_L1Ip_SHIFT, 2, CTR_EL0_L1Ip_VIPT), /* L1Ip */ ARM64_FTR_BITS(FTR_VISIBLE, FTR_STRICT, FTR_LOWER_SAFE, CTR_EL0_IminLine_SHIFT, 4, 0), ARM64_FTR_END, }; static struct arm64_ftr_override __ro_after_init no_override = { }; struct arm64_ftr_reg arm64_ftr_reg_ctrel0 = { .name = "SYS_CTR_EL0", .ftr_bits = ftr_ctr, .override = &no_override, }; static const struct arm64_ftr_bits ftr_id_mmfr0[] = { S_ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_MMFR0_EL1_InnerShr_SHIFT, 4, 0xf), ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_MMFR0_EL1_FCSE_SHIFT, 4, 0), ARM64_FTR_BITS(FTR_HIDDEN, FTR_NONSTRICT, FTR_LOWER_SAFE, ID_MMFR0_EL1_AuxReg_SHIFT, 4, 0), ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_MMFR0_EL1_TCM_SHIFT, 4, 0), ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_MMFR0_EL1_ShareLvl_SHIFT, 4, 0), S_ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_MMFR0_EL1_OuterShr_SHIFT, 4, 0xf), ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_MMFR0_EL1_PMSA_SHIFT, 4, 0), ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_MMFR0_EL1_VMSA_SHIFT, 4, 0), ARM64_FTR_END, }; static const struct arm64_ftr_bits ftr_id_aa64dfr0[] = { S_ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64DFR0_EL1_DoubleLock_SHIFT, 4, 0), ARM64_FTR_BITS(FTR_HIDDEN, FTR_NONSTRICT, FTR_LOWER_SAFE, ID_AA64DFR0_EL1_PMSVer_SHIFT, 4, 0), ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64DFR0_EL1_CTX_CMPs_SHIFT, 4, 0), ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64DFR0_EL1_WRPs_SHIFT, 4, 0), ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64DFR0_EL1_BRPs_SHIFT, 4, 0), /* * We can instantiate multiple PMU instances with different levels * of support. */ S_ARM64_FTR_BITS(FTR_HIDDEN, FTR_NONSTRICT, FTR_EXACT, ID_AA64DFR0_EL1_PMUVer_SHIFT, 4, 0), ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_EXACT, ID_AA64DFR0_EL1_DebugVer_SHIFT, 4, 0x6), ARM64_FTR_END, }; static const struct arm64_ftr_bits ftr_mvfr0[] = { ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, MVFR0_EL1_FPRound_SHIFT, 4, 0), ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, MVFR0_EL1_FPShVec_SHIFT, 4, 0), ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, MVFR0_EL1_FPSqrt_SHIFT, 4, 0), ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, MVFR0_EL1_FPDivide_SHIFT, 4, 0), ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, MVFR0_EL1_FPTrap_SHIFT, 4, 0), ARM64_FTR_BITS(FTR_VISIBLE, FTR_STRICT, FTR_LOWER_SAFE, MVFR0_EL1_FPDP_SHIFT, 4, 0), ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, MVFR0_EL1_FPSP_SHIFT, 4, 0), ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, MVFR0_EL1_SIMDReg_SHIFT, 4, 0), ARM64_FTR_END, }; static const struct arm64_ftr_bits ftr_mvfr1[] = { ARM64_FTR_BITS(FTR_VISIBLE, FTR_STRICT, FTR_LOWER_SAFE, MVFR1_EL1_SIMDFMAC_SHIFT, 4, 0), ARM64_FTR_BITS(FTR_VISIBLE, FTR_STRICT, FTR_LOWER_SAFE, MVFR1_EL1_FPHP_SHIFT, 4, 0), ARM64_FTR_BITS(FTR_VISIBLE, FTR_STRICT, FTR_LOWER_SAFE, MVFR1_EL1_SIMDHP_SHIFT, 4, 0), ARM64_FTR_BITS(FTR_VISIBLE, FTR_STRICT, FTR_LOWER_SAFE, MVFR1_EL1_SIMDSP_SHIFT, 4, 0), ARM64_FTR_BITS(FTR_VISIBLE, FTR_STRICT, FTR_LOWER_SAFE, MVFR1_EL1_SIMDInt_SHIFT, 4, 0), ARM64_FTR_BITS(FTR_VISIBLE, FTR_STRICT, FTR_LOWER_SAFE, MVFR1_EL1_SIMDLS_SHIFT, 4, 0), ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, MVFR1_EL1_FPDNaN_SHIFT, 4, 0), ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, MVFR1_EL1_FPFtZ_SHIFT, 4, 0), ARM64_FTR_END, }; static const struct arm64_ftr_bits ftr_mvfr2[] = { ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, MVFR2_EL1_FPMisc_SHIFT, 4, 0), ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, MVFR2_EL1_SIMDMisc_SHIFT, 4, 0), ARM64_FTR_END, }; static const struct arm64_ftr_bits ftr_dczid[] = { ARM64_FTR_BITS(FTR_VISIBLE, FTR_STRICT, FTR_EXACT, DCZID_EL0_DZP_SHIFT, 1, 1), ARM64_FTR_BITS(FTR_VISIBLE, FTR_STRICT, FTR_LOWER_SAFE, DCZID_EL0_BS_SHIFT, 4, 0), ARM64_FTR_END, }; static const struct arm64_ftr_bits ftr_gmid[] = { ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, GMID_EL1_BS_SHIFT, 4, 0), ARM64_FTR_END, }; static const struct arm64_ftr_bits ftr_id_isar0[] = { ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_ISAR0_EL1_Divide_SHIFT, 4, 0), ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_ISAR0_EL1_Debug_SHIFT, 4, 0), ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_ISAR0_EL1_Coproc_SHIFT, 4, 0), ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_ISAR0_EL1_CmpBranch_SHIFT, 4, 0), ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_ISAR0_EL1_BitField_SHIFT, 4, 0), ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_ISAR0_EL1_BitCount_SHIFT, 4, 0), ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_ISAR0_EL1_Swap_SHIFT, 4, 0), ARM64_FTR_END, }; static const struct arm64_ftr_bits ftr_id_isar5[] = { ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_ISAR5_EL1_RDM_SHIFT, 4, 0), ARM64_FTR_BITS(FTR_VISIBLE, FTR_STRICT, FTR_LOWER_SAFE, ID_ISAR5_EL1_CRC32_SHIFT, 4, 0), ARM64_FTR_BITS(FTR_VISIBLE, FTR_STRICT, FTR_LOWER_SAFE, ID_ISAR5_EL1_SHA2_SHIFT, 4, 0), ARM64_FTR_BITS(FTR_VISIBLE, FTR_STRICT, FTR_LOWER_SAFE, ID_ISAR5_EL1_SHA1_SHIFT, 4, 0), ARM64_FTR_BITS(FTR_VISIBLE, FTR_STRICT, FTR_LOWER_SAFE, ID_ISAR5_EL1_AES_SHIFT, 4, 0), ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_ISAR5_EL1_SEVL_SHIFT, 4, 0), ARM64_FTR_END, }; static const struct arm64_ftr_bits ftr_id_mmfr4[] = { ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_MMFR4_EL1_EVT_SHIFT, 4, 0), ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_MMFR4_EL1_CCIDX_SHIFT, 4, 0), ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_MMFR4_EL1_LSM_SHIFT, 4, 0), ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_MMFR4_EL1_HPDS_SHIFT, 4, 0), ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_MMFR4_EL1_CnP_SHIFT, 4, 0), ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_MMFR4_EL1_XNX_SHIFT, 4, 0), ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_MMFR4_EL1_AC2_SHIFT, 4, 0), /* * SpecSEI = 1 indicates that the PE might generate an SError on an * external abort on speculative read. It is safe to assume that an * SError might be generated than it will not be. Hence it has been * classified as FTR_HIGHER_SAFE. */ ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_HIGHER_SAFE, ID_MMFR4_EL1_SpecSEI_SHIFT, 4, 0), ARM64_FTR_END, }; static const struct arm64_ftr_bits ftr_id_isar4[] = { ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_ISAR4_EL1_SWP_frac_SHIFT, 4, 0), ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_ISAR4_EL1_PSR_M_SHIFT, 4, 0), ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_ISAR4_EL1_SynchPrim_frac_SHIFT, 4, 0), ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_ISAR4_EL1_Barrier_SHIFT, 4, 0), ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_ISAR4_EL1_SMC_SHIFT, 4, 0), ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_ISAR4_EL1_Writeback_SHIFT, 4, 0), ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_ISAR4_EL1_WithShifts_SHIFT, 4, 0), ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_ISAR4_EL1_Unpriv_SHIFT, 4, 0), ARM64_FTR_END, }; static const struct arm64_ftr_bits ftr_id_mmfr5[] = { ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_MMFR5_EL1_ETS_SHIFT, 4, 0), ARM64_FTR_END, }; static const struct arm64_ftr_bits ftr_id_isar6[] = { ARM64_FTR_BITS(FTR_VISIBLE, FTR_STRICT, FTR_LOWER_SAFE, ID_ISAR6_EL1_I8MM_SHIFT, 4, 0), ARM64_FTR_BITS(FTR_VISIBLE, FTR_STRICT, FTR_LOWER_SAFE, ID_ISAR6_EL1_BF16_SHIFT, 4, 0), ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_ISAR6_EL1_SPECRES_SHIFT, 4, 0), ARM64_FTR_BITS(FTR_VISIBLE, FTR_STRICT, FTR_LOWER_SAFE, ID_ISAR6_EL1_SB_SHIFT, 4, 0), ARM64_FTR_BITS(FTR_VISIBLE, FTR_STRICT, FTR_LOWER_SAFE, ID_ISAR6_EL1_FHM_SHIFT, 4, 0), ARM64_FTR_BITS(FTR_VISIBLE, FTR_STRICT, FTR_LOWER_SAFE, ID_ISAR6_EL1_DP_SHIFT, 4, 0), ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_ISAR6_EL1_JSCVT_SHIFT, 4, 0), ARM64_FTR_END, }; static const struct arm64_ftr_bits ftr_id_pfr0[] = { ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_PFR0_EL1_DIT_SHIFT, 4, 0), ARM64_FTR_BITS(FTR_HIDDEN, FTR_NONSTRICT, FTR_LOWER_SAFE, ID_PFR0_EL1_CSV2_SHIFT, 4, 0), ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_PFR0_EL1_State3_SHIFT, 4, 0), ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_PFR0_EL1_State2_SHIFT, 4, 0), ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_PFR0_EL1_State1_SHIFT, 4, 0), ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_PFR0_EL1_State0_SHIFT, 4, 0), ARM64_FTR_END, }; static const struct arm64_ftr_bits ftr_id_pfr1[] = { ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_PFR1_EL1_GIC_SHIFT, 4, 0), ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_PFR1_EL1_Virt_frac_SHIFT, 4, 0), ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_PFR1_EL1_Sec_frac_SHIFT, 4, 0), ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_PFR1_EL1_GenTimer_SHIFT, 4, 0), ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_PFR1_EL1_Virtualization_SHIFT, 4, 0), ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_PFR1_EL1_MProgMod_SHIFT, 4, 0), ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_PFR1_EL1_Security_SHIFT, 4, 0), ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_PFR1_EL1_ProgMod_SHIFT, 4, 0), ARM64_FTR_END, }; static const struct arm64_ftr_bits ftr_id_pfr2[] = { ARM64_FTR_BITS(FTR_VISIBLE, FTR_NONSTRICT, FTR_LOWER_SAFE, ID_PFR2_EL1_SSBS_SHIFT, 4, 0), ARM64_FTR_BITS(FTR_HIDDEN, FTR_NONSTRICT, FTR_LOWER_SAFE, ID_PFR2_EL1_CSV3_SHIFT, 4, 0), ARM64_FTR_END, }; static const struct arm64_ftr_bits ftr_id_dfr0[] = { /* [31:28] TraceFilt */ S_ARM64_FTR_BITS(FTR_HIDDEN, FTR_NONSTRICT, FTR_EXACT, ID_DFR0_EL1_PerfMon_SHIFT, 4, 0), ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_DFR0_EL1_MProfDbg_SHIFT, 4, 0), ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_DFR0_EL1_MMapTrc_SHIFT, 4, 0), ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_DFR0_EL1_CopTrc_SHIFT, 4, 0), ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_DFR0_EL1_MMapDbg_SHIFT, 4, 0), ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_DFR0_EL1_CopSDbg_SHIFT, 4, 0), ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_DFR0_EL1_CopDbg_SHIFT, 4, 0), ARM64_FTR_END, }; static const struct arm64_ftr_bits ftr_id_dfr1[] = { S_ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_DFR1_EL1_MTPMU_SHIFT, 4, 0), ARM64_FTR_END, }; static const struct arm64_ftr_bits ftr_mpamidr[] = { ARM64_FTR_BITS(FTR_HIDDEN, FTR_NONSTRICT, FTR_LOWER_SAFE, MPAMIDR_EL1_PMG_MAX_SHIFT, MPAMIDR_EL1_PMG_MAX_WIDTH, 0), ARM64_FTR_BITS(FTR_HIDDEN, FTR_NONSTRICT, FTR_LOWER_SAFE, MPAMIDR_EL1_VPMR_MAX_SHIFT, MPAMIDR_EL1_VPMR_MAX_WIDTH, 0), ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, MPAMIDR_EL1_HAS_HCR_SHIFT, 1, 0), ARM64_FTR_BITS(FTR_HIDDEN, FTR_NONSTRICT, FTR_LOWER_SAFE, MPAMIDR_EL1_PARTID_MAX_SHIFT, MPAMIDR_EL1_PARTID_MAX_WIDTH, 0), ARM64_FTR_END, }; /* * Common ftr bits for a 32bit register with all hidden, strict * attributes, with 4bit feature fields and a default safe value of * 0. Covers the following 32bit registers: * id_isar[1-3], id_mmfr[1-3] */ static const struct arm64_ftr_bits ftr_generic_32bits[] = { ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, 28, 4, 0), ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, 24, 4, 0), ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, 20, 4, 0), ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, 16, 4, 0), ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, 12, 4, 0), ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, 8, 4, 0), ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, 4, 4, 0), ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, 0, 4, 0), ARM64_FTR_END, }; /* Table for a single 32bit feature value */ static const struct arm64_ftr_bits ftr_single32[] = { ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_EXACT, 0, 32, 0), ARM64_FTR_END, }; static const struct arm64_ftr_bits ftr_raz[] = { ARM64_FTR_END, }; #define __ARM64_FTR_REG_OVERRIDE(id_str, id, table, ovr) { \ .sys_id = id, \ .reg = &(struct arm64_ftr_reg){ \ .name = id_str, \ .override = (ovr), \ .ftr_bits = &((table)[0]), \ }} #define ARM64_FTR_REG_OVERRIDE(id, table, ovr) \ __ARM64_FTR_REG_OVERRIDE(#id, id, table, ovr) #define ARM64_FTR_REG(id, table) \ __ARM64_FTR_REG_OVERRIDE(#id, id, table, &no_override) struct arm64_ftr_override id_aa64mmfr0_override; struct arm64_ftr_override id_aa64mmfr1_override; struct arm64_ftr_override id_aa64mmfr2_override; struct arm64_ftr_override id_aa64pfr0_override; struct arm64_ftr_override id_aa64pfr1_override; struct arm64_ftr_override id_aa64zfr0_override; struct arm64_ftr_override id_aa64smfr0_override; struct arm64_ftr_override id_aa64isar1_override; struct arm64_ftr_override id_aa64isar2_override; struct arm64_ftr_override arm64_sw_feature_override; static const struct __ftr_reg_entry { u32 sys_id; struct arm64_ftr_reg *reg; } arm64_ftr_regs[] = { /* Op1 = 0, CRn = 0, CRm = 1 */ ARM64_FTR_REG(SYS_ID_PFR0_EL1, ftr_id_pfr0), ARM64_FTR_REG(SYS_ID_PFR1_EL1, ftr_id_pfr1), ARM64_FTR_REG(SYS_ID_DFR0_EL1, ftr_id_dfr0), ARM64_FTR_REG(SYS_ID_MMFR0_EL1, ftr_id_mmfr0), ARM64_FTR_REG(SYS_ID_MMFR1_EL1, ftr_generic_32bits), ARM64_FTR_REG(SYS_ID_MMFR2_EL1, ftr_generic_32bits), ARM64_FTR_REG(SYS_ID_MMFR3_EL1, ftr_generic_32bits), /* Op1 = 0, CRn = 0, CRm = 2 */ ARM64_FTR_REG(SYS_ID_ISAR0_EL1, ftr_id_isar0), ARM64_FTR_REG(SYS_ID_ISAR1_EL1, ftr_generic_32bits), ARM64_FTR_REG(SYS_ID_ISAR2_EL1, ftr_generic_32bits), ARM64_FTR_REG(SYS_ID_ISAR3_EL1, ftr_generic_32bits), ARM64_FTR_REG(SYS_ID_ISAR4_EL1, ftr_id_isar4), ARM64_FTR_REG(SYS_ID_ISAR5_EL1, ftr_id_isar5), ARM64_FTR_REG(SYS_ID_MMFR4_EL1, ftr_id_mmfr4), ARM64_FTR_REG(SYS_ID_ISAR6_EL1, ftr_id_isar6), /* Op1 = 0, CRn = 0, CRm = 3 */ ARM64_FTR_REG(SYS_MVFR0_EL1, ftr_mvfr0), ARM64_FTR_REG(SYS_MVFR1_EL1, ftr_mvfr1), ARM64_FTR_REG(SYS_MVFR2_EL1, ftr_mvfr2), ARM64_FTR_REG(SYS_ID_PFR2_EL1, ftr_id_pfr2), ARM64_FTR_REG(SYS_ID_DFR1_EL1, ftr_id_dfr1), ARM64_FTR_REG(SYS_ID_MMFR5_EL1, ftr_id_mmfr5), /* Op1 = 0, CRn = 0, CRm = 4 */ ARM64_FTR_REG_OVERRIDE(SYS_ID_AA64PFR0_EL1, ftr_id_aa64pfr0, &id_aa64pfr0_override), ARM64_FTR_REG_OVERRIDE(SYS_ID_AA64PFR1_EL1, ftr_id_aa64pfr1, &id_aa64pfr1_override), ARM64_FTR_REG(SYS_ID_AA64PFR2_EL1, ftr_id_aa64pfr2), ARM64_FTR_REG_OVERRIDE(SYS_ID_AA64ZFR0_EL1, ftr_id_aa64zfr0, &id_aa64zfr0_override), ARM64_FTR_REG_OVERRIDE(SYS_ID_AA64SMFR0_EL1, ftr_id_aa64smfr0, &id_aa64smfr0_override), ARM64_FTR_REG(SYS_ID_AA64FPFR0_EL1, ftr_id_aa64fpfr0), /* Op1 = 0, CRn = 0, CRm = 5 */ ARM64_FTR_REG(SYS_ID_AA64DFR0_EL1, ftr_id_aa64dfr0), ARM64_FTR_REG(SYS_ID_AA64DFR1_EL1, ftr_raz), /* Op1 = 0, CRn = 0, CRm = 6 */ ARM64_FTR_REG(SYS_ID_AA64ISAR0_EL1, ftr_id_aa64isar0), ARM64_FTR_REG_OVERRIDE(SYS_ID_AA64ISAR1_EL1, ftr_id_aa64isar1, &id_aa64isar1_override), ARM64_FTR_REG_OVERRIDE(SYS_ID_AA64ISAR2_EL1, ftr_id_aa64isar2, &id_aa64isar2_override), ARM64_FTR_REG(SYS_ID_AA64ISAR3_EL1, ftr_id_aa64isar3), /* Op1 = 0, CRn = 0, CRm = 7 */ ARM64_FTR_REG_OVERRIDE(SYS_ID_AA64MMFR0_EL1, ftr_id_aa64mmfr0, &id_aa64mmfr0_override), ARM64_FTR_REG_OVERRIDE(SYS_ID_AA64MMFR1_EL1, ftr_id_aa64mmfr1, &id_aa64mmfr1_override), ARM64_FTR_REG_OVERRIDE(SYS_ID_AA64MMFR2_EL1, ftr_id_aa64mmfr2, &id_aa64mmfr2_override), ARM64_FTR_REG(SYS_ID_AA64MMFR3_EL1, ftr_id_aa64mmfr3), ARM64_FTR_REG(SYS_ID_AA64MMFR4_EL1, ftr_id_aa64mmfr4), /* Op1 = 0, CRn = 10, CRm = 4 */ ARM64_FTR_REG(SYS_MPAMIDR_EL1, ftr_mpamidr), /* Op1 = 1, CRn = 0, CRm = 0 */ ARM64_FTR_REG(SYS_GMID_EL1, ftr_gmid), /* Op1 = 3, CRn = 0, CRm = 0 */ { SYS_CTR_EL0, &arm64_ftr_reg_ctrel0 }, ARM64_FTR_REG(SYS_DCZID_EL0, ftr_dczid), /* Op1 = 3, CRn = 14, CRm = 0 */ ARM64_FTR_REG(SYS_CNTFRQ_EL0, ftr_single32), }; static int search_cmp_ftr_reg(const void *id, const void *regp) { return (int)(unsigned long)id - (int)((const struct __ftr_reg_entry *)regp)->sys_id; } /* * get_arm64_ftr_reg_nowarn - Looks up a feature register entry using * its sys_reg() encoding. With the array arm64_ftr_regs sorted in the * ascending order of sys_id, we use binary search to find a matching * entry. * * returns - Upon success, matching ftr_reg entry for id. * - NULL on failure. It is upto the caller to decide * the impact of a failure. */ static struct arm64_ftr_reg *get_arm64_ftr_reg_nowarn(u32 sys_id) { const struct __ftr_reg_entry *ret; ret = bsearch((const void *)(unsigned long)sys_id, arm64_ftr_regs, ARRAY_SIZE(arm64_ftr_regs), sizeof(arm64_ftr_regs[0]), search_cmp_ftr_reg); if (ret) return ret->reg; return NULL; } /* * get_arm64_ftr_reg - Looks up a feature register entry using * its sys_reg() encoding. This calls get_arm64_ftr_reg_nowarn(). * * returns - Upon success, matching ftr_reg entry for id. * - NULL on failure but with an WARN_ON(). */ struct arm64_ftr_reg *get_arm64_ftr_reg(u32 sys_id) { struct arm64_ftr_reg *reg; reg = get_arm64_ftr_reg_nowarn(sys_id); /* * Requesting a non-existent register search is an error. Warn * and let the caller handle it. */ WARN_ON(!reg); return reg; } static u64 arm64_ftr_set_value(const struct arm64_ftr_bits *ftrp, s64 reg, s64 ftr_val) { u64 mask = arm64_ftr_mask(ftrp); reg &= ~mask; reg |= (ftr_val << ftrp->shift) & mask; return reg; } s64 arm64_ftr_safe_value(const struct arm64_ftr_bits *ftrp, s64 new, s64 cur) { s64 ret = 0; switch (ftrp->type) { case FTR_EXACT: ret = ftrp->safe_val; break; case FTR_LOWER_SAFE: ret = min(new, cur); break; case FTR_HIGHER_OR_ZERO_SAFE: if (!cur || !new) break; fallthrough; case FTR_HIGHER_SAFE: ret = max(new, cur); break; default: BUG(); } return ret; } static void __init sort_ftr_regs(void) { unsigned int i; for (i = 0; i < ARRAY_SIZE(arm64_ftr_regs); i++) { const struct arm64_ftr_reg *ftr_reg = arm64_ftr_regs[i].reg; const struct arm64_ftr_bits *ftr_bits = ftr_reg->ftr_bits; unsigned int j = 0; /* * Features here must be sorted in descending order with respect * to their shift values and should not overlap with each other. */ for (; ftr_bits->width != 0; ftr_bits++, j++) { unsigned int width = ftr_reg->ftr_bits[j].width; unsigned int shift = ftr_reg->ftr_bits[j].shift; unsigned int prev_shift; WARN((shift + width) > 64, "%s has invalid feature at shift %d\n", ftr_reg->name, shift); /* * Skip the first feature. There is nothing to * compare against for now. */ if (j == 0) continue; prev_shift = ftr_reg->ftr_bits[j - 1].shift; WARN((shift + width) > prev_shift, "%s has feature overlap at shift %d\n", ftr_reg->name, shift); } /* * Skip the first register. There is nothing to * compare against for now. */ if (i == 0) continue; /* * Registers here must be sorted in ascending order with respect * to sys_id for subsequent binary search in get_arm64_ftr_reg() * to work correctly. */ BUG_ON(arm64_ftr_regs[i].sys_id <= arm64_ftr_regs[i - 1].sys_id); } } /* * Initialise the CPU feature register from Boot CPU values. * Also initiliases the strict_mask for the register. * Any bits that are not covered by an arm64_ftr_bits entry are considered * RES0 for the system-wide value, and must strictly match. */ static void init_cpu_ftr_reg(u32 sys_reg, u64 new) { u64 val = 0; u64 strict_mask = ~0x0ULL; u64 user_mask = 0; u64 valid_mask = 0; const struct arm64_ftr_bits *ftrp; struct arm64_ftr_reg *reg = get_arm64_ftr_reg(sys_reg); if (!reg) return; for (ftrp = reg->ftr_bits; ftrp->width; ftrp++) { u64 ftr_mask = arm64_ftr_mask(ftrp); s64 ftr_new = arm64_ftr_value(ftrp, new); s64 ftr_ovr = arm64_ftr_value(ftrp, reg->override->val); if ((ftr_mask & reg->override->mask) == ftr_mask) { s64 tmp = arm64_ftr_safe_value(ftrp, ftr_ovr, ftr_new); char *str = NULL; if (ftr_ovr != tmp) { /* Unsafe, remove the override */ reg->override->mask &= ~ftr_mask; reg->override->val &= ~ftr_mask; tmp = ftr_ovr; str = "ignoring override"; } else if (ftr_new != tmp) { /* Override was valid */ ftr_new = tmp; str = "forced"; } else { /* Override was the safe value */ str = "already set"; } pr_warn("%s[%d:%d]: %s to %llx\n", reg->name, ftrp->shift + ftrp->width - 1, ftrp->shift, str, tmp & (BIT(ftrp->width) - 1)); } else if ((ftr_mask & reg->override->val) == ftr_mask) { reg->override->val &= ~ftr_mask; pr_warn("%s[%d:%d]: impossible override, ignored\n", reg->name, ftrp->shift + ftrp->width - 1, ftrp->shift); } val = arm64_ftr_set_value(ftrp, val, ftr_new); valid_mask |= ftr_mask; if (!ftrp->strict) strict_mask &= ~ftr_mask; if (ftrp->visible) user_mask |= ftr_mask; else reg->user_val = arm64_ftr_set_value(ftrp, reg->user_val, ftrp->safe_val); } val &= valid_mask; reg->sys_val = val; reg->strict_mask = strict_mask; reg->user_mask = user_mask; } extern const struct arm64_cpu_capabilities arm64_errata[]; static const struct arm64_cpu_capabilities arm64_features[]; static void __init init_cpucap_indirect_list_from_array(const struct arm64_cpu_capabilities *caps) { for (; caps->matches; caps++) { if (WARN(caps->capability >= ARM64_NCAPS, "Invalid capability %d\n", caps->capability)) continue; if (WARN(cpucap_ptrs[caps->capability], "Duplicate entry for capability %d\n", caps->capability)) continue; cpucap_ptrs[caps->capability] = caps; } } static void __init init_cpucap_indirect_list(void) { init_cpucap_indirect_list_from_array(arm64_features); init_cpucap_indirect_list_from_array(arm64_errata); } static void __init setup_boot_cpu_capabilities(void); static void init_32bit_cpu_features(struct cpuinfo_32bit *info) { init_cpu_ftr_reg(SYS_ID_DFR0_EL1, info->reg_id_dfr0); init_cpu_ftr_reg(SYS_ID_DFR1_EL1, info->reg_id_dfr1); init_cpu_ftr_reg(SYS_ID_ISAR0_EL1, info->reg_id_isar0); init_cpu_ftr_reg(SYS_ID_ISAR1_EL1, info->reg_id_isar1); init_cpu_ftr_reg(SYS_ID_ISAR2_EL1, info->reg_id_isar2); init_cpu_ftr_reg(SYS_ID_ISAR3_EL1, info->reg_id_isar3); init_cpu_ftr_reg(SYS_ID_ISAR4_EL1, info->reg_id_isar4); init_cpu_ftr_reg(SYS_ID_ISAR5_EL1, info->reg_id_isar5); init_cpu_ftr_reg(SYS_ID_ISAR6_EL1, info->reg_id_isar6); init_cpu_ftr_reg(SYS_ID_MMFR0_EL1, info->reg_id_mmfr0); init_cpu_ftr_reg(SYS_ID_MMFR1_EL1, info->reg_id_mmfr1); init_cpu_ftr_reg(SYS_ID_MMFR2_EL1, info->reg_id_mmfr2); init_cpu_ftr_reg(SYS_ID_MMFR3_EL1, info->reg_id_mmfr3); init_cpu_ftr_reg(SYS_ID_MMFR4_EL1, info->reg_id_mmfr4); init_cpu_ftr_reg(SYS_ID_MMFR5_EL1, info->reg_id_mmfr5); init_cpu_ftr_reg(SYS_ID_PFR0_EL1, info->reg_id_pfr0); init_cpu_ftr_reg(SYS_ID_PFR1_EL1, info->reg_id_pfr1); init_cpu_ftr_reg(SYS_ID_PFR2_EL1, info->reg_id_pfr2); init_cpu_ftr_reg(SYS_MVFR0_EL1, info->reg_mvfr0); init_cpu_ftr_reg(SYS_MVFR1_EL1, info->reg_mvfr1); init_cpu_ftr_reg(SYS_MVFR2_EL1, info->reg_mvfr2); } #ifdef CONFIG_ARM64_PSEUDO_NMI static bool enable_pseudo_nmi; static int __init early_enable_pseudo_nmi(char *p) { return kstrtobool(p, &enable_pseudo_nmi); } early_param("irqchip.gicv3_pseudo_nmi", early_enable_pseudo_nmi); static __init void detect_system_supports_pseudo_nmi(void) { struct device_node *np; if (!enable_pseudo_nmi) return; /* * Detect broken MediaTek firmware that doesn't properly save and * restore GIC priorities. */ np = of_find_compatible_node(NULL, NULL, "arm,gic-v3"); if (np && of_property_read_bool(np, "mediatek,broken-save-restore-fw")) { pr_info("Pseudo-NMI disabled due to MediaTek Chromebook GICR save problem\n"); enable_pseudo_nmi = false; } of_node_put(np); } #else /* CONFIG_ARM64_PSEUDO_NMI */ static inline void detect_system_supports_pseudo_nmi(void) { } #endif void __init init_cpu_features(struct cpuinfo_arm64 *info) { /* Before we start using the tables, make sure it is sorted */ sort_ftr_regs(); init_cpu_ftr_reg(SYS_CTR_EL0, info->reg_ctr); init_cpu_ftr_reg(SYS_DCZID_EL0, info->reg_dczid); init_cpu_ftr_reg(SYS_CNTFRQ_EL0, info->reg_cntfrq); init_cpu_ftr_reg(SYS_ID_AA64DFR0_EL1, info->reg_id_aa64dfr0); init_cpu_ftr_reg(SYS_ID_AA64DFR1_EL1, info->reg_id_aa64dfr1); init_cpu_ftr_reg(SYS_ID_AA64ISAR0_EL1, info->reg_id_aa64isar0); init_cpu_ftr_reg(SYS_ID_AA64ISAR1_EL1, info->reg_id_aa64isar1); init_cpu_ftr_reg(SYS_ID_AA64ISAR2_EL1, info->reg_id_aa64isar2); init_cpu_ftr_reg(SYS_ID_AA64ISAR3_EL1, info->reg_id_aa64isar3); init_cpu_ftr_reg(SYS_ID_AA64MMFR0_EL1, info->reg_id_aa64mmfr0); init_cpu_ftr_reg(SYS_ID_AA64MMFR1_EL1, info->reg_id_aa64mmfr1); init_cpu_ftr_reg(SYS_ID_AA64MMFR2_EL1, info->reg_id_aa64mmfr2); init_cpu_ftr_reg(SYS_ID_AA64MMFR3_EL1, info->reg_id_aa64mmfr3); init_cpu_ftr_reg(SYS_ID_AA64MMFR4_EL1, info->reg_id_aa64mmfr4); init_cpu_ftr_reg(SYS_ID_AA64PFR0_EL1, info->reg_id_aa64pfr0); init_cpu_ftr_reg(SYS_ID_AA64PFR1_EL1, info->reg_id_aa64pfr1); init_cpu_ftr_reg(SYS_ID_AA64PFR2_EL1, info->reg_id_aa64pfr2); init_cpu_ftr_reg(SYS_ID_AA64ZFR0_EL1, info->reg_id_aa64zfr0); init_cpu_ftr_reg(SYS_ID_AA64SMFR0_EL1, info->reg_id_aa64smfr0); init_cpu_ftr_reg(SYS_ID_AA64FPFR0_EL1, info->reg_id_aa64fpfr0); if (id_aa64pfr0_32bit_el0(info->reg_id_aa64pfr0)) init_32bit_cpu_features(&info->aarch32); if (IS_ENABLED(CONFIG_ARM64_SVE) && id_aa64pfr0_sve(read_sanitised_ftr_reg(SYS_ID_AA64PFR0_EL1))) { unsigned long cpacr = cpacr_save_enable_kernel_sve(); vec_init_vq_map(ARM64_VEC_SVE); cpacr_restore(cpacr); } if (IS_ENABLED(CONFIG_ARM64_SME) && id_aa64pfr1_sme(read_sanitised_ftr_reg(SYS_ID_AA64PFR1_EL1))) { unsigned long cpacr = cpacr_save_enable_kernel_sme(); /* * We mask out SMPS since even if the hardware * supports priorities the kernel does not at present * and we block access to them. */ info->reg_smidr = read_cpuid(SMIDR_EL1) & ~SMIDR_EL1_SMPS; vec_init_vq_map(ARM64_VEC_SME); cpacr_restore(cpacr); } if (id_aa64pfr0_mpam(info->reg_id_aa64pfr0)) init_cpu_ftr_reg(SYS_MPAMIDR_EL1, info->reg_mpamidr); if (id_aa64pfr1_mte(info->reg_id_aa64pfr1)) init_cpu_ftr_reg(SYS_GMID_EL1, info->reg_gmid); } static void update_cpu_ftr_reg(struct arm64_ftr_reg *reg, u64 new) { const struct arm64_ftr_bits *ftrp; for (ftrp = reg->ftr_bits; ftrp->width; ftrp++) { s64 ftr_cur = arm64_ftr_value(ftrp, reg->sys_val); s64 ftr_new = arm64_ftr_value(ftrp, new); if (ftr_cur == ftr_new) continue; /* Find a safe value */ ftr_new = arm64_ftr_safe_value(ftrp, ftr_new, ftr_cur); reg->sys_val = arm64_ftr_set_value(ftrp, reg->sys_val, ftr_new); } } static int check_update_ftr_reg(u32 sys_id, int cpu, u64 val, u64 boot) { struct arm64_ftr_reg *regp = get_arm64_ftr_reg(sys_id); if (!regp) return 0; update_cpu_ftr_reg(regp, val); if ((boot & regp->strict_mask) == (val & regp->strict_mask)) return 0; pr_warn("SANITY CHECK: Unexpected variation in %s. Boot CPU: %#016llx, CPU%d: %#016llx\n", regp->name, boot, cpu, val); return 1; } static void relax_cpu_ftr_reg(u32 sys_id, int field) { const struct arm64_ftr_bits *ftrp; struct arm64_ftr_reg *regp = get_arm64_ftr_reg(sys_id); if (!regp) return; for (ftrp = regp->ftr_bits; ftrp->width; ftrp++) { if (ftrp->shift == field) { regp->strict_mask &= ~arm64_ftr_mask(ftrp); break; } } /* Bogus field? */ WARN_ON(!ftrp->width); } static void lazy_init_32bit_cpu_features(struct cpuinfo_arm64 *info, struct cpuinfo_arm64 *boot) { static bool boot_cpu_32bit_regs_overridden = false; if (!allow_mismatched_32bit_el0 || boot_cpu_32bit_regs_overridden) return; if (id_aa64pfr0_32bit_el0(boot->reg_id_aa64pfr0)) return; boot->aarch32 = info->aarch32; init_32bit_cpu_features(&boot->aarch32); boot_cpu_32bit_regs_overridden = true; } static int update_32bit_cpu_features(int cpu, struct cpuinfo_32bit *info, struct cpuinfo_32bit *boot) { int taint = 0; u64 pfr0 = read_sanitised_ftr_reg(SYS_ID_AA64PFR0_EL1); /* * If we don't have AArch32 at EL1, then relax the strictness of * EL1-dependent register fields to avoid spurious sanity check fails. */ if (!id_aa64pfr0_32bit_el1(pfr0)) { relax_cpu_ftr_reg(SYS_ID_ISAR4_EL1, ID_ISAR4_EL1_SMC_SHIFT); relax_cpu_ftr_reg(SYS_ID_PFR1_EL1, ID_PFR1_EL1_Virt_frac_SHIFT); relax_cpu_ftr_reg(SYS_ID_PFR1_EL1, ID_PFR1_EL1_Sec_frac_SHIFT); relax_cpu_ftr_reg(SYS_ID_PFR1_EL1, ID_PFR1_EL1_Virtualization_SHIFT); relax_cpu_ftr_reg(SYS_ID_PFR1_EL1, ID_PFR1_EL1_Security_SHIFT); relax_cpu_ftr_reg(SYS_ID_PFR1_EL1, ID_PFR1_EL1_ProgMod_SHIFT); } taint |= check_update_ftr_reg(SYS_ID_DFR0_EL1, cpu, info->reg_id_dfr0, boot->reg_id_dfr0); taint |= check_update_ftr_reg(SYS_ID_DFR1_EL1, cpu, info->reg_id_dfr1, boot->reg_id_dfr1); taint |= check_update_ftr_reg(SYS_ID_ISAR0_EL1, cpu, info->reg_id_isar0, boot->reg_id_isar0); taint |= check_update_ftr_reg(SYS_ID_ISAR1_EL1, cpu, info->reg_id_isar1, boot->reg_id_isar1); taint |= check_update_ftr_reg(SYS_ID_ISAR2_EL1, cpu, info->reg_id_isar2, boot->reg_id_isar2); taint |= check_update_ftr_reg(SYS_ID_ISAR3_EL1, cpu, info->reg_id_isar3, boot->reg_id_isar3); taint |= check_update_ftr_reg(SYS_ID_ISAR4_EL1, cpu, info->reg_id_isar4, boot->reg_id_isar4); taint |= check_update_ftr_reg(SYS_ID_ISAR5_EL1, cpu, info->reg_id_isar5, boot->reg_id_isar5); taint |= check_update_ftr_reg(SYS_ID_ISAR6_EL1, cpu, info->reg_id_isar6, boot->reg_id_isar6); /* * Regardless of the value of the AuxReg field, the AIFSR, ADFSR, and * ACTLR formats could differ across CPUs and therefore would have to * be trapped for virtualization anyway. */ taint |= check_update_ftr_reg(SYS_ID_MMFR0_EL1, cpu, info->reg_id_mmfr0, boot->reg_id_mmfr0); taint |= check_update_ftr_reg(SYS_ID_MMFR1_EL1, cpu, info->reg_id_mmfr1, boot->reg_id_mmfr1); taint |= check_update_ftr_reg(SYS_ID_MMFR2_EL1, cpu, info->reg_id_mmfr2, boot->reg_id_mmfr2); taint |= check_update_ftr_reg(SYS_ID_MMFR3_EL1, cpu, info->reg_id_mmfr3, boot->reg_id_mmfr3); taint |= check_update_ftr_reg(SYS_ID_MMFR4_EL1, cpu, info->reg_id_mmfr4, boot->reg_id_mmfr4); taint |= check_update_ftr_reg(SYS_ID_MMFR5_EL1, cpu, info->reg_id_mmfr5, boot->reg_id_mmfr5); taint |= check_update_ftr_reg(SYS_ID_PFR0_EL1, cpu, info->reg_id_pfr0, boot->reg_id_pfr0); taint |= check_update_ftr_reg(SYS_ID_PFR1_EL1, cpu, info->reg_id_pfr1, boot->reg_id_pfr1); taint |= check_update_ftr_reg(SYS_ID_PFR2_EL1, cpu, info->reg_id_pfr2, boot->reg_id_pfr2); taint |= check_update_ftr_reg(SYS_MVFR0_EL1, cpu, info->reg_mvfr0, boot->reg_mvfr0); taint |= check_update_ftr_reg(SYS_MVFR1_EL1, cpu, info->reg_mvfr1, boot->reg_mvfr1); taint |= check_update_ftr_reg(SYS_MVFR2_EL1, cpu, info->reg_mvfr2, boot->reg_mvfr2); return taint; } /* * Update system wide CPU feature registers with the values from a * non-boot CPU. Also performs SANITY checks to make sure that there * aren't any insane variations from that of the boot CPU. */ void update_cpu_features(int cpu, struct cpuinfo_arm64 *info, struct cpuinfo_arm64 *boot) { int taint = 0; /* * The kernel can handle differing I-cache policies, but otherwise * caches should look identical. Userspace JITs will make use of * *minLine. */ taint |= check_update_ftr_reg(SYS_CTR_EL0, cpu, info->reg_ctr, boot->reg_ctr); /* * Userspace may perform DC ZVA instructions. Mismatched block sizes * could result in too much or too little memory being zeroed if a * process is preempted and migrated between CPUs. */ taint |= check_update_ftr_reg(SYS_DCZID_EL0, cpu, info->reg_dczid, boot->reg_dczid); /* If different, timekeeping will be broken (especially with KVM) */ taint |= check_update_ftr_reg(SYS_CNTFRQ_EL0, cpu, info->reg_cntfrq, boot->reg_cntfrq); /* * The kernel uses self-hosted debug features and expects CPUs to * support identical debug features. We presently need CTX_CMPs, WRPs, * and BRPs to be identical. * ID_AA64DFR1 is currently RES0. */ taint |= check_update_ftr_reg(SYS_ID_AA64DFR0_EL1, cpu, info->reg_id_aa64dfr0, boot->reg_id_aa64dfr0); taint |= check_update_ftr_reg(SYS_ID_AA64DFR1_EL1, cpu, info->reg_id_aa64dfr1, boot->reg_id_aa64dfr1); /* * Even in big.LITTLE, processors should be identical instruction-set * wise. */ taint |= check_update_ftr_reg(SYS_ID_AA64ISAR0_EL1, cpu, info->reg_id_aa64isar0, boot->reg_id_aa64isar0); taint |= check_update_ftr_reg(SYS_ID_AA64ISAR1_EL1, cpu, info->reg_id_aa64isar1, boot->reg_id_aa64isar1); taint |= check_update_ftr_reg(SYS_ID_AA64ISAR2_EL1, cpu, info->reg_id_aa64isar2, boot->reg_id_aa64isar2); taint |= check_update_ftr_reg(SYS_ID_AA64ISAR3_EL1, cpu, info->reg_id_aa64isar3, boot->reg_id_aa64isar3); /* * Differing PARange support is fine as long as all peripherals and * memory are mapped within the minimum PARange of all CPUs. * Linux should not care about secure memory. */ taint |= check_update_ftr_reg(SYS_ID_AA64MMFR0_EL1, cpu, info->reg_id_aa64mmfr0, boot->reg_id_aa64mmfr0); taint |= check_update_ftr_reg(SYS_ID_AA64MMFR1_EL1, cpu, info->reg_id_aa64mmfr1, boot->reg_id_aa64mmfr1); taint |= check_update_ftr_reg(SYS_ID_AA64MMFR2_EL1, cpu, info->reg_id_aa64mmfr2, boot->reg_id_aa64mmfr2); taint |= check_update_ftr_reg(SYS_ID_AA64MMFR3_EL1, cpu, info->reg_id_aa64mmfr3, boot->reg_id_aa64mmfr3); taint |= check_update_ftr_reg(SYS_ID_AA64PFR0_EL1, cpu, info->reg_id_aa64pfr0, boot->reg_id_aa64pfr0); taint |= check_update_ftr_reg(SYS_ID_AA64PFR1_EL1, cpu, info->reg_id_aa64pfr1, boot->reg_id_aa64pfr1); taint |= check_update_ftr_reg(SYS_ID_AA64PFR2_EL1, cpu, info->reg_id_aa64pfr2, boot->reg_id_aa64pfr2); taint |= check_update_ftr_reg(SYS_ID_AA64ZFR0_EL1, cpu, info->reg_id_aa64zfr0, boot->reg_id_aa64zfr0); taint |= check_update_ftr_reg(SYS_ID_AA64SMFR0_EL1, cpu, info->reg_id_aa64smfr0, boot->reg_id_aa64smfr0); taint |= check_update_ftr_reg(SYS_ID_AA64FPFR0_EL1, cpu, info->reg_id_aa64fpfr0, boot->reg_id_aa64fpfr0); /* Probe vector lengths */ if (IS_ENABLED(CONFIG_ARM64_SVE) && id_aa64pfr0_sve(read_sanitised_ftr_reg(SYS_ID_AA64PFR0_EL1))) { if (!system_capabilities_finalized()) { unsigned long cpacr = cpacr_save_enable_kernel_sve(); vec_update_vq_map(ARM64_VEC_SVE); cpacr_restore(cpacr); } } if (IS_ENABLED(CONFIG_ARM64_SME) && id_aa64pfr1_sme(read_sanitised_ftr_reg(SYS_ID_AA64PFR1_EL1))) { unsigned long cpacr = cpacr_save_enable_kernel_sme(); /* * We mask out SMPS since even if the hardware * supports priorities the kernel does not at present * and we block access to them. */ info->reg_smidr = read_cpuid(SMIDR_EL1) & ~SMIDR_EL1_SMPS; /* Probe vector lengths */ if (!system_capabilities_finalized()) vec_update_vq_map(ARM64_VEC_SME); cpacr_restore(cpacr); } if (id_aa64pfr0_mpam(info->reg_id_aa64pfr0)) { taint |= check_update_ftr_reg(SYS_MPAMIDR_EL1, cpu, info->reg_mpamidr, boot->reg_mpamidr); } /* * The kernel uses the LDGM/STGM instructions and the number of tags * they read/write depends on the GMID_EL1.BS field. Check that the * value is the same on all CPUs. */ if (IS_ENABLED(CONFIG_ARM64_MTE) && id_aa64pfr1_mte(info->reg_id_aa64pfr1)) { taint |= check_update_ftr_reg(SYS_GMID_EL1, cpu, info->reg_gmid, boot->reg_gmid); } /* * If we don't have AArch32 at all then skip the checks entirely * as the register values may be UNKNOWN and we're not going to be * using them for anything. * * This relies on a sanitised view of the AArch64 ID registers * (e.g. SYS_ID_AA64PFR0_EL1), so we call it last. */ if (id_aa64pfr0_32bit_el0(info->reg_id_aa64pfr0)) { lazy_init_32bit_cpu_features(info, boot); taint |= update_32bit_cpu_features(cpu, &info->aarch32, &boot->aarch32); } /* * Mismatched CPU features are a recipe for disaster. Don't even * pretend to support them. */ if (taint) { pr_warn_once("Unsupported CPU feature variation detected.\n"); add_taint(TAINT_CPU_OUT_OF_SPEC, LOCKDEP_STILL_OK); } } u64 read_sanitised_ftr_reg(u32 id) { struct arm64_ftr_reg *regp = get_arm64_ftr_reg(id); if (!regp) return 0; return regp->sys_val; } EXPORT_SYMBOL_GPL(read_sanitised_ftr_reg); #define read_sysreg_case(r) \ case r: val = read_sysreg_s(r); break; /* * __read_sysreg_by_encoding() - Used by a STARTING cpu before cpuinfo is populated. * Read the system register on the current CPU */ u64 __read_sysreg_by_encoding(u32 sys_id) { struct arm64_ftr_reg *regp; u64 val; switch (sys_id) { read_sysreg_case(SYS_ID_PFR0_EL1); read_sysreg_case(SYS_ID_PFR1_EL1); read_sysreg_case(SYS_ID_PFR2_EL1); read_sysreg_case(SYS_ID_DFR0_EL1); read_sysreg_case(SYS_ID_DFR1_EL1); read_sysreg_case(SYS_ID_MMFR0_EL1); read_sysreg_case(SYS_ID_MMFR1_EL1); read_sysreg_case(SYS_ID_MMFR2_EL1); read_sysreg_case(SYS_ID_MMFR3_EL1); read_sysreg_case(SYS_ID_MMFR4_EL1); read_sysreg_case(SYS_ID_MMFR5_EL1); read_sysreg_case(SYS_ID_ISAR0_EL1); read_sysreg_case(SYS_ID_ISAR1_EL1); read_sysreg_case(SYS_ID_ISAR2_EL1); read_sysreg_case(SYS_ID_ISAR3_EL1); read_sysreg_case(SYS_ID_ISAR4_EL1); read_sysreg_case(SYS_ID_ISAR5_EL1); read_sysreg_case(SYS_ID_ISAR6_EL1); read_sysreg_case(SYS_MVFR0_EL1); read_sysreg_case(SYS_MVFR1_EL1); read_sysreg_case(SYS_MVFR2_EL1); read_sysreg_case(SYS_ID_AA64PFR0_EL1); read_sysreg_case(SYS_ID_AA64PFR1_EL1); read_sysreg_case(SYS_ID_AA64PFR2_EL1); read_sysreg_case(SYS_ID_AA64ZFR0_EL1); read_sysreg_case(SYS_ID_AA64SMFR0_EL1); read_sysreg_case(SYS_ID_AA64FPFR0_EL1); read_sysreg_case(SYS_ID_AA64DFR0_EL1); read_sysreg_case(SYS_ID_AA64DFR1_EL1); read_sysreg_case(SYS_ID_AA64MMFR0_EL1); read_sysreg_case(SYS_ID_AA64MMFR1_EL1); read_sysreg_case(SYS_ID_AA64MMFR2_EL1); read_sysreg_case(SYS_ID_AA64MMFR3_EL1); read_sysreg_case(SYS_ID_AA64MMFR4_EL1); read_sysreg_case(SYS_ID_AA64ISAR0_EL1); read_sysreg_case(SYS_ID_AA64ISAR1_EL1); read_sysreg_case(SYS_ID_AA64ISAR2_EL1); read_sysreg_case(SYS_ID_AA64ISAR3_EL1); read_sysreg_case(SYS_CNTFRQ_EL0); read_sysreg_case(SYS_CTR_EL0); read_sysreg_case(SYS_DCZID_EL0); default: BUG(); return 0; } regp = get_arm64_ftr_reg(sys_id); if (regp) { val &= ~regp->override->mask; val |= (regp->override->val & regp->override->mask); } return val; } #include <linux/irqchip/arm-gic-v3.h> static bool has_always(const struct arm64_cpu_capabilities *entry, int scope) { return true; } static bool feature_matches(u64 reg, const struct arm64_cpu_capabilities *entry) { int val, min, max; u64 tmp; val = cpuid_feature_extract_field_width(reg, entry->field_pos, entry->field_width, entry->sign); tmp = entry->min_field_value; tmp <<= entry->field_pos; min = cpuid_feature_extract_field_width(tmp, entry->field_pos, entry->field_width, entry->sign); tmp = entry->max_field_value; tmp <<= entry->field_pos; max = cpuid_feature_extract_field_width(tmp, entry->field_pos, entry->field_width, entry->sign); return val >= min && val <= max; } static u64 read_scoped_sysreg(const struct arm64_cpu_capabilities *entry, int scope) { WARN_ON(scope == SCOPE_LOCAL_CPU && preemptible()); if (scope == SCOPE_SYSTEM) return read_sanitised_ftr_reg(entry->sys_reg); else return __read_sysreg_by_encoding(entry->sys_reg); } static bool has_user_cpuid_feature(const struct arm64_cpu_capabilities *entry, int scope) { int mask; struct arm64_ftr_reg *regp; u64 val = read_scoped_sysreg(entry, scope); regp = get_arm64_ftr_reg(entry->sys_reg); if (!regp) return false; mask = cpuid_feature_extract_unsigned_field_width(regp->user_mask, entry->field_pos, entry->field_width); if (!mask) return false; return feature_matches(val, entry); } static bool has_cpuid_feature(const struct arm64_cpu_capabilities *entry, int scope) { u64 val = read_scoped_sysreg(entry, scope); return feature_matches(val, entry); } const struct cpumask *system_32bit_el0_cpumask(void) { if (!system_supports_32bit_el0()) return cpu_none_mask; if (static_branch_unlikely(&arm64_mismatched_32bit_el0)) return cpu_32bit_el0_mask; return cpu_possible_mask; } static int __init parse_32bit_el0_param(char *str) { allow_mismatched_32bit_el0 = true; return 0; } early_param("allow_mismatched_32bit_el0", parse_32bit_el0_param); static ssize_t aarch32_el0_show(struct device *dev, struct device_attribute *attr, char *buf) { const struct cpumask *mask = system_32bit_el0_cpumask(); return sysfs_emit(buf, "%*pbl\n", cpumask_pr_args(mask)); } static const DEVICE_ATTR_RO(aarch32_el0); static int __init aarch32_el0_sysfs_init(void) { struct device *dev_root; int ret = 0; if (!allow_mismatched_32bit_el0) return 0; dev_root = bus_get_dev_root(&cpu_subsys); if (dev_root) { ret = device_create_file(dev_root, &dev_attr_aarch32_el0); put_device(dev_root); } return ret; } device_initcall(aarch32_el0_sysfs_init); static bool has_32bit_el0(const struct arm64_cpu_capabilities *entry, int scope) { if (!has_cpuid_feature(entry, scope)) return allow_mismatched_32bit_el0; if (scope == SCOPE_SYSTEM) pr_info("detected: 32-bit EL0 Support\n"); return true; } static bool has_useable_gicv3_cpuif(const struct arm64_cpu_capabilities *entry, int scope) { bool has_sre; if (!has_cpuid_feature(entry, scope)) return false; has_sre = gic_enable_sre(); if (!has_sre) pr_warn_once("%s present but disabled by higher exception level\n", entry->desc); return has_sre; } static bool has_cache_idc(const struct arm64_cpu_capabilities *entry, int scope) { u64 ctr; if (scope == SCOPE_SYSTEM) ctr = arm64_ftr_reg_ctrel0.sys_val; else ctr = read_cpuid_effective_cachetype(); return ctr & BIT(CTR_EL0_IDC_SHIFT); } static void cpu_emulate_effective_ctr(const struct arm64_cpu_capabilities *__unused) { /* * If the CPU exposes raw CTR_EL0.IDC = 0, while effectively * CTR_EL0.IDC = 1 (from CLIDR values), we need to trap accesses * to the CTR_EL0 on this CPU and emulate it with the real/safe * value. */ if (!(read_cpuid_cachetype() & BIT(CTR_EL0_IDC_SHIFT))) sysreg_clear_set(sctlr_el1, SCTLR_EL1_UCT, 0); } static bool has_cache_dic(const struct arm64_cpu_capabilities *entry, int scope) { u64 ctr; if (scope == SCOPE_SYSTEM) ctr = arm64_ftr_reg_ctrel0.sys_val; else ctr = read_cpuid_cachetype(); return ctr & BIT(CTR_EL0_DIC_SHIFT); } static bool __maybe_unused has_useable_cnp(const struct arm64_cpu_capabilities *entry, int scope) { /* * Kdump isn't guaranteed to power-off all secondary CPUs, CNP * may share TLB entries with a CPU stuck in the crashed * kernel. */ if (is_kdump_kernel()) return false; if (cpus_have_cap(ARM64_WORKAROUND_NVIDIA_CARMEL_CNP)) return false; return has_cpuid_feature(entry, scope); } static bool __meltdown_safe = true; static int __kpti_forced; /* 0: not forced, >0: forced on, <0: forced off */ static bool unmap_kernel_at_el0(const struct arm64_cpu_capabilities *entry, int scope) { /* List of CPUs that are not vulnerable and don't need KPTI */ static const struct midr_range kpti_safe_list[] = { MIDR_ALL_VERSIONS(MIDR_CAVIUM_THUNDERX2), MIDR_ALL_VERSIONS(MIDR_BRCM_VULCAN), MIDR_ALL_VERSIONS(MIDR_BRAHMA_B53), MIDR_ALL_VERSIONS(MIDR_CORTEX_A35), MIDR_ALL_VERSIONS(MIDR_CORTEX_A53), MIDR_ALL_VERSIONS(MIDR_CORTEX_A55), MIDR_ALL_VERSIONS(MIDR_CORTEX_A57), MIDR_ALL_VERSIONS(MIDR_CORTEX_A72), MIDR_ALL_VERSIONS(MIDR_CORTEX_A73), MIDR_ALL_VERSIONS(MIDR_HISI_TSV110), MIDR_ALL_VERSIONS(MIDR_NVIDIA_CARMEL), MIDR_ALL_VERSIONS(MIDR_QCOM_KRYO_2XX_GOLD), MIDR_ALL_VERSIONS(MIDR_QCOM_KRYO_2XX_SILVER), MIDR_ALL_VERSIONS(MIDR_QCOM_KRYO_3XX_SILVER), MIDR_ALL_VERSIONS(MIDR_QCOM_KRYO_4XX_SILVER), { /* sentinel */ } }; char const *str = "kpti command line option"; bool meltdown_safe; meltdown_safe = is_midr_in_range_list(read_cpuid_id(), kpti_safe_list); /* Defer to CPU feature registers */ if (has_cpuid_feature(entry, scope)) meltdown_safe = true; if (!meltdown_safe) __meltdown_safe = false; /* * For reasons that aren't entirely clear, enabling KPTI on Cavium * ThunderX leads to apparent I-cache corruption of kernel text, which * ends as well as you might imagine. Don't even try. We cannot rely * on the cpus_have_*cap() helpers here to detect the CPU erratum * because cpucap detection order may change. However, since we know * affected CPUs are always in a homogeneous configuration, it is * safe to rely on this_cpu_has_cap() here. */ if (this_cpu_has_cap(ARM64_WORKAROUND_CAVIUM_27456)) { str = "ARM64_WORKAROUND_CAVIUM_27456"; __kpti_forced = -1; } /* Useful for KASLR robustness */ if (kaslr_enabled() && kaslr_requires_kpti()) { if (!__kpti_forced) { str = "KASLR"; __kpti_forced = 1; } } if (cpu_mitigations_off() && !__kpti_forced) { str = "mitigations=off"; __kpti_forced = -1; } if (!IS_ENABLED(CONFIG_UNMAP_KERNEL_AT_EL0)) { pr_info_once("kernel page table isolation disabled by kernel configuration\n"); return false; } /* Forced? */ if (__kpti_forced) { pr_info_once("kernel page table isolation forced %s by %s\n", __kpti_forced > 0 ? "ON" : "OFF", str); return __kpti_forced > 0; } return !meltdown_safe; } static bool has_nv1(const struct arm64_cpu_capabilities *entry, int scope) { /* * Although the Apple M2 family appears to support NV1, the * PTW barfs on the nVHE EL2 S1 page table format. Pretend * that it doesn't support NV1 at all. */ static const struct midr_range nv1_ni_list[] = { MIDR_ALL_VERSIONS(MIDR_APPLE_M2_BLIZZARD), MIDR_ALL_VERSIONS(MIDR_APPLE_M2_AVALANCHE), MIDR_ALL_VERSIONS(MIDR_APPLE_M2_BLIZZARD_PRO), MIDR_ALL_VERSIONS(MIDR_APPLE_M2_AVALANCHE_PRO), MIDR_ALL_VERSIONS(MIDR_APPLE_M2_BLIZZARD_MAX), MIDR_ALL_VERSIONS(MIDR_APPLE_M2_AVALANCHE_MAX), {} }; return (__system_matches_cap(ARM64_HAS_NESTED_VIRT) && !(has_cpuid_feature(entry, scope) || is_midr_in_range_list(read_cpuid_id(), nv1_ni_list))); } #if defined(ID_AA64MMFR0_EL1_TGRAN_LPA2) && defined(ID_AA64MMFR0_EL1_TGRAN_2_SUPPORTED_LPA2) static bool has_lpa2_at_stage1(u64 mmfr0) { unsigned int tgran; tgran = cpuid_feature_extract_unsigned_field(mmfr0, ID_AA64MMFR0_EL1_TGRAN_SHIFT); return tgran == ID_AA64MMFR0_EL1_TGRAN_LPA2; } static bool has_lpa2_at_stage2(u64 mmfr0) { unsigned int tgran; tgran = cpuid_feature_extract_unsigned_field(mmfr0, ID_AA64MMFR0_EL1_TGRAN_2_SHIFT); return tgran == ID_AA64MMFR0_EL1_TGRAN_2_SUPPORTED_LPA2; } static bool has_lpa2(const struct arm64_cpu_capabilities *entry, int scope) { u64 mmfr0; mmfr0 = read_sanitised_ftr_reg(SYS_ID_AA64MMFR0_EL1); return has_lpa2_at_stage1(mmfr0) && has_lpa2_at_stage2(mmfr0); } #else static bool has_lpa2(const struct arm64_cpu_capabilities *entry, int scope) { return false; } #endif #ifdef CONFIG_UNMAP_KERNEL_AT_EL0 #define KPTI_NG_TEMP_VA (-(1UL << PMD_SHIFT)) extern void create_kpti_ng_temp_pgd(pgd_t *pgdir, phys_addr_t phys, unsigned long virt, phys_addr_t size, pgprot_t prot, phys_addr_t (*pgtable_alloc)(int), int flags); static phys_addr_t __initdata kpti_ng_temp_alloc; static phys_addr_t __init kpti_ng_pgd_alloc(int shift) { kpti_ng_temp_alloc -= PAGE_SIZE; return kpti_ng_temp_alloc; } static int __init __kpti_install_ng_mappings(void *__unused) { typedef void (kpti_remap_fn)(int, int, phys_addr_t, unsigned long); extern kpti_remap_fn idmap_kpti_install_ng_mappings; kpti_remap_fn *remap_fn; int cpu = smp_processor_id(); int levels = CONFIG_PGTABLE_LEVELS; int order = order_base_2(levels); u64 kpti_ng_temp_pgd_pa = 0; pgd_t *kpti_ng_temp_pgd; u64 alloc = 0; if (levels == 5 && !pgtable_l5_enabled()) levels = 4; else if (levels == 4 && !pgtable_l4_enabled()) levels = 3; remap_fn = (void *)__pa_symbol(idmap_kpti_install_ng_mappings); if (!cpu) { alloc = __get_free_pages(GFP_ATOMIC | __GFP_ZERO, order); kpti_ng_temp_pgd = (pgd_t *)(alloc + (levels - 1) * PAGE_SIZE); kpti_ng_temp_alloc = kpti_ng_temp_pgd_pa = __pa(kpti_ng_temp_pgd); // // Create a minimal page table hierarchy that permits us to map // the swapper page tables temporarily as we traverse them. // // The physical pages are laid out as follows: // // +--------+-/-------+-/------ +-/------ +-\\\--------+ // : PTE[] : | PMD[] : | PUD[] : | P4D[] : ||| PGD[] : // +--------+-\-------+-\------ +-\------ +-///--------+ // ^ // The first page is mapped into this hierarchy at a PMD_SHIFT // aligned virtual address, so that we can manipulate the PTE // level entries while the mapping is active. The first entry // covers the PTE[] page itself, the remaining entries are free // to be used as a ad-hoc fixmap. // create_kpti_ng_temp_pgd(kpti_ng_temp_pgd, __pa(alloc), KPTI_NG_TEMP_VA, PAGE_SIZE, PAGE_KERNEL, kpti_ng_pgd_alloc, 0); } cpu_install_idmap(); remap_fn(cpu, num_online_cpus(), kpti_ng_temp_pgd_pa, KPTI_NG_TEMP_VA); cpu_uninstall_idmap(); if (!cpu) { free_pages(alloc, order); arm64_use_ng_mappings = true; } return 0; } static void __init kpti_install_ng_mappings(void) { /* Check whether KPTI is going to be used */ if (!arm64_kernel_unmapped_at_el0()) return; /* * We don't need to rewrite the page-tables if either we've done * it already or we have KASLR enabled and therefore have not * created any global mappings at all. */ if (arm64_use_ng_mappings) return; stop_machine(__kpti_install_ng_mappings, NULL, cpu_online_mask); } #else static inline void kpti_install_ng_mappings(void) { } #endif /* CONFIG_UNMAP_KERNEL_AT_EL0 */ static void cpu_enable_kpti(struct arm64_cpu_capabilities const *cap) { if (__this_cpu_read(this_cpu_vector) == vectors) { const char *v = arm64_get_bp_hardening_vector(EL1_VECTOR_KPTI); __this_cpu_write(this_cpu_vector, v); } } static int __init parse_kpti(char *str) { bool enabled; int ret = kstrtobool(str, &enabled); if (ret) return ret; __kpti_forced = enabled ? 1 : -1; return 0; } early_param("kpti", parse_kpti); #ifdef CONFIG_ARM64_HW_AFDBM static struct cpumask dbm_cpus __read_mostly; static inline void __cpu_enable_hw_dbm(void) { u64 tcr = read_sysreg(tcr_el1) | TCR_HD; write_sysreg(tcr, tcr_el1); isb(); local_flush_tlb_all(); } static bool cpu_has_broken_dbm(void) { /* List of CPUs which have broken DBM support. */ static const struct midr_range cpus[] = { #ifdef CONFIG_ARM64_ERRATUM_1024718 MIDR_ALL_VERSIONS(MIDR_CORTEX_A55), /* Kryo4xx Silver (rdpe => r1p0) */ MIDR_REV(MIDR_QCOM_KRYO_4XX_SILVER, 0xd, 0xe), #endif #ifdef CONFIG_ARM64_ERRATUM_2051678 MIDR_REV_RANGE(MIDR_CORTEX_A510, 0, 0, 2), #endif {}, }; return is_midr_in_range_list(read_cpuid_id(), cpus); } static bool cpu_can_use_dbm(const struct arm64_cpu_capabilities *cap) { return has_cpuid_feature(cap, SCOPE_LOCAL_CPU) && !cpu_has_broken_dbm(); } static void cpu_enable_hw_dbm(struct arm64_cpu_capabilities const *cap) { if (cpu_can_use_dbm(cap)) { __cpu_enable_hw_dbm(); cpumask_set_cpu(smp_processor_id(), &dbm_cpus); } } static bool has_hw_dbm(const struct arm64_cpu_capabilities *cap, int __unused) { /* * DBM is a non-conflicting feature. i.e, the kernel can safely * run a mix of CPUs with and without the feature. So, we * unconditionally enable the capability to allow any late CPU * to use the feature. We only enable the control bits on the * CPU, if it is supported. */ return true; } #endif #ifdef CONFIG_ARM64_AMU_EXTN /* * The "amu_cpus" cpumask only signals that the CPU implementation for the * flagged CPUs supports the Activity Monitors Unit (AMU) but does not provide * information regarding all the events that it supports. When a CPU bit is * set in the cpumask, the user of this feature can only rely on the presence * of the 4 fixed counters for that CPU. But this does not guarantee that the * counters are enabled or access to these counters is enabled by code * executed at higher exception levels (firmware). */ static struct cpumask amu_cpus __read_mostly; bool cpu_has_amu_feat(int cpu) { return cpumask_test_cpu(cpu, &amu_cpus); } int get_cpu_with_amu_feat(void) { return cpumask_any(&amu_cpus); } static void cpu_amu_enable(struct arm64_cpu_capabilities const *cap) { if (has_cpuid_feature(cap, SCOPE_LOCAL_CPU)) { cpumask_set_cpu(smp_processor_id(), &amu_cpus); /* 0 reference values signal broken/disabled counters */ if (!this_cpu_has_cap(ARM64_WORKAROUND_2457168)) update_freq_counters_refs(); } } static bool has_amu(const struct arm64_cpu_capabilities *cap, int __unused) { /* * The AMU extension is a non-conflicting feature: the kernel can * safely run a mix of CPUs with and without support for the * activity monitors extension. Therefore, unconditionally enable * the capability to allow any late CPU to use the feature. * * With this feature unconditionally enabled, the cpu_enable * function will be called for all CPUs that match the criteria, * including secondary and hotplugged, marking this feature as * present on that respective CPU. The enable function will also * print a detection message. */ return true; } #else int get_cpu_with_amu_feat(void) { return nr_cpu_ids; } #endif static bool runs_at_el2(const struct arm64_cpu_capabilities *entry, int __unused) { return is_kernel_in_hyp_mode(); } static void cpu_copy_el2regs(const struct arm64_cpu_capabilities *__unused) { /* * Copy register values that aren't redirected by hardware. * * Before code patching, we only set tpidr_el1, all CPUs need to copy * this value to tpidr_el2 before we patch the code. Once we've done * that, freshly-onlined CPUs will set tpidr_el2, so we don't need to * do anything here. */ if (!alternative_is_applied(ARM64_HAS_VIRT_HOST_EXTN)) write_sysreg(read_sysreg(tpidr_el1), tpidr_el2); } static bool has_nested_virt_support(const struct arm64_cpu_capabilities *cap, int scope) { if (kvm_get_mode() != KVM_MODE_NV) return false; if (!has_cpuid_feature(cap, scope)) { pr_warn("unavailable: %s\n", cap->desc); return false; } return true; } static bool hvhe_possible(const struct arm64_cpu_capabilities *entry, int __unused) { return arm64_test_sw_feature_override(ARM64_SW_FEATURE_OVERRIDE_HVHE); } #ifdef CONFIG_ARM64_PAN static void cpu_enable_pan(const struct arm64_cpu_capabilities *__unused) { /* * We modify PSTATE. This won't work from irq context as the PSTATE * is discarded once we return from the exception. */ WARN_ON_ONCE(in_interrupt()); sysreg_clear_set(sctlr_el1, SCTLR_EL1_SPAN, 0); set_pstate_pan(1); } #endif /* CONFIG_ARM64_PAN */ #ifdef CONFIG_ARM64_RAS_EXTN static void cpu_clear_disr(const struct arm64_cpu_capabilities *__unused) { /* Firmware may have left a deferred SError in this register. */ write_sysreg_s(0, SYS_DISR_EL1); } #endif /* CONFIG_ARM64_RAS_EXTN */ #ifdef CONFIG_ARM64_PTR_AUTH static bool has_address_auth_cpucap(const struct arm64_cpu_capabilities *entry, int scope) { int boot_val, sec_val; /* We don't expect to be called with SCOPE_SYSTEM */ WARN_ON(scope == SCOPE_SYSTEM); /* * The ptr-auth feature levels are not intercompatible with lower * levels. Hence we must match ptr-auth feature level of the secondary * CPUs with that of the boot CPU. The level of boot cpu is fetched * from the sanitised register whereas direct register read is done for * the secondary CPUs. * The sanitised feature state is guaranteed to match that of the * boot CPU as a mismatched secondary CPU is parked before it gets * a chance to update the state, with the capability. */ boot_val = cpuid_feature_extract_field(read_sanitised_ftr_reg(entry->sys_reg), entry->field_pos, entry->sign); if (scope & SCOPE_BOOT_CPU) return boot_val >= entry->min_field_value; /* Now check for the secondary CPUs with SCOPE_LOCAL_CPU scope */ sec_val = cpuid_feature_extract_field(__read_sysreg_by_encoding(entry->sys_reg), entry->field_pos, entry->sign); return (sec_val >= entry->min_field_value) && (sec_val == boot_val); } static bool has_address_auth_metacap(const struct arm64_cpu_capabilities *entry, int scope) { bool api = has_address_auth_cpucap(cpucap_ptrs[ARM64_HAS_ADDRESS_AUTH_IMP_DEF], scope); bool apa = has_address_auth_cpucap(cpucap_ptrs[ARM64_HAS_ADDRESS_AUTH_ARCH_QARMA5], scope); bool apa3 = has_address_auth_cpucap(cpucap_ptrs[ARM64_HAS_ADDRESS_AUTH_ARCH_QARMA3], scope); return apa || apa3 || api; } static bool has_generic_auth(const struct arm64_cpu_capabilities *entry, int __unused) { bool gpi = __system_matches_cap(ARM64_HAS_GENERIC_AUTH_IMP_DEF); bool gpa = __system_matches_cap(ARM64_HAS_GENERIC_AUTH_ARCH_QARMA5); bool gpa3 = __system_matches_cap(ARM64_HAS_GENERIC_AUTH_ARCH_QARMA3); return gpa || gpa3 || gpi; } #endif /* CONFIG_ARM64_PTR_AUTH */ #ifdef CONFIG_ARM64_E0PD static void cpu_enable_e0pd(struct arm64_cpu_capabilities const *cap) { if (this_cpu_has_cap(ARM64_HAS_E0PD)) sysreg_clear_set(tcr_el1, 0, TCR_E0PD1); } #endif /* CONFIG_ARM64_E0PD */ #ifdef CONFIG_ARM64_PSEUDO_NMI static bool can_use_gic_priorities(const struct arm64_cpu_capabilities *entry, int scope) { /* * ARM64_HAS_GIC_CPUIF_SYSREGS has a lower index, and is a boot CPU * feature, so will be detected earlier. */ BUILD_BUG_ON(ARM64_HAS_GIC_PRIO_MASKING <= ARM64_HAS_GIC_CPUIF_SYSREGS); if (!cpus_have_cap(ARM64_HAS_GIC_CPUIF_SYSREGS)) return false; return enable_pseudo_nmi; } static bool has_gic_prio_relaxed_sync(const struct arm64_cpu_capabilities *entry, int scope) { /* * If we're not using priority masking then we won't be poking PMR_EL1, * and there's no need to relax synchronization of writes to it, and * ICC_CTLR_EL1 might not be accessible and we must avoid reads from * that. * * ARM64_HAS_GIC_PRIO_MASKING has a lower index, and is a boot CPU * feature, so will be detected earlier. */ BUILD_BUG_ON(ARM64_HAS_GIC_PRIO_RELAXED_SYNC <= ARM64_HAS_GIC_PRIO_MASKING); if (!cpus_have_cap(ARM64_HAS_GIC_PRIO_MASKING)) return false; /* * When Priority Mask Hint Enable (PMHE) == 0b0, PMR is not used as a * hint for interrupt distribution, a DSB is not necessary when * unmasking IRQs via PMR, and we can relax the barrier to a NOP. * * Linux itself doesn't use 1:N distribution, so has no need to * set PMHE. The only reason to have it set is if EL3 requires it * (and we can't change it). */ return (gic_read_ctlr() & ICC_CTLR_EL1_PMHE_MASK) == 0; } #endif #ifdef CONFIG_ARM64_BTI static void bti_enable(const struct arm64_cpu_capabilities *__unused) { /* * Use of X16/X17 for tail-calls and trampolines that jump to * function entry points using BR is a requirement for * marking binaries with GNU_PROPERTY_AARCH64_FEATURE_1_BTI. * So, be strict and forbid other BRs using other registers to * jump onto a PACIxSP instruction: */ sysreg_clear_set(sctlr_el1, 0, SCTLR_EL1_BT0 | SCTLR_EL1_BT1); isb(); } #endif /* CONFIG_ARM64_BTI */ #ifdef CONFIG_ARM64_MTE static void cpu_enable_mte(struct arm64_cpu_capabilities const *cap) { sysreg_clear_set(sctlr_el1, 0, SCTLR_ELx_ATA | SCTLR_EL1_ATA0); mte_cpu_setup(); /* * Clear the tags in the zero page. This needs to be done via the * linear map which has the Tagged attribute. */ if (try_page_mte_tagging(ZERO_PAGE(0))) { mte_clear_page_tags(lm_alias(empty_zero_page)); set_page_mte_tagged(ZERO_PAGE(0)); } kasan_init_hw_tags_cpu(); } #endif /* CONFIG_ARM64_MTE */ static void user_feature_fixup(void) { if (cpus_have_cap(ARM64_WORKAROUND_2658417)) { struct arm64_ftr_reg *regp; regp = get_arm64_ftr_reg(SYS_ID_AA64ISAR1_EL1); if (regp) regp->user_mask &= ~ID_AA64ISAR1_EL1_BF16_MASK; } if (cpus_have_cap(ARM64_WORKAROUND_SPECULATIVE_SSBS)) { struct arm64_ftr_reg *regp; regp = get_arm64_ftr_reg(SYS_ID_AA64PFR1_EL1); if (regp) regp->user_mask &= ~ID_AA64PFR1_EL1_SSBS_MASK; } } static void elf_hwcap_fixup(void) { #ifdef CONFIG_COMPAT if (cpus_have_cap(ARM64_WORKAROUND_1742098)) compat_elf_hwcap2 &= ~COMPAT_HWCAP2_AES; #endif /* CONFIG_COMPAT */ } #ifdef CONFIG_KVM static bool is_kvm_protected_mode(const struct arm64_cpu_capabilities *entry, int __unused) { return kvm_get_mode() == KVM_MODE_PROTECTED; } #endif /* CONFIG_KVM */ static void cpu_trap_el0_impdef(const struct arm64_cpu_capabilities *__unused) { sysreg_clear_set(sctlr_el1, 0, SCTLR_EL1_TIDCP); } static void cpu_enable_dit(const struct arm64_cpu_capabilities *__unused) { set_pstate_dit(1); } static void cpu_enable_mops(const struct arm64_cpu_capabilities *__unused) { sysreg_clear_set(sctlr_el1, 0, SCTLR_EL1_MSCEn); } #ifdef CONFIG_ARM64_POE static void cpu_enable_poe(const struct arm64_cpu_capabilities *__unused) { sysreg_clear_set(REG_TCR2_EL1, 0, TCR2_EL1_E0POE); sysreg_clear_set(CPACR_EL1, 0, CPACR_EL1_E0POE); } #endif #ifdef CONFIG_ARM64_GCS static void cpu_enable_gcs(const struct arm64_cpu_capabilities *__unused) { /* GCSPR_EL0 is always readable */ write_sysreg_s(GCSCRE0_EL1_nTR, SYS_GCSCRE0_EL1); } #endif /* Internal helper functions to match cpu capability type */ static bool cpucap_late_cpu_optional(const struct arm64_cpu_capabilities *cap) { return !!(cap->type & ARM64_CPUCAP_OPTIONAL_FOR_LATE_CPU); } static bool cpucap_late_cpu_permitted(const struct arm64_cpu_capabilities *cap) { return !!(cap->type & ARM64_CPUCAP_PERMITTED_FOR_LATE_CPU); } static bool cpucap_panic_on_conflict(const struct arm64_cpu_capabilities *cap) { return !!(cap->type & ARM64_CPUCAP_PANIC_ON_CONFLICT); } static bool test_has_mpam(const struct arm64_cpu_capabilities *entry, int scope) { if (!has_cpuid_feature(entry, scope)) return false; /* Check firmware actually enabled MPAM on this cpu. */ return (read_sysreg_s(SYS_MPAM1_EL1) & MPAM1_EL1_MPAMEN); } static void cpu_enable_mpam(const struct arm64_cpu_capabilities *entry) { /* * Access by the kernel (at EL1) should use the reserved PARTID * which is configured unrestricted. This avoids priority-inversion * where latency sensitive tasks have to wait for a task that has * been throttled to release the lock. */ write_sysreg_s(0, SYS_MPAM1_EL1); } static bool test_has_mpam_hcr(const struct arm64_cpu_capabilities *entry, int scope) { u64 idr = read_sanitised_ftr_reg(SYS_MPAMIDR_EL1); return idr & MPAMIDR_EL1_HAS_HCR; } static const struct arm64_cpu_capabilities arm64_features[] = { { .capability = ARM64_ALWAYS_BOOT, .type = ARM64_CPUCAP_BOOT_CPU_FEATURE, .matches = has_always, }, { .capability = ARM64_ALWAYS_SYSTEM, .type = ARM64_CPUCAP_SYSTEM_FEATURE, .matches = has_always, }, { .desc = "GIC system register CPU interface", .capability = ARM64_HAS_GIC_CPUIF_SYSREGS, .type = ARM64_CPUCAP_STRICT_BOOT_CPU_FEATURE, .matches = has_useable_gicv3_cpuif, ARM64_CPUID_FIELDS(ID_AA64PFR0_EL1, GIC, IMP) }, { .desc = "Enhanced Counter Virtualization", .capability = ARM64_HAS_ECV, .type = ARM64_CPUCAP_SYSTEM_FEATURE, .matches = has_cpuid_feature, ARM64_CPUID_FIELDS(ID_AA64MMFR0_EL1, ECV, IMP) }, { .desc = "Enhanced Counter Virtualization (CNTPOFF)", .capability = ARM64_HAS_ECV_CNTPOFF, .type = ARM64_CPUCAP_SYSTEM_FEATURE, .matches = has_cpuid_feature, ARM64_CPUID_FIELDS(ID_AA64MMFR0_EL1, ECV, CNTPOFF) }, #ifdef CONFIG_ARM64_PAN { .desc = "Privileged Access Never", .capability = ARM64_HAS_PAN, .type = ARM64_CPUCAP_SYSTEM_FEATURE, .matches = has_cpuid_feature, .cpu_enable = cpu_enable_pan, ARM64_CPUID_FIELDS(ID_AA64MMFR1_EL1, PAN, IMP) }, #endif /* CONFIG_ARM64_PAN */ #ifdef CONFIG_ARM64_EPAN { .desc = "Enhanced Privileged Access Never", .capability = ARM64_HAS_EPAN, .type = ARM64_CPUCAP_SYSTEM_FEATURE, .matches = has_cpuid_feature, ARM64_CPUID_FIELDS(ID_AA64MMFR1_EL1, PAN, PAN3) }, #endif /* CONFIG_ARM64_EPAN */ #ifdef CONFIG_ARM64_LSE_ATOMICS { .desc = "LSE atomic instructions", .capability = ARM64_HAS_LSE_ATOMICS, .type = ARM64_CPUCAP_SYSTEM_FEATURE, .matches = has_cpuid_feature, ARM64_CPUID_FIELDS(ID_AA64ISAR0_EL1, ATOMIC, IMP) }, #endif /* CONFIG_ARM64_LSE_ATOMICS */ { .desc = "Virtualization Host Extensions", .capability = ARM64_HAS_VIRT_HOST_EXTN, .type = ARM64_CPUCAP_STRICT_BOOT_CPU_FEATURE, .matches = runs_at_el2, .cpu_enable = cpu_copy_el2regs, }, { .desc = "Nested Virtualization Support", .capability = ARM64_HAS_NESTED_VIRT, .type = ARM64_CPUCAP_SYSTEM_FEATURE, .matches = has_nested_virt_support, ARM64_CPUID_FIELDS(ID_AA64MMFR2_EL1, NV, NV2) }, { .capability = ARM64_HAS_32BIT_EL0_DO_NOT_USE, .type = ARM64_CPUCAP_SYSTEM_FEATURE, .matches = has_32bit_el0, ARM64_CPUID_FIELDS(ID_AA64PFR0_EL1, EL0, AARCH32) }, #ifdef CONFIG_KVM { .desc = "32-bit EL1 Support", .capability = ARM64_HAS_32BIT_EL1, .type = ARM64_CPUCAP_SYSTEM_FEATURE, .matches = has_cpuid_feature, ARM64_CPUID_FIELDS(ID_AA64PFR0_EL1, EL1, AARCH32) }, { .desc = "Protected KVM", .capability = ARM64_KVM_PROTECTED_MODE, .type = ARM64_CPUCAP_SYSTEM_FEATURE, .matches = is_kvm_protected_mode, }, { .desc = "HCRX_EL2 register", .capability = ARM64_HAS_HCX, .type = ARM64_CPUCAP_STRICT_BOOT_CPU_FEATURE, .matches = has_cpuid_feature, ARM64_CPUID_FIELDS(ID_AA64MMFR1_EL1, HCX, IMP) }, #endif { .desc = "Kernel page table isolation (KPTI)", .capability = ARM64_UNMAP_KERNEL_AT_EL0, .type = ARM64_CPUCAP_BOOT_RESTRICTED_CPU_LOCAL_FEATURE, .cpu_enable = cpu_enable_kpti, .matches = unmap_kernel_at_el0, /* * The ID feature fields below are used to indicate that * the CPU doesn't need KPTI. See unmap_kernel_at_el0 for * more details. */ ARM64_CPUID_FIELDS(ID_AA64PFR0_EL1, CSV3, IMP) }, { .capability = ARM64_HAS_FPSIMD, .type = ARM64_CPUCAP_SYSTEM_FEATURE, .matches = has_cpuid_feature, .cpu_enable = cpu_enable_fpsimd, ARM64_CPUID_FIELDS(ID_AA64PFR0_EL1, FP, IMP) }, #ifdef CONFIG_ARM64_PMEM { .desc = "Data cache clean to Point of Persistence", .capability = ARM64_HAS_DCPOP, .type = ARM64_CPUCAP_SYSTEM_FEATURE, .matches = has_cpuid_feature, ARM64_CPUID_FIELDS(ID_AA64ISAR1_EL1, DPB, IMP) }, { .desc = "Data cache clean to Point of Deep Persistence", .capability = ARM64_HAS_DCPODP, .type = ARM64_CPUCAP_SYSTEM_FEATURE, .matches = has_cpuid_feature, ARM64_CPUID_FIELDS(ID_AA64ISAR1_EL1, DPB, DPB2) }, #endif #ifdef CONFIG_ARM64_SVE { .desc = "Scalable Vector Extension", .type = ARM64_CPUCAP_SYSTEM_FEATURE, .capability = ARM64_SVE, .cpu_enable = cpu_enable_sve, .matches = has_cpuid_feature, ARM64_CPUID_FIELDS(ID_AA64PFR0_EL1, SVE, IMP) }, #endif /* CONFIG_ARM64_SVE */ #ifdef CONFIG_ARM64_RAS_EXTN { .desc = "RAS Extension Support", .capability = ARM64_HAS_RAS_EXTN, .type = ARM64_CPUCAP_SYSTEM_FEATURE, .matches = has_cpuid_feature, .cpu_enable = cpu_clear_disr, ARM64_CPUID_FIELDS(ID_AA64PFR0_EL1, RAS, IMP) }, #endif /* CONFIG_ARM64_RAS_EXTN */ #ifdef CONFIG_ARM64_AMU_EXTN { .desc = "Activity Monitors Unit (AMU)", .capability = ARM64_HAS_AMU_EXTN, .type = ARM64_CPUCAP_WEAK_LOCAL_CPU_FEATURE, .matches = has_amu, .cpu_enable = cpu_amu_enable, .cpus = &amu_cpus, ARM64_CPUID_FIELDS(ID_AA64PFR0_EL1, AMU, IMP) }, #endif /* CONFIG_ARM64_AMU_EXTN */ { .desc = "Data cache clean to the PoU not required for I/D coherence", .capability = ARM64_HAS_CACHE_IDC, .type = ARM64_CPUCAP_SYSTEM_FEATURE, .matches = has_cache_idc, .cpu_enable = cpu_emulate_effective_ctr, }, { .desc = "Instruction cache invalidation not required for I/D coherence", .capability = ARM64_HAS_CACHE_DIC, .type = ARM64_CPUCAP_SYSTEM_FEATURE, .matches = has_cache_dic, }, { .desc = "Stage-2 Force Write-Back", .type = ARM64_CPUCAP_SYSTEM_FEATURE, .capability = ARM64_HAS_STAGE2_FWB, .matches = has_cpuid_feature, ARM64_CPUID_FIELDS(ID_AA64MMFR2_EL1, FWB, IMP) }, { .desc = "ARMv8.4 Translation Table Level", .type = ARM64_CPUCAP_SYSTEM_FEATURE, .capability = ARM64_HAS_ARMv8_4_TTL, .matches = has_cpuid_feature, ARM64_CPUID_FIELDS(ID_AA64MMFR2_EL1, TTL, IMP) }, { .desc = "TLB range maintenance instructions", .capability = ARM64_HAS_TLB_RANGE, .type = ARM64_CPUCAP_SYSTEM_FEATURE, .matches = has_cpuid_feature, ARM64_CPUID_FIELDS(ID_AA64ISAR0_EL1, TLB, RANGE) }, #ifdef CONFIG_ARM64_HW_AFDBM { .desc = "Hardware dirty bit management", .type = ARM64_CPUCAP_WEAK_LOCAL_CPU_FEATURE, .capability = ARM64_HW_DBM, .matches = has_hw_dbm, .cpu_enable = cpu_enable_hw_dbm, .cpus = &dbm_cpus, ARM64_CPUID_FIELDS(ID_AA64MMFR1_EL1, HAFDBS, DBM) }, #endif #ifdef CONFIG_ARM64_HAFT { .desc = "Hardware managed Access Flag for Table Descriptors", /* * Contrary to the page/block access flag, the table access flag * cannot be emulated in software (no access fault will occur). * Therefore this should be used only if it's supported system * wide. */ .type = ARM64_CPUCAP_SYSTEM_FEATURE, .capability = ARM64_HAFT, .matches = has_cpuid_feature, ARM64_CPUID_FIELDS(ID_AA64MMFR1_EL1, HAFDBS, HAFT) }, #endif { .desc = "CRC32 instructions", .capability = ARM64_HAS_CRC32, .type = ARM64_CPUCAP_SYSTEM_FEATURE, .matches = has_cpuid_feature, ARM64_CPUID_FIELDS(ID_AA64ISAR0_EL1, CRC32, IMP) }, { .desc = "Speculative Store Bypassing Safe (SSBS)", .capability = ARM64_SSBS, .type = ARM64_CPUCAP_SYSTEM_FEATURE, .matches = has_cpuid_feature, ARM64_CPUID_FIELDS(ID_AA64PFR1_EL1, SSBS, IMP) }, #ifdef CONFIG_ARM64_CNP { .desc = "Common not Private translations", .capability = ARM64_HAS_CNP, .type = ARM64_CPUCAP_SYSTEM_FEATURE, .matches = has_useable_cnp, .cpu_enable = cpu_enable_cnp, ARM64_CPUID_FIELDS(ID_AA64MMFR2_EL1, CnP, IMP) }, #endif { .desc = "Speculation barrier (SB)", .capability = ARM64_HAS_SB, .type = ARM64_CPUCAP_SYSTEM_FEATURE, .matches = has_cpuid_feature, ARM64_CPUID_FIELDS(ID_AA64ISAR1_EL1, SB, IMP) }, #ifdef CONFIG_ARM64_PTR_AUTH { .desc = "Address authentication (architected QARMA5 algorithm)", .capability = ARM64_HAS_ADDRESS_AUTH_ARCH_QARMA5, .type = ARM64_CPUCAP_BOOT_CPU_FEATURE, .matches = has_address_auth_cpucap, ARM64_CPUID_FIELDS(ID_AA64ISAR1_EL1, APA, PAuth) }, { .desc = "Address authentication (architected QARMA3 algorithm)", .capability = ARM64_HAS_ADDRESS_AUTH_ARCH_QARMA3, .type = ARM64_CPUCAP_BOOT_CPU_FEATURE, .matches = has_address_auth_cpucap, ARM64_CPUID_FIELDS(ID_AA64ISAR2_EL1, APA3, PAuth) }, { .desc = "Address authentication (IMP DEF algorithm)", .capability = ARM64_HAS_ADDRESS_AUTH_IMP_DEF, .type = ARM64_CPUCAP_BOOT_CPU_FEATURE, .matches = has_address_auth_cpucap, ARM64_CPUID_FIELDS(ID_AA64ISAR1_EL1, API, PAuth) }, { .capability = ARM64_HAS_ADDRESS_AUTH, .type = ARM64_CPUCAP_BOOT_CPU_FEATURE, .matches = has_address_auth_metacap, }, { .desc = "Generic authentication (architected QARMA5 algorithm)", .capability = ARM64_HAS_GENERIC_AUTH_ARCH_QARMA5, .type = ARM64_CPUCAP_SYSTEM_FEATURE, .matches = has_cpuid_feature, ARM64_CPUID_FIELDS(ID_AA64ISAR1_EL1, GPA, IMP) }, { .desc = "Generic authentication (architected QARMA3 algorithm)", .capability = ARM64_HAS_GENERIC_AUTH_ARCH_QARMA3, .type = ARM64_CPUCAP_SYSTEM_FEATURE, .matches = has_cpuid_feature, ARM64_CPUID_FIELDS(ID_AA64ISAR2_EL1, GPA3, IMP) }, { .desc = "Generic authentication (IMP DEF algorithm)", .capability = ARM64_HAS_GENERIC_AUTH_IMP_DEF, .type = ARM64_CPUCAP_SYSTEM_FEATURE, .matches = has_cpuid_feature, ARM64_CPUID_FIELDS(ID_AA64ISAR1_EL1, GPI, IMP) }, { .capability = ARM64_HAS_GENERIC_AUTH, .type = ARM64_CPUCAP_SYSTEM_FEATURE, .matches = has_generic_auth, }, #endif /* CONFIG_ARM64_PTR_AUTH */ #ifdef CONFIG_ARM64_PSEUDO_NMI { /* * Depends on having GICv3 */ .desc = "IRQ priority masking", .capability = ARM64_HAS_GIC_PRIO_MASKING, .type = ARM64_CPUCAP_STRICT_BOOT_CPU_FEATURE, .matches = can_use_gic_priorities, }, { /* * Depends on ARM64_HAS_GIC_PRIO_MASKING */ .capability = ARM64_HAS_GIC_PRIO_RELAXED_SYNC, .type = ARM64_CPUCAP_STRICT_BOOT_CPU_FEATURE, .matches = has_gic_prio_relaxed_sync, }, #endif #ifdef CONFIG_ARM64_E0PD { .desc = "E0PD", .capability = ARM64_HAS_E0PD, .type = ARM64_CPUCAP_SYSTEM_FEATURE, .cpu_enable = cpu_enable_e0pd, .matches = has_cpuid_feature, ARM64_CPUID_FIELDS(ID_AA64MMFR2_EL1, E0PD, IMP) }, #endif { .desc = "Random Number Generator", .capability = ARM64_HAS_RNG, .type = ARM64_CPUCAP_SYSTEM_FEATURE, .matches = has_cpuid_feature, ARM64_CPUID_FIELDS(ID_AA64ISAR0_EL1, RNDR, IMP) }, #ifdef CONFIG_ARM64_BTI { .desc = "Branch Target Identification", .capability = ARM64_BTI, #ifdef CONFIG_ARM64_BTI_KERNEL .type = ARM64_CPUCAP_STRICT_BOOT_CPU_FEATURE, #else .type = ARM64_CPUCAP_SYSTEM_FEATURE, #endif .matches = has_cpuid_feature, .cpu_enable = bti_enable, ARM64_CPUID_FIELDS(ID_AA64PFR1_EL1, BT, IMP) }, #endif #ifdef CONFIG_ARM64_MTE { .desc = "Memory Tagging Extension", .capability = ARM64_MTE, .type = ARM64_CPUCAP_STRICT_BOOT_CPU_FEATURE, .matches = has_cpuid_feature, .cpu_enable = cpu_enable_mte, ARM64_CPUID_FIELDS(ID_AA64PFR1_EL1, MTE, MTE2) }, { .desc = "Asymmetric MTE Tag Check Fault", .capability = ARM64_MTE_ASYMM, .type = ARM64_CPUCAP_BOOT_CPU_FEATURE, .matches = has_cpuid_feature, ARM64_CPUID_FIELDS(ID_AA64PFR1_EL1, MTE, MTE3) }, #endif /* CONFIG_ARM64_MTE */ { .desc = "RCpc load-acquire (LDAPR)", .capability = ARM64_HAS_LDAPR, .type = ARM64_CPUCAP_SYSTEM_FEATURE, .matches = has_cpuid_feature, ARM64_CPUID_FIELDS(ID_AA64ISAR1_EL1, LRCPC, IMP) }, { .desc = "Fine Grained Traps", .type = ARM64_CPUCAP_SYSTEM_FEATURE, .capability = ARM64_HAS_FGT, .matches = has_cpuid_feature, ARM64_CPUID_FIELDS(ID_AA64MMFR0_EL1, FGT, IMP) }, #ifdef CONFIG_ARM64_SME { .desc = "Scalable Matrix Extension", .type = ARM64_CPUCAP_SYSTEM_FEATURE, .capability = ARM64_SME, .matches = has_cpuid_feature, .cpu_enable = cpu_enable_sme, ARM64_CPUID_FIELDS(ID_AA64PFR1_EL1, SME, IMP) }, /* FA64 should be sorted after the base SME capability */ { .desc = "FA64", .type = ARM64_CPUCAP_SYSTEM_FEATURE, .capability = ARM64_SME_FA64, .matches = has_cpuid_feature, .cpu_enable = cpu_enable_fa64, ARM64_CPUID_FIELDS(ID_AA64SMFR0_EL1, FA64, IMP) }, { .desc = "SME2", .type = ARM64_CPUCAP_SYSTEM_FEATURE, .capability = ARM64_SME2, .matches = has_cpuid_feature, .cpu_enable = cpu_enable_sme2, ARM64_CPUID_FIELDS(ID_AA64PFR1_EL1, SME, SME2) }, #endif /* CONFIG_ARM64_SME */ { .desc = "WFx with timeout", .capability = ARM64_HAS_WFXT, .type = ARM64_CPUCAP_SYSTEM_FEATURE, .matches = has_cpuid_feature, ARM64_CPUID_FIELDS(ID_AA64ISAR2_EL1, WFxT, IMP) }, { .desc = "Trap EL0 IMPLEMENTATION DEFINED functionality", .capability = ARM64_HAS_TIDCP1, .type = ARM64_CPUCAP_SYSTEM_FEATURE, .matches = has_cpuid_feature, .cpu_enable = cpu_trap_el0_impdef, ARM64_CPUID_FIELDS(ID_AA64MMFR1_EL1, TIDCP1, IMP) }, { .desc = "Data independent timing control (DIT)", .capability = ARM64_HAS_DIT, .type = ARM64_CPUCAP_SYSTEM_FEATURE, .matches = has_cpuid_feature, .cpu_enable = cpu_enable_dit, ARM64_CPUID_FIELDS(ID_AA64PFR0_EL1, DIT, IMP) }, { .desc = "Memory Copy and Memory Set instructions", .capability = ARM64_HAS_MOPS, .type = ARM64_CPUCAP_SYSTEM_FEATURE, .matches = has_cpuid_feature, .cpu_enable = cpu_enable_mops, ARM64_CPUID_FIELDS(ID_AA64ISAR2_EL1, MOPS, IMP) }, { .capability = ARM64_HAS_TCR2, .type = ARM64_CPUCAP_SYSTEM_FEATURE, .matches = has_cpuid_feature, ARM64_CPUID_FIELDS(ID_AA64MMFR3_EL1, TCRX, IMP) }, { .desc = "Stage-1 Permission Indirection Extension (S1PIE)", .capability = ARM64_HAS_S1PIE, .type = ARM64_CPUCAP_BOOT_CPU_FEATURE, .matches = has_cpuid_feature, ARM64_CPUID_FIELDS(ID_AA64MMFR3_EL1, S1PIE, IMP) }, { .desc = "VHE for hypervisor only", .capability = ARM64_KVM_HVHE, .type = ARM64_CPUCAP_SYSTEM_FEATURE, .matches = hvhe_possible, }, { .desc = "Enhanced Virtualization Traps", .capability = ARM64_HAS_EVT, .type = ARM64_CPUCAP_SYSTEM_FEATURE, .matches = has_cpuid_feature, ARM64_CPUID_FIELDS(ID_AA64MMFR2_EL1, EVT, IMP) }, { .desc = "52-bit Virtual Addressing for KVM (LPA2)", .capability = ARM64_HAS_LPA2, .type = ARM64_CPUCAP_SYSTEM_FEATURE, .matches = has_lpa2, }, { .desc = "FPMR", .type = ARM64_CPUCAP_SYSTEM_FEATURE, .capability = ARM64_HAS_FPMR, .matches = has_cpuid_feature, .cpu_enable = cpu_enable_fpmr, ARM64_CPUID_FIELDS(ID_AA64PFR2_EL1, FPMR, IMP) }, #ifdef CONFIG_ARM64_VA_BITS_52 { .capability = ARM64_HAS_VA52, .type = ARM64_CPUCAP_BOOT_CPU_FEATURE, .matches = has_cpuid_feature, #ifdef CONFIG_ARM64_64K_PAGES .desc = "52-bit Virtual Addressing (LVA)", ARM64_CPUID_FIELDS(ID_AA64MMFR2_EL1, VARange, 52) #else .desc = "52-bit Virtual Addressing (LPA2)", #ifdef CONFIG_ARM64_4K_PAGES ARM64_CPUID_FIELDS(ID_AA64MMFR0_EL1, TGRAN4, 52_BIT) #else ARM64_CPUID_FIELDS(ID_AA64MMFR0_EL1, TGRAN16, 52_BIT) #endif #endif }, #endif { .desc = "Memory Partitioning And Monitoring", .type = ARM64_CPUCAP_SYSTEM_FEATURE, .capability = ARM64_MPAM, .matches = test_has_mpam, .cpu_enable = cpu_enable_mpam, ARM64_CPUID_FIELDS(ID_AA64PFR0_EL1, MPAM, 1) }, { .desc = "Memory Partitioning And Monitoring Virtualisation", .type = ARM64_CPUCAP_SYSTEM_FEATURE, .capability = ARM64_MPAM_HCR, .matches = test_has_mpam_hcr, }, { .desc = "NV1", .capability = ARM64_HAS_HCR_NV1, .type = ARM64_CPUCAP_SYSTEM_FEATURE, .matches = has_nv1, ARM64_CPUID_FIELDS_NEG(ID_AA64MMFR4_EL1, E2H0, NI_NV1) }, #ifdef CONFIG_ARM64_POE { .desc = "Stage-1 Permission Overlay Extension (S1POE)", .capability = ARM64_HAS_S1POE, .type = ARM64_CPUCAP_BOOT_CPU_FEATURE, .matches = has_cpuid_feature, .cpu_enable = cpu_enable_poe, ARM64_CPUID_FIELDS(ID_AA64MMFR3_EL1, S1POE, IMP) }, #endif #ifdef CONFIG_ARM64_GCS { .desc = "Guarded Control Stack (GCS)", .capability = ARM64_HAS_GCS, .type = ARM64_CPUCAP_SYSTEM_FEATURE, .cpu_enable = cpu_enable_gcs, .matches = has_cpuid_feature, ARM64_CPUID_FIELDS(ID_AA64PFR1_EL1, GCS, IMP) }, #endif {}, }; #define HWCAP_CPUID_MATCH(reg, field, min_value) \ .matches = has_user_cpuid_feature, \ ARM64_CPUID_FIELDS(reg, field, min_value) #define __HWCAP_CAP(name, cap_type, cap) \ .desc = name, \ .type = ARM64_CPUCAP_SYSTEM_FEATURE, \ .hwcap_type = cap_type, \ .hwcap = cap, \ #define HWCAP_CAP(reg, field, min_value, cap_type, cap) \ { \ __HWCAP_CAP(#cap, cap_type, cap) \ HWCAP_CPUID_MATCH(reg, field, min_value) \ } #define HWCAP_MULTI_CAP(list, cap_type, cap) \ { \ __HWCAP_CAP(#cap, cap_type, cap) \ .matches = cpucap_multi_entry_cap_matches, \ .match_list = list, \ } #define HWCAP_CAP_MATCH(match, cap_type, cap) \ { \ __HWCAP_CAP(#cap, cap_type, cap) \ .matches = match, \ } #ifdef CONFIG_ARM64_PTR_AUTH static const struct arm64_cpu_capabilities ptr_auth_hwcap_addr_matches[] = { { HWCAP_CPUID_MATCH(ID_AA64ISAR1_EL1, APA, PAuth) }, { HWCAP_CPUID_MATCH(ID_AA64ISAR2_EL1, APA3, PAuth) }, { HWCAP_CPUID_MATCH(ID_AA64ISAR1_EL1, API, PAuth) }, {}, }; static const struct arm64_cpu_capabilities ptr_auth_hwcap_gen_matches[] = { { HWCAP_CPUID_MATCH(ID_AA64ISAR1_EL1, GPA, IMP) }, { HWCAP_CPUID_MATCH(ID_AA64ISAR2_EL1, GPA3, IMP) }, { HWCAP_CPUID_MATCH(ID_AA64ISAR1_EL1, GPI, IMP) }, {}, }; #endif static const struct arm64_cpu_capabilities arm64_elf_hwcaps[] = { HWCAP_CAP(ID_AA64ISAR0_EL1, AES, PMULL, CAP_HWCAP, KERNEL_HWCAP_PMULL), HWCAP_CAP(ID_AA64ISAR0_EL1, AES, AES, CAP_HWCAP, KERNEL_HWCAP_AES), HWCAP_CAP(ID_AA64ISAR0_EL1, SHA1, IMP, CAP_HWCAP, KERNEL_HWCAP_SHA1), HWCAP_CAP(ID_AA64ISAR0_EL1, SHA2, SHA256, CAP_HWCAP, KERNEL_HWCAP_SHA2), HWCAP_CAP(ID_AA64ISAR0_EL1, SHA2, SHA512, CAP_HWCAP, KERNEL_HWCAP_SHA512), HWCAP_CAP(ID_AA64ISAR0_EL1, CRC32, IMP, CAP_HWCAP, KERNEL_HWCAP_CRC32), HWCAP_CAP(ID_AA64ISAR0_EL1, ATOMIC, IMP, CAP_HWCAP, KERNEL_HWCAP_ATOMICS), HWCAP_CAP(ID_AA64ISAR0_EL1, ATOMIC, FEAT_LSE128, CAP_HWCAP, KERNEL_HWCAP_LSE128), HWCAP_CAP(ID_AA64ISAR0_EL1, RDM, IMP, CAP_HWCAP, KERNEL_HWCAP_ASIMDRDM), HWCAP_CAP(ID_AA64ISAR0_EL1, SHA3, IMP, CAP_HWCAP, KERNEL_HWCAP_SHA3), HWCAP_CAP(ID_AA64ISAR0_EL1, SM3, IMP, CAP_HWCAP, KERNEL_HWCAP_SM3), HWCAP_CAP(ID_AA64ISAR0_EL1, SM4, IMP, CAP_HWCAP, KERNEL_HWCAP_SM4), HWCAP_CAP(ID_AA64ISAR0_EL1, DP, IMP, CAP_HWCAP, KERNEL_HWCAP_ASIMDDP), HWCAP_CAP(ID_AA64ISAR0_EL1, FHM, IMP, CAP_HWCAP, KERNEL_HWCAP_ASIMDFHM), HWCAP_CAP(ID_AA64ISAR0_EL1, TS, FLAGM, CAP_HWCAP, KERNEL_HWCAP_FLAGM), HWCAP_CAP(ID_AA64ISAR0_EL1, TS, FLAGM2, CAP_HWCAP, KERNEL_HWCAP_FLAGM2), HWCAP_CAP(ID_AA64ISAR0_EL1, RNDR, IMP, CAP_HWCAP, KERNEL_HWCAP_RNG), HWCAP_CAP(ID_AA64PFR0_EL1, FP, IMP, CAP_HWCAP, KERNEL_HWCAP_FP), HWCAP_CAP(ID_AA64PFR0_EL1, FP, FP16, CAP_HWCAP, KERNEL_HWCAP_FPHP), HWCAP_CAP(ID_AA64PFR0_EL1, AdvSIMD, IMP, CAP_HWCAP, KERNEL_HWCAP_ASIMD), HWCAP_CAP(ID_AA64PFR0_EL1, AdvSIMD, FP16, CAP_HWCAP, KERNEL_HWCAP_ASIMDHP), HWCAP_CAP(ID_AA64PFR0_EL1, DIT, IMP, CAP_HWCAP, KERNEL_HWCAP_DIT), HWCAP_CAP(ID_AA64PFR2_EL1, FPMR, IMP, CAP_HWCAP, KERNEL_HWCAP_FPMR), HWCAP_CAP(ID_AA64ISAR1_EL1, DPB, IMP, CAP_HWCAP, KERNEL_HWCAP_DCPOP), HWCAP_CAP(ID_AA64ISAR1_EL1, DPB, DPB2, CAP_HWCAP, KERNEL_HWCAP_DCPODP), HWCAP_CAP(ID_AA64ISAR1_EL1, JSCVT, IMP, CAP_HWCAP, KERNEL_HWCAP_JSCVT), HWCAP_CAP(ID_AA64ISAR1_EL1, FCMA, IMP, CAP_HWCAP, KERNEL_HWCAP_FCMA), HWCAP_CAP(ID_AA64ISAR1_EL1, LRCPC, IMP, CAP_HWCAP, KERNEL_HWCAP_LRCPC), HWCAP_CAP(ID_AA64ISAR1_EL1, LRCPC, LRCPC2, CAP_HWCAP, KERNEL_HWCAP_ILRCPC), HWCAP_CAP(ID_AA64ISAR1_EL1, LRCPC, LRCPC3, CAP_HWCAP, KERNEL_HWCAP_LRCPC3), HWCAP_CAP(ID_AA64ISAR1_EL1, FRINTTS, IMP, CAP_HWCAP, KERNEL_HWCAP_FRINT), HWCAP_CAP(ID_AA64ISAR1_EL1, SB, IMP, CAP_HWCAP, KERNEL_HWCAP_SB), HWCAP_CAP(ID_AA64ISAR1_EL1, BF16, IMP, CAP_HWCAP, KERNEL_HWCAP_BF16), HWCAP_CAP(ID_AA64ISAR1_EL1, BF16, EBF16, CAP_HWCAP, KERNEL_HWCAP_EBF16), HWCAP_CAP(ID_AA64ISAR1_EL1, DGH, IMP, CAP_HWCAP, KERNEL_HWCAP_DGH), HWCAP_CAP(ID_AA64ISAR1_EL1, I8MM, IMP, CAP_HWCAP, KERNEL_HWCAP_I8MM), HWCAP_CAP(ID_AA64ISAR2_EL1, LUT, IMP, CAP_HWCAP, KERNEL_HWCAP_LUT), HWCAP_CAP(ID_AA64ISAR3_EL1, FAMINMAX, IMP, CAP_HWCAP, KERNEL_HWCAP_FAMINMAX), HWCAP_CAP(ID_AA64MMFR2_EL1, AT, IMP, CAP_HWCAP, KERNEL_HWCAP_USCAT), #ifdef CONFIG_ARM64_SVE HWCAP_CAP(ID_AA64PFR0_EL1, SVE, IMP, CAP_HWCAP, KERNEL_HWCAP_SVE), HWCAP_CAP(ID_AA64ZFR0_EL1, SVEver, SVE2p1, CAP_HWCAP, KERNEL_HWCAP_SVE2P1), HWCAP_CAP(ID_AA64ZFR0_EL1, SVEver, SVE2, CAP_HWCAP, KERNEL_HWCAP_SVE2), HWCAP_CAP(ID_AA64ZFR0_EL1, AES, IMP, CAP_HWCAP, KERNEL_HWCAP_SVEAES), HWCAP_CAP(ID_AA64ZFR0_EL1, AES, PMULL128, CAP_HWCAP, KERNEL_HWCAP_SVEPMULL), HWCAP_CAP(ID_AA64ZFR0_EL1, BitPerm, IMP, CAP_HWCAP, KERNEL_HWCAP_SVEBITPERM), HWCAP_CAP(ID_AA64ZFR0_EL1, B16B16, IMP, CAP_HWCAP, KERNEL_HWCAP_SVE_B16B16), HWCAP_CAP(ID_AA64ZFR0_EL1, BF16, IMP, CAP_HWCAP, KERNEL_HWCAP_SVEBF16), HWCAP_CAP(ID_AA64ZFR0_EL1, BF16, EBF16, CAP_HWCAP, KERNEL_HWCAP_SVE_EBF16), HWCAP_CAP(ID_AA64ZFR0_EL1, SHA3, IMP, CAP_HWCAP, KERNEL_HWCAP_SVESHA3), HWCAP_CAP(ID_AA64ZFR0_EL1, SM4, IMP, CAP_HWCAP, KERNEL_HWCAP_SVESM4), HWCAP_CAP(ID_AA64ZFR0_EL1, I8MM, IMP, CAP_HWCAP, KERNEL_HWCAP_SVEI8MM), HWCAP_CAP(ID_AA64ZFR0_EL1, F32MM, IMP, CAP_HWCAP, KERNEL_HWCAP_SVEF32MM), HWCAP_CAP(ID_AA64ZFR0_EL1, F64MM, IMP, CAP_HWCAP, KERNEL_HWCAP_SVEF64MM), #endif #ifdef CONFIG_ARM64_GCS HWCAP_CAP(ID_AA64PFR1_EL1, GCS, IMP, CAP_HWCAP, KERNEL_HWCAP_GCS), #endif HWCAP_CAP(ID_AA64PFR1_EL1, SSBS, SSBS2, CAP_HWCAP, KERNEL_HWCAP_SSBS), #ifdef CONFIG_ARM64_BTI HWCAP_CAP(ID_AA64PFR1_EL1, BT, IMP, CAP_HWCAP, KERNEL_HWCAP_BTI), #endif #ifdef CONFIG_ARM64_PTR_AUTH HWCAP_MULTI_CAP(ptr_auth_hwcap_addr_matches, CAP_HWCAP, KERNEL_HWCAP_PACA), HWCAP_MULTI_CAP(ptr_auth_hwcap_gen_matches, CAP_HWCAP, KERNEL_HWCAP_PACG), #endif #ifdef CONFIG_ARM64_MTE HWCAP_CAP(ID_AA64PFR1_EL1, MTE, MTE2, CAP_HWCAP, KERNEL_HWCAP_MTE), HWCAP_CAP(ID_AA64PFR1_EL1, MTE, MTE3, CAP_HWCAP, KERNEL_HWCAP_MTE3), #endif /* CONFIG_ARM64_MTE */ HWCAP_CAP(ID_AA64MMFR0_EL1, ECV, IMP, CAP_HWCAP, KERNEL_HWCAP_ECV), HWCAP_CAP(ID_AA64MMFR1_EL1, AFP, IMP, CAP_HWCAP, KERNEL_HWCAP_AFP), HWCAP_CAP(ID_AA64ISAR2_EL1, CSSC, IMP, CAP_HWCAP, KERNEL_HWCAP_CSSC), HWCAP_CAP(ID_AA64ISAR2_EL1, RPRFM, IMP, CAP_HWCAP, KERNEL_HWCAP_RPRFM), HWCAP_CAP(ID_AA64ISAR2_EL1, RPRES, IMP, CAP_HWCAP, KERNEL_HWCAP_RPRES), HWCAP_CAP(ID_AA64ISAR2_EL1, WFxT, IMP, CAP_HWCAP, KERNEL_HWCAP_WFXT), HWCAP_CAP(ID_AA64ISAR2_EL1, MOPS, IMP, CAP_HWCAP, KERNEL_HWCAP_MOPS), HWCAP_CAP(ID_AA64ISAR2_EL1, BC, IMP, CAP_HWCAP, KERNEL_HWCAP_HBC), #ifdef CONFIG_ARM64_SME HWCAP_CAP(ID_AA64PFR1_EL1, SME, IMP, CAP_HWCAP, KERNEL_HWCAP_SME), HWCAP_CAP(ID_AA64SMFR0_EL1, FA64, IMP, CAP_HWCAP, KERNEL_HWCAP_SME_FA64), HWCAP_CAP(ID_AA64SMFR0_EL1, LUTv2, IMP, CAP_HWCAP, KERNEL_HWCAP_SME_LUTV2), HWCAP_CAP(ID_AA64SMFR0_EL1, SMEver, SME2p1, CAP_HWCAP, KERNEL_HWCAP_SME2P1), HWCAP_CAP(ID_AA64SMFR0_EL1, SMEver, SME2, CAP_HWCAP, KERNEL_HWCAP_SME2), HWCAP_CAP(ID_AA64SMFR0_EL1, I16I64, IMP, CAP_HWCAP, KERNEL_HWCAP_SME_I16I64), HWCAP_CAP(ID_AA64SMFR0_EL1, F64F64, IMP, CAP_HWCAP, KERNEL_HWCAP_SME_F64F64), HWCAP_CAP(ID_AA64SMFR0_EL1, I16I32, IMP, CAP_HWCAP, KERNEL_HWCAP_SME_I16I32), HWCAP_CAP(ID_AA64SMFR0_EL1, B16B16, IMP, CAP_HWCAP, KERNEL_HWCAP_SME_B16B16), HWCAP_CAP(ID_AA64SMFR0_EL1, F16F16, IMP, CAP_HWCAP, KERNEL_HWCAP_SME_F16F16), HWCAP_CAP(ID_AA64SMFR0_EL1, F8F16, IMP, CAP_HWCAP, KERNEL_HWCAP_SME_F8F16), HWCAP_CAP(ID_AA64SMFR0_EL1, F8F32, IMP, CAP_HWCAP, KERNEL_HWCAP_SME_F8F32), HWCAP_CAP(ID_AA64SMFR0_EL1, I8I32, IMP, CAP_HWCAP, KERNEL_HWCAP_SME_I8I32), HWCAP_CAP(ID_AA64SMFR0_EL1, F16F32, IMP, CAP_HWCAP, KERNEL_HWCAP_SME_F16F32), HWCAP_CAP(ID_AA64SMFR0_EL1, B16F32, IMP, CAP_HWCAP, KERNEL_HWCAP_SME_B16F32), HWCAP_CAP(ID_AA64SMFR0_EL1, BI32I32, IMP, CAP_HWCAP, KERNEL_HWCAP_SME_BI32I32), HWCAP_CAP(ID_AA64SMFR0_EL1, F32F32, IMP, CAP_HWCAP, KERNEL_HWCAP_SME_F32F32), HWCAP_CAP(ID_AA64SMFR0_EL1, SF8FMA, IMP, CAP_HWCAP, KERNEL_HWCAP_SME_SF8FMA), HWCAP_CAP(ID_AA64SMFR0_EL1, SF8DP4, IMP, CAP_HWCAP, KERNEL_HWCAP_SME_SF8DP4), HWCAP_CAP(ID_AA64SMFR0_EL1, SF8DP2, IMP, CAP_HWCAP, KERNEL_HWCAP_SME_SF8DP2), #endif /* CONFIG_ARM64_SME */ HWCAP_CAP(ID_AA64FPFR0_EL1, F8CVT, IMP, CAP_HWCAP, KERNEL_HWCAP_F8CVT), HWCAP_CAP(ID_AA64FPFR0_EL1, F8FMA, IMP, CAP_HWCAP, KERNEL_HWCAP_F8FMA), HWCAP_CAP(ID_AA64FPFR0_EL1, F8DP4, IMP, CAP_HWCAP, KERNEL_HWCAP_F8DP4), HWCAP_CAP(ID_AA64FPFR0_EL1, F8DP2, IMP, CAP_HWCAP, KERNEL_HWCAP_F8DP2), HWCAP_CAP(ID_AA64FPFR0_EL1, F8E4M3, IMP, CAP_HWCAP, KERNEL_HWCAP_F8E4M3), HWCAP_CAP(ID_AA64FPFR0_EL1, F8E5M2, IMP, CAP_HWCAP, KERNEL_HWCAP_F8E5M2), #ifdef CONFIG_ARM64_POE HWCAP_CAP(ID_AA64MMFR3_EL1, S1POE, IMP, CAP_HWCAP, KERNEL_HWCAP_POE), #endif {}, }; #ifdef CONFIG_COMPAT static bool compat_has_neon(const struct arm64_cpu_capabilities *cap, int scope) { /* * Check that all of MVFR1_EL1.{SIMDSP, SIMDInt, SIMDLS} are available, * in line with that of arm32 as in vfp_init(). We make sure that the * check is future proof, by making sure value is non-zero. */ u32 mvfr1; WARN_ON(scope == SCOPE_LOCAL_CPU && preemptible()); if (scope == SCOPE_SYSTEM) mvfr1 = read_sanitised_ftr_reg(SYS_MVFR1_EL1); else mvfr1 = read_sysreg_s(SYS_MVFR1_EL1); return cpuid_feature_extract_unsigned_field(mvfr1, MVFR1_EL1_SIMDSP_SHIFT) && cpuid_feature_extract_unsigned_field(mvfr1, MVFR1_EL1_SIMDInt_SHIFT) && cpuid_feature_extract_unsigned_field(mvfr1, MVFR1_EL1_SIMDLS_SHIFT); } #endif static const struct arm64_cpu_capabilities compat_elf_hwcaps[] = { #ifdef CONFIG_COMPAT HWCAP_CAP_MATCH(compat_has_neon, CAP_COMPAT_HWCAP, COMPAT_HWCAP_NEON), HWCAP_CAP(MVFR1_EL1, SIMDFMAC, IMP, CAP_COMPAT_HWCAP, COMPAT_HWCAP_VFPv4), /* Arm v8 mandates MVFR0.FPDP == {0, 2}. So, piggy back on this for the presence of VFP support */ HWCAP_CAP(MVFR0_EL1, FPDP, VFPv3, CAP_COMPAT_HWCAP, COMPAT_HWCAP_VFP), HWCAP_CAP(MVFR0_EL1, FPDP, VFPv3, CAP_COMPAT_HWCAP, COMPAT_HWCAP_VFPv3), HWCAP_CAP(MVFR1_EL1, FPHP, FP16, CAP_COMPAT_HWCAP, COMPAT_HWCAP_FPHP), HWCAP_CAP(MVFR1_EL1, SIMDHP, SIMDHP_FLOAT, CAP_COMPAT_HWCAP, COMPAT_HWCAP_ASIMDHP), HWCAP_CAP(ID_ISAR5_EL1, AES, VMULL, CAP_COMPAT_HWCAP2, COMPAT_HWCAP2_PMULL), HWCAP_CAP(ID_ISAR5_EL1, AES, IMP, CAP_COMPAT_HWCAP2, COMPAT_HWCAP2_AES), HWCAP_CAP(ID_ISAR5_EL1, SHA1, IMP, CAP_COMPAT_HWCAP2, COMPAT_HWCAP2_SHA1), HWCAP_CAP(ID_ISAR5_EL1, SHA2, IMP, CAP_COMPAT_HWCAP2, COMPAT_HWCAP2_SHA2), HWCAP_CAP(ID_ISAR5_EL1, CRC32, IMP, CAP_COMPAT_HWCAP2, COMPAT_HWCAP2_CRC32), HWCAP_CAP(ID_ISAR6_EL1, DP, IMP, CAP_COMPAT_HWCAP, COMPAT_HWCAP_ASIMDDP), HWCAP_CAP(ID_ISAR6_EL1, FHM, IMP, CAP_COMPAT_HWCAP, COMPAT_HWCAP_ASIMDFHM), HWCAP_CAP(ID_ISAR6_EL1, SB, IMP, CAP_COMPAT_HWCAP2, COMPAT_HWCAP2_SB), HWCAP_CAP(ID_ISAR6_EL1, BF16, IMP, CAP_COMPAT_HWCAP, COMPAT_HWCAP_ASIMDBF16), HWCAP_CAP(ID_ISAR6_EL1, I8MM, IMP, CAP_COMPAT_HWCAP, COMPAT_HWCAP_I8MM), HWCAP_CAP(ID_PFR2_EL1, SSBS, IMP, CAP_COMPAT_HWCAP2, COMPAT_HWCAP2_SSBS), #endif {}, }; static void cap_set_elf_hwcap(const struct arm64_cpu_capabilities *cap) { switch (cap->hwcap_type) { case CAP_HWCAP: cpu_set_feature(cap->hwcap); break; #ifdef CONFIG_COMPAT case CAP_COMPAT_HWCAP: compat_elf_hwcap |= (u32)cap->hwcap; break; case CAP_COMPAT_HWCAP2: compat_elf_hwcap2 |= (u32)cap->hwcap; break; #endif default: WARN_ON(1); break; } } /* Check if we have a particular HWCAP enabled */ static bool cpus_have_elf_hwcap(const struct arm64_cpu_capabilities *cap) { bool rc; switch (cap->hwcap_type) { case CAP_HWCAP: rc = cpu_have_feature(cap->hwcap); break; #ifdef CONFIG_COMPAT case CAP_COMPAT_HWCAP: rc = (compat_elf_hwcap & (u32)cap->hwcap) != 0; break; case CAP_COMPAT_HWCAP2: rc = (compat_elf_hwcap2 & (u32)cap->hwcap) != 0; break; #endif default: WARN_ON(1); rc = false; } return rc; } static void setup_elf_hwcaps(const struct arm64_cpu_capabilities *hwcaps) { /* We support emulation of accesses to CPU ID feature registers */ cpu_set_named_feature(CPUID); for (; hwcaps->matches; hwcaps++) if (hwcaps->matches(hwcaps, cpucap_default_scope(hwcaps))) cap_set_elf_hwcap(hwcaps); } static void update_cpu_capabilities(u16 scope_mask) { int i; const struct arm64_cpu_capabilities *caps; scope_mask &= ARM64_CPUCAP_SCOPE_MASK; for (i = 0; i < ARM64_NCAPS; i++) { caps = cpucap_ptrs[i]; if (!caps || !(caps->type & scope_mask) || cpus_have_cap(caps->capability) || !caps->matches(caps, cpucap_default_scope(caps))) continue; if (caps->desc && !caps->cpus) pr_info("detected: %s\n", caps->desc); __set_bit(caps->capability, system_cpucaps); if ((scope_mask & SCOPE_BOOT_CPU) && (caps->type & SCOPE_BOOT_CPU)) set_bit(caps->capability, boot_cpucaps); } } /* * Enable all the available capabilities on this CPU. The capabilities * with BOOT_CPU scope are handled separately and hence skipped here. */ static int cpu_enable_non_boot_scope_capabilities(void *__unused) { int i; u16 non_boot_scope = SCOPE_ALL & ~SCOPE_BOOT_CPU; for_each_available_cap(i) { const struct arm64_cpu_capabilities *cap = cpucap_ptrs[i]; if (WARN_ON(!cap)) continue; if (!(cap->type & non_boot_scope)) continue; if (cap->cpu_enable) cap->cpu_enable(cap); } return 0; } /* * Run through the enabled capabilities and enable() it on all active * CPUs */ static void __init enable_cpu_capabilities(u16 scope_mask) { int i; const struct arm64_cpu_capabilities *caps; bool boot_scope; scope_mask &= ARM64_CPUCAP_SCOPE_MASK; boot_scope = !!(scope_mask & SCOPE_BOOT_CPU); for (i = 0; i < ARM64_NCAPS; i++) { caps = cpucap_ptrs[i]; if (!caps || !(caps->type & scope_mask) || !cpus_have_cap(caps->capability)) continue; if (boot_scope && caps->cpu_enable) /* * Capabilities with SCOPE_BOOT_CPU scope are finalised * before any secondary CPU boots. Thus, each secondary * will enable the capability as appropriate via * check_local_cpu_capabilities(). The only exception is * the boot CPU, for which the capability must be * enabled here. This approach avoids costly * stop_machine() calls for this case. */ caps->cpu_enable(caps); } /* * For all non-boot scope capabilities, use stop_machine() * as it schedules the work allowing us to modify PSTATE, * instead of on_each_cpu() which uses an IPI, giving us a * PSTATE that disappears when we return. */ if (!boot_scope) stop_machine(cpu_enable_non_boot_scope_capabilities, NULL, cpu_online_mask); } /* * Run through the list of capabilities to check for conflicts. * If the system has already detected a capability, take necessary * action on this CPU. */ static void verify_local_cpu_caps(u16 scope_mask) { int i; bool cpu_has_cap, system_has_cap; const struct arm64_cpu_capabilities *caps; scope_mask &= ARM64_CPUCAP_SCOPE_MASK; for (i = 0; i < ARM64_NCAPS; i++) { caps = cpucap_ptrs[i]; if (!caps || !(caps->type & scope_mask)) continue; cpu_has_cap = caps->matches(caps, SCOPE_LOCAL_CPU); system_has_cap = cpus_have_cap(caps->capability); if (system_has_cap) { /* * Check if the new CPU misses an advertised feature, * which is not safe to miss. */ if (!cpu_has_cap && !cpucap_late_cpu_optional(caps)) break; /* * We have to issue cpu_enable() irrespective of * whether the CPU has it or not, as it is enabeld * system wide. It is upto the call back to take * appropriate action on this CPU. */ if (caps->cpu_enable) caps->cpu_enable(caps); } else { /* * Check if the CPU has this capability if it isn't * safe to have when the system doesn't. */ if (cpu_has_cap && !cpucap_late_cpu_permitted(caps)) break; } } if (i < ARM64_NCAPS) { pr_crit("CPU%d: Detected conflict for capability %d (%s), System: %d, CPU: %d\n", smp_processor_id(), caps->capability, caps->desc, system_has_cap, cpu_has_cap); if (cpucap_panic_on_conflict(caps)) cpu_panic_kernel(); else cpu_die_early(); } } /* * Check for CPU features that are used in early boot * based on the Boot CPU value. */ static void check_early_cpu_features(void) { verify_cpu_asid_bits(); verify_local_cpu_caps(SCOPE_BOOT_CPU); } static void __verify_local_elf_hwcaps(const struct arm64_cpu_capabilities *caps) { for (; caps->matches; caps++) if (cpus_have_elf_hwcap(caps) && !caps->matches(caps, SCOPE_LOCAL_CPU)) { pr_crit("CPU%d: missing HWCAP: %s\n", smp_processor_id(), caps->desc); cpu_die_early(); } } static void verify_local_elf_hwcaps(void) { __verify_local_elf_hwcaps(arm64_elf_hwcaps); if (id_aa64pfr0_32bit_el0(read_cpuid(ID_AA64PFR0_EL1))) __verify_local_elf_hwcaps(compat_elf_hwcaps); } static void verify_sve_features(void) { unsigned long cpacr = cpacr_save_enable_kernel_sve(); if (vec_verify_vq_map(ARM64_VEC_SVE)) { pr_crit("CPU%d: SVE: vector length support mismatch\n", smp_processor_id()); cpu_die_early(); } cpacr_restore(cpacr); } static void verify_sme_features(void) { unsigned long cpacr = cpacr_save_enable_kernel_sme(); if (vec_verify_vq_map(ARM64_VEC_SME)) { pr_crit("CPU%d: SME: vector length support mismatch\n", smp_processor_id()); cpu_die_early(); } cpacr_restore(cpacr); } static void verify_hyp_capabilities(void) { u64 safe_mmfr1, mmfr0, mmfr1; int parange, ipa_max; unsigned int safe_vmid_bits, vmid_bits; if (!IS_ENABLED(CONFIG_KVM)) return; safe_mmfr1 = read_sanitised_ftr_reg(SYS_ID_AA64MMFR1_EL1); mmfr0 = read_cpuid(ID_AA64MMFR0_EL1); mmfr1 = read_cpuid(ID_AA64MMFR1_EL1); /* Verify VMID bits */ safe_vmid_bits = get_vmid_bits(safe_mmfr1); vmid_bits = get_vmid_bits(mmfr1); if (vmid_bits < safe_vmid_bits) { pr_crit("CPU%d: VMID width mismatch\n", smp_processor_id()); cpu_die_early(); } /* Verify IPA range */ parange = cpuid_feature_extract_unsigned_field(mmfr0, ID_AA64MMFR0_EL1_PARANGE_SHIFT); ipa_max = id_aa64mmfr0_parange_to_phys_shift(parange); if (ipa_max < get_kvm_ipa_limit()) { pr_crit("CPU%d: IPA range mismatch\n", smp_processor_id()); cpu_die_early(); } } static void verify_mpam_capabilities(void) { u64 cpu_idr = read_cpuid(ID_AA64PFR0_EL1); u64 sys_idr = read_sanitised_ftr_reg(SYS_ID_AA64PFR0_EL1); u16 cpu_partid_max, cpu_pmg_max, sys_partid_max, sys_pmg_max; if (FIELD_GET(ID_AA64PFR0_EL1_MPAM_MASK, cpu_idr) != FIELD_GET(ID_AA64PFR0_EL1_MPAM_MASK, sys_idr)) { pr_crit("CPU%d: MPAM version mismatch\n", smp_processor_id()); cpu_die_early(); } cpu_idr = read_cpuid(MPAMIDR_EL1); sys_idr = read_sanitised_ftr_reg(SYS_MPAMIDR_EL1); if (FIELD_GET(MPAMIDR_EL1_HAS_HCR, cpu_idr) != FIELD_GET(MPAMIDR_EL1_HAS_HCR, sys_idr)) { pr_crit("CPU%d: Missing MPAM HCR\n", smp_processor_id()); cpu_die_early(); } cpu_partid_max = FIELD_GET(MPAMIDR_EL1_PARTID_MAX, cpu_idr); cpu_pmg_max = FIELD_GET(MPAMIDR_EL1_PMG_MAX, cpu_idr); sys_partid_max = FIELD_GET(MPAMIDR_EL1_PARTID_MAX, sys_idr); sys_pmg_max = FIELD_GET(MPAMIDR_EL1_PMG_MAX, sys_idr); if (cpu_partid_max < sys_partid_max || cpu_pmg_max < sys_pmg_max) { pr_crit("CPU%d: MPAM PARTID/PMG max values are mismatched\n", smp_processor_id()); cpu_die_early(); } } /* * Run through the enabled system capabilities and enable() it on this CPU. * The capabilities were decided based on the available CPUs at the boot time. * Any new CPU should match the system wide status of the capability. If the * new CPU doesn't have a capability which the system now has enabled, we * cannot do anything to fix it up and could cause unexpected failures. So * we park the CPU. */ static void verify_local_cpu_capabilities(void) { /* * The capabilities with SCOPE_BOOT_CPU are checked from * check_early_cpu_features(), as they need to be verified * on all secondary CPUs. */ verify_local_cpu_caps(SCOPE_ALL & ~SCOPE_BOOT_CPU); verify_local_elf_hwcaps(); if (system_supports_sve()) verify_sve_features(); if (system_supports_sme()) verify_sme_features(); if (is_hyp_mode_available()) verify_hyp_capabilities(); if (system_supports_mpam()) verify_mpam_capabilities(); } void check_local_cpu_capabilities(void) { /* * All secondary CPUs should conform to the early CPU features * in use by the kernel based on boot CPU. */ check_early_cpu_features(); /* * If we haven't finalised the system capabilities, this CPU gets * a chance to update the errata work arounds and local features. * Otherwise, this CPU should verify that it has all the system * advertised capabilities. */ if (!system_capabilities_finalized()) update_cpu_capabilities(SCOPE_LOCAL_CPU); else verify_local_cpu_capabilities(); } bool this_cpu_has_cap(unsigned int n) { if (!WARN_ON(preemptible()) && n < ARM64_NCAPS) { const struct arm64_cpu_capabilities *cap = cpucap_ptrs[n]; if (cap) return cap->matches(cap, SCOPE_LOCAL_CPU); } return false; } EXPORT_SYMBOL_GPL(this_cpu_has_cap); /* * This helper function is used in a narrow window when, * - The system wide safe registers are set with all the SMP CPUs and, * - The SYSTEM_FEATURE system_cpucaps may not have been set. */ static bool __maybe_unused __system_matches_cap(unsigned int n) { if (n < ARM64_NCAPS) { const struct arm64_cpu_capabilities *cap = cpucap_ptrs[n]; if (cap) return cap->matches(cap, SCOPE_SYSTEM); } return false; } void cpu_set_feature(unsigned int num) { set_bit(num, elf_hwcap); } bool cpu_have_feature(unsigned int num) { return test_bit(num, elf_hwcap); } EXPORT_SYMBOL_GPL(cpu_have_feature); unsigned long cpu_get_elf_hwcap(void) { /* * We currently only populate the first 32 bits of AT_HWCAP. Please * note that for userspace compatibility we guarantee that bits 62 * and 63 will always be returned as 0. */ return elf_hwcap[0]; } unsigned long cpu_get_elf_hwcap2(void) { return elf_hwcap[1]; } unsigned long cpu_get_elf_hwcap3(void) { return elf_hwcap[2]; } static void __init setup_boot_cpu_capabilities(void) { /* * The boot CPU's feature register values have been recorded. Detect * boot cpucaps and local cpucaps for the boot CPU, then enable and * patch alternatives for the available boot cpucaps. */ update_cpu_capabilities(SCOPE_BOOT_CPU | SCOPE_LOCAL_CPU); enable_cpu_capabilities(SCOPE_BOOT_CPU); apply_boot_alternatives(); } void __init setup_boot_cpu_features(void) { /* * Initialize the indirect array of CPU capabilities pointers before we * handle the boot CPU. */ init_cpucap_indirect_list(); /* * Detect broken pseudo-NMI. Must be called _before_ the call to * setup_boot_cpu_capabilities() since it interacts with * can_use_gic_priorities(). */ detect_system_supports_pseudo_nmi(); setup_boot_cpu_capabilities(); } static void __init setup_system_capabilities(void) { /* * The system-wide safe feature register values have been finalized. * Detect, enable, and patch alternatives for the available system * cpucaps. */ update_cpu_capabilities(SCOPE_SYSTEM); enable_cpu_capabilities(SCOPE_ALL & ~SCOPE_BOOT_CPU); apply_alternatives_all(); /* * Log any cpucaps with a cpumask as these aren't logged by * update_cpu_capabilities(). */ for (int i = 0; i < ARM64_NCAPS; i++) { const struct arm64_cpu_capabilities *caps = cpucap_ptrs[i]; if (caps && caps->cpus && caps->desc && cpumask_any(caps->cpus) < nr_cpu_ids) pr_info("detected: %s on CPU%*pbl\n", caps->desc, cpumask_pr_args(caps->cpus)); } /* * TTBR0 PAN doesn't have its own cpucap, so log it manually. */ if (system_uses_ttbr0_pan()) pr_info("emulated: Privileged Access Never (PAN) using TTBR0_EL1 switching\n"); } void __init setup_system_features(void) { setup_system_capabilities(); kpti_install_ng_mappings(); sve_setup(); sme_setup(); /* * Check for sane CTR_EL0.CWG value. */ if (!cache_type_cwg()) pr_warn("No Cache Writeback Granule information, assuming %d\n", ARCH_DMA_MINALIGN); } void __init setup_user_features(void) { user_feature_fixup(); setup_elf_hwcaps(arm64_elf_hwcaps); if (system_supports_32bit_el0()) { setup_elf_hwcaps(compat_elf_hwcaps); elf_hwcap_fixup(); } minsigstksz_setup(); } static int enable_mismatched_32bit_el0(unsigned int cpu) { /* * The first 32-bit-capable CPU we detected and so can no longer * be offlined by userspace. -1 indicates we haven't yet onlined * a 32-bit-capable CPU. */ static int lucky_winner = -1; struct cpuinfo_arm64 *info = &per_cpu(cpu_data, cpu); bool cpu_32bit = id_aa64pfr0_32bit_el0(info->reg_id_aa64pfr0); if (cpu_32bit) { cpumask_set_cpu(cpu, cpu_32bit_el0_mask); static_branch_enable_cpuslocked(&arm64_mismatched_32bit_el0); } if (cpumask_test_cpu(0, cpu_32bit_el0_mask) == cpu_32bit) return 0; if (lucky_winner >= 0) return 0; /* * We've detected a mismatch. We need to keep one of our CPUs with * 32-bit EL0 online so that is_cpu_allowed() doesn't end up rejecting * every CPU in the system for a 32-bit task. */ lucky_winner = cpu_32bit ? cpu : cpumask_any_and(cpu_32bit_el0_mask, cpu_active_mask); get_cpu_device(lucky_winner)->offline_disabled = true; setup_elf_hwcaps(compat_elf_hwcaps); elf_hwcap_fixup(); pr_info("Asymmetric 32-bit EL0 support detected on CPU %u; CPU hot-unplug disabled on CPU %u\n", cpu, lucky_winner); return 0; } static int __init init_32bit_el0_mask(void) { if (!allow_mismatched_32bit_el0) return 0; if (!zalloc_cpumask_var(&cpu_32bit_el0_mask, GFP_KERNEL)) return -ENOMEM; return cpuhp_setup_state(CPUHP_AP_ONLINE_DYN, "arm64/mismatched_32bit_el0:online", enable_mismatched_32bit_el0, NULL); } subsys_initcall_sync(init_32bit_el0_mask); static void __maybe_unused cpu_enable_cnp(struct arm64_cpu_capabilities const *cap) { cpu_enable_swapper_cnp(); } /* * We emulate only the following system register space. * Op0 = 0x3, CRn = 0x0, Op1 = 0x0, CRm = [0, 2 - 7] * See Table C5-6 System instruction encodings for System register accesses, * ARMv8 ARM(ARM DDI 0487A.f) for more details. */ static inline bool __attribute_const__ is_emulated(u32 id) { return (sys_reg_Op0(id) == 0x3 && sys_reg_CRn(id) == 0x0 && sys_reg_Op1(id) == 0x0 && (sys_reg_CRm(id) == 0 || ((sys_reg_CRm(id) >= 2) && (sys_reg_CRm(id) <= 7)))); } /* * With CRm == 0, reg should be one of : * MIDR_EL1, MPIDR_EL1 or REVIDR_EL1. */ static inline int emulate_id_reg(u32 id, u64 *valp) { switch (id) { case SYS_MIDR_EL1: *valp = read_cpuid_id(); break; case SYS_MPIDR_EL1: *valp = SYS_MPIDR_SAFE_VAL; break; case SYS_REVIDR_EL1: /* IMPLEMENTATION DEFINED values are emulated with 0 */ *valp = 0; break; default: return -EINVAL; } return 0; } static int emulate_sys_reg(u32 id, u64 *valp) { struct arm64_ftr_reg *regp; if (!is_emulated(id)) return -EINVAL; if (sys_reg_CRm(id) == 0) return emulate_id_reg(id, valp); regp = get_arm64_ftr_reg_nowarn(id); if (regp) *valp = arm64_ftr_reg_user_value(regp); else /* * The untracked registers are either IMPLEMENTATION DEFINED * (e.g, ID_AFR0_EL1) or reserved RAZ. */ *valp = 0; return 0; } int do_emulate_mrs(struct pt_regs *regs, u32 sys_reg, u32 rt) { int rc; u64 val; rc = emulate_sys_reg(sys_reg, &val); if (!rc) { pt_regs_write_reg(regs, rt, val); arm64_skip_faulting_instruction(regs, AARCH64_INSN_SIZE); } return rc; } bool try_emulate_mrs(struct pt_regs *regs, u32 insn) { u32 sys_reg, rt; if (compat_user_mode(regs) || !aarch64_insn_is_mrs(insn)) return false; /* * sys_reg values are defined as used in mrs/msr instruction. * shift the imm value to get the encoding. */ sys_reg = (u32)aarch64_insn_decode_immediate(AARCH64_INSN_IMM_16, insn) << 5; rt = aarch64_insn_decode_register(AARCH64_INSN_REGTYPE_RT, insn); return do_emulate_mrs(regs, sys_reg, rt) == 0; } enum mitigation_state arm64_get_meltdown_state(void) { if (__meltdown_safe) return SPECTRE_UNAFFECTED; if (arm64_kernel_unmapped_at_el0()) return SPECTRE_MITIGATED; return SPECTRE_VULNERABLE; } ssize_t cpu_show_meltdown(struct device *dev, struct device_attribute *attr, char *buf) { switch (arm64_get_meltdown_state()) { case SPECTRE_UNAFFECTED: return sprintf(buf, "Not affected\n"); case SPECTRE_MITIGATED: return sprintf(buf, "Mitigation: PTI\n"); default: return sprintf(buf, "Vulnerable\n"); } } |
| 36 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 | /* * linux/include/linux/console.h * * Copyright (C) 1993 Hamish Macdonald * * This file is subject to the terms and conditions of the GNU General Public * License. See the file COPYING in the main directory of this archive * for more details. * * Changed: * 10-Mar-94: Arno Griffioen: Conversion for vt100 emulator port from PC LINUX */ #ifndef _LINUX_CONSOLE_H_ #define _LINUX_CONSOLE_H_ 1 #include <linux/atomic.h> #include <linux/bits.h> #include <linux/irq_work.h> #include <linux/rculist.h> #include <linux/rcuwait.h> #include <linux/types.h> #include <linux/vesa.h> struct vc_data; struct console_font_op; struct console_font; struct module; struct tty_struct; struct notifier_block; enum con_scroll { SM_UP, SM_DOWN, }; enum vc_intensity; /** * struct consw - callbacks for consoles * * @owner: the module to get references of when this console is used * @con_startup: set up the console and return its name (like VGA, EGA, ...) * @con_init: initialize the console on @vc. @init is true for the very first * call on this @vc. * @con_deinit: deinitialize the console from @vc. * @con_clear: erase @count characters at [@x, @y] on @vc. @count >= 1. * @con_putc: emit one character with attributes @ca to [@x, @y] on @vc. * (optional -- @con_putcs would be called instead) * @con_putcs: emit @count characters with attributes @s to [@x, @y] on @vc. * @con_cursor: enable/disable cursor depending on @enable * @con_scroll: move lines from @top to @bottom in direction @dir by @lines. * Return true if no generic handling should be done. * Invoked by csi_M and printing to the console. * @con_switch: notifier about the console switch; it is supposed to return * true if a redraw is needed. * @con_blank: blank/unblank the console. The target mode is passed in @blank. * @mode_switch is set if changing from/to text/graphics. The hook * is supposed to return true if a redraw is needed. * @con_font_set: set console @vc font to @font with height @vpitch. @flags can * be %KD_FONT_FLAG_DONT_RECALC. (optional) * @con_font_get: fetch the current font on @vc of height @vpitch into @font. * (optional) * @con_font_default: set default font on @vc. @name can be %NULL or font name * to search for. @font can be filled back. (optional) * @con_resize: resize the @vc console to @width x @height. @from_user is true * when this change comes from the user space. * @con_set_palette: sets the palette of the console @vc to @table (optional) * @con_scrolldelta: the contents of the console should be scrolled by @lines. * Invoked by user. (optional) * @con_set_origin: set origin (see &vc_data::vc_origin) of the @vc. If not * provided or returns false, the origin is set to * @vc->vc_screenbuf. (optional) * @con_save_screen: save screen content into @vc->vc_screenbuf. Called e.g. * upon entering graphics. (optional) * @con_build_attr: build attributes based on @color, @intensity and other * parameters. The result is used for both normal and erase * characters. (optional) * @con_invert_region: invert a region of length @count on @vc starting at @p. * (optional) * @con_debug_enter: prepare the console for the debugger. This includes, but * is not limited to, unblanking the console, loading an * appropriate palette, and allowing debugger generated output. * (optional) * @con_debug_leave: restore the console to its pre-debug state as closely as * possible. (optional) */ struct consw { struct module *owner; const char *(*con_startup)(void); void (*con_init)(struct vc_data *vc, bool init); void (*con_deinit)(struct vc_data *vc); void (*con_clear)(struct vc_data *vc, unsigned int y, unsigned int x, unsigned int count); void (*con_putc)(struct vc_data *vc, u16 ca, unsigned int y, unsigned int x); void (*con_putcs)(struct vc_data *vc, const u16 *s, unsigned int count, unsigned int ypos, unsigned int xpos); void (*con_cursor)(struct vc_data *vc, bool enable); bool (*con_scroll)(struct vc_data *vc, unsigned int top, unsigned int bottom, enum con_scroll dir, unsigned int lines); bool (*con_switch)(struct vc_data *vc); bool (*con_blank)(struct vc_data *vc, enum vesa_blank_mode blank, bool mode_switch); int (*con_font_set)(struct vc_data *vc, const struct console_font *font, unsigned int vpitch, unsigned int flags); int (*con_font_get)(struct vc_data *vc, struct console_font *font, unsigned int vpitch); int (*con_font_default)(struct vc_data *vc, struct console_font *font, const char *name); int (*con_resize)(struct vc_data *vc, unsigned int width, unsigned int height, bool from_user); void (*con_set_palette)(struct vc_data *vc, const unsigned char *table); void (*con_scrolldelta)(struct vc_data *vc, int lines); bool (*con_set_origin)(struct vc_data *vc); void (*con_save_screen)(struct vc_data *vc); u8 (*con_build_attr)(struct vc_data *vc, u8 color, enum vc_intensity intensity, bool blink, bool underline, bool reverse, bool italic); void (*con_invert_region)(struct vc_data *vc, u16 *p, int count); void (*con_debug_enter)(struct vc_data *vc); void (*con_debug_leave)(struct vc_data *vc); }; extern const struct consw *conswitchp; extern const struct consw dummy_con; /* dummy console buffer */ extern const struct consw vga_con; /* VGA text console */ extern const struct consw newport_con; /* SGI Newport console */ struct screen_info; #ifdef CONFIG_VGA_CONSOLE void vgacon_register_screen(struct screen_info *si); #else static inline void vgacon_register_screen(struct screen_info *si) { } #endif int con_is_bound(const struct consw *csw); int do_unregister_con_driver(const struct consw *csw); int do_take_over_console(const struct consw *sw, int first, int last, int deflt); void give_up_console(const struct consw *sw); #ifdef CONFIG_VT void con_debug_enter(struct vc_data *vc); void con_debug_leave(void); #else static inline void con_debug_enter(struct vc_data *vc) { } static inline void con_debug_leave(void) { } #endif /* * The interface for a console, or any other device that wants to capture * console messages (printer driver?) */ /** * enum cons_flags - General console flags * @CON_PRINTBUFFER: Used by newly registered consoles to avoid duplicate * output of messages that were already shown by boot * consoles or read by userspace via syslog() syscall. * @CON_CONSDEV: Indicates that the console driver is backing * /dev/console. * @CON_ENABLED: Indicates if a console is allowed to print records. If * false, the console also will not advance to later * records. * @CON_BOOT: Marks the console driver as early console driver which * is used during boot before the real driver becomes * available. It will be automatically unregistered * when the real console driver is registered unless * "keep_bootcon" parameter is used. * @CON_ANYTIME: A misnomed historical flag which tells the core code * that the legacy @console::write callback can be invoked * on a CPU which is marked OFFLINE. That is misleading as * it suggests that there is no contextual limit for * invoking the callback. The original motivation was * readiness of the per-CPU areas. * @CON_BRL: Indicates a braille device which is exempt from * receiving the printk spam for obvious reasons. * @CON_EXTENDED: The console supports the extended output format of * /dev/kmesg which requires a larger output buffer. * @CON_SUSPENDED: Indicates if a console is suspended. If true, the * printing callbacks must not be called. * @CON_NBCON: Console can operate outside of the legacy style console_lock * constraints. */ enum cons_flags { CON_PRINTBUFFER = BIT(0), CON_CONSDEV = BIT(1), CON_ENABLED = BIT(2), CON_BOOT = BIT(3), CON_ANYTIME = BIT(4), CON_BRL = BIT(5), CON_EXTENDED = BIT(6), CON_SUSPENDED = BIT(7), CON_NBCON = BIT(8), }; /** * struct nbcon_state - console state for nbcon consoles * @atom: Compound of the state fields for atomic operations * * @req_prio: The priority of a handover request * @prio: The priority of the current owner * @unsafe: Console is busy in a non takeover region * @unsafe_takeover: A hostile takeover in an unsafe state happened in the * past. The console cannot be safe until re-initialized. * @cpu: The CPU on which the owner runs * * To be used for reading and preparing of the value stored in the nbcon * state variable @console::nbcon_state. * * The @prio and @req_prio fields are particularly important to allow * spin-waiting to timeout and give up without the risk of a waiter being * assigned the lock after giving up. */ struct nbcon_state { union { unsigned int atom; struct { unsigned int prio : 2; unsigned int req_prio : 2; unsigned int unsafe : 1; unsigned int unsafe_takeover : 1; unsigned int cpu : 24; }; }; }; /* * The nbcon_state struct is used to easily create and interpret values that * are stored in the @console::nbcon_state variable. Ensure this struct stays * within the size boundaries of the atomic variable's underlying type in * order to avoid any accidental truncation. */ static_assert(sizeof(struct nbcon_state) <= sizeof(int)); /** * enum nbcon_prio - console owner priority for nbcon consoles * @NBCON_PRIO_NONE: Unused * @NBCON_PRIO_NORMAL: Normal (non-emergency) usage * @NBCON_PRIO_EMERGENCY: Emergency output (WARN/OOPS...) * @NBCON_PRIO_PANIC: Panic output * @NBCON_PRIO_MAX: The number of priority levels * * A higher priority context can takeover the console when it is * in the safe state. The final attempt to flush consoles in panic() * can be allowed to do so even in an unsafe state (Hope and pray). */ enum nbcon_prio { NBCON_PRIO_NONE = 0, NBCON_PRIO_NORMAL, NBCON_PRIO_EMERGENCY, NBCON_PRIO_PANIC, NBCON_PRIO_MAX, }; struct console; struct printk_buffers; /** * struct nbcon_context - Context for console acquire/release * @console: The associated console * @spinwait_max_us: Limit for spin-wait acquire * @prio: Priority of the context * @allow_unsafe_takeover: Allow performing takeover even if unsafe. Can * be used only with NBCON_PRIO_PANIC @prio. It * might cause a system freeze when the console * is used later. * @backlog: Ringbuffer has pending records * @pbufs: Pointer to the text buffer for this context * @seq: The sequence number to print for this context */ struct nbcon_context { /* members set by caller */ struct console *console; unsigned int spinwait_max_us; enum nbcon_prio prio; unsigned int allow_unsafe_takeover : 1; /* members set by emit */ unsigned int backlog : 1; /* members set by acquire */ struct printk_buffers *pbufs; u64 seq; }; /** * struct nbcon_write_context - Context handed to the nbcon write callbacks * @ctxt: The core console context * @outbuf: Pointer to the text buffer for output * @len: Length to write * @unsafe_takeover: If a hostile takeover in an unsafe state has occurred */ struct nbcon_write_context { struct nbcon_context __private ctxt; char *outbuf; unsigned int len; bool unsafe_takeover; }; /** * struct console - The console descriptor structure * @name: The name of the console driver * @write: Legacy write callback to output messages (Optional) * @read: Read callback for console input (Optional) * @device: The underlying TTY device driver (Optional) * @unblank: Callback to unblank the console (Optional) * @setup: Callback for initializing the console (Optional) * @exit: Callback for teardown of the console (Optional) * @match: Callback for matching a console (Optional) * @flags: Console flags. See enum cons_flags * @index: Console index, e.g. port number * @cflag: TTY control mode flags * @ispeed: TTY input speed * @ospeed: TTY output speed * @seq: Sequence number of the next ringbuffer record to print * @dropped: Number of unreported dropped ringbuffer records * @data: Driver private data * @node: hlist node for the console list * * @nbcon_state: State for nbcon consoles * @nbcon_seq: Sequence number of the next record for nbcon to print * @nbcon_device_ctxt: Context available for non-printing operations * @nbcon_prev_seq: Seq num the previous nbcon owner was assigned to print * @pbufs: Pointer to nbcon private buffer * @kthread: Printer kthread for this console * @rcuwait: RCU-safe wait object for @kthread waking * @irq_work: Defer @kthread waking to IRQ work context */ struct console { char name[16]; void (*write)(struct console *co, const char *s, unsigned int count); int (*read)(struct console *co, char *s, unsigned int count); struct tty_driver *(*device)(struct console *co, int *index); void (*unblank)(void); int (*setup)(struct console *co, char *options); int (*exit)(struct console *co); int (*match)(struct console *co, char *name, int idx, char *options); short flags; short index; int cflag; uint ispeed; uint ospeed; u64 seq; unsigned long dropped; void *data; struct hlist_node node; /* nbcon console specific members */ /** * @write_atomic: * * NBCON callback to write out text in any context. (Optional) * * This callback is called with the console already acquired. However, * a higher priority context is allowed to take it over by default. * * The callback must call nbcon_enter_unsafe() and nbcon_exit_unsafe() * around any code where the takeover is not safe, for example, when * manipulating the serial port registers. * * nbcon_enter_unsafe() will fail if the context has lost the console * ownership in the meantime. In this case, the callback is no longer * allowed to go forward. It must back out immediately and carefully. * The buffer content is also no longer trusted since it no longer * belongs to the context. * * The callback should allow the takeover whenever it is safe. It * increases the chance to see messages when the system is in trouble. * If the driver must reacquire ownership in order to finalize or * revert hardware changes, nbcon_reacquire_nobuf() can be used. * However, on reacquire the buffer content is no longer available. A * reacquire cannot be used to resume printing. * * The callback can be called from any context (including NMI). * Therefore it must avoid usage of any locking and instead rely * on the console ownership for synchronization. */ void (*write_atomic)(struct console *con, struct nbcon_write_context *wctxt); /** * @write_thread: * * NBCON callback to write out text in task context. * * This callback must be called only in task context with both * device_lock() and the nbcon console acquired with * NBCON_PRIO_NORMAL. * * The same rules for console ownership verification and unsafe * sections handling applies as with write_atomic(). * * The console ownership handling is necessary for synchronization * against write_atomic() which is synchronized only via the context. * * The device_lock() provides the primary serialization for operations * on the device. It might be as relaxed (mutex)[*] or as tight * (disabled preemption and interrupts) as needed. It allows * the kthread to operate in the least restrictive mode[**]. * * [*] Standalone nbcon_context_try_acquire() is not safe with * the preemption enabled, see nbcon_owner_matches(). But it * can be safe when always called in the preemptive context * under the device_lock(). * * [**] The device_lock() makes sure that nbcon_context_try_acquire() * would never need to spin which is important especially with * PREEMPT_RT. */ void (*write_thread)(struct console *con, struct nbcon_write_context *wctxt); /** * @device_lock: * * NBCON callback to begin synchronization with driver code. * * Console drivers typically must deal with access to the hardware * via user input/output (such as an interactive login shell) and * output of kernel messages via printk() calls. This callback is * called by the printk-subsystem whenever it needs to synchronize * with hardware access by the driver. It should be implemented to * use whatever synchronization mechanism the driver is using for * itself (for example, the port lock for uart serial consoles). * * The callback is always called from task context. It may use any * synchronization method required by the driver. * * IMPORTANT: The callback MUST disable migration. The console driver * may be using a synchronization mechanism that already takes * care of this (such as spinlocks). Otherwise this function must * explicitly call migrate_disable(). * * The flags argument is provided as a convenience to the driver. It * will be passed again to device_unlock(). It can be ignored if the * driver does not need it. */ void (*device_lock)(struct console *con, unsigned long *flags); /** * @device_unlock: * * NBCON callback to finish synchronization with driver code. * * It is the counterpart to device_lock(). * * This callback is always called from task context. It must * appropriately re-enable migration (depending on how device_lock() * disabled migration). * * The flags argument is the value of the same variable that was * passed to device_lock(). */ void (*device_unlock)(struct console *con, unsigned long flags); atomic_t __private nbcon_state; atomic_long_t __private nbcon_seq; struct nbcon_context __private nbcon_device_ctxt; atomic_long_t __private nbcon_prev_seq; struct printk_buffers *pbufs; struct task_struct *kthread; struct rcuwait rcuwait; struct irq_work irq_work; }; #ifdef CONFIG_LOCKDEP extern void lockdep_assert_console_list_lock_held(void); #else static inline void lockdep_assert_console_list_lock_held(void) { } #endif #ifdef CONFIG_DEBUG_LOCK_ALLOC extern bool console_srcu_read_lock_is_held(void); #else static inline bool console_srcu_read_lock_is_held(void) { return 1; } #endif extern int console_srcu_read_lock(void); extern void console_srcu_read_unlock(int cookie); extern void console_list_lock(void) __acquires(console_mutex); extern void console_list_unlock(void) __releases(console_mutex); extern struct hlist_head console_list; /** * console_srcu_read_flags - Locklessly read flags of a possibly registered * console * @con: struct console pointer of console to read flags from * * Locklessly reading @con->flags provides a consistent read value because * there is at most one CPU modifying @con->flags and that CPU is using only * read-modify-write operations to do so. * * Requires console_srcu_read_lock to be held, which implies that @con might * be a registered console. The purpose of holding console_srcu_read_lock is * to guarantee that the console state is valid (CON_SUSPENDED/CON_ENABLED) * and that no exit/cleanup routines will run if the console is currently * undergoing unregistration. * * If the caller is holding the console_list_lock or it is _certain_ that * @con is not and will not become registered, the caller may read * @con->flags directly instead. * * Context: Any context. * Return: The current value of the @con->flags field. */ static inline short console_srcu_read_flags(const struct console *con) { WARN_ON_ONCE(!console_srcu_read_lock_is_held()); /* * The READ_ONCE() matches the WRITE_ONCE() when @flags are modified * for registered consoles with console_srcu_write_flags(). */ return data_race(READ_ONCE(con->flags)); } /** * console_srcu_write_flags - Write flags for a registered console * @con: struct console pointer of console to write flags to * @flags: new flags value to write * * Only use this function to write flags for registered consoles. It * requires holding the console_list_lock. * * Context: Any context. */ static inline void console_srcu_write_flags(struct console *con, short flags) { lockdep_assert_console_list_lock_held(); /* This matches the READ_ONCE() in console_srcu_read_flags(). */ WRITE_ONCE(con->flags, flags); } /* Variant of console_is_registered() when the console_list_lock is held. */ static inline bool console_is_registered_locked(const struct console *con) { lockdep_assert_console_list_lock_held(); return !hlist_unhashed(&con->node); } /* * console_is_registered - Check if the console is registered * @con: struct console pointer of console to check * * Context: Process context. May sleep while acquiring console list lock. * Return: true if the console is in the console list, otherwise false. * * If false is returned for a console that was previously registered, it * can be assumed that the console's unregistration is fully completed, * including the exit() callback after console list removal. */ static inline bool console_is_registered(const struct console *con) { bool ret; console_list_lock(); ret = console_is_registered_locked(con); console_list_unlock(); return ret; } /** * for_each_console_srcu() - Iterator over registered consoles * @con: struct console pointer used as loop cursor * * Although SRCU guarantees the console list will be consistent, the * struct console fields may be updated by other CPUs while iterating. * * Requires console_srcu_read_lock to be held. Can be invoked from * any context. */ #define for_each_console_srcu(con) \ hlist_for_each_entry_srcu(con, &console_list, node, \ console_srcu_read_lock_is_held()) /** * for_each_console() - Iterator over registered consoles * @con: struct console pointer used as loop cursor * * The console list and the &console.flags are immutable while iterating. * * Requires console_list_lock to be held. */ #define for_each_console(con) \ lockdep_assert_console_list_lock_held(); \ hlist_for_each_entry(con, &console_list, node) #ifdef CONFIG_PRINTK extern void nbcon_cpu_emergency_enter(void); extern void nbcon_cpu_emergency_exit(void); extern bool nbcon_can_proceed(struct nbcon_write_context *wctxt); extern bool nbcon_enter_unsafe(struct nbcon_write_context *wctxt); extern bool nbcon_exit_unsafe(struct nbcon_write_context *wctxt); extern void nbcon_reacquire_nobuf(struct nbcon_write_context *wctxt); #else static inline void nbcon_cpu_emergency_enter(void) { } static inline void nbcon_cpu_emergency_exit(void) { } static inline bool nbcon_can_proceed(struct nbcon_write_context *wctxt) { return false; } static inline bool nbcon_enter_unsafe(struct nbcon_write_context *wctxt) { return false; } static inline bool nbcon_exit_unsafe(struct nbcon_write_context *wctxt) { return false; } static inline void nbcon_reacquire_nobuf(struct nbcon_write_context *wctxt) { } #endif extern int console_set_on_cmdline; extern struct console *early_console; enum con_flush_mode { CONSOLE_FLUSH_PENDING, CONSOLE_REPLAY_ALL, }; extern int add_preferred_console(const char *name, const short idx, char *options); extern void console_force_preferred_locked(struct console *con); extern void register_console(struct console *); extern int unregister_console(struct console *); extern void console_lock(void); extern int console_trylock(void); extern void console_unlock(void); extern void console_conditional_schedule(void); extern void console_unblank(void); extern void console_flush_on_panic(enum con_flush_mode mode); extern struct tty_driver *console_device(int *); extern void console_stop(struct console *); extern void console_start(struct console *); extern int is_console_locked(void); extern int braille_register_console(struct console *, int index, char *console_options, char *braille_options); extern int braille_unregister_console(struct console *); #ifdef CONFIG_TTY extern void console_sysfs_notify(void); #else static inline void console_sysfs_notify(void) { } #endif extern bool console_suspend_enabled; /* Suspend and resume console messages over PM events */ extern void suspend_console(void); extern void resume_console(void); int mda_console_init(void); void vcs_make_sysfs(int index); void vcs_remove_sysfs(int index); /* Some debug stub to catch some of the obvious races in the VT code */ #define WARN_CONSOLE_UNLOCKED() \ WARN_ON(!atomic_read(&ignore_console_lock_warning) && \ !is_console_locked() && !oops_in_progress) /* * Increment ignore_console_lock_warning if you need to quiet * WARN_CONSOLE_UNLOCKED() for debugging purposes. */ extern atomic_t ignore_console_lock_warning; extern void console_init(void); /* For deferred console takeover */ void dummycon_register_output_notifier(struct notifier_block *nb); void dummycon_unregister_output_notifier(struct notifier_block *nb); #endif /* _LINUX_CONSOLE_H */ |
| 2 174 60 17 70 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 1522 1523 1524 1525 1526 1527 1528 1529 1530 1531 1532 1533 1534 1535 1536 1537 1538 1539 1540 1541 1542 1543 1544 1545 1546 1547 | /* SPDX-License-Identifier: GPL-2.0-only */ /* * Copyright (C) 2012,2013 - ARM Ltd * Author: Marc Zyngier <marc.zyngier@arm.com> * * Derived from arch/arm/include/asm/kvm_host.h: * Copyright (C) 2012 - Virtual Open Systems and Columbia University * Author: Christoffer Dall <c.dall@virtualopensystems.com> */ #ifndef __ARM64_KVM_HOST_H__ #define __ARM64_KVM_HOST_H__ #include <linux/arm-smccc.h> #include <linux/bitmap.h> #include <linux/types.h> #include <linux/jump_label.h> #include <linux/kvm_types.h> #include <linux/maple_tree.h> #include <linux/percpu.h> #include <linux/psci.h> #include <asm/arch_gicv3.h> #include <asm/barrier.h> #include <asm/cpufeature.h> #include <asm/cputype.h> #include <asm/daifflags.h> #include <asm/fpsimd.h> #include <asm/kvm.h> #include <asm/kvm_asm.h> #include <asm/vncr_mapping.h> #define __KVM_HAVE_ARCH_INTC_INITIALIZED #define KVM_HALT_POLL_NS_DEFAULT 500000 #include <kvm/arm_vgic.h> #include <kvm/arm_arch_timer.h> #include <kvm/arm_pmu.h> #define KVM_MAX_VCPUS VGIC_V3_MAX_CPUS #define KVM_VCPU_MAX_FEATURES 7 #define KVM_VCPU_VALID_FEATURES (BIT(KVM_VCPU_MAX_FEATURES) - 1) #define KVM_REQ_SLEEP \ KVM_ARCH_REQ_FLAGS(0, KVM_REQUEST_WAIT | KVM_REQUEST_NO_WAKEUP) #define KVM_REQ_IRQ_PENDING KVM_ARCH_REQ(1) #define KVM_REQ_VCPU_RESET KVM_ARCH_REQ(2) #define KVM_REQ_RECORD_STEAL KVM_ARCH_REQ(3) #define KVM_REQ_RELOAD_GICv4 KVM_ARCH_REQ(4) #define KVM_REQ_RELOAD_PMU KVM_ARCH_REQ(5) #define KVM_REQ_SUSPEND KVM_ARCH_REQ(6) #define KVM_REQ_RESYNC_PMU_EL0 KVM_ARCH_REQ(7) #define KVM_REQ_NESTED_S2_UNMAP KVM_ARCH_REQ(8) #define KVM_DIRTY_LOG_MANUAL_CAPS (KVM_DIRTY_LOG_MANUAL_PROTECT_ENABLE | \ KVM_DIRTY_LOG_INITIALLY_SET) #define KVM_HAVE_MMU_RWLOCK /* * Mode of operation configurable with kvm-arm.mode early param. * See Documentation/admin-guide/kernel-parameters.txt for more information. */ enum kvm_mode { KVM_MODE_DEFAULT, KVM_MODE_PROTECTED, KVM_MODE_NV, KVM_MODE_NONE, }; #ifdef CONFIG_KVM enum kvm_mode kvm_get_mode(void); #else static inline enum kvm_mode kvm_get_mode(void) { return KVM_MODE_NONE; }; #endif extern unsigned int __ro_after_init kvm_sve_max_vl; extern unsigned int __ro_after_init kvm_host_sve_max_vl; int __init kvm_arm_init_sve(void); u32 __attribute_const__ kvm_target_cpu(void); void kvm_reset_vcpu(struct kvm_vcpu *vcpu); void kvm_arm_vcpu_destroy(struct kvm_vcpu *vcpu); struct kvm_hyp_memcache { phys_addr_t head; unsigned long nr_pages; struct pkvm_mapping *mapping; /* only used from EL1 */ }; static inline void push_hyp_memcache(struct kvm_hyp_memcache *mc, phys_addr_t *p, phys_addr_t (*to_pa)(void *virt)) { *p = mc->head; mc->head = to_pa(p); mc->nr_pages++; } static inline void *pop_hyp_memcache(struct kvm_hyp_memcache *mc, void *(*to_va)(phys_addr_t phys)) { phys_addr_t *p = to_va(mc->head); if (!mc->nr_pages) return NULL; mc->head = *p; mc->nr_pages--; return p; } static inline int __topup_hyp_memcache(struct kvm_hyp_memcache *mc, unsigned long min_pages, void *(*alloc_fn)(void *arg), phys_addr_t (*to_pa)(void *virt), void *arg) { while (mc->nr_pages < min_pages) { phys_addr_t *p = alloc_fn(arg); if (!p) return -ENOMEM; push_hyp_memcache(mc, p, to_pa); } return 0; } static inline void __free_hyp_memcache(struct kvm_hyp_memcache *mc, void (*free_fn)(void *virt, void *arg), void *(*to_va)(phys_addr_t phys), void *arg) { while (mc->nr_pages) free_fn(pop_hyp_memcache(mc, to_va), arg); } void free_hyp_memcache(struct kvm_hyp_memcache *mc); int topup_hyp_memcache(struct kvm_hyp_memcache *mc, unsigned long min_pages); struct kvm_vmid { atomic64_t id; }; struct kvm_s2_mmu { struct kvm_vmid vmid; /* * stage2 entry level table * * Two kvm_s2_mmu structures in the same VM can point to the same * pgd here. This happens when running a guest using a * translation regime that isn't affected by its own stage-2 * translation, such as a non-VHE hypervisor running at vEL2, or * for vEL1/EL0 with vHCR_EL2.VM == 0. In that case, we use the * canonical stage-2 page tables. */ phys_addr_t pgd_phys; struct kvm_pgtable *pgt; /* * VTCR value used on the host. For a non-NV guest (or a NV * guest that runs in a context where its own S2 doesn't * apply), its T0SZ value reflects that of the IPA size. * * For a shadow S2 MMU, T0SZ reflects the PARange exposed to * the guest. */ u64 vtcr; /* The last vcpu id that ran on each physical CPU */ int __percpu *last_vcpu_ran; #define KVM_ARM_EAGER_SPLIT_CHUNK_SIZE_DEFAULT 0 /* * Memory cache used to split * KVM_CAP_ARM_EAGER_SPLIT_CHUNK_SIZE worth of huge pages. It * is used to allocate stage2 page tables while splitting huge * pages. The choice of KVM_CAP_ARM_EAGER_SPLIT_CHUNK_SIZE * influences both the capacity of the split page cache, and * how often KVM reschedules. Be wary of raising CHUNK_SIZE * too high. * * Protected by kvm->slots_lock. */ struct kvm_mmu_memory_cache split_page_cache; uint64_t split_page_chunk_size; struct kvm_arch *arch; /* * For a shadow stage-2 MMU, the virtual vttbr used by the * host to parse the guest S2. * This either contains: * - the virtual VTTBR programmed by the guest hypervisor with * CnP cleared * - The value 1 (VMID=0, BADDR=0, CnP=1) if invalid * * We also cache the full VTCR which gets used for TLB invalidation, * taking the ARM ARM's "Any of the bits in VTCR_EL2 are permitted * to be cached in a TLB" to the letter. */ u64 tlb_vttbr; u64 tlb_vtcr; /* * true when this represents a nested context where virtual * HCR_EL2.VM == 1 */ bool nested_stage2_enabled; /* * true when this MMU needs to be unmapped before being used for a new * purpose. */ bool pending_unmap; /* * 0: Nobody is currently using this, check vttbr for validity * >0: Somebody is actively using this. */ atomic_t refcnt; }; struct kvm_arch_memory_slot { }; /** * struct kvm_smccc_features: Descriptor of the hypercall services exposed to the guests * * @std_bmap: Bitmap of standard secure service calls * @std_hyp_bmap: Bitmap of standard hypervisor service calls * @vendor_hyp_bmap: Bitmap of vendor specific hypervisor service calls */ struct kvm_smccc_features { unsigned long std_bmap; unsigned long std_hyp_bmap; unsigned long vendor_hyp_bmap; }; typedef unsigned int pkvm_handle_t; struct kvm_protected_vm { pkvm_handle_t handle; struct kvm_hyp_memcache teardown_mc; bool enabled; }; struct kvm_mpidr_data { u64 mpidr_mask; DECLARE_FLEX_ARRAY(u16, cmpidr_to_idx); }; static inline u16 kvm_mpidr_index(struct kvm_mpidr_data *data, u64 mpidr) { unsigned long index = 0, mask = data->mpidr_mask; unsigned long aff = mpidr & MPIDR_HWID_BITMASK; bitmap_gather(&index, &aff, &mask, fls(mask)); return index; } struct kvm_sysreg_masks; enum fgt_group_id { __NO_FGT_GROUP__, HFGxTR_GROUP, HDFGRTR_GROUP, HDFGWTR_GROUP = HDFGRTR_GROUP, HFGITR_GROUP, HAFGRTR_GROUP, /* Must be last */ __NR_FGT_GROUP_IDS__ }; struct kvm_arch { struct kvm_s2_mmu mmu; /* * Fine-Grained UNDEF, mimicking the FGT layout defined by the * architecture. We track them globally, as we present the * same feature-set to all vcpus. * * Index 0 is currently spare. */ u64 fgu[__NR_FGT_GROUP_IDS__]; /* * Stage 2 paging state for VMs with nested S2 using a virtual * VMID. */ struct kvm_s2_mmu *nested_mmus; size_t nested_mmus_size; int nested_mmus_next; /* Interrupt controller */ struct vgic_dist vgic; /* Timers */ struct arch_timer_vm_data timer_data; /* Mandated version of PSCI */ u32 psci_version; /* Protects VM-scoped configuration data */ struct mutex config_lock; /* * If we encounter a data abort without valid instruction syndrome * information, report this to user space. User space can (and * should) opt in to this feature if KVM_CAP_ARM_NISV_TO_USER is * supported. */ #define KVM_ARCH_FLAG_RETURN_NISV_IO_ABORT_TO_USER 0 /* Memory Tagging Extension enabled for the guest */ #define KVM_ARCH_FLAG_MTE_ENABLED 1 /* At least one vCPU has ran in the VM */ #define KVM_ARCH_FLAG_HAS_RAN_ONCE 2 /* The vCPU feature set for the VM is configured */ #define KVM_ARCH_FLAG_VCPU_FEATURES_CONFIGURED 3 /* PSCI SYSTEM_SUSPEND enabled for the guest */ #define KVM_ARCH_FLAG_SYSTEM_SUSPEND_ENABLED 4 /* VM counter offset */ #define KVM_ARCH_FLAG_VM_COUNTER_OFFSET 5 /* Timer PPIs made immutable */ #define KVM_ARCH_FLAG_TIMER_PPIS_IMMUTABLE 6 /* Initial ID reg values loaded */ #define KVM_ARCH_FLAG_ID_REGS_INITIALIZED 7 /* Fine-Grained UNDEF initialised */ #define KVM_ARCH_FLAG_FGU_INITIALIZED 8 /* SVE exposed to guest */ #define KVM_ARCH_FLAG_GUEST_HAS_SVE 9 unsigned long flags; /* VM-wide vCPU feature set */ DECLARE_BITMAP(vcpu_features, KVM_VCPU_MAX_FEATURES); /* MPIDR to vcpu index mapping, optional */ struct kvm_mpidr_data *mpidr_data; /* * VM-wide PMU filter, implemented as a bitmap and big enough for * up to 2^10 events (ARMv8.0) or 2^16 events (ARMv8.1+). */ unsigned long *pmu_filter; struct arm_pmu *arm_pmu; cpumask_var_t supported_cpus; /* PMCR_EL0.N value for the guest */ u8 pmcr_n; /* Iterator for idreg debugfs */ u8 idreg_debugfs_iter; /* Hypercall features firmware registers' descriptor */ struct kvm_smccc_features smccc_feat; struct maple_tree smccc_filter; /* * Emulated CPU ID registers per VM * (Op0, Op1, CRn, CRm, Op2) of the ID registers to be saved in it * is (3, 0, 0, crm, op2), where 1<=crm<8, 0<=op2<8. * * These emulated idregs are VM-wide, but accessed from the context of a vCPU. * Atomic access to multiple idregs are guarded by kvm_arch.config_lock. */ #define IDREG_IDX(id) (((sys_reg_CRm(id) - 1) << 3) | sys_reg_Op2(id)) #define KVM_ARM_ID_REG_NUM (IDREG_IDX(sys_reg(3, 0, 0, 7, 7)) + 1) u64 id_regs[KVM_ARM_ID_REG_NUM]; u64 ctr_el0; /* Masks for VNCR-backed and general EL2 sysregs */ struct kvm_sysreg_masks *sysreg_masks; /* * For an untrusted host VM, 'pkvm.handle' is used to lookup * the associated pKVM instance in the hypervisor. */ struct kvm_protected_vm pkvm; }; struct kvm_vcpu_fault_info { u64 esr_el2; /* Hyp Syndrom Register */ u64 far_el2; /* Hyp Fault Address Register */ u64 hpfar_el2; /* Hyp IPA Fault Address Register */ u64 disr_el1; /* Deferred [SError] Status Register */ }; /* * VNCR() just places the VNCR_capable registers in the enum after * __VNCR_START__, and the value (after correction) to be an 8-byte offset * from the VNCR base. As we don't require the enum to be otherwise ordered, * we need the terrible hack below to ensure that we correctly size the * sys_regs array, no matter what. * * The __MAX__ macro has been lifted from Sean Eron Anderson's wonderful * treasure trove of bit hacks: * https://graphics.stanford.edu/~seander/bithacks.html#IntegerMinOrMax */ #define __MAX__(x,y) ((x) ^ (((x) ^ (y)) & -((x) < (y)))) #define VNCR(r) \ __before_##r, \ r = __VNCR_START__ + ((VNCR_ ## r) / 8), \ __after_##r = __MAX__(__before_##r - 1, r) #define MARKER(m) \ m, __after_##m = m - 1 enum vcpu_sysreg { __INVALID_SYSREG__, /* 0 is reserved as an invalid value */ MPIDR_EL1, /* MultiProcessor Affinity Register */ CLIDR_EL1, /* Cache Level ID Register */ CSSELR_EL1, /* Cache Size Selection Register */ TPIDR_EL0, /* Thread ID, User R/W */ TPIDRRO_EL0, /* Thread ID, User R/O */ TPIDR_EL1, /* Thread ID, Privileged */ CNTKCTL_EL1, /* Timer Control Register (EL1) */ PAR_EL1, /* Physical Address Register */ MDCCINT_EL1, /* Monitor Debug Comms Channel Interrupt Enable Reg */ OSLSR_EL1, /* OS Lock Status Register */ DISR_EL1, /* Deferred Interrupt Status Register */ /* Performance Monitors Registers */ PMCR_EL0, /* Control Register */ PMSELR_EL0, /* Event Counter Selection Register */ PMEVCNTR0_EL0, /* Event Counter Register (0-30) */ PMEVCNTR30_EL0 = PMEVCNTR0_EL0 + 30, PMCCNTR_EL0, /* Cycle Counter Register */ PMEVTYPER0_EL0, /* Event Type Register (0-30) */ PMEVTYPER30_EL0 = PMEVTYPER0_EL0 + 30, PMCCFILTR_EL0, /* Cycle Count Filter Register */ PMCNTENSET_EL0, /* Count Enable Set Register */ PMINTENSET_EL1, /* Interrupt Enable Set Register */ PMOVSSET_EL0, /* Overflow Flag Status Set Register */ PMUSERENR_EL0, /* User Enable Register */ /* Pointer Authentication Registers in a strict increasing order. */ APIAKEYLO_EL1, APIAKEYHI_EL1, APIBKEYLO_EL1, APIBKEYHI_EL1, APDAKEYLO_EL1, APDAKEYHI_EL1, APDBKEYLO_EL1, APDBKEYHI_EL1, APGAKEYLO_EL1, APGAKEYHI_EL1, /* Memory Tagging Extension registers */ RGSR_EL1, /* Random Allocation Tag Seed Register */ GCR_EL1, /* Tag Control Register */ TFSRE0_EL1, /* Tag Fault Status Register (EL0) */ POR_EL0, /* Permission Overlay Register 0 (EL0) */ /* FP/SIMD/SVE */ SVCR, FPMR, /* 32bit specific registers. */ DACR32_EL2, /* Domain Access Control Register */ IFSR32_EL2, /* Instruction Fault Status Register */ FPEXC32_EL2, /* Floating-Point Exception Control Register */ DBGVCR32_EL2, /* Debug Vector Catch Register */ /* EL2 registers */ SCTLR_EL2, /* System Control Register (EL2) */ ACTLR_EL2, /* Auxiliary Control Register (EL2) */ CPTR_EL2, /* Architectural Feature Trap Register (EL2) */ HACR_EL2, /* Hypervisor Auxiliary Control Register */ ZCR_EL2, /* SVE Control Register (EL2) */ TTBR0_EL2, /* Translation Table Base Register 0 (EL2) */ TTBR1_EL2, /* Translation Table Base Register 1 (EL2) */ TCR_EL2, /* Translation Control Register (EL2) */ PIRE0_EL2, /* Permission Indirection Register 0 (EL2) */ PIR_EL2, /* Permission Indirection Register 1 (EL2) */ POR_EL2, /* Permission Overlay Register 2 (EL2) */ SPSR_EL2, /* EL2 saved program status register */ ELR_EL2, /* EL2 exception link register */ AFSR0_EL2, /* Auxiliary Fault Status Register 0 (EL2) */ AFSR1_EL2, /* Auxiliary Fault Status Register 1 (EL2) */ ESR_EL2, /* Exception Syndrome Register (EL2) */ FAR_EL2, /* Fault Address Register (EL2) */ HPFAR_EL2, /* Hypervisor IPA Fault Address Register */ MAIR_EL2, /* Memory Attribute Indirection Register (EL2) */ AMAIR_EL2, /* Auxiliary Memory Attribute Indirection Register (EL2) */ VBAR_EL2, /* Vector Base Address Register (EL2) */ RVBAR_EL2, /* Reset Vector Base Address Register */ CONTEXTIDR_EL2, /* Context ID Register (EL2) */ SP_EL2, /* EL2 Stack Pointer */ CNTHP_CTL_EL2, CNTHP_CVAL_EL2, CNTHV_CTL_EL2, CNTHV_CVAL_EL2, /* Anything from this can be RES0/RES1 sanitised */ MARKER(__SANITISED_REG_START__), TCR2_EL2, /* Extended Translation Control Register (EL2) */ MDCR_EL2, /* Monitor Debug Configuration Register (EL2) */ CNTHCTL_EL2, /* Counter-timer Hypervisor Control register */ /* Any VNCR-capable reg goes after this point */ MARKER(__VNCR_START__), VNCR(SCTLR_EL1),/* System Control Register */ VNCR(ACTLR_EL1),/* Auxiliary Control Register */ VNCR(CPACR_EL1),/* Coprocessor Access Control */ VNCR(ZCR_EL1), /* SVE Control */ VNCR(TTBR0_EL1),/* Translation Table Base Register 0 */ VNCR(TTBR1_EL1),/* Translation Table Base Register 1 */ VNCR(TCR_EL1), /* Translation Control Register */ VNCR(TCR2_EL1), /* Extended Translation Control Register */ VNCR(ESR_EL1), /* Exception Syndrome Register */ VNCR(AFSR0_EL1),/* Auxiliary Fault Status Register 0 */ VNCR(AFSR1_EL1),/* Auxiliary Fault Status Register 1 */ VNCR(FAR_EL1), /* Fault Address Register */ VNCR(MAIR_EL1), /* Memory Attribute Indirection Register */ VNCR(VBAR_EL1), /* Vector Base Address Register */ VNCR(CONTEXTIDR_EL1), /* Context ID Register */ VNCR(AMAIR_EL1),/* Aux Memory Attribute Indirection Register */ VNCR(MDSCR_EL1),/* Monitor Debug System Control Register */ VNCR(ELR_EL1), VNCR(SP_EL1), VNCR(SPSR_EL1), VNCR(TFSR_EL1), /* Tag Fault Status Register (EL1) */ VNCR(VPIDR_EL2),/* Virtualization Processor ID Register */ VNCR(VMPIDR_EL2),/* Virtualization Multiprocessor ID Register */ VNCR(HCR_EL2), /* Hypervisor Configuration Register */ VNCR(HSTR_EL2), /* Hypervisor System Trap Register */ VNCR(VTTBR_EL2),/* Virtualization Translation Table Base Register */ VNCR(VTCR_EL2), /* Virtualization Translation Control Register */ VNCR(TPIDR_EL2),/* EL2 Software Thread ID Register */ VNCR(HCRX_EL2), /* Extended Hypervisor Configuration Register */ /* Permission Indirection Extension registers */ VNCR(PIR_EL1), /* Permission Indirection Register 1 (EL1) */ VNCR(PIRE0_EL1), /* Permission Indirection Register 0 (EL1) */ VNCR(POR_EL1), /* Permission Overlay Register 1 (EL1) */ VNCR(HFGRTR_EL2), VNCR(HFGWTR_EL2), VNCR(HFGITR_EL2), VNCR(HDFGRTR_EL2), VNCR(HDFGWTR_EL2), VNCR(HAFGRTR_EL2), VNCR(CNTVOFF_EL2), VNCR(CNTV_CVAL_EL0), VNCR(CNTV_CTL_EL0), VNCR(CNTP_CVAL_EL0), VNCR(CNTP_CTL_EL0), VNCR(ICH_HCR_EL2), NR_SYS_REGS /* Nothing after this line! */ }; struct kvm_sysreg_masks { struct { u64 res0; u64 res1; } mask[NR_SYS_REGS - __SANITISED_REG_START__]; }; struct kvm_cpu_context { struct user_pt_regs regs; /* sp = sp_el0 */ u64 spsr_abt; u64 spsr_und; u64 spsr_irq; u64 spsr_fiq; struct user_fpsimd_state fp_regs; u64 sys_regs[NR_SYS_REGS]; struct kvm_vcpu *__hyp_running_vcpu; /* This pointer has to be 4kB aligned. */ u64 *vncr_array; }; struct cpu_sve_state { __u64 zcr_el1; /* * Ordering is important since __sve_save_state/__sve_restore_state * relies on it. */ __u32 fpsr; __u32 fpcr; /* Must be SVE_VQ_BYTES (128 bit) aligned. */ __u8 sve_regs[]; }; /* * This structure is instantiated on a per-CPU basis, and contains * data that is: * * - tied to a single physical CPU, and * - either have a lifetime that does not extend past vcpu_put() * - or is an invariant for the lifetime of the system * * Use host_data_ptr(field) as a way to access a pointer to such a * field. */ struct kvm_host_data { #define KVM_HOST_DATA_FLAG_HAS_SPE 0 #define KVM_HOST_DATA_FLAG_HAS_TRBE 1 #define KVM_HOST_DATA_FLAG_HOST_SVE_ENABLED 2 #define KVM_HOST_DATA_FLAG_HOST_SME_ENABLED 3 unsigned long flags; struct kvm_cpu_context host_ctxt; /* * All pointers in this union are hyp VA. * sve_state is only used in pKVM and if system_supports_sve(). */ union { struct user_fpsimd_state *fpsimd_state; struct cpu_sve_state *sve_state; }; union { /* HYP VA pointer to the host storage for FPMR */ u64 *fpmr_ptr; /* * Used by pKVM only, as it needs to provide storage * for the host */ u64 fpmr; }; /* Ownership of the FP regs */ enum { FP_STATE_FREE, FP_STATE_HOST_OWNED, FP_STATE_GUEST_OWNED, } fp_owner; /* * host_debug_state contains the host registers which are * saved and restored during world switches. */ struct { /* {Break,watch}point registers */ struct kvm_guest_debug_arch regs; /* Statistical profiling extension */ u64 pmscr_el1; /* Self-hosted trace */ u64 trfcr_el1; /* Values of trap registers for the host before guest entry. */ u64 mdcr_el2; } host_debug_state; /* Number of programmable event counters (PMCR_EL0.N) for this CPU */ unsigned int nr_event_counters; /* Number of debug breakpoints/watchpoints for this CPU (minus 1) */ unsigned int debug_brps; unsigned int debug_wrps; }; struct kvm_host_psci_config { /* PSCI version used by host. */ u32 version; u32 smccc_version; /* Function IDs used by host if version is v0.1. */ struct psci_0_1_function_ids function_ids_0_1; bool psci_0_1_cpu_suspend_implemented; bool psci_0_1_cpu_on_implemented; bool psci_0_1_cpu_off_implemented; bool psci_0_1_migrate_implemented; }; extern struct kvm_host_psci_config kvm_nvhe_sym(kvm_host_psci_config); #define kvm_host_psci_config CHOOSE_NVHE_SYM(kvm_host_psci_config) extern s64 kvm_nvhe_sym(hyp_physvirt_offset); #define hyp_physvirt_offset CHOOSE_NVHE_SYM(hyp_physvirt_offset) extern u64 kvm_nvhe_sym(hyp_cpu_logical_map)[NR_CPUS]; #define hyp_cpu_logical_map CHOOSE_NVHE_SYM(hyp_cpu_logical_map) struct vcpu_reset_state { unsigned long pc; unsigned long r0; bool be; bool reset; }; struct kvm_vcpu_arch { struct kvm_cpu_context ctxt; /* * Guest floating point state * * The architecture has two main floating point extensions, * the original FPSIMD and SVE. These have overlapping * register views, with the FPSIMD V registers occupying the * low 128 bits of the SVE Z registers. When the core * floating point code saves the register state of a task it * records which view it saved in fp_type. */ void *sve_state; enum fp_type fp_type; unsigned int sve_max_vl; /* Stage 2 paging state used by the hardware on next switch */ struct kvm_s2_mmu *hw_mmu; /* Values of trap registers for the guest. */ u64 hcr_el2; u64 hcrx_el2; u64 mdcr_el2; /* Exception Information */ struct kvm_vcpu_fault_info fault; /* Configuration flags, set once and for all before the vcpu can run */ u8 cflags; /* Input flags to the hypervisor code, potentially cleared after use */ u8 iflags; /* State flags for kernel bookkeeping, unused by the hypervisor code */ u8 sflags; /* * Don't run the guest (internal implementation need). * * Contrary to the flags above, this is set/cleared outside of * a vcpu context, and thus cannot be mixed with the flags * themselves (or the flag accesses need to be made atomic). */ bool pause; /* * We maintain more than a single set of debug registers to support * debugging the guest from the host and to maintain separate host and * guest state during world switches. vcpu_debug_state are the debug * registers of the vcpu as the guest sees them. * * external_debug_state contains the debug values we want to debug the * guest. This is set via the KVM_SET_GUEST_DEBUG ioctl. */ struct kvm_guest_debug_arch vcpu_debug_state; struct kvm_guest_debug_arch external_debug_state; u64 external_mdscr_el1; enum { VCPU_DEBUG_FREE, VCPU_DEBUG_HOST_OWNED, VCPU_DEBUG_GUEST_OWNED, } debug_owner; /* VGIC state */ struct vgic_cpu vgic_cpu; struct arch_timer_cpu timer_cpu; struct kvm_pmu pmu; /* vcpu power state */ struct kvm_mp_state mp_state; spinlock_t mp_state_lock; /* Cache some mmu pages needed inside spinlock regions */ struct kvm_mmu_memory_cache mmu_page_cache; /* Pages to top-up the pKVM/EL2 guest pool */ struct kvm_hyp_memcache pkvm_memcache; /* Virtual SError ESR to restore when HCR_EL2.VSE is set */ u64 vsesr_el2; /* Additional reset state */ struct vcpu_reset_state reset_state; /* Guest PV state */ struct { u64 last_steal; gpa_t base; } steal; /* Per-vcpu CCSIDR override or NULL */ u32 *ccsidr; }; /* * Each 'flag' is composed of a comma-separated triplet: * * - the flag-set it belongs to in the vcpu->arch structure * - the value for that flag * - the mask for that flag * * __vcpu_single_flag() builds such a triplet for a single-bit flag. * unpack_vcpu_flag() extract the flag value from the triplet for * direct use outside of the flag accessors. */ #define __vcpu_single_flag(_set, _f) _set, (_f), (_f) #define __unpack_flag(_set, _f, _m) _f #define unpack_vcpu_flag(...) __unpack_flag(__VA_ARGS__) #define __build_check_flag(v, flagset, f, m) \ do { \ typeof(v->arch.flagset) *_fset; \ \ /* Check that the flags fit in the mask */ \ BUILD_BUG_ON(HWEIGHT(m) != HWEIGHT((f) | (m))); \ /* Check that the flags fit in the type */ \ BUILD_BUG_ON((sizeof(*_fset) * 8) <= __fls(m)); \ } while (0) #define __vcpu_get_flag(v, flagset, f, m) \ ({ \ __build_check_flag(v, flagset, f, m); \ \ READ_ONCE(v->arch.flagset) & (m); \ }) /* * Note that the set/clear accessors must be preempt-safe in order to * avoid nesting them with load/put which also manipulate flags... */ #ifdef __KVM_NVHE_HYPERVISOR__ /* the nVHE hypervisor is always non-preemptible */ #define __vcpu_flags_preempt_disable() #define __vcpu_flags_preempt_enable() #else #define __vcpu_flags_preempt_disable() preempt_disable() #define __vcpu_flags_preempt_enable() preempt_enable() #endif #define __vcpu_set_flag(v, flagset, f, m) \ do { \ typeof(v->arch.flagset) *fset; \ \ __build_check_flag(v, flagset, f, m); \ \ fset = &v->arch.flagset; \ __vcpu_flags_preempt_disable(); \ if (HWEIGHT(m) > 1) \ *fset &= ~(m); \ *fset |= (f); \ __vcpu_flags_preempt_enable(); \ } while (0) #define __vcpu_clear_flag(v, flagset, f, m) \ do { \ typeof(v->arch.flagset) *fset; \ \ __build_check_flag(v, flagset, f, m); \ \ fset = &v->arch.flagset; \ __vcpu_flags_preempt_disable(); \ *fset &= ~(m); \ __vcpu_flags_preempt_enable(); \ } while (0) #define vcpu_get_flag(v, ...) __vcpu_get_flag((v), __VA_ARGS__) #define vcpu_set_flag(v, ...) __vcpu_set_flag((v), __VA_ARGS__) #define vcpu_clear_flag(v, ...) __vcpu_clear_flag((v), __VA_ARGS__) /* KVM_ARM_VCPU_INIT completed */ #define VCPU_INITIALIZED __vcpu_single_flag(cflags, BIT(0)) /* SVE config completed */ #define VCPU_SVE_FINALIZED __vcpu_single_flag(cflags, BIT(1)) /* Exception pending */ #define PENDING_EXCEPTION __vcpu_single_flag(iflags, BIT(0)) /* * PC increment. Overlaps with EXCEPT_MASK on purpose so that it can't * be set together with an exception... */ #define INCREMENT_PC __vcpu_single_flag(iflags, BIT(1)) /* Target EL/MODE (not a single flag, but let's abuse the macro) */ #define EXCEPT_MASK __vcpu_single_flag(iflags, GENMASK(3, 1)) /* Helpers to encode exceptions with minimum fuss */ #define __EXCEPT_MASK_VAL unpack_vcpu_flag(EXCEPT_MASK) #define __EXCEPT_SHIFT __builtin_ctzl(__EXCEPT_MASK_VAL) #define __vcpu_except_flags(_f) iflags, (_f << __EXCEPT_SHIFT), __EXCEPT_MASK_VAL /* * When PENDING_EXCEPTION is set, EXCEPT_MASK can take the following * values: * * For AArch32 EL1: */ #define EXCEPT_AA32_UND __vcpu_except_flags(0) #define EXCEPT_AA32_IABT __vcpu_except_flags(1) #define EXCEPT_AA32_DABT __vcpu_except_flags(2) /* For AArch64: */ #define EXCEPT_AA64_EL1_SYNC __vcpu_except_flags(0) #define EXCEPT_AA64_EL1_IRQ __vcpu_except_flags(1) #define EXCEPT_AA64_EL1_FIQ __vcpu_except_flags(2) #define EXCEPT_AA64_EL1_SERR __vcpu_except_flags(3) /* For AArch64 with NV: */ #define EXCEPT_AA64_EL2_SYNC __vcpu_except_flags(4) #define EXCEPT_AA64_EL2_IRQ __vcpu_except_flags(5) #define EXCEPT_AA64_EL2_FIQ __vcpu_except_flags(6) #define EXCEPT_AA64_EL2_SERR __vcpu_except_flags(7) /* Physical CPU not in supported_cpus */ #define ON_UNSUPPORTED_CPU __vcpu_single_flag(sflags, BIT(0)) /* WFIT instruction trapped */ #define IN_WFIT __vcpu_single_flag(sflags, BIT(1)) /* vcpu system registers loaded on physical CPU */ #define SYSREGS_ON_CPU __vcpu_single_flag(sflags, BIT(2)) /* Software step state is Active-pending for external debug */ #define HOST_SS_ACTIVE_PENDING __vcpu_single_flag(sflags, BIT(3)) /* Software step state is Active pending for guest debug */ #define GUEST_SS_ACTIVE_PENDING __vcpu_single_flag(sflags, BIT(4)) /* PMUSERENR for the guest EL0 is on physical CPU */ #define PMUSERENR_ON_CPU __vcpu_single_flag(sflags, BIT(5)) /* WFI instruction trapped */ #define IN_WFI __vcpu_single_flag(sflags, BIT(6)) /* Pointer to the vcpu's SVE FFR for sve_{save,load}_state() */ #define vcpu_sve_pffr(vcpu) (kern_hyp_va((vcpu)->arch.sve_state) + \ sve_ffr_offset((vcpu)->arch.sve_max_vl)) #define vcpu_sve_max_vq(vcpu) sve_vq_from_vl((vcpu)->arch.sve_max_vl) #define vcpu_sve_zcr_elx(vcpu) \ (unlikely(is_hyp_ctxt(vcpu)) ? ZCR_EL2 : ZCR_EL1) #define vcpu_sve_state_size(vcpu) ({ \ size_t __size_ret; \ unsigned int __vcpu_vq; \ \ if (WARN_ON(!sve_vl_valid((vcpu)->arch.sve_max_vl))) { \ __size_ret = 0; \ } else { \ __vcpu_vq = vcpu_sve_max_vq(vcpu); \ __size_ret = SVE_SIG_REGS_SIZE(__vcpu_vq); \ } \ \ __size_ret; \ }) #define KVM_GUESTDBG_VALID_MASK (KVM_GUESTDBG_ENABLE | \ KVM_GUESTDBG_USE_SW_BP | \ KVM_GUESTDBG_USE_HW | \ KVM_GUESTDBG_SINGLESTEP) #define kvm_has_sve(kvm) (system_supports_sve() && \ test_bit(KVM_ARCH_FLAG_GUEST_HAS_SVE, &(kvm)->arch.flags)) #ifdef __KVM_NVHE_HYPERVISOR__ #define vcpu_has_sve(vcpu) kvm_has_sve(kern_hyp_va((vcpu)->kvm)) #else #define vcpu_has_sve(vcpu) kvm_has_sve((vcpu)->kvm) #endif #ifdef CONFIG_ARM64_PTR_AUTH #define vcpu_has_ptrauth(vcpu) \ ((cpus_have_final_cap(ARM64_HAS_ADDRESS_AUTH) || \ cpus_have_final_cap(ARM64_HAS_GENERIC_AUTH)) && \ (vcpu_has_feature(vcpu, KVM_ARM_VCPU_PTRAUTH_ADDRESS) || \ vcpu_has_feature(vcpu, KVM_ARM_VCPU_PTRAUTH_GENERIC))) #else #define vcpu_has_ptrauth(vcpu) false #endif #define vcpu_on_unsupported_cpu(vcpu) \ vcpu_get_flag(vcpu, ON_UNSUPPORTED_CPU) #define vcpu_set_on_unsupported_cpu(vcpu) \ vcpu_set_flag(vcpu, ON_UNSUPPORTED_CPU) #define vcpu_clear_on_unsupported_cpu(vcpu) \ vcpu_clear_flag(vcpu, ON_UNSUPPORTED_CPU) #define vcpu_gp_regs(v) (&(v)->arch.ctxt.regs) /* * Only use __vcpu_sys_reg/ctxt_sys_reg if you know you want the * memory backed version of a register, and not the one most recently * accessed by a running VCPU. For example, for userspace access or * for system registers that are never context switched, but only * emulated. * * Don't bother with VNCR-based accesses in the nVHE code, it has no * business dealing with NV. */ static inline u64 *___ctxt_sys_reg(const struct kvm_cpu_context *ctxt, int r) { #if !defined (__KVM_NVHE_HYPERVISOR__) if (unlikely(cpus_have_final_cap(ARM64_HAS_NESTED_VIRT) && r >= __VNCR_START__ && ctxt->vncr_array)) return &ctxt->vncr_array[r - __VNCR_START__]; #endif return (u64 *)&ctxt->sys_regs[r]; } #define __ctxt_sys_reg(c,r) \ ({ \ BUILD_BUG_ON(__builtin_constant_p(r) && \ (r) >= NR_SYS_REGS); \ ___ctxt_sys_reg(c, r); \ }) #define ctxt_sys_reg(c,r) (*__ctxt_sys_reg(c,r)) u64 kvm_vcpu_apply_reg_masks(const struct kvm_vcpu *, enum vcpu_sysreg, u64); #define __vcpu_sys_reg(v,r) \ (*({ \ const struct kvm_cpu_context *ctxt = &(v)->arch.ctxt; \ u64 *__r = __ctxt_sys_reg(ctxt, (r)); \ if (vcpu_has_nv((v)) && (r) >= __SANITISED_REG_START__) \ *__r = kvm_vcpu_apply_reg_masks((v), (r), *__r);\ __r; \ })) u64 vcpu_read_sys_reg(const struct kvm_vcpu *vcpu, int reg); void vcpu_write_sys_reg(struct kvm_vcpu *vcpu, u64 val, int reg); static inline bool __vcpu_read_sys_reg_from_cpu(int reg, u64 *val) { /* * *** VHE ONLY *** * * System registers listed in the switch are not saved on every * exit from the guest but are only saved on vcpu_put. * * Note that MPIDR_EL1 for the guest is set by KVM via VMPIDR_EL2 but * should never be listed below, because the guest cannot modify its * own MPIDR_EL1 and MPIDR_EL1 is accessed for VCPU A from VCPU B's * thread when emulating cross-VCPU communication. */ if (!has_vhe()) return false; switch (reg) { case SCTLR_EL1: *val = read_sysreg_s(SYS_SCTLR_EL12); break; case CPACR_EL1: *val = read_sysreg_s(SYS_CPACR_EL12); break; case TTBR0_EL1: *val = read_sysreg_s(SYS_TTBR0_EL12); break; case TTBR1_EL1: *val = read_sysreg_s(SYS_TTBR1_EL12); break; case TCR_EL1: *val = read_sysreg_s(SYS_TCR_EL12); break; case TCR2_EL1: *val = read_sysreg_s(SYS_TCR2_EL12); break; case PIR_EL1: *val = read_sysreg_s(SYS_PIR_EL12); break; case PIRE0_EL1: *val = read_sysreg_s(SYS_PIRE0_EL12); break; case POR_EL1: *val = read_sysreg_s(SYS_POR_EL12); break; case ESR_EL1: *val = read_sysreg_s(SYS_ESR_EL12); break; case AFSR0_EL1: *val = read_sysreg_s(SYS_AFSR0_EL12); break; case AFSR1_EL1: *val = read_sysreg_s(SYS_AFSR1_EL12); break; case FAR_EL1: *val = read_sysreg_s(SYS_FAR_EL12); break; case MAIR_EL1: *val = read_sysreg_s(SYS_MAIR_EL12); break; case VBAR_EL1: *val = read_sysreg_s(SYS_VBAR_EL12); break; case CONTEXTIDR_EL1: *val = read_sysreg_s(SYS_CONTEXTIDR_EL12);break; case TPIDR_EL0: *val = read_sysreg_s(SYS_TPIDR_EL0); break; case TPIDRRO_EL0: *val = read_sysreg_s(SYS_TPIDRRO_EL0); break; case TPIDR_EL1: *val = read_sysreg_s(SYS_TPIDR_EL1); break; case AMAIR_EL1: *val = read_sysreg_s(SYS_AMAIR_EL12); break; case CNTKCTL_EL1: *val = read_sysreg_s(SYS_CNTKCTL_EL12); break; case ELR_EL1: *val = read_sysreg_s(SYS_ELR_EL12); break; case SPSR_EL1: *val = read_sysreg_s(SYS_SPSR_EL12); break; case PAR_EL1: *val = read_sysreg_par(); break; case DACR32_EL2: *val = read_sysreg_s(SYS_DACR32_EL2); break; case IFSR32_EL2: *val = read_sysreg_s(SYS_IFSR32_EL2); break; case DBGVCR32_EL2: *val = read_sysreg_s(SYS_DBGVCR32_EL2); break; case ZCR_EL1: *val = read_sysreg_s(SYS_ZCR_EL12); break; default: return false; } return true; } static inline bool __vcpu_write_sys_reg_to_cpu(u64 val, int reg) { /* * *** VHE ONLY *** * * System registers listed in the switch are not restored on every * entry to the guest but are only restored on vcpu_load. * * Note that MPIDR_EL1 for the guest is set by KVM via VMPIDR_EL2 but * should never be listed below, because the MPIDR should only be set * once, before running the VCPU, and never changed later. */ if (!has_vhe()) return false; switch (reg) { case SCTLR_EL1: write_sysreg_s(val, SYS_SCTLR_EL12); break; case CPACR_EL1: write_sysreg_s(val, SYS_CPACR_EL12); break; case TTBR0_EL1: write_sysreg_s(val, SYS_TTBR0_EL12); break; case TTBR1_EL1: write_sysreg_s(val, SYS_TTBR1_EL12); break; case TCR_EL1: write_sysreg_s(val, SYS_TCR_EL12); break; case TCR2_EL1: write_sysreg_s(val, SYS_TCR2_EL12); break; case PIR_EL1: write_sysreg_s(val, SYS_PIR_EL12); break; case PIRE0_EL1: write_sysreg_s(val, SYS_PIRE0_EL12); break; case POR_EL1: write_sysreg_s(val, SYS_POR_EL12); break; case ESR_EL1: write_sysreg_s(val, SYS_ESR_EL12); break; case AFSR0_EL1: write_sysreg_s(val, SYS_AFSR0_EL12); break; case AFSR1_EL1: write_sysreg_s(val, SYS_AFSR1_EL12); break; case FAR_EL1: write_sysreg_s(val, SYS_FAR_EL12); break; case MAIR_EL1: write_sysreg_s(val, SYS_MAIR_EL12); break; case VBAR_EL1: write_sysreg_s(val, SYS_VBAR_EL12); break; case CONTEXTIDR_EL1: write_sysreg_s(val, SYS_CONTEXTIDR_EL12);break; case TPIDR_EL0: write_sysreg_s(val, SYS_TPIDR_EL0); break; case TPIDRRO_EL0: write_sysreg_s(val, SYS_TPIDRRO_EL0); break; case TPIDR_EL1: write_sysreg_s(val, SYS_TPIDR_EL1); break; case AMAIR_EL1: write_sysreg_s(val, SYS_AMAIR_EL12); break; case CNTKCTL_EL1: write_sysreg_s(val, SYS_CNTKCTL_EL12); break; case ELR_EL1: write_sysreg_s(val, SYS_ELR_EL12); break; case SPSR_EL1: write_sysreg_s(val, SYS_SPSR_EL12); break; case PAR_EL1: write_sysreg_s(val, SYS_PAR_EL1); break; case DACR32_EL2: write_sysreg_s(val, SYS_DACR32_EL2); break; case IFSR32_EL2: write_sysreg_s(val, SYS_IFSR32_EL2); break; case DBGVCR32_EL2: write_sysreg_s(val, SYS_DBGVCR32_EL2); break; case ZCR_EL1: write_sysreg_s(val, SYS_ZCR_EL12); break; default: return false; } return true; } struct kvm_vm_stat { struct kvm_vm_stat_generic generic; }; struct kvm_vcpu_stat { struct kvm_vcpu_stat_generic generic; u64 hvc_exit_stat; u64 wfe_exit_stat; u64 wfi_exit_stat; u64 mmio_exit_user; u64 mmio_exit_kernel; u64 signal_exits; u64 exits; }; unsigned long kvm_arm_num_regs(struct kvm_vcpu *vcpu); int kvm_arm_copy_reg_indices(struct kvm_vcpu *vcpu, u64 __user *indices); int kvm_arm_get_reg(struct kvm_vcpu *vcpu, const struct kvm_one_reg *reg); int kvm_arm_set_reg(struct kvm_vcpu *vcpu, const struct kvm_one_reg *reg); unsigned long kvm_arm_num_sys_reg_descs(struct kvm_vcpu *vcpu); int kvm_arm_copy_sys_reg_indices(struct kvm_vcpu *vcpu, u64 __user *uindices); int __kvm_arm_vcpu_get_events(struct kvm_vcpu *vcpu, struct kvm_vcpu_events *events); int __kvm_arm_vcpu_set_events(struct kvm_vcpu *vcpu, struct kvm_vcpu_events *events); void kvm_arm_halt_guest(struct kvm *kvm); void kvm_arm_resume_guest(struct kvm *kvm); #define vcpu_has_run_once(vcpu) (!!READ_ONCE((vcpu)->pid)) #ifndef __KVM_NVHE_HYPERVISOR__ #define kvm_call_hyp_nvhe(f, ...) \ ({ \ struct arm_smccc_res res; \ \ arm_smccc_1_1_hvc(KVM_HOST_SMCCC_FUNC(f), \ ##__VA_ARGS__, &res); \ WARN_ON(res.a0 != SMCCC_RET_SUCCESS); \ \ res.a1; \ }) /* * The couple of isb() below are there to guarantee the same behaviour * on VHE as on !VHE, where the eret to EL1 acts as a context * synchronization event. */ #define kvm_call_hyp(f, ...) \ do { \ if (has_vhe()) { \ f(__VA_ARGS__); \ isb(); \ } else { \ kvm_call_hyp_nvhe(f, ##__VA_ARGS__); \ } \ } while(0) #define kvm_call_hyp_ret(f, ...) \ ({ \ typeof(f(__VA_ARGS__)) ret; \ \ if (has_vhe()) { \ ret = f(__VA_ARGS__); \ isb(); \ } else { \ ret = kvm_call_hyp_nvhe(f, ##__VA_ARGS__); \ } \ \ ret; \ }) #else /* __KVM_NVHE_HYPERVISOR__ */ #define kvm_call_hyp(f, ...) f(__VA_ARGS__) #define kvm_call_hyp_ret(f, ...) f(__VA_ARGS__) #define kvm_call_hyp_nvhe(f, ...) f(__VA_ARGS__) #endif /* __KVM_NVHE_HYPERVISOR__ */ int handle_exit(struct kvm_vcpu *vcpu, int exception_index); void handle_exit_early(struct kvm_vcpu *vcpu, int exception_index); int kvm_handle_cp14_load_store(struct kvm_vcpu *vcpu); int kvm_handle_cp14_32(struct kvm_vcpu *vcpu); int kvm_handle_cp14_64(struct kvm_vcpu *vcpu); int kvm_handle_cp15_32(struct kvm_vcpu *vcpu); int kvm_handle_cp15_64(struct kvm_vcpu *vcpu); int kvm_handle_sys_reg(struct kvm_vcpu *vcpu); int kvm_handle_cp10_id(struct kvm_vcpu *vcpu); void kvm_sys_regs_create_debugfs(struct kvm *kvm); void kvm_reset_sys_regs(struct kvm_vcpu *vcpu); int __init kvm_sys_reg_table_init(void); struct sys_reg_desc; int __init populate_sysreg_config(const struct sys_reg_desc *sr, unsigned int idx); int __init populate_nv_trap_config(void); bool lock_all_vcpus(struct kvm *kvm); void unlock_all_vcpus(struct kvm *kvm); void kvm_calculate_traps(struct kvm_vcpu *vcpu); /* MMIO helpers */ void kvm_mmio_write_buf(void *buf, unsigned int len, unsigned long data); unsigned long kvm_mmio_read_buf(const void *buf, unsigned int len); int kvm_handle_mmio_return(struct kvm_vcpu *vcpu); int io_mem_abort(struct kvm_vcpu *vcpu, phys_addr_t fault_ipa); /* * Returns true if a Performance Monitoring Interrupt (PMI), a.k.a. perf event, * arrived in guest context. For arm64, any event that arrives while a vCPU is * loaded is considered to be "in guest". */ static inline bool kvm_arch_pmi_in_guest(struct kvm_vcpu *vcpu) { return IS_ENABLED(CONFIG_GUEST_PERF_EVENTS) && !!vcpu; } long kvm_hypercall_pv_features(struct kvm_vcpu *vcpu); gpa_t kvm_init_stolen_time(struct kvm_vcpu *vcpu); void kvm_update_stolen_time(struct kvm_vcpu *vcpu); bool kvm_arm_pvtime_supported(void); int kvm_arm_pvtime_set_attr(struct kvm_vcpu *vcpu, struct kvm_device_attr *attr); int kvm_arm_pvtime_get_attr(struct kvm_vcpu *vcpu, struct kvm_device_attr *attr); int kvm_arm_pvtime_has_attr(struct kvm_vcpu *vcpu, struct kvm_device_attr *attr); extern unsigned int __ro_after_init kvm_arm_vmid_bits; int __init kvm_arm_vmid_alloc_init(void); void __init kvm_arm_vmid_alloc_free(void); bool kvm_arm_vmid_update(struct kvm_vmid *kvm_vmid); void kvm_arm_vmid_clear_active(void); static inline void kvm_arm_pvtime_vcpu_init(struct kvm_vcpu_arch *vcpu_arch) { vcpu_arch->steal.base = INVALID_GPA; } static inline bool kvm_arm_is_pvtime_enabled(struct kvm_vcpu_arch *vcpu_arch) { return (vcpu_arch->steal.base != INVALID_GPA); } void kvm_set_sei_esr(struct kvm_vcpu *vcpu, u64 syndrome); struct kvm_vcpu *kvm_mpidr_to_vcpu(struct kvm *kvm, unsigned long mpidr); DECLARE_KVM_HYP_PER_CPU(struct kvm_host_data, kvm_host_data); /* * How we access per-CPU host data depends on the where we access it from, * and the mode we're in: * * - VHE and nVHE hypervisor bits use their locally defined instance * * - the rest of the kernel use either the VHE or nVHE one, depending on * the mode we're running in. * * Unless we're in protected mode, fully deprivileged, and the nVHE * per-CPU stuff is exclusively accessible to the protected EL2 code. * In this case, the EL1 code uses the *VHE* data as its private state * (which makes sense in a way as there shouldn't be any shared state * between the host and the hypervisor). * * Yes, this is all totally trivial. Shoot me now. */ #if defined(__KVM_NVHE_HYPERVISOR__) || defined(__KVM_VHE_HYPERVISOR__) #define host_data_ptr(f) (&this_cpu_ptr(&kvm_host_data)->f) #else #define host_data_ptr(f) \ (static_branch_unlikely(&kvm_protected_mode_initialized) ? \ &this_cpu_ptr(&kvm_host_data)->f : \ &this_cpu_ptr_hyp_sym(kvm_host_data)->f) #endif #define host_data_test_flag(flag) \ (test_bit(KVM_HOST_DATA_FLAG_##flag, host_data_ptr(flags))) #define host_data_set_flag(flag) \ set_bit(KVM_HOST_DATA_FLAG_##flag, host_data_ptr(flags)) #define host_data_clear_flag(flag) \ clear_bit(KVM_HOST_DATA_FLAG_##flag, host_data_ptr(flags)) /* Check whether the FP regs are owned by the guest */ static inline bool guest_owns_fp_regs(void) { return *host_data_ptr(fp_owner) == FP_STATE_GUEST_OWNED; } /* Check whether the FP regs are owned by the host */ static inline bool host_owns_fp_regs(void) { return *host_data_ptr(fp_owner) == FP_STATE_HOST_OWNED; } static inline void kvm_init_host_cpu_context(struct kvm_cpu_context *cpu_ctxt) { /* The host's MPIDR is immutable, so let's set it up at boot time */ ctxt_sys_reg(cpu_ctxt, MPIDR_EL1) = read_cpuid_mpidr(); } static inline bool kvm_system_needs_idmapped_vectors(void) { return cpus_have_final_cap(ARM64_SPECTRE_V3A); } static inline void kvm_arch_sync_events(struct kvm *kvm) {} void kvm_init_host_debug_data(void); void kvm_vcpu_load_debug(struct kvm_vcpu *vcpu); void kvm_vcpu_put_debug(struct kvm_vcpu *vcpu); void kvm_debug_set_guest_ownership(struct kvm_vcpu *vcpu); void kvm_debug_handle_oslar(struct kvm_vcpu *vcpu, u64 val); #define kvm_vcpu_os_lock_enabled(vcpu) \ (!!(__vcpu_sys_reg(vcpu, OSLSR_EL1) & OSLSR_EL1_OSLK)) #define kvm_debug_regs_in_use(vcpu) \ ((vcpu)->arch.debug_owner != VCPU_DEBUG_FREE) #define kvm_host_owns_debug_regs(vcpu) \ ((vcpu)->arch.debug_owner == VCPU_DEBUG_HOST_OWNED) #define kvm_guest_owns_debug_regs(vcpu) \ ((vcpu)->arch.debug_owner == VCPU_DEBUG_GUEST_OWNED) int kvm_arm_vcpu_arch_set_attr(struct kvm_vcpu *vcpu, struct kvm_device_attr *attr); int kvm_arm_vcpu_arch_get_attr(struct kvm_vcpu *vcpu, struct kvm_device_attr *attr); int kvm_arm_vcpu_arch_has_attr(struct kvm_vcpu *vcpu, struct kvm_device_attr *attr); int kvm_vm_ioctl_mte_copy_tags(struct kvm *kvm, struct kvm_arm_copy_mte_tags *copy_tags); int kvm_vm_ioctl_set_counter_offset(struct kvm *kvm, struct kvm_arm_counter_offset *offset); int kvm_vm_ioctl_get_reg_writable_masks(struct kvm *kvm, struct reg_mask_range *range); /* Guest/host FPSIMD coordination helpers */ int kvm_arch_vcpu_run_map_fp(struct kvm_vcpu *vcpu); void kvm_arch_vcpu_load_fp(struct kvm_vcpu *vcpu); void kvm_arch_vcpu_ctxflush_fp(struct kvm_vcpu *vcpu); void kvm_arch_vcpu_ctxsync_fp(struct kvm_vcpu *vcpu); void kvm_arch_vcpu_put_fp(struct kvm_vcpu *vcpu); static inline bool kvm_pmu_counter_deferred(struct perf_event_attr *attr) { return (!has_vhe() && attr->exclude_host); } #ifdef CONFIG_KVM void kvm_set_pmu_events(u64 set, struct perf_event_attr *attr); void kvm_clr_pmu_events(u64 clr); bool kvm_set_pmuserenr(u64 val); #else static inline void kvm_set_pmu_events(u64 set, struct perf_event_attr *attr) {} static inline void kvm_clr_pmu_events(u64 clr) {} static inline bool kvm_set_pmuserenr(u64 val) { return false; } #endif void kvm_vcpu_load_vhe(struct kvm_vcpu *vcpu); void kvm_vcpu_put_vhe(struct kvm_vcpu *vcpu); int __init kvm_set_ipa_limit(void); u32 kvm_get_pa_bits(struct kvm *kvm); #define __KVM_HAVE_ARCH_VM_ALLOC struct kvm *kvm_arch_alloc_vm(void); #define __KVM_HAVE_ARCH_FLUSH_REMOTE_TLBS #define __KVM_HAVE_ARCH_FLUSH_REMOTE_TLBS_RANGE #define kvm_vm_is_protected(kvm) (is_protected_kvm_enabled() && (kvm)->arch.pkvm.enabled) #define vcpu_is_protected(vcpu) kvm_vm_is_protected((vcpu)->kvm) int kvm_arm_vcpu_finalize(struct kvm_vcpu *vcpu, int feature); bool kvm_arm_vcpu_is_finalized(struct kvm_vcpu *vcpu); #define kvm_arm_vcpu_sve_finalized(vcpu) vcpu_get_flag(vcpu, VCPU_SVE_FINALIZED) #define kvm_has_mte(kvm) \ (system_supports_mte() && \ test_bit(KVM_ARCH_FLAG_MTE_ENABLED, &(kvm)->arch.flags)) #define kvm_supports_32bit_el0() \ (system_supports_32bit_el0() && \ !static_branch_unlikely(&arm64_mismatched_32bit_el0)) #define kvm_vm_has_ran_once(kvm) \ (test_bit(KVM_ARCH_FLAG_HAS_RAN_ONCE, &(kvm)->arch.flags)) static inline bool __vcpu_has_feature(const struct kvm_arch *ka, int feature) { return test_bit(feature, ka->vcpu_features); } #define kvm_vcpu_has_feature(k, f) __vcpu_has_feature(&(k)->arch, (f)) #define vcpu_has_feature(v, f) __vcpu_has_feature(&(v)->kvm->arch, (f)) #define kvm_vcpu_initialized(v) vcpu_get_flag(vcpu, VCPU_INITIALIZED) int kvm_trng_call(struct kvm_vcpu *vcpu); #ifdef CONFIG_KVM extern phys_addr_t hyp_mem_base; extern phys_addr_t hyp_mem_size; void __init kvm_hyp_reserve(void); #else static inline void kvm_hyp_reserve(void) { } #endif void kvm_arm_vcpu_power_off(struct kvm_vcpu *vcpu); bool kvm_arm_vcpu_stopped(struct kvm_vcpu *vcpu); static inline u64 *__vm_id_reg(struct kvm_arch *ka, u32 reg) { switch (reg) { case sys_reg(3, 0, 0, 1, 0) ... sys_reg(3, 0, 0, 7, 7): return &ka->id_regs[IDREG_IDX(reg)]; case SYS_CTR_EL0: return &ka->ctr_el0; default: WARN_ON_ONCE(1); return NULL; } } #define kvm_read_vm_id_reg(kvm, reg) \ ({ u64 __val = *__vm_id_reg(&(kvm)->arch, reg); __val; }) void kvm_set_vm_id_reg(struct kvm *kvm, u32 reg, u64 val); #define __expand_field_sign_unsigned(id, fld, val) \ ((u64)SYS_FIELD_VALUE(id, fld, val)) #define __expand_field_sign_signed(id, fld, val) \ ({ \ u64 __val = SYS_FIELD_VALUE(id, fld, val); \ sign_extend64(__val, id##_##fld##_WIDTH - 1); \ }) #define get_idreg_field_unsigned(kvm, id, fld) \ ({ \ u64 __val = kvm_read_vm_id_reg((kvm), SYS_##id); \ FIELD_GET(id##_##fld##_MASK, __val); \ }) #define get_idreg_field_signed(kvm, id, fld) \ ({ \ u64 __val = get_idreg_field_unsigned(kvm, id, fld); \ sign_extend64(__val, id##_##fld##_WIDTH - 1); \ }) #define get_idreg_field_enum(kvm, id, fld) \ get_idreg_field_unsigned(kvm, id, fld) #define kvm_cmp_feat_signed(kvm, id, fld, op, limit) \ (get_idreg_field_signed((kvm), id, fld) op __expand_field_sign_signed(id, fld, limit)) #define kvm_cmp_feat_unsigned(kvm, id, fld, op, limit) \ (get_idreg_field_unsigned((kvm), id, fld) op __expand_field_sign_unsigned(id, fld, limit)) #define kvm_cmp_feat(kvm, id, fld, op, limit) \ (id##_##fld##_SIGNED ? \ kvm_cmp_feat_signed(kvm, id, fld, op, limit) : \ kvm_cmp_feat_unsigned(kvm, id, fld, op, limit)) #define kvm_has_feat(kvm, id, fld, limit) \ kvm_cmp_feat(kvm, id, fld, >=, limit) #define kvm_has_feat_enum(kvm, id, fld, val) \ kvm_cmp_feat_unsigned(kvm, id, fld, ==, val) #define kvm_has_feat_range(kvm, id, fld, min, max) \ (kvm_cmp_feat(kvm, id, fld, >=, min) && \ kvm_cmp_feat(kvm, id, fld, <=, max)) /* Check for a given level of PAuth support */ #define kvm_has_pauth(k, l) \ ({ \ bool pa, pi, pa3; \ \ pa = kvm_has_feat((k), ID_AA64ISAR1_EL1, APA, l); \ pa &= kvm_has_feat((k), ID_AA64ISAR1_EL1, GPA, IMP); \ pi = kvm_has_feat((k), ID_AA64ISAR1_EL1, API, l); \ pi &= kvm_has_feat((k), ID_AA64ISAR1_EL1, GPI, IMP); \ pa3 = kvm_has_feat((k), ID_AA64ISAR2_EL1, APA3, l); \ pa3 &= kvm_has_feat((k), ID_AA64ISAR2_EL1, GPA3, IMP); \ \ (pa + pi + pa3) == 1; \ }) #define kvm_has_fpmr(k) \ (system_supports_fpmr() && \ kvm_has_feat((k), ID_AA64PFR2_EL1, FPMR, IMP)) #define kvm_has_tcr2(k) \ (kvm_has_feat((k), ID_AA64MMFR3_EL1, TCRX, IMP)) #define kvm_has_s1pie(k) \ (kvm_has_feat((k), ID_AA64MMFR3_EL1, S1PIE, IMP)) #define kvm_has_s1poe(k) \ (kvm_has_feat((k), ID_AA64MMFR3_EL1, S1POE, IMP)) #endif /* __ARM64_KVM_HOST_H__ */ |
| 4 4 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 | // SPDX-License-Identifier: GPL-2.0-only /* * fs/crypto/hooks.c * * Encryption hooks for higher-level filesystem operations. */ #include "fscrypt_private.h" /** * fscrypt_file_open() - prepare to open a possibly-encrypted regular file * @inode: the inode being opened * @filp: the struct file being set up * * Currently, an encrypted regular file can only be opened if its encryption key * is available; access to the raw encrypted contents is not supported. * Therefore, we first set up the inode's encryption key (if not already done) * and return an error if it's unavailable. * * We also verify that if the parent directory (from the path via which the file * is being opened) is encrypted, then the inode being opened uses the same * encryption policy. This is needed as part of the enforcement that all files * in an encrypted directory tree use the same encryption policy, as a * protection against certain types of offline attacks. Note that this check is * needed even when opening an *unencrypted* file, since it's forbidden to have * an unencrypted file in an encrypted directory. * * Return: 0 on success, -ENOKEY if the key is missing, or another -errno code */ int fscrypt_file_open(struct inode *inode, struct file *filp) { int err; struct dentry *dentry, *dentry_parent; struct inode *inode_parent; err = fscrypt_require_key(inode); if (err) return err; dentry = file_dentry(filp); /* * Getting a reference to the parent dentry is needed for the actual * encryption policy comparison, but it's expensive on multi-core * systems. Since this function runs on unencrypted files too, start * with a lightweight RCU-mode check for the parent directory being * unencrypted (in which case it's fine for the child to be either * unencrypted, or encrypted with any policy). Only continue on to the * full policy check if the parent directory is actually encrypted. */ rcu_read_lock(); dentry_parent = READ_ONCE(dentry->d_parent); inode_parent = d_inode_rcu(dentry_parent); if (inode_parent != NULL && !IS_ENCRYPTED(inode_parent)) { rcu_read_unlock(); return 0; } rcu_read_unlock(); dentry_parent = dget_parent(dentry); if (!fscrypt_has_permitted_context(d_inode(dentry_parent), inode)) { fscrypt_warn(inode, "Inconsistent encryption context (parent directory: %lu)", d_inode(dentry_parent)->i_ino); err = -EPERM; } dput(dentry_parent); return err; } EXPORT_SYMBOL_GPL(fscrypt_file_open); int __fscrypt_prepare_link(struct inode *inode, struct inode *dir, struct dentry *dentry) { if (fscrypt_is_nokey_name(dentry)) return -ENOKEY; /* * We don't need to separately check that the directory inode's key is * available, as it's implied by the dentry not being a no-key name. */ if (!fscrypt_has_permitted_context(dir, inode)) return -EXDEV; return 0; } EXPORT_SYMBOL_GPL(__fscrypt_prepare_link); int __fscrypt_prepare_rename(struct inode *old_dir, struct dentry *old_dentry, struct inode *new_dir, struct dentry *new_dentry, unsigned int flags) { if (fscrypt_is_nokey_name(old_dentry) || fscrypt_is_nokey_name(new_dentry)) return -ENOKEY; /* * We don't need to separately check that the directory inodes' keys are * available, as it's implied by the dentries not being no-key names. */ if (old_dir != new_dir) { if (IS_ENCRYPTED(new_dir) && !fscrypt_has_permitted_context(new_dir, d_inode(old_dentry))) return -EXDEV; if ((flags & RENAME_EXCHANGE) && IS_ENCRYPTED(old_dir) && !fscrypt_has_permitted_context(old_dir, d_inode(new_dentry))) return -EXDEV; } return 0; } EXPORT_SYMBOL_GPL(__fscrypt_prepare_rename); int __fscrypt_prepare_lookup(struct inode *dir, struct dentry *dentry, struct fscrypt_name *fname) { int err = fscrypt_setup_filename(dir, &dentry->d_name, 1, fname); if (err && err != -ENOENT) return err; fscrypt_prepare_dentry(dentry, fname->is_nokey_name); return err; } EXPORT_SYMBOL_GPL(__fscrypt_prepare_lookup); /** * fscrypt_prepare_lookup_partial() - prepare lookup without filename setup * @dir: the encrypted directory being searched * @dentry: the dentry being looked up in @dir * * This function should be used by the ->lookup and ->atomic_open methods of * filesystems that handle filename encryption and no-key name encoding * themselves and thus can't use fscrypt_prepare_lookup(). Like * fscrypt_prepare_lookup(), this will try to set up the directory's encryption * key and will set DCACHE_NOKEY_NAME on the dentry if the key is unavailable. * However, this function doesn't set up a struct fscrypt_name for the filename. * * Return: 0 on success; -errno on error. Note that the encryption key being * unavailable is not considered an error. It is also not an error if * the encryption policy is unsupported by this kernel; that is treated * like the key being unavailable, so that files can still be deleted. */ int fscrypt_prepare_lookup_partial(struct inode *dir, struct dentry *dentry) { int err = fscrypt_get_encryption_info(dir, true); bool is_nokey_name = (!err && !fscrypt_has_encryption_key(dir)); fscrypt_prepare_dentry(dentry, is_nokey_name); return err; } EXPORT_SYMBOL_GPL(fscrypt_prepare_lookup_partial); int __fscrypt_prepare_readdir(struct inode *dir) { return fscrypt_get_encryption_info(dir, true); } EXPORT_SYMBOL_GPL(__fscrypt_prepare_readdir); int __fscrypt_prepare_setattr(struct dentry *dentry, struct iattr *attr) { if (attr->ia_valid & ATTR_SIZE) return fscrypt_require_key(d_inode(dentry)); return 0; } EXPORT_SYMBOL_GPL(__fscrypt_prepare_setattr); /** * fscrypt_prepare_setflags() - prepare to change flags with FS_IOC_SETFLAGS * @inode: the inode on which flags are being changed * @oldflags: the old flags * @flags: the new flags * * The caller should be holding i_rwsem for write. * * Return: 0 on success; -errno if the flags change isn't allowed or if * another error occurs. */ int fscrypt_prepare_setflags(struct inode *inode, unsigned int oldflags, unsigned int flags) { struct fscrypt_inode_info *ci; struct fscrypt_master_key *mk; int err; /* * When the CASEFOLD flag is set on an encrypted directory, we must * derive the secret key needed for the dirhash. This is only possible * if the directory uses a v2 encryption policy. */ if (IS_ENCRYPTED(inode) && (flags & ~oldflags & FS_CASEFOLD_FL)) { err = fscrypt_require_key(inode); if (err) return err; ci = inode->i_crypt_info; if (ci->ci_policy.version != FSCRYPT_POLICY_V2) return -EINVAL; mk = ci->ci_master_key; down_read(&mk->mk_sem); if (mk->mk_present) err = fscrypt_derive_dirhash_key(ci, mk); else err = -ENOKEY; up_read(&mk->mk_sem); return err; } return 0; } /** * fscrypt_prepare_symlink() - prepare to create a possibly-encrypted symlink * @dir: directory in which the symlink is being created * @target: plaintext symlink target * @len: length of @target excluding null terminator * @max_len: space the filesystem has available to store the symlink target * @disk_link: (out) the on-disk symlink target being prepared * * This function computes the size the symlink target will require on-disk, * stores it in @disk_link->len, and validates it against @max_len. An * encrypted symlink may be longer than the original. * * Additionally, @disk_link->name is set to @target if the symlink will be * unencrypted, but left NULL if the symlink will be encrypted. For encrypted * symlinks, the filesystem must call fscrypt_encrypt_symlink() to create the * on-disk target later. (The reason for the two-step process is that some * filesystems need to know the size of the symlink target before creating the * inode, e.g. to determine whether it will be a "fast" or "slow" symlink.) * * Return: 0 on success, -ENAMETOOLONG if the symlink target is too long, * -ENOKEY if the encryption key is missing, or another -errno code if a problem * occurred while setting up the encryption key. */ int fscrypt_prepare_symlink(struct inode *dir, const char *target, unsigned int len, unsigned int max_len, struct fscrypt_str *disk_link) { const union fscrypt_policy *policy; /* * To calculate the size of the encrypted symlink target we need to know * the amount of NUL padding, which is determined by the flags set in * the encryption policy which will be inherited from the directory. */ policy = fscrypt_policy_to_inherit(dir); if (policy == NULL) { /* Not encrypted */ disk_link->name = (unsigned char *)target; disk_link->len = len + 1; if (disk_link->len > max_len) return -ENAMETOOLONG; return 0; } if (IS_ERR(policy)) return PTR_ERR(policy); /* * Calculate the size of the encrypted symlink and verify it won't * exceed max_len. Note that for historical reasons, encrypted symlink * targets are prefixed with the ciphertext length, despite this * actually being redundant with i_size. This decreases by 2 bytes the * longest symlink target we can accept. * * We could recover 1 byte by not counting a null terminator, but * counting it (even though it is meaningless for ciphertext) is simpler * for now since filesystems will assume it is there and subtract it. */ if (!__fscrypt_fname_encrypted_size(policy, len, max_len - sizeof(struct fscrypt_symlink_data) - 1, &disk_link->len)) return -ENAMETOOLONG; disk_link->len += sizeof(struct fscrypt_symlink_data) + 1; disk_link->name = NULL; return 0; } EXPORT_SYMBOL_GPL(fscrypt_prepare_symlink); int __fscrypt_encrypt_symlink(struct inode *inode, const char *target, unsigned int len, struct fscrypt_str *disk_link) { int err; struct qstr iname = QSTR_INIT(target, len); struct fscrypt_symlink_data *sd; unsigned int ciphertext_len; /* * fscrypt_prepare_new_inode() should have already set up the new * symlink inode's encryption key. We don't wait until now to do it, * since we may be in a filesystem transaction now. */ if (WARN_ON_ONCE(!fscrypt_has_encryption_key(inode))) return -ENOKEY; if (disk_link->name) { /* filesystem-provided buffer */ sd = (struct fscrypt_symlink_data *)disk_link->name; } else { sd = kmalloc(disk_link->len, GFP_NOFS); if (!sd) return -ENOMEM; } ciphertext_len = disk_link->len - sizeof(*sd) - 1; sd->len = cpu_to_le16(ciphertext_len); err = fscrypt_fname_encrypt(inode, &iname, sd->encrypted_path, ciphertext_len); if (err) goto err_free_sd; /* * Null-terminating the ciphertext doesn't make sense, but we still * count the null terminator in the length, so we might as well * initialize it just in case the filesystem writes it out. */ sd->encrypted_path[ciphertext_len] = '\0'; /* Cache the plaintext symlink target for later use by get_link() */ err = -ENOMEM; inode->i_link = kmemdup(target, len + 1, GFP_NOFS); if (!inode->i_link) goto err_free_sd; if (!disk_link->name) disk_link->name = (unsigned char *)sd; return 0; err_free_sd: if (!disk_link->name) kfree(sd); return err; } EXPORT_SYMBOL_GPL(__fscrypt_encrypt_symlink); /** * fscrypt_get_symlink() - get the target of an encrypted symlink * @inode: the symlink inode * @caddr: the on-disk contents of the symlink * @max_size: size of @caddr buffer * @done: if successful, will be set up to free the returned target if needed * * If the symlink's encryption key is available, we decrypt its target. * Otherwise, we encode its target for presentation. * * This may sleep, so the filesystem must have dropped out of RCU mode already. * * Return: the presentable symlink target or an ERR_PTR() */ const char *fscrypt_get_symlink(struct inode *inode, const void *caddr, unsigned int max_size, struct delayed_call *done) { const struct fscrypt_symlink_data *sd; struct fscrypt_str cstr, pstr; bool has_key; int err; /* This is for encrypted symlinks only */ if (WARN_ON_ONCE(!IS_ENCRYPTED(inode))) return ERR_PTR(-EINVAL); /* If the decrypted target is already cached, just return it. */ pstr.name = READ_ONCE(inode->i_link); if (pstr.name) return pstr.name; /* * Try to set up the symlink's encryption key, but we can continue * regardless of whether the key is available or not. */ err = fscrypt_get_encryption_info(inode, false); if (err) return ERR_PTR(err); has_key = fscrypt_has_encryption_key(inode); /* * For historical reasons, encrypted symlink targets are prefixed with * the ciphertext length, even though this is redundant with i_size. */ if (max_size < sizeof(*sd) + 1) return ERR_PTR(-EUCLEAN); sd = caddr; cstr.name = (unsigned char *)sd->encrypted_path; cstr.len = le16_to_cpu(sd->len); if (cstr.len == 0) return ERR_PTR(-EUCLEAN); if (cstr.len + sizeof(*sd) > max_size) return ERR_PTR(-EUCLEAN); err = fscrypt_fname_alloc_buffer(cstr.len, &pstr); if (err) return ERR_PTR(err); err = fscrypt_fname_disk_to_usr(inode, 0, 0, &cstr, &pstr); if (err) goto err_kfree; err = -EUCLEAN; if (pstr.name[0] == '\0') goto err_kfree; pstr.name[pstr.len] = '\0'; /* * Cache decrypted symlink targets in i_link for later use. Don't cache * symlink targets encoded without the key, since those become outdated * once the key is added. This pairs with the READ_ONCE() above and in * the VFS path lookup code. */ if (!has_key || cmpxchg_release(&inode->i_link, NULL, pstr.name) != NULL) set_delayed_call(done, kfree_link, pstr.name); return pstr.name; err_kfree: kfree(pstr.name); return ERR_PTR(err); } EXPORT_SYMBOL_GPL(fscrypt_get_symlink); /** * fscrypt_symlink_getattr() - set the correct st_size for encrypted symlinks * @path: the path for the encrypted symlink being queried * @stat: the struct being filled with the symlink's attributes * * Override st_size of encrypted symlinks to be the length of the decrypted * symlink target (or the no-key encoded symlink target, if the key is * unavailable) rather than the length of the encrypted symlink target. This is * necessary for st_size to match the symlink target that userspace actually * sees. POSIX requires this, and some userspace programs depend on it. * * This requires reading the symlink target from disk if needed, setting up the * inode's encryption key if possible, and then decrypting or encoding the * symlink target. This makes lstat() more heavyweight than is normally the * case. However, decrypted symlink targets will be cached in ->i_link, so * usually the symlink won't have to be read and decrypted again later if/when * it is actually followed, readlink() is called, or lstat() is called again. * * Return: 0 on success, -errno on failure */ int fscrypt_symlink_getattr(const struct path *path, struct kstat *stat) { struct dentry *dentry = path->dentry; struct inode *inode = d_inode(dentry); const char *link; DEFINE_DELAYED_CALL(done); /* * To get the symlink target that userspace will see (whether it's the * decrypted target or the no-key encoded target), we can just get it in * the same way the VFS does during path resolution and readlink(). */ link = READ_ONCE(inode->i_link); if (!link) { link = inode->i_op->get_link(dentry, inode, &done); if (IS_ERR(link)) return PTR_ERR(link); } stat->size = strlen(link); do_delayed_call(&done); return 0; } EXPORT_SYMBOL_GPL(fscrypt_symlink_getattr); |
| 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 | /* SPDX-License-Identifier: GPL-2.0-only */ /* include/net/xdp.h * * Copyright (c) 2017 Jesper Dangaard Brouer, Red Hat Inc. */ #ifndef __LINUX_NET_XDP_H__ #define __LINUX_NET_XDP_H__ #include <linux/bitfield.h> #include <linux/filter.h> #include <linux/netdevice.h> #include <linux/skbuff.h> /* skb_shared_info */ /** * DOC: XDP RX-queue information * * The XDP RX-queue info (xdp_rxq_info) is associated with the driver * level RX-ring queues. It is information that is specific to how * the driver has configured a given RX-ring queue. * * Each xdp_buff frame received in the driver carries a (pointer) * reference to this xdp_rxq_info structure. This provides the XDP * data-path read-access to RX-info for both kernel and bpf-side * (limited subset). * * For now, direct access is only safe while running in NAPI/softirq * context. Contents are read-mostly and must not be updated during * driver NAPI/softirq poll. * * The driver usage API is a register and unregister API. * * The struct is not directly tied to the XDP prog. A new XDP prog * can be attached as long as it doesn't change the underlying * RX-ring. If the RX-ring does change significantly, the NIC driver * naturally needs to stop the RX-ring before purging and reallocating * memory. In that process the driver MUST call unregister (which * also applies for driver shutdown and unload). The register API is * also mandatory during RX-ring setup. */ enum xdp_mem_type { MEM_TYPE_PAGE_SHARED = 0, /* Split-page refcnt based model */ MEM_TYPE_PAGE_ORDER0, /* Orig XDP full page model */ MEM_TYPE_PAGE_POOL, MEM_TYPE_XSK_BUFF_POOL, MEM_TYPE_MAX, }; /* XDP flags for ndo_xdp_xmit */ #define XDP_XMIT_FLUSH (1U << 0) /* doorbell signal consumer */ #define XDP_XMIT_FLAGS_MASK XDP_XMIT_FLUSH struct xdp_mem_info { u32 type; /* enum xdp_mem_type, but known size type */ u32 id; }; struct page_pool; struct xdp_rxq_info { struct net_device *dev; u32 queue_index; u32 reg_state; struct xdp_mem_info mem; unsigned int napi_id; u32 frag_size; } ____cacheline_aligned; /* perf critical, avoid false-sharing */ struct xdp_txq_info { struct net_device *dev; }; enum xdp_buff_flags { XDP_FLAGS_HAS_FRAGS = BIT(0), /* non-linear xdp buff */ XDP_FLAGS_FRAGS_PF_MEMALLOC = BIT(1), /* xdp paged memory is under * pressure */ }; struct xdp_buff { void *data; void *data_end; void *data_meta; void *data_hard_start; struct xdp_rxq_info *rxq; struct xdp_txq_info *txq; u32 frame_sz; /* frame size to deduce data_hard_end/reserved tailroom*/ u32 flags; /* supported values defined in xdp_buff_flags */ }; static __always_inline bool xdp_buff_has_frags(struct xdp_buff *xdp) { return !!(xdp->flags & XDP_FLAGS_HAS_FRAGS); } static __always_inline void xdp_buff_set_frags_flag(struct xdp_buff *xdp) { xdp->flags |= XDP_FLAGS_HAS_FRAGS; } static __always_inline void xdp_buff_clear_frags_flag(struct xdp_buff *xdp) { xdp->flags &= ~XDP_FLAGS_HAS_FRAGS; } static __always_inline bool xdp_buff_is_frag_pfmemalloc(struct xdp_buff *xdp) { return !!(xdp->flags & XDP_FLAGS_FRAGS_PF_MEMALLOC); } static __always_inline void xdp_buff_set_frag_pfmemalloc(struct xdp_buff *xdp) { xdp->flags |= XDP_FLAGS_FRAGS_PF_MEMALLOC; } static __always_inline void xdp_init_buff(struct xdp_buff *xdp, u32 frame_sz, struct xdp_rxq_info *rxq) { xdp->frame_sz = frame_sz; xdp->rxq = rxq; xdp->flags = 0; } static __always_inline void xdp_prepare_buff(struct xdp_buff *xdp, unsigned char *hard_start, int headroom, int data_len, const bool meta_valid) { unsigned char *data = hard_start + headroom; xdp->data_hard_start = hard_start; xdp->data = data; xdp->data_end = data + data_len; xdp->data_meta = meta_valid ? data : data + 1; } /* Reserve memory area at end-of data area. * * This macro reserves tailroom in the XDP buffer by limiting the * XDP/BPF data access to data_hard_end. Notice same area (and size) * is used for XDP_PASS, when constructing the SKB via build_skb(). */ #define xdp_data_hard_end(xdp) \ ((xdp)->data_hard_start + (xdp)->frame_sz - \ SKB_DATA_ALIGN(sizeof(struct skb_shared_info))) static inline struct skb_shared_info * xdp_get_shared_info_from_buff(struct xdp_buff *xdp) { return (struct skb_shared_info *)xdp_data_hard_end(xdp); } static __always_inline unsigned int xdp_get_buff_len(struct xdp_buff *xdp) { unsigned int len = xdp->data_end - xdp->data; struct skb_shared_info *sinfo; if (likely(!xdp_buff_has_frags(xdp))) goto out; sinfo = xdp_get_shared_info_from_buff(xdp); len += sinfo->xdp_frags_size; out: return len; } struct xdp_frame { void *data; u16 len; u16 headroom; u32 metasize; /* uses lower 8-bits */ /* Lifetime of xdp_rxq_info is limited to NAPI/enqueue time, * while mem info is valid on remote CPU. */ struct xdp_mem_info mem; struct net_device *dev_rx; /* used by cpumap */ u32 frame_sz; u32 flags; /* supported values defined in xdp_buff_flags */ }; static __always_inline bool xdp_frame_has_frags(struct xdp_frame *frame) { return !!(frame->flags & XDP_FLAGS_HAS_FRAGS); } static __always_inline bool xdp_frame_is_frag_pfmemalloc(struct xdp_frame *frame) { return !!(frame->flags & XDP_FLAGS_FRAGS_PF_MEMALLOC); } #define XDP_BULK_QUEUE_SIZE 16 struct xdp_frame_bulk { int count; void *xa; void *q[XDP_BULK_QUEUE_SIZE]; }; static __always_inline void xdp_frame_bulk_init(struct xdp_frame_bulk *bq) { /* bq->count will be zero'ed when bq->xa gets updated */ bq->xa = NULL; } static inline struct skb_shared_info * xdp_get_shared_info_from_frame(struct xdp_frame *frame) { void *data_hard_start = frame->data - frame->headroom - sizeof(*frame); return (struct skb_shared_info *)(data_hard_start + frame->frame_sz - SKB_DATA_ALIGN(sizeof(struct skb_shared_info))); } struct xdp_cpumap_stats { unsigned int redirect; unsigned int pass; unsigned int drop; }; /* Clear kernel pointers in xdp_frame */ static inline void xdp_scrub_frame(struct xdp_frame *frame) { frame->data = NULL; frame->dev_rx = NULL; } static inline void xdp_update_skb_shared_info(struct sk_buff *skb, u8 nr_frags, unsigned int size, unsigned int truesize, bool pfmemalloc) { skb_shinfo(skb)->nr_frags = nr_frags; skb->len += size; skb->data_len += size; skb->truesize += truesize; skb->pfmemalloc |= pfmemalloc; } /* Avoids inlining WARN macro in fast-path */ void xdp_warn(const char *msg, const char *func, const int line); #define XDP_WARN(msg) xdp_warn(msg, __func__, __LINE__) struct xdp_frame *xdp_convert_zc_to_xdp_frame(struct xdp_buff *xdp); struct sk_buff *__xdp_build_skb_from_frame(struct xdp_frame *xdpf, struct sk_buff *skb, struct net_device *dev); struct sk_buff *xdp_build_skb_from_frame(struct xdp_frame *xdpf, struct net_device *dev); int xdp_alloc_skb_bulk(void **skbs, int n_skb, gfp_t gfp); struct xdp_frame *xdpf_clone(struct xdp_frame *xdpf); static inline void xdp_convert_frame_to_buff(struct xdp_frame *frame, struct xdp_buff *xdp) { xdp->data_hard_start = frame->data - frame->headroom - sizeof(*frame); xdp->data = frame->data; xdp->data_end = frame->data + frame->len; xdp->data_meta = frame->data - frame->metasize; xdp->frame_sz = frame->frame_sz; xdp->flags = frame->flags; } static inline int xdp_update_frame_from_buff(struct xdp_buff *xdp, struct xdp_frame *xdp_frame) { int metasize, headroom; /* Assure headroom is available for storing info */ headroom = xdp->data - xdp->data_hard_start; metasize = xdp->data - xdp->data_meta; metasize = metasize > 0 ? metasize : 0; if (unlikely((headroom - metasize) < sizeof(*xdp_frame))) return -ENOSPC; /* Catch if driver didn't reserve tailroom for skb_shared_info */ if (unlikely(xdp->data_end > xdp_data_hard_end(xdp))) { XDP_WARN("Driver BUG: missing reserved tailroom"); return -ENOSPC; } xdp_frame->data = xdp->data; xdp_frame->len = xdp->data_end - xdp->data; xdp_frame->headroom = headroom - sizeof(*xdp_frame); xdp_frame->metasize = metasize; xdp_frame->frame_sz = xdp->frame_sz; xdp_frame->flags = xdp->flags; return 0; } /* Convert xdp_buff to xdp_frame */ static inline struct xdp_frame *xdp_convert_buff_to_frame(struct xdp_buff *xdp) { struct xdp_frame *xdp_frame; if (xdp->rxq->mem.type == MEM_TYPE_XSK_BUFF_POOL) return xdp_convert_zc_to_xdp_frame(xdp); /* Store info in top of packet */ xdp_frame = xdp->data_hard_start; if (unlikely(xdp_update_frame_from_buff(xdp, xdp_frame) < 0)) return NULL; /* rxq only valid until napi_schedule ends, convert to xdp_mem_info */ xdp_frame->mem = xdp->rxq->mem; return xdp_frame; } void __xdp_return(void *data, struct xdp_mem_info *mem, bool napi_direct, struct xdp_buff *xdp); void xdp_return_frame(struct xdp_frame *xdpf); void xdp_return_frame_rx_napi(struct xdp_frame *xdpf); void xdp_return_buff(struct xdp_buff *xdp); void xdp_flush_frame_bulk(struct xdp_frame_bulk *bq); void xdp_return_frame_bulk(struct xdp_frame *xdpf, struct xdp_frame_bulk *bq); static __always_inline unsigned int xdp_get_frame_len(struct xdp_frame *xdpf) { struct skb_shared_info *sinfo; unsigned int len = xdpf->len; if (likely(!xdp_frame_has_frags(xdpf))) goto out; sinfo = xdp_get_shared_info_from_frame(xdpf); len += sinfo->xdp_frags_size; out: return len; } int __xdp_rxq_info_reg(struct xdp_rxq_info *xdp_rxq, struct net_device *dev, u32 queue_index, unsigned int napi_id, u32 frag_size); static inline int xdp_rxq_info_reg(struct xdp_rxq_info *xdp_rxq, struct net_device *dev, u32 queue_index, unsigned int napi_id) { return __xdp_rxq_info_reg(xdp_rxq, dev, queue_index, napi_id, 0); } void xdp_rxq_info_unreg(struct xdp_rxq_info *xdp_rxq); void xdp_rxq_info_unused(struct xdp_rxq_info *xdp_rxq); bool xdp_rxq_info_is_reg(struct xdp_rxq_info *xdp_rxq); int xdp_rxq_info_reg_mem_model(struct xdp_rxq_info *xdp_rxq, enum xdp_mem_type type, void *allocator); void xdp_rxq_info_unreg_mem_model(struct xdp_rxq_info *xdp_rxq); int xdp_reg_mem_model(struct xdp_mem_info *mem, enum xdp_mem_type type, void *allocator); void xdp_unreg_mem_model(struct xdp_mem_info *mem); /* Drivers not supporting XDP metadata can use this helper, which * rejects any room expansion for metadata as a result. */ static __always_inline void xdp_set_data_meta_invalid(struct xdp_buff *xdp) { xdp->data_meta = xdp->data + 1; } static __always_inline bool xdp_data_meta_unsupported(const struct xdp_buff *xdp) { return unlikely(xdp->data_meta > xdp->data); } static inline bool xdp_metalen_invalid(unsigned long metalen) { unsigned long meta_max; meta_max = type_max(typeof_member(struct skb_shared_info, meta_len)); BUILD_BUG_ON(!__builtin_constant_p(meta_max)); return !IS_ALIGNED(metalen, sizeof(u32)) || metalen > meta_max; } struct xdp_attachment_info { struct bpf_prog *prog; u32 flags; }; struct netdev_bpf; void xdp_attachment_setup(struct xdp_attachment_info *info, struct netdev_bpf *bpf); #define DEV_MAP_BULK_SIZE XDP_BULK_QUEUE_SIZE /* Define the relationship between xdp-rx-metadata kfunc and * various other entities: * - xdp_rx_metadata enum * - netdev netlink enum (Documentation/netlink/specs/netdev.yaml) * - kfunc name * - xdp_metadata_ops field */ #define XDP_METADATA_KFUNC_xxx \ XDP_METADATA_KFUNC(XDP_METADATA_KFUNC_RX_TIMESTAMP, \ NETDEV_XDP_RX_METADATA_TIMESTAMP, \ bpf_xdp_metadata_rx_timestamp, \ xmo_rx_timestamp) \ XDP_METADATA_KFUNC(XDP_METADATA_KFUNC_RX_HASH, \ NETDEV_XDP_RX_METADATA_HASH, \ bpf_xdp_metadata_rx_hash, \ xmo_rx_hash) \ XDP_METADATA_KFUNC(XDP_METADATA_KFUNC_RX_VLAN_TAG, \ NETDEV_XDP_RX_METADATA_VLAN_TAG, \ bpf_xdp_metadata_rx_vlan_tag, \ xmo_rx_vlan_tag) \ enum xdp_rx_metadata { #define XDP_METADATA_KFUNC(name, _, __, ___) name, XDP_METADATA_KFUNC_xxx #undef XDP_METADATA_KFUNC MAX_XDP_METADATA_KFUNC, }; enum xdp_rss_hash_type { /* First part: Individual bits for L3/L4 types */ XDP_RSS_L3_IPV4 = BIT(0), XDP_RSS_L3_IPV6 = BIT(1), /* The fixed (L3) IPv4 and IPv6 headers can both be followed by * variable/dynamic headers, IPv4 called Options and IPv6 called * Extension Headers. HW RSS type can contain this info. */ XDP_RSS_L3_DYNHDR = BIT(2), /* When RSS hash covers L4 then drivers MUST set XDP_RSS_L4 bit in * addition to the protocol specific bit. This ease interaction with * SKBs and avoids reserving a fixed mask for future L4 protocol bits. */ XDP_RSS_L4 = BIT(3), /* L4 based hash, proto can be unknown */ XDP_RSS_L4_TCP = BIT(4), XDP_RSS_L4_UDP = BIT(5), XDP_RSS_L4_SCTP = BIT(6), XDP_RSS_L4_IPSEC = BIT(7), /* L4 based hash include IPSEC SPI */ XDP_RSS_L4_ICMP = BIT(8), /* Second part: RSS hash type combinations used for driver HW mapping */ XDP_RSS_TYPE_NONE = 0, XDP_RSS_TYPE_L2 = XDP_RSS_TYPE_NONE, XDP_RSS_TYPE_L3_IPV4 = XDP_RSS_L3_IPV4, XDP_RSS_TYPE_L3_IPV6 = XDP_RSS_L3_IPV6, XDP_RSS_TYPE_L3_IPV4_OPT = XDP_RSS_L3_IPV4 | XDP_RSS_L3_DYNHDR, XDP_RSS_TYPE_L3_IPV6_EX = XDP_RSS_L3_IPV6 | XDP_RSS_L3_DYNHDR, XDP_RSS_TYPE_L4_ANY = XDP_RSS_L4, XDP_RSS_TYPE_L4_IPV4_TCP = XDP_RSS_L3_IPV4 | XDP_RSS_L4 | XDP_RSS_L4_TCP, XDP_RSS_TYPE_L4_IPV4_UDP = XDP_RSS_L3_IPV4 | XDP_RSS_L4 | XDP_RSS_L4_UDP, XDP_RSS_TYPE_L4_IPV4_SCTP = XDP_RSS_L3_IPV4 | XDP_RSS_L4 | XDP_RSS_L4_SCTP, XDP_RSS_TYPE_L4_IPV4_IPSEC = XDP_RSS_L3_IPV4 | XDP_RSS_L4 | XDP_RSS_L4_IPSEC, XDP_RSS_TYPE_L4_IPV4_ICMP = XDP_RSS_L3_IPV4 | XDP_RSS_L4 | XDP_RSS_L4_ICMP, XDP_RSS_TYPE_L4_IPV6_TCP = XDP_RSS_L3_IPV6 | XDP_RSS_L4 | XDP_RSS_L4_TCP, XDP_RSS_TYPE_L4_IPV6_UDP = XDP_RSS_L3_IPV6 | XDP_RSS_L4 | XDP_RSS_L4_UDP, XDP_RSS_TYPE_L4_IPV6_SCTP = XDP_RSS_L3_IPV6 | XDP_RSS_L4 | XDP_RSS_L4_SCTP, XDP_RSS_TYPE_L4_IPV6_IPSEC = XDP_RSS_L3_IPV6 | XDP_RSS_L4 | XDP_RSS_L4_IPSEC, XDP_RSS_TYPE_L4_IPV6_ICMP = XDP_RSS_L3_IPV6 | XDP_RSS_L4 | XDP_RSS_L4_ICMP, XDP_RSS_TYPE_L4_IPV6_TCP_EX = XDP_RSS_TYPE_L4_IPV6_TCP | XDP_RSS_L3_DYNHDR, XDP_RSS_TYPE_L4_IPV6_UDP_EX = XDP_RSS_TYPE_L4_IPV6_UDP | XDP_RSS_L3_DYNHDR, XDP_RSS_TYPE_L4_IPV6_SCTP_EX = XDP_RSS_TYPE_L4_IPV6_SCTP | XDP_RSS_L3_DYNHDR, }; struct xdp_metadata_ops { int (*xmo_rx_timestamp)(const struct xdp_md *ctx, u64 *timestamp); int (*xmo_rx_hash)(const struct xdp_md *ctx, u32 *hash, enum xdp_rss_hash_type *rss_type); int (*xmo_rx_vlan_tag)(const struct xdp_md *ctx, __be16 *vlan_proto, u16 *vlan_tci); }; #ifdef CONFIG_NET u32 bpf_xdp_metadata_kfunc_id(int id); bool bpf_dev_bound_kfunc_id(u32 btf_id); void xdp_set_features_flag(struct net_device *dev, xdp_features_t val); void xdp_features_set_redirect_target(struct net_device *dev, bool support_sg); void xdp_features_clear_redirect_target(struct net_device *dev); #else static inline u32 bpf_xdp_metadata_kfunc_id(int id) { return 0; } static inline bool bpf_dev_bound_kfunc_id(u32 btf_id) { return false; } static inline void xdp_set_features_flag(struct net_device *dev, xdp_features_t val) { } static inline void xdp_features_set_redirect_target(struct net_device *dev, bool support_sg) { } static inline void xdp_features_clear_redirect_target(struct net_device *dev) { } #endif static inline void xdp_clear_features_flag(struct net_device *dev) { xdp_set_features_flag(dev, 0); } static __always_inline u32 bpf_prog_run_xdp(const struct bpf_prog *prog, struct xdp_buff *xdp) { /* Driver XDP hooks are invoked within a single NAPI poll cycle and thus * under local_bh_disable(), which provides the needed RCU protection * for accessing map entries. */ u32 act = __bpf_prog_run(prog, xdp, BPF_DISPATCHER_FUNC(xdp)); if (static_branch_unlikely(&bpf_master_redirect_enabled_key)) { if (act == XDP_TX && netif_is_bond_slave(xdp->rxq->dev)) act = xdp_master_redirect(xdp); } return act; } #endif /* __LINUX_NET_XDP_H__ */ |
| 1 13 2 1 4 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 | /* SPDX-License-Identifier: GPL-2.0 */ #if !defined(_TRACE_HANDLE_EXIT_ARM64_KVM_H) || defined(TRACE_HEADER_MULTI_READ) #define _TRACE_HANDLE_EXIT_ARM64_KVM_H #include <linux/tracepoint.h> #include "sys_regs.h" #undef TRACE_SYSTEM #define TRACE_SYSTEM kvm TRACE_EVENT(kvm_wfx_arm64, TP_PROTO(unsigned long vcpu_pc, bool is_wfe), TP_ARGS(vcpu_pc, is_wfe), TP_STRUCT__entry( __field(unsigned long, vcpu_pc) __field(bool, is_wfe) ), TP_fast_assign( __entry->vcpu_pc = vcpu_pc; __entry->is_wfe = is_wfe; ), TP_printk("guest executed wf%c at: 0x%016lx", __entry->is_wfe ? 'e' : 'i', __entry->vcpu_pc) ); TRACE_EVENT(kvm_hvc_arm64, TP_PROTO(unsigned long vcpu_pc, unsigned long r0, unsigned long imm), TP_ARGS(vcpu_pc, r0, imm), TP_STRUCT__entry( __field(unsigned long, vcpu_pc) __field(unsigned long, r0) __field(unsigned long, imm) ), TP_fast_assign( __entry->vcpu_pc = vcpu_pc; __entry->r0 = r0; __entry->imm = imm; ), TP_printk("HVC at 0x%016lx (r0: 0x%016lx, imm: 0x%lx)", __entry->vcpu_pc, __entry->r0, __entry->imm) ); /* * The dreg32 name is a leftover from a distant past. This will really * output a 64bit value... */ TRACE_EVENT(kvm_arm_set_dreg32, TP_PROTO(const char *name, __u64 value), TP_ARGS(name, value), TP_STRUCT__entry( __field(const char *, name) __field(__u64, value) ), TP_fast_assign( __entry->name = name; __entry->value = value; ), TP_printk("%s: 0x%llx", __entry->name, __entry->value) ); TRACE_EVENT(kvm_handle_sys_reg, TP_PROTO(unsigned long hsr), TP_ARGS(hsr), TP_STRUCT__entry( __field(unsigned long, hsr) ), TP_fast_assign( __entry->hsr = hsr; ), TP_printk("HSR 0x%08lx", __entry->hsr) ); TRACE_EVENT(kvm_sys_access, TP_PROTO(unsigned long vcpu_pc, struct sys_reg_params *params, const struct sys_reg_desc *reg), TP_ARGS(vcpu_pc, params, reg), TP_STRUCT__entry( __field(unsigned long, vcpu_pc) __field(bool, is_write) __field(const char *, name) __field(u8, Op0) __field(u8, Op1) __field(u8, CRn) __field(u8, CRm) __field(u8, Op2) ), TP_fast_assign( __entry->vcpu_pc = vcpu_pc; __entry->is_write = params->is_write; __entry->name = reg->name; __entry->Op0 = reg->Op0; __entry->Op0 = reg->Op0; __entry->Op1 = reg->Op1; __entry->CRn = reg->CRn; __entry->CRm = reg->CRm; __entry->Op2 = reg->Op2; ), TP_printk("PC: %lx %s (%d,%d,%d,%d,%d) %s", __entry->vcpu_pc, __entry->name ?: "UNKN", __entry->Op0, __entry->Op1, __entry->CRn, __entry->CRm, __entry->Op2, __entry->is_write ? "write" : "read") ); TRACE_EVENT(kvm_set_guest_debug, TP_PROTO(struct kvm_vcpu *vcpu, __u32 guest_debug), TP_ARGS(vcpu, guest_debug), TP_STRUCT__entry( __field(struct kvm_vcpu *, vcpu) __field(__u32, guest_debug) ), TP_fast_assign( __entry->vcpu = vcpu; __entry->guest_debug = guest_debug; ), TP_printk("vcpu: %p, flags: 0x%08x", __entry->vcpu, __entry->guest_debug) ); #endif /* _TRACE_HANDLE_EXIT_ARM64_KVM_H */ #undef TRACE_INCLUDE_PATH #define TRACE_INCLUDE_PATH . #undef TRACE_INCLUDE_FILE #define TRACE_INCLUDE_FILE trace_handle_exit /* This part must be outside protection */ #include <trace/define_trace.h> |
| 138 48 97 98 96 48 48 48 48 48 48 358 358 357 358 356 15 15 15 358 358 357 349 358 358 358 235 232 235 232 233 233 364 8 166 78 14 16 185 185 233 232 12 224 189 20 174 364 305 348 364 364 364 362 364 363 364 360 350 361 362 98 97 2 360 97 358 98 33 2 33 33 33 33 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 | // SPDX-License-Identifier: GPL-2.0-only /* * linux/mm/swap.c * * Copyright (C) 1991, 1992, 1993, 1994 Linus Torvalds */ /* * This file contains the default values for the operation of the * Linux VM subsystem. Fine-tuning documentation can be found in * Documentation/admin-guide/sysctl/vm.rst. * Started 18.12.91 * Swap aging added 23.2.95, Stephen Tweedie. * Buffermem limits added 12.3.98, Rik van Riel. */ #include <linux/mm.h> #include <linux/sched.h> #include <linux/kernel_stat.h> #include <linux/swap.h> #include <linux/mman.h> #include <linux/pagemap.h> #include <linux/pagevec.h> #include <linux/init.h> #include <linux/export.h> #include <linux/mm_inline.h> #include <linux/percpu_counter.h> #include <linux/memremap.h> #include <linux/percpu.h> #include <linux/cpu.h> #include <linux/notifier.h> #include <linux/backing-dev.h> #include <linux/memcontrol.h> #include <linux/gfp.h> #include <linux/uio.h> #include <linux/hugetlb.h> #include <linux/page_idle.h> #include <linux/local_lock.h> #include <linux/buffer_head.h> #include "internal.h" #define CREATE_TRACE_POINTS #include <trace/events/pagemap.h> /* How many pages do we try to swap or page in/out together? As a power of 2 */ int page_cluster; const int page_cluster_max = 31; struct cpu_fbatches { /* * The following folio batches are grouped together because they are protected * by disabling preemption (and interrupts remain enabled). */ local_lock_t lock; struct folio_batch lru_add; struct folio_batch lru_deactivate_file; struct folio_batch lru_deactivate; struct folio_batch lru_lazyfree; #ifdef CONFIG_SMP struct folio_batch lru_activate; #endif /* Protecting the following batches which require disabling interrupts */ local_lock_t lock_irq; struct folio_batch lru_move_tail; }; static DEFINE_PER_CPU(struct cpu_fbatches, cpu_fbatches) = { .lock = INIT_LOCAL_LOCK(lock), .lock_irq = INIT_LOCAL_LOCK(lock_irq), }; static void __page_cache_release(struct folio *folio, struct lruvec **lruvecp, unsigned long *flagsp) { if (folio_test_lru(folio)) { folio_lruvec_relock_irqsave(folio, lruvecp, flagsp); lruvec_del_folio(*lruvecp, folio); __folio_clear_lru_flags(folio); } } /* * This path almost never happens for VM activity - pages are normally freed * in batches. But it gets used by networking - and for compound pages. */ static void page_cache_release(struct folio *folio) { struct lruvec *lruvec = NULL; unsigned long flags; __page_cache_release(folio, &lruvec, &flags); if (lruvec) unlock_page_lruvec_irqrestore(lruvec, flags); } void __folio_put(struct folio *folio) { if (unlikely(folio_is_zone_device(folio))) { free_zone_device_folio(folio); return; } if (folio_test_hugetlb(folio)) { free_huge_folio(folio); return; } page_cache_release(folio); folio_unqueue_deferred_split(folio); mem_cgroup_uncharge(folio); free_unref_page(&folio->page, folio_order(folio)); } EXPORT_SYMBOL(__folio_put); typedef void (*move_fn_t)(struct lruvec *lruvec, struct folio *folio); static void lru_add(struct lruvec *lruvec, struct folio *folio) { int was_unevictable = folio_test_clear_unevictable(folio); long nr_pages = folio_nr_pages(folio); VM_BUG_ON_FOLIO(folio_test_lru(folio), folio); /* * Is an smp_mb__after_atomic() still required here, before * folio_evictable() tests the mlocked flag, to rule out the possibility * of stranding an evictable folio on an unevictable LRU? I think * not, because __munlock_folio() only clears the mlocked flag * while the LRU lock is held. * * (That is not true of __page_cache_release(), and not necessarily * true of folios_put(): but those only clear the mlocked flag after * folio_put_testzero() has excluded any other users of the folio.) */ if (folio_evictable(folio)) { if (was_unevictable) __count_vm_events(UNEVICTABLE_PGRESCUED, nr_pages); } else { folio_clear_active(folio); folio_set_unevictable(folio); /* * folio->mlock_count = !!folio_test_mlocked(folio)? * But that leaves __mlock_folio() in doubt whether another * actor has already counted the mlock or not. Err on the * safe side, underestimate, let page reclaim fix it, rather * than leaving a page on the unevictable LRU indefinitely. */ folio->mlock_count = 0; if (!was_unevictable) __count_vm_events(UNEVICTABLE_PGCULLED, nr_pages); } lruvec_add_folio(lruvec, folio); trace_mm_lru_insertion(folio); } static void folio_batch_move_lru(struct folio_batch *fbatch, move_fn_t move_fn) { int i; struct lruvec *lruvec = NULL; unsigned long flags = 0; for (i = 0; i < folio_batch_count(fbatch); i++) { struct folio *folio = fbatch->folios[i]; folio_lruvec_relock_irqsave(folio, &lruvec, &flags); move_fn(lruvec, folio); folio_set_lru(folio); } if (lruvec) unlock_page_lruvec_irqrestore(lruvec, flags); folios_put(fbatch); } static void __folio_batch_add_and_move(struct folio_batch __percpu *fbatch, struct folio *folio, move_fn_t move_fn, bool on_lru, bool disable_irq) { unsigned long flags; if (on_lru && !folio_test_clear_lru(folio)) return; folio_get(folio); if (disable_irq) local_lock_irqsave(&cpu_fbatches.lock_irq, flags); else local_lock(&cpu_fbatches.lock); if (!folio_batch_add(this_cpu_ptr(fbatch), folio) || folio_test_large(folio) || lru_cache_disabled()) folio_batch_move_lru(this_cpu_ptr(fbatch), move_fn); if (disable_irq) local_unlock_irqrestore(&cpu_fbatches.lock_irq, flags); else local_unlock(&cpu_fbatches.lock); } #define folio_batch_add_and_move(folio, op, on_lru) \ __folio_batch_add_and_move( \ &cpu_fbatches.op, \ folio, \ op, \ on_lru, \ offsetof(struct cpu_fbatches, op) >= offsetof(struct cpu_fbatches, lock_irq) \ ) static void lru_move_tail(struct lruvec *lruvec, struct folio *folio) { if (folio_test_unevictable(folio)) return; lruvec_del_folio(lruvec, folio); folio_clear_active(folio); lruvec_add_folio_tail(lruvec, folio); __count_vm_events(PGROTATED, folio_nr_pages(folio)); } /* * Writeback is about to end against a folio which has been marked for * immediate reclaim. If it still appears to be reclaimable, move it * to the tail of the inactive list. * * folio_rotate_reclaimable() must disable IRQs, to prevent nasty races. */ void folio_rotate_reclaimable(struct folio *folio) { if (folio_test_locked(folio) || folio_test_dirty(folio) || folio_test_unevictable(folio)) return; folio_batch_add_and_move(folio, lru_move_tail, true); } void lru_note_cost(struct lruvec *lruvec, bool file, unsigned int nr_io, unsigned int nr_rotated) { unsigned long cost; /* * Reflect the relative cost of incurring IO and spending CPU * time on rotations. This doesn't attempt to make a precise * comparison, it just says: if reloads are about comparable * between the LRU lists, or rotations are overwhelmingly * different between them, adjust scan balance for CPU work. */ cost = nr_io * SWAP_CLUSTER_MAX + nr_rotated; do { unsigned long lrusize; /* * Hold lruvec->lru_lock is safe here, since * 1) The pinned lruvec in reclaim, or * 2) From a pre-LRU page during refault (which also holds the * rcu lock, so would be safe even if the page was on the LRU * and could move simultaneously to a new lruvec). */ spin_lock_irq(&lruvec->lru_lock); /* Record cost event */ if (file) lruvec->file_cost += cost; else lruvec->anon_cost += cost; /* * Decay previous events * * Because workloads change over time (and to avoid * overflow) we keep these statistics as a floating * average, which ends up weighing recent refaults * more than old ones. */ lrusize = lruvec_page_state(lruvec, NR_INACTIVE_ANON) + lruvec_page_state(lruvec, NR_ACTIVE_ANON) + lruvec_page_state(lruvec, NR_INACTIVE_FILE) + lruvec_page_state(lruvec, NR_ACTIVE_FILE); if (lruvec->file_cost + lruvec->anon_cost > lrusize / 4) { lruvec->file_cost /= 2; lruvec->anon_cost /= 2; } spin_unlock_irq(&lruvec->lru_lock); } while ((lruvec = parent_lruvec(lruvec))); } void lru_note_cost_refault(struct folio *folio) { lru_note_cost(folio_lruvec(folio), folio_is_file_lru(folio), folio_nr_pages(folio), 0); } static void lru_activate(struct lruvec *lruvec, struct folio *folio) { long nr_pages = folio_nr_pages(folio); if (folio_test_active(folio) || folio_test_unevictable(folio)) return; lruvec_del_folio(lruvec, folio); folio_set_active(folio); lruvec_add_folio(lruvec, folio); trace_mm_lru_activate(folio); __count_vm_events(PGACTIVATE, nr_pages); __count_memcg_events(lruvec_memcg(lruvec), PGACTIVATE, nr_pages); } #ifdef CONFIG_SMP static void folio_activate_drain(int cpu) { struct folio_batch *fbatch = &per_cpu(cpu_fbatches.lru_activate, cpu); if (folio_batch_count(fbatch)) folio_batch_move_lru(fbatch, lru_activate); } void folio_activate(struct folio *folio) { if (folio_test_active(folio) || folio_test_unevictable(folio)) return; folio_batch_add_and_move(folio, lru_activate, true); } #else static inline void folio_activate_drain(int cpu) { } void folio_activate(struct folio *folio) { struct lruvec *lruvec; if (!folio_test_clear_lru(folio)) return; lruvec = folio_lruvec_lock_irq(folio); lru_activate(lruvec, folio); unlock_page_lruvec_irq(lruvec); folio_set_lru(folio); } #endif static void __lru_cache_activate_folio(struct folio *folio) { struct folio_batch *fbatch; int i; local_lock(&cpu_fbatches.lock); fbatch = this_cpu_ptr(&cpu_fbatches.lru_add); /* * Search backwards on the optimistic assumption that the folio being * activated has just been added to this batch. Note that only * the local batch is examined as a !LRU folio could be in the * process of being released, reclaimed, migrated or on a remote * batch that is currently being drained. Furthermore, marking * a remote batch's folio active potentially hits a race where * a folio is marked active just after it is added to the inactive * list causing accounting errors and BUG_ON checks to trigger. */ for (i = folio_batch_count(fbatch) - 1; i >= 0; i--) { struct folio *batch_folio = fbatch->folios[i]; if (batch_folio == folio) { folio_set_active(folio); break; } } local_unlock(&cpu_fbatches.lock); } #ifdef CONFIG_LRU_GEN static void folio_inc_refs(struct folio *folio) { unsigned long new_flags, old_flags = READ_ONCE(folio->flags); if (folio_test_unevictable(folio)) return; if (!folio_test_referenced(folio)) { folio_set_referenced(folio); return; } if (!folio_test_workingset(folio)) { folio_set_workingset(folio); return; } /* see the comment on MAX_NR_TIERS */ do { new_flags = old_flags & LRU_REFS_MASK; if (new_flags == LRU_REFS_MASK) break; new_flags += BIT(LRU_REFS_PGOFF); new_flags |= old_flags & ~LRU_REFS_MASK; } while (!try_cmpxchg(&folio->flags, &old_flags, new_flags)); } #else static void folio_inc_refs(struct folio *folio) { } #endif /* CONFIG_LRU_GEN */ /** * folio_mark_accessed - Mark a folio as having seen activity. * @folio: The folio to mark. * * This function will perform one of the following transitions: * * * inactive,unreferenced -> inactive,referenced * * inactive,referenced -> active,unreferenced * * active,unreferenced -> active,referenced * * When a newly allocated folio is not yet visible, so safe for non-atomic ops, * __folio_set_referenced() may be substituted for folio_mark_accessed(). */ void folio_mark_accessed(struct folio *folio) { if (lru_gen_enabled()) { folio_inc_refs(folio); return; } if (!folio_test_referenced(folio)) { folio_set_referenced(folio); } else if (folio_test_unevictable(folio)) { /* * Unevictable pages are on the "LRU_UNEVICTABLE" list. But, * this list is never rotated or maintained, so marking an * unevictable page accessed has no effect. */ } else if (!folio_test_active(folio)) { /* * If the folio is on the LRU, queue it for activation via * cpu_fbatches.lru_activate. Otherwise, assume the folio is in a * folio_batch, mark it active and it'll be moved to the active * LRU on the next drain. */ if (folio_test_lru(folio)) folio_activate(folio); else __lru_cache_activate_folio(folio); folio_clear_referenced(folio); workingset_activation(folio); } if (folio_test_idle(folio)) folio_clear_idle(folio); } EXPORT_SYMBOL(folio_mark_accessed); /** * folio_add_lru - Add a folio to an LRU list. * @folio: The folio to be added to the LRU. * * Queue the folio for addition to the LRU. The decision on whether * to add the page to the [in]active [file|anon] list is deferred until the * folio_batch is drained. This gives a chance for the caller of folio_add_lru() * have the folio added to the active list using folio_mark_accessed(). */ void folio_add_lru(struct folio *folio) { VM_BUG_ON_FOLIO(folio_test_active(folio) && folio_test_unevictable(folio), folio); VM_BUG_ON_FOLIO(folio_test_lru(folio), folio); /* see the comment in lru_gen_add_folio() */ if (lru_gen_enabled() && !folio_test_unevictable(folio) && lru_gen_in_fault() && !(current->flags & PF_MEMALLOC)) folio_set_active(folio); folio_batch_add_and_move(folio, lru_add, false); } EXPORT_SYMBOL(folio_add_lru); /** * folio_add_lru_vma() - Add a folio to the appropate LRU list for this VMA. * @folio: The folio to be added to the LRU. * @vma: VMA in which the folio is mapped. * * If the VMA is mlocked, @folio is added to the unevictable list. * Otherwise, it is treated the same way as folio_add_lru(). */ void folio_add_lru_vma(struct folio *folio, struct vm_area_struct *vma) { VM_BUG_ON_FOLIO(folio_test_lru(folio), folio); if (unlikely((vma->vm_flags & (VM_LOCKED | VM_SPECIAL)) == VM_LOCKED)) mlock_new_folio(folio); else folio_add_lru(folio); } /* * If the folio cannot be invalidated, it is moved to the * inactive list to speed up its reclaim. It is moved to the * head of the list, rather than the tail, to give the flusher * threads some time to write it out, as this is much more * effective than the single-page writeout from reclaim. * * If the folio isn't mapped and dirty/writeback, the folio * could be reclaimed asap using the reclaim flag. * * 1. active, mapped folio -> none * 2. active, dirty/writeback folio -> inactive, head, reclaim * 3. inactive, mapped folio -> none * 4. inactive, dirty/writeback folio -> inactive, head, reclaim * 5. inactive, clean -> inactive, tail * 6. Others -> none * * In 4, it moves to the head of the inactive list so the folio is * written out by flusher threads as this is much more efficient * than the single-page writeout from reclaim. */ static void lru_deactivate_file(struct lruvec *lruvec, struct folio *folio) { bool active = folio_test_active(folio); long nr_pages = folio_nr_pages(folio); if (folio_test_unevictable(folio)) return; /* Some processes are using the folio */ if (folio_mapped(folio)) return; lruvec_del_folio(lruvec, folio); folio_clear_active(folio); folio_clear_referenced(folio); if (folio_test_writeback(folio) || folio_test_dirty(folio)) { /* * Setting the reclaim flag could race with * folio_end_writeback() and confuse readahead. But the * race window is _really_ small and it's not a critical * problem. */ lruvec_add_folio(lruvec, folio); folio_set_reclaim(folio); } else { /* * The folio's writeback ended while it was in the batch. * We move that folio to the tail of the inactive list. */ lruvec_add_folio_tail(lruvec, folio); __count_vm_events(PGROTATED, nr_pages); } if (active) { __count_vm_events(PGDEACTIVATE, nr_pages); __count_memcg_events(lruvec_memcg(lruvec), PGDEACTIVATE, nr_pages); } } static void lru_deactivate(struct lruvec *lruvec, struct folio *folio) { long nr_pages = folio_nr_pages(folio); if (folio_test_unevictable(folio) || !(folio_test_active(folio) || lru_gen_enabled())) return; lruvec_del_folio(lruvec, folio); folio_clear_active(folio); folio_clear_referenced(folio); lruvec_add_folio(lruvec, folio); __count_vm_events(PGDEACTIVATE, nr_pages); __count_memcg_events(lruvec_memcg(lruvec), PGDEACTIVATE, nr_pages); } static void lru_lazyfree(struct lruvec *lruvec, struct folio *folio) { long nr_pages = folio_nr_pages(folio); if (!folio_test_anon(folio) || !folio_test_swapbacked(folio) || folio_test_swapcache(folio) || folio_test_unevictable(folio)) return; lruvec_del_folio(lruvec, folio); folio_clear_active(folio); folio_clear_referenced(folio); /* * Lazyfree folios are clean anonymous folios. They have * the swapbacked flag cleared, to distinguish them from normal * anonymous folios */ folio_clear_swapbacked(folio); lruvec_add_folio(lruvec, folio); __count_vm_events(PGLAZYFREE, nr_pages); __count_memcg_events(lruvec_memcg(lruvec), PGLAZYFREE, nr_pages); } /* * Drain pages out of the cpu's folio_batch. * Either "cpu" is the current CPU, and preemption has already been * disabled; or "cpu" is being hot-unplugged, and is already dead. */ void lru_add_drain_cpu(int cpu) { struct cpu_fbatches *fbatches = &per_cpu(cpu_fbatches, cpu); struct folio_batch *fbatch = &fbatches->lru_add; if (folio_batch_count(fbatch)) folio_batch_move_lru(fbatch, lru_add); fbatch = &fbatches->lru_move_tail; /* Disabling interrupts below acts as a compiler barrier. */ if (data_race(folio_batch_count(fbatch))) { unsigned long flags; /* No harm done if a racing interrupt already did this */ local_lock_irqsave(&cpu_fbatches.lock_irq, flags); folio_batch_move_lru(fbatch, lru_move_tail); local_unlock_irqrestore(&cpu_fbatches.lock_irq, flags); } fbatch = &fbatches->lru_deactivate_file; if (folio_batch_count(fbatch)) folio_batch_move_lru(fbatch, lru_deactivate_file); fbatch = &fbatches->lru_deactivate; if (folio_batch_count(fbatch)) folio_batch_move_lru(fbatch, lru_deactivate); fbatch = &fbatches->lru_lazyfree; if (folio_batch_count(fbatch)) folio_batch_move_lru(fbatch, lru_lazyfree); folio_activate_drain(cpu); } /** * deactivate_file_folio() - Deactivate a file folio. * @folio: Folio to deactivate. * * This function hints to the VM that @folio is a good reclaim candidate, * for example if its invalidation fails due to the folio being dirty * or under writeback. * * Context: Caller holds a reference on the folio. */ void deactivate_file_folio(struct folio *folio) { /* Deactivating an unevictable folio will not accelerate reclaim */ if (folio_test_unevictable(folio)) return; folio_batch_add_and_move(folio, lru_deactivate_file, true); } /* * folio_deactivate - deactivate a folio * @folio: folio to deactivate * * folio_deactivate() moves @folio to the inactive list if @folio was on the * active list and was not unevictable. This is done to accelerate the * reclaim of @folio. */ void folio_deactivate(struct folio *folio) { if (folio_test_unevictable(folio) || !(folio_test_active(folio) || lru_gen_enabled())) return; folio_batch_add_and_move(folio, lru_deactivate, true); } /** * folio_mark_lazyfree - make an anon folio lazyfree * @folio: folio to deactivate * * folio_mark_lazyfree() moves @folio to the inactive file list. * This is done to accelerate the reclaim of @folio. */ void folio_mark_lazyfree(struct folio *folio) { if (!folio_test_anon(folio) || !folio_test_swapbacked(folio) || folio_test_swapcache(folio) || folio_test_unevictable(folio)) return; folio_batch_add_and_move(folio, lru_lazyfree, true); } void lru_add_drain(void) { local_lock(&cpu_fbatches.lock); lru_add_drain_cpu(smp_processor_id()); local_unlock(&cpu_fbatches.lock); mlock_drain_local(); } /* * It's called from per-cpu workqueue context in SMP case so * lru_add_drain_cpu and invalidate_bh_lrus_cpu should run on * the same cpu. It shouldn't be a problem in !SMP case since * the core is only one and the locks will disable preemption. */ static void lru_add_and_bh_lrus_drain(void) { local_lock(&cpu_fbatches.lock); lru_add_drain_cpu(smp_processor_id()); local_unlock(&cpu_fbatches.lock); invalidate_bh_lrus_cpu(); mlock_drain_local(); } void lru_add_drain_cpu_zone(struct zone *zone) { local_lock(&cpu_fbatches.lock); lru_add_drain_cpu(smp_processor_id()); drain_local_pages(zone); local_unlock(&cpu_fbatches.lock); mlock_drain_local(); } #ifdef CONFIG_SMP static DEFINE_PER_CPU(struct work_struct, lru_add_drain_work); static void lru_add_drain_per_cpu(struct work_struct *dummy) { lru_add_and_bh_lrus_drain(); } static bool cpu_needs_drain(unsigned int cpu) { struct cpu_fbatches *fbatches = &per_cpu(cpu_fbatches, cpu); /* Check these in order of likelihood that they're not zero */ return folio_batch_count(&fbatches->lru_add) || folio_batch_count(&fbatches->lru_move_tail) || folio_batch_count(&fbatches->lru_deactivate_file) || folio_batch_count(&fbatches->lru_deactivate) || folio_batch_count(&fbatches->lru_lazyfree) || folio_batch_count(&fbatches->lru_activate) || need_mlock_drain(cpu) || has_bh_in_lru(cpu, NULL); } /* * Doesn't need any cpu hotplug locking because we do rely on per-cpu * kworkers being shut down before our page_alloc_cpu_dead callback is * executed on the offlined cpu. * Calling this function with cpu hotplug locks held can actually lead * to obscure indirect dependencies via WQ context. */ static inline void __lru_add_drain_all(bool force_all_cpus) { /* * lru_drain_gen - Global pages generation number * * (A) Definition: global lru_drain_gen = x implies that all generations * 0 < n <= x are already *scheduled* for draining. * * This is an optimization for the highly-contended use case where a * user space workload keeps constantly generating a flow of pages for * each CPU. */ static unsigned int lru_drain_gen; static struct cpumask has_work; static DEFINE_MUTEX(lock); unsigned cpu, this_gen; /* * Make sure nobody triggers this path before mm_percpu_wq is fully * initialized. */ if (WARN_ON(!mm_percpu_wq)) return; /* * Guarantee folio_batch counter stores visible by this CPU * are visible to other CPUs before loading the current drain * generation. */ smp_mb(); /* * (B) Locally cache global LRU draining generation number * * The read barrier ensures that the counter is loaded before the mutex * is taken. It pairs with smp_mb() inside the mutex critical section * at (D). */ this_gen = smp_load_acquire(&lru_drain_gen); mutex_lock(&lock); /* * (C) Exit the draining operation if a newer generation, from another * lru_add_drain_all(), was already scheduled for draining. Check (A). */ if (unlikely(this_gen != lru_drain_gen && !force_all_cpus)) goto done; /* * (D) Increment global generation number * * Pairs with smp_load_acquire() at (B), outside of the critical * section. Use a full memory barrier to guarantee that the * new global drain generation number is stored before loading * folio_batch counters. * * This pairing must be done here, before the for_each_online_cpu loop * below which drains the page vectors. * * Let x, y, and z represent some system CPU numbers, where x < y < z. * Assume CPU #z is in the middle of the for_each_online_cpu loop * below and has already reached CPU #y's per-cpu data. CPU #x comes * along, adds some pages to its per-cpu vectors, then calls * lru_add_drain_all(). * * If the paired barrier is done at any later step, e.g. after the * loop, CPU #x will just exit at (C) and miss flushing out all of its * added pages. */ WRITE_ONCE(lru_drain_gen, lru_drain_gen + 1); smp_mb(); cpumask_clear(&has_work); for_each_online_cpu(cpu) { struct work_struct *work = &per_cpu(lru_add_drain_work, cpu); if (cpu_needs_drain(cpu)) { INIT_WORK(work, lru_add_drain_per_cpu); queue_work_on(cpu, mm_percpu_wq, work); __cpumask_set_cpu(cpu, &has_work); } } for_each_cpu(cpu, &has_work) flush_work(&per_cpu(lru_add_drain_work, cpu)); done: mutex_unlock(&lock); } void lru_add_drain_all(void) { __lru_add_drain_all(false); } #else void lru_add_drain_all(void) { lru_add_drain(); } #endif /* CONFIG_SMP */ atomic_t lru_disable_count = ATOMIC_INIT(0); /* * lru_cache_disable() needs to be called before we start compiling * a list of folios to be migrated using folio_isolate_lru(). * It drains folios on LRU cache and then disable on all cpus until * lru_cache_enable is called. * * Must be paired with a call to lru_cache_enable(). */ void lru_cache_disable(void) { atomic_inc(&lru_disable_count); /* * Readers of lru_disable_count are protected by either disabling * preemption or rcu_read_lock: * * preempt_disable, local_irq_disable [bh_lru_lock()] * rcu_read_lock [rt_spin_lock CONFIG_PREEMPT_RT] * preempt_disable [local_lock !CONFIG_PREEMPT_RT] * * Since v5.1 kernel, synchronize_rcu() is guaranteed to wait on * preempt_disable() regions of code. So any CPU which sees * lru_disable_count = 0 will have exited the critical * section when synchronize_rcu() returns. */ synchronize_rcu_expedited(); #ifdef CONFIG_SMP __lru_add_drain_all(true); #else lru_add_and_bh_lrus_drain(); #endif } /** * folios_put_refs - Reduce the reference count on a batch of folios. * @folios: The folios. * @refs: The number of refs to subtract from each folio. * * Like folio_put(), but for a batch of folios. This is more efficient * than writing the loop yourself as it will optimise the locks which need * to be taken if the folios are freed. The folios batch is returned * empty and ready to be reused for another batch; there is no need * to reinitialise it. If @refs is NULL, we subtract one from each * folio refcount. * * Context: May be called in process or interrupt context, but not in NMI * context. May be called while holding a spinlock. */ void folios_put_refs(struct folio_batch *folios, unsigned int *refs) { int i, j; struct lruvec *lruvec = NULL; unsigned long flags = 0; for (i = 0, j = 0; i < folios->nr; i++) { struct folio *folio = folios->folios[i]; unsigned int nr_refs = refs ? refs[i] : 1; if (is_huge_zero_folio(folio)) continue; if (folio_is_zone_device(folio)) { if (lruvec) { unlock_page_lruvec_irqrestore(lruvec, flags); lruvec = NULL; } if (put_devmap_managed_folio_refs(folio, nr_refs)) continue; if (folio_ref_sub_and_test(folio, nr_refs)) free_zone_device_folio(folio); continue; } if (!folio_ref_sub_and_test(folio, nr_refs)) continue; /* hugetlb has its own memcg */ if (folio_test_hugetlb(folio)) { if (lruvec) { unlock_page_lruvec_irqrestore(lruvec, flags); lruvec = NULL; } free_huge_folio(folio); continue; } folio_unqueue_deferred_split(folio); __page_cache_release(folio, &lruvec, &flags); if (j != i) folios->folios[j] = folio; j++; } if (lruvec) unlock_page_lruvec_irqrestore(lruvec, flags); if (!j) { folio_batch_reinit(folios); return; } folios->nr = j; mem_cgroup_uncharge_folios(folios); free_unref_folios(folios); } EXPORT_SYMBOL(folios_put_refs); /** * release_pages - batched put_page() * @arg: array of pages to release * @nr: number of pages * * Decrement the reference count on all the pages in @arg. If it * fell to zero, remove the page from the LRU and free it. * * Note that the argument can be an array of pages, encoded pages, * or folio pointers. We ignore any encoded bits, and turn any of * them into just a folio that gets free'd. */ void release_pages(release_pages_arg arg, int nr) { struct folio_batch fbatch; int refs[PAGEVEC_SIZE]; struct encoded_page **encoded = arg.encoded_pages; int i; folio_batch_init(&fbatch); for (i = 0; i < nr; i++) { /* Turn any of the argument types into a folio */ struct folio *folio = page_folio(encoded_page_ptr(encoded[i])); /* Is our next entry actually "nr_pages" -> "nr_refs" ? */ refs[fbatch.nr] = 1; if (unlikely(encoded_page_flags(encoded[i]) & ENCODED_PAGE_BIT_NR_PAGES_NEXT)) refs[fbatch.nr] = encoded_nr_pages(encoded[++i]); if (folio_batch_add(&fbatch, folio) > 0) continue; folios_put_refs(&fbatch, refs); } if (fbatch.nr) folios_put_refs(&fbatch, refs); } EXPORT_SYMBOL(release_pages); /* * The folios which we're about to release may be in the deferred lru-addition * queues. That would prevent them from really being freed right now. That's * OK from a correctness point of view but is inefficient - those folios may be * cache-warm and we want to give them back to the page allocator ASAP. * * So __folio_batch_release() will drain those queues here. * folio_batch_move_lru() calls folios_put() directly to avoid * mutual recursion. */ void __folio_batch_release(struct folio_batch *fbatch) { if (!fbatch->percpu_pvec_drained) { lru_add_drain(); fbatch->percpu_pvec_drained = true; } folios_put(fbatch); } EXPORT_SYMBOL(__folio_batch_release); /** * folio_batch_remove_exceptionals() - Prune non-folios from a batch. * @fbatch: The batch to prune * * find_get_entries() fills a batch with both folios and shadow/swap/DAX * entries. This function prunes all the non-folio entries from @fbatch * without leaving holes, so that it can be passed on to folio-only batch * operations. */ void folio_batch_remove_exceptionals(struct folio_batch *fbatch) { unsigned int i, j; for (i = 0, j = 0; i < folio_batch_count(fbatch); i++) { struct folio *folio = fbatch->folios[i]; if (!xa_is_value(folio)) fbatch->folios[j++] = folio; } fbatch->nr = j; } /* * Perform any setup for the swap system */ void __init swap_setup(void) { unsigned long megs = totalram_pages() >> (20 - PAGE_SHIFT); /* Use a smaller cluster for small-memory machines */ if (megs < 16) page_cluster = 2; else page_cluster = 3; /* * Right now other parts of the system means that we * _really_ don't want to cluster much more */ } |
| 3 3 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 | // SPDX-License-Identifier: GPL-2.0-or-later /* Copyright (c) 2014 Mahesh Bandewar <maheshb@google.com> */ #include <linux/ethtool.h> #include "ipvlan.h" static int ipvlan_set_port_mode(struct ipvl_port *port, u16 nval, struct netlink_ext_ack *extack) { struct ipvl_dev *ipvlan; unsigned int flags; int err; ASSERT_RTNL(); if (port->mode != nval) { list_for_each_entry(ipvlan, &port->ipvlans, pnode) { flags = ipvlan->dev->flags; if (nval == IPVLAN_MODE_L3 || nval == IPVLAN_MODE_L3S) { err = dev_change_flags(ipvlan->dev, flags | IFF_NOARP, extack); } else { err = dev_change_flags(ipvlan->dev, flags & ~IFF_NOARP, extack); } if (unlikely(err)) goto fail; } if (nval == IPVLAN_MODE_L3S) { /* New mode is L3S */ err = ipvlan_l3s_register(port); if (err) goto fail; } else if (port->mode == IPVLAN_MODE_L3S) { /* Old mode was L3S */ ipvlan_l3s_unregister(port); } port->mode = nval; } return 0; fail: /* Undo the flags changes that have been done so far. */ list_for_each_entry_continue_reverse(ipvlan, &port->ipvlans, pnode) { flags = ipvlan->dev->flags; if (port->mode == IPVLAN_MODE_L3 || port->mode == IPVLAN_MODE_L3S) dev_change_flags(ipvlan->dev, flags | IFF_NOARP, NULL); else dev_change_flags(ipvlan->dev, flags & ~IFF_NOARP, NULL); } return err; } static int ipvlan_port_create(struct net_device *dev) { struct ipvl_port *port; int err, idx; port = kzalloc(sizeof(struct ipvl_port), GFP_KERNEL); if (!port) return -ENOMEM; write_pnet(&port->pnet, dev_net(dev)); port->dev = dev; port->mode = IPVLAN_MODE_L3; INIT_LIST_HEAD(&port->ipvlans); for (idx = 0; idx < IPVLAN_HASH_SIZE; idx++) INIT_HLIST_HEAD(&port->hlhead[idx]); skb_queue_head_init(&port->backlog); INIT_WORK(&port->wq, ipvlan_process_multicast); ida_init(&port->ida); port->dev_id_start = 1; err = netdev_rx_handler_register(dev, ipvlan_handle_frame, port); if (err) goto err; netdev_hold(dev, &port->dev_tracker, GFP_KERNEL); return 0; err: kfree(port); return err; } static void ipvlan_port_destroy(struct net_device *dev) { struct ipvl_port *port = ipvlan_port_get_rtnl(dev); struct sk_buff *skb; netdev_put(dev, &port->dev_tracker); if (port->mode == IPVLAN_MODE_L3S) ipvlan_l3s_unregister(port); netdev_rx_handler_unregister(dev); cancel_work_sync(&port->wq); while ((skb = __skb_dequeue(&port->backlog)) != NULL) { dev_put(skb->dev); kfree_skb(skb); } ida_destroy(&port->ida); kfree(port); } #define IPVLAN_ALWAYS_ON_OFLOADS \ (NETIF_F_SG | NETIF_F_HW_CSUM | \ NETIF_F_GSO_ROBUST | NETIF_F_GSO_SOFTWARE | NETIF_F_GSO_ENCAP_ALL) #define IPVLAN_ALWAYS_ON \ (IPVLAN_ALWAYS_ON_OFLOADS | NETIF_F_VLAN_CHALLENGED) #define IPVLAN_FEATURES \ (NETIF_F_SG | NETIF_F_HW_CSUM | NETIF_F_HIGHDMA | NETIF_F_FRAGLIST | \ NETIF_F_GSO | NETIF_F_ALL_TSO | NETIF_F_GSO_ROBUST | \ NETIF_F_GRO | NETIF_F_RXCSUM | \ NETIF_F_HW_VLAN_CTAG_FILTER | NETIF_F_HW_VLAN_STAG_FILTER) /* NETIF_F_GSO_ENCAP_ALL NETIF_F_GSO_SOFTWARE Newly added */ #define IPVLAN_STATE_MASK \ ((1<<__LINK_STATE_NOCARRIER) | (1<<__LINK_STATE_DORMANT)) static int ipvlan_init(struct net_device *dev) { struct ipvl_dev *ipvlan = netdev_priv(dev); struct net_device *phy_dev = ipvlan->phy_dev; struct ipvl_port *port; int err; dev->state = (dev->state & ~IPVLAN_STATE_MASK) | (phy_dev->state & IPVLAN_STATE_MASK); dev->features = phy_dev->features & IPVLAN_FEATURES; dev->features |= IPVLAN_ALWAYS_ON; dev->vlan_features = phy_dev->vlan_features & IPVLAN_FEATURES; dev->vlan_features |= IPVLAN_ALWAYS_ON_OFLOADS; dev->hw_enc_features |= dev->features; dev->lltx = true; netif_inherit_tso_max(dev, phy_dev); dev->hard_header_len = phy_dev->hard_header_len; netdev_lockdep_set_classes(dev); ipvlan->pcpu_stats = netdev_alloc_pcpu_stats(struct ipvl_pcpu_stats); if (!ipvlan->pcpu_stats) return -ENOMEM; if (!netif_is_ipvlan_port(phy_dev)) { err = ipvlan_port_create(phy_dev); if (err < 0) { free_percpu(ipvlan->pcpu_stats); return err; } } port = ipvlan_port_get_rtnl(phy_dev); port->count += 1; return 0; } static void ipvlan_uninit(struct net_device *dev) { struct ipvl_dev *ipvlan = netdev_priv(dev); struct net_device *phy_dev = ipvlan->phy_dev; struct ipvl_port *port; free_percpu(ipvlan->pcpu_stats); port = ipvlan_port_get_rtnl(phy_dev); port->count -= 1; if (!port->count) ipvlan_port_destroy(port->dev); } static int ipvlan_open(struct net_device *dev) { struct ipvl_dev *ipvlan = netdev_priv(dev); struct ipvl_addr *addr; if (ipvlan->port->mode == IPVLAN_MODE_L3 || ipvlan->port->mode == IPVLAN_MODE_L3S) dev->flags |= IFF_NOARP; else dev->flags &= ~IFF_NOARP; rcu_read_lock(); list_for_each_entry_rcu(addr, &ipvlan->addrs, anode) ipvlan_ht_addr_add(ipvlan, addr); rcu_read_unlock(); return 0; } static int ipvlan_stop(struct net_device *dev) { struct ipvl_dev *ipvlan = netdev_priv(dev); struct net_device *phy_dev = ipvlan->phy_dev; struct ipvl_addr *addr; dev_uc_unsync(phy_dev, dev); dev_mc_unsync(phy_dev, dev); rcu_read_lock(); list_for_each_entry_rcu(addr, &ipvlan->addrs, anode) ipvlan_ht_addr_del(addr); rcu_read_unlock(); return 0; } static netdev_tx_t ipvlan_start_xmit(struct sk_buff *skb, struct net_device *dev) { const struct ipvl_dev *ipvlan = netdev_priv(dev); int skblen = skb->len; int ret; ret = ipvlan_queue_xmit(skb, dev); if (likely(ret == NET_XMIT_SUCCESS || ret == NET_XMIT_CN)) { struct ipvl_pcpu_stats *pcptr; pcptr = this_cpu_ptr(ipvlan->pcpu_stats); u64_stats_update_begin(&pcptr->syncp); u64_stats_inc(&pcptr->tx_pkts); u64_stats_add(&pcptr->tx_bytes, skblen); u64_stats_update_end(&pcptr->syncp); } else { this_cpu_inc(ipvlan->pcpu_stats->tx_drps); } return ret; } static netdev_features_t ipvlan_fix_features(struct net_device *dev, netdev_features_t features) { struct ipvl_dev *ipvlan = netdev_priv(dev); features |= NETIF_F_ALL_FOR_ALL; features &= (ipvlan->sfeatures | ~IPVLAN_FEATURES); features = netdev_increment_features(ipvlan->phy_dev->features, features, features); features |= IPVLAN_ALWAYS_ON; features &= (IPVLAN_FEATURES | IPVLAN_ALWAYS_ON); return features; } static void ipvlan_change_rx_flags(struct net_device *dev, int change) { struct ipvl_dev *ipvlan = netdev_priv(dev); struct net_device *phy_dev = ipvlan->phy_dev; if (change & IFF_ALLMULTI) dev_set_allmulti(phy_dev, dev->flags & IFF_ALLMULTI? 1 : -1); } static void ipvlan_set_multicast_mac_filter(struct net_device *dev) { struct ipvl_dev *ipvlan = netdev_priv(dev); if (dev->flags & (IFF_PROMISC | IFF_ALLMULTI)) { bitmap_fill(ipvlan->mac_filters, IPVLAN_MAC_FILTER_SIZE); } else { struct netdev_hw_addr *ha; DECLARE_BITMAP(mc_filters, IPVLAN_MAC_FILTER_SIZE); bitmap_zero(mc_filters, IPVLAN_MAC_FILTER_SIZE); netdev_for_each_mc_addr(ha, dev) __set_bit(ipvlan_mac_hash(ha->addr), mc_filters); /* Turn-on broadcast bit irrespective of address family, * since broadcast is deferred to a work-queue, hence no * impact on fast-path processing. */ __set_bit(ipvlan_mac_hash(dev->broadcast), mc_filters); bitmap_copy(ipvlan->mac_filters, mc_filters, IPVLAN_MAC_FILTER_SIZE); } dev_uc_sync(ipvlan->phy_dev, dev); dev_mc_sync(ipvlan->phy_dev, dev); } static void ipvlan_get_stats64(struct net_device *dev, struct rtnl_link_stats64 *s) { struct ipvl_dev *ipvlan = netdev_priv(dev); if (ipvlan->pcpu_stats) { struct ipvl_pcpu_stats *pcptr; u64 rx_pkts, rx_bytes, rx_mcast, tx_pkts, tx_bytes; u32 rx_errs = 0, tx_drps = 0; u32 strt; int idx; for_each_possible_cpu(idx) { pcptr = per_cpu_ptr(ipvlan->pcpu_stats, idx); do { strt = u64_stats_fetch_begin(&pcptr->syncp); rx_pkts = u64_stats_read(&pcptr->rx_pkts); rx_bytes = u64_stats_read(&pcptr->rx_bytes); rx_mcast = u64_stats_read(&pcptr->rx_mcast); tx_pkts = u64_stats_read(&pcptr->tx_pkts); tx_bytes = u64_stats_read(&pcptr->tx_bytes); } while (u64_stats_fetch_retry(&pcptr->syncp, strt)); s->rx_packets += rx_pkts; s->rx_bytes += rx_bytes; s->multicast += rx_mcast; s->tx_packets += tx_pkts; s->tx_bytes += tx_bytes; /* u32 values are updated without syncp protection. */ rx_errs += READ_ONCE(pcptr->rx_errs); tx_drps += READ_ONCE(pcptr->tx_drps); } s->rx_errors = rx_errs; s->rx_dropped = rx_errs; s->tx_dropped = tx_drps; } s->tx_errors = DEV_STATS_READ(dev, tx_errors); } static int ipvlan_vlan_rx_add_vid(struct net_device *dev, __be16 proto, u16 vid) { struct ipvl_dev *ipvlan = netdev_priv(dev); struct net_device *phy_dev = ipvlan->phy_dev; return vlan_vid_add(phy_dev, proto, vid); } static int ipvlan_vlan_rx_kill_vid(struct net_device *dev, __be16 proto, u16 vid) { struct ipvl_dev *ipvlan = netdev_priv(dev); struct net_device *phy_dev = ipvlan->phy_dev; vlan_vid_del(phy_dev, proto, vid); return 0; } static int ipvlan_get_iflink(const struct net_device *dev) { struct ipvl_dev *ipvlan = netdev_priv(dev); return READ_ONCE(ipvlan->phy_dev->ifindex); } static const struct net_device_ops ipvlan_netdev_ops = { .ndo_init = ipvlan_init, .ndo_uninit = ipvlan_uninit, .ndo_open = ipvlan_open, .ndo_stop = ipvlan_stop, .ndo_start_xmit = ipvlan_start_xmit, .ndo_fix_features = ipvlan_fix_features, .ndo_change_rx_flags = ipvlan_change_rx_flags, .ndo_set_rx_mode = ipvlan_set_multicast_mac_filter, .ndo_get_stats64 = ipvlan_get_stats64, .ndo_vlan_rx_add_vid = ipvlan_vlan_rx_add_vid, .ndo_vlan_rx_kill_vid = ipvlan_vlan_rx_kill_vid, .ndo_get_iflink = ipvlan_get_iflink, }; static int ipvlan_hard_header(struct sk_buff *skb, struct net_device *dev, unsigned short type, const void *daddr, const void *saddr, unsigned len) { const struct ipvl_dev *ipvlan = netdev_priv(dev); struct net_device *phy_dev = ipvlan->phy_dev; /* TODO Probably use a different field than dev_addr so that the * mac-address on the virtual device is portable and can be carried * while the packets use the mac-addr on the physical device. */ return dev_hard_header(skb, phy_dev, type, daddr, saddr ? : phy_dev->dev_addr, len); } static const struct header_ops ipvlan_header_ops = { .create = ipvlan_hard_header, .parse = eth_header_parse, .cache = eth_header_cache, .cache_update = eth_header_cache_update, .parse_protocol = eth_header_parse_protocol, }; static void ipvlan_adjust_mtu(struct ipvl_dev *ipvlan, struct net_device *dev) { ipvlan->dev->mtu = dev->mtu; } static bool netif_is_ipvlan(const struct net_device *dev) { /* both ipvlan and ipvtap devices use the same netdev_ops */ return dev->netdev_ops == &ipvlan_netdev_ops; } static int ipvlan_ethtool_get_link_ksettings(struct net_device *dev, struct ethtool_link_ksettings *cmd) { const struct ipvl_dev *ipvlan = netdev_priv(dev); return __ethtool_get_link_ksettings(ipvlan->phy_dev, cmd); } static void ipvlan_ethtool_get_drvinfo(struct net_device *dev, struct ethtool_drvinfo *drvinfo) { strscpy(drvinfo->driver, IPVLAN_DRV, sizeof(drvinfo->driver)); strscpy(drvinfo->version, IPV_DRV_VER, sizeof(drvinfo->version)); } static u32 ipvlan_ethtool_get_msglevel(struct net_device *dev) { const struct ipvl_dev *ipvlan = netdev_priv(dev); return ipvlan->msg_enable; } static void ipvlan_ethtool_set_msglevel(struct net_device *dev, u32 value) { struct ipvl_dev *ipvlan = netdev_priv(dev); ipvlan->msg_enable = value; } static const struct ethtool_ops ipvlan_ethtool_ops = { .get_link = ethtool_op_get_link, .get_link_ksettings = ipvlan_ethtool_get_link_ksettings, .get_drvinfo = ipvlan_ethtool_get_drvinfo, .get_msglevel = ipvlan_ethtool_get_msglevel, .set_msglevel = ipvlan_ethtool_set_msglevel, }; static int ipvlan_nl_changelink(struct net_device *dev, struct nlattr *tb[], struct nlattr *data[], struct netlink_ext_ack *extack) { struct ipvl_dev *ipvlan = netdev_priv(dev); struct ipvl_port *port = ipvlan_port_get_rtnl(ipvlan->phy_dev); int err = 0; if (!data) return 0; if (!ns_capable(dev_net(ipvlan->phy_dev)->user_ns, CAP_NET_ADMIN)) return -EPERM; if (data[IFLA_IPVLAN_MODE]) { u16 nmode = nla_get_u16(data[IFLA_IPVLAN_MODE]); err = ipvlan_set_port_mode(port, nmode, extack); } if (!err && data[IFLA_IPVLAN_FLAGS]) { u16 flags = nla_get_u16(data[IFLA_IPVLAN_FLAGS]); if (flags & IPVLAN_F_PRIVATE) ipvlan_mark_private(port); else ipvlan_clear_private(port); if (flags & IPVLAN_F_VEPA) ipvlan_mark_vepa(port); else ipvlan_clear_vepa(port); } return err; } static size_t ipvlan_nl_getsize(const struct net_device *dev) { return (0 + nla_total_size(2) /* IFLA_IPVLAN_MODE */ + nla_total_size(2) /* IFLA_IPVLAN_FLAGS */ ); } static int ipvlan_nl_validate(struct nlattr *tb[], struct nlattr *data[], struct netlink_ext_ack *extack) { if (!data) return 0; if (data[IFLA_IPVLAN_MODE]) { u16 mode = nla_get_u16(data[IFLA_IPVLAN_MODE]); if (mode >= IPVLAN_MODE_MAX) return -EINVAL; } if (data[IFLA_IPVLAN_FLAGS]) { u16 flags = nla_get_u16(data[IFLA_IPVLAN_FLAGS]); /* Only two bits are used at this moment. */ if (flags & ~(IPVLAN_F_PRIVATE | IPVLAN_F_VEPA)) return -EINVAL; /* Also both flags can't be active at the same time. */ if ((flags & (IPVLAN_F_PRIVATE | IPVLAN_F_VEPA)) == (IPVLAN_F_PRIVATE | IPVLAN_F_VEPA)) return -EINVAL; } return 0; } static int ipvlan_nl_fillinfo(struct sk_buff *skb, const struct net_device *dev) { struct ipvl_dev *ipvlan = netdev_priv(dev); struct ipvl_port *port = ipvlan_port_get_rtnl(ipvlan->phy_dev); int ret = -EINVAL; if (!port) goto err; ret = -EMSGSIZE; if (nla_put_u16(skb, IFLA_IPVLAN_MODE, port->mode)) goto err; if (nla_put_u16(skb, IFLA_IPVLAN_FLAGS, port->flags)) goto err; return 0; err: return ret; } int ipvlan_link_new(struct net *src_net, struct net_device *dev, struct nlattr *tb[], struct nlattr *data[], struct netlink_ext_ack *extack) { struct ipvl_dev *ipvlan = netdev_priv(dev); struct ipvl_port *port; struct net_device *phy_dev; int err; u16 mode = IPVLAN_MODE_L3; if (!tb[IFLA_LINK]) return -EINVAL; phy_dev = __dev_get_by_index(src_net, nla_get_u32(tb[IFLA_LINK])); if (!phy_dev) return -ENODEV; if (netif_is_ipvlan(phy_dev)) { struct ipvl_dev *tmp = netdev_priv(phy_dev); phy_dev = tmp->phy_dev; if (!ns_capable(dev_net(phy_dev)->user_ns, CAP_NET_ADMIN)) return -EPERM; } else if (!netif_is_ipvlan_port(phy_dev)) { /* Exit early if the underlying link is invalid or busy */ if (phy_dev->type != ARPHRD_ETHER || phy_dev->flags & IFF_LOOPBACK) { netdev_err(phy_dev, "Master is either lo or non-ether device\n"); return -EINVAL; } if (netdev_is_rx_handler_busy(phy_dev)) { netdev_err(phy_dev, "Device is already in use.\n"); return -EBUSY; } } ipvlan->phy_dev = phy_dev; ipvlan->dev = dev; ipvlan->sfeatures = IPVLAN_FEATURES; if (!tb[IFLA_MTU]) ipvlan_adjust_mtu(ipvlan, phy_dev); INIT_LIST_HEAD(&ipvlan->addrs); spin_lock_init(&ipvlan->addrs_lock); /* TODO Probably put random address here to be presented to the * world but keep using the physical-dev address for the outgoing * packets. */ eth_hw_addr_set(dev, phy_dev->dev_addr); dev->priv_flags |= IFF_NO_RX_HANDLER; err = register_netdevice(dev); if (err < 0) return err; /* ipvlan_init() would have created the port, if required */ port = ipvlan_port_get_rtnl(phy_dev); ipvlan->port = port; /* If the port-id base is at the MAX value, then wrap it around and * begin from 0x1 again. This may be due to a busy system where lots * of slaves are getting created and deleted. */ if (port->dev_id_start == 0xFFFE) port->dev_id_start = 0x1; /* Since L2 address is shared among all IPvlan slaves including * master, use unique 16 bit dev-ids to differentiate among them. * Assign IDs between 0x1 and 0xFFFE (used by the master) to each * slave link [see addrconf_ifid_eui48()]. */ err = ida_alloc_range(&port->ida, port->dev_id_start, 0xFFFD, GFP_KERNEL); if (err < 0) err = ida_alloc_range(&port->ida, 0x1, port->dev_id_start - 1, GFP_KERNEL); if (err < 0) goto unregister_netdev; dev->dev_id = err; /* Increment id-base to the next slot for the future assignment */ port->dev_id_start = err + 1; err = netdev_upper_dev_link(phy_dev, dev, extack); if (err) goto remove_ida; /* Flags are per port and latest update overrides. User has * to be consistent in setting it just like the mode attribute. */ if (data && data[IFLA_IPVLAN_FLAGS]) port->flags = nla_get_u16(data[IFLA_IPVLAN_FLAGS]); if (data && data[IFLA_IPVLAN_MODE]) mode = nla_get_u16(data[IFLA_IPVLAN_MODE]); err = ipvlan_set_port_mode(port, mode, extack); if (err) goto unlink_netdev; list_add_tail_rcu(&ipvlan->pnode, &port->ipvlans); netif_stacked_transfer_operstate(phy_dev, dev); return 0; unlink_netdev: netdev_upper_dev_unlink(phy_dev, dev); remove_ida: ida_free(&port->ida, dev->dev_id); unregister_netdev: unregister_netdevice(dev); return err; } EXPORT_SYMBOL_GPL(ipvlan_link_new); void ipvlan_link_delete(struct net_device *dev, struct list_head *head) { struct ipvl_dev *ipvlan = netdev_priv(dev); struct ipvl_addr *addr, *next; spin_lock_bh(&ipvlan->addrs_lock); list_for_each_entry_safe(addr, next, &ipvlan->addrs, anode) { ipvlan_ht_addr_del(addr); list_del_rcu(&addr->anode); kfree_rcu(addr, rcu); } spin_unlock_bh(&ipvlan->addrs_lock); ida_free(&ipvlan->port->ida, dev->dev_id); list_del_rcu(&ipvlan->pnode); unregister_netdevice_queue(dev, head); netdev_upper_dev_unlink(ipvlan->phy_dev, dev); } EXPORT_SYMBOL_GPL(ipvlan_link_delete); void ipvlan_link_setup(struct net_device *dev) { ether_setup(dev); dev->max_mtu = ETH_MAX_MTU; dev->priv_flags &= ~(IFF_XMIT_DST_RELEASE | IFF_TX_SKB_SHARING); dev->priv_flags |= IFF_UNICAST_FLT | IFF_NO_QUEUE; dev->netdev_ops = &ipvlan_netdev_ops; dev->needs_free_netdev = true; dev->header_ops = &ipvlan_header_ops; dev->ethtool_ops = &ipvlan_ethtool_ops; } EXPORT_SYMBOL_GPL(ipvlan_link_setup); static const struct nla_policy ipvlan_nl_policy[IFLA_IPVLAN_MAX + 1] = { [IFLA_IPVLAN_MODE] = { .type = NLA_U16 }, [IFLA_IPVLAN_FLAGS] = { .type = NLA_U16 }, }; static struct net *ipvlan_get_link_net(const struct net_device *dev) { struct ipvl_dev *ipvlan = netdev_priv(dev); return dev_net(ipvlan->phy_dev); } static struct rtnl_link_ops ipvlan_link_ops = { .kind = "ipvlan", .priv_size = sizeof(struct ipvl_dev), .setup = ipvlan_link_setup, .newlink = ipvlan_link_new, .dellink = ipvlan_link_delete, .get_link_net = ipvlan_get_link_net, }; int ipvlan_link_register(struct rtnl_link_ops *ops) { ops->get_size = ipvlan_nl_getsize; ops->policy = ipvlan_nl_policy; ops->validate = ipvlan_nl_validate; ops->fill_info = ipvlan_nl_fillinfo; ops->changelink = ipvlan_nl_changelink; ops->maxtype = IFLA_IPVLAN_MAX; return rtnl_link_register(ops); } EXPORT_SYMBOL_GPL(ipvlan_link_register); static int ipvlan_device_event(struct notifier_block *unused, unsigned long event, void *ptr) { struct netlink_ext_ack *extack = netdev_notifier_info_to_extack(ptr); struct netdev_notifier_pre_changeaddr_info *prechaddr_info; struct net_device *dev = netdev_notifier_info_to_dev(ptr); struct ipvl_dev *ipvlan, *next; struct ipvl_port *port; LIST_HEAD(lst_kill); int err; if (!netif_is_ipvlan_port(dev)) return NOTIFY_DONE; port = ipvlan_port_get_rtnl(dev); switch (event) { case NETDEV_UP: case NETDEV_DOWN: case NETDEV_CHANGE: list_for_each_entry(ipvlan, &port->ipvlans, pnode) netif_stacked_transfer_operstate(ipvlan->phy_dev, ipvlan->dev); break; case NETDEV_REGISTER: { struct net *oldnet, *newnet = dev_net(dev); oldnet = read_pnet(&port->pnet); if (net_eq(newnet, oldnet)) break; write_pnet(&port->pnet, newnet); if (port->mode == IPVLAN_MODE_L3S) ipvlan_migrate_l3s_hook(oldnet, newnet); break; } case NETDEV_UNREGISTER: if (dev->reg_state != NETREG_UNREGISTERING) break; list_for_each_entry_safe(ipvlan, next, &port->ipvlans, pnode) ipvlan->dev->rtnl_link_ops->dellink(ipvlan->dev, &lst_kill); unregister_netdevice_many(&lst_kill); break; case NETDEV_FEAT_CHANGE: list_for_each_entry(ipvlan, &port->ipvlans, pnode) { netif_inherit_tso_max(ipvlan->dev, dev); netdev_update_features(ipvlan->dev); } break; case NETDEV_CHANGEMTU: list_for_each_entry(ipvlan, &port->ipvlans, pnode) ipvlan_adjust_mtu(ipvlan, dev); break; case NETDEV_PRE_CHANGEADDR: prechaddr_info = ptr; list_for_each_entry(ipvlan, &port->ipvlans, pnode) { err = dev_pre_changeaddr_notify(ipvlan->dev, prechaddr_info->dev_addr, extack); if (err) return notifier_from_errno(err); } break; case NETDEV_CHANGEADDR: list_for_each_entry(ipvlan, &port->ipvlans, pnode) { eth_hw_addr_set(ipvlan->dev, dev->dev_addr); call_netdevice_notifiers(NETDEV_CHANGEADDR, ipvlan->dev); } break; case NETDEV_PRE_TYPE_CHANGE: /* Forbid underlying device to change its type. */ return NOTIFY_BAD; } return NOTIFY_DONE; } /* the caller must held the addrs lock */ static int ipvlan_add_addr(struct ipvl_dev *ipvlan, void *iaddr, bool is_v6) { struct ipvl_addr *addr; addr = kzalloc(sizeof(struct ipvl_addr), GFP_ATOMIC); if (!addr) return -ENOMEM; addr->master = ipvlan; if (!is_v6) { memcpy(&addr->ip4addr, iaddr, sizeof(struct in_addr)); addr->atype = IPVL_IPV4; #if IS_ENABLED(CONFIG_IPV6) } else { memcpy(&addr->ip6addr, iaddr, sizeof(struct in6_addr)); addr->atype = IPVL_IPV6; #endif } list_add_tail_rcu(&addr->anode, &ipvlan->addrs); /* If the interface is not up, the address will be added to the hash * list by ipvlan_open. */ if (netif_running(ipvlan->dev)) ipvlan_ht_addr_add(ipvlan, addr); return 0; } static void ipvlan_del_addr(struct ipvl_dev *ipvlan, void *iaddr, bool is_v6) { struct ipvl_addr *addr; spin_lock_bh(&ipvlan->addrs_lock); addr = ipvlan_find_addr(ipvlan, iaddr, is_v6); if (!addr) { spin_unlock_bh(&ipvlan->addrs_lock); return; } ipvlan_ht_addr_del(addr); list_del_rcu(&addr->anode); spin_unlock_bh(&ipvlan->addrs_lock); kfree_rcu(addr, rcu); } static bool ipvlan_is_valid_dev(const struct net_device *dev) { struct ipvl_dev *ipvlan = netdev_priv(dev); if (!netif_is_ipvlan(dev)) return false; if (!ipvlan || !ipvlan->port) return false; return true; } #if IS_ENABLED(CONFIG_IPV6) static int ipvlan_add_addr6(struct ipvl_dev *ipvlan, struct in6_addr *ip6_addr) { int ret = -EINVAL; spin_lock_bh(&ipvlan->addrs_lock); if (ipvlan_addr_busy(ipvlan->port, ip6_addr, true)) netif_err(ipvlan, ifup, ipvlan->dev, "Failed to add IPv6=%pI6c addr for %s intf\n", ip6_addr, ipvlan->dev->name); else ret = ipvlan_add_addr(ipvlan, ip6_addr, true); spin_unlock_bh(&ipvlan->addrs_lock); return ret; } static void ipvlan_del_addr6(struct ipvl_dev *ipvlan, struct in6_addr *ip6_addr) { return ipvlan_del_addr(ipvlan, ip6_addr, true); } static int ipvlan_addr6_event(struct notifier_block *unused, unsigned long event, void *ptr) { struct inet6_ifaddr *if6 = (struct inet6_ifaddr *)ptr; struct net_device *dev = (struct net_device *)if6->idev->dev; struct ipvl_dev *ipvlan = netdev_priv(dev); if (!ipvlan_is_valid_dev(dev)) return NOTIFY_DONE; switch (event) { case NETDEV_UP: if (ipvlan_add_addr6(ipvlan, &if6->addr)) return NOTIFY_BAD; break; case NETDEV_DOWN: ipvlan_del_addr6(ipvlan, &if6->addr); break; } return NOTIFY_OK; } static int ipvlan_addr6_validator_event(struct notifier_block *unused, unsigned long event, void *ptr) { struct in6_validator_info *i6vi = (struct in6_validator_info *)ptr; struct net_device *dev = (struct net_device *)i6vi->i6vi_dev->dev; struct ipvl_dev *ipvlan = netdev_priv(dev); if (!ipvlan_is_valid_dev(dev)) return NOTIFY_DONE; switch (event) { case NETDEV_UP: if (ipvlan_addr_busy(ipvlan->port, &i6vi->i6vi_addr, true)) { NL_SET_ERR_MSG(i6vi->extack, "Address already assigned to an ipvlan device"); return notifier_from_errno(-EADDRINUSE); } break; } return NOTIFY_OK; } #endif static int ipvlan_add_addr4(struct ipvl_dev *ipvlan, struct in_addr *ip4_addr) { int ret = -EINVAL; spin_lock_bh(&ipvlan->addrs_lock); if (ipvlan_addr_busy(ipvlan->port, ip4_addr, false)) netif_err(ipvlan, ifup, ipvlan->dev, "Failed to add IPv4=%pI4 on %s intf.\n", ip4_addr, ipvlan->dev->name); else ret = ipvlan_add_addr(ipvlan, ip4_addr, false); spin_unlock_bh(&ipvlan->addrs_lock); return ret; } static void ipvlan_del_addr4(struct ipvl_dev *ipvlan, struct in_addr *ip4_addr) { return ipvlan_del_addr(ipvlan, ip4_addr, false); } static int ipvlan_addr4_event(struct notifier_block *unused, unsigned long event, void *ptr) { struct in_ifaddr *if4 = (struct in_ifaddr *)ptr; struct net_device *dev = (struct net_device *)if4->ifa_dev->dev; struct ipvl_dev *ipvlan = netdev_priv(dev); struct in_addr ip4_addr; if (!ipvlan_is_valid_dev(dev)) return NOTIFY_DONE; switch (event) { case NETDEV_UP: ip4_addr.s_addr = if4->ifa_address; if (ipvlan_add_addr4(ipvlan, &ip4_addr)) return NOTIFY_BAD; break; case NETDEV_DOWN: ip4_addr.s_addr = if4->ifa_address; ipvlan_del_addr4(ipvlan, &ip4_addr); break; } return NOTIFY_OK; } static int ipvlan_addr4_validator_event(struct notifier_block *unused, unsigned long event, void *ptr) { struct in_validator_info *ivi = (struct in_validator_info *)ptr; struct net_device *dev = (struct net_device *)ivi->ivi_dev->dev; struct ipvl_dev *ipvlan = netdev_priv(dev); if (!ipvlan_is_valid_dev(dev)) return NOTIFY_DONE; switch (event) { case NETDEV_UP: if (ipvlan_addr_busy(ipvlan->port, &ivi->ivi_addr, false)) { NL_SET_ERR_MSG(ivi->extack, "Address already assigned to an ipvlan device"); return notifier_from_errno(-EADDRINUSE); } break; } return NOTIFY_OK; } static struct notifier_block ipvlan_addr4_notifier_block __read_mostly = { .notifier_call = ipvlan_addr4_event, }; static struct notifier_block ipvlan_addr4_vtor_notifier_block __read_mostly = { .notifier_call = ipvlan_addr4_validator_event, }; static struct notifier_block ipvlan_notifier_block __read_mostly = { .notifier_call = ipvlan_device_event, }; #if IS_ENABLED(CONFIG_IPV6) static struct notifier_block ipvlan_addr6_notifier_block __read_mostly = { .notifier_call = ipvlan_addr6_event, }; static struct notifier_block ipvlan_addr6_vtor_notifier_block __read_mostly = { .notifier_call = ipvlan_addr6_validator_event, }; #endif static int __init ipvlan_init_module(void) { int err; ipvlan_init_secret(); register_netdevice_notifier(&ipvlan_notifier_block); #if IS_ENABLED(CONFIG_IPV6) register_inet6addr_notifier(&ipvlan_addr6_notifier_block); register_inet6addr_validator_notifier( &ipvlan_addr6_vtor_notifier_block); #endif register_inetaddr_notifier(&ipvlan_addr4_notifier_block); register_inetaddr_validator_notifier(&ipvlan_addr4_vtor_notifier_block); err = ipvlan_l3s_init(); if (err < 0) goto error; err = ipvlan_link_register(&ipvlan_link_ops); if (err < 0) { ipvlan_l3s_cleanup(); goto error; } return 0; error: unregister_inetaddr_notifier(&ipvlan_addr4_notifier_block); unregister_inetaddr_validator_notifier( &ipvlan_addr4_vtor_notifier_block); #if IS_ENABLED(CONFIG_IPV6) unregister_inet6addr_notifier(&ipvlan_addr6_notifier_block); unregister_inet6addr_validator_notifier( &ipvlan_addr6_vtor_notifier_block); #endif unregister_netdevice_notifier(&ipvlan_notifier_block); return err; } static void __exit ipvlan_cleanup_module(void) { rtnl_link_unregister(&ipvlan_link_ops); ipvlan_l3s_cleanup(); unregister_netdevice_notifier(&ipvlan_notifier_block); unregister_inetaddr_notifier(&ipvlan_addr4_notifier_block); unregister_inetaddr_validator_notifier( &ipvlan_addr4_vtor_notifier_block); #if IS_ENABLED(CONFIG_IPV6) unregister_inet6addr_notifier(&ipvlan_addr6_notifier_block); unregister_inet6addr_validator_notifier( &ipvlan_addr6_vtor_notifier_block); #endif } module_init(ipvlan_init_module); module_exit(ipvlan_cleanup_module); MODULE_LICENSE("GPL"); MODULE_AUTHOR("Mahesh Bandewar <maheshb@google.com>"); MODULE_DESCRIPTION("Driver for L3 (IPv6/IPv4) based VLANs"); MODULE_ALIAS_RTNL_LINK("ipvlan"); |
| 3 3 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 1522 1523 1524 1525 1526 1527 1528 1529 1530 1531 1532 1533 1534 1535 1536 1537 1538 1539 1540 1541 1542 1543 1544 1545 1546 1547 1548 1549 1550 1551 1552 1553 1554 1555 1556 1557 1558 1559 1560 1561 1562 1563 1564 1565 1566 1567 1568 1569 1570 1571 1572 1573 1574 1575 1576 1577 1578 1579 1580 1581 1582 1583 1584 1585 1586 1587 1588 1589 1590 1591 1592 1593 1594 1595 1596 1597 1598 1599 1600 1601 1602 1603 1604 1605 1606 1607 1608 1609 1610 1611 1612 1613 1614 1615 1616 1617 1618 1619 1620 1621 1622 1623 1624 1625 1626 1627 1628 1629 1630 1631 1632 1633 1634 1635 1636 1637 1638 1639 1640 1641 1642 1643 1644 1645 1646 1647 1648 1649 1650 1651 1652 1653 1654 1655 1656 1657 1658 1659 1660 1661 1662 1663 1664 1665 1666 1667 1668 1669 1670 1671 1672 1673 1674 1675 1676 1677 1678 1679 1680 1681 1682 1683 1684 1685 1686 1687 1688 1689 1690 1691 1692 1693 1694 1695 1696 1697 1698 1699 1700 1701 1702 1703 1704 1705 1706 1707 1708 1709 1710 1711 1712 1713 1714 1715 1716 1717 1718 1719 1720 1721 1722 1723 1724 1725 1726 1727 1728 1729 1730 1731 1732 1733 1734 1735 1736 1737 1738 1739 1740 1741 1742 1743 1744 1745 1746 1747 1748 1749 1750 1751 1752 1753 1754 1755 1756 1757 1758 1759 1760 1761 1762 1763 1764 1765 1766 1767 1768 1769 1770 1771 1772 1773 1774 1775 1776 1777 1778 1779 1780 1781 1782 1783 1784 1785 1786 1787 1788 1789 1790 1791 1792 1793 1794 1795 1796 1797 1798 1799 1800 1801 1802 1803 1804 1805 1806 1807 1808 1809 1810 1811 1812 1813 1814 1815 1816 1817 1818 1819 1820 1821 1822 1823 1824 1825 1826 1827 1828 1829 1830 1831 1832 1833 1834 1835 1836 1837 1838 1839 1840 1841 1842 1843 1844 1845 1846 1847 1848 1849 1850 1851 1852 1853 1854 1855 1856 1857 1858 1859 1860 1861 1862 1863 1864 1865 1866 1867 1868 1869 1870 1871 1872 1873 1874 1875 1876 1877 1878 1879 1880 1881 1882 1883 1884 1885 1886 1887 1888 1889 1890 1891 1892 1893 1894 1895 1896 1897 1898 1899 1900 1901 1902 1903 1904 1905 1906 1907 1908 1909 1910 1911 1912 1913 1914 1915 1916 1917 1918 1919 1920 1921 1922 1923 1924 1925 1926 1927 1928 1929 1930 1931 1932 1933 1934 1935 1936 1937 1938 1939 1940 1941 1942 1943 1944 1945 1946 1947 1948 1949 1950 1951 1952 1953 1954 1955 1956 1957 1958 1959 1960 1961 1962 1963 1964 1965 1966 1967 1968 1969 1970 1971 1972 1973 1974 1975 1976 1977 1978 1979 1980 1981 1982 1983 1984 | // SPDX-License-Identifier: GPL-2.0-only /* * GENEVE: Generic Network Virtualization Encapsulation * * Copyright (c) 2015 Red Hat, Inc. */ #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt #include <linux/ethtool.h> #include <linux/kernel.h> #include <linux/module.h> #include <linux/etherdevice.h> #include <linux/hash.h> #include <net/ipv6_stubs.h> #include <net/dst_metadata.h> #include <net/gro_cells.h> #include <net/rtnetlink.h> #include <net/geneve.h> #include <net/gro.h> #include <net/protocol.h> #define GENEVE_NETDEV_VER "0.6" #define GENEVE_N_VID (1u << 24) #define GENEVE_VID_MASK (GENEVE_N_VID - 1) #define VNI_HASH_BITS 10 #define VNI_HASH_SIZE (1<<VNI_HASH_BITS) static bool log_ecn_error = true; module_param(log_ecn_error, bool, 0644); MODULE_PARM_DESC(log_ecn_error, "Log packets received with corrupted ECN"); #define GENEVE_VER 0 #define GENEVE_BASE_HLEN (sizeof(struct udphdr) + sizeof(struct genevehdr)) #define GENEVE_IPV4_HLEN (ETH_HLEN + sizeof(struct iphdr) + GENEVE_BASE_HLEN) #define GENEVE_IPV6_HLEN (ETH_HLEN + sizeof(struct ipv6hdr) + GENEVE_BASE_HLEN) /* per-network namespace private data for this module */ struct geneve_net { struct list_head geneve_list; struct list_head sock_list; }; static unsigned int geneve_net_id; struct geneve_dev_node { struct hlist_node hlist; struct geneve_dev *geneve; }; struct geneve_config { struct ip_tunnel_info info; bool collect_md; bool use_udp6_rx_checksums; bool ttl_inherit; enum ifla_geneve_df df; bool inner_proto_inherit; }; /* Pseudo network device */ struct geneve_dev { struct geneve_dev_node hlist4; /* vni hash table for IPv4 socket */ #if IS_ENABLED(CONFIG_IPV6) struct geneve_dev_node hlist6; /* vni hash table for IPv6 socket */ #endif struct net *net; /* netns for packet i/o */ struct net_device *dev; /* netdev for geneve tunnel */ struct geneve_sock __rcu *sock4; /* IPv4 socket used for geneve tunnel */ #if IS_ENABLED(CONFIG_IPV6) struct geneve_sock __rcu *sock6; /* IPv6 socket used for geneve tunnel */ #endif struct list_head next; /* geneve's per namespace list */ struct gro_cells gro_cells; struct geneve_config cfg; }; struct geneve_sock { bool collect_md; struct list_head list; struct socket *sock; struct rcu_head rcu; int refcnt; struct hlist_head vni_list[VNI_HASH_SIZE]; }; static inline __u32 geneve_net_vni_hash(u8 vni[3]) { __u32 vnid; vnid = (vni[0] << 16) | (vni[1] << 8) | vni[2]; return hash_32(vnid, VNI_HASH_BITS); } static __be64 vni_to_tunnel_id(const __u8 *vni) { #ifdef __BIG_ENDIAN return (vni[0] << 16) | (vni[1] << 8) | vni[2]; #else return (__force __be64)(((__force u64)vni[0] << 40) | ((__force u64)vni[1] << 48) | ((__force u64)vni[2] << 56)); #endif } /* Convert 64 bit tunnel ID to 24 bit VNI. */ static void tunnel_id_to_vni(__be64 tun_id, __u8 *vni) { #ifdef __BIG_ENDIAN vni[0] = (__force __u8)(tun_id >> 16); vni[1] = (__force __u8)(tun_id >> 8); vni[2] = (__force __u8)tun_id; #else vni[0] = (__force __u8)((__force u64)tun_id >> 40); vni[1] = (__force __u8)((__force u64)tun_id >> 48); vni[2] = (__force __u8)((__force u64)tun_id >> 56); #endif } static bool eq_tun_id_and_vni(u8 *tun_id, u8 *vni) { return !memcmp(vni, &tun_id[5], 3); } static sa_family_t geneve_get_sk_family(struct geneve_sock *gs) { return gs->sock->sk->sk_family; } static struct geneve_dev *geneve_lookup(struct geneve_sock *gs, __be32 addr, u8 vni[]) { struct hlist_head *vni_list_head; struct geneve_dev_node *node; __u32 hash; /* Find the device for this VNI */ hash = geneve_net_vni_hash(vni); vni_list_head = &gs->vni_list[hash]; hlist_for_each_entry_rcu(node, vni_list_head, hlist) { if (eq_tun_id_and_vni((u8 *)&node->geneve->cfg.info.key.tun_id, vni) && addr == node->geneve->cfg.info.key.u.ipv4.dst) return node->geneve; } return NULL; } #if IS_ENABLED(CONFIG_IPV6) static struct geneve_dev *geneve6_lookup(struct geneve_sock *gs, struct in6_addr addr6, u8 vni[]) { struct hlist_head *vni_list_head; struct geneve_dev_node *node; __u32 hash; /* Find the device for this VNI */ hash = geneve_net_vni_hash(vni); vni_list_head = &gs->vni_list[hash]; hlist_for_each_entry_rcu(node, vni_list_head, hlist) { if (eq_tun_id_and_vni((u8 *)&node->geneve->cfg.info.key.tun_id, vni) && ipv6_addr_equal(&addr6, &node->geneve->cfg.info.key.u.ipv6.dst)) return node->geneve; } return NULL; } #endif static inline struct genevehdr *geneve_hdr(const struct sk_buff *skb) { return (struct genevehdr *)(udp_hdr(skb) + 1); } static struct geneve_dev *geneve_lookup_skb(struct geneve_sock *gs, struct sk_buff *skb) { static u8 zero_vni[3]; u8 *vni; if (geneve_get_sk_family(gs) == AF_INET) { struct iphdr *iph; __be32 addr; iph = ip_hdr(skb); /* outer IP header... */ if (gs->collect_md) { vni = zero_vni; addr = 0; } else { vni = geneve_hdr(skb)->vni; addr = iph->saddr; } return geneve_lookup(gs, addr, vni); #if IS_ENABLED(CONFIG_IPV6) } else if (geneve_get_sk_family(gs) == AF_INET6) { static struct in6_addr zero_addr6; struct ipv6hdr *ip6h; struct in6_addr addr6; ip6h = ipv6_hdr(skb); /* outer IPv6 header... */ if (gs->collect_md) { vni = zero_vni; addr6 = zero_addr6; } else { vni = geneve_hdr(skb)->vni; addr6 = ip6h->saddr; } return geneve6_lookup(gs, addr6, vni); #endif } return NULL; } /* geneve receive/decap routine */ static void geneve_rx(struct geneve_dev *geneve, struct geneve_sock *gs, struct sk_buff *skb) { struct genevehdr *gnvh = geneve_hdr(skb); struct metadata_dst *tun_dst = NULL; unsigned int len; int nh, err = 0; void *oiph; if (ip_tunnel_collect_metadata() || gs->collect_md) { IP_TUNNEL_DECLARE_FLAGS(flags) = { }; __set_bit(IP_TUNNEL_KEY_BIT, flags); __assign_bit(IP_TUNNEL_OAM_BIT, flags, gnvh->oam); __assign_bit(IP_TUNNEL_CRIT_OPT_BIT, flags, gnvh->critical); tun_dst = udp_tun_rx_dst(skb, geneve_get_sk_family(gs), flags, vni_to_tunnel_id(gnvh->vni), gnvh->opt_len * 4); if (!tun_dst) { DEV_STATS_INC(geneve->dev, rx_dropped); goto drop; } /* Update tunnel dst according to Geneve options. */ ip_tunnel_flags_zero(flags); __set_bit(IP_TUNNEL_GENEVE_OPT_BIT, flags); ip_tunnel_info_opts_set(&tun_dst->u.tun_info, gnvh->options, gnvh->opt_len * 4, flags); } else { /* Drop packets w/ critical options, * since we don't support any... */ if (gnvh->critical) { DEV_STATS_INC(geneve->dev, rx_frame_errors); DEV_STATS_INC(geneve->dev, rx_errors); goto drop; } } if (tun_dst) skb_dst_set(skb, &tun_dst->dst); if (gnvh->proto_type == htons(ETH_P_TEB)) { skb_reset_mac_header(skb); skb->protocol = eth_type_trans(skb, geneve->dev); skb_postpull_rcsum(skb, eth_hdr(skb), ETH_HLEN); /* Ignore packet loops (and multicast echo) */ if (ether_addr_equal(eth_hdr(skb)->h_source, geneve->dev->dev_addr)) { DEV_STATS_INC(geneve->dev, rx_errors); goto drop; } } else { skb_reset_mac_header(skb); skb->dev = geneve->dev; skb->pkt_type = PACKET_HOST; } /* Save offset of outer header relative to skb->head, * because we are going to reset the network header to the inner header * and might change skb->head. */ nh = skb_network_header(skb) - skb->head; skb_reset_network_header(skb); if (!pskb_inet_may_pull(skb)) { DEV_STATS_INC(geneve->dev, rx_length_errors); DEV_STATS_INC(geneve->dev, rx_errors); goto drop; } /* Get the outer header. */ oiph = skb->head + nh; if (geneve_get_sk_family(gs) == AF_INET) err = IP_ECN_decapsulate(oiph, skb); #if IS_ENABLED(CONFIG_IPV6) else err = IP6_ECN_decapsulate(oiph, skb); #endif if (unlikely(err)) { if (log_ecn_error) { if (geneve_get_sk_family(gs) == AF_INET) net_info_ratelimited("non-ECT from %pI4 " "with TOS=%#x\n", &((struct iphdr *)oiph)->saddr, ((struct iphdr *)oiph)->tos); #if IS_ENABLED(CONFIG_IPV6) else net_info_ratelimited("non-ECT from %pI6\n", &((struct ipv6hdr *)oiph)->saddr); #endif } if (err > 1) { DEV_STATS_INC(geneve->dev, rx_frame_errors); DEV_STATS_INC(geneve->dev, rx_errors); goto drop; } } len = skb->len; err = gro_cells_receive(&geneve->gro_cells, skb); if (likely(err == NET_RX_SUCCESS)) dev_sw_netstats_rx_add(geneve->dev, len); return; drop: /* Consume bad packet */ kfree_skb(skb); } /* Setup stats when device is created */ static int geneve_init(struct net_device *dev) { struct geneve_dev *geneve = netdev_priv(dev); int err; err = gro_cells_init(&geneve->gro_cells, dev); if (err) return err; err = dst_cache_init(&geneve->cfg.info.dst_cache, GFP_KERNEL); if (err) { gro_cells_destroy(&geneve->gro_cells); return err; } netdev_lockdep_set_classes(dev); return 0; } static void geneve_uninit(struct net_device *dev) { struct geneve_dev *geneve = netdev_priv(dev); dst_cache_destroy(&geneve->cfg.info.dst_cache); gro_cells_destroy(&geneve->gro_cells); } /* Callback from net/ipv4/udp.c to receive packets */ static int geneve_udp_encap_recv(struct sock *sk, struct sk_buff *skb) { struct genevehdr *geneveh; struct geneve_dev *geneve; struct geneve_sock *gs; __be16 inner_proto; int opts_len; /* Need UDP and Geneve header to be present */ if (unlikely(!pskb_may_pull(skb, GENEVE_BASE_HLEN))) goto drop; /* Return packets with reserved bits set */ geneveh = geneve_hdr(skb); if (unlikely(geneveh->ver != GENEVE_VER)) goto drop; gs = rcu_dereference_sk_user_data(sk); if (!gs) goto drop; geneve = geneve_lookup_skb(gs, skb); if (!geneve) goto drop; inner_proto = geneveh->proto_type; if (unlikely((!geneve->cfg.inner_proto_inherit && inner_proto != htons(ETH_P_TEB)))) { DEV_STATS_INC(geneve->dev, rx_dropped); goto drop; } opts_len = geneveh->opt_len * 4; if (iptunnel_pull_header(skb, GENEVE_BASE_HLEN + opts_len, inner_proto, !net_eq(geneve->net, dev_net(geneve->dev)))) { DEV_STATS_INC(geneve->dev, rx_dropped); goto drop; } geneve_rx(geneve, gs, skb); return 0; drop: /* Consume bad packet */ kfree_skb(skb); return 0; } /* Callback from net/ipv{4,6}/udp.c to check that we have a tunnel for errors */ static int geneve_udp_encap_err_lookup(struct sock *sk, struct sk_buff *skb) { struct genevehdr *geneveh; struct geneve_sock *gs; u8 zero_vni[3] = { 0 }; u8 *vni = zero_vni; if (!pskb_may_pull(skb, skb_transport_offset(skb) + GENEVE_BASE_HLEN)) return -EINVAL; geneveh = geneve_hdr(skb); if (geneveh->ver != GENEVE_VER) return -EINVAL; if (geneveh->proto_type != htons(ETH_P_TEB)) return -EINVAL; gs = rcu_dereference_sk_user_data(sk); if (!gs) return -ENOENT; if (geneve_get_sk_family(gs) == AF_INET) { struct iphdr *iph = ip_hdr(skb); __be32 addr4 = 0; if (!gs->collect_md) { vni = geneve_hdr(skb)->vni; addr4 = iph->daddr; } return geneve_lookup(gs, addr4, vni) ? 0 : -ENOENT; } #if IS_ENABLED(CONFIG_IPV6) if (geneve_get_sk_family(gs) == AF_INET6) { struct ipv6hdr *ip6h = ipv6_hdr(skb); struct in6_addr addr6; memset(&addr6, 0, sizeof(struct in6_addr)); if (!gs->collect_md) { vni = geneve_hdr(skb)->vni; addr6 = ip6h->daddr; } return geneve6_lookup(gs, addr6, vni) ? 0 : -ENOENT; } #endif return -EPFNOSUPPORT; } static struct socket *geneve_create_sock(struct net *net, bool ipv6, __be16 port, bool ipv6_rx_csum) { struct socket *sock; struct udp_port_cfg udp_conf; int err; memset(&udp_conf, 0, sizeof(udp_conf)); if (ipv6) { udp_conf.family = AF_INET6; udp_conf.ipv6_v6only = 1; udp_conf.use_udp6_rx_checksums = ipv6_rx_csum; } else { udp_conf.family = AF_INET; udp_conf.local_ip.s_addr = htonl(INADDR_ANY); } udp_conf.local_udp_port = port; /* Open UDP socket */ err = udp_sock_create(net, &udp_conf, &sock); if (err < 0) return ERR_PTR(err); udp_allow_gso(sock->sk); return sock; } static int geneve_hlen(struct genevehdr *gh) { return sizeof(*gh) + gh->opt_len * 4; } static struct sk_buff *geneve_gro_receive(struct sock *sk, struct list_head *head, struct sk_buff *skb) { struct sk_buff *pp = NULL; struct sk_buff *p; struct genevehdr *gh, *gh2; unsigned int hlen, gh_len, off_gnv; const struct packet_offload *ptype; __be16 type; int flush = 1; off_gnv = skb_gro_offset(skb); hlen = off_gnv + sizeof(*gh); gh = skb_gro_header(skb, hlen, off_gnv); if (unlikely(!gh)) goto out; if (gh->ver != GENEVE_VER || gh->oam) goto out; gh_len = geneve_hlen(gh); hlen = off_gnv + gh_len; if (!skb_gro_may_pull(skb, hlen)) { gh = skb_gro_header_slow(skb, hlen, off_gnv); if (unlikely(!gh)) goto out; } list_for_each_entry(p, head, list) { if (!NAPI_GRO_CB(p)->same_flow) continue; gh2 = (struct genevehdr *)(p->data + off_gnv); if (gh->opt_len != gh2->opt_len || memcmp(gh, gh2, gh_len)) { NAPI_GRO_CB(p)->same_flow = 0; continue; } } skb_gro_pull(skb, gh_len); skb_gro_postpull_rcsum(skb, gh, gh_len); type = gh->proto_type; if (likely(type == htons(ETH_P_TEB))) return call_gro_receive(eth_gro_receive, head, skb); ptype = gro_find_receive_by_type(type); if (!ptype) goto out; pp = call_gro_receive(ptype->callbacks.gro_receive, head, skb); flush = 0; out: skb_gro_flush_final(skb, pp, flush); return pp; } static int geneve_gro_complete(struct sock *sk, struct sk_buff *skb, int nhoff) { struct genevehdr *gh; struct packet_offload *ptype; __be16 type; int gh_len; int err = -ENOSYS; gh = (struct genevehdr *)(skb->data + nhoff); gh_len = geneve_hlen(gh); type = gh->proto_type; /* since skb->encapsulation is set, eth_gro_complete() sets the inner mac header */ if (likely(type == htons(ETH_P_TEB))) return eth_gro_complete(skb, nhoff + gh_len); ptype = gro_find_complete_by_type(type); if (ptype) err = ptype->callbacks.gro_complete(skb, nhoff + gh_len); skb_set_inner_mac_header(skb, nhoff + gh_len); return err; } /* Create new listen socket if needed */ static struct geneve_sock *geneve_socket_create(struct net *net, __be16 port, bool ipv6, bool ipv6_rx_csum) { struct geneve_net *gn = net_generic(net, geneve_net_id); struct geneve_sock *gs; struct socket *sock; struct udp_tunnel_sock_cfg tunnel_cfg; int h; gs = kzalloc(sizeof(*gs), GFP_KERNEL); if (!gs) return ERR_PTR(-ENOMEM); sock = geneve_create_sock(net, ipv6, port, ipv6_rx_csum); if (IS_ERR(sock)) { kfree(gs); return ERR_CAST(sock); } gs->sock = sock; gs->refcnt = 1; for (h = 0; h < VNI_HASH_SIZE; ++h) INIT_HLIST_HEAD(&gs->vni_list[h]); /* Initialize the geneve udp offloads structure */ udp_tunnel_notify_add_rx_port(gs->sock, UDP_TUNNEL_TYPE_GENEVE); /* Mark socket as an encapsulation socket */ memset(&tunnel_cfg, 0, sizeof(tunnel_cfg)); tunnel_cfg.sk_user_data = gs; tunnel_cfg.encap_type = 1; tunnel_cfg.gro_receive = geneve_gro_receive; tunnel_cfg.gro_complete = geneve_gro_complete; tunnel_cfg.encap_rcv = geneve_udp_encap_recv; tunnel_cfg.encap_err_lookup = geneve_udp_encap_err_lookup; tunnel_cfg.encap_destroy = NULL; setup_udp_tunnel_sock(net, sock, &tunnel_cfg); list_add(&gs->list, &gn->sock_list); return gs; } static void __geneve_sock_release(struct geneve_sock *gs) { if (!gs || --gs->refcnt) return; list_del(&gs->list); udp_tunnel_notify_del_rx_port(gs->sock, UDP_TUNNEL_TYPE_GENEVE); udp_tunnel_sock_release(gs->sock); kfree_rcu(gs, rcu); } static void geneve_sock_release(struct geneve_dev *geneve) { struct geneve_sock *gs4 = rtnl_dereference(geneve->sock4); #if IS_ENABLED(CONFIG_IPV6) struct geneve_sock *gs6 = rtnl_dereference(geneve->sock6); rcu_assign_pointer(geneve->sock6, NULL); #endif rcu_assign_pointer(geneve->sock4, NULL); synchronize_net(); __geneve_sock_release(gs4); #if IS_ENABLED(CONFIG_IPV6) __geneve_sock_release(gs6); #endif } static struct geneve_sock *geneve_find_sock(struct geneve_net *gn, sa_family_t family, __be16 dst_port) { struct geneve_sock *gs; list_for_each_entry(gs, &gn->sock_list, list) { if (inet_sk(gs->sock->sk)->inet_sport == dst_port && geneve_get_sk_family(gs) == family) { return gs; } } return NULL; } static int geneve_sock_add(struct geneve_dev *geneve, bool ipv6) { struct net *net = geneve->net; struct geneve_net *gn = net_generic(net, geneve_net_id); struct geneve_dev_node *node; struct geneve_sock *gs; __u8 vni[3]; __u32 hash; gs = geneve_find_sock(gn, ipv6 ? AF_INET6 : AF_INET, geneve->cfg.info.key.tp_dst); if (gs) { gs->refcnt++; goto out; } gs = geneve_socket_create(net, geneve->cfg.info.key.tp_dst, ipv6, geneve->cfg.use_udp6_rx_checksums); if (IS_ERR(gs)) return PTR_ERR(gs); out: gs->collect_md = geneve->cfg.collect_md; #if IS_ENABLED(CONFIG_IPV6) if (ipv6) { rcu_assign_pointer(geneve->sock6, gs); node = &geneve->hlist6; } else #endif { rcu_assign_pointer(geneve->sock4, gs); node = &geneve->hlist4; } node->geneve = geneve; tunnel_id_to_vni(geneve->cfg.info.key.tun_id, vni); hash = geneve_net_vni_hash(vni); hlist_add_head_rcu(&node->hlist, &gs->vni_list[hash]); return 0; } static int geneve_open(struct net_device *dev) { struct geneve_dev *geneve = netdev_priv(dev); bool metadata = geneve->cfg.collect_md; bool ipv4, ipv6; int ret = 0; ipv6 = geneve->cfg.info.mode & IP_TUNNEL_INFO_IPV6 || metadata; ipv4 = !ipv6 || metadata; #if IS_ENABLED(CONFIG_IPV6) if (ipv6) { ret = geneve_sock_add(geneve, true); if (ret < 0 && ret != -EAFNOSUPPORT) ipv4 = false; } #endif if (ipv4) ret = geneve_sock_add(geneve, false); if (ret < 0) geneve_sock_release(geneve); return ret; } static int geneve_stop(struct net_device *dev) { struct geneve_dev *geneve = netdev_priv(dev); hlist_del_init_rcu(&geneve->hlist4.hlist); #if IS_ENABLED(CONFIG_IPV6) hlist_del_init_rcu(&geneve->hlist6.hlist); #endif geneve_sock_release(geneve); return 0; } static void geneve_build_header(struct genevehdr *geneveh, const struct ip_tunnel_info *info, __be16 inner_proto) { geneveh->ver = GENEVE_VER; geneveh->opt_len = info->options_len / 4; geneveh->oam = test_bit(IP_TUNNEL_OAM_BIT, info->key.tun_flags); geneveh->critical = test_bit(IP_TUNNEL_CRIT_OPT_BIT, info->key.tun_flags); geneveh->rsvd1 = 0; tunnel_id_to_vni(info->key.tun_id, geneveh->vni); geneveh->proto_type = inner_proto; geneveh->rsvd2 = 0; if (test_bit(IP_TUNNEL_GENEVE_OPT_BIT, info->key.tun_flags)) ip_tunnel_info_opts_get(geneveh->options, info); } static int geneve_build_skb(struct dst_entry *dst, struct sk_buff *skb, const struct ip_tunnel_info *info, bool xnet, int ip_hdr_len, bool inner_proto_inherit) { bool udp_sum = test_bit(IP_TUNNEL_CSUM_BIT, info->key.tun_flags); struct genevehdr *gnvh; __be16 inner_proto; int min_headroom; int err; skb_reset_mac_header(skb); skb_scrub_packet(skb, xnet); min_headroom = LL_RESERVED_SPACE(dst->dev) + dst->header_len + GENEVE_BASE_HLEN + info->options_len + ip_hdr_len; err = skb_cow_head(skb, min_headroom); if (unlikely(err)) goto free_dst; err = udp_tunnel_handle_offloads(skb, udp_sum); if (err) goto free_dst; gnvh = __skb_push(skb, sizeof(*gnvh) + info->options_len); inner_proto = inner_proto_inherit ? skb->protocol : htons(ETH_P_TEB); geneve_build_header(gnvh, info, inner_proto); skb_set_inner_protocol(skb, inner_proto); return 0; free_dst: dst_release(dst); return err; } static u8 geneve_get_dsfield(struct sk_buff *skb, struct net_device *dev, const struct ip_tunnel_info *info, bool *use_cache) { struct geneve_dev *geneve = netdev_priv(dev); u8 dsfield; dsfield = info->key.tos; if (dsfield == 1 && !geneve->cfg.collect_md) { dsfield = ip_tunnel_get_dsfield(ip_hdr(skb), skb); *use_cache = false; } return dsfield; } static int geneve_xmit_skb(struct sk_buff *skb, struct net_device *dev, struct geneve_dev *geneve, const struct ip_tunnel_info *info) { bool inner_proto_inherit = geneve->cfg.inner_proto_inherit; bool xnet = !net_eq(geneve->net, dev_net(geneve->dev)); struct geneve_sock *gs4 = rcu_dereference(geneve->sock4); const struct ip_tunnel_key *key = &info->key; struct rtable *rt; bool use_cache; __u8 tos, ttl; __be16 df = 0; __be32 saddr; __be16 sport; int err; if (skb_vlan_inet_prepare(skb, inner_proto_inherit)) return -EINVAL; if (!gs4) return -EIO; use_cache = ip_tunnel_dst_cache_usable(skb, info); tos = geneve_get_dsfield(skb, dev, info, &use_cache); sport = udp_flow_src_port(geneve->net, skb, 1, USHRT_MAX, true); rt = udp_tunnel_dst_lookup(skb, dev, geneve->net, 0, &saddr, &info->key, sport, geneve->cfg.info.key.tp_dst, tos, use_cache ? (struct dst_cache *)&info->dst_cache : NULL); if (IS_ERR(rt)) return PTR_ERR(rt); err = skb_tunnel_check_pmtu(skb, &rt->dst, GENEVE_IPV4_HLEN + info->options_len, netif_is_any_bridge_port(dev)); if (err < 0) { dst_release(&rt->dst); return err; } else if (err) { struct ip_tunnel_info *info; info = skb_tunnel_info(skb); if (info) { struct ip_tunnel_info *unclone; unclone = skb_tunnel_info_unclone(skb); if (unlikely(!unclone)) { dst_release(&rt->dst); return -ENOMEM; } unclone->key.u.ipv4.dst = saddr; unclone->key.u.ipv4.src = info->key.u.ipv4.dst; } if (!pskb_may_pull(skb, ETH_HLEN)) { dst_release(&rt->dst); return -EINVAL; } skb->protocol = eth_type_trans(skb, geneve->dev); __netif_rx(skb); dst_release(&rt->dst); return -EMSGSIZE; } tos = ip_tunnel_ecn_encap(tos, ip_hdr(skb), skb); if (geneve->cfg.collect_md) { ttl = key->ttl; df = test_bit(IP_TUNNEL_DONT_FRAGMENT_BIT, key->tun_flags) ? htons(IP_DF) : 0; } else { if (geneve->cfg.ttl_inherit) ttl = ip_tunnel_get_ttl(ip_hdr(skb), skb); else ttl = key->ttl; ttl = ttl ? : ip4_dst_hoplimit(&rt->dst); if (geneve->cfg.df == GENEVE_DF_SET) { df = htons(IP_DF); } else if (geneve->cfg.df == GENEVE_DF_INHERIT) { struct ethhdr *eth = skb_eth_hdr(skb); if (ntohs(eth->h_proto) == ETH_P_IPV6) { df = htons(IP_DF); } else if (ntohs(eth->h_proto) == ETH_P_IP) { struct iphdr *iph = ip_hdr(skb); if (iph->frag_off & htons(IP_DF)) df = htons(IP_DF); } } } err = geneve_build_skb(&rt->dst, skb, info, xnet, sizeof(struct iphdr), inner_proto_inherit); if (unlikely(err)) return err; udp_tunnel_xmit_skb(rt, gs4->sock->sk, skb, saddr, info->key.u.ipv4.dst, tos, ttl, df, sport, geneve->cfg.info.key.tp_dst, !net_eq(geneve->net, dev_net(geneve->dev)), !test_bit(IP_TUNNEL_CSUM_BIT, info->key.tun_flags)); return 0; } #if IS_ENABLED(CONFIG_IPV6) static int geneve6_xmit_skb(struct sk_buff *skb, struct net_device *dev, struct geneve_dev *geneve, const struct ip_tunnel_info *info) { bool inner_proto_inherit = geneve->cfg.inner_proto_inherit; bool xnet = !net_eq(geneve->net, dev_net(geneve->dev)); struct geneve_sock *gs6 = rcu_dereference(geneve->sock6); const struct ip_tunnel_key *key = &info->key; struct dst_entry *dst = NULL; struct in6_addr saddr; bool use_cache; __u8 prio, ttl; __be16 sport; int err; if (skb_vlan_inet_prepare(skb, inner_proto_inherit)) return -EINVAL; if (!gs6) return -EIO; use_cache = ip_tunnel_dst_cache_usable(skb, info); prio = geneve_get_dsfield(skb, dev, info, &use_cache); sport = udp_flow_src_port(geneve->net, skb, 1, USHRT_MAX, true); dst = udp_tunnel6_dst_lookup(skb, dev, geneve->net, gs6->sock, 0, &saddr, key, sport, geneve->cfg.info.key.tp_dst, prio, use_cache ? (struct dst_cache *)&info->dst_cache : NULL); if (IS_ERR(dst)) return PTR_ERR(dst); err = skb_tunnel_check_pmtu(skb, dst, GENEVE_IPV6_HLEN + info->options_len, netif_is_any_bridge_port(dev)); if (err < 0) { dst_release(dst); return err; } else if (err) { struct ip_tunnel_info *info = skb_tunnel_info(skb); if (info) { struct ip_tunnel_info *unclone; unclone = skb_tunnel_info_unclone(skb); if (unlikely(!unclone)) { dst_release(dst); return -ENOMEM; } unclone->key.u.ipv6.dst = saddr; unclone->key.u.ipv6.src = info->key.u.ipv6.dst; } if (!pskb_may_pull(skb, ETH_HLEN)) { dst_release(dst); return -EINVAL; } skb->protocol = eth_type_trans(skb, geneve->dev); __netif_rx(skb); dst_release(dst); return -EMSGSIZE; } prio = ip_tunnel_ecn_encap(prio, ip_hdr(skb), skb); if (geneve->cfg.collect_md) { ttl = key->ttl; } else { if (geneve->cfg.ttl_inherit) ttl = ip_tunnel_get_ttl(ip_hdr(skb), skb); else ttl = key->ttl; ttl = ttl ? : ip6_dst_hoplimit(dst); } err = geneve_build_skb(dst, skb, info, xnet, sizeof(struct ipv6hdr), inner_proto_inherit); if (unlikely(err)) return err; udp_tunnel6_xmit_skb(dst, gs6->sock->sk, skb, dev, &saddr, &key->u.ipv6.dst, prio, ttl, info->key.label, sport, geneve->cfg.info.key.tp_dst, !test_bit(IP_TUNNEL_CSUM_BIT, info->key.tun_flags)); return 0; } #endif static netdev_tx_t geneve_xmit(struct sk_buff *skb, struct net_device *dev) { struct geneve_dev *geneve = netdev_priv(dev); struct ip_tunnel_info *info = NULL; int err; if (geneve->cfg.collect_md) { info = skb_tunnel_info(skb); if (unlikely(!info || !(info->mode & IP_TUNNEL_INFO_TX))) { netdev_dbg(dev, "no tunnel metadata\n"); dev_kfree_skb(skb); DEV_STATS_INC(dev, tx_dropped); return NETDEV_TX_OK; } } else { info = &geneve->cfg.info; } rcu_read_lock(); #if IS_ENABLED(CONFIG_IPV6) if (info->mode & IP_TUNNEL_INFO_IPV6) err = geneve6_xmit_skb(skb, dev, geneve, info); else #endif err = geneve_xmit_skb(skb, dev, geneve, info); rcu_read_unlock(); if (likely(!err)) return NETDEV_TX_OK; if (err != -EMSGSIZE) dev_kfree_skb(skb); if (err == -ELOOP) DEV_STATS_INC(dev, collisions); else if (err == -ENETUNREACH) DEV_STATS_INC(dev, tx_carrier_errors); DEV_STATS_INC(dev, tx_errors); return NETDEV_TX_OK; } static int geneve_change_mtu(struct net_device *dev, int new_mtu) { if (new_mtu > dev->max_mtu) new_mtu = dev->max_mtu; else if (new_mtu < dev->min_mtu) new_mtu = dev->min_mtu; WRITE_ONCE(dev->mtu, new_mtu); return 0; } static int geneve_fill_metadata_dst(struct net_device *dev, struct sk_buff *skb) { struct ip_tunnel_info *info = skb_tunnel_info(skb); struct geneve_dev *geneve = netdev_priv(dev); __be16 sport; if (ip_tunnel_info_af(info) == AF_INET) { struct rtable *rt; struct geneve_sock *gs4 = rcu_dereference(geneve->sock4); bool use_cache; __be32 saddr; u8 tos; if (!gs4) return -EIO; use_cache = ip_tunnel_dst_cache_usable(skb, info); tos = geneve_get_dsfield(skb, dev, info, &use_cache); sport = udp_flow_src_port(geneve->net, skb, 1, USHRT_MAX, true); rt = udp_tunnel_dst_lookup(skb, dev, geneve->net, 0, &saddr, &info->key, sport, geneve->cfg.info.key.tp_dst, tos, use_cache ? &info->dst_cache : NULL); if (IS_ERR(rt)) return PTR_ERR(rt); ip_rt_put(rt); info->key.u.ipv4.src = saddr; #if IS_ENABLED(CONFIG_IPV6) } else if (ip_tunnel_info_af(info) == AF_INET6) { struct dst_entry *dst; struct geneve_sock *gs6 = rcu_dereference(geneve->sock6); struct in6_addr saddr; bool use_cache; u8 prio; if (!gs6) return -EIO; use_cache = ip_tunnel_dst_cache_usable(skb, info); prio = geneve_get_dsfield(skb, dev, info, &use_cache); sport = udp_flow_src_port(geneve->net, skb, 1, USHRT_MAX, true); dst = udp_tunnel6_dst_lookup(skb, dev, geneve->net, gs6->sock, 0, &saddr, &info->key, sport, geneve->cfg.info.key.tp_dst, prio, use_cache ? &info->dst_cache : NULL); if (IS_ERR(dst)) return PTR_ERR(dst); dst_release(dst); info->key.u.ipv6.src = saddr; #endif } else { return -EINVAL; } info->key.tp_src = sport; info->key.tp_dst = geneve->cfg.info.key.tp_dst; return 0; } static const struct net_device_ops geneve_netdev_ops = { .ndo_init = geneve_init, .ndo_uninit = geneve_uninit, .ndo_open = geneve_open, .ndo_stop = geneve_stop, .ndo_start_xmit = geneve_xmit, .ndo_change_mtu = geneve_change_mtu, .ndo_validate_addr = eth_validate_addr, .ndo_set_mac_address = eth_mac_addr, .ndo_fill_metadata_dst = geneve_fill_metadata_dst, }; static void geneve_get_drvinfo(struct net_device *dev, struct ethtool_drvinfo *drvinfo) { strscpy(drvinfo->version, GENEVE_NETDEV_VER, sizeof(drvinfo->version)); strscpy(drvinfo->driver, "geneve", sizeof(drvinfo->driver)); } static const struct ethtool_ops geneve_ethtool_ops = { .get_drvinfo = geneve_get_drvinfo, .get_link = ethtool_op_get_link, }; /* Info for udev, that this is a virtual tunnel endpoint */ static const struct device_type geneve_type = { .name = "geneve", }; /* Calls the ndo_udp_tunnel_add of the caller in order to * supply the listening GENEVE udp ports. Callers are expected * to implement the ndo_udp_tunnel_add. */ static void geneve_offload_rx_ports(struct net_device *dev, bool push) { struct net *net = dev_net(dev); struct geneve_net *gn = net_generic(net, geneve_net_id); struct geneve_sock *gs; rcu_read_lock(); list_for_each_entry_rcu(gs, &gn->sock_list, list) { if (push) { udp_tunnel_push_rx_port(dev, gs->sock, UDP_TUNNEL_TYPE_GENEVE); } else { udp_tunnel_drop_rx_port(dev, gs->sock, UDP_TUNNEL_TYPE_GENEVE); } } rcu_read_unlock(); } /* Initialize the device structure. */ static void geneve_setup(struct net_device *dev) { ether_setup(dev); dev->netdev_ops = &geneve_netdev_ops; dev->ethtool_ops = &geneve_ethtool_ops; dev->needs_free_netdev = true; SET_NETDEV_DEVTYPE(dev, &geneve_type); dev->features |= NETIF_F_SG | NETIF_F_HW_CSUM | NETIF_F_FRAGLIST; dev->features |= NETIF_F_RXCSUM; dev->features |= NETIF_F_GSO_SOFTWARE; dev->hw_features |= NETIF_F_SG | NETIF_F_HW_CSUM | NETIF_F_FRAGLIST; dev->hw_features |= NETIF_F_RXCSUM; dev->hw_features |= NETIF_F_GSO_SOFTWARE; dev->pcpu_stat_type = NETDEV_PCPU_STAT_TSTATS; /* MTU range: 68 - (something less than 65535) */ dev->min_mtu = ETH_MIN_MTU; /* The max_mtu calculation does not take account of GENEVE * options, to avoid excluding potentially valid * configurations. This will be further reduced by IPvX hdr size. */ dev->max_mtu = IP_MAX_MTU - GENEVE_BASE_HLEN - dev->hard_header_len; netif_keep_dst(dev); dev->priv_flags &= ~IFF_TX_SKB_SHARING; dev->priv_flags |= IFF_LIVE_ADDR_CHANGE | IFF_NO_QUEUE; dev->lltx = true; eth_hw_addr_random(dev); } static const struct nla_policy geneve_policy[IFLA_GENEVE_MAX + 1] = { [IFLA_GENEVE_UNSPEC] = { .strict_start_type = IFLA_GENEVE_INNER_PROTO_INHERIT }, [IFLA_GENEVE_ID] = { .type = NLA_U32 }, [IFLA_GENEVE_REMOTE] = { .len = sizeof_field(struct iphdr, daddr) }, [IFLA_GENEVE_REMOTE6] = { .len = sizeof(struct in6_addr) }, [IFLA_GENEVE_TTL] = { .type = NLA_U8 }, [IFLA_GENEVE_TOS] = { .type = NLA_U8 }, [IFLA_GENEVE_LABEL] = { .type = NLA_U32 }, [IFLA_GENEVE_PORT] = { .type = NLA_U16 }, [IFLA_GENEVE_COLLECT_METADATA] = { .type = NLA_FLAG }, [IFLA_GENEVE_UDP_CSUM] = { .type = NLA_U8 }, [IFLA_GENEVE_UDP_ZERO_CSUM6_TX] = { .type = NLA_U8 }, [IFLA_GENEVE_UDP_ZERO_CSUM6_RX] = { .type = NLA_U8 }, [IFLA_GENEVE_TTL_INHERIT] = { .type = NLA_U8 }, [IFLA_GENEVE_DF] = { .type = NLA_U8 }, [IFLA_GENEVE_INNER_PROTO_INHERIT] = { .type = NLA_FLAG }, }; static int geneve_validate(struct nlattr *tb[], struct nlattr *data[], struct netlink_ext_ack *extack) { if (tb[IFLA_ADDRESS]) { if (nla_len(tb[IFLA_ADDRESS]) != ETH_ALEN) { NL_SET_ERR_MSG_ATTR(extack, tb[IFLA_ADDRESS], "Provided link layer address is not Ethernet"); return -EINVAL; } if (!is_valid_ether_addr(nla_data(tb[IFLA_ADDRESS]))) { NL_SET_ERR_MSG_ATTR(extack, tb[IFLA_ADDRESS], "Provided Ethernet address is not unicast"); return -EADDRNOTAVAIL; } } if (!data) { NL_SET_ERR_MSG(extack, "Not enough attributes provided to perform the operation"); return -EINVAL; } if (data[IFLA_GENEVE_ID]) { __u32 vni = nla_get_u32(data[IFLA_GENEVE_ID]); if (vni >= GENEVE_N_VID) { NL_SET_ERR_MSG_ATTR(extack, data[IFLA_GENEVE_ID], "Geneve ID must be lower than 16777216"); return -ERANGE; } } if (data[IFLA_GENEVE_DF]) { enum ifla_geneve_df df = nla_get_u8(data[IFLA_GENEVE_DF]); if (df < 0 || df > GENEVE_DF_MAX) { NL_SET_ERR_MSG_ATTR(extack, data[IFLA_GENEVE_DF], "Invalid DF attribute"); return -EINVAL; } } return 0; } static struct geneve_dev *geneve_find_dev(struct geneve_net *gn, const struct ip_tunnel_info *info, bool *tun_on_same_port, bool *tun_collect_md) { struct geneve_dev *geneve, *t = NULL; *tun_on_same_port = false; *tun_collect_md = false; list_for_each_entry(geneve, &gn->geneve_list, next) { if (info->key.tp_dst == geneve->cfg.info.key.tp_dst) { *tun_collect_md = geneve->cfg.collect_md; *tun_on_same_port = true; } if (info->key.tun_id == geneve->cfg.info.key.tun_id && info->key.tp_dst == geneve->cfg.info.key.tp_dst && !memcmp(&info->key.u, &geneve->cfg.info.key.u, sizeof(info->key.u))) t = geneve; } return t; } static bool is_tnl_info_zero(const struct ip_tunnel_info *info) { return !(info->key.tun_id || info->key.tos || !ip_tunnel_flags_empty(info->key.tun_flags) || info->key.ttl || info->key.label || info->key.tp_src || memchr_inv(&info->key.u, 0, sizeof(info->key.u))); } static bool geneve_dst_addr_equal(struct ip_tunnel_info *a, struct ip_tunnel_info *b) { if (ip_tunnel_info_af(a) == AF_INET) return a->key.u.ipv4.dst == b->key.u.ipv4.dst; else return ipv6_addr_equal(&a->key.u.ipv6.dst, &b->key.u.ipv6.dst); } static int geneve_configure(struct net *net, struct net_device *dev, struct netlink_ext_ack *extack, const struct geneve_config *cfg) { struct geneve_net *gn = net_generic(net, geneve_net_id); struct geneve_dev *t, *geneve = netdev_priv(dev); const struct ip_tunnel_info *info = &cfg->info; bool tun_collect_md, tun_on_same_port; int err, encap_len; if (cfg->collect_md && !is_tnl_info_zero(info)) { NL_SET_ERR_MSG(extack, "Device is externally controlled, so attributes (VNI, Port, and so on) must not be specified"); return -EINVAL; } geneve->net = net; geneve->dev = dev; t = geneve_find_dev(gn, info, &tun_on_same_port, &tun_collect_md); if (t) return -EBUSY; /* make enough headroom for basic scenario */ encap_len = GENEVE_BASE_HLEN + ETH_HLEN; if (!cfg->collect_md && ip_tunnel_info_af(info) == AF_INET) { encap_len += sizeof(struct iphdr); dev->max_mtu -= sizeof(struct iphdr); } else { encap_len += sizeof(struct ipv6hdr); dev->max_mtu -= sizeof(struct ipv6hdr); } dev->needed_headroom = encap_len + ETH_HLEN; if (cfg->collect_md) { if (tun_on_same_port) { NL_SET_ERR_MSG(extack, "There can be only one externally controlled device on a destination port"); return -EPERM; } } else { if (tun_collect_md) { NL_SET_ERR_MSG(extack, "There already exists an externally controlled device on this destination port"); return -EPERM; } } dst_cache_reset(&geneve->cfg.info.dst_cache); memcpy(&geneve->cfg, cfg, sizeof(*cfg)); if (geneve->cfg.inner_proto_inherit) { dev->header_ops = NULL; dev->type = ARPHRD_NONE; dev->hard_header_len = 0; dev->addr_len = 0; dev->flags = IFF_POINTOPOINT | IFF_NOARP; } err = register_netdevice(dev); if (err) return err; list_add(&geneve->next, &gn->geneve_list); return 0; } static void init_tnl_info(struct ip_tunnel_info *info, __u16 dst_port) { memset(info, 0, sizeof(*info)); info->key.tp_dst = htons(dst_port); } static int geneve_nl2info(struct nlattr *tb[], struct nlattr *data[], struct netlink_ext_ack *extack, struct geneve_config *cfg, bool changelink) { struct ip_tunnel_info *info = &cfg->info; int attrtype; if (data[IFLA_GENEVE_REMOTE] && data[IFLA_GENEVE_REMOTE6]) { NL_SET_ERR_MSG(extack, "Cannot specify both IPv4 and IPv6 Remote addresses"); return -EINVAL; } if (data[IFLA_GENEVE_REMOTE]) { if (changelink && (ip_tunnel_info_af(info) == AF_INET6)) { attrtype = IFLA_GENEVE_REMOTE; goto change_notsup; } info->key.u.ipv4.dst = nla_get_in_addr(data[IFLA_GENEVE_REMOTE]); if (ipv4_is_multicast(info->key.u.ipv4.dst)) { NL_SET_ERR_MSG_ATTR(extack, data[IFLA_GENEVE_REMOTE], "Remote IPv4 address cannot be Multicast"); return -EINVAL; } } if (data[IFLA_GENEVE_REMOTE6]) { #if IS_ENABLED(CONFIG_IPV6) if (changelink && (ip_tunnel_info_af(info) == AF_INET)) { attrtype = IFLA_GENEVE_REMOTE6; goto change_notsup; } info->mode = IP_TUNNEL_INFO_IPV6; info->key.u.ipv6.dst = nla_get_in6_addr(data[IFLA_GENEVE_REMOTE6]); if (ipv6_addr_type(&info->key.u.ipv6.dst) & IPV6_ADDR_LINKLOCAL) { NL_SET_ERR_MSG_ATTR(extack, data[IFLA_GENEVE_REMOTE6], "Remote IPv6 address cannot be link-local"); return -EINVAL; } if (ipv6_addr_is_multicast(&info->key.u.ipv6.dst)) { NL_SET_ERR_MSG_ATTR(extack, data[IFLA_GENEVE_REMOTE6], "Remote IPv6 address cannot be Multicast"); return -EINVAL; } __set_bit(IP_TUNNEL_CSUM_BIT, info->key.tun_flags); cfg->use_udp6_rx_checksums = true; #else NL_SET_ERR_MSG_ATTR(extack, data[IFLA_GENEVE_REMOTE6], "IPv6 support not enabled in the kernel"); return -EPFNOSUPPORT; #endif } if (data[IFLA_GENEVE_ID]) { __u32 vni; __u8 tvni[3]; __be64 tunid; vni = nla_get_u32(data[IFLA_GENEVE_ID]); tvni[0] = (vni & 0x00ff0000) >> 16; tvni[1] = (vni & 0x0000ff00) >> 8; tvni[2] = vni & 0x000000ff; tunid = vni_to_tunnel_id(tvni); if (changelink && (tunid != info->key.tun_id)) { attrtype = IFLA_GENEVE_ID; goto change_notsup; } info->key.tun_id = tunid; } if (data[IFLA_GENEVE_TTL_INHERIT]) { if (nla_get_u8(data[IFLA_GENEVE_TTL_INHERIT])) cfg->ttl_inherit = true; else cfg->ttl_inherit = false; } else if (data[IFLA_GENEVE_TTL]) { info->key.ttl = nla_get_u8(data[IFLA_GENEVE_TTL]); cfg->ttl_inherit = false; } if (data[IFLA_GENEVE_TOS]) info->key.tos = nla_get_u8(data[IFLA_GENEVE_TOS]); if (data[IFLA_GENEVE_DF]) cfg->df = nla_get_u8(data[IFLA_GENEVE_DF]); if (data[IFLA_GENEVE_LABEL]) { info->key.label = nla_get_be32(data[IFLA_GENEVE_LABEL]) & IPV6_FLOWLABEL_MASK; if (info->key.label && (!(info->mode & IP_TUNNEL_INFO_IPV6))) { NL_SET_ERR_MSG_ATTR(extack, data[IFLA_GENEVE_LABEL], "Label attribute only applies for IPv6 Geneve devices"); return -EINVAL; } } if (data[IFLA_GENEVE_PORT]) { if (changelink) { attrtype = IFLA_GENEVE_PORT; goto change_notsup; } info->key.tp_dst = nla_get_be16(data[IFLA_GENEVE_PORT]); } if (data[IFLA_GENEVE_COLLECT_METADATA]) { if (changelink) { attrtype = IFLA_GENEVE_COLLECT_METADATA; goto change_notsup; } cfg->collect_md = true; } if (data[IFLA_GENEVE_UDP_CSUM]) { if (changelink) { attrtype = IFLA_GENEVE_UDP_CSUM; goto change_notsup; } if (nla_get_u8(data[IFLA_GENEVE_UDP_CSUM])) __set_bit(IP_TUNNEL_CSUM_BIT, info->key.tun_flags); } if (data[IFLA_GENEVE_UDP_ZERO_CSUM6_TX]) { #if IS_ENABLED(CONFIG_IPV6) if (changelink) { attrtype = IFLA_GENEVE_UDP_ZERO_CSUM6_TX; goto change_notsup; } if (nla_get_u8(data[IFLA_GENEVE_UDP_ZERO_CSUM6_TX])) __clear_bit(IP_TUNNEL_CSUM_BIT, info->key.tun_flags); #else NL_SET_ERR_MSG_ATTR(extack, data[IFLA_GENEVE_UDP_ZERO_CSUM6_TX], "IPv6 support not enabled in the kernel"); return -EPFNOSUPPORT; #endif } if (data[IFLA_GENEVE_UDP_ZERO_CSUM6_RX]) { #if IS_ENABLED(CONFIG_IPV6) if (changelink) { attrtype = IFLA_GENEVE_UDP_ZERO_CSUM6_RX; goto change_notsup; } if (nla_get_u8(data[IFLA_GENEVE_UDP_ZERO_CSUM6_RX])) cfg->use_udp6_rx_checksums = false; #else NL_SET_ERR_MSG_ATTR(extack, data[IFLA_GENEVE_UDP_ZERO_CSUM6_RX], "IPv6 support not enabled in the kernel"); return -EPFNOSUPPORT; #endif } if (data[IFLA_GENEVE_INNER_PROTO_INHERIT]) { if (changelink) { attrtype = IFLA_GENEVE_INNER_PROTO_INHERIT; goto change_notsup; } cfg->inner_proto_inherit = true; } return 0; change_notsup: NL_SET_ERR_MSG_ATTR(extack, data[attrtype], "Changing VNI, Port, endpoint IP address family, external, inner_proto_inherit, and UDP checksum attributes are not supported"); return -EOPNOTSUPP; } static void geneve_link_config(struct net_device *dev, struct ip_tunnel_info *info, struct nlattr *tb[]) { struct geneve_dev *geneve = netdev_priv(dev); int ldev_mtu = 0; if (tb[IFLA_MTU]) { geneve_change_mtu(dev, nla_get_u32(tb[IFLA_MTU])); return; } switch (ip_tunnel_info_af(info)) { case AF_INET: { struct flowi4 fl4 = { .daddr = info->key.u.ipv4.dst }; struct rtable *rt = ip_route_output_key(geneve->net, &fl4); if (!IS_ERR(rt) && rt->dst.dev) { ldev_mtu = rt->dst.dev->mtu - GENEVE_IPV4_HLEN; ip_rt_put(rt); } break; } #if IS_ENABLED(CONFIG_IPV6) case AF_INET6: { struct rt6_info *rt; if (!__in6_dev_get(dev)) break; rt = rt6_lookup(geneve->net, &info->key.u.ipv6.dst, NULL, 0, NULL, 0); if (rt && rt->dst.dev) ldev_mtu = rt->dst.dev->mtu - GENEVE_IPV6_HLEN; ip6_rt_put(rt); break; } #endif } if (ldev_mtu <= 0) return; geneve_change_mtu(dev, ldev_mtu - info->options_len); } static int geneve_newlink(struct net *net, struct net_device *dev, struct nlattr *tb[], struct nlattr *data[], struct netlink_ext_ack *extack) { struct geneve_config cfg = { .df = GENEVE_DF_UNSET, .use_udp6_rx_checksums = false, .ttl_inherit = false, .collect_md = false, }; int err; init_tnl_info(&cfg.info, GENEVE_UDP_PORT); err = geneve_nl2info(tb, data, extack, &cfg, false); if (err) return err; err = geneve_configure(net, dev, extack, &cfg); if (err) return err; geneve_link_config(dev, &cfg.info, tb); return 0; } /* Quiesces the geneve device data path for both TX and RX. * * On transmit geneve checks for non-NULL geneve_sock before it proceeds. * So, if we set that socket to NULL under RCU and wait for synchronize_net() * to complete for the existing set of in-flight packets to be transmitted, * then we would have quiesced the transmit data path. All the future packets * will get dropped until we unquiesce the data path. * * On receive geneve dereference the geneve_sock stashed in the socket. So, * if we set that to NULL under RCU and wait for synchronize_net() to * complete, then we would have quiesced the receive data path. */ static void geneve_quiesce(struct geneve_dev *geneve, struct geneve_sock **gs4, struct geneve_sock **gs6) { *gs4 = rtnl_dereference(geneve->sock4); rcu_assign_pointer(geneve->sock4, NULL); if (*gs4) rcu_assign_sk_user_data((*gs4)->sock->sk, NULL); #if IS_ENABLED(CONFIG_IPV6) *gs6 = rtnl_dereference(geneve->sock6); rcu_assign_pointer(geneve->sock6, NULL); if (*gs6) rcu_assign_sk_user_data((*gs6)->sock->sk, NULL); #else *gs6 = NULL; #endif synchronize_net(); } /* Resumes the geneve device data path for both TX and RX. */ static void geneve_unquiesce(struct geneve_dev *geneve, struct geneve_sock *gs4, struct geneve_sock __maybe_unused *gs6) { rcu_assign_pointer(geneve->sock4, gs4); if (gs4) rcu_assign_sk_user_data(gs4->sock->sk, gs4); #if IS_ENABLED(CONFIG_IPV6) rcu_assign_pointer(geneve->sock6, gs6); if (gs6) rcu_assign_sk_user_data(gs6->sock->sk, gs6); #endif synchronize_net(); } static int geneve_changelink(struct net_device *dev, struct nlattr *tb[], struct nlattr *data[], struct netlink_ext_ack *extack) { struct geneve_dev *geneve = netdev_priv(dev); struct geneve_sock *gs4, *gs6; struct geneve_config cfg; int err; /* If the geneve device is configured for metadata (or externally * controlled, for example, OVS), then nothing can be changed. */ if (geneve->cfg.collect_md) return -EOPNOTSUPP; /* Start with the existing info. */ memcpy(&cfg, &geneve->cfg, sizeof(cfg)); err = geneve_nl2info(tb, data, extack, &cfg, true); if (err) return err; if (!geneve_dst_addr_equal(&geneve->cfg.info, &cfg.info)) { dst_cache_reset(&cfg.info.dst_cache); geneve_link_config(dev, &cfg.info, tb); } geneve_quiesce(geneve, &gs4, &gs6); memcpy(&geneve->cfg, &cfg, sizeof(cfg)); geneve_unquiesce(geneve, gs4, gs6); return 0; } static void geneve_dellink(struct net_device *dev, struct list_head *head) { struct geneve_dev *geneve = netdev_priv(dev); list_del(&geneve->next); unregister_netdevice_queue(dev, head); } static size_t geneve_get_size(const struct net_device *dev) { return nla_total_size(sizeof(__u32)) + /* IFLA_GENEVE_ID */ nla_total_size(sizeof(struct in6_addr)) + /* IFLA_GENEVE_REMOTE{6} */ nla_total_size(sizeof(__u8)) + /* IFLA_GENEVE_TTL */ nla_total_size(sizeof(__u8)) + /* IFLA_GENEVE_TOS */ nla_total_size(sizeof(__u8)) + /* IFLA_GENEVE_DF */ nla_total_size(sizeof(__be32)) + /* IFLA_GENEVE_LABEL */ nla_total_size(sizeof(__be16)) + /* IFLA_GENEVE_PORT */ nla_total_size(0) + /* IFLA_GENEVE_COLLECT_METADATA */ nla_total_size(sizeof(__u8)) + /* IFLA_GENEVE_UDP_CSUM */ nla_total_size(sizeof(__u8)) + /* IFLA_GENEVE_UDP_ZERO_CSUM6_TX */ nla_total_size(sizeof(__u8)) + /* IFLA_GENEVE_UDP_ZERO_CSUM6_RX */ nla_total_size(sizeof(__u8)) + /* IFLA_GENEVE_TTL_INHERIT */ nla_total_size(0) + /* IFLA_GENEVE_INNER_PROTO_INHERIT */ 0; } static int geneve_fill_info(struct sk_buff *skb, const struct net_device *dev) { struct geneve_dev *geneve = netdev_priv(dev); struct ip_tunnel_info *info = &geneve->cfg.info; bool ttl_inherit = geneve->cfg.ttl_inherit; bool metadata = geneve->cfg.collect_md; __u8 tmp_vni[3]; __u32 vni; tunnel_id_to_vni(info->key.tun_id, tmp_vni); vni = (tmp_vni[0] << 16) | (tmp_vni[1] << 8) | tmp_vni[2]; if (nla_put_u32(skb, IFLA_GENEVE_ID, vni)) goto nla_put_failure; if (!metadata && ip_tunnel_info_af(info) == AF_INET) { if (nla_put_in_addr(skb, IFLA_GENEVE_REMOTE, info->key.u.ipv4.dst)) goto nla_put_failure; if (nla_put_u8(skb, IFLA_GENEVE_UDP_CSUM, test_bit(IP_TUNNEL_CSUM_BIT, info->key.tun_flags))) goto nla_put_failure; #if IS_ENABLED(CONFIG_IPV6) } else if (!metadata) { if (nla_put_in6_addr(skb, IFLA_GENEVE_REMOTE6, &info->key.u.ipv6.dst)) goto nla_put_failure; if (nla_put_u8(skb, IFLA_GENEVE_UDP_ZERO_CSUM6_TX, !test_bit(IP_TUNNEL_CSUM_BIT, info->key.tun_flags))) goto nla_put_failure; #endif } if (nla_put_u8(skb, IFLA_GENEVE_TTL, info->key.ttl) || nla_put_u8(skb, IFLA_GENEVE_TOS, info->key.tos) || nla_put_be32(skb, IFLA_GENEVE_LABEL, info->key.label)) goto nla_put_failure; if (nla_put_u8(skb, IFLA_GENEVE_DF, geneve->cfg.df)) goto nla_put_failure; if (nla_put_be16(skb, IFLA_GENEVE_PORT, info->key.tp_dst)) goto nla_put_failure; if (metadata && nla_put_flag(skb, IFLA_GENEVE_COLLECT_METADATA)) goto nla_put_failure; #if IS_ENABLED(CONFIG_IPV6) if (nla_put_u8(skb, IFLA_GENEVE_UDP_ZERO_CSUM6_RX, !geneve->cfg.use_udp6_rx_checksums)) goto nla_put_failure; #endif if (nla_put_u8(skb, IFLA_GENEVE_TTL_INHERIT, ttl_inherit)) goto nla_put_failure; if (geneve->cfg.inner_proto_inherit && nla_put_flag(skb, IFLA_GENEVE_INNER_PROTO_INHERIT)) goto nla_put_failure; return 0; nla_put_failure: return -EMSGSIZE; } static struct rtnl_link_ops geneve_link_ops __read_mostly = { .kind = "geneve", .maxtype = IFLA_GENEVE_MAX, .policy = geneve_policy, .priv_size = sizeof(struct geneve_dev), .setup = geneve_setup, .validate = geneve_validate, .newlink = geneve_newlink, .changelink = geneve_changelink, .dellink = geneve_dellink, .get_size = geneve_get_size, .fill_info = geneve_fill_info, }; struct net_device *geneve_dev_create_fb(struct net *net, const char *name, u8 name_assign_type, u16 dst_port) { struct nlattr *tb[IFLA_MAX + 1]; struct net_device *dev; LIST_HEAD(list_kill); int err; struct geneve_config cfg = { .df = GENEVE_DF_UNSET, .use_udp6_rx_checksums = true, .ttl_inherit = false, .collect_md = true, }; memset(tb, 0, sizeof(tb)); dev = rtnl_create_link(net, name, name_assign_type, &geneve_link_ops, tb, NULL); if (IS_ERR(dev)) return dev; init_tnl_info(&cfg.info, dst_port); err = geneve_configure(net, dev, NULL, &cfg); if (err) { free_netdev(dev); return ERR_PTR(err); } /* openvswitch users expect packet sizes to be unrestricted, * so set the largest MTU we can. */ err = geneve_change_mtu(dev, IP_MAX_MTU); if (err) goto err; err = rtnl_configure_link(dev, NULL, 0, NULL); if (err < 0) goto err; return dev; err: geneve_dellink(dev, &list_kill); unregister_netdevice_many(&list_kill); return ERR_PTR(err); } EXPORT_SYMBOL_GPL(geneve_dev_create_fb); static int geneve_netdevice_event(struct notifier_block *unused, unsigned long event, void *ptr) { struct net_device *dev = netdev_notifier_info_to_dev(ptr); if (event == NETDEV_UDP_TUNNEL_PUSH_INFO) geneve_offload_rx_ports(dev, true); else if (event == NETDEV_UDP_TUNNEL_DROP_INFO) geneve_offload_rx_ports(dev, false); return NOTIFY_DONE; } static struct notifier_block geneve_notifier_block __read_mostly = { .notifier_call = geneve_netdevice_event, }; static __net_init int geneve_init_net(struct net *net) { struct geneve_net *gn = net_generic(net, geneve_net_id); INIT_LIST_HEAD(&gn->geneve_list); INIT_LIST_HEAD(&gn->sock_list); return 0; } static void geneve_destroy_tunnels(struct net *net, struct list_head *head) { struct geneve_net *gn = net_generic(net, geneve_net_id); struct geneve_dev *geneve, *next; struct net_device *dev, *aux; /* gather any geneve devices that were moved into this ns */ for_each_netdev_safe(net, dev, aux) if (dev->rtnl_link_ops == &geneve_link_ops) unregister_netdevice_queue(dev, head); /* now gather any other geneve devices that were created in this ns */ list_for_each_entry_safe(geneve, next, &gn->geneve_list, next) { /* If geneve->dev is in the same netns, it was already added * to the list by the previous loop. */ if (!net_eq(dev_net(geneve->dev), net)) unregister_netdevice_queue(geneve->dev, head); } } static void __net_exit geneve_exit_batch_rtnl(struct list_head *net_list, struct list_head *dev_to_kill) { struct net *net; list_for_each_entry(net, net_list, exit_list) geneve_destroy_tunnels(net, dev_to_kill); } static void __net_exit geneve_exit_net(struct net *net) { const struct geneve_net *gn = net_generic(net, geneve_net_id); WARN_ON_ONCE(!list_empty(&gn->sock_list)); } static struct pernet_operations geneve_net_ops = { .init = geneve_init_net, .exit_batch_rtnl = geneve_exit_batch_rtnl, .exit = geneve_exit_net, .id = &geneve_net_id, .size = sizeof(struct geneve_net), }; static int __init geneve_init_module(void) { int rc; rc = register_pernet_subsys(&geneve_net_ops); if (rc) goto out1; rc = register_netdevice_notifier(&geneve_notifier_block); if (rc) goto out2; rc = rtnl_link_register(&geneve_link_ops); if (rc) goto out3; return 0; out3: unregister_netdevice_notifier(&geneve_notifier_block); out2: unregister_pernet_subsys(&geneve_net_ops); out1: return rc; } late_initcall(geneve_init_module); static void __exit geneve_cleanup_module(void) { rtnl_link_unregister(&geneve_link_ops); unregister_netdevice_notifier(&geneve_notifier_block); unregister_pernet_subsys(&geneve_net_ops); } module_exit(geneve_cleanup_module); MODULE_LICENSE("GPL"); MODULE_VERSION(GENEVE_NETDEV_VER); MODULE_AUTHOR("John W. Linville <linville@tuxdriver.com>"); MODULE_DESCRIPTION("Interface driver for GENEVE encapsulated traffic"); MODULE_ALIAS_RTNL_LINK("geneve"); |
| 137 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _LINUX_TIME64_H #define _LINUX_TIME64_H #include <linux/math64.h> #include <vdso/time64.h> typedef __s64 time64_t; typedef __u64 timeu64_t; #include <uapi/linux/time.h> struct timespec64 { time64_t tv_sec; /* seconds */ long tv_nsec; /* nanoseconds */ }; struct itimerspec64 { struct timespec64 it_interval; struct timespec64 it_value; }; /* Parameters used to convert the timespec values: */ #define PSEC_PER_NSEC 1000L /* Located here for timespec[64]_valid_strict */ #define TIME64_MAX ((s64)~((u64)1 << 63)) #define TIME64_MIN (-TIME64_MAX - 1) #define KTIME_MAX ((s64)~((u64)1 << 63)) #define KTIME_MIN (-KTIME_MAX - 1) #define KTIME_SEC_MAX (KTIME_MAX / NSEC_PER_SEC) #define KTIME_SEC_MIN (KTIME_MIN / NSEC_PER_SEC) /* * Limits for settimeofday(): * * To prevent setting the time close to the wraparound point time setting * is limited so a reasonable uptime can be accomodated. Uptime of 30 years * should be really sufficient, which means the cutoff is 2232. At that * point the cutoff is just a small part of the larger problem. */ #define TIME_UPTIME_SEC_MAX (30LL * 365 * 24 *3600) #define TIME_SETTOD_SEC_MAX (KTIME_SEC_MAX - TIME_UPTIME_SEC_MAX) static inline int timespec64_equal(const struct timespec64 *a, const struct timespec64 *b) { return (a->tv_sec == b->tv_sec) && (a->tv_nsec == b->tv_nsec); } /* * lhs < rhs: return <0 * lhs == rhs: return 0 * lhs > rhs: return >0 */ static inline int timespec64_compare(const struct timespec64 *lhs, const struct timespec64 *rhs) { if (lhs->tv_sec < rhs->tv_sec) return -1; if (lhs->tv_sec > rhs->tv_sec) return 1; return lhs->tv_nsec - rhs->tv_nsec; } extern void set_normalized_timespec64(struct timespec64 *ts, time64_t sec, s64 nsec); static inline struct timespec64 timespec64_add(struct timespec64 lhs, struct timespec64 rhs) { struct timespec64 ts_delta; set_normalized_timespec64(&ts_delta, lhs.tv_sec + rhs.tv_sec, lhs.tv_nsec + rhs.tv_nsec); return ts_delta; } /* * sub = lhs - rhs, in normalized form */ static inline struct timespec64 timespec64_sub(struct timespec64 lhs, struct timespec64 rhs) { struct timespec64 ts_delta; set_normalized_timespec64(&ts_delta, lhs.tv_sec - rhs.tv_sec, lhs.tv_nsec - rhs.tv_nsec); return ts_delta; } /* * Returns true if the timespec64 is norm, false if denorm: */ static inline bool timespec64_valid(const struct timespec64 *ts) { /* Dates before 1970 are bogus */ if (ts->tv_sec < 0) return false; /* Can't have more nanoseconds then a second */ if ((unsigned long)ts->tv_nsec >= NSEC_PER_SEC) return false; return true; } static inline bool timespec64_valid_strict(const struct timespec64 *ts) { if (!timespec64_valid(ts)) return false; /* Disallow values that could overflow ktime_t */ if ((unsigned long long)ts->tv_sec >= KTIME_SEC_MAX) return false; return true; } static inline bool timespec64_valid_settod(const struct timespec64 *ts) { if (!timespec64_valid(ts)) return false; /* Disallow values which cause overflow issues vs. CLOCK_REALTIME */ if ((unsigned long long)ts->tv_sec >= TIME_SETTOD_SEC_MAX) return false; return true; } /** * timespec64_to_ns - Convert timespec64 to nanoseconds * @ts: pointer to the timespec64 variable to be converted * * Returns the scalar nanosecond representation of the timespec64 * parameter. */ static inline s64 timespec64_to_ns(const struct timespec64 *ts) { /* Prevent multiplication overflow / underflow */ if (ts->tv_sec >= KTIME_SEC_MAX) return KTIME_MAX; if (ts->tv_sec <= KTIME_SEC_MIN) return KTIME_MIN; return ((s64) ts->tv_sec * NSEC_PER_SEC) + ts->tv_nsec; } /** * ns_to_timespec64 - Convert nanoseconds to timespec64 * @nsec: the nanoseconds value to be converted * * Returns the timespec64 representation of the nsec parameter. */ extern struct timespec64 ns_to_timespec64(s64 nsec); /** * timespec64_add_ns - Adds nanoseconds to a timespec64 * @a: pointer to timespec64 to be incremented * @ns: unsigned nanoseconds value to be added * * This must always be inlined because its used from the x86-64 vdso, * which cannot call other kernel functions. */ static __always_inline void timespec64_add_ns(struct timespec64 *a, u64 ns) { a->tv_sec += __iter_div_u64_rem(a->tv_nsec + ns, NSEC_PER_SEC, &ns); a->tv_nsec = ns; } /* * timespec64_add_safe assumes both values are positive and checks for * overflow. It will return TIME64_MAX in case of overflow. */ extern struct timespec64 timespec64_add_safe(const struct timespec64 lhs, const struct timespec64 rhs); #endif /* _LINUX_TIME64_H */ |
| 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef __ASM_CURRENT_H #define __ASM_CURRENT_H #include <linux/compiler.h> #ifndef __ASSEMBLY__ struct task_struct; /* * We don't use read_sysreg() as we want the compiler to cache the value where * possible. */ static __always_inline struct task_struct *get_current(void) { unsigned long sp_el0; asm ("mrs %0, sp_el0" : "=r" (sp_el0)); return (struct task_struct *)sp_el0; } #define current get_current() #endif /* __ASSEMBLY__ */ #endif /* __ASM_CURRENT_H */ |
| 93 112 113 56 43 56 43 20 23 10 14 48 12 20 71 38 40 94 86 46 46 46 46 46 45 46 46 46 46 45 76 76 7 179 179 76 76 76 76 57 7 58 48 61 60 60 93 35 59 48 48 48 47 47 47 47 47 47 47 47 47 48 47 42 5 6 48 48 48 46 48 48 48 47 48 48 76 76 47 31 31 31 6 6 31 31 31 31 31 8 23 23 31 31 72 48 31 31 31 72 48 31 31 48 48 10 6 42 48 58 58 1 57 57 58 58 179 174 179 40 7 40 7 47 47 47 40 7 7 76 76 41 38 3 31 23 23 23 23 23 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 1522 1523 1524 1525 1526 1527 1528 1529 1530 1531 1532 1533 1534 1535 1536 1537 1538 1539 1540 1541 1542 1543 1544 1545 1546 1547 1548 1549 1550 1551 1552 1553 1554 1555 1556 1557 1558 1559 1560 1561 1562 1563 1564 1565 1566 1567 1568 1569 1570 1571 1572 1573 1574 1575 1576 1577 1578 1579 1580 1581 1582 1583 1584 1585 1586 1587 1588 1589 1590 1591 1592 1593 1594 1595 1596 1597 1598 1599 1600 1601 1602 1603 1604 1605 1606 1607 1608 1609 1610 1611 1612 1613 1614 1615 1616 1617 1618 1619 1620 1621 1622 1623 1624 1625 1626 1627 1628 1629 1630 1631 1632 1633 1634 1635 1636 1637 1638 1639 1640 1641 1642 1643 1644 1645 1646 1647 1648 1649 1650 1651 1652 1653 1654 1655 1656 1657 1658 1659 1660 1661 1662 1663 1664 1665 1666 1667 1668 1669 1670 1671 1672 1673 1674 1675 1676 1677 1678 1679 1680 1681 1682 1683 1684 1685 1686 1687 1688 1689 1690 1691 1692 1693 1694 1695 1696 1697 1698 1699 1700 1701 1702 1703 1704 1705 1706 1707 1708 1709 1710 1711 1712 1713 1714 1715 1716 1717 1718 1719 1720 1721 1722 1723 1724 1725 1726 1727 1728 1729 1730 1731 1732 1733 1734 1735 1736 1737 1738 1739 1740 1741 1742 1743 1744 1745 1746 1747 1748 1749 1750 1751 1752 1753 1754 1755 1756 1757 1758 1759 1760 1761 1762 1763 1764 1765 1766 1767 1768 1769 1770 1771 1772 1773 1774 1775 1776 1777 1778 1779 1780 1781 1782 1783 1784 1785 1786 1787 1788 1789 1790 1791 1792 1793 1794 1795 1796 1797 1798 1799 1800 1801 1802 1803 1804 1805 1806 1807 1808 1809 1810 1811 1812 1813 1814 1815 1816 1817 1818 1819 1820 1821 1822 1823 1824 1825 1826 1827 1828 1829 1830 1831 1832 1833 1834 1835 1836 1837 1838 1839 1840 1841 1842 1843 1844 1845 1846 1847 1848 1849 1850 1851 1852 1853 1854 1855 1856 1857 1858 1859 1860 1861 1862 1863 1864 1865 1866 1867 1868 1869 1870 1871 1872 1873 1874 1875 1876 1877 1878 1879 1880 1881 1882 1883 1884 1885 1886 1887 1888 1889 1890 1891 1892 1893 1894 1895 1896 1897 1898 1899 1900 1901 1902 1903 1904 1905 1906 1907 1908 1909 1910 1911 1912 1913 1914 1915 1916 1917 1918 1919 1920 1921 1922 1923 1924 1925 1926 1927 1928 1929 1930 1931 1932 1933 1934 1935 1936 1937 1938 1939 1940 1941 1942 1943 1944 1945 1946 1947 1948 1949 1950 1951 1952 1953 1954 1955 1956 1957 1958 1959 1960 1961 1962 1963 1964 1965 1966 1967 1968 1969 1970 1971 1972 1973 1974 1975 1976 1977 1978 1979 1980 1981 1982 1983 1984 1985 1986 1987 1988 1989 1990 1991 1992 1993 1994 1995 1996 1997 1998 1999 2000 2001 2002 2003 2004 2005 2006 2007 2008 2009 2010 2011 2012 2013 2014 2015 2016 2017 2018 2019 2020 2021 2022 2023 2024 2025 2026 2027 2028 2029 2030 2031 2032 2033 2034 2035 2036 2037 2038 2039 2040 2041 2042 2043 2044 2045 2046 2047 2048 2049 2050 2051 2052 2053 2054 2055 2056 2057 2058 2059 2060 2061 2062 2063 2064 2065 2066 2067 2068 2069 2070 2071 2072 2073 2074 2075 2076 2077 2078 2079 2080 2081 2082 2083 2084 2085 2086 2087 2088 2089 2090 2091 2092 2093 2094 2095 2096 2097 2098 2099 2100 2101 2102 2103 2104 2105 2106 2107 2108 2109 2110 2111 2112 2113 2114 2115 2116 2117 2118 2119 2120 2121 2122 2123 2124 2125 2126 2127 2128 2129 2130 2131 2132 2133 2134 2135 2136 2137 2138 2139 2140 2141 2142 2143 2144 2145 2146 2147 2148 2149 2150 2151 2152 2153 2154 2155 2156 2157 2158 2159 2160 2161 2162 2163 2164 2165 2166 2167 2168 2169 2170 2171 2172 2173 2174 2175 2176 2177 2178 2179 2180 2181 2182 2183 2184 2185 2186 2187 2188 2189 2190 2191 2192 2193 2194 2195 2196 2197 2198 2199 2200 2201 2202 2203 2204 2205 2206 2207 2208 2209 2210 2211 2212 2213 2214 2215 2216 2217 2218 2219 2220 2221 2222 2223 2224 2225 2226 2227 2228 2229 2230 2231 2232 2233 2234 2235 2236 2237 2238 2239 2240 2241 2242 2243 2244 2245 2246 2247 2248 2249 2250 2251 2252 2253 2254 2255 2256 2257 2258 2259 2260 2261 2262 2263 2264 2265 2266 2267 2268 2269 2270 2271 2272 2273 2274 2275 2276 2277 2278 2279 2280 2281 2282 2283 2284 2285 2286 2287 2288 2289 2290 2291 2292 2293 2294 2295 2296 2297 2298 2299 2300 2301 2302 2303 2304 2305 2306 2307 2308 2309 2310 2311 2312 2313 2314 2315 2316 2317 2318 2319 2320 2321 2322 2323 2324 2325 2326 2327 2328 2329 2330 2331 2332 2333 2334 2335 2336 2337 2338 2339 2340 2341 2342 2343 2344 2345 2346 2347 2348 2349 2350 2351 2352 2353 2354 2355 2356 2357 2358 2359 2360 2361 2362 2363 2364 2365 2366 2367 2368 2369 2370 2371 2372 2373 2374 2375 2376 2377 2378 2379 2380 2381 2382 2383 2384 2385 2386 2387 2388 2389 2390 2391 2392 2393 2394 2395 2396 2397 2398 2399 2400 2401 2402 2403 2404 2405 2406 2407 2408 2409 2410 2411 2412 2413 2414 2415 2416 2417 2418 2419 2420 2421 2422 2423 2424 2425 2426 2427 2428 2429 2430 2431 2432 2433 2434 2435 2436 2437 2438 2439 2440 2441 2442 2443 2444 2445 2446 2447 2448 2449 2450 2451 2452 2453 2454 2455 2456 2457 2458 2459 2460 2461 2462 2463 2464 2465 2466 2467 2468 2469 2470 2471 2472 2473 2474 2475 2476 2477 2478 2479 2480 2481 2482 2483 2484 2485 2486 2487 2488 2489 2490 2491 2492 2493 2494 2495 2496 2497 2498 2499 2500 2501 2502 2503 2504 2505 2506 2507 2508 2509 2510 2511 2512 2513 2514 2515 2516 2517 2518 2519 2520 2521 2522 2523 2524 2525 2526 2527 2528 2529 2530 2531 2532 2533 2534 2535 2536 2537 2538 2539 2540 2541 2542 2543 2544 2545 2546 2547 2548 2549 2550 2551 2552 2553 2554 2555 2556 2557 2558 2559 2560 2561 2562 2563 2564 2565 2566 2567 2568 2569 2570 2571 2572 2573 2574 2575 2576 2577 2578 2579 2580 2581 2582 2583 2584 2585 2586 2587 2588 2589 2590 2591 2592 2593 2594 2595 2596 2597 2598 2599 2600 2601 2602 2603 2604 2605 2606 2607 2608 2609 2610 2611 2612 2613 2614 2615 2616 2617 2618 2619 2620 2621 2622 2623 2624 2625 2626 2627 2628 2629 2630 2631 2632 2633 2634 2635 2636 2637 2638 2639 2640 2641 2642 2643 2644 2645 2646 2647 2648 2649 2650 2651 2652 2653 2654 2655 2656 2657 2658 2659 2660 2661 2662 2663 2664 2665 2666 2667 2668 2669 2670 2671 2672 2673 2674 2675 2676 2677 2678 2679 2680 2681 2682 2683 2684 2685 2686 2687 2688 2689 2690 2691 2692 2693 2694 2695 2696 2697 2698 2699 2700 2701 2702 2703 2704 2705 2706 2707 2708 2709 2710 2711 2712 2713 2714 2715 2716 2717 2718 2719 2720 2721 2722 2723 2724 2725 2726 2727 2728 2729 2730 2731 2732 2733 2734 2735 2736 2737 2738 2739 2740 2741 2742 2743 2744 2745 2746 2747 2748 2749 2750 2751 2752 2753 2754 2755 2756 2757 2758 2759 2760 2761 2762 2763 2764 2765 2766 2767 2768 2769 2770 2771 2772 2773 2774 2775 2776 2777 2778 2779 2780 2781 2782 2783 2784 2785 2786 2787 2788 2789 2790 2791 2792 2793 2794 2795 2796 2797 2798 2799 2800 2801 2802 2803 2804 2805 2806 2807 2808 2809 2810 2811 2812 2813 2814 2815 2816 2817 2818 2819 2820 2821 2822 2823 2824 2825 2826 2827 2828 2829 2830 2831 2832 2833 2834 2835 2836 2837 2838 2839 2840 2841 2842 2843 2844 2845 2846 2847 2848 2849 2850 2851 2852 2853 2854 2855 2856 2857 2858 2859 2860 2861 2862 2863 2864 2865 2866 2867 2868 2869 2870 2871 2872 2873 2874 2875 2876 2877 2878 2879 2880 2881 2882 2883 2884 2885 2886 2887 2888 2889 2890 2891 2892 2893 2894 2895 2896 2897 2898 2899 2900 2901 2902 2903 2904 2905 2906 2907 2908 2909 2910 2911 2912 2913 2914 2915 2916 2917 2918 2919 2920 2921 2922 2923 2924 2925 2926 2927 2928 2929 2930 2931 2932 2933 2934 2935 2936 2937 2938 2939 2940 2941 2942 2943 2944 2945 2946 2947 2948 2949 2950 2951 2952 2953 2954 2955 2956 2957 2958 2959 2960 2961 2962 2963 2964 2965 2966 2967 2968 2969 2970 2971 2972 2973 2974 2975 2976 2977 2978 2979 2980 2981 2982 2983 2984 2985 2986 2987 2988 2989 2990 2991 2992 2993 2994 2995 2996 2997 2998 2999 3000 3001 3002 3003 3004 3005 3006 3007 3008 3009 3010 3011 3012 3013 3014 3015 3016 3017 3018 3019 3020 3021 3022 3023 3024 3025 3026 3027 3028 3029 3030 3031 3032 3033 3034 3035 3036 3037 3038 3039 3040 3041 3042 3043 3044 3045 3046 3047 3048 3049 3050 3051 3052 3053 3054 3055 3056 3057 3058 3059 3060 3061 3062 3063 3064 3065 3066 3067 3068 3069 3070 3071 3072 3073 3074 3075 3076 3077 3078 3079 3080 3081 3082 3083 3084 3085 3086 3087 3088 3089 3090 3091 3092 3093 3094 3095 3096 3097 3098 3099 3100 3101 3102 3103 3104 3105 3106 3107 3108 3109 3110 3111 3112 3113 3114 3115 3116 3117 3118 3119 3120 3121 3122 3123 3124 3125 3126 3127 3128 3129 3130 3131 3132 3133 3134 3135 3136 3137 3138 3139 3140 3141 3142 3143 3144 3145 3146 3147 3148 3149 3150 3151 3152 3153 3154 3155 3156 3157 3158 3159 3160 3161 3162 3163 3164 3165 3166 3167 3168 3169 3170 3171 3172 3173 3174 3175 3176 3177 3178 3179 3180 3181 3182 3183 3184 3185 3186 3187 3188 3189 3190 3191 3192 3193 3194 3195 3196 3197 3198 3199 3200 3201 3202 3203 3204 3205 3206 3207 3208 3209 3210 3211 3212 3213 3214 3215 3216 3217 3218 3219 3220 3221 3222 3223 3224 3225 3226 3227 3228 3229 3230 3231 3232 3233 3234 3235 3236 3237 3238 3239 3240 3241 3242 3243 3244 3245 3246 3247 3248 3249 3250 3251 3252 3253 3254 3255 3256 3257 3258 3259 3260 3261 3262 3263 3264 3265 3266 3267 3268 3269 3270 3271 3272 3273 3274 3275 3276 3277 3278 3279 3280 3281 3282 3283 3284 3285 3286 3287 3288 3289 3290 3291 3292 3293 3294 3295 3296 3297 3298 3299 3300 3301 3302 3303 3304 3305 3306 3307 3308 3309 3310 3311 3312 3313 3314 3315 3316 3317 3318 3319 3320 3321 3322 3323 3324 3325 3326 3327 3328 3329 3330 3331 3332 3333 3334 3335 3336 3337 3338 3339 3340 3341 3342 3343 3344 3345 3346 3347 3348 3349 3350 3351 3352 3353 3354 3355 3356 3357 3358 3359 3360 3361 3362 3363 3364 3365 3366 3367 3368 3369 3370 3371 3372 3373 3374 3375 3376 3377 3378 3379 3380 3381 3382 3383 3384 3385 3386 3387 3388 3389 3390 3391 3392 3393 3394 3395 3396 3397 3398 3399 3400 3401 3402 3403 3404 3405 3406 3407 3408 3409 3410 3411 3412 3413 3414 3415 3416 3417 3418 3419 3420 3421 3422 3423 3424 3425 3426 3427 3428 3429 3430 3431 3432 3433 3434 3435 3436 3437 3438 3439 3440 3441 3442 3443 3444 3445 3446 3447 3448 3449 3450 3451 3452 3453 3454 3455 3456 3457 3458 3459 3460 3461 3462 3463 3464 3465 3466 3467 3468 3469 3470 3471 3472 3473 3474 3475 3476 3477 3478 3479 3480 3481 3482 3483 3484 3485 3486 3487 3488 3489 3490 3491 3492 3493 3494 3495 3496 3497 3498 3499 3500 3501 3502 3503 3504 3505 3506 3507 3508 3509 3510 3511 3512 3513 3514 3515 3516 3517 3518 3519 3520 3521 3522 3523 3524 3525 3526 3527 3528 3529 3530 3531 3532 3533 3534 3535 3536 3537 3538 3539 3540 3541 3542 3543 3544 3545 3546 3547 3548 3549 3550 3551 3552 3553 3554 3555 3556 3557 3558 3559 3560 3561 3562 3563 3564 3565 3566 3567 3568 3569 3570 3571 3572 3573 3574 3575 3576 3577 3578 3579 3580 3581 3582 3583 3584 3585 3586 3587 3588 3589 3590 3591 3592 3593 3594 3595 3596 3597 3598 3599 3600 3601 3602 3603 3604 3605 3606 3607 3608 3609 3610 3611 3612 3613 3614 3615 3616 3617 3618 3619 3620 3621 3622 3623 3624 3625 3626 3627 3628 3629 3630 3631 3632 3633 3634 3635 3636 3637 3638 3639 3640 3641 3642 3643 3644 3645 3646 3647 3648 3649 3650 3651 3652 3653 3654 3655 3656 3657 3658 3659 3660 3661 3662 3663 3664 3665 3666 3667 3668 3669 3670 3671 3672 3673 3674 3675 3676 3677 3678 3679 3680 3681 3682 3683 3684 3685 3686 3687 3688 3689 3690 3691 3692 3693 3694 3695 3696 3697 3698 3699 3700 3701 3702 3703 3704 3705 3706 3707 3708 3709 3710 3711 3712 3713 3714 3715 3716 3717 3718 3719 3720 3721 3722 3723 3724 3725 3726 3727 3728 3729 3730 3731 3732 3733 3734 3735 3736 3737 3738 3739 3740 3741 3742 3743 3744 3745 3746 3747 3748 3749 3750 3751 3752 3753 3754 3755 3756 3757 3758 3759 3760 3761 3762 3763 3764 3765 3766 3767 3768 3769 3770 3771 3772 3773 3774 3775 3776 3777 3778 3779 3780 3781 3782 3783 3784 3785 3786 3787 3788 3789 3790 3791 3792 3793 3794 3795 3796 3797 3798 3799 3800 3801 3802 3803 3804 3805 3806 3807 3808 3809 3810 3811 3812 3813 3814 3815 3816 3817 3818 3819 3820 3821 3822 3823 3824 3825 3826 3827 3828 3829 3830 3831 3832 3833 3834 3835 3836 3837 3838 3839 3840 3841 3842 3843 3844 3845 3846 3847 3848 3849 3850 3851 3852 3853 3854 3855 3856 3857 3858 3859 3860 3861 3862 3863 3864 3865 3866 3867 3868 3869 3870 3871 3872 3873 3874 3875 3876 3877 3878 3879 3880 3881 3882 3883 3884 3885 3886 3887 3888 3889 3890 3891 3892 3893 3894 3895 3896 3897 3898 3899 3900 3901 3902 3903 3904 3905 3906 3907 3908 3909 3910 3911 3912 3913 3914 3915 3916 3917 3918 3919 3920 3921 3922 3923 3924 3925 3926 3927 3928 3929 3930 3931 3932 3933 3934 3935 3936 3937 3938 3939 3940 3941 3942 3943 3944 3945 3946 3947 3948 3949 3950 3951 3952 3953 3954 3955 3956 3957 3958 3959 3960 3961 3962 3963 3964 3965 3966 3967 3968 3969 3970 3971 3972 3973 3974 3975 3976 3977 3978 3979 3980 3981 3982 3983 3984 3985 3986 3987 3988 3989 3990 3991 3992 3993 3994 3995 3996 3997 3998 3999 4000 4001 4002 4003 4004 4005 4006 4007 4008 4009 4010 4011 4012 4013 4014 4015 4016 4017 4018 4019 4020 4021 4022 4023 4024 4025 4026 4027 4028 4029 4030 4031 4032 4033 4034 4035 4036 4037 4038 4039 4040 4041 4042 4043 4044 4045 4046 4047 4048 4049 4050 4051 4052 4053 4054 4055 4056 4057 4058 4059 4060 4061 4062 4063 4064 4065 4066 4067 4068 4069 4070 4071 4072 4073 4074 4075 4076 4077 4078 4079 4080 4081 4082 4083 4084 4085 4086 4087 4088 4089 4090 4091 4092 4093 4094 4095 4096 4097 4098 4099 4100 4101 4102 4103 4104 4105 4106 4107 4108 4109 4110 4111 4112 4113 4114 4115 4116 4117 4118 4119 4120 4121 4122 4123 4124 4125 4126 4127 4128 4129 4130 4131 4132 4133 4134 4135 4136 4137 4138 4139 4140 4141 4142 4143 4144 4145 4146 4147 4148 4149 4150 4151 4152 4153 4154 4155 4156 4157 4158 4159 4160 4161 4162 4163 4164 4165 4166 4167 4168 4169 4170 4171 4172 4173 4174 4175 4176 4177 4178 4179 4180 4181 4182 4183 4184 4185 4186 4187 4188 4189 4190 4191 4192 4193 4194 4195 4196 4197 4198 4199 4200 4201 4202 4203 4204 4205 4206 4207 4208 4209 4210 4211 4212 4213 4214 4215 4216 4217 4218 4219 4220 4221 4222 4223 4224 4225 4226 4227 4228 4229 4230 4231 4232 4233 4234 4235 4236 4237 4238 4239 4240 4241 4242 4243 4244 4245 4246 4247 4248 4249 4250 4251 4252 4253 4254 4255 4256 4257 4258 4259 4260 4261 4262 4263 4264 4265 4266 4267 4268 4269 4270 4271 4272 4273 4274 4275 4276 4277 4278 4279 4280 4281 4282 4283 4284 4285 4286 4287 4288 4289 4290 4291 4292 4293 4294 4295 4296 4297 4298 4299 4300 4301 4302 4303 4304 4305 4306 4307 4308 4309 4310 4311 4312 4313 4314 4315 4316 4317 4318 4319 4320 4321 4322 4323 4324 4325 4326 4327 4328 4329 4330 4331 4332 4333 4334 4335 4336 4337 4338 4339 4340 4341 4342 4343 4344 4345 4346 4347 4348 4349 4350 4351 4352 4353 4354 4355 4356 4357 4358 4359 4360 4361 4362 4363 4364 4365 4366 4367 4368 4369 4370 4371 4372 4373 4374 4375 4376 4377 4378 4379 4380 4381 4382 4383 4384 4385 4386 4387 4388 4389 4390 4391 4392 4393 4394 4395 4396 4397 4398 4399 4400 4401 4402 4403 4404 4405 4406 4407 4408 4409 4410 4411 4412 4413 4414 4415 4416 4417 4418 4419 4420 4421 4422 4423 4424 4425 4426 4427 4428 4429 4430 4431 4432 4433 4434 4435 4436 4437 4438 4439 4440 4441 4442 4443 4444 4445 4446 4447 4448 4449 4450 4451 4452 4453 4454 4455 4456 4457 4458 4459 4460 4461 4462 4463 4464 4465 4466 4467 4468 4469 4470 4471 4472 4473 4474 4475 4476 4477 4478 4479 4480 4481 4482 4483 4484 4485 4486 4487 4488 4489 4490 4491 4492 4493 4494 4495 4496 4497 4498 4499 4500 4501 4502 4503 4504 4505 4506 4507 4508 4509 4510 4511 4512 4513 4514 4515 4516 4517 4518 4519 4520 4521 4522 4523 4524 4525 4526 4527 4528 4529 4530 4531 4532 4533 4534 4535 4536 4537 4538 4539 4540 4541 4542 4543 4544 4545 4546 4547 4548 4549 4550 4551 4552 4553 4554 4555 4556 4557 4558 4559 4560 4561 4562 4563 4564 4565 4566 4567 4568 4569 4570 4571 4572 4573 4574 4575 4576 4577 4578 4579 4580 4581 4582 4583 4584 4585 4586 4587 4588 4589 4590 4591 4592 4593 4594 4595 4596 4597 4598 4599 4600 4601 4602 4603 4604 4605 4606 4607 4608 4609 4610 4611 4612 4613 4614 4615 4616 4617 4618 4619 4620 4621 4622 4623 4624 4625 4626 4627 4628 4629 4630 4631 4632 4633 4634 4635 4636 4637 4638 4639 4640 4641 4642 4643 4644 4645 4646 4647 4648 4649 4650 4651 4652 4653 4654 4655 4656 4657 4658 4659 4660 4661 4662 4663 4664 4665 4666 4667 4668 4669 4670 4671 4672 4673 4674 4675 4676 4677 4678 4679 4680 4681 4682 4683 4684 4685 4686 4687 4688 4689 4690 4691 4692 4693 4694 4695 4696 4697 4698 4699 4700 4701 4702 4703 4704 4705 4706 4707 4708 4709 4710 4711 4712 4713 4714 4715 4716 4717 4718 4719 4720 4721 4722 4723 4724 4725 4726 4727 4728 4729 4730 4731 4732 4733 4734 4735 4736 4737 4738 4739 4740 4741 4742 4743 4744 4745 4746 4747 4748 4749 4750 4751 4752 4753 4754 4755 4756 4757 4758 4759 4760 4761 4762 4763 4764 4765 4766 4767 4768 4769 4770 4771 4772 4773 4774 4775 4776 4777 4778 4779 4780 4781 4782 4783 4784 4785 4786 4787 4788 4789 4790 4791 4792 4793 4794 4795 4796 4797 4798 4799 4800 4801 4802 4803 4804 4805 4806 4807 4808 4809 4810 4811 4812 4813 4814 4815 4816 4817 4818 4819 4820 4821 4822 4823 4824 4825 4826 4827 4828 4829 4830 4831 4832 4833 4834 4835 4836 4837 4838 4839 4840 4841 4842 4843 4844 4845 4846 4847 4848 4849 4850 4851 4852 4853 4854 4855 4856 4857 4858 4859 4860 4861 4862 4863 4864 4865 4866 4867 4868 4869 4870 4871 4872 4873 4874 4875 4876 4877 4878 4879 4880 4881 4882 4883 4884 4885 4886 4887 4888 4889 4890 4891 4892 4893 4894 4895 4896 4897 4898 4899 4900 4901 4902 4903 4904 4905 4906 4907 4908 4909 4910 4911 4912 4913 4914 4915 4916 4917 4918 4919 4920 4921 4922 4923 4924 4925 4926 4927 4928 4929 4930 4931 4932 4933 4934 4935 4936 4937 4938 4939 4940 4941 4942 4943 4944 4945 4946 4947 4948 4949 4950 4951 4952 4953 4954 4955 4956 4957 4958 4959 4960 4961 4962 4963 4964 4965 4966 4967 4968 4969 4970 4971 4972 4973 4974 4975 4976 4977 4978 4979 4980 4981 4982 4983 4984 4985 4986 4987 4988 4989 4990 4991 4992 4993 4994 4995 4996 4997 4998 4999 5000 5001 5002 5003 5004 5005 5006 5007 5008 5009 5010 5011 5012 5013 5014 5015 5016 5017 5018 5019 5020 5021 5022 5023 5024 5025 5026 5027 5028 5029 5030 5031 5032 5033 5034 5035 5036 5037 5038 5039 5040 5041 5042 5043 5044 5045 5046 5047 5048 5049 5050 5051 5052 5053 5054 5055 5056 5057 5058 5059 5060 5061 5062 5063 5064 5065 5066 5067 5068 5069 5070 5071 5072 5073 5074 5075 5076 5077 5078 5079 5080 5081 5082 5083 5084 5085 5086 5087 5088 5089 5090 5091 5092 5093 5094 5095 5096 5097 5098 5099 5100 5101 5102 5103 5104 5105 5106 5107 5108 5109 5110 5111 5112 5113 5114 5115 5116 5117 5118 5119 5120 5121 5122 5123 5124 5125 5126 5127 5128 5129 5130 5131 5132 5133 5134 5135 5136 5137 5138 5139 5140 5141 5142 5143 5144 5145 5146 5147 5148 5149 5150 5151 5152 5153 5154 5155 5156 5157 5158 5159 5160 5161 5162 5163 5164 5165 5166 5167 5168 5169 5170 5171 5172 5173 5174 5175 5176 5177 5178 5179 5180 5181 5182 5183 5184 5185 5186 5187 5188 5189 5190 5191 5192 5193 5194 5195 5196 5197 5198 5199 5200 5201 5202 5203 5204 5205 5206 5207 5208 5209 5210 5211 5212 5213 5214 5215 5216 5217 5218 5219 5220 5221 5222 5223 5224 5225 5226 5227 5228 5229 5230 5231 5232 5233 5234 5235 5236 5237 5238 5239 5240 5241 5242 5243 5244 5245 5246 5247 5248 5249 5250 5251 5252 5253 5254 5255 5256 5257 5258 5259 5260 5261 5262 5263 5264 5265 5266 5267 5268 5269 5270 5271 5272 5273 5274 5275 5276 5277 5278 5279 5280 5281 5282 5283 5284 5285 5286 5287 5288 5289 5290 5291 5292 5293 5294 5295 5296 5297 5298 5299 5300 5301 5302 5303 5304 5305 5306 5307 5308 5309 5310 5311 5312 5313 5314 5315 5316 5317 5318 5319 5320 5321 5322 5323 5324 5325 5326 5327 5328 5329 5330 5331 5332 5333 5334 5335 5336 5337 5338 5339 5340 5341 5342 5343 5344 5345 5346 5347 5348 5349 5350 5351 5352 5353 5354 5355 5356 5357 5358 5359 5360 5361 5362 5363 5364 5365 5366 5367 5368 5369 5370 5371 5372 5373 5374 5375 5376 5377 5378 5379 5380 5381 5382 5383 5384 5385 5386 5387 5388 5389 5390 5391 5392 5393 5394 5395 5396 5397 5398 5399 5400 5401 5402 5403 5404 5405 5406 5407 5408 5409 5410 5411 5412 5413 5414 5415 5416 5417 5418 5419 5420 5421 5422 5423 5424 5425 5426 5427 5428 5429 5430 5431 5432 5433 5434 5435 5436 5437 5438 5439 5440 5441 5442 5443 5444 5445 5446 5447 5448 5449 5450 5451 5452 5453 5454 5455 5456 5457 5458 5459 5460 5461 5462 5463 5464 5465 5466 5467 5468 5469 5470 5471 5472 5473 5474 5475 5476 5477 5478 5479 5480 5481 5482 5483 5484 5485 5486 5487 5488 5489 5490 5491 5492 5493 5494 5495 5496 5497 5498 5499 5500 5501 5502 5503 5504 5505 5506 5507 5508 5509 5510 5511 5512 5513 5514 5515 5516 5517 5518 5519 5520 5521 5522 5523 5524 5525 5526 5527 5528 5529 5530 5531 5532 5533 5534 5535 5536 5537 5538 5539 5540 5541 5542 5543 5544 5545 5546 5547 5548 5549 5550 5551 5552 5553 5554 5555 5556 5557 5558 5559 5560 5561 5562 5563 5564 5565 5566 5567 5568 5569 5570 5571 5572 5573 5574 5575 5576 5577 5578 5579 5580 5581 5582 5583 5584 5585 5586 5587 5588 5589 5590 5591 5592 5593 5594 5595 5596 5597 5598 5599 5600 5601 5602 5603 5604 5605 5606 5607 5608 5609 5610 5611 5612 5613 5614 5615 5616 5617 5618 5619 5620 5621 5622 5623 5624 5625 5626 5627 5628 5629 5630 5631 5632 5633 5634 5635 5636 5637 5638 5639 5640 5641 5642 5643 5644 5645 5646 5647 5648 5649 5650 5651 5652 5653 5654 5655 5656 5657 5658 5659 5660 5661 5662 5663 5664 5665 5666 5667 5668 5669 5670 5671 5672 5673 5674 5675 5676 5677 5678 5679 5680 5681 5682 5683 5684 5685 5686 5687 5688 5689 5690 5691 5692 5693 5694 5695 5696 5697 5698 5699 5700 5701 5702 5703 5704 5705 5706 5707 5708 5709 5710 5711 5712 5713 5714 5715 5716 5717 5718 5719 5720 5721 5722 5723 5724 5725 5726 5727 5728 5729 5730 5731 5732 5733 5734 5735 5736 5737 5738 5739 5740 5741 5742 5743 5744 5745 5746 5747 5748 5749 5750 5751 5752 5753 5754 5755 5756 5757 5758 5759 5760 5761 5762 5763 5764 5765 5766 5767 5768 5769 5770 5771 5772 5773 5774 5775 5776 5777 5778 5779 5780 5781 5782 5783 5784 5785 5786 5787 5788 5789 5790 5791 5792 5793 5794 5795 5796 5797 5798 5799 5800 5801 5802 5803 5804 5805 5806 5807 5808 5809 5810 5811 5812 5813 5814 5815 5816 5817 5818 5819 5820 5821 5822 5823 5824 5825 5826 5827 5828 5829 5830 5831 5832 5833 5834 5835 5836 5837 5838 5839 5840 5841 5842 5843 5844 5845 5846 5847 5848 5849 5850 5851 5852 5853 5854 5855 5856 5857 5858 5859 5860 5861 5862 5863 5864 5865 5866 5867 5868 5869 5870 5871 5872 5873 5874 5875 5876 5877 5878 5879 5880 5881 5882 5883 5884 5885 5886 5887 5888 5889 5890 5891 5892 5893 5894 5895 5896 5897 5898 5899 5900 5901 5902 5903 5904 5905 5906 5907 5908 5909 5910 5911 5912 5913 5914 5915 5916 5917 5918 5919 5920 5921 5922 5923 5924 5925 5926 5927 5928 5929 5930 5931 5932 5933 5934 5935 5936 5937 5938 5939 5940 5941 5942 5943 5944 5945 5946 5947 5948 5949 5950 5951 5952 5953 5954 5955 5956 5957 5958 5959 5960 5961 5962 5963 5964 5965 5966 5967 5968 5969 5970 5971 5972 5973 5974 5975 5976 5977 5978 5979 5980 5981 5982 5983 5984 5985 5986 5987 5988 5989 5990 5991 5992 5993 5994 5995 5996 5997 5998 5999 6000 6001 6002 6003 6004 6005 6006 6007 6008 6009 6010 6011 6012 6013 6014 6015 6016 6017 6018 6019 6020 6021 6022 6023 6024 6025 6026 6027 6028 6029 6030 6031 6032 6033 6034 6035 6036 6037 6038 6039 6040 6041 6042 6043 6044 6045 6046 6047 6048 6049 6050 6051 6052 6053 6054 6055 6056 6057 6058 6059 6060 6061 6062 6063 6064 6065 6066 6067 6068 6069 6070 6071 6072 6073 6074 6075 6076 6077 6078 6079 6080 6081 6082 6083 6084 6085 6086 6087 6088 6089 6090 6091 6092 6093 6094 6095 6096 6097 6098 6099 6100 6101 6102 6103 6104 6105 6106 6107 6108 6109 6110 6111 6112 6113 6114 6115 6116 6117 6118 6119 6120 6121 6122 6123 6124 6125 6126 6127 6128 6129 6130 6131 6132 6133 6134 6135 6136 6137 6138 6139 6140 6141 6142 6143 6144 6145 6146 6147 6148 6149 6150 6151 6152 6153 6154 6155 6156 6157 6158 6159 6160 6161 6162 6163 6164 6165 6166 6167 6168 6169 6170 6171 6172 6173 6174 6175 6176 6177 6178 6179 6180 6181 6182 6183 6184 6185 6186 6187 6188 6189 6190 6191 6192 6193 6194 6195 6196 6197 6198 6199 6200 6201 6202 6203 6204 6205 6206 6207 6208 6209 6210 6211 6212 6213 6214 6215 6216 6217 6218 6219 6220 6221 6222 6223 6224 6225 6226 6227 6228 6229 6230 6231 6232 6233 6234 6235 6236 6237 6238 6239 6240 6241 6242 6243 6244 6245 6246 6247 6248 6249 6250 6251 6252 6253 6254 6255 6256 6257 6258 6259 6260 6261 6262 6263 6264 6265 6266 6267 6268 6269 6270 6271 6272 6273 6274 6275 6276 6277 6278 6279 6280 6281 6282 6283 6284 6285 6286 6287 6288 6289 6290 6291 6292 6293 6294 6295 6296 6297 6298 6299 6300 6301 6302 6303 6304 6305 6306 6307 6308 6309 6310 6311 6312 6313 6314 6315 6316 6317 6318 6319 6320 6321 6322 6323 6324 6325 6326 6327 6328 6329 6330 6331 6332 6333 6334 6335 6336 6337 6338 6339 6340 6341 6342 6343 6344 6345 6346 6347 6348 6349 6350 6351 6352 6353 6354 6355 6356 6357 6358 6359 6360 6361 6362 6363 6364 6365 6366 6367 6368 6369 6370 6371 6372 6373 6374 6375 6376 6377 6378 6379 6380 6381 6382 6383 6384 6385 6386 6387 6388 6389 6390 6391 6392 6393 6394 6395 6396 6397 6398 6399 6400 6401 6402 6403 6404 6405 6406 6407 6408 6409 6410 6411 6412 6413 6414 6415 6416 6417 6418 6419 6420 6421 6422 6423 6424 6425 6426 6427 6428 6429 6430 6431 6432 6433 6434 6435 6436 6437 6438 6439 6440 6441 6442 6443 6444 6445 6446 6447 6448 6449 6450 6451 6452 6453 6454 6455 6456 6457 6458 6459 6460 6461 6462 6463 6464 6465 6466 6467 6468 6469 6470 6471 6472 6473 6474 6475 6476 6477 6478 6479 6480 6481 6482 6483 6484 6485 6486 6487 6488 6489 6490 6491 6492 6493 6494 6495 6496 6497 6498 6499 6500 6501 6502 6503 6504 6505 6506 6507 6508 6509 6510 6511 6512 6513 6514 6515 6516 6517 6518 6519 6520 6521 6522 6523 6524 6525 6526 6527 6528 6529 6530 6531 6532 6533 6534 6535 6536 6537 6538 6539 6540 6541 6542 6543 6544 6545 6546 6547 6548 6549 6550 6551 6552 6553 6554 6555 6556 6557 6558 6559 6560 6561 6562 6563 6564 6565 6566 6567 6568 6569 6570 6571 6572 6573 6574 6575 6576 6577 6578 6579 6580 6581 6582 6583 6584 6585 6586 6587 6588 6589 6590 6591 6592 6593 6594 6595 6596 6597 6598 6599 6600 6601 6602 6603 6604 6605 6606 6607 6608 6609 6610 6611 6612 6613 6614 6615 6616 6617 6618 6619 6620 6621 6622 6623 6624 6625 6626 6627 6628 6629 6630 6631 6632 6633 6634 6635 6636 6637 6638 6639 6640 6641 6642 6643 6644 6645 6646 6647 6648 6649 6650 6651 6652 6653 6654 6655 6656 6657 6658 6659 6660 6661 6662 6663 6664 6665 6666 6667 6668 6669 6670 6671 6672 6673 6674 6675 6676 6677 6678 6679 6680 6681 6682 6683 6684 6685 6686 6687 6688 6689 6690 6691 6692 6693 6694 6695 6696 6697 6698 6699 6700 6701 6702 6703 6704 6705 6706 6707 6708 6709 6710 6711 6712 6713 6714 6715 6716 6717 6718 6719 6720 6721 6722 6723 6724 6725 6726 6727 6728 6729 6730 6731 6732 6733 6734 6735 6736 6737 6738 6739 6740 6741 6742 6743 6744 6745 6746 6747 6748 6749 6750 6751 6752 6753 6754 6755 6756 6757 6758 6759 6760 6761 6762 6763 6764 6765 6766 6767 6768 6769 6770 6771 6772 6773 6774 6775 6776 6777 6778 6779 6780 6781 6782 6783 6784 6785 6786 6787 6788 6789 6790 6791 6792 6793 6794 6795 6796 6797 6798 6799 6800 6801 6802 6803 6804 6805 6806 6807 6808 6809 6810 6811 6812 6813 6814 6815 6816 6817 6818 6819 6820 6821 6822 6823 6824 6825 6826 6827 6828 6829 6830 6831 6832 6833 6834 6835 6836 6837 6838 6839 6840 6841 6842 6843 6844 6845 6846 6847 6848 6849 6850 6851 6852 6853 6854 6855 6856 6857 6858 6859 6860 6861 6862 6863 6864 6865 6866 6867 6868 6869 6870 6871 6872 6873 6874 6875 6876 6877 6878 6879 6880 6881 6882 6883 6884 6885 6886 6887 6888 6889 6890 6891 6892 6893 6894 6895 6896 6897 6898 6899 6900 6901 6902 6903 6904 6905 6906 6907 6908 6909 6910 6911 6912 6913 6914 6915 6916 6917 6918 6919 6920 6921 6922 6923 6924 6925 6926 6927 6928 6929 6930 6931 6932 6933 6934 6935 6936 6937 6938 6939 6940 6941 6942 6943 6944 6945 6946 6947 6948 6949 6950 6951 6952 6953 6954 6955 6956 6957 6958 6959 6960 6961 6962 6963 6964 6965 6966 6967 6968 6969 6970 6971 6972 6973 6974 6975 6976 6977 6978 6979 6980 6981 6982 6983 6984 6985 6986 6987 6988 6989 6990 6991 6992 6993 6994 6995 6996 6997 6998 6999 7000 7001 7002 7003 7004 7005 7006 7007 7008 7009 7010 7011 7012 7013 7014 7015 7016 7017 7018 7019 7020 7021 7022 7023 7024 7025 7026 7027 7028 7029 7030 7031 7032 7033 7034 7035 7036 7037 7038 7039 7040 7041 7042 7043 7044 7045 7046 7047 7048 7049 7050 7051 7052 7053 7054 7055 7056 7057 7058 7059 7060 7061 7062 7063 7064 7065 7066 7067 7068 7069 7070 7071 7072 7073 7074 7075 7076 7077 7078 7079 7080 7081 7082 7083 7084 7085 7086 7087 7088 7089 7090 7091 7092 7093 7094 7095 7096 7097 7098 7099 7100 7101 7102 7103 7104 7105 7106 7107 7108 7109 7110 7111 7112 7113 7114 7115 7116 7117 7118 7119 7120 7121 7122 7123 7124 7125 7126 7127 7128 7129 7130 7131 7132 7133 7134 7135 7136 7137 7138 7139 7140 7141 7142 7143 7144 7145 7146 7147 7148 7149 7150 7151 7152 7153 7154 7155 7156 7157 7158 7159 7160 7161 7162 7163 7164 7165 7166 7167 7168 7169 7170 7171 7172 7173 7174 7175 7176 7177 7178 7179 7180 7181 7182 7183 7184 7185 7186 7187 7188 7189 7190 7191 7192 7193 7194 7195 7196 7197 7198 7199 7200 7201 7202 7203 7204 7205 7206 7207 7208 7209 7210 7211 7212 7213 7214 7215 7216 7217 7218 7219 7220 7221 7222 7223 7224 7225 7226 7227 7228 7229 7230 7231 7232 7233 7234 7235 7236 7237 7238 7239 7240 7241 7242 7243 7244 7245 7246 7247 7248 7249 7250 7251 7252 7253 7254 7255 7256 7257 7258 7259 7260 7261 7262 7263 7264 7265 7266 7267 7268 7269 7270 7271 7272 7273 7274 7275 7276 7277 7278 7279 7280 7281 7282 7283 7284 7285 7286 7287 7288 7289 7290 7291 7292 7293 7294 7295 7296 7297 7298 7299 7300 7301 7302 7303 7304 7305 7306 7307 7308 7309 7310 7311 7312 7313 7314 7315 7316 7317 7318 7319 7320 7321 7322 7323 7324 7325 7326 7327 7328 7329 7330 7331 7332 7333 7334 7335 7336 7337 7338 7339 7340 7341 7342 7343 7344 7345 7346 7347 7348 7349 7350 7351 7352 7353 7354 7355 7356 7357 7358 7359 7360 7361 7362 7363 7364 7365 7366 7367 7368 7369 7370 7371 7372 7373 7374 7375 7376 7377 7378 7379 7380 7381 7382 7383 7384 7385 7386 7387 7388 7389 7390 7391 7392 7393 7394 7395 7396 7397 7398 7399 7400 7401 7402 7403 7404 7405 7406 7407 7408 7409 7410 7411 7412 7413 7414 7415 7416 7417 7418 7419 7420 7421 7422 7423 7424 7425 7426 7427 7428 7429 7430 7431 7432 7433 7434 7435 7436 7437 7438 7439 7440 7441 7442 7443 7444 7445 7446 7447 7448 7449 7450 7451 7452 7453 7454 7455 7456 7457 7458 7459 7460 7461 7462 7463 7464 7465 7466 7467 7468 7469 7470 7471 7472 7473 7474 7475 7476 7477 7478 7479 7480 7481 7482 7483 7484 7485 7486 7487 7488 7489 7490 7491 7492 7493 7494 7495 7496 7497 7498 7499 7500 7501 7502 7503 7504 7505 7506 7507 7508 7509 7510 7511 7512 7513 7514 7515 7516 7517 7518 7519 7520 7521 7522 7523 7524 7525 7526 7527 7528 7529 7530 7531 7532 7533 7534 7535 7536 7537 7538 7539 7540 7541 7542 7543 7544 7545 7546 7547 7548 7549 7550 7551 7552 7553 7554 7555 7556 7557 7558 7559 7560 7561 7562 7563 7564 7565 7566 7567 7568 7569 7570 7571 7572 7573 7574 7575 7576 7577 7578 7579 7580 7581 7582 7583 7584 7585 7586 7587 7588 7589 7590 7591 7592 7593 7594 7595 7596 7597 7598 7599 7600 7601 7602 7603 7604 7605 7606 7607 7608 7609 7610 7611 7612 7613 7614 7615 7616 7617 7618 7619 7620 7621 7622 7623 7624 7625 7626 7627 7628 7629 7630 7631 7632 7633 7634 7635 7636 7637 7638 7639 7640 7641 7642 7643 7644 7645 7646 7647 7648 7649 7650 7651 7652 7653 7654 7655 7656 7657 7658 7659 7660 7661 7662 7663 7664 7665 7666 7667 7668 7669 7670 7671 7672 7673 7674 7675 7676 7677 7678 7679 7680 7681 7682 7683 7684 7685 7686 7687 7688 7689 7690 7691 7692 7693 7694 7695 7696 7697 7698 7699 7700 7701 7702 7703 7704 7705 7706 7707 7708 7709 7710 7711 | // SPDX-License-Identifier: GPL-2.0-only /* * Generic hugetlb support. * (C) Nadia Yvette Chambers, April 2004 */ #include <linux/list.h> #include <linux/init.h> #include <linux/mm.h> #include <linux/seq_file.h> #include <linux/sysctl.h> #include <linux/highmem.h> #include <linux/mmu_notifier.h> #include <linux/nodemask.h> #include <linux/pagemap.h> #include <linux/mempolicy.h> #include <linux/compiler.h> #include <linux/cpuset.h> #include <linux/mutex.h> #include <linux/memblock.h> #include <linux/sysfs.h> #include <linux/slab.h> #include <linux/sched/mm.h> #include <linux/mmdebug.h> #include <linux/sched/signal.h> #include <linux/rmap.h> #include <linux/string_helpers.h> #include <linux/swap.h> #include <linux/swapops.h> #include <linux/jhash.h> #include <linux/numa.h> #include <linux/llist.h> #include <linux/cma.h> #include <linux/migrate.h> #include <linux/nospec.h> #include <linux/delayacct.h> #include <linux/memory.h> #include <linux/mm_inline.h> #include <linux/padata.h> #include <asm/page.h> #include <asm/pgalloc.h> #include <asm/tlb.h> #include <linux/io.h> #include <linux/hugetlb.h> #include <linux/hugetlb_cgroup.h> #include <linux/node.h> #include <linux/page_owner.h> #include "internal.h" #include "hugetlb_vmemmap.h" int hugetlb_max_hstate __read_mostly; unsigned int default_hstate_idx; struct hstate hstates[HUGE_MAX_HSTATE]; #ifdef CONFIG_CMA static struct cma *hugetlb_cma[MAX_NUMNODES]; static unsigned long hugetlb_cma_size_in_node[MAX_NUMNODES] __initdata; #endif static unsigned long hugetlb_cma_size __initdata; __initdata struct list_head huge_boot_pages[MAX_NUMNODES]; /* for command line parsing */ static struct hstate * __initdata parsed_hstate; static unsigned long __initdata default_hstate_max_huge_pages; static bool __initdata parsed_valid_hugepagesz = true; static bool __initdata parsed_default_hugepagesz; static unsigned int default_hugepages_in_node[MAX_NUMNODES] __initdata; /* * Protects updates to hugepage_freelists, hugepage_activelist, nr_huge_pages, * free_huge_pages, and surplus_huge_pages. */ __cacheline_aligned_in_smp DEFINE_SPINLOCK(hugetlb_lock); /* * Serializes faults on the same logical page. This is used to * prevent spurious OOMs when the hugepage pool is fully utilized. */ static int num_fault_mutexes __ro_after_init; struct mutex *hugetlb_fault_mutex_table __ro_after_init; /* Forward declaration */ static int hugetlb_acct_memory(struct hstate *h, long delta); static void hugetlb_vma_lock_free(struct vm_area_struct *vma); static void hugetlb_vma_lock_alloc(struct vm_area_struct *vma); static void __hugetlb_vma_unlock_write_free(struct vm_area_struct *vma); static void hugetlb_unshare_pmds(struct vm_area_struct *vma, unsigned long start, unsigned long end); static struct resv_map *vma_resv_map(struct vm_area_struct *vma); static void hugetlb_free_folio(struct folio *folio) { #ifdef CONFIG_CMA int nid = folio_nid(folio); if (cma_free_folio(hugetlb_cma[nid], folio)) return; #endif folio_put(folio); } static inline bool subpool_is_free(struct hugepage_subpool *spool) { if (spool->count) return false; if (spool->max_hpages != -1) return spool->used_hpages == 0; if (spool->min_hpages != -1) return spool->rsv_hpages == spool->min_hpages; return true; } static inline void unlock_or_release_subpool(struct hugepage_subpool *spool, unsigned long irq_flags) { spin_unlock_irqrestore(&spool->lock, irq_flags); /* If no pages are used, and no other handles to the subpool * remain, give up any reservations based on minimum size and * free the subpool */ if (subpool_is_free(spool)) { if (spool->min_hpages != -1) hugetlb_acct_memory(spool->hstate, -spool->min_hpages); kfree(spool); } } struct hugepage_subpool *hugepage_new_subpool(struct hstate *h, long max_hpages, long min_hpages) { struct hugepage_subpool *spool; spool = kzalloc(sizeof(*spool), GFP_KERNEL); if (!spool) return NULL; spin_lock_init(&spool->lock); spool->count = 1; spool->max_hpages = max_hpages; spool->hstate = h; spool->min_hpages = min_hpages; if (min_hpages != -1 && hugetlb_acct_memory(h, min_hpages)) { kfree(spool); return NULL; } spool->rsv_hpages = min_hpages; return spool; } void hugepage_put_subpool(struct hugepage_subpool *spool) { unsigned long flags; spin_lock_irqsave(&spool->lock, flags); BUG_ON(!spool->count); spool->count--; unlock_or_release_subpool(spool, flags); } /* * Subpool accounting for allocating and reserving pages. * Return -ENOMEM if there are not enough resources to satisfy the * request. Otherwise, return the number of pages by which the * global pools must be adjusted (upward). The returned value may * only be different than the passed value (delta) in the case where * a subpool minimum size must be maintained. */ static long hugepage_subpool_get_pages(struct hugepage_subpool *spool, long delta) { long ret = delta; if (!spool) return ret; spin_lock_irq(&spool->lock); if (spool->max_hpages != -1) { /* maximum size accounting */ if ((spool->used_hpages + delta) <= spool->max_hpages) spool->used_hpages += delta; else { ret = -ENOMEM; goto unlock_ret; } } /* minimum size accounting */ if (spool->min_hpages != -1 && spool->rsv_hpages) { if (delta > spool->rsv_hpages) { /* * Asking for more reserves than those already taken on * behalf of subpool. Return difference. */ ret = delta - spool->rsv_hpages; spool->rsv_hpages = 0; } else { ret = 0; /* reserves already accounted for */ spool->rsv_hpages -= delta; } } unlock_ret: spin_unlock_irq(&spool->lock); return ret; } /* * Subpool accounting for freeing and unreserving pages. * Return the number of global page reservations that must be dropped. * The return value may only be different than the passed value (delta) * in the case where a subpool minimum size must be maintained. */ static long hugepage_subpool_put_pages(struct hugepage_subpool *spool, long delta) { long ret = delta; unsigned long flags; if (!spool) return delta; spin_lock_irqsave(&spool->lock, flags); if (spool->max_hpages != -1) /* maximum size accounting */ spool->used_hpages -= delta; /* minimum size accounting */ if (spool->min_hpages != -1 && spool->used_hpages < spool->min_hpages) { if (spool->rsv_hpages + delta <= spool->min_hpages) ret = 0; else ret = spool->rsv_hpages + delta - spool->min_hpages; spool->rsv_hpages += delta; if (spool->rsv_hpages > spool->min_hpages) spool->rsv_hpages = spool->min_hpages; } /* * If hugetlbfs_put_super couldn't free spool due to an outstanding * quota reference, free it now. */ unlock_or_release_subpool(spool, flags); return ret; } static inline struct hugepage_subpool *subpool_inode(struct inode *inode) { return HUGETLBFS_SB(inode->i_sb)->spool; } static inline struct hugepage_subpool *subpool_vma(struct vm_area_struct *vma) { return subpool_inode(file_inode(vma->vm_file)); } /* * hugetlb vma_lock helper routines */ void hugetlb_vma_lock_read(struct vm_area_struct *vma) { if (__vma_shareable_lock(vma)) { struct hugetlb_vma_lock *vma_lock = vma->vm_private_data; down_read(&vma_lock->rw_sema); } else if (__vma_private_lock(vma)) { struct resv_map *resv_map = vma_resv_map(vma); down_read(&resv_map->rw_sema); } } void hugetlb_vma_unlock_read(struct vm_area_struct *vma) { if (__vma_shareable_lock(vma)) { struct hugetlb_vma_lock *vma_lock = vma->vm_private_data; up_read(&vma_lock->rw_sema); } else if (__vma_private_lock(vma)) { struct resv_map *resv_map = vma_resv_map(vma); up_read(&resv_map->rw_sema); } } void hugetlb_vma_lock_write(struct vm_area_struct *vma) { if (__vma_shareable_lock(vma)) { struct hugetlb_vma_lock *vma_lock = vma->vm_private_data; down_write(&vma_lock->rw_sema); } else if (__vma_private_lock(vma)) { struct resv_map *resv_map = vma_resv_map(vma); down_write(&resv_map->rw_sema); } } void hugetlb_vma_unlock_write(struct vm_area_struct *vma) { if (__vma_shareable_lock(vma)) { struct hugetlb_vma_lock *vma_lock = vma->vm_private_data; up_write(&vma_lock->rw_sema); } else if (__vma_private_lock(vma)) { struct resv_map *resv_map = vma_resv_map(vma); up_write(&resv_map->rw_sema); } } int hugetlb_vma_trylock_write(struct vm_area_struct *vma) { if (__vma_shareable_lock(vma)) { struct hugetlb_vma_lock *vma_lock = vma->vm_private_data; return down_write_trylock(&vma_lock->rw_sema); } else if (__vma_private_lock(vma)) { struct resv_map *resv_map = vma_resv_map(vma); return down_write_trylock(&resv_map->rw_sema); } return 1; } void hugetlb_vma_assert_locked(struct vm_area_struct *vma) { if (__vma_shareable_lock(vma)) { struct hugetlb_vma_lock *vma_lock = vma->vm_private_data; lockdep_assert_held(&vma_lock->rw_sema); } else if (__vma_private_lock(vma)) { struct resv_map *resv_map = vma_resv_map(vma); lockdep_assert_held(&resv_map->rw_sema); } } void hugetlb_vma_lock_release(struct kref *kref) { struct hugetlb_vma_lock *vma_lock = container_of(kref, struct hugetlb_vma_lock, refs); kfree(vma_lock); } static void __hugetlb_vma_unlock_write_put(struct hugetlb_vma_lock *vma_lock) { struct vm_area_struct *vma = vma_lock->vma; /* * vma_lock structure may or not be released as a result of put, * it certainly will no longer be attached to vma so clear pointer. * Semaphore synchronizes access to vma_lock->vma field. */ vma_lock->vma = NULL; vma->vm_private_data = NULL; up_write(&vma_lock->rw_sema); kref_put(&vma_lock->refs, hugetlb_vma_lock_release); } static void __hugetlb_vma_unlock_write_free(struct vm_area_struct *vma) { if (__vma_shareable_lock(vma)) { struct hugetlb_vma_lock *vma_lock = vma->vm_private_data; __hugetlb_vma_unlock_write_put(vma_lock); } else if (__vma_private_lock(vma)) { struct resv_map *resv_map = vma_resv_map(vma); /* no free for anon vmas, but still need to unlock */ up_write(&resv_map->rw_sema); } } static void hugetlb_vma_lock_free(struct vm_area_struct *vma) { /* * Only present in sharable vmas. */ if (!vma || !__vma_shareable_lock(vma)) return; if (vma->vm_private_data) { struct hugetlb_vma_lock *vma_lock = vma->vm_private_data; down_write(&vma_lock->rw_sema); __hugetlb_vma_unlock_write_put(vma_lock); } } static void hugetlb_vma_lock_alloc(struct vm_area_struct *vma) { struct hugetlb_vma_lock *vma_lock; /* Only establish in (flags) sharable vmas */ if (!vma || !(vma->vm_flags & VM_MAYSHARE)) return; /* Should never get here with non-NULL vm_private_data */ if (vma->vm_private_data) return; vma_lock = kmalloc(sizeof(*vma_lock), GFP_KERNEL); if (!vma_lock) { /* * If we can not allocate structure, then vma can not * participate in pmd sharing. This is only a possible * performance enhancement and memory saving issue. * However, the lock is also used to synchronize page * faults with truncation. If the lock is not present, * unlikely races could leave pages in a file past i_size * until the file is removed. Warn in the unlikely case of * allocation failure. */ pr_warn_once("HugeTLB: unable to allocate vma specific lock\n"); return; } kref_init(&vma_lock->refs); init_rwsem(&vma_lock->rw_sema); vma_lock->vma = vma; vma->vm_private_data = vma_lock; } /* Helper that removes a struct file_region from the resv_map cache and returns * it for use. */ static struct file_region * get_file_region_entry_from_cache(struct resv_map *resv, long from, long to) { struct file_region *nrg; VM_BUG_ON(resv->region_cache_count <= 0); resv->region_cache_count--; nrg = list_first_entry(&resv->region_cache, struct file_region, link); list_del(&nrg->link); nrg->from = from; nrg->to = to; return nrg; } static void copy_hugetlb_cgroup_uncharge_info(struct file_region *nrg, struct file_region *rg) { #ifdef CONFIG_CGROUP_HUGETLB nrg->reservation_counter = rg->reservation_counter; nrg->css = rg->css; if (rg->css) css_get(rg->css); #endif } /* Helper that records hugetlb_cgroup uncharge info. */ static void record_hugetlb_cgroup_uncharge_info(struct hugetlb_cgroup *h_cg, struct hstate *h, struct resv_map *resv, struct file_region *nrg) { #ifdef CONFIG_CGROUP_HUGETLB if (h_cg) { nrg->reservation_counter = &h_cg->rsvd_hugepage[hstate_index(h)]; nrg->css = &h_cg->css; /* * The caller will hold exactly one h_cg->css reference for the * whole contiguous reservation region. But this area might be * scattered when there are already some file_regions reside in * it. As a result, many file_regions may share only one css * reference. In order to ensure that one file_region must hold * exactly one h_cg->css reference, we should do css_get for * each file_region and leave the reference held by caller * untouched. */ css_get(&h_cg->css); if (!resv->pages_per_hpage) resv->pages_per_hpage = pages_per_huge_page(h); /* pages_per_hpage should be the same for all entries in * a resv_map. */ VM_BUG_ON(resv->pages_per_hpage != pages_per_huge_page(h)); } else { nrg->reservation_counter = NULL; nrg->css = NULL; } #endif } static void put_uncharge_info(struct file_region *rg) { #ifdef CONFIG_CGROUP_HUGETLB if (rg->css) css_put(rg->css); #endif } static bool has_same_uncharge_info(struct file_region *rg, struct file_region *org) { #ifdef CONFIG_CGROUP_HUGETLB return rg->reservation_counter == org->reservation_counter && rg->css == org->css; #else return true; #endif } static void coalesce_file_region(struct resv_map *resv, struct file_region *rg) { struct file_region *nrg, *prg; prg = list_prev_entry(rg, link); if (&prg->link != &resv->regions && prg->to == rg->from && has_same_uncharge_info(prg, rg)) { prg->to = rg->to; list_del(&rg->link); put_uncharge_info(rg); kfree(rg); rg = prg; } nrg = list_next_entry(rg, link); if (&nrg->link != &resv->regions && nrg->from == rg->to && has_same_uncharge_info(nrg, rg)) { nrg->from = rg->from; list_del(&rg->link); put_uncharge_info(rg); kfree(rg); } } static inline long hugetlb_resv_map_add(struct resv_map *map, struct list_head *rg, long from, long to, struct hstate *h, struct hugetlb_cgroup *cg, long *regions_needed) { struct file_region *nrg; if (!regions_needed) { nrg = get_file_region_entry_from_cache(map, from, to); record_hugetlb_cgroup_uncharge_info(cg, h, map, nrg); list_add(&nrg->link, rg); coalesce_file_region(map, nrg); } else *regions_needed += 1; return to - from; } /* * Must be called with resv->lock held. * * Calling this with regions_needed != NULL will count the number of pages * to be added but will not modify the linked list. And regions_needed will * indicate the number of file_regions needed in the cache to carry out to add * the regions for this range. */ static long add_reservation_in_range(struct resv_map *resv, long f, long t, struct hugetlb_cgroup *h_cg, struct hstate *h, long *regions_needed) { long add = 0; struct list_head *head = &resv->regions; long last_accounted_offset = f; struct file_region *iter, *trg = NULL; struct list_head *rg = NULL; if (regions_needed) *regions_needed = 0; /* In this loop, we essentially handle an entry for the range * [last_accounted_offset, iter->from), at every iteration, with some * bounds checking. */ list_for_each_entry_safe(iter, trg, head, link) { /* Skip irrelevant regions that start before our range. */ if (iter->from < f) { /* If this region ends after the last accounted offset, * then we need to update last_accounted_offset. */ if (iter->to > last_accounted_offset) last_accounted_offset = iter->to; continue; } /* When we find a region that starts beyond our range, we've * finished. */ if (iter->from >= t) { rg = iter->link.prev; break; } /* Add an entry for last_accounted_offset -> iter->from, and * update last_accounted_offset. */ if (iter->from > last_accounted_offset) add += hugetlb_resv_map_add(resv, iter->link.prev, last_accounted_offset, iter->from, h, h_cg, regions_needed); last_accounted_offset = iter->to; } /* Handle the case where our range extends beyond * last_accounted_offset. */ if (!rg) rg = head->prev; if (last_accounted_offset < t) add += hugetlb_resv_map_add(resv, rg, last_accounted_offset, t, h, h_cg, regions_needed); return add; } /* Must be called with resv->lock acquired. Will drop lock to allocate entries. */ static int allocate_file_region_entries(struct resv_map *resv, int regions_needed) __must_hold(&resv->lock) { LIST_HEAD(allocated_regions); int to_allocate = 0, i = 0; struct file_region *trg = NULL, *rg = NULL; VM_BUG_ON(regions_needed < 0); /* * Check for sufficient descriptors in the cache to accommodate * the number of in progress add operations plus regions_needed. * * This is a while loop because when we drop the lock, some other call * to region_add or region_del may have consumed some region_entries, * so we keep looping here until we finally have enough entries for * (adds_in_progress + regions_needed). */ while (resv->region_cache_count < (resv->adds_in_progress + regions_needed)) { to_allocate = resv->adds_in_progress + regions_needed - resv->region_cache_count; /* At this point, we should have enough entries in the cache * for all the existing adds_in_progress. We should only be * needing to allocate for regions_needed. */ VM_BUG_ON(resv->region_cache_count < resv->adds_in_progress); spin_unlock(&resv->lock); for (i = 0; i < to_allocate; i++) { trg = kmalloc(sizeof(*trg), GFP_KERNEL); if (!trg) goto out_of_memory; list_add(&trg->link, &allocated_regions); } spin_lock(&resv->lock); list_splice(&allocated_regions, &resv->region_cache); resv->region_cache_count += to_allocate; } return 0; out_of_memory: list_for_each_entry_safe(rg, trg, &allocated_regions, link) { list_del(&rg->link); kfree(rg); } return -ENOMEM; } /* * Add the huge page range represented by [f, t) to the reserve * map. Regions will be taken from the cache to fill in this range. * Sufficient regions should exist in the cache due to the previous * call to region_chg with the same range, but in some cases the cache will not * have sufficient entries due to races with other code doing region_add or * region_del. The extra needed entries will be allocated. * * regions_needed is the out value provided by a previous call to region_chg. * * Return the number of new huge pages added to the map. This number is greater * than or equal to zero. If file_region entries needed to be allocated for * this operation and we were not able to allocate, it returns -ENOMEM. * region_add of regions of length 1 never allocate file_regions and cannot * fail; region_chg will always allocate at least 1 entry and a region_add for * 1 page will only require at most 1 entry. */ static long region_add(struct resv_map *resv, long f, long t, long in_regions_needed, struct hstate *h, struct hugetlb_cgroup *h_cg) { long add = 0, actual_regions_needed = 0; spin_lock(&resv->lock); retry: /* Count how many regions are actually needed to execute this add. */ add_reservation_in_range(resv, f, t, NULL, NULL, &actual_regions_needed); /* * Check for sufficient descriptors in the cache to accommodate * this add operation. Note that actual_regions_needed may be greater * than in_regions_needed, as the resv_map may have been modified since * the region_chg call. In this case, we need to make sure that we * allocate extra entries, such that we have enough for all the * existing adds_in_progress, plus the excess needed for this * operation. */ if (actual_regions_needed > in_regions_needed && resv->region_cache_count < resv->adds_in_progress + (actual_regions_needed - in_regions_needed)) { /* region_add operation of range 1 should never need to * allocate file_region entries. */ VM_BUG_ON(t - f <= 1); if (allocate_file_region_entries( resv, actual_regions_needed - in_regions_needed)) { return -ENOMEM; } goto retry; } add = add_reservation_in_range(resv, f, t, h_cg, h, NULL); resv->adds_in_progress -= in_regions_needed; spin_unlock(&resv->lock); return add; } /* * Examine the existing reserve map and determine how many * huge pages in the specified range [f, t) are NOT currently * represented. This routine is called before a subsequent * call to region_add that will actually modify the reserve * map to add the specified range [f, t). region_chg does * not change the number of huge pages represented by the * map. A number of new file_region structures is added to the cache as a * placeholder, for the subsequent region_add call to use. At least 1 * file_region structure is added. * * out_regions_needed is the number of regions added to the * resv->adds_in_progress. This value needs to be provided to a follow up call * to region_add or region_abort for proper accounting. * * Returns the number of huge pages that need to be added to the existing * reservation map for the range [f, t). This number is greater or equal to * zero. -ENOMEM is returned if a new file_region structure or cache entry * is needed and can not be allocated. */ static long region_chg(struct resv_map *resv, long f, long t, long *out_regions_needed) { long chg = 0; spin_lock(&resv->lock); /* Count how many hugepages in this range are NOT represented. */ chg = add_reservation_in_range(resv, f, t, NULL, NULL, out_regions_needed); if (*out_regions_needed == 0) *out_regions_needed = 1; if (allocate_file_region_entries(resv, *out_regions_needed)) return -ENOMEM; resv->adds_in_progress += *out_regions_needed; spin_unlock(&resv->lock); return chg; } /* * Abort the in progress add operation. The adds_in_progress field * of the resv_map keeps track of the operations in progress between * calls to region_chg and region_add. Operations are sometimes * aborted after the call to region_chg. In such cases, region_abort * is called to decrement the adds_in_progress counter. regions_needed * is the value returned by the region_chg call, it is used to decrement * the adds_in_progress counter. * * NOTE: The range arguments [f, t) are not needed or used in this * routine. They are kept to make reading the calling code easier as * arguments will match the associated region_chg call. */ static void region_abort(struct resv_map *resv, long f, long t, long regions_needed) { spin_lock(&resv->lock); VM_BUG_ON(!resv->region_cache_count); resv->adds_in_progress -= regions_needed; spin_unlock(&resv->lock); } /* * Delete the specified range [f, t) from the reserve map. If the * t parameter is LONG_MAX, this indicates that ALL regions after f * should be deleted. Locate the regions which intersect [f, t) * and either trim, delete or split the existing regions. * * Returns the number of huge pages deleted from the reserve map. * In the normal case, the return value is zero or more. In the * case where a region must be split, a new region descriptor must * be allocated. If the allocation fails, -ENOMEM will be returned. * NOTE: If the parameter t == LONG_MAX, then we will never split * a region and possibly return -ENOMEM. Callers specifying * t == LONG_MAX do not need to check for -ENOMEM error. */ static long region_del(struct resv_map *resv, long f, long t) { struct list_head *head = &resv->regions; struct file_region *rg, *trg; struct file_region *nrg = NULL; long del = 0; retry: spin_lock(&resv->lock); list_for_each_entry_safe(rg, trg, head, link) { /* * Skip regions before the range to be deleted. file_region * ranges are normally of the form [from, to). However, there * may be a "placeholder" entry in the map which is of the form * (from, to) with from == to. Check for placeholder entries * at the beginning of the range to be deleted. */ if (rg->to <= f && (rg->to != rg->from || rg->to != f)) continue; if (rg->from >= t) break; if (f > rg->from && t < rg->to) { /* Must split region */ /* * Check for an entry in the cache before dropping * lock and attempting allocation. */ if (!nrg && resv->region_cache_count > resv->adds_in_progress) { nrg = list_first_entry(&resv->region_cache, struct file_region, link); list_del(&nrg->link); resv->region_cache_count--; } if (!nrg) { spin_unlock(&resv->lock); nrg = kmalloc(sizeof(*nrg), GFP_KERNEL); if (!nrg) return -ENOMEM; goto retry; } del += t - f; hugetlb_cgroup_uncharge_file_region( resv, rg, t - f, false); /* New entry for end of split region */ nrg->from = t; nrg->to = rg->to; copy_hugetlb_cgroup_uncharge_info(nrg, rg); INIT_LIST_HEAD(&nrg->link); /* Original entry is trimmed */ rg->to = f; list_add(&nrg->link, &rg->link); nrg = NULL; break; } if (f <= rg->from && t >= rg->to) { /* Remove entire region */ del += rg->to - rg->from; hugetlb_cgroup_uncharge_file_region(resv, rg, rg->to - rg->from, true); list_del(&rg->link); kfree(rg); continue; } if (f <= rg->from) { /* Trim beginning of region */ hugetlb_cgroup_uncharge_file_region(resv, rg, t - rg->from, false); del += t - rg->from; rg->from = t; } else { /* Trim end of region */ hugetlb_cgroup_uncharge_file_region(resv, rg, rg->to - f, false); del += rg->to - f; rg->to = f; } } spin_unlock(&resv->lock); kfree(nrg); return del; } /* * A rare out of memory error was encountered which prevented removal of * the reserve map region for a page. The huge page itself was free'ed * and removed from the page cache. This routine will adjust the subpool * usage count, and the global reserve count if needed. By incrementing * these counts, the reserve map entry which could not be deleted will * appear as a "reserved" entry instead of simply dangling with incorrect * counts. */ void hugetlb_fix_reserve_counts(struct inode *inode) { struct hugepage_subpool *spool = subpool_inode(inode); long rsv_adjust; bool reserved = false; rsv_adjust = hugepage_subpool_get_pages(spool, 1); if (rsv_adjust > 0) { struct hstate *h = hstate_inode(inode); if (!hugetlb_acct_memory(h, 1)) reserved = true; } else if (!rsv_adjust) { reserved = true; } if (!reserved) pr_warn("hugetlb: Huge Page Reserved count may go negative.\n"); } /* * Count and return the number of huge pages in the reserve map * that intersect with the range [f, t). */ static long region_count(struct resv_map *resv, long f, long t) { struct list_head *head = &resv->regions; struct file_region *rg; long chg = 0; spin_lock(&resv->lock); /* Locate each segment we overlap with, and count that overlap. */ list_for_each_entry(rg, head, link) { long seg_from; long seg_to; if (rg->to <= f) continue; if (rg->from >= t) break; seg_from = max(rg->from, f); seg_to = min(rg->to, t); chg += seg_to - seg_from; } spin_unlock(&resv->lock); return chg; } /* * Convert the address within this vma to the page offset within * the mapping, huge page units here. */ static pgoff_t vma_hugecache_offset(struct hstate *h, struct vm_area_struct *vma, unsigned long address) { return ((address - vma->vm_start) >> huge_page_shift(h)) + (vma->vm_pgoff >> huge_page_order(h)); } /** * vma_kernel_pagesize - Page size granularity for this VMA. * @vma: The user mapping. * * Folios in this VMA will be aligned to, and at least the size of the * number of bytes returned by this function. * * Return: The default size of the folios allocated when backing a VMA. */ unsigned long vma_kernel_pagesize(struct vm_area_struct *vma) { if (vma->vm_ops && vma->vm_ops->pagesize) return vma->vm_ops->pagesize(vma); return PAGE_SIZE; } EXPORT_SYMBOL_GPL(vma_kernel_pagesize); /* * Return the page size being used by the MMU to back a VMA. In the majority * of cases, the page size used by the kernel matches the MMU size. On * architectures where it differs, an architecture-specific 'strong' * version of this symbol is required. */ __weak unsigned long vma_mmu_pagesize(struct vm_area_struct *vma) { return vma_kernel_pagesize(vma); } /* * Flags for MAP_PRIVATE reservations. These are stored in the bottom * bits of the reservation map pointer, which are always clear due to * alignment. */ #define HPAGE_RESV_OWNER (1UL << 0) #define HPAGE_RESV_UNMAPPED (1UL << 1) #define HPAGE_RESV_MASK (HPAGE_RESV_OWNER | HPAGE_RESV_UNMAPPED) /* * These helpers are used to track how many pages are reserved for * faults in a MAP_PRIVATE mapping. Only the process that called mmap() * is guaranteed to have their future faults succeed. * * With the exception of hugetlb_dup_vma_private() which is called at fork(), * the reserve counters are updated with the hugetlb_lock held. It is safe * to reset the VMA at fork() time as it is not in use yet and there is no * chance of the global counters getting corrupted as a result of the values. * * The private mapping reservation is represented in a subtly different * manner to a shared mapping. A shared mapping has a region map associated * with the underlying file, this region map represents the backing file * pages which have ever had a reservation assigned which this persists even * after the page is instantiated. A private mapping has a region map * associated with the original mmap which is attached to all VMAs which * reference it, this region map represents those offsets which have consumed * reservation ie. where pages have been instantiated. */ static unsigned long get_vma_private_data(struct vm_area_struct *vma) { return (unsigned long)vma->vm_private_data; } static void set_vma_private_data(struct vm_area_struct *vma, unsigned long value) { vma->vm_private_data = (void *)value; } static void resv_map_set_hugetlb_cgroup_uncharge_info(struct resv_map *resv_map, struct hugetlb_cgroup *h_cg, struct hstate *h) { #ifdef CONFIG_CGROUP_HUGETLB if (!h_cg || !h) { resv_map->reservation_counter = NULL; resv_map->pages_per_hpage = 0; resv_map->css = NULL; } else { resv_map->reservation_counter = &h_cg->rsvd_hugepage[hstate_index(h)]; resv_map->pages_per_hpage = pages_per_huge_page(h); resv_map->css = &h_cg->css; } #endif } struct resv_map *resv_map_alloc(void) { struct resv_map *resv_map = kmalloc(sizeof(*resv_map), GFP_KERNEL); struct file_region *rg = kmalloc(sizeof(*rg), GFP_KERNEL); if (!resv_map || !rg) { kfree(resv_map); kfree(rg); return NULL; } kref_init(&resv_map->refs); spin_lock_init(&resv_map->lock); INIT_LIST_HEAD(&resv_map->regions); init_rwsem(&resv_map->rw_sema); resv_map->adds_in_progress = 0; /* * Initialize these to 0. On shared mappings, 0's here indicate these * fields don't do cgroup accounting. On private mappings, these will be * re-initialized to the proper values, to indicate that hugetlb cgroup * reservations are to be un-charged from here. */ resv_map_set_hugetlb_cgroup_uncharge_info(resv_map, NULL, NULL); INIT_LIST_HEAD(&resv_map->region_cache); list_add(&rg->link, &resv_map->region_cache); resv_map->region_cache_count = 1; return resv_map; } void resv_map_release(struct kref *ref) { struct resv_map *resv_map = container_of(ref, struct resv_map, refs); struct list_head *head = &resv_map->region_cache; struct file_region *rg, *trg; /* Clear out any active regions before we release the map. */ region_del(resv_map, 0, LONG_MAX); /* ... and any entries left in the cache */ list_for_each_entry_safe(rg, trg, head, link) { list_del(&rg->link); kfree(rg); } VM_BUG_ON(resv_map->adds_in_progress); kfree(resv_map); } static inline struct resv_map *inode_resv_map(struct inode *inode) { /* * At inode evict time, i_mapping may not point to the original * address space within the inode. This original address space * contains the pointer to the resv_map. So, always use the * address space embedded within the inode. * The VERY common case is inode->mapping == &inode->i_data but, * this may not be true for device special inodes. */ return (struct resv_map *)(&inode->i_data)->i_private_data; } static struct resv_map *vma_resv_map(struct vm_area_struct *vma) { VM_BUG_ON_VMA(!is_vm_hugetlb_page(vma), vma); if (vma->vm_flags & VM_MAYSHARE) { struct address_space *mapping = vma->vm_file->f_mapping; struct inode *inode = mapping->host; return inode_resv_map(inode); } else { return (struct resv_map *)(get_vma_private_data(vma) & ~HPAGE_RESV_MASK); } } static void set_vma_resv_map(struct vm_area_struct *vma, struct resv_map *map) { VM_BUG_ON_VMA(!is_vm_hugetlb_page(vma), vma); VM_BUG_ON_VMA(vma->vm_flags & VM_MAYSHARE, vma); set_vma_private_data(vma, (unsigned long)map); } static void set_vma_resv_flags(struct vm_area_struct *vma, unsigned long flags) { VM_BUG_ON_VMA(!is_vm_hugetlb_page(vma), vma); VM_BUG_ON_VMA(vma->vm_flags & VM_MAYSHARE, vma); set_vma_private_data(vma, get_vma_private_data(vma) | flags); } static int is_vma_resv_set(struct vm_area_struct *vma, unsigned long flag) { VM_BUG_ON_VMA(!is_vm_hugetlb_page(vma), vma); return (get_vma_private_data(vma) & flag) != 0; } bool __vma_private_lock(struct vm_area_struct *vma) { return !(vma->vm_flags & VM_MAYSHARE) && get_vma_private_data(vma) & ~HPAGE_RESV_MASK && is_vma_resv_set(vma, HPAGE_RESV_OWNER); } void hugetlb_dup_vma_private(struct vm_area_struct *vma) { VM_BUG_ON_VMA(!is_vm_hugetlb_page(vma), vma); /* * Clear vm_private_data * - For shared mappings this is a per-vma semaphore that may be * allocated in a subsequent call to hugetlb_vm_op_open. * Before clearing, make sure pointer is not associated with vma * as this will leak the structure. This is the case when called * via clear_vma_resv_huge_pages() and hugetlb_vm_op_open has already * been called to allocate a new structure. * - For MAP_PRIVATE mappings, this is the reserve map which does * not apply to children. Faults generated by the children are * not guaranteed to succeed, even if read-only. */ if (vma->vm_flags & VM_MAYSHARE) { struct hugetlb_vma_lock *vma_lock = vma->vm_private_data; if (vma_lock && vma_lock->vma != vma) vma->vm_private_data = NULL; } else vma->vm_private_data = NULL; } /* * Reset and decrement one ref on hugepage private reservation. * Called with mm->mmap_lock writer semaphore held. * This function should be only used by move_vma() and operate on * same sized vma. It should never come here with last ref on the * reservation. */ void clear_vma_resv_huge_pages(struct vm_area_struct *vma) { /* * Clear the old hugetlb private page reservation. * It has already been transferred to new_vma. * * During a mremap() operation of a hugetlb vma we call move_vma() * which copies vma into new_vma and unmaps vma. After the copy * operation both new_vma and vma share a reference to the resv_map * struct, and at that point vma is about to be unmapped. We don't * want to return the reservation to the pool at unmap of vma because * the reservation still lives on in new_vma, so simply decrement the * ref here and remove the resv_map reference from this vma. */ struct resv_map *reservations = vma_resv_map(vma); if (reservations && is_vma_resv_set(vma, HPAGE_RESV_OWNER)) { resv_map_put_hugetlb_cgroup_uncharge_info(reservations); kref_put(&reservations->refs, resv_map_release); } hugetlb_dup_vma_private(vma); } /* Returns true if the VMA has associated reserve pages */ static bool vma_has_reserves(struct vm_area_struct *vma, long chg) { if (vma->vm_flags & VM_NORESERVE) { /* * This address is already reserved by other process(chg == 0), * so, we should decrement reserved count. Without decrementing, * reserve count remains after releasing inode, because this * allocated page will go into page cache and is regarded as * coming from reserved pool in releasing step. Currently, we * don't have any other solution to deal with this situation * properly, so add work-around here. */ if (vma->vm_flags & VM_MAYSHARE && chg == 0) return true; else return false; } /* Shared mappings always use reserves */ if (vma->vm_flags & VM_MAYSHARE) { /* * We know VM_NORESERVE is not set. Therefore, there SHOULD * be a region map for all pages. The only situation where * there is no region map is if a hole was punched via * fallocate. In this case, there really are no reserves to * use. This situation is indicated if chg != 0. */ if (chg) return false; else return true; } /* * Only the process that called mmap() has reserves for * private mappings. */ if (is_vma_resv_set(vma, HPAGE_RESV_OWNER)) { /* * Like the shared case above, a hole punch or truncate * could have been performed on the private mapping. * Examine the value of chg to determine if reserves * actually exist or were previously consumed. * Very Subtle - The value of chg comes from a previous * call to vma_needs_reserves(). The reserve map for * private mappings has different (opposite) semantics * than that of shared mappings. vma_needs_reserves() * has already taken this difference in semantics into * account. Therefore, the meaning of chg is the same * as in the shared case above. Code could easily be * combined, but keeping it separate draws attention to * subtle differences. */ if (chg) return false; else return true; } return false; } static void enqueue_hugetlb_folio(struct hstate *h, struct folio *folio) { int nid = folio_nid(folio); lockdep_assert_held(&hugetlb_lock); VM_BUG_ON_FOLIO(folio_ref_count(folio), folio); list_move(&folio->lru, &h->hugepage_freelists[nid]); h->free_huge_pages++; h->free_huge_pages_node[nid]++; folio_set_hugetlb_freed(folio); } static struct folio *dequeue_hugetlb_folio_node_exact(struct hstate *h, int nid) { struct folio *folio; bool pin = !!(current->flags & PF_MEMALLOC_PIN); lockdep_assert_held(&hugetlb_lock); list_for_each_entry(folio, &h->hugepage_freelists[nid], lru) { if (pin && !folio_is_longterm_pinnable(folio)) continue; if (folio_test_hwpoison(folio)) continue; list_move(&folio->lru, &h->hugepage_activelist); folio_ref_unfreeze(folio, 1); folio_clear_hugetlb_freed(folio); h->free_huge_pages--; h->free_huge_pages_node[nid]--; return folio; } return NULL; } static struct folio *dequeue_hugetlb_folio_nodemask(struct hstate *h, gfp_t gfp_mask, int nid, nodemask_t *nmask) { unsigned int cpuset_mems_cookie; struct zonelist *zonelist; struct zone *zone; struct zoneref *z; int node = NUMA_NO_NODE; /* 'nid' should not be NUMA_NO_NODE. Try to catch any misuse of it and rectifiy. */ if (nid == NUMA_NO_NODE) nid = numa_node_id(); zonelist = node_zonelist(nid, gfp_mask); retry_cpuset: cpuset_mems_cookie = read_mems_allowed_begin(); for_each_zone_zonelist_nodemask(zone, z, zonelist, gfp_zone(gfp_mask), nmask) { struct folio *folio; if (!cpuset_zone_allowed(zone, gfp_mask)) continue; /* * no need to ask again on the same node. Pool is node rather than * zone aware */ if (zone_to_nid(zone) == node) continue; node = zone_to_nid(zone); folio = dequeue_hugetlb_folio_node_exact(h, node); if (folio) return folio; } if (unlikely(read_mems_allowed_retry(cpuset_mems_cookie))) goto retry_cpuset; return NULL; } static unsigned long available_huge_pages(struct hstate *h) { return h->free_huge_pages - h->resv_huge_pages; } static struct folio *dequeue_hugetlb_folio_vma(struct hstate *h, struct vm_area_struct *vma, unsigned long address, int avoid_reserve, long chg) { struct folio *folio = NULL; struct mempolicy *mpol; gfp_t gfp_mask; nodemask_t *nodemask; int nid; /* * A child process with MAP_PRIVATE mappings created by their parent * have no page reserves. This check ensures that reservations are * not "stolen". The child may still get SIGKILLed */ if (!vma_has_reserves(vma, chg) && !available_huge_pages(h)) goto err; /* If reserves cannot be used, ensure enough pages are in the pool */ if (avoid_reserve && !available_huge_pages(h)) goto err; gfp_mask = htlb_alloc_mask(h); nid = huge_node(vma, address, gfp_mask, &mpol, &nodemask); if (mpol_is_preferred_many(mpol)) { folio = dequeue_hugetlb_folio_nodemask(h, gfp_mask, nid, nodemask); /* Fallback to all nodes if page==NULL */ nodemask = NULL; } if (!folio) folio = dequeue_hugetlb_folio_nodemask(h, gfp_mask, nid, nodemask); if (folio && !avoid_reserve && vma_has_reserves(vma, chg)) { folio_set_hugetlb_restore_reserve(folio); h->resv_huge_pages--; } mpol_cond_put(mpol); return folio; err: return NULL; } /* * common helper functions for hstate_next_node_to_{alloc|free}. * We may have allocated or freed a huge page based on a different * nodes_allowed previously, so h->next_node_to_{alloc|free} might * be outside of *nodes_allowed. Ensure that we use an allowed * node for alloc or free. */ static int next_node_allowed(int nid, nodemask_t *nodes_allowed) { nid = next_node_in(nid, *nodes_allowed); VM_BUG_ON(nid >= MAX_NUMNODES); return nid; } static int get_valid_node_allowed(int nid, nodemask_t *nodes_allowed) { if (!node_isset(nid, *nodes_allowed)) nid = next_node_allowed(nid, nodes_allowed); return nid; } /* * returns the previously saved node ["this node"] from which to * allocate a persistent huge page for the pool and advance the * next node from which to allocate, handling wrap at end of node * mask. */ static int hstate_next_node_to_alloc(int *next_node, nodemask_t *nodes_allowed) { int nid; VM_BUG_ON(!nodes_allowed); nid = get_valid_node_allowed(*next_node, nodes_allowed); *next_node = next_node_allowed(nid, nodes_allowed); return nid; } /* * helper for remove_pool_hugetlb_folio() - return the previously saved * node ["this node"] from which to free a huge page. Advance the * next node id whether or not we find a free huge page to free so * that the next attempt to free addresses the next node. */ static int hstate_next_node_to_free(struct hstate *h, nodemask_t *nodes_allowed) { int nid; VM_BUG_ON(!nodes_allowed); nid = get_valid_node_allowed(h->next_nid_to_free, nodes_allowed); h->next_nid_to_free = next_node_allowed(nid, nodes_allowed); return nid; } #define for_each_node_mask_to_alloc(next_node, nr_nodes, node, mask) \ for (nr_nodes = nodes_weight(*mask); \ nr_nodes > 0 && \ ((node = hstate_next_node_to_alloc(next_node, mask)) || 1); \ nr_nodes--) #define for_each_node_mask_to_free(hs, nr_nodes, node, mask) \ for (nr_nodes = nodes_weight(*mask); \ nr_nodes > 0 && \ ((node = hstate_next_node_to_free(hs, mask)) || 1); \ nr_nodes--) #ifdef CONFIG_ARCH_HAS_GIGANTIC_PAGE #ifdef CONFIG_CONTIG_ALLOC static struct folio *alloc_gigantic_folio(struct hstate *h, gfp_t gfp_mask, int nid, nodemask_t *nodemask) { struct folio *folio; int order = huge_page_order(h); bool retried = false; if (nid == NUMA_NO_NODE) nid = numa_mem_id(); retry: folio = NULL; #ifdef CONFIG_CMA { int node; if (hugetlb_cma[nid]) folio = cma_alloc_folio(hugetlb_cma[nid], order, gfp_mask); if (!folio && !(gfp_mask & __GFP_THISNODE)) { for_each_node_mask(node, *nodemask) { if (node == nid || !hugetlb_cma[node]) continue; folio = cma_alloc_folio(hugetlb_cma[node], order, gfp_mask); if (folio) break; } } } #endif if (!folio) { folio = folio_alloc_gigantic(order, gfp_mask, nid, nodemask); if (!folio) return NULL; } if (folio_ref_freeze(folio, 1)) return folio; pr_warn("HugeTLB: unexpected refcount on PFN %lu\n", folio_pfn(folio)); hugetlb_free_folio(folio); if (!retried) { retried = true; goto retry; } return NULL; } #else /* !CONFIG_CONTIG_ALLOC */ static struct folio *alloc_gigantic_folio(struct hstate *h, gfp_t gfp_mask, int nid, nodemask_t *nodemask) { return NULL; } #endif /* CONFIG_CONTIG_ALLOC */ #else /* !CONFIG_ARCH_HAS_GIGANTIC_PAGE */ static struct folio *alloc_gigantic_folio(struct hstate *h, gfp_t gfp_mask, int nid, nodemask_t *nodemask) { return NULL; } #endif /* * Remove hugetlb folio from lists. * If vmemmap exists for the folio, clear the hugetlb flag so that the * folio appears as just a compound page. Otherwise, wait until after * allocating vmemmap to clear the flag. * * Must be called with hugetlb lock held. */ static void remove_hugetlb_folio(struct hstate *h, struct folio *folio, bool adjust_surplus) { int nid = folio_nid(folio); VM_BUG_ON_FOLIO(hugetlb_cgroup_from_folio(folio), folio); VM_BUG_ON_FOLIO(hugetlb_cgroup_from_folio_rsvd(folio), folio); lockdep_assert_held(&hugetlb_lock); if (hstate_is_gigantic(h) && !gigantic_page_runtime_supported()) return; list_del(&folio->lru); if (folio_test_hugetlb_freed(folio)) { folio_clear_hugetlb_freed(folio); h->free_huge_pages--; h->free_huge_pages_node[nid]--; } if (adjust_surplus) { h->surplus_huge_pages--; h->surplus_huge_pages_node[nid]--; } /* * We can only clear the hugetlb flag after allocating vmemmap * pages. Otherwise, someone (memory error handling) may try to write * to tail struct pages. */ if (!folio_test_hugetlb_vmemmap_optimized(folio)) __folio_clear_hugetlb(folio); h->nr_huge_pages--; h->nr_huge_pages_node[nid]--; } static void add_hugetlb_folio(struct hstate *h, struct folio *folio, bool adjust_surplus) { int nid = folio_nid(folio); VM_BUG_ON_FOLIO(!folio_test_hugetlb_vmemmap_optimized(folio), folio); lockdep_assert_held(&hugetlb_lock); INIT_LIST_HEAD(&folio->lru); h->nr_huge_pages++; h->nr_huge_pages_node[nid]++; if (adjust_surplus) { h->surplus_huge_pages++; h->surplus_huge_pages_node[nid]++; } __folio_set_hugetlb(folio); folio_change_private(folio, NULL); /* * We have to set hugetlb_vmemmap_optimized again as above * folio_change_private(folio, NULL) cleared it. */ folio_set_hugetlb_vmemmap_optimized(folio); arch_clear_hugetlb_flags(folio); enqueue_hugetlb_folio(h, folio); } static void __update_and_free_hugetlb_folio(struct hstate *h, struct folio *folio) { bool clear_flag = folio_test_hugetlb_vmemmap_optimized(folio); if (hstate_is_gigantic(h) && !gigantic_page_runtime_supported()) return; /* * If we don't know which subpages are hwpoisoned, we can't free * the hugepage, so it's leaked intentionally. */ if (folio_test_hugetlb_raw_hwp_unreliable(folio)) return; /* * If folio is not vmemmap optimized (!clear_flag), then the folio * is no longer identified as a hugetlb page. hugetlb_vmemmap_restore_folio * can only be passed hugetlb pages and will BUG otherwise. */ if (clear_flag && hugetlb_vmemmap_restore_folio(h, folio)) { spin_lock_irq(&hugetlb_lock); /* * If we cannot allocate vmemmap pages, just refuse to free the * page and put the page back on the hugetlb free list and treat * as a surplus page. */ add_hugetlb_folio(h, folio, true); spin_unlock_irq(&hugetlb_lock); return; } /* * If vmemmap pages were allocated above, then we need to clear the * hugetlb flag under the hugetlb lock. */ if (folio_test_hugetlb(folio)) { spin_lock_irq(&hugetlb_lock); __folio_clear_hugetlb(folio); spin_unlock_irq(&hugetlb_lock); } /* * Move PageHWPoison flag from head page to the raw error pages, * which makes any healthy subpages reusable. */ if (unlikely(folio_test_hwpoison(folio))) folio_clear_hugetlb_hwpoison(folio); folio_ref_unfreeze(folio, 1); INIT_LIST_HEAD(&folio->_deferred_list); hugetlb_free_folio(folio); } /* * As update_and_free_hugetlb_folio() can be called under any context, so we cannot * use GFP_KERNEL to allocate vmemmap pages. However, we can defer the * actual freeing in a workqueue to prevent from using GFP_ATOMIC to allocate * the vmemmap pages. * * free_hpage_workfn() locklessly retrieves the linked list of pages to be * freed and frees them one-by-one. As the page->mapping pointer is going * to be cleared in free_hpage_workfn() anyway, it is reused as the llist_node * structure of a lockless linked list of huge pages to be freed. */ static LLIST_HEAD(hpage_freelist); static void free_hpage_workfn(struct work_struct *work) { struct llist_node *node; node = llist_del_all(&hpage_freelist); while (node) { struct folio *folio; struct hstate *h; folio = container_of((struct address_space **)node, struct folio, mapping); node = node->next; folio->mapping = NULL; /* * The VM_BUG_ON_FOLIO(!folio_test_hugetlb(folio), folio) in * folio_hstate() is going to trigger because a previous call to * remove_hugetlb_folio() will clear the hugetlb bit, so do * not use folio_hstate() directly. */ h = size_to_hstate(folio_size(folio)); __update_and_free_hugetlb_folio(h, folio); cond_resched(); } } static DECLARE_WORK(free_hpage_work, free_hpage_workfn); static inline void flush_free_hpage_work(struct hstate *h) { if (hugetlb_vmemmap_optimizable(h)) flush_work(&free_hpage_work); } static void update_and_free_hugetlb_folio(struct hstate *h, struct folio *folio, bool atomic) { if (!folio_test_hugetlb_vmemmap_optimized(folio) || !atomic) { __update_and_free_hugetlb_folio(h, folio); return; } /* * Defer freeing to avoid using GFP_ATOMIC to allocate vmemmap pages. * * Only call schedule_work() if hpage_freelist is previously * empty. Otherwise, schedule_work() had been called but the workfn * hasn't retrieved the list yet. */ if (llist_add((struct llist_node *)&folio->mapping, &hpage_freelist)) schedule_work(&free_hpage_work); } static void bulk_vmemmap_restore_error(struct hstate *h, struct list_head *folio_list, struct list_head *non_hvo_folios) { struct folio *folio, *t_folio; if (!list_empty(non_hvo_folios)) { /* * Free any restored hugetlb pages so that restore of the * entire list can be retried. * The idea is that in the common case of ENOMEM errors freeing * hugetlb pages with vmemmap we will free up memory so that we * can allocate vmemmap for more hugetlb pages. */ list_for_each_entry_safe(folio, t_folio, non_hvo_folios, lru) { list_del(&folio->lru); spin_lock_irq(&hugetlb_lock); __folio_clear_hugetlb(folio); spin_unlock_irq(&hugetlb_lock); update_and_free_hugetlb_folio(h, folio, false); cond_resched(); } } else { /* * In the case where there are no folios which can be * immediately freed, we loop through the list trying to restore * vmemmap individually in the hope that someone elsewhere may * have done something to cause success (such as freeing some * memory). If unable to restore a hugetlb page, the hugetlb * page is made a surplus page and removed from the list. * If are able to restore vmemmap and free one hugetlb page, we * quit processing the list to retry the bulk operation. */ list_for_each_entry_safe(folio, t_folio, folio_list, lru) if (hugetlb_vmemmap_restore_folio(h, folio)) { list_del(&folio->lru); spin_lock_irq(&hugetlb_lock); add_hugetlb_folio(h, folio, true); spin_unlock_irq(&hugetlb_lock); } else { list_del(&folio->lru); spin_lock_irq(&hugetlb_lock); __folio_clear_hugetlb(folio); spin_unlock_irq(&hugetlb_lock); update_and_free_hugetlb_folio(h, folio, false); cond_resched(); break; } } } static void update_and_free_pages_bulk(struct hstate *h, struct list_head *folio_list) { long ret; struct folio *folio, *t_folio; LIST_HEAD(non_hvo_folios); /* * First allocate required vmemmmap (if necessary) for all folios. * Carefully handle errors and free up any available hugetlb pages * in an effort to make forward progress. */ retry: ret = hugetlb_vmemmap_restore_folios(h, folio_list, &non_hvo_folios); if (ret < 0) { bulk_vmemmap_restore_error(h, folio_list, &non_hvo_folios); goto retry; } /* * At this point, list should be empty, ret should be >= 0 and there * should only be pages on the non_hvo_folios list. * Do note that the non_hvo_folios list could be empty. * Without HVO enabled, ret will be 0 and there is no need to call * __folio_clear_hugetlb as this was done previously. */ VM_WARN_ON(!list_empty(folio_list)); VM_WARN_ON(ret < 0); if (!list_empty(&non_hvo_folios) && ret) { spin_lock_irq(&hugetlb_lock); list_for_each_entry(folio, &non_hvo_folios, lru) __folio_clear_hugetlb(folio); spin_unlock_irq(&hugetlb_lock); } list_for_each_entry_safe(folio, t_folio, &non_hvo_folios, lru) { update_and_free_hugetlb_folio(h, folio, false); cond_resched(); } } struct hstate *size_to_hstate(unsigned long size) { struct hstate *h; for_each_hstate(h) { if (huge_page_size(h) == size) return h; } return NULL; } void free_huge_folio(struct folio *folio) { /* * Can't pass hstate in here because it is called from the * generic mm code. */ struct hstate *h = folio_hstate(folio); int nid = folio_nid(folio); struct hugepage_subpool *spool = hugetlb_folio_subpool(folio); bool restore_reserve; unsigned long flags; VM_BUG_ON_FOLIO(folio_ref_count(folio), folio); VM_BUG_ON_FOLIO(folio_mapcount(folio), folio); hugetlb_set_folio_subpool(folio, NULL); if (folio_test_anon(folio)) __ClearPageAnonExclusive(&folio->page); folio->mapping = NULL; restore_reserve = folio_test_hugetlb_restore_reserve(folio); folio_clear_hugetlb_restore_reserve(folio); /* * If HPageRestoreReserve was set on page, page allocation consumed a * reservation. If the page was associated with a subpool, there * would have been a page reserved in the subpool before allocation * via hugepage_subpool_get_pages(). Since we are 'restoring' the * reservation, do not call hugepage_subpool_put_pages() as this will * remove the reserved page from the subpool. */ if (!restore_reserve) { /* * A return code of zero implies that the subpool will be * under its minimum size if the reservation is not restored * after page is free. Therefore, force restore_reserve * operation. */ if (hugepage_subpool_put_pages(spool, 1) == 0) restore_reserve = true; } spin_lock_irqsave(&hugetlb_lock, flags); folio_clear_hugetlb_migratable(folio); hugetlb_cgroup_uncharge_folio(hstate_index(h), pages_per_huge_page(h), folio); hugetlb_cgroup_uncharge_folio_rsvd(hstate_index(h), pages_per_huge_page(h), folio); lruvec_stat_mod_folio(folio, NR_HUGETLB, -pages_per_huge_page(h)); mem_cgroup_uncharge(folio); if (restore_reserve) h->resv_huge_pages++; if (folio_test_hugetlb_temporary(folio)) { remove_hugetlb_folio(h, folio, false); spin_unlock_irqrestore(&hugetlb_lock, flags); update_and_free_hugetlb_folio(h, folio, true); } else if (h->surplus_huge_pages_node[nid]) { /* remove the page from active list */ remove_hugetlb_folio(h, folio, true); spin_unlock_irqrestore(&hugetlb_lock, flags); update_and_free_hugetlb_folio(h, folio, true); } else { arch_clear_hugetlb_flags(folio); enqueue_hugetlb_folio(h, folio); spin_unlock_irqrestore(&hugetlb_lock, flags); } } /* * Must be called with the hugetlb lock held */ static void __prep_account_new_huge_page(struct hstate *h, int nid) { lockdep_assert_held(&hugetlb_lock); h->nr_huge_pages++; h->nr_huge_pages_node[nid]++; } static void init_new_hugetlb_folio(struct hstate *h, struct folio *folio) { __folio_set_hugetlb(folio); INIT_LIST_HEAD(&folio->lru); hugetlb_set_folio_subpool(folio, NULL); set_hugetlb_cgroup(folio, NULL); set_hugetlb_cgroup_rsvd(folio, NULL); } static void __prep_new_hugetlb_folio(struct hstate *h, struct folio *folio) { init_new_hugetlb_folio(h, folio); hugetlb_vmemmap_optimize_folio(h, folio); } static void prep_new_hugetlb_folio(struct hstate *h, struct folio *folio, int nid) { __prep_new_hugetlb_folio(h, folio); spin_lock_irq(&hugetlb_lock); __prep_account_new_huge_page(h, nid); spin_unlock_irq(&hugetlb_lock); } /* * Find and lock address space (mapping) in write mode. * * Upon entry, the folio is locked which means that folio_mapping() is * stable. Due to locking order, we can only trylock_write. If we can * not get the lock, simply return NULL to caller. */ struct address_space *hugetlb_folio_mapping_lock_write(struct folio *folio) { struct address_space *mapping = folio_mapping(folio); if (!mapping) return mapping; if (i_mmap_trylock_write(mapping)) return mapping; return NULL; } static struct folio *alloc_buddy_hugetlb_folio(struct hstate *h, gfp_t gfp_mask, int nid, nodemask_t *nmask, nodemask_t *node_alloc_noretry) { int order = huge_page_order(h); struct folio *folio; bool alloc_try_hard = true; bool retry = true; /* * By default we always try hard to allocate the folio with * __GFP_RETRY_MAYFAIL flag. However, if we are allocating folios in * a loop (to adjust global huge page counts) and previous allocation * failed, do not continue to try hard on the same node. Use the * node_alloc_noretry bitmap to manage this state information. */ if (node_alloc_noretry && node_isset(nid, *node_alloc_noretry)) alloc_try_hard = false; if (alloc_try_hard) gfp_mask |= __GFP_RETRY_MAYFAIL; if (nid == NUMA_NO_NODE) nid = numa_mem_id(); retry: folio = __folio_alloc(gfp_mask, order, nid, nmask); /* Ensure hugetlb folio won't have large_rmappable flag set. */ if (folio) folio_clear_large_rmappable(folio); if (folio && !folio_ref_freeze(folio, 1)) { folio_put(folio); if (retry) { /* retry once */ retry = false; goto retry; } /* WOW! twice in a row. */ pr_warn("HugeTLB unexpected inflated folio ref count\n"); folio = NULL; } /* * If we did not specify __GFP_RETRY_MAYFAIL, but still got a * folio this indicates an overall state change. Clear bit so * that we resume normal 'try hard' allocations. */ if (node_alloc_noretry && folio && !alloc_try_hard) node_clear(nid, *node_alloc_noretry); /* * If we tried hard to get a folio but failed, set bit so that * subsequent attempts will not try as hard until there is an * overall state change. */ if (node_alloc_noretry && !folio && alloc_try_hard) node_set(nid, *node_alloc_noretry); if (!folio) { __count_vm_event(HTLB_BUDDY_PGALLOC_FAIL); return NULL; } __count_vm_event(HTLB_BUDDY_PGALLOC); return folio; } static struct folio *only_alloc_fresh_hugetlb_folio(struct hstate *h, gfp_t gfp_mask, int nid, nodemask_t *nmask, nodemask_t *node_alloc_noretry) { struct folio *folio; if (hstate_is_gigantic(h)) folio = alloc_gigantic_folio(h, gfp_mask, nid, nmask); else folio = alloc_buddy_hugetlb_folio(h, gfp_mask, nid, nmask, node_alloc_noretry); if (folio) init_new_hugetlb_folio(h, folio); return folio; } /* * Common helper to allocate a fresh hugetlb page. All specific allocators * should use this function to get new hugetlb pages * * Note that returned page is 'frozen': ref count of head page and all tail * pages is zero. */ static struct folio *alloc_fresh_hugetlb_folio(struct hstate *h, gfp_t gfp_mask, int nid, nodemask_t *nmask) { struct folio *folio; if (hstate_is_gigantic(h)) folio = alloc_gigantic_folio(h, gfp_mask, nid, nmask); else folio = alloc_buddy_hugetlb_folio(h, gfp_mask, nid, nmask, NULL); if (!folio) return NULL; prep_new_hugetlb_folio(h, folio, folio_nid(folio)); return folio; } static void prep_and_add_allocated_folios(struct hstate *h, struct list_head *folio_list) { unsigned long flags; struct folio *folio, *tmp_f; /* Send list for bulk vmemmap optimization processing */ hugetlb_vmemmap_optimize_folios(h, folio_list); /* Add all new pool pages to free lists in one lock cycle */ spin_lock_irqsave(&hugetlb_lock, flags); list_for_each_entry_safe(folio, tmp_f, folio_list, lru) { __prep_account_new_huge_page(h, folio_nid(folio)); enqueue_hugetlb_folio(h, folio); } spin_unlock_irqrestore(&hugetlb_lock, flags); } /* * Allocates a fresh hugetlb page in a node interleaved manner. The page * will later be added to the appropriate hugetlb pool. */ static struct folio *alloc_pool_huge_folio(struct hstate *h, nodemask_t *nodes_allowed, nodemask_t *node_alloc_noretry, int *next_node) { gfp_t gfp_mask = htlb_alloc_mask(h) | __GFP_THISNODE; int nr_nodes, node; for_each_node_mask_to_alloc(next_node, nr_nodes, node, nodes_allowed) { struct folio *folio; folio = only_alloc_fresh_hugetlb_folio(h, gfp_mask, node, nodes_allowed, node_alloc_noretry); if (folio) return folio; } return NULL; } /* * Remove huge page from pool from next node to free. Attempt to keep * persistent huge pages more or less balanced over allowed nodes. * This routine only 'removes' the hugetlb page. The caller must make * an additional call to free the page to low level allocators. * Called with hugetlb_lock locked. */ static struct folio *remove_pool_hugetlb_folio(struct hstate *h, nodemask_t *nodes_allowed, bool acct_surplus) { int nr_nodes, node; struct folio *folio = NULL; lockdep_assert_held(&hugetlb_lock); for_each_node_mask_to_free(h, nr_nodes, node, nodes_allowed) { /* * If we're returning unused surplus pages, only examine * nodes with surplus pages. */ if ((!acct_surplus || h->surplus_huge_pages_node[node]) && !list_empty(&h->hugepage_freelists[node])) { folio = list_entry(h->hugepage_freelists[node].next, struct folio, lru); remove_hugetlb_folio(h, folio, acct_surplus); break; } } return folio; } /* * Dissolve a given free hugetlb folio into free buddy pages. This function * does nothing for in-use hugetlb folios and non-hugetlb folios. * This function returns values like below: * * -ENOMEM: failed to allocate vmemmap pages to free the freed hugepages * when the system is under memory pressure and the feature of * freeing unused vmemmap pages associated with each hugetlb page * is enabled. * -EBUSY: failed to dissolved free hugepages or the hugepage is in-use * (allocated or reserved.) * 0: successfully dissolved free hugepages or the page is not a * hugepage (considered as already dissolved) */ int dissolve_free_hugetlb_folio(struct folio *folio) { int rc = -EBUSY; retry: /* Not to disrupt normal path by vainly holding hugetlb_lock */ if (!folio_test_hugetlb(folio)) return 0; spin_lock_irq(&hugetlb_lock); if (!folio_test_hugetlb(folio)) { rc = 0; goto out; } if (!folio_ref_count(folio)) { struct hstate *h = folio_hstate(folio); if (!available_huge_pages(h)) goto out; /* * We should make sure that the page is already on the free list * when it is dissolved. */ if (unlikely(!folio_test_hugetlb_freed(folio))) { spin_unlock_irq(&hugetlb_lock); cond_resched(); /* * Theoretically, we should return -EBUSY when we * encounter this race. In fact, we have a chance * to successfully dissolve the page if we do a * retry. Because the race window is quite small. * If we seize this opportunity, it is an optimization * for increasing the success rate of dissolving page. */ goto retry; } remove_hugetlb_folio(h, folio, false); h->max_huge_pages--; spin_unlock_irq(&hugetlb_lock); /* * Normally update_and_free_hugtlb_folio will allocate required vmemmmap * before freeing the page. update_and_free_hugtlb_folio will fail to * free the page if it can not allocate required vmemmap. We * need to adjust max_huge_pages if the page is not freed. * Attempt to allocate vmemmmap here so that we can take * appropriate action on failure. * * The folio_test_hugetlb check here is because * remove_hugetlb_folio will clear hugetlb folio flag for * non-vmemmap optimized hugetlb folios. */ if (folio_test_hugetlb(folio)) { rc = hugetlb_vmemmap_restore_folio(h, folio); if (rc) { spin_lock_irq(&hugetlb_lock); add_hugetlb_folio(h, folio, false); h->max_huge_pages++; goto out; } } else rc = 0; update_and_free_hugetlb_folio(h, folio, false); return rc; } out: spin_unlock_irq(&hugetlb_lock); return rc; } /* * Dissolve free hugepages in a given pfn range. Used by memory hotplug to * make specified memory blocks removable from the system. * Note that this will dissolve a free gigantic hugepage completely, if any * part of it lies within the given range. * Also note that if dissolve_free_hugetlb_folio() returns with an error, all * free hugetlb folios that were dissolved before that error are lost. */ int dissolve_free_hugetlb_folios(unsigned long start_pfn, unsigned long end_pfn) { unsigned long pfn; struct folio *folio; int rc = 0; unsigned int order; struct hstate *h; if (!hugepages_supported()) return rc; order = huge_page_order(&default_hstate); for_each_hstate(h) order = min(order, huge_page_order(h)); for (pfn = start_pfn; pfn < end_pfn; pfn += 1 << order) { folio = pfn_folio(pfn); rc = dissolve_free_hugetlb_folio(folio); if (rc) break; } return rc; } /* * Allocates a fresh surplus page from the page allocator. */ static struct folio *alloc_surplus_hugetlb_folio(struct hstate *h, gfp_t gfp_mask, int nid, nodemask_t *nmask) { struct folio *folio = NULL; if (hstate_is_gigantic(h)) return NULL; spin_lock_irq(&hugetlb_lock); if (h->surplus_huge_pages >= h->nr_overcommit_huge_pages) goto out_unlock; spin_unlock_irq(&hugetlb_lock); folio = alloc_fresh_hugetlb_folio(h, gfp_mask, nid, nmask); if (!folio) return NULL; spin_lock_irq(&hugetlb_lock); /* * We could have raced with the pool size change. * Double check that and simply deallocate the new page * if we would end up overcommiting the surpluses. Abuse * temporary page to workaround the nasty free_huge_folio * codeflow */ if (h->surplus_huge_pages >= h->nr_overcommit_huge_pages) { folio_set_hugetlb_temporary(folio); spin_unlock_irq(&hugetlb_lock); free_huge_folio(folio); return NULL; } h->surplus_huge_pages++; h->surplus_huge_pages_node[folio_nid(folio)]++; out_unlock: spin_unlock_irq(&hugetlb_lock); return folio; } static struct folio *alloc_migrate_hugetlb_folio(struct hstate *h, gfp_t gfp_mask, int nid, nodemask_t *nmask) { struct folio *folio; if (hstate_is_gigantic(h)) return NULL; folio = alloc_fresh_hugetlb_folio(h, gfp_mask, nid, nmask); if (!folio) return NULL; /* fresh huge pages are frozen */ folio_ref_unfreeze(folio, 1); /* * We do not account these pages as surplus because they are only * temporary and will be released properly on the last reference */ folio_set_hugetlb_temporary(folio); return folio; } /* * Use the VMA's mpolicy to allocate a huge page from the buddy. */ static struct folio *alloc_buddy_hugetlb_folio_with_mpol(struct hstate *h, struct vm_area_struct *vma, unsigned long addr) { struct folio *folio = NULL; struct mempolicy *mpol; gfp_t gfp_mask = htlb_alloc_mask(h); int nid; nodemask_t *nodemask; nid = huge_node(vma, addr, gfp_mask, &mpol, &nodemask); if (mpol_is_preferred_many(mpol)) { gfp_t gfp = gfp_mask & ~(__GFP_DIRECT_RECLAIM | __GFP_NOFAIL); folio = alloc_surplus_hugetlb_folio(h, gfp, nid, nodemask); /* Fallback to all nodes if page==NULL */ nodemask = NULL; } if (!folio) folio = alloc_surplus_hugetlb_folio(h, gfp_mask, nid, nodemask); mpol_cond_put(mpol); return folio; } struct folio *alloc_hugetlb_folio_reserve(struct hstate *h, int preferred_nid, nodemask_t *nmask, gfp_t gfp_mask) { struct folio *folio; spin_lock_irq(&hugetlb_lock); folio = dequeue_hugetlb_folio_nodemask(h, gfp_mask, preferred_nid, nmask); if (folio) { VM_BUG_ON(!h->resv_huge_pages); h->resv_huge_pages--; } spin_unlock_irq(&hugetlb_lock); return folio; } /* folio migration callback function */ struct folio *alloc_hugetlb_folio_nodemask(struct hstate *h, int preferred_nid, nodemask_t *nmask, gfp_t gfp_mask, bool allow_alloc_fallback) { spin_lock_irq(&hugetlb_lock); if (available_huge_pages(h)) { struct folio *folio; folio = dequeue_hugetlb_folio_nodemask(h, gfp_mask, preferred_nid, nmask); if (folio) { spin_unlock_irq(&hugetlb_lock); return folio; } } spin_unlock_irq(&hugetlb_lock); /* We cannot fallback to other nodes, as we could break the per-node pool. */ if (!allow_alloc_fallback) gfp_mask |= __GFP_THISNODE; return alloc_migrate_hugetlb_folio(h, gfp_mask, preferred_nid, nmask); } static nodemask_t *policy_mbind_nodemask(gfp_t gfp) { #ifdef CONFIG_NUMA struct mempolicy *mpol = get_task_policy(current); /* * Only enforce MPOL_BIND policy which overlaps with cpuset policy * (from policy_nodemask) specifically for hugetlb case */ if (mpol->mode == MPOL_BIND && (apply_policy_zone(mpol, gfp_zone(gfp)) && cpuset_nodemask_valid_mems_allowed(&mpol->nodes))) return &mpol->nodes; #endif return NULL; } /* * Increase the hugetlb pool such that it can accommodate a reservation * of size 'delta'. */ static int gather_surplus_pages(struct hstate *h, long delta) __must_hold(&hugetlb_lock) { LIST_HEAD(surplus_list); struct folio *folio, *tmp; int ret; long i; long needed, allocated; bool alloc_ok = true; int node; nodemask_t *mbind_nodemask = policy_mbind_nodemask(htlb_alloc_mask(h)); lockdep_assert_held(&hugetlb_lock); needed = (h->resv_huge_pages + delta) - h->free_huge_pages; if (needed <= 0) { h->resv_huge_pages += delta; return 0; } allocated = 0; ret = -ENOMEM; retry: spin_unlock_irq(&hugetlb_lock); for (i = 0; i < needed; i++) { folio = NULL; for_each_node_mask(node, cpuset_current_mems_allowed) { if (!mbind_nodemask || node_isset(node, *mbind_nodemask)) { folio = alloc_surplus_hugetlb_folio(h, htlb_alloc_mask(h), node, NULL); if (folio) break; } } if (!folio) { alloc_ok = false; break; } list_add(&folio->lru, &surplus_list); cond_resched(); } allocated += i; /* * After retaking hugetlb_lock, we need to recalculate 'needed' * because either resv_huge_pages or free_huge_pages may have changed. */ spin_lock_irq(&hugetlb_lock); needed = (h->resv_huge_pages + delta) - (h->free_huge_pages + allocated); if (needed > 0) { if (alloc_ok) goto retry; /* * We were not able to allocate enough pages to * satisfy the entire reservation so we free what * we've allocated so far. */ goto free; } /* * The surplus_list now contains _at_least_ the number of extra pages * needed to accommodate the reservation. Add the appropriate number * of pages to the hugetlb pool and free the extras back to the buddy * allocator. Commit the entire reservation here to prevent another * process from stealing the pages as they are added to the pool but * before they are reserved. */ needed += allocated; h->resv_huge_pages += delta; ret = 0; /* Free the needed pages to the hugetlb pool */ list_for_each_entry_safe(folio, tmp, &surplus_list, lru) { if ((--needed) < 0) break; /* Add the page to the hugetlb allocator */ enqueue_hugetlb_folio(h, folio); } free: spin_unlock_irq(&hugetlb_lock); /* * Free unnecessary surplus pages to the buddy allocator. * Pages have no ref count, call free_huge_folio directly. */ list_for_each_entry_safe(folio, tmp, &surplus_list, lru) free_huge_folio(folio); spin_lock_irq(&hugetlb_lock); return ret; } /* * This routine has two main purposes: * 1) Decrement the reservation count (resv_huge_pages) by the value passed * in unused_resv_pages. This corresponds to the prior adjustments made * to the associated reservation map. * 2) Free any unused surplus pages that may have been allocated to satisfy * the reservation. As many as unused_resv_pages may be freed. */ static void return_unused_surplus_pages(struct hstate *h, unsigned long unused_resv_pages) { unsigned long nr_pages; LIST_HEAD(page_list); lockdep_assert_held(&hugetlb_lock); /* Uncommit the reservation */ h->resv_huge_pages -= unused_resv_pages; if (hstate_is_gigantic(h) && !gigantic_page_runtime_supported()) goto out; /* * Part (or even all) of the reservation could have been backed * by pre-allocated pages. Only free surplus pages. */ nr_pages = min(unused_resv_pages, h->surplus_huge_pages); /* * We want to release as many surplus pages as possible, spread * evenly across all nodes with memory. Iterate across these nodes * until we can no longer free unreserved surplus pages. This occurs * when the nodes with surplus pages have no free pages. * remove_pool_hugetlb_folio() will balance the freed pages across the * on-line nodes with memory and will handle the hstate accounting. */ while (nr_pages--) { struct folio *folio; folio = remove_pool_hugetlb_folio(h, &node_states[N_MEMORY], 1); if (!folio) goto out; list_add(&folio->lru, &page_list); } out: spin_unlock_irq(&hugetlb_lock); update_and_free_pages_bulk(h, &page_list); spin_lock_irq(&hugetlb_lock); } /* * vma_needs_reservation, vma_commit_reservation and vma_end_reservation * are used by the huge page allocation routines to manage reservations. * * vma_needs_reservation is called to determine if the huge page at addr * within the vma has an associated reservation. If a reservation is * needed, the value 1 is returned. The caller is then responsible for * managing the global reservation and subpool usage counts. After * the huge page has been allocated, vma_commit_reservation is called * to add the page to the reservation map. If the page allocation fails, * the reservation must be ended instead of committed. vma_end_reservation * is called in such cases. * * In the normal case, vma_commit_reservation returns the same value * as the preceding vma_needs_reservation call. The only time this * is not the case is if a reserve map was changed between calls. It * is the responsibility of the caller to notice the difference and * take appropriate action. * * vma_add_reservation is used in error paths where a reservation must * be restored when a newly allocated huge page must be freed. It is * to be called after calling vma_needs_reservation to determine if a * reservation exists. * * vma_del_reservation is used in error paths where an entry in the reserve * map was created during huge page allocation and must be removed. It is to * be called after calling vma_needs_reservation to determine if a reservation * exists. */ enum vma_resv_mode { VMA_NEEDS_RESV, VMA_COMMIT_RESV, VMA_END_RESV, VMA_ADD_RESV, VMA_DEL_RESV, }; static long __vma_reservation_common(struct hstate *h, struct vm_area_struct *vma, unsigned long addr, enum vma_resv_mode mode) { struct resv_map *resv; pgoff_t idx; long ret; long dummy_out_regions_needed; resv = vma_resv_map(vma); if (!resv) return 1; idx = vma_hugecache_offset(h, vma, addr); switch (mode) { case VMA_NEEDS_RESV: ret = region_chg(resv, idx, idx + 1, &dummy_out_regions_needed); /* We assume that vma_reservation_* routines always operate on * 1 page, and that adding to resv map a 1 page entry can only * ever require 1 region. */ VM_BUG_ON(dummy_out_regions_needed != 1); break; case VMA_COMMIT_RESV: ret = region_add(resv, idx, idx + 1, 1, NULL, NULL); /* region_add calls of range 1 should never fail. */ VM_BUG_ON(ret < 0); break; case VMA_END_RESV: region_abort(resv, idx, idx + 1, 1); ret = 0; break; case VMA_ADD_RESV: if (vma->vm_flags & VM_MAYSHARE) { ret = region_add(resv, idx, idx + 1, 1, NULL, NULL); /* region_add calls of range 1 should never fail. */ VM_BUG_ON(ret < 0); } else { region_abort(resv, idx, idx + 1, 1); ret = region_del(resv, idx, idx + 1); } break; case VMA_DEL_RESV: if (vma->vm_flags & VM_MAYSHARE) { region_abort(resv, idx, idx + 1, 1); ret = region_del(resv, idx, idx + 1); } else { ret = region_add(resv, idx, idx + 1, 1, NULL, NULL); /* region_add calls of range 1 should never fail. */ VM_BUG_ON(ret < 0); } break; default: BUG(); } if (vma->vm_flags & VM_MAYSHARE || mode == VMA_DEL_RESV) return ret; /* * We know private mapping must have HPAGE_RESV_OWNER set. * * In most cases, reserves always exist for private mappings. * However, a file associated with mapping could have been * hole punched or truncated after reserves were consumed. * As subsequent fault on such a range will not use reserves. * Subtle - The reserve map for private mappings has the * opposite meaning than that of shared mappings. If NO * entry is in the reserve map, it means a reservation exists. * If an entry exists in the reserve map, it means the * reservation has already been consumed. As a result, the * return value of this routine is the opposite of the * value returned from reserve map manipulation routines above. */ if (ret > 0) return 0; if (ret == 0) return 1; return ret; } static long vma_needs_reservation(struct hstate *h, struct vm_area_struct *vma, unsigned long addr) { return __vma_reservation_common(h, vma, addr, VMA_NEEDS_RESV); } static long vma_commit_reservation(struct hstate *h, struct vm_area_struct *vma, unsigned long addr) { return __vma_reservation_common(h, vma, addr, VMA_COMMIT_RESV); } static void vma_end_reservation(struct hstate *h, struct vm_area_struct *vma, unsigned long addr) { (void)__vma_reservation_common(h, vma, addr, VMA_END_RESV); } static long vma_add_reservation(struct hstate *h, struct vm_area_struct *vma, unsigned long addr) { return __vma_reservation_common(h, vma, addr, VMA_ADD_RESV); } static long vma_del_reservation(struct hstate *h, struct vm_area_struct *vma, unsigned long addr) { return __vma_reservation_common(h, vma, addr, VMA_DEL_RESV); } /* * This routine is called to restore reservation information on error paths. * It should ONLY be called for folios allocated via alloc_hugetlb_folio(), * and the hugetlb mutex should remain held when calling this routine. * * It handles two specific cases: * 1) A reservation was in place and the folio consumed the reservation. * hugetlb_restore_reserve is set in the folio. * 2) No reservation was in place for the page, so hugetlb_restore_reserve is * not set. However, alloc_hugetlb_folio always updates the reserve map. * * In case 1, free_huge_folio later in the error path will increment the * global reserve count. But, free_huge_folio does not have enough context * to adjust the reservation map. This case deals primarily with private * mappings. Adjust the reserve map here to be consistent with global * reserve count adjustments to be made by free_huge_folio. Make sure the * reserve map indicates there is a reservation present. * * In case 2, simply undo reserve map modifications done by alloc_hugetlb_folio. */ void restore_reserve_on_error(struct hstate *h, struct vm_area_struct *vma, unsigned long address, struct folio *folio) { long rc = vma_needs_reservation(h, vma, address); if (folio_test_hugetlb_restore_reserve(folio)) { if (unlikely(rc < 0)) /* * Rare out of memory condition in reserve map * manipulation. Clear hugetlb_restore_reserve so * that global reserve count will not be incremented * by free_huge_folio. This will make it appear * as though the reservation for this folio was * consumed. This may prevent the task from * faulting in the folio at a later time. This * is better than inconsistent global huge page * accounting of reserve counts. */ folio_clear_hugetlb_restore_reserve(folio); else if (rc) (void)vma_add_reservation(h, vma, address); else vma_end_reservation(h, vma, address); } else { if (!rc) { /* * This indicates there is an entry in the reserve map * not added by alloc_hugetlb_folio. We know it was added * before the alloc_hugetlb_folio call, otherwise * hugetlb_restore_reserve would be set on the folio. * Remove the entry so that a subsequent allocation * does not consume a reservation. */ rc = vma_del_reservation(h, vma, address); if (rc < 0) /* * VERY rare out of memory condition. Since * we can not delete the entry, set * hugetlb_restore_reserve so that the reserve * count will be incremented when the folio * is freed. This reserve will be consumed * on a subsequent allocation. */ folio_set_hugetlb_restore_reserve(folio); } else if (rc < 0) { /* * Rare out of memory condition from * vma_needs_reservation call. Memory allocation is * only attempted if a new entry is needed. Therefore, * this implies there is not an entry in the * reserve map. * * For shared mappings, no entry in the map indicates * no reservation. We are done. */ if (!(vma->vm_flags & VM_MAYSHARE)) /* * For private mappings, no entry indicates * a reservation is present. Since we can * not add an entry, set hugetlb_restore_reserve * on the folio so reserve count will be * incremented when freed. This reserve will * be consumed on a subsequent allocation. */ folio_set_hugetlb_restore_reserve(folio); } else /* * No reservation present, do nothing */ vma_end_reservation(h, vma, address); } } /* * alloc_and_dissolve_hugetlb_folio - Allocate a new folio and dissolve * the old one * @h: struct hstate old page belongs to * @old_folio: Old folio to dissolve * @list: List to isolate the page in case we need to * Returns 0 on success, otherwise negated error. */ static int alloc_and_dissolve_hugetlb_folio(struct hstate *h, struct folio *old_folio, struct list_head *list) { gfp_t gfp_mask = htlb_alloc_mask(h) | __GFP_THISNODE; int nid = folio_nid(old_folio); struct folio *new_folio = NULL; int ret = 0; retry: spin_lock_irq(&hugetlb_lock); if (!folio_test_hugetlb(old_folio)) { /* * Freed from under us. Drop new_folio too. */ goto free_new; } else if (folio_ref_count(old_folio)) { bool isolated; /* * Someone has grabbed the folio, try to isolate it here. * Fail with -EBUSY if not possible. */ spin_unlock_irq(&hugetlb_lock); isolated = isolate_hugetlb(old_folio, list); ret = isolated ? 0 : -EBUSY; spin_lock_irq(&hugetlb_lock); goto free_new; } else if (!folio_test_hugetlb_freed(old_folio)) { /* * Folio's refcount is 0 but it has not been enqueued in the * freelist yet. Race window is small, so we can succeed here if * we retry. */ spin_unlock_irq(&hugetlb_lock); cond_resched(); goto retry; } else { if (!new_folio) { spin_unlock_irq(&hugetlb_lock); new_folio = alloc_buddy_hugetlb_folio(h, gfp_mask, nid, NULL, NULL); if (!new_folio) return -ENOMEM; __prep_new_hugetlb_folio(h, new_folio); goto retry; } /* * Ok, old_folio is still a genuine free hugepage. Remove it from * the freelist and decrease the counters. These will be * incremented again when calling __prep_account_new_huge_page() * and enqueue_hugetlb_folio() for new_folio. The counters will * remain stable since this happens under the lock. */ remove_hugetlb_folio(h, old_folio, false); /* * Ref count on new_folio is already zero as it was dropped * earlier. It can be directly added to the pool free list. */ __prep_account_new_huge_page(h, nid); enqueue_hugetlb_folio(h, new_folio); /* * Folio has been replaced, we can safely free the old one. */ spin_unlock_irq(&hugetlb_lock); update_and_free_hugetlb_folio(h, old_folio, false); } return ret; free_new: spin_unlock_irq(&hugetlb_lock); if (new_folio) update_and_free_hugetlb_folio(h, new_folio, false); return ret; } int isolate_or_dissolve_huge_page(struct page *page, struct list_head *list) { struct hstate *h; struct folio *folio = page_folio(page); int ret = -EBUSY; /* * The page might have been dissolved from under our feet, so make sure * to carefully check the state under the lock. * Return success when racing as if we dissolved the page ourselves. */ spin_lock_irq(&hugetlb_lock); if (folio_test_hugetlb(folio)) { h = folio_hstate(folio); } else { spin_unlock_irq(&hugetlb_lock); return 0; } spin_unlock_irq(&hugetlb_lock); /* * Fence off gigantic pages as there is a cyclic dependency between * alloc_contig_range and them. Return -ENOMEM as this has the effect * of bailing out right away without further retrying. */ if (hstate_is_gigantic(h)) return -ENOMEM; if (folio_ref_count(folio) && isolate_hugetlb(folio, list)) ret = 0; else if (!folio_ref_count(folio)) ret = alloc_and_dissolve_hugetlb_folio(h, folio, list); return ret; } struct folio *alloc_hugetlb_folio(struct vm_area_struct *vma, unsigned long addr, int avoid_reserve) { struct hugepage_subpool *spool = subpool_vma(vma); struct hstate *h = hstate_vma(vma); struct folio *folio; long map_chg, map_commit, nr_pages = pages_per_huge_page(h); long gbl_chg; int memcg_charge_ret, ret, idx; struct hugetlb_cgroup *h_cg = NULL; struct mem_cgroup *memcg; bool deferred_reserve; gfp_t gfp = htlb_alloc_mask(h) | __GFP_RETRY_MAYFAIL; memcg = get_mem_cgroup_from_current(); memcg_charge_ret = mem_cgroup_hugetlb_try_charge(memcg, gfp, nr_pages); if (memcg_charge_ret == -ENOMEM) { mem_cgroup_put(memcg); return ERR_PTR(-ENOMEM); } idx = hstate_index(h); /* * Examine the region/reserve map to determine if the process * has a reservation for the page to be allocated. A return * code of zero indicates a reservation exists (no change). */ map_chg = gbl_chg = vma_needs_reservation(h, vma, addr); if (map_chg < 0) { if (!memcg_charge_ret) mem_cgroup_cancel_charge(memcg, nr_pages); mem_cgroup_put(memcg); return ERR_PTR(-ENOMEM); } /* * Processes that did not create the mapping will have no * reserves as indicated by the region/reserve map. Check * that the allocation will not exceed the subpool limit. * Allocations for MAP_NORESERVE mappings also need to be * checked against any subpool limit. */ if (map_chg || avoid_reserve) { gbl_chg = hugepage_subpool_get_pages(spool, 1); if (gbl_chg < 0) goto out_end_reservation; /* * Even though there was no reservation in the region/reserve * map, there could be reservations associated with the * subpool that can be used. This would be indicated if the * return value of hugepage_subpool_get_pages() is zero. * However, if avoid_reserve is specified we still avoid even * the subpool reservations. */ if (avoid_reserve) gbl_chg = 1; } /* If this allocation is not consuming a reservation, charge it now. */ deferred_reserve = map_chg || avoid_reserve; if (deferred_reserve) { ret = hugetlb_cgroup_charge_cgroup_rsvd( idx, pages_per_huge_page(h), &h_cg); if (ret) goto out_subpool_put; } ret = hugetlb_cgroup_charge_cgroup(idx, pages_per_huge_page(h), &h_cg); if (ret) goto out_uncharge_cgroup_reservation; spin_lock_irq(&hugetlb_lock); /* * glb_chg is passed to indicate whether or not a page must be taken * from the global free pool (global change). gbl_chg == 0 indicates * a reservation exists for the allocation. */ folio = dequeue_hugetlb_folio_vma(h, vma, addr, avoid_reserve, gbl_chg); if (!folio) { spin_unlock_irq(&hugetlb_lock); folio = alloc_buddy_hugetlb_folio_with_mpol(h, vma, addr); if (!folio) goto out_uncharge_cgroup; spin_lock_irq(&hugetlb_lock); if (!avoid_reserve && vma_has_reserves(vma, gbl_chg)) { folio_set_hugetlb_restore_reserve(folio); h->resv_huge_pages--; } list_add(&folio->lru, &h->hugepage_activelist); folio_ref_unfreeze(folio, 1); /* Fall through */ } hugetlb_cgroup_commit_charge(idx, pages_per_huge_page(h), h_cg, folio); /* If allocation is not consuming a reservation, also store the * hugetlb_cgroup pointer on the page. */ if (deferred_reserve) { hugetlb_cgroup_commit_charge_rsvd(idx, pages_per_huge_page(h), h_cg, folio); } spin_unlock_irq(&hugetlb_lock); hugetlb_set_folio_subpool(folio, spool); map_commit = vma_commit_reservation(h, vma, addr); if (unlikely(map_chg > map_commit)) { /* * The page was added to the reservation map between * vma_needs_reservation and vma_commit_reservation. * This indicates a race with hugetlb_reserve_pages. * Adjust for the subpool count incremented above AND * in hugetlb_reserve_pages for the same page. Also, * the reservation count added in hugetlb_reserve_pages * no longer applies. */ long rsv_adjust; rsv_adjust = hugepage_subpool_put_pages(spool, 1); hugetlb_acct_memory(h, -rsv_adjust); if (deferred_reserve) { spin_lock_irq(&hugetlb_lock); hugetlb_cgroup_uncharge_folio_rsvd(hstate_index(h), pages_per_huge_page(h), folio); spin_unlock_irq(&hugetlb_lock); } } if (!memcg_charge_ret) mem_cgroup_commit_charge(folio, memcg); lruvec_stat_mod_folio(folio, NR_HUGETLB, pages_per_huge_page(h)); mem_cgroup_put(memcg); return folio; out_uncharge_cgroup: hugetlb_cgroup_uncharge_cgroup(idx, pages_per_huge_page(h), h_cg); out_uncharge_cgroup_reservation: if (deferred_reserve) hugetlb_cgroup_uncharge_cgroup_rsvd(idx, pages_per_huge_page(h), h_cg); out_subpool_put: if (map_chg || avoid_reserve) hugepage_subpool_put_pages(spool, 1); out_end_reservation: vma_end_reservation(h, vma, addr); if (!memcg_charge_ret) mem_cgroup_cancel_charge(memcg, nr_pages); mem_cgroup_put(memcg); return ERR_PTR(-ENOSPC); } int alloc_bootmem_huge_page(struct hstate *h, int nid) __attribute__ ((weak, alias("__alloc_bootmem_huge_page"))); int __alloc_bootmem_huge_page(struct hstate *h, int nid) { struct huge_bootmem_page *m = NULL; /* initialize for clang */ int nr_nodes, node = nid; /* do node specific alloc */ if (nid != NUMA_NO_NODE) { m = memblock_alloc_try_nid_raw(huge_page_size(h), huge_page_size(h), 0, MEMBLOCK_ALLOC_ACCESSIBLE, nid); if (!m) return 0; goto found; } /* allocate from next node when distributing huge pages */ for_each_node_mask_to_alloc(&h->next_nid_to_alloc, nr_nodes, node, &node_states[N_MEMORY]) { m = memblock_alloc_try_nid_raw( huge_page_size(h), huge_page_size(h), 0, MEMBLOCK_ALLOC_ACCESSIBLE, node); /* * Use the beginning of the huge page to store the * huge_bootmem_page struct (until gather_bootmem * puts them into the mem_map). */ if (!m) return 0; goto found; } found: /* * Only initialize the head struct page in memmap_init_reserved_pages, * rest of the struct pages will be initialized by the HugeTLB * subsystem itself. * The head struct page is used to get folio information by the HugeTLB * subsystem like zone id and node id. */ memblock_reserved_mark_noinit(virt_to_phys((void *)m + PAGE_SIZE), huge_page_size(h) - PAGE_SIZE); /* Put them into a private list first because mem_map is not up yet */ INIT_LIST_HEAD(&m->list); list_add(&m->list, &huge_boot_pages[node]); m->hstate = h; return 1; } /* Initialize [start_page:end_page_number] tail struct pages of a hugepage */ static void __init hugetlb_folio_init_tail_vmemmap(struct folio *folio, unsigned long start_page_number, unsigned long end_page_number) { enum zone_type zone = zone_idx(folio_zone(folio)); int nid = folio_nid(folio); unsigned long head_pfn = folio_pfn(folio); unsigned long pfn, end_pfn = head_pfn + end_page_number; int ret; for (pfn = head_pfn + start_page_number; pfn < end_pfn; pfn++) { struct page *page = pfn_to_page(pfn); __ClearPageReserved(folio_page(folio, pfn - head_pfn)); __init_single_page(page, pfn, zone, nid); prep_compound_tail((struct page *)folio, pfn - head_pfn); ret = page_ref_freeze(page, 1); VM_BUG_ON(!ret); } } static void __init hugetlb_folio_init_vmemmap(struct folio *folio, struct hstate *h, unsigned long nr_pages) { int ret; /* Prepare folio head */ __folio_clear_reserved(folio); __folio_set_head(folio); ret = folio_ref_freeze(folio, 1); VM_BUG_ON(!ret); /* Initialize the necessary tail struct pages */ hugetlb_folio_init_tail_vmemmap(folio, 1, nr_pages); prep_compound_head((struct page *)folio, huge_page_order(h)); } static void __init prep_and_add_bootmem_folios(struct hstate *h, struct list_head *folio_list) { unsigned long flags; struct folio *folio, *tmp_f; /* Send list for bulk vmemmap optimization processing */ hugetlb_vmemmap_optimize_folios(h, folio_list); list_for_each_entry_safe(folio, tmp_f, folio_list, lru) { if (!folio_test_hugetlb_vmemmap_optimized(folio)) { /* * If HVO fails, initialize all tail struct pages * We do not worry about potential long lock hold * time as this is early in boot and there should * be no contention. */ hugetlb_folio_init_tail_vmemmap(folio, HUGETLB_VMEMMAP_RESERVE_PAGES, pages_per_huge_page(h)); } /* Subdivide locks to achieve better parallel performance */ spin_lock_irqsave(&hugetlb_lock, flags); __prep_account_new_huge_page(h, folio_nid(folio)); enqueue_hugetlb_folio(h, folio); spin_unlock_irqrestore(&hugetlb_lock, flags); } } /* * Put bootmem huge pages into the standard lists after mem_map is up. * Note: This only applies to gigantic (order > MAX_PAGE_ORDER) pages. */ static void __init gather_bootmem_prealloc_node(unsigned long nid) { LIST_HEAD(folio_list); struct huge_bootmem_page *m; struct hstate *h = NULL, *prev_h = NULL; list_for_each_entry(m, &huge_boot_pages[nid], list) { struct page *page = virt_to_page(m); struct folio *folio = (void *)page; h = m->hstate; /* * It is possible to have multiple huge page sizes (hstates) * in this list. If so, process each size separately. */ if (h != prev_h && prev_h != NULL) prep_and_add_bootmem_folios(prev_h, &folio_list); prev_h = h; VM_BUG_ON(!hstate_is_gigantic(h)); WARN_ON(folio_ref_count(folio) != 1); hugetlb_folio_init_vmemmap(folio, h, HUGETLB_VMEMMAP_RESERVE_PAGES); init_new_hugetlb_folio(h, folio); list_add(&folio->lru, &folio_list); /* * We need to restore the 'stolen' pages to totalram_pages * in order to fix confusing memory reports from free(1) and * other side-effects, like CommitLimit going negative. */ adjust_managed_page_count(page, pages_per_huge_page(h)); cond_resched(); } prep_and_add_bootmem_folios(h, &folio_list); } static void __init gather_bootmem_prealloc_parallel(unsigned long start, unsigned long end, void *arg) { int nid; for (nid = start; nid < end; nid++) gather_bootmem_prealloc_node(nid); } static void __init gather_bootmem_prealloc(void) { struct padata_mt_job job = { .thread_fn = gather_bootmem_prealloc_parallel, .fn_arg = NULL, .start = 0, .size = num_node_state(N_MEMORY), .align = 1, .min_chunk = 1, .max_threads = num_node_state(N_MEMORY), .numa_aware = true, }; padata_do_multithreaded(&job); } static void __init hugetlb_hstate_alloc_pages_onenode(struct hstate *h, int nid) { unsigned long i; char buf[32]; LIST_HEAD(folio_list); for (i = 0; i < h->max_huge_pages_node[nid]; ++i) { if (hstate_is_gigantic(h)) { if (!alloc_bootmem_huge_page(h, nid)) break; } else { struct folio *folio; gfp_t gfp_mask = htlb_alloc_mask(h) | __GFP_THISNODE; folio = only_alloc_fresh_hugetlb_folio(h, gfp_mask, nid, &node_states[N_MEMORY], NULL); if (!folio) break; list_add(&folio->lru, &folio_list); } cond_resched(); } if (!list_empty(&folio_list)) prep_and_add_allocated_folios(h, &folio_list); if (i == h->max_huge_pages_node[nid]) return; string_get_size(huge_page_size(h), 1, STRING_UNITS_2, buf, 32); pr_warn("HugeTLB: allocating %u of page size %s failed node%d. Only allocated %lu hugepages.\n", h->max_huge_pages_node[nid], buf, nid, i); h->max_huge_pages -= (h->max_huge_pages_node[nid] - i); h->max_huge_pages_node[nid] = i; } static bool __init hugetlb_hstate_alloc_pages_specific_nodes(struct hstate *h) { int i; bool node_specific_alloc = false; for_each_online_node(i) { if (h->max_huge_pages_node[i] > 0) { hugetlb_hstate_alloc_pages_onenode(h, i); node_specific_alloc = true; } } return node_specific_alloc; } static void __init hugetlb_hstate_alloc_pages_errcheck(unsigned long allocated, struct hstate *h) { if (allocated < h->max_huge_pages) { char buf[32]; string_get_size(huge_page_size(h), 1, STRING_UNITS_2, buf, 32); pr_warn("HugeTLB: allocating %lu of page size %s failed. Only allocated %lu hugepages.\n", h->max_huge_pages, buf, allocated); h->max_huge_pages = allocated; } } static void __init hugetlb_pages_alloc_boot_node(unsigned long start, unsigned long end, void *arg) { struct hstate *h = (struct hstate *)arg; int i, num = end - start; nodemask_t node_alloc_noretry; LIST_HEAD(folio_list); int next_node = first_online_node; /* Bit mask controlling how hard we retry per-node allocations.*/ nodes_clear(node_alloc_noretry); for (i = 0; i < num; ++i) { struct folio *folio = alloc_pool_huge_folio(h, &node_states[N_MEMORY], &node_alloc_noretry, &next_node); if (!folio) break; list_move(&folio->lru, &folio_list); cond_resched(); } prep_and_add_allocated_folios(h, &folio_list); } static unsigned long __init hugetlb_gigantic_pages_alloc_boot(struct hstate *h) { unsigned long i; for (i = 0; i < h->max_huge_pages; ++i) { if (!alloc_bootmem_huge_page(h, NUMA_NO_NODE)) break; cond_resched(); } return i; } static unsigned long __init hugetlb_pages_alloc_boot(struct hstate *h) { struct padata_mt_job job = { .fn_arg = h, .align = 1, .numa_aware = true }; job.thread_fn = hugetlb_pages_alloc_boot_node; job.start = 0; job.size = h->max_huge_pages; /* * job.max_threads is twice the num_node_state(N_MEMORY), * * Tests below indicate that a multiplier of 2 significantly improves * performance, and although larger values also provide improvements, * the gains are marginal. * * Therefore, choosing 2 as the multiplier strikes a good balance between * enhancing parallel processing capabilities and maintaining efficient * resource management. * * +------------+-------+-------+-------+-------+-------+ * | multiplier | 1 | 2 | 3 | 4 | 5 | * +------------+-------+-------+-------+-------+-------+ * | 256G 2node | 358ms | 215ms | 157ms | 134ms | 126ms | * | 2T 4node | 979ms | 679ms | 543ms | 489ms | 481ms | * | 50G 2node | 71ms | 44ms | 37ms | 30ms | 31ms | * +------------+-------+-------+-------+-------+-------+ */ job.max_threads = num_node_state(N_MEMORY) * 2; job.min_chunk = h->max_huge_pages / num_node_state(N_MEMORY) / 2; padata_do_multithreaded(&job); return h->nr_huge_pages; } /* * NOTE: this routine is called in different contexts for gigantic and * non-gigantic pages. * - For gigantic pages, this is called early in the boot process and * pages are allocated from memblock allocated or something similar. * Gigantic pages are actually added to pools later with the routine * gather_bootmem_prealloc. * - For non-gigantic pages, this is called later in the boot process after * all of mm is up and functional. Pages are allocated from buddy and * then added to hugetlb pools. */ static void __init hugetlb_hstate_alloc_pages(struct hstate *h) { unsigned long allocated; static bool initialized __initdata; /* skip gigantic hugepages allocation if hugetlb_cma enabled */ if (hstate_is_gigantic(h) && hugetlb_cma_size) { pr_warn_once("HugeTLB: hugetlb_cma is enabled, skip boot time allocation\n"); return; } /* hugetlb_hstate_alloc_pages will be called many times, initialize huge_boot_pages once */ if (!initialized) { int i = 0; for (i = 0; i < MAX_NUMNODES; i++) INIT_LIST_HEAD(&huge_boot_pages[i]); initialized = true; } /* do node specific alloc */ if (hugetlb_hstate_alloc_pages_specific_nodes(h)) return; /* below will do all node balanced alloc */ if (hstate_is_gigantic(h)) allocated = hugetlb_gigantic_pages_alloc_boot(h); else allocated = hugetlb_pages_alloc_boot(h); hugetlb_hstate_alloc_pages_errcheck(allocated, h); } static void __init hugetlb_init_hstates(void) { struct hstate *h, *h2; for_each_hstate(h) { /* oversize hugepages were init'ed in early boot */ if (!hstate_is_gigantic(h)) hugetlb_hstate_alloc_pages(h); /* * Set demote order for each hstate. Note that * h->demote_order is initially 0. * - We can not demote gigantic pages if runtime freeing * is not supported, so skip this. * - If CMA allocation is possible, we can not demote * HUGETLB_PAGE_ORDER or smaller size pages. */ if (hstate_is_gigantic(h) && !gigantic_page_runtime_supported()) continue; if (hugetlb_cma_size && h->order <= HUGETLB_PAGE_ORDER) continue; for_each_hstate(h2) { if (h2 == h) continue; if (h2->order < h->order && h2->order > h->demote_order) h->demote_order = h2->order; } } } static void __init report_hugepages(void) { struct hstate *h; for_each_hstate(h) { char buf[32]; string_get_size(huge_page_size(h), 1, STRING_UNITS_2, buf, 32); pr_info("HugeTLB: registered %s page size, pre-allocated %ld pages\n", buf, h->free_huge_pages); pr_info("HugeTLB: %d KiB vmemmap can be freed for a %s page\n", hugetlb_vmemmap_optimizable_size(h) / SZ_1K, buf); } } #ifdef CONFIG_HIGHMEM static void try_to_free_low(struct hstate *h, unsigned long count, nodemask_t *nodes_allowed) { int i; LIST_HEAD(page_list); lockdep_assert_held(&hugetlb_lock); if (hstate_is_gigantic(h)) return; /* * Collect pages to be freed on a list, and free after dropping lock */ for_each_node_mask(i, *nodes_allowed) { struct folio *folio, *next; struct list_head *freel = &h->hugepage_freelists[i]; list_for_each_entry_safe(folio, next, freel, lru) { if (count >= h->nr_huge_pages) goto out; if (folio_test_highmem(folio)) continue; remove_hugetlb_folio(h, folio, false); list_add(&folio->lru, &page_list); } } out: spin_unlock_irq(&hugetlb_lock); update_and_free_pages_bulk(h, &page_list); spin_lock_irq(&hugetlb_lock); } #else static inline void try_to_free_low(struct hstate *h, unsigned long count, nodemask_t *nodes_allowed) { } #endif /* * Increment or decrement surplus_huge_pages. Keep node-specific counters * balanced by operating on them in a round-robin fashion. * Returns 1 if an adjustment was made. */ static int adjust_pool_surplus(struct hstate *h, nodemask_t *nodes_allowed, int delta) { int nr_nodes, node; lockdep_assert_held(&hugetlb_lock); VM_BUG_ON(delta != -1 && delta != 1); if (delta < 0) { for_each_node_mask_to_alloc(&h->next_nid_to_alloc, nr_nodes, node, nodes_allowed) { if (h->surplus_huge_pages_node[node]) goto found; } } else { for_each_node_mask_to_free(h, nr_nodes, node, nodes_allowed) { if (h->surplus_huge_pages_node[node] < h->nr_huge_pages_node[node]) goto found; } } return 0; found: h->surplus_huge_pages += delta; h->surplus_huge_pages_node[node] += delta; return 1; } #define persistent_huge_pages(h) (h->nr_huge_pages - h->surplus_huge_pages) static int set_max_huge_pages(struct hstate *h, unsigned long count, int nid, nodemask_t *nodes_allowed) { unsigned long min_count; unsigned long allocated; struct folio *folio; LIST_HEAD(page_list); NODEMASK_ALLOC(nodemask_t, node_alloc_noretry, GFP_KERNEL); /* * Bit mask controlling how hard we retry per-node allocations. * If we can not allocate the bit mask, do not attempt to allocate * the requested huge pages. */ if (node_alloc_noretry) nodes_clear(*node_alloc_noretry); else return -ENOMEM; /* * resize_lock mutex prevents concurrent adjustments to number of * pages in hstate via the proc/sysfs interfaces. */ mutex_lock(&h->resize_lock); flush_free_hpage_work(h); spin_lock_irq(&hugetlb_lock); /* * Check for a node specific request. * Changing node specific huge page count may require a corresponding * change to the global count. In any case, the passed node mask * (nodes_allowed) will restrict alloc/free to the specified node. */ if (nid != NUMA_NO_NODE) { unsigned long old_count = count; count += persistent_huge_pages(h) - (h->nr_huge_pages_node[nid] - h->surplus_huge_pages_node[nid]); /* * User may have specified a large count value which caused the * above calculation to overflow. In this case, they wanted * to allocate as many huge pages as possible. Set count to * largest possible value to align with their intention. */ if (count < old_count) count = ULONG_MAX; } /* * Gigantic pages runtime allocation depend on the capability for large * page range allocation. * If the system does not provide this feature, return an error when * the user tries to allocate gigantic pages but let the user free the * boottime allocated gigantic pages. */ if (hstate_is_gigantic(h) && !IS_ENABLED(CONFIG_CONTIG_ALLOC)) { if (count > persistent_huge_pages(h)) { spin_unlock_irq(&hugetlb_lock); mutex_unlock(&h->resize_lock); NODEMASK_FREE(node_alloc_noretry); return -EINVAL; } /* Fall through to decrease pool */ } /* * Increase the pool size * First take pages out of surplus state. Then make up the * remaining difference by allocating fresh huge pages. * * We might race with alloc_surplus_hugetlb_folio() here and be unable * to convert a surplus huge page to a normal huge page. That is * not critical, though, it just means the overall size of the * pool might be one hugepage larger than it needs to be, but * within all the constraints specified by the sysctls. */ while (h->surplus_huge_pages && count > persistent_huge_pages(h)) { if (!adjust_pool_surplus(h, nodes_allowed, -1)) break; } allocated = 0; while (count > (persistent_huge_pages(h) + allocated)) { /* * If this allocation races such that we no longer need the * page, free_huge_folio will handle it by freeing the page * and reducing the surplus. */ spin_unlock_irq(&hugetlb_lock); /* yield cpu to avoid soft lockup */ cond_resched(); folio = alloc_pool_huge_folio(h, nodes_allowed, node_alloc_noretry, &h->next_nid_to_alloc); if (!folio) { prep_and_add_allocated_folios(h, &page_list); spin_lock_irq(&hugetlb_lock); goto out; } list_add(&folio->lru, &page_list); allocated++; /* Bail for signals. Probably ctrl-c from user */ if (signal_pending(current)) { prep_and_add_allocated_folios(h, &page_list); spin_lock_irq(&hugetlb_lock); goto out; } spin_lock_irq(&hugetlb_lock); } /* Add allocated pages to the pool */ if (!list_empty(&page_list)) { spin_unlock_irq(&hugetlb_lock); prep_and_add_allocated_folios(h, &page_list); spin_lock_irq(&hugetlb_lock); } /* * Decrease the pool size * First return free pages to the buddy allocator (being careful * to keep enough around to satisfy reservations). Then place * pages into surplus state as needed so the pool will shrink * to the desired size as pages become free. * * By placing pages into the surplus state independent of the * overcommit value, we are allowing the surplus pool size to * exceed overcommit. There are few sane options here. Since * alloc_surplus_hugetlb_folio() is checking the global counter, * though, we'll note that we're not allowed to exceed surplus * and won't grow the pool anywhere else. Not until one of the * sysctls are changed, or the surplus pages go out of use. */ min_count = h->resv_huge_pages + h->nr_huge_pages - h->free_huge_pages; min_count = max(count, min_count); try_to_free_low(h, min_count, nodes_allowed); /* * Collect pages to be removed on list without dropping lock */ while (min_count < persistent_huge_pages(h)) { folio = remove_pool_hugetlb_folio(h, nodes_allowed, 0); if (!folio) break; list_add(&folio->lru, &page_list); } /* free the pages after dropping lock */ spin_unlock_irq(&hugetlb_lock); update_and_free_pages_bulk(h, &page_list); flush_free_hpage_work(h); spin_lock_irq(&hugetlb_lock); while (count < persistent_huge_pages(h)) { if (!adjust_pool_surplus(h, nodes_allowed, 1)) break; } out: h->max_huge_pages = persistent_huge_pages(h); spin_unlock_irq(&hugetlb_lock); mutex_unlock(&h->resize_lock); NODEMASK_FREE(node_alloc_noretry); return 0; } static long demote_free_hugetlb_folios(struct hstate *src, struct hstate *dst, struct list_head *src_list) { long rc; struct folio *folio, *next; LIST_HEAD(dst_list); LIST_HEAD(ret_list); rc = hugetlb_vmemmap_restore_folios(src, src_list, &ret_list); list_splice_init(&ret_list, src_list); /* * Taking target hstate mutex synchronizes with set_max_huge_pages. * Without the mutex, pages added to target hstate could be marked * as surplus. * * Note that we already hold src->resize_lock. To prevent deadlock, * use the convention of always taking larger size hstate mutex first. */ mutex_lock(&dst->resize_lock); list_for_each_entry_safe(folio, next, src_list, lru) { int i; if (folio_test_hugetlb_vmemmap_optimized(folio)) continue; list_del(&folio->lru); split_page_owner(&folio->page, huge_page_order(src), huge_page_order(dst)); pgalloc_tag_split(folio, huge_page_order(src), huge_page_order(dst)); for (i = 0; i < pages_per_huge_page(src); i += pages_per_huge_page(dst)) { struct page *page = folio_page(folio, i); page->mapping = NULL; clear_compound_head(page); prep_compound_page(page, dst->order); init_new_hugetlb_folio(dst, page_folio(page)); list_add(&page->lru, &dst_list); } } prep_and_add_allocated_folios(dst, &dst_list); mutex_unlock(&dst->resize_lock); return rc; } static long demote_pool_huge_page(struct hstate *src, nodemask_t *nodes_allowed, unsigned long nr_to_demote) __must_hold(&hugetlb_lock) { int nr_nodes, node; struct hstate *dst; long rc = 0; long nr_demoted = 0; lockdep_assert_held(&hugetlb_lock); /* We should never get here if no demote order */ if (!src->demote_order) { pr_warn("HugeTLB: NULL demote order passed to demote_pool_huge_page.\n"); return -EINVAL; /* internal error */ } dst = size_to_hstate(PAGE_SIZE << src->demote_order); for_each_node_mask_to_free(src, nr_nodes, node, nodes_allowed) { LIST_HEAD(list); struct folio *folio, *next; list_for_each_entry_safe(folio, next, &src->hugepage_freelists[node], lru) { if (folio_test_hwpoison(folio)) continue; remove_hugetlb_folio(src, folio, false); list_add(&folio->lru, &list); if (++nr_demoted == nr_to_demote) break; } spin_unlock_irq(&hugetlb_lock); rc = demote_free_hugetlb_folios(src, dst, &list); spin_lock_irq(&hugetlb_lock); list_for_each_entry_safe(folio, next, &list, lru) { list_del(&folio->lru); add_hugetlb_folio(src, folio, false); nr_demoted--; } if (rc < 0 || nr_demoted == nr_to_demote) break; } /* * Not absolutely necessary, but for consistency update max_huge_pages * based on pool changes for the demoted page. */ src->max_huge_pages -= nr_demoted; dst->max_huge_pages += nr_demoted << (huge_page_order(src) - huge_page_order(dst)); if (rc < 0) return rc; if (nr_demoted) return nr_demoted; /* * Only way to get here is if all pages on free lists are poisoned. * Return -EBUSY so that caller will not retry. */ return -EBUSY; } #define HSTATE_ATTR_RO(_name) \ static struct kobj_attribute _name##_attr = __ATTR_RO(_name) #define HSTATE_ATTR_WO(_name) \ static struct kobj_attribute _name##_attr = __ATTR_WO(_name) #define HSTATE_ATTR(_name) \ static struct kobj_attribute _name##_attr = __ATTR_RW(_name) static struct kobject *hugepages_kobj; static struct kobject *hstate_kobjs[HUGE_MAX_HSTATE]; static struct hstate *kobj_to_node_hstate(struct kobject *kobj, int *nidp); static struct hstate *kobj_to_hstate(struct kobject *kobj, int *nidp) { int i; for (i = 0; i < HUGE_MAX_HSTATE; i++) if (hstate_kobjs[i] == kobj) { if (nidp) *nidp = NUMA_NO_NODE; return &hstates[i]; } return kobj_to_node_hstate(kobj, nidp); } static ssize_t nr_hugepages_show_common(struct kobject *kobj, struct kobj_attribute *attr, char *buf) { struct hstate *h; unsigned long nr_huge_pages; int nid; h = kobj_to_hstate(kobj, &nid); if (nid == NUMA_NO_NODE) nr_huge_pages = h->nr_huge_pages; else nr_huge_pages = h->nr_huge_pages_node[nid]; return sysfs_emit(buf, "%lu\n", nr_huge_pages); } static ssize_t __nr_hugepages_store_common(bool obey_mempolicy, struct hstate *h, int nid, unsigned long count, size_t len) { int err; nodemask_t nodes_allowed, *n_mask; if (hstate_is_gigantic(h) && !gigantic_page_runtime_supported()) return -EINVAL; if (nid == NUMA_NO_NODE) { /* * global hstate attribute */ if (!(obey_mempolicy && init_nodemask_of_mempolicy(&nodes_allowed))) n_mask = &node_states[N_MEMORY]; else n_mask = &nodes_allowed; } else { /* * Node specific request. count adjustment happens in * set_max_huge_pages() after acquiring hugetlb_lock. */ init_nodemask_of_node(&nodes_allowed, nid); n_mask = &nodes_allowed; } err = set_max_huge_pages(h, count, nid, n_mask); return err ? err : len; } static ssize_t nr_hugepages_store_common(bool obey_mempolicy, struct kobject *kobj, const char *buf, size_t len) { struct hstate *h; unsigned long count; int nid; int err; err = kstrtoul(buf, 10, &count); if (err) return err; h = kobj_to_hstate(kobj, &nid); return __nr_hugepages_store_common(obey_mempolicy, h, nid, count, len); } static ssize_t nr_hugepages_show(struct kobject *kobj, struct kobj_attribute *attr, char *buf) { return nr_hugepages_show_common(kobj, attr, buf); } static ssize_t nr_hugepages_store(struct kobject *kobj, struct kobj_attribute *attr, const char *buf, size_t len) { return nr_hugepages_store_common(false, kobj, buf, len); } HSTATE_ATTR(nr_hugepages); #ifdef CONFIG_NUMA /* * hstate attribute for optionally mempolicy-based constraint on persistent * huge page alloc/free. */ static ssize_t nr_hugepages_mempolicy_show(struct kobject *kobj, struct kobj_attribute *attr, char *buf) { return nr_hugepages_show_common(kobj, attr, buf); } static ssize_t nr_hugepages_mempolicy_store(struct kobject *kobj, struct kobj_attribute *attr, const char *buf, size_t len) { return nr_hugepages_store_common(true, kobj, buf, len); } HSTATE_ATTR(nr_hugepages_mempolicy); #endif static ssize_t nr_overcommit_hugepages_show(struct kobject *kobj, struct kobj_attribute *attr, char *buf) { struct hstate *h = kobj_to_hstate(kobj, NULL); return sysfs_emit(buf, "%lu\n", h->nr_overcommit_huge_pages); } static ssize_t nr_overcommit_hugepages_store(struct kobject *kobj, struct kobj_attribute *attr, const char *buf, size_t count) { int err; unsigned long input; struct hstate *h = kobj_to_hstate(kobj, NULL); if (hstate_is_gigantic(h)) return -EINVAL; err = kstrtoul(buf, 10, &input); if (err) return err; spin_lock_irq(&hugetlb_lock); h->nr_overcommit_huge_pages = input; spin_unlock_irq(&hugetlb_lock); return count; } HSTATE_ATTR(nr_overcommit_hugepages); static ssize_t free_hugepages_show(struct kobject *kobj, struct kobj_attribute *attr, char *buf) { struct hstate *h; unsigned long free_huge_pages; int nid; h = kobj_to_hstate(kobj, &nid); if (nid == NUMA_NO_NODE) free_huge_pages = h->free_huge_pages; else free_huge_pages = h->free_huge_pages_node[nid]; return sysfs_emit(buf, "%lu\n", free_huge_pages); } HSTATE_ATTR_RO(free_hugepages); static ssize_t resv_hugepages_show(struct kobject *kobj, struct kobj_attribute *attr, char *buf) { struct hstate *h = kobj_to_hstate(kobj, NULL); return sysfs_emit(buf, "%lu\n", h->resv_huge_pages); } HSTATE_ATTR_RO(resv_hugepages); static ssize_t surplus_hugepages_show(struct kobject *kobj, struct kobj_attribute *attr, char *buf) { struct hstate *h; unsigned long surplus_huge_pages; int nid; h = kobj_to_hstate(kobj, &nid); if (nid == NUMA_NO_NODE) surplus_huge_pages = h->surplus_huge_pages; else surplus_huge_pages = h->surplus_huge_pages_node[nid]; return sysfs_emit(buf, "%lu\n", surplus_huge_pages); } HSTATE_ATTR_RO(surplus_hugepages); static ssize_t demote_store(struct kobject *kobj, struct kobj_attribute *attr, const char *buf, size_t len) { unsigned long nr_demote; unsigned long nr_available; nodemask_t nodes_allowed, *n_mask; struct hstate *h; int err; int nid; err = kstrtoul(buf, 10, &nr_demote); if (err) return err; h = kobj_to_hstate(kobj, &nid); if (nid != NUMA_NO_NODE) { init_nodemask_of_node(&nodes_allowed, nid); n_mask = &nodes_allowed; } else { n_mask = &node_states[N_MEMORY]; } /* Synchronize with other sysfs operations modifying huge pages */ mutex_lock(&h->resize_lock); spin_lock_irq(&hugetlb_lock); while (nr_demote) { long rc; /* * Check for available pages to demote each time thorough the * loop as demote_pool_huge_page will drop hugetlb_lock. */ if (nid != NUMA_NO_NODE) nr_available = h->free_huge_pages_node[nid]; else nr_available = h->free_huge_pages; nr_available -= h->resv_huge_pages; if (!nr_available) break; rc = demote_pool_huge_page(h, n_mask, nr_demote); if (rc < 0) { err = rc; break; } nr_demote -= rc; } spin_unlock_irq(&hugetlb_lock); mutex_unlock(&h->resize_lock); if (err) return err; return len; } HSTATE_ATTR_WO(demote); static ssize_t demote_size_show(struct kobject *kobj, struct kobj_attribute *attr, char *buf) { struct hstate *h = kobj_to_hstate(kobj, NULL); unsigned long demote_size = (PAGE_SIZE << h->demote_order) / SZ_1K; return sysfs_emit(buf, "%lukB\n", demote_size); } static ssize_t demote_size_store(struct kobject *kobj, struct kobj_attribute *attr, const char *buf, size_t count) { struct hstate *h, *demote_hstate; unsigned long demote_size; unsigned int demote_order; demote_size = (unsigned long)memparse(buf, NULL); demote_hstate = size_to_hstate(demote_size); if (!demote_hstate) return -EINVAL; demote_order = demote_hstate->order; if (demote_order < HUGETLB_PAGE_ORDER) return -EINVAL; /* demote order must be smaller than hstate order */ h = kobj_to_hstate(kobj, NULL); if (demote_order >= h->order) return -EINVAL; /* resize_lock synchronizes access to demote size and writes */ mutex_lock(&h->resize_lock); h->demote_order = demote_order; mutex_unlock(&h->resize_lock); return count; } HSTATE_ATTR(demote_size); static struct attribute *hstate_attrs[] = { &nr_hugepages_attr.attr, &nr_overcommit_hugepages_attr.attr, &free_hugepages_attr.attr, &resv_hugepages_attr.attr, &surplus_hugepages_attr.attr, #ifdef CONFIG_NUMA &nr_hugepages_mempolicy_attr.attr, #endif NULL, }; static const struct attribute_group hstate_attr_group = { .attrs = hstate_attrs, }; static struct attribute *hstate_demote_attrs[] = { &demote_size_attr.attr, &demote_attr.attr, NULL, }; static const struct attribute_group hstate_demote_attr_group = { .attrs = hstate_demote_attrs, }; static int hugetlb_sysfs_add_hstate(struct hstate *h, struct kobject *parent, struct kobject **hstate_kobjs, const struct attribute_group *hstate_attr_group) { int retval; int hi = hstate_index(h); hstate_kobjs[hi] = kobject_create_and_add(h->name, parent); if (!hstate_kobjs[hi]) return -ENOMEM; retval = sysfs_create_group(hstate_kobjs[hi], hstate_attr_group); if (retval) { kobject_put(hstate_kobjs[hi]); hstate_kobjs[hi] = NULL; return retval; } if (h->demote_order) { retval = sysfs_create_group(hstate_kobjs[hi], &hstate_demote_attr_group); if (retval) { pr_warn("HugeTLB unable to create demote interfaces for %s\n", h->name); sysfs_remove_group(hstate_kobjs[hi], hstate_attr_group); kobject_put(hstate_kobjs[hi]); hstate_kobjs[hi] = NULL; return retval; } } return 0; } #ifdef CONFIG_NUMA static bool hugetlb_sysfs_initialized __ro_after_init; /* * node_hstate/s - associate per node hstate attributes, via their kobjects, * with node devices in node_devices[] using a parallel array. The array * index of a node device or _hstate == node id. * This is here to avoid any static dependency of the node device driver, in * the base kernel, on the hugetlb module. */ struct node_hstate { struct kobject *hugepages_kobj; struct kobject *hstate_kobjs[HUGE_MAX_HSTATE]; }; static struct node_hstate node_hstates[MAX_NUMNODES]; /* * A subset of global hstate attributes for node devices */ static struct attribute *per_node_hstate_attrs[] = { &nr_hugepages_attr.attr, &free_hugepages_attr.attr, &surplus_hugepages_attr.attr, NULL, }; static const struct attribute_group per_node_hstate_attr_group = { .attrs = per_node_hstate_attrs, }; /* * kobj_to_node_hstate - lookup global hstate for node device hstate attr kobj. * Returns node id via non-NULL nidp. */ static struct hstate *kobj_to_node_hstate(struct kobject *kobj, int *nidp) { int nid; for (nid = 0; nid < nr_node_ids; nid++) { struct node_hstate *nhs = &node_hstates[nid]; int i; for (i = 0; i < HUGE_MAX_HSTATE; i++) if (nhs->hstate_kobjs[i] == kobj) { if (nidp) *nidp = nid; return &hstates[i]; } } BUG(); return NULL; } /* * Unregister hstate attributes from a single node device. * No-op if no hstate attributes attached. */ void hugetlb_unregister_node(struct node *node) { struct hstate *h; struct node_hstate *nhs = &node_hstates[node->dev.id]; if (!nhs->hugepages_kobj) return; /* no hstate attributes */ for_each_hstate(h) { int idx = hstate_index(h); struct kobject *hstate_kobj = nhs->hstate_kobjs[idx]; if (!hstate_kobj) continue; if (h->demote_order) sysfs_remove_group(hstate_kobj, &hstate_demote_attr_group); sysfs_remove_group(hstate_kobj, &per_node_hstate_attr_group); kobject_put(hstate_kobj); nhs->hstate_kobjs[idx] = NULL; } kobject_put(nhs->hugepages_kobj); nhs->hugepages_kobj = NULL; } /* * Register hstate attributes for a single node device. * No-op if attributes already registered. */ void hugetlb_register_node(struct node *node) { struct hstate *h; struct node_hstate *nhs = &node_hstates[node->dev.id]; int err; if (!hugetlb_sysfs_initialized) return; if (nhs->hugepages_kobj) return; /* already allocated */ nhs->hugepages_kobj = kobject_create_and_add("hugepages", &node->dev.kobj); if (!nhs->hugepages_kobj) return; for_each_hstate(h) { err = hugetlb_sysfs_add_hstate(h, nhs->hugepages_kobj, nhs->hstate_kobjs, &per_node_hstate_attr_group); if (err) { pr_err("HugeTLB: Unable to add hstate %s for node %d\n", h->name, node->dev.id); hugetlb_unregister_node(node); break; } } } /* * hugetlb init time: register hstate attributes for all registered node * devices of nodes that have memory. All on-line nodes should have * registered their associated device by this time. */ static void __init hugetlb_register_all_nodes(void) { int nid; for_each_online_node(nid) hugetlb_register_node(node_devices[nid]); } #else /* !CONFIG_NUMA */ static struct hstate *kobj_to_node_hstate(struct kobject *kobj, int *nidp) { BUG(); if (nidp) *nidp = -1; return NULL; } static void hugetlb_register_all_nodes(void) { } #endif #ifdef CONFIG_CMA static void __init hugetlb_cma_check(void); #else static inline __init void hugetlb_cma_check(void) { } #endif static void __init hugetlb_sysfs_init(void) { struct hstate *h; int err; hugepages_kobj = kobject_create_and_add("hugepages", mm_kobj); if (!hugepages_kobj) return; for_each_hstate(h) { err = hugetlb_sysfs_add_hstate(h, hugepages_kobj, hstate_kobjs, &hstate_attr_group); if (err) pr_err("HugeTLB: Unable to add hstate %s", h->name); } #ifdef CONFIG_NUMA hugetlb_sysfs_initialized = true; #endif hugetlb_register_all_nodes(); } #ifdef CONFIG_SYSCTL static void hugetlb_sysctl_init(void); #else static inline void hugetlb_sysctl_init(void) { } #endif static int __init hugetlb_init(void) { int i; BUILD_BUG_ON(sizeof_field(struct page, private) * BITS_PER_BYTE < __NR_HPAGEFLAGS); if (!hugepages_supported()) { if (hugetlb_max_hstate || default_hstate_max_huge_pages) pr_warn("HugeTLB: huge pages not supported, ignoring associated command-line parameters\n"); return 0; } /* * Make sure HPAGE_SIZE (HUGETLB_PAGE_ORDER) hstate exists. Some * architectures depend on setup being done here. */ hugetlb_add_hstate(HUGETLB_PAGE_ORDER); if (!parsed_default_hugepagesz) { /* * If we did not parse a default huge page size, set * default_hstate_idx to HPAGE_SIZE hstate. And, if the * number of huge pages for this default size was implicitly * specified, set that here as well. * Note that the implicit setting will overwrite an explicit * setting. A warning will be printed in this case. */ default_hstate_idx = hstate_index(size_to_hstate(HPAGE_SIZE)); if (default_hstate_max_huge_pages) { if (default_hstate.max_huge_pages) { char buf[32]; string_get_size(huge_page_size(&default_hstate), 1, STRING_UNITS_2, buf, 32); pr_warn("HugeTLB: Ignoring hugepages=%lu associated with %s page size\n", default_hstate.max_huge_pages, buf); pr_warn("HugeTLB: Using hugepages=%lu for number of default huge pages\n", default_hstate_max_huge_pages); } default_hstate.max_huge_pages = default_hstate_max_huge_pages; for_each_online_node(i) default_hstate.max_huge_pages_node[i] = default_hugepages_in_node[i]; } } hugetlb_cma_check(); hugetlb_init_hstates(); gather_bootmem_prealloc(); report_hugepages(); hugetlb_sysfs_init(); hugetlb_cgroup_file_init(); hugetlb_sysctl_init(); #ifdef CONFIG_SMP num_fault_mutexes = roundup_pow_of_two(8 * num_possible_cpus()); #else num_fault_mutexes = 1; #endif hugetlb_fault_mutex_table = kmalloc_array(num_fault_mutexes, sizeof(struct mutex), GFP_KERNEL); BUG_ON(!hugetlb_fault_mutex_table); for (i = 0; i < num_fault_mutexes; i++) mutex_init(&hugetlb_fault_mutex_table[i]); return 0; } subsys_initcall(hugetlb_init); /* Overwritten by architectures with more huge page sizes */ bool __init __attribute((weak)) arch_hugetlb_valid_size(unsigned long size) { return size == HPAGE_SIZE; } void __init hugetlb_add_hstate(unsigned int order) { struct hstate *h; unsigned long i; if (size_to_hstate(PAGE_SIZE << order)) { return; } BUG_ON(hugetlb_max_hstate >= HUGE_MAX_HSTATE); BUG_ON(order < order_base_2(__NR_USED_SUBPAGE)); h = &hstates[hugetlb_max_hstate++]; __mutex_init(&h->resize_lock, "resize mutex", &h->resize_key); h->order = order; h->mask = ~(huge_page_size(h) - 1); for (i = 0; i < MAX_NUMNODES; ++i) INIT_LIST_HEAD(&h->hugepage_freelists[i]); INIT_LIST_HEAD(&h->hugepage_activelist); h->next_nid_to_alloc = first_memory_node; h->next_nid_to_free = first_memory_node; snprintf(h->name, HSTATE_NAME_LEN, "hugepages-%lukB", huge_page_size(h)/SZ_1K); parsed_hstate = h; } bool __init __weak hugetlb_node_alloc_supported(void) { return true; } static void __init hugepages_clear_pages_in_node(void) { if (!hugetlb_max_hstate) { default_hstate_max_huge_pages = 0; memset(default_hugepages_in_node, 0, sizeof(default_hugepages_in_node)); } else { parsed_hstate->max_huge_pages = 0; memset(parsed_hstate->max_huge_pages_node, 0, sizeof(parsed_hstate->max_huge_pages_node)); } } /* * hugepages command line processing * hugepages normally follows a valid hugepagsz or default_hugepagsz * specification. If not, ignore the hugepages value. hugepages can also * be the first huge page command line option in which case it implicitly * specifies the number of huge pages for the default size. */ static int __init hugepages_setup(char *s) { unsigned long *mhp; static unsigned long *last_mhp; int node = NUMA_NO_NODE; int count; unsigned long tmp; char *p = s; if (!parsed_valid_hugepagesz) { pr_warn("HugeTLB: hugepages=%s does not follow a valid hugepagesz, ignoring\n", s); parsed_valid_hugepagesz = true; return 1; } /* * !hugetlb_max_hstate means we haven't parsed a hugepagesz= parameter * yet, so this hugepages= parameter goes to the "default hstate". * Otherwise, it goes with the previously parsed hugepagesz or * default_hugepagesz. */ else if (!hugetlb_max_hstate) mhp = &default_hstate_max_huge_pages; else mhp = &parsed_hstate->max_huge_pages; if (mhp == last_mhp) { pr_warn("HugeTLB: hugepages= specified twice without interleaving hugepagesz=, ignoring hugepages=%s\n", s); return 1; } while (*p) { count = 0; if (sscanf(p, "%lu%n", &tmp, &count) != 1) goto invalid; /* Parameter is node format */ if (p[count] == ':') { if (!hugetlb_node_alloc_supported()) { pr_warn("HugeTLB: architecture can't support node specific alloc, ignoring!\n"); return 1; } if (tmp >= MAX_NUMNODES || !node_online(tmp)) goto invalid; node = array_index_nospec(tmp, MAX_NUMNODES); p += count + 1; /* Parse hugepages */ if (sscanf(p, "%lu%n", &tmp, &count) != 1) goto invalid; if (!hugetlb_max_hstate) default_hugepages_in_node[node] = tmp; else parsed_hstate->max_huge_pages_node[node] = tmp; *mhp += tmp; /* Go to parse next node*/ if (p[count] == ',') p += count + 1; else break; } else { if (p != s) goto invalid; *mhp = tmp; break; } } /* * Global state is always initialized later in hugetlb_init. * But we need to allocate gigantic hstates here early to still * use the bootmem allocator. */ if (hugetlb_max_hstate && hstate_is_gigantic(parsed_hstate)) hugetlb_hstate_alloc_pages(parsed_hstate); last_mhp = mhp; return 1; invalid: pr_warn("HugeTLB: Invalid hugepages parameter %s\n", p); hugepages_clear_pages_in_node(); return 1; } __setup("hugepages=", hugepages_setup); /* * hugepagesz command line processing * A specific huge page size can only be specified once with hugepagesz. * hugepagesz is followed by hugepages on the command line. The global * variable 'parsed_valid_hugepagesz' is used to determine if prior * hugepagesz argument was valid. */ static int __init hugepagesz_setup(char *s) { unsigned long size; struct hstate *h; parsed_valid_hugepagesz = false; size = (unsigned long)memparse(s, NULL); if (!arch_hugetlb_valid_size(size)) { pr_err("HugeTLB: unsupported hugepagesz=%s\n", s); return 1; } h = size_to_hstate(size); if (h) { /* * hstate for this size already exists. This is normally * an error, but is allowed if the existing hstate is the * default hstate. More specifically, it is only allowed if * the number of huge pages for the default hstate was not * previously specified. */ if (!parsed_default_hugepagesz || h != &default_hstate || default_hstate.max_huge_pages) { pr_warn("HugeTLB: hugepagesz=%s specified twice, ignoring\n", s); return 1; } /* * No need to call hugetlb_add_hstate() as hstate already * exists. But, do set parsed_hstate so that a following * hugepages= parameter will be applied to this hstate. */ parsed_hstate = h; parsed_valid_hugepagesz = true; return 1; } hugetlb_add_hstate(ilog2(size) - PAGE_SHIFT); parsed_valid_hugepagesz = true; return 1; } __setup("hugepagesz=", hugepagesz_setup); /* * default_hugepagesz command line input * Only one instance of default_hugepagesz allowed on command line. */ static int __init default_hugepagesz_setup(char *s) { unsigned long size; int i; parsed_valid_hugepagesz = false; if (parsed_default_hugepagesz) { pr_err("HugeTLB: default_hugepagesz previously specified, ignoring %s\n", s); return 1; } size = (unsigned long)memparse(s, NULL); if (!arch_hugetlb_valid_size(size)) { pr_err("HugeTLB: unsupported default_hugepagesz=%s\n", s); return 1; } hugetlb_add_hstate(ilog2(size) - PAGE_SHIFT); parsed_valid_hugepagesz = true; parsed_default_hugepagesz = true; default_hstate_idx = hstate_index(size_to_hstate(size)); /* * The number of default huge pages (for this size) could have been * specified as the first hugetlb parameter: hugepages=X. If so, * then default_hstate_max_huge_pages is set. If the default huge * page size is gigantic (> MAX_PAGE_ORDER), then the pages must be * allocated here from bootmem allocator. */ if (default_hstate_max_huge_pages) { default_hstate.max_huge_pages = default_hstate_max_huge_pages; for_each_online_node(i) default_hstate.max_huge_pages_node[i] = default_hugepages_in_node[i]; if (hstate_is_gigantic(&default_hstate)) hugetlb_hstate_alloc_pages(&default_hstate); default_hstate_max_huge_pages = 0; } return 1; } __setup("default_hugepagesz=", default_hugepagesz_setup); static unsigned int allowed_mems_nr(struct hstate *h) { int node; unsigned int nr = 0; nodemask_t *mbind_nodemask; unsigned int *array = h->free_huge_pages_node; gfp_t gfp_mask = htlb_alloc_mask(h); mbind_nodemask = policy_mbind_nodemask(gfp_mask); for_each_node_mask(node, cpuset_current_mems_allowed) { if (!mbind_nodemask || node_isset(node, *mbind_nodemask)) nr += array[node]; } return nr; } #ifdef CONFIG_SYSCTL static int proc_hugetlb_doulongvec_minmax(const struct ctl_table *table, int write, void *buffer, size_t *length, loff_t *ppos, unsigned long *out) { struct ctl_table dup_table; /* * In order to avoid races with __do_proc_doulongvec_minmax(), we * can duplicate the @table and alter the duplicate of it. */ dup_table = *table; dup_table.data = out; return proc_doulongvec_minmax(&dup_table, write, buffer, length, ppos); } static int hugetlb_sysctl_handler_common(bool obey_mempolicy, const struct ctl_table *table, int write, void *buffer, size_t *length, loff_t *ppos) { struct hstate *h = &default_hstate; unsigned long tmp = h->max_huge_pages; int ret; if (!hugepages_supported()) return -EOPNOTSUPP; ret = proc_hugetlb_doulongvec_minmax(table, write, buffer, length, ppos, &tmp); if (ret) goto out; if (write) ret = __nr_hugepages_store_common(obey_mempolicy, h, NUMA_NO_NODE, tmp, *length); out: return ret; } static int hugetlb_sysctl_handler(const struct ctl_table *table, int write, void *buffer, size_t *length, loff_t *ppos) { return hugetlb_sysctl_handler_common(false, table, write, buffer, length, ppos); } #ifdef CONFIG_NUMA static int hugetlb_mempolicy_sysctl_handler(const struct ctl_table *table, int write, void *buffer, size_t *length, loff_t *ppos) { return hugetlb_sysctl_handler_common(true, table, write, buffer, length, ppos); } #endif /* CONFIG_NUMA */ static int hugetlb_overcommit_handler(const struct ctl_table *table, int write, void *buffer, size_t *length, loff_t *ppos) { struct hstate *h = &default_hstate; unsigned long tmp; int ret; if (!hugepages_supported()) return -EOPNOTSUPP; tmp = h->nr_overcommit_huge_pages; if (write && hstate_is_gigantic(h)) return -EINVAL; ret = proc_hugetlb_doulongvec_minmax(table, write, buffer, length, ppos, &tmp); if (ret) goto out; if (write) { spin_lock_irq(&hugetlb_lock); h->nr_overcommit_huge_pages = tmp; spin_unlock_irq(&hugetlb_lock); } out: return ret; } static struct ctl_table hugetlb_table[] = { { .procname = "nr_hugepages", .data = NULL, .maxlen = sizeof(unsigned long), .mode = 0644, .proc_handler = hugetlb_sysctl_handler, }, #ifdef CONFIG_NUMA { .procname = "nr_hugepages_mempolicy", .data = NULL, .maxlen = sizeof(unsigned long), .mode = 0644, .proc_handler = &hugetlb_mempolicy_sysctl_handler, }, #endif { .procname = "hugetlb_shm_group", .data = &sysctl_hugetlb_shm_group, .maxlen = sizeof(gid_t), .mode = 0644, .proc_handler = proc_dointvec, }, { .procname = "nr_overcommit_hugepages", .data = NULL, .maxlen = sizeof(unsigned long), .mode = 0644, .proc_handler = hugetlb_overcommit_handler, }, }; static void hugetlb_sysctl_init(void) { register_sysctl_init("vm", hugetlb_table); } #endif /* CONFIG_SYSCTL */ void hugetlb_report_meminfo(struct seq_file *m) { struct hstate *h; unsigned long total = 0; if (!hugepages_supported()) return; for_each_hstate(h) { unsigned long count = h->nr_huge_pages; total += huge_page_size(h) * count; if (h == &default_hstate) seq_printf(m, "HugePages_Total: %5lu\n" "HugePages_Free: %5lu\n" "HugePages_Rsvd: %5lu\n" "HugePages_Surp: %5lu\n" "Hugepagesize: %8lu kB\n", count, h->free_huge_pages, h->resv_huge_pages, h->surplus_huge_pages, huge_page_size(h) / SZ_1K); } seq_printf(m, "Hugetlb: %8lu kB\n", total / SZ_1K); } int hugetlb_report_node_meminfo(char *buf, int len, int nid) { struct hstate *h = &default_hstate; if (!hugepages_supported()) return 0; return sysfs_emit_at(buf, len, "Node %d HugePages_Total: %5u\n" "Node %d HugePages_Free: %5u\n" "Node %d HugePages_Surp: %5u\n", nid, h->nr_huge_pages_node[nid], nid, h->free_huge_pages_node[nid], nid, h->surplus_huge_pages_node[nid]); } void hugetlb_show_meminfo_node(int nid) { struct hstate *h; if (!hugepages_supported()) return; for_each_hstate(h) printk("Node %d hugepages_total=%u hugepages_free=%u hugepages_surp=%u hugepages_size=%lukB\n", nid, h->nr_huge_pages_node[nid], h->free_huge_pages_node[nid], h->surplus_huge_pages_node[nid], huge_page_size(h) / SZ_1K); } void hugetlb_report_usage(struct seq_file *m, struct mm_struct *mm) { seq_printf(m, "HugetlbPages:\t%8lu kB\n", K(atomic_long_read(&mm->hugetlb_usage))); } /* Return the number pages of memory we physically have, in PAGE_SIZE units. */ unsigned long hugetlb_total_pages(void) { struct hstate *h; unsigned long nr_total_pages = 0; for_each_hstate(h) nr_total_pages += h->nr_huge_pages * pages_per_huge_page(h); return nr_total_pages; } static int hugetlb_acct_memory(struct hstate *h, long delta) { int ret = -ENOMEM; if (!delta) return 0; spin_lock_irq(&hugetlb_lock); /* * When cpuset is configured, it breaks the strict hugetlb page * reservation as the accounting is done on a global variable. Such * reservation is completely rubbish in the presence of cpuset because * the reservation is not checked against page availability for the * current cpuset. Application can still potentially OOM'ed by kernel * with lack of free htlb page in cpuset that the task is in. * Attempt to enforce strict accounting with cpuset is almost * impossible (or too ugly) because cpuset is too fluid that * task or memory node can be dynamically moved between cpusets. * * The change of semantics for shared hugetlb mapping with cpuset is * undesirable. However, in order to preserve some of the semantics, * we fall back to check against current free page availability as * a best attempt and hopefully to minimize the impact of changing * semantics that cpuset has. * * Apart from cpuset, we also have memory policy mechanism that * also determines from which node the kernel will allocate memory * in a NUMA system. So similar to cpuset, we also should consider * the memory policy of the current task. Similar to the description * above. */ if (delta > 0) { if (gather_surplus_pages(h, delta) < 0) goto out; if (delta > allowed_mems_nr(h)) { return_unused_surplus_pages(h, delta); goto out; } } ret = 0; if (delta < 0) return_unused_surplus_pages(h, (unsigned long) -delta); out: spin_unlock_irq(&hugetlb_lock); return ret; } static void hugetlb_vm_op_open(struct vm_area_struct *vma) { struct resv_map *resv = vma_resv_map(vma); /* * HPAGE_RESV_OWNER indicates a private mapping. * This new VMA should share its siblings reservation map if present. * The VMA will only ever have a valid reservation map pointer where * it is being copied for another still existing VMA. As that VMA * has a reference to the reservation map it cannot disappear until * after this open call completes. It is therefore safe to take a * new reference here without additional locking. */ if (resv && is_vma_resv_set(vma, HPAGE_RESV_OWNER)) { resv_map_dup_hugetlb_cgroup_uncharge_info(resv); kref_get(&resv->refs); } /* * vma_lock structure for sharable mappings is vma specific. * Clear old pointer (if copied via vm_area_dup) and allocate * new structure. Before clearing, make sure vma_lock is not * for this vma. */ if (vma->vm_flags & VM_MAYSHARE) { struct hugetlb_vma_lock *vma_lock = vma->vm_private_data; if (vma_lock) { if (vma_lock->vma != vma) { vma->vm_private_data = NULL; hugetlb_vma_lock_alloc(vma); } else pr_warn("HugeTLB: vma_lock already exists in %s.\n", __func__); } else hugetlb_vma_lock_alloc(vma); } } static void hugetlb_vm_op_close(struct vm_area_struct *vma) { struct hstate *h = hstate_vma(vma); struct resv_map *resv; struct hugepage_subpool *spool = subpool_vma(vma); unsigned long reserve, start, end; long gbl_reserve; hugetlb_vma_lock_free(vma); resv = vma_resv_map(vma); if (!resv || !is_vma_resv_set(vma, HPAGE_RESV_OWNER)) return; start = vma_hugecache_offset(h, vma, vma->vm_start); end = vma_hugecache_offset(h, vma, vma->vm_end); reserve = (end - start) - region_count(resv, start, end); hugetlb_cgroup_uncharge_counter(resv, start, end); if (reserve) { /* * Decrement reserve counts. The global reserve count may be * adjusted if the subpool has a minimum size. */ gbl_reserve = hugepage_subpool_put_pages(spool, reserve); hugetlb_acct_memory(h, -gbl_reserve); } kref_put(&resv->refs, resv_map_release); } static int hugetlb_vm_op_split(struct vm_area_struct *vma, unsigned long addr) { if (addr & ~(huge_page_mask(hstate_vma(vma)))) return -EINVAL; /* * PMD sharing is only possible for PUD_SIZE-aligned address ranges * in HugeTLB VMAs. If we will lose PUD_SIZE alignment due to this * split, unshare PMDs in the PUD_SIZE interval surrounding addr now. */ if (addr & ~PUD_MASK) { /* * hugetlb_vm_op_split is called right before we attempt to * split the VMA. We will need to unshare PMDs in the old and * new VMAs, so let's unshare before we split. */ unsigned long floor = addr & PUD_MASK; unsigned long ceil = floor + PUD_SIZE; if (floor >= vma->vm_start && ceil <= vma->vm_end) hugetlb_unshare_pmds(vma, floor, ceil); } return 0; } static unsigned long hugetlb_vm_op_pagesize(struct vm_area_struct *vma) { return huge_page_size(hstate_vma(vma)); } /* * We cannot handle pagefaults against hugetlb pages at all. They cause * handle_mm_fault() to try to instantiate regular-sized pages in the * hugepage VMA. do_page_fault() is supposed to trap this, so BUG is we get * this far. */ static vm_fault_t hugetlb_vm_op_fault(struct vm_fault *vmf) { BUG(); return 0; } /* * When a new function is introduced to vm_operations_struct and added * to hugetlb_vm_ops, please consider adding the function to shm_vm_ops. * This is because under System V memory model, mappings created via * shmget/shmat with "huge page" specified are backed by hugetlbfs files, * their original vm_ops are overwritten with shm_vm_ops. */ const struct vm_operations_struct hugetlb_vm_ops = { .fault = hugetlb_vm_op_fault, .open = hugetlb_vm_op_open, .close = hugetlb_vm_op_close, .may_split = hugetlb_vm_op_split, .pagesize = hugetlb_vm_op_pagesize, }; static pte_t make_huge_pte(struct vm_area_struct *vma, struct page *page, int writable) { pte_t entry; unsigned int shift = huge_page_shift(hstate_vma(vma)); if (writable) { entry = huge_pte_mkwrite(huge_pte_mkdirty(mk_huge_pte(page, vma->vm_page_prot))); } else { entry = huge_pte_wrprotect(mk_huge_pte(page, vma->vm_page_prot)); } entry = pte_mkyoung(entry); entry = arch_make_huge_pte(entry, shift, vma->vm_flags); return entry; } static void set_huge_ptep_writable(struct vm_area_struct *vma, unsigned long address, pte_t *ptep) { pte_t entry; entry = huge_pte_mkwrite(huge_pte_mkdirty(huge_ptep_get(vma->vm_mm, address, ptep))); if (huge_ptep_set_access_flags(vma, address, ptep, entry, 1)) update_mmu_cache(vma, address, ptep); } bool is_hugetlb_entry_migration(pte_t pte) { swp_entry_t swp; if (huge_pte_none(pte) || pte_present(pte)) return false; swp = pte_to_swp_entry(pte); if (is_migration_entry(swp)) return true; else return false; } bool is_hugetlb_entry_hwpoisoned(pte_t pte) { swp_entry_t swp; if (huge_pte_none(pte) || pte_present(pte)) return false; swp = pte_to_swp_entry(pte); if (is_hwpoison_entry(swp)) return true; else return false; } static void hugetlb_install_folio(struct vm_area_struct *vma, pte_t *ptep, unsigned long addr, struct folio *new_folio, pte_t old, unsigned long sz) { pte_t newpte = make_huge_pte(vma, &new_folio->page, 1); __folio_mark_uptodate(new_folio); hugetlb_add_new_anon_rmap(new_folio, vma, addr); if (userfaultfd_wp(vma) && huge_pte_uffd_wp(old)) newpte = huge_pte_mkuffd_wp(newpte); set_huge_pte_at(vma->vm_mm, addr, ptep, newpte, sz); hugetlb_count_add(pages_per_huge_page(hstate_vma(vma)), vma->vm_mm); folio_set_hugetlb_migratable(new_folio); } int copy_hugetlb_page_range(struct mm_struct *dst, struct mm_struct *src, struct vm_area_struct *dst_vma, struct vm_area_struct *src_vma) { pte_t *src_pte, *dst_pte, entry; struct folio *pte_folio; unsigned long addr; bool cow = is_cow_mapping(src_vma->vm_flags); struct hstate *h = hstate_vma(src_vma); unsigned long sz = huge_page_size(h); unsigned long npages = pages_per_huge_page(h); struct mmu_notifier_range range; unsigned long last_addr_mask; int ret = 0; if (cow) { mmu_notifier_range_init(&range, MMU_NOTIFY_CLEAR, 0, src, src_vma->vm_start, src_vma->vm_end); mmu_notifier_invalidate_range_start(&range); vma_assert_write_locked(src_vma); raw_write_seqcount_begin(&src->write_protect_seq); } else { /* * For shared mappings the vma lock must be held before * calling hugetlb_walk() in the src vma. Otherwise, the * returned ptep could go away if part of a shared pmd and * another thread calls huge_pmd_unshare. */ hugetlb_vma_lock_read(src_vma); } last_addr_mask = hugetlb_mask_last_page(h); for (addr = src_vma->vm_start; addr < src_vma->vm_end; addr += sz) { spinlock_t *src_ptl, *dst_ptl; src_pte = hugetlb_walk(src_vma, addr, sz); if (!src_pte) { addr |= last_addr_mask; continue; } dst_pte = huge_pte_alloc(dst, dst_vma, addr, sz); if (!dst_pte) { ret = -ENOMEM; break; } /* * If the pagetables are shared don't copy or take references. * * dst_pte == src_pte is the common case of src/dest sharing. * However, src could have 'unshared' and dst shares with * another vma. So page_count of ptep page is checked instead * to reliably determine whether pte is shared. */ if (page_count(virt_to_page(dst_pte)) > 1) { addr |= last_addr_mask; continue; } dst_ptl = huge_pte_lock(h, dst, dst_pte); src_ptl = huge_pte_lockptr(h, src, src_pte); spin_lock_nested(src_ptl, SINGLE_DEPTH_NESTING); entry = huge_ptep_get(src_vma->vm_mm, addr, src_pte); again: if (huge_pte_none(entry)) { /* * Skip if src entry none. */ ; } else if (unlikely(is_hugetlb_entry_hwpoisoned(entry))) { if (!userfaultfd_wp(dst_vma)) entry = huge_pte_clear_uffd_wp(entry); set_huge_pte_at(dst, addr, dst_pte, entry, sz); } else if (unlikely(is_hugetlb_entry_migration(entry))) { swp_entry_t swp_entry = pte_to_swp_entry(entry); bool uffd_wp = pte_swp_uffd_wp(entry); if (!is_readable_migration_entry(swp_entry) && cow) { /* * COW mappings require pages in both * parent and child to be set to read. */ swp_entry = make_readable_migration_entry( swp_offset(swp_entry)); entry = swp_entry_to_pte(swp_entry); if (userfaultfd_wp(src_vma) && uffd_wp) entry = pte_swp_mkuffd_wp(entry); set_huge_pte_at(src, addr, src_pte, entry, sz); } if (!userfaultfd_wp(dst_vma)) entry = huge_pte_clear_uffd_wp(entry); set_huge_pte_at(dst, addr, dst_pte, entry, sz); } else if (unlikely(is_pte_marker(entry))) { pte_marker marker = copy_pte_marker( pte_to_swp_entry(entry), dst_vma); if (marker) set_huge_pte_at(dst, addr, dst_pte, make_pte_marker(marker), sz); } else { entry = huge_ptep_get(src_vma->vm_mm, addr, src_pte); pte_folio = page_folio(pte_page(entry)); folio_get(pte_folio); /* * Failing to duplicate the anon rmap is a rare case * where we see pinned hugetlb pages while they're * prone to COW. We need to do the COW earlier during * fork. * * When pre-allocating the page or copying data, we * need to be without the pgtable locks since we could * sleep during the process. */ if (!folio_test_anon(pte_folio)) { hugetlb_add_file_rmap(pte_folio); } else if (hugetlb_try_dup_anon_rmap(pte_folio, src_vma)) { pte_t src_pte_old = entry; struct folio *new_folio; spin_unlock(src_ptl); spin_unlock(dst_ptl); /* Do not use reserve as it's private owned */ new_folio = alloc_hugetlb_folio(dst_vma, addr, 1); if (IS_ERR(new_folio)) { folio_put(pte_folio); ret = PTR_ERR(new_folio); break; } ret = copy_user_large_folio(new_folio, pte_folio, ALIGN_DOWN(addr, sz), dst_vma); folio_put(pte_folio); if (ret) { folio_put(new_folio); break; } /* Install the new hugetlb folio if src pte stable */ dst_ptl = huge_pte_lock(h, dst, dst_pte); src_ptl = huge_pte_lockptr(h, src, src_pte); spin_lock_nested(src_ptl, SINGLE_DEPTH_NESTING); entry = huge_ptep_get(src_vma->vm_mm, addr, src_pte); if (!pte_same(src_pte_old, entry)) { restore_reserve_on_error(h, dst_vma, addr, new_folio); folio_put(new_folio); /* huge_ptep of dst_pte won't change as in child */ goto again; } hugetlb_install_folio(dst_vma, dst_pte, addr, new_folio, src_pte_old, sz); spin_unlock(src_ptl); spin_unlock(dst_ptl); continue; } if (cow) { /* * No need to notify as we are downgrading page * table protection not changing it to point * to a new page. * * See Documentation/mm/mmu_notifier.rst */ huge_ptep_set_wrprotect(src, addr, src_pte); entry = huge_pte_wrprotect(entry); } if (!userfaultfd_wp(dst_vma)) entry = huge_pte_clear_uffd_wp(entry); set_huge_pte_at(dst, addr, dst_pte, entry, sz); hugetlb_count_add(npages, dst); } spin_unlock(src_ptl); spin_unlock(dst_ptl); } if (cow) { raw_write_seqcount_end(&src->write_protect_seq); mmu_notifier_invalidate_range_end(&range); } else { hugetlb_vma_unlock_read(src_vma); } return ret; } static void move_huge_pte(struct vm_area_struct *vma, unsigned long old_addr, unsigned long new_addr, pte_t *src_pte, pte_t *dst_pte, unsigned long sz) { struct hstate *h = hstate_vma(vma); struct mm_struct *mm = vma->vm_mm; spinlock_t *src_ptl, *dst_ptl; pte_t pte; dst_ptl = huge_pte_lock(h, mm, dst_pte); src_ptl = huge_pte_lockptr(h, mm, src_pte); /* * We don't have to worry about the ordering of src and dst ptlocks * because exclusive mmap_lock (or the i_mmap_lock) prevents deadlock. */ if (src_ptl != dst_ptl) spin_lock_nested(src_ptl, SINGLE_DEPTH_NESTING); pte = huge_ptep_get_and_clear(mm, old_addr, src_pte); set_huge_pte_at(mm, new_addr, dst_pte, pte, sz); if (src_ptl != dst_ptl) spin_unlock(src_ptl); spin_unlock(dst_ptl); } int move_hugetlb_page_tables(struct vm_area_struct *vma, struct vm_area_struct *new_vma, unsigned long old_addr, unsigned long new_addr, unsigned long len) { struct hstate *h = hstate_vma(vma); struct address_space *mapping = vma->vm_file->f_mapping; unsigned long sz = huge_page_size(h); struct mm_struct *mm = vma->vm_mm; unsigned long old_end = old_addr + len; unsigned long last_addr_mask; pte_t *src_pte, *dst_pte; struct mmu_notifier_range range; bool shared_pmd = false; mmu_notifier_range_init(&range, MMU_NOTIFY_CLEAR, 0, mm, old_addr, old_end); adjust_range_if_pmd_sharing_possible(vma, &range.start, &range.end); /* * In case of shared PMDs, we should cover the maximum possible * range. */ flush_cache_range(vma, range.start, range.end); mmu_notifier_invalidate_range_start(&range); last_addr_mask = hugetlb_mask_last_page(h); /* Prevent race with file truncation */ hugetlb_vma_lock_write(vma); i_mmap_lock_write(mapping); for (; old_addr < old_end; old_addr += sz, new_addr += sz) { src_pte = hugetlb_walk(vma, old_addr, sz); if (!src_pte) { old_addr |= last_addr_mask; new_addr |= last_addr_mask; continue; } if (huge_pte_none(huge_ptep_get(mm, old_addr, src_pte))) continue; if (huge_pmd_unshare(mm, vma, old_addr, src_pte)) { shared_pmd = true; old_addr |= last_addr_mask; new_addr |= last_addr_mask; continue; } dst_pte = huge_pte_alloc(mm, new_vma, new_addr, sz); if (!dst_pte) break; move_huge_pte(vma, old_addr, new_addr, src_pte, dst_pte, sz); } if (shared_pmd) flush_hugetlb_tlb_range(vma, range.start, range.end); else flush_hugetlb_tlb_range(vma, old_end - len, old_end); mmu_notifier_invalidate_range_end(&range); i_mmap_unlock_write(mapping); hugetlb_vma_unlock_write(vma); return len + old_addr - old_end; } void __unmap_hugepage_range(struct mmu_gather *tlb, struct vm_area_struct *vma, unsigned long start, unsigned long end, struct page *ref_page, zap_flags_t zap_flags) { struct mm_struct *mm = vma->vm_mm; unsigned long address; pte_t *ptep; pte_t pte; spinlock_t *ptl; struct page *page; struct hstate *h = hstate_vma(vma); unsigned long sz = huge_page_size(h); bool adjust_reservation = false; unsigned long last_addr_mask; bool force_flush = false; WARN_ON(!is_vm_hugetlb_page(vma)); BUG_ON(start & ~huge_page_mask(h)); BUG_ON(end & ~huge_page_mask(h)); /* * This is a hugetlb vma, all the pte entries should point * to huge page. */ tlb_change_page_size(tlb, sz); tlb_start_vma(tlb, vma); last_addr_mask = hugetlb_mask_last_page(h); address = start; for (; address < end; address += sz) { ptep = hugetlb_walk(vma, address, sz); if (!ptep) { address |= last_addr_mask; continue; } ptl = huge_pte_lock(h, mm, ptep); if (huge_pmd_unshare(mm, vma, address, ptep)) { spin_unlock(ptl); tlb_flush_pmd_range(tlb, address & PUD_MASK, PUD_SIZE); force_flush = true; address |= last_addr_mask; continue; } pte = huge_ptep_get(mm, address, ptep); if (huge_pte_none(pte)) { spin_unlock(ptl); continue; } /* * Migrating hugepage or HWPoisoned hugepage is already * unmapped and its refcount is dropped, so just clear pte here. */ if (unlikely(!pte_present(pte))) { /* * If the pte was wr-protected by uffd-wp in any of the * swap forms, meanwhile the caller does not want to * drop the uffd-wp bit in this zap, then replace the * pte with a marker. */ if (pte_swp_uffd_wp_any(pte) && !(zap_flags & ZAP_FLAG_DROP_MARKER)) set_huge_pte_at(mm, address, ptep, make_pte_marker(PTE_MARKER_UFFD_WP), sz); else huge_pte_clear(mm, address, ptep, sz); spin_unlock(ptl); continue; } page = pte_page(pte); /* * If a reference page is supplied, it is because a specific * page is being unmapped, not a range. Ensure the page we * are about to unmap is the actual page of interest. */ if (ref_page) { if (page != ref_page) { spin_unlock(ptl); continue; } /* * Mark the VMA as having unmapped its page so that * future faults in this VMA will fail rather than * looking like data was lost */ set_vma_resv_flags(vma, HPAGE_RESV_UNMAPPED); } pte = huge_ptep_get_and_clear(mm, address, ptep); tlb_remove_huge_tlb_entry(h, tlb, ptep, address); if (huge_pte_dirty(pte)) set_page_dirty(page); /* Leave a uffd-wp pte marker if needed */ if (huge_pte_uffd_wp(pte) && !(zap_flags & ZAP_FLAG_DROP_MARKER)) set_huge_pte_at(mm, address, ptep, make_pte_marker(PTE_MARKER_UFFD_WP), sz); hugetlb_count_sub(pages_per_huge_page(h), mm); hugetlb_remove_rmap(page_folio(page)); /* * Restore the reservation for anonymous page, otherwise the * backing page could be stolen by someone. * If there we are freeing a surplus, do not set the restore * reservation bit. */ if (!h->surplus_huge_pages && __vma_private_lock(vma) && folio_test_anon(page_folio(page))) { folio_set_hugetlb_restore_reserve(page_folio(page)); /* Reservation to be adjusted after the spin lock */ adjust_reservation = true; } spin_unlock(ptl); /* * Adjust the reservation for the region that will have the * reserve restored. Keep in mind that vma_needs_reservation() changes * resv->adds_in_progress if it succeeds. If this is not done, * do_exit() will not see it, and will keep the reservation * forever. */ if (adjust_reservation) { int rc = vma_needs_reservation(h, vma, address); if (rc < 0) /* Pressumably allocate_file_region_entries failed * to allocate a file_region struct. Clear * hugetlb_restore_reserve so that global reserve * count will not be incremented by free_huge_folio. * Act as if we consumed the reservation. */ folio_clear_hugetlb_restore_reserve(page_folio(page)); else if (rc) vma_add_reservation(h, vma, address); } tlb_remove_page_size(tlb, page, huge_page_size(h)); /* * Bail out after unmapping reference page if supplied */ if (ref_page) break; } tlb_end_vma(tlb, vma); /* * If we unshared PMDs, the TLB flush was not recorded in mmu_gather. We * could defer the flush until now, since by holding i_mmap_rwsem we * guaranteed that the last refernece would not be dropped. But we must * do the flushing before we return, as otherwise i_mmap_rwsem will be * dropped and the last reference to the shared PMDs page might be * dropped as well. * * In theory we could defer the freeing of the PMD pages as well, but * huge_pmd_unshare() relies on the exact page_count for the PMD page to * detect sharing, so we cannot defer the release of the page either. * Instead, do flush now. */ if (force_flush) tlb_flush_mmu_tlbonly(tlb); } void __hugetlb_zap_begin(struct vm_area_struct *vma, unsigned long *start, unsigned long *end) { if (!vma->vm_file) /* hugetlbfs_file_mmap error */ return; adjust_range_if_pmd_sharing_possible(vma, start, end); hugetlb_vma_lock_write(vma); if (vma->vm_file) i_mmap_lock_write(vma->vm_file->f_mapping); } void __hugetlb_zap_end(struct vm_area_struct *vma, struct zap_details *details) { zap_flags_t zap_flags = details ? details->zap_flags : 0; if (!vma->vm_file) /* hugetlbfs_file_mmap error */ return; if (zap_flags & ZAP_FLAG_UNMAP) { /* final unmap */ /* * Unlock and free the vma lock before releasing i_mmap_rwsem. * When the vma_lock is freed, this makes the vma ineligible * for pmd sharing. And, i_mmap_rwsem is required to set up * pmd sharing. This is important as page tables for this * unmapped range will be asynchrously deleted. If the page * tables are shared, there will be issues when accessed by * someone else. */ __hugetlb_vma_unlock_write_free(vma); } else { hugetlb_vma_unlock_write(vma); } if (vma->vm_file) i_mmap_unlock_write(vma->vm_file->f_mapping); } void unmap_hugepage_range(struct vm_area_struct *vma, unsigned long start, unsigned long end, struct page *ref_page, zap_flags_t zap_flags) { struct mmu_notifier_range range; struct mmu_gather tlb; mmu_notifier_range_init(&range, MMU_NOTIFY_CLEAR, 0, vma->vm_mm, start, end); adjust_range_if_pmd_sharing_possible(vma, &range.start, &range.end); mmu_notifier_invalidate_range_start(&range); tlb_gather_mmu(&tlb, vma->vm_mm); __unmap_hugepage_range(&tlb, vma, start, end, ref_page, zap_flags); mmu_notifier_invalidate_range_end(&range); tlb_finish_mmu(&tlb); } /* * This is called when the original mapper is failing to COW a MAP_PRIVATE * mapping it owns the reserve page for. The intention is to unmap the page * from other VMAs and let the children be SIGKILLed if they are faulting the * same region. */ static void unmap_ref_private(struct mm_struct *mm, struct vm_area_struct *vma, struct page *page, unsigned long address) { struct hstate *h = hstate_vma(vma); struct vm_area_struct *iter_vma; struct address_space *mapping; pgoff_t pgoff; /* * vm_pgoff is in PAGE_SIZE units, hence the different calculation * from page cache lookup which is in HPAGE_SIZE units. */ address = address & huge_page_mask(h); pgoff = ((address - vma->vm_start) >> PAGE_SHIFT) + vma->vm_pgoff; mapping = vma->vm_file->f_mapping; /* * Take the mapping lock for the duration of the table walk. As * this mapping should be shared between all the VMAs, * __unmap_hugepage_range() is called as the lock is already held */ i_mmap_lock_write(mapping); vma_interval_tree_foreach(iter_vma, &mapping->i_mmap, pgoff, pgoff) { /* Do not unmap the current VMA */ if (iter_vma == vma) continue; /* * Shared VMAs have their own reserves and do not affect * MAP_PRIVATE accounting but it is possible that a shared * VMA is using the same page so check and skip such VMAs. */ if (iter_vma->vm_flags & VM_MAYSHARE) continue; /* * Unmap the page from other VMAs without their own reserves. * They get marked to be SIGKILLed if they fault in these * areas. This is because a future no-page fault on this VMA * could insert a zeroed page instead of the data existing * from the time of fork. This would look like data corruption */ if (!is_vma_resv_set(iter_vma, HPAGE_RESV_OWNER)) unmap_hugepage_range(iter_vma, address, address + huge_page_size(h), page, 0); } i_mmap_unlock_write(mapping); } /* * hugetlb_wp() should be called with page lock of the original hugepage held. * Called with hugetlb_fault_mutex_table held and pte_page locked so we * cannot race with other handlers or page migration. * Keep the pte_same checks anyway to make transition from the mutex easier. */ static vm_fault_t hugetlb_wp(struct folio *pagecache_folio, struct vm_fault *vmf) { struct vm_area_struct *vma = vmf->vma; struct mm_struct *mm = vma->vm_mm; const bool unshare = vmf->flags & FAULT_FLAG_UNSHARE; pte_t pte = huge_ptep_get(mm, vmf->address, vmf->pte); struct hstate *h = hstate_vma(vma); struct folio *old_folio; struct folio *new_folio; int outside_reserve = 0; vm_fault_t ret = 0; struct mmu_notifier_range range; /* * Never handle CoW for uffd-wp protected pages. It should be only * handled when the uffd-wp protection is removed. * * Note that only the CoW optimization path (in hugetlb_no_page()) * can trigger this, because hugetlb_fault() will always resolve * uffd-wp bit first. */ if (!unshare && huge_pte_uffd_wp(pte)) return 0; /* * hugetlb does not support FOLL_FORCE-style write faults that keep the * PTE mapped R/O such as maybe_mkwrite() would do. */ if (WARN_ON_ONCE(!unshare && !(vma->vm_flags & VM_WRITE))) return VM_FAULT_SIGSEGV; /* Let's take out MAP_SHARED mappings first. */ if (vma->vm_flags & VM_MAYSHARE) { set_huge_ptep_writable(vma, vmf->address, vmf->pte); return 0; } old_folio = page_folio(pte_page(pte)); delayacct_wpcopy_start(); retry_avoidcopy: /* * If no-one else is actually using this page, we're the exclusive * owner and can reuse this page. * * Note that we don't rely on the (safer) folio refcount here, because * copying the hugetlb folio when there are unexpected (temporary) * folio references could harm simple fork()+exit() users when * we run out of free hugetlb folios: we would have to kill processes * in scenarios that used to work. As a side effect, there can still * be leaks between processes, for example, with FOLL_GET users. */ if (folio_mapcount(old_folio) == 1 && folio_test_anon(old_folio)) { if (!PageAnonExclusive(&old_folio->page)) { folio_move_anon_rmap(old_folio, vma); SetPageAnonExclusive(&old_folio->page); } if (likely(!unshare)) set_huge_ptep_writable(vma, vmf->address, vmf->pte); delayacct_wpcopy_end(); return 0; } VM_BUG_ON_PAGE(folio_test_anon(old_folio) && PageAnonExclusive(&old_folio->page), &old_folio->page); /* * If the process that created a MAP_PRIVATE mapping is about to * perform a COW due to a shared page count, attempt to satisfy * the allocation without using the existing reserves. The pagecache * page is used to determine if the reserve at this address was * consumed or not. If reserves were used, a partial faulted mapping * at the time of fork() could consume its reserves on COW instead * of the full address range. */ if (is_vma_resv_set(vma, HPAGE_RESV_OWNER) && old_folio != pagecache_folio) outside_reserve = 1; folio_get(old_folio); /* * Drop page table lock as buddy allocator may be called. It will * be acquired again before returning to the caller, as expected. */ spin_unlock(vmf->ptl); new_folio = alloc_hugetlb_folio(vma, vmf->address, outside_reserve); if (IS_ERR(new_folio)) { /* * If a process owning a MAP_PRIVATE mapping fails to COW, * it is due to references held by a child and an insufficient * huge page pool. To guarantee the original mappers * reliability, unmap the page from child processes. The child * may get SIGKILLed if it later faults. */ if (outside_reserve) { struct address_space *mapping = vma->vm_file->f_mapping; pgoff_t idx; u32 hash; folio_put(old_folio); /* * Drop hugetlb_fault_mutex and vma_lock before * unmapping. unmapping needs to hold vma_lock * in write mode. Dropping vma_lock in read mode * here is OK as COW mappings do not interact with * PMD sharing. * * Reacquire both after unmap operation. */ idx = vma_hugecache_offset(h, vma, vmf->address); hash = hugetlb_fault_mutex_hash(mapping, idx); hugetlb_vma_unlock_read(vma); mutex_unlock(&hugetlb_fault_mutex_table[hash]); unmap_ref_private(mm, vma, &old_folio->page, vmf->address); mutex_lock(&hugetlb_fault_mutex_table[hash]); hugetlb_vma_lock_read(vma); spin_lock(vmf->ptl); vmf->pte = hugetlb_walk(vma, vmf->address, huge_page_size(h)); if (likely(vmf->pte && pte_same(huge_ptep_get(mm, vmf->address, vmf->pte), pte))) goto retry_avoidcopy; /* * race occurs while re-acquiring page table * lock, and our job is done. */ delayacct_wpcopy_end(); return 0; } ret = vmf_error(PTR_ERR(new_folio)); goto out_release_old; } /* * When the original hugepage is shared one, it does not have * anon_vma prepared. */ ret = __vmf_anon_prepare(vmf); if (unlikely(ret)) goto out_release_all; if (copy_user_large_folio(new_folio, old_folio, vmf->real_address, vma)) { ret = VM_FAULT_HWPOISON_LARGE | VM_FAULT_SET_HINDEX(hstate_index(h)); goto out_release_all; } __folio_mark_uptodate(new_folio); mmu_notifier_range_init(&range, MMU_NOTIFY_CLEAR, 0, mm, vmf->address, vmf->address + huge_page_size(h)); mmu_notifier_invalidate_range_start(&range); /* * Retake the page table lock to check for racing updates * before the page tables are altered */ spin_lock(vmf->ptl); vmf->pte = hugetlb_walk(vma, vmf->address, huge_page_size(h)); if (likely(vmf->pte && pte_same(huge_ptep_get(mm, vmf->address, vmf->pte), pte))) { pte_t newpte = make_huge_pte(vma, &new_folio->page, !unshare); /* Break COW or unshare */ huge_ptep_clear_flush(vma, vmf->address, vmf->pte); hugetlb_remove_rmap(old_folio); hugetlb_add_new_anon_rmap(new_folio, vma, vmf->address); if (huge_pte_uffd_wp(pte)) newpte = huge_pte_mkuffd_wp(newpte); set_huge_pte_at(mm, vmf->address, vmf->pte, newpte, huge_page_size(h)); folio_set_hugetlb_migratable(new_folio); /* Make the old page be freed below */ new_folio = old_folio; } spin_unlock(vmf->ptl); mmu_notifier_invalidate_range_end(&range); out_release_all: /* * No restore in case of successful pagetable update (Break COW or * unshare) */ if (new_folio != old_folio) restore_reserve_on_error(h, vma, vmf->address, new_folio); folio_put(new_folio); out_release_old: folio_put(old_folio); spin_lock(vmf->ptl); /* Caller expects lock to be held */ delayacct_wpcopy_end(); return ret; } /* * Return whether there is a pagecache page to back given address within VMA. */ bool hugetlbfs_pagecache_present(struct hstate *h, struct vm_area_struct *vma, unsigned long address) { struct address_space *mapping = vma->vm_file->f_mapping; pgoff_t idx = linear_page_index(vma, address); struct folio *folio; folio = filemap_get_folio(mapping, idx); if (IS_ERR(folio)) return false; folio_put(folio); return true; } int hugetlb_add_to_page_cache(struct folio *folio, struct address_space *mapping, pgoff_t idx) { struct inode *inode = mapping->host; struct hstate *h = hstate_inode(inode); int err; idx <<= huge_page_order(h); __folio_set_locked(folio); err = __filemap_add_folio(mapping, folio, idx, GFP_KERNEL, NULL); if (unlikely(err)) { __folio_clear_locked(folio); return err; } folio_clear_hugetlb_restore_reserve(folio); /* * mark folio dirty so that it will not be removed from cache/file * by non-hugetlbfs specific code paths. */ folio_mark_dirty(folio); spin_lock(&inode->i_lock); inode->i_blocks += blocks_per_huge_page(h); spin_unlock(&inode->i_lock); return 0; } static inline vm_fault_t hugetlb_handle_userfault(struct vm_fault *vmf, struct address_space *mapping, unsigned long reason) { u32 hash; /* * vma_lock and hugetlb_fault_mutex must be dropped before handling * userfault. Also mmap_lock could be dropped due to handling * userfault, any vma operation should be careful from here. */ hugetlb_vma_unlock_read(vmf->vma); hash = hugetlb_fault_mutex_hash(mapping, vmf->pgoff); mutex_unlock(&hugetlb_fault_mutex_table[hash]); return handle_userfault(vmf, reason); } /* * Recheck pte with pgtable lock. Returns true if pte didn't change, or * false if pte changed or is changing. */ static bool hugetlb_pte_stable(struct hstate *h, struct mm_struct *mm, unsigned long addr, pte_t *ptep, pte_t old_pte) { spinlock_t *ptl; bool same; ptl = huge_pte_lock(h, mm, ptep); same = pte_same(huge_ptep_get(mm, addr, ptep), old_pte); spin_unlock(ptl); return same; } static vm_fault_t hugetlb_no_page(struct address_space *mapping, struct vm_fault *vmf) { struct vm_area_struct *vma = vmf->vma; struct mm_struct *mm = vma->vm_mm; struct hstate *h = hstate_vma(vma); vm_fault_t ret = VM_FAULT_SIGBUS; int anon_rmap = 0; unsigned long size; struct folio *folio; pte_t new_pte; bool new_folio, new_pagecache_folio = false; u32 hash = hugetlb_fault_mutex_hash(mapping, vmf->pgoff); /* * Currently, we are forced to kill the process in the event the * original mapper has unmapped pages from the child due to a failed * COW/unsharing. Warn that such a situation has occurred as it may not * be obvious. */ if (is_vma_resv_set(vma, HPAGE_RESV_UNMAPPED)) { pr_warn_ratelimited("PID %d killed due to inadequate hugepage pool\n", current->pid); goto out; } /* * Use page lock to guard against racing truncation * before we get page_table_lock. */ new_folio = false; folio = filemap_lock_hugetlb_folio(h, mapping, vmf->pgoff); if (IS_ERR(folio)) { size = i_size_read(mapping->host) >> huge_page_shift(h); if (vmf->pgoff >= size) goto out; /* Check for page in userfault range */ if (userfaultfd_missing(vma)) { /* * Since hugetlb_no_page() was examining pte * without pgtable lock, we need to re-test under * lock because the pte may not be stable and could * have changed from under us. Try to detect * either changed or during-changing ptes and retry * properly when needed. * * Note that userfaultfd is actually fine with * false positives (e.g. caused by pte changed), * but not wrong logical events (e.g. caused by * reading a pte during changing). The latter can * confuse the userspace, so the strictness is very * much preferred. E.g., MISSING event should * never happen on the page after UFFDIO_COPY has * correctly installed the page and returned. */ if (!hugetlb_pte_stable(h, mm, vmf->address, vmf->pte, vmf->orig_pte)) { ret = 0; goto out; } return hugetlb_handle_userfault(vmf, mapping, VM_UFFD_MISSING); } if (!(vma->vm_flags & VM_MAYSHARE)) { ret = __vmf_anon_prepare(vmf); if (unlikely(ret)) goto out; } folio = alloc_hugetlb_folio(vma, vmf->address, 0); if (IS_ERR(folio)) { /* * Returning error will result in faulting task being * sent SIGBUS. The hugetlb fault mutex prevents two * tasks from racing to fault in the same page which * could result in false unable to allocate errors. * Page migration does not take the fault mutex, but * does a clear then write of pte's under page table * lock. Page fault code could race with migration, * notice the clear pte and try to allocate a page * here. Before returning error, get ptl and make * sure there really is no pte entry. */ if (hugetlb_pte_stable(h, mm, vmf->address, vmf->pte, vmf->orig_pte)) ret = vmf_error(PTR_ERR(folio)); else ret = 0; goto out; } folio_zero_user(folio, vmf->real_address); __folio_mark_uptodate(folio); new_folio = true; if (vma->vm_flags & VM_MAYSHARE) { int err = hugetlb_add_to_page_cache(folio, mapping, vmf->pgoff); if (err) { /* * err can't be -EEXIST which implies someone * else consumed the reservation since hugetlb * fault mutex is held when add a hugetlb page * to the page cache. So it's safe to call * restore_reserve_on_error() here. */ restore_reserve_on_error(h, vma, vmf->address, folio); folio_put(folio); ret = VM_FAULT_SIGBUS; goto out; } new_pagecache_folio = true; } else { folio_lock(folio); anon_rmap = 1; } } else { /* * If memory error occurs between mmap() and fault, some process * don't have hwpoisoned swap entry for errored virtual address. * So we need to block hugepage fault by PG_hwpoison bit check. */ if (unlikely(folio_test_hwpoison(folio))) { ret = VM_FAULT_HWPOISON_LARGE | VM_FAULT_SET_HINDEX(hstate_index(h)); goto backout_unlocked; } /* Check for page in userfault range. */ if (userfaultfd_minor(vma)) { folio_unlock(folio); folio_put(folio); /* See comment in userfaultfd_missing() block above */ if (!hugetlb_pte_stable(h, mm, vmf->address, vmf->pte, vmf->orig_pte)) { ret = 0; goto out; } return hugetlb_handle_userfault(vmf, mapping, VM_UFFD_MINOR); } } /* * If we are going to COW a private mapping later, we examine the * pending reservations for this page now. This will ensure that * any allocations necessary to record that reservation occur outside * the spinlock. */ if ((vmf->flags & FAULT_FLAG_WRITE) && !(vma->vm_flags & VM_SHARED)) { if (vma_needs_reservation(h, vma, vmf->address) < 0) { ret = VM_FAULT_OOM; goto backout_unlocked; } /* Just decrements count, does not deallocate */ vma_end_reservation(h, vma, vmf->address); } vmf->ptl = huge_pte_lock(h, mm, vmf->pte); ret = 0; /* If pte changed from under us, retry */ if (!pte_same(huge_ptep_get(mm, vmf->address, vmf->pte), vmf->orig_pte)) goto backout; if (anon_rmap) hugetlb_add_new_anon_rmap(folio, vma, vmf->address); else hugetlb_add_file_rmap(folio); new_pte = make_huge_pte(vma, &folio->page, ((vma->vm_flags & VM_WRITE) && (vma->vm_flags & VM_SHARED))); /* * If this pte was previously wr-protected, keep it wr-protected even * if populated. */ if (unlikely(pte_marker_uffd_wp(vmf->orig_pte))) new_pte = huge_pte_mkuffd_wp(new_pte); set_huge_pte_at(mm, vmf->address, vmf->pte, new_pte, huge_page_size(h)); hugetlb_count_add(pages_per_huge_page(h), mm); if ((vmf->flags & FAULT_FLAG_WRITE) && !(vma->vm_flags & VM_SHARED)) { /* Optimization, do the COW without a second fault */ ret = hugetlb_wp(folio, vmf); } spin_unlock(vmf->ptl); /* * Only set hugetlb_migratable in newly allocated pages. Existing pages * found in the pagecache may not have hugetlb_migratable if they have * been isolated for migration. */ if (new_folio) folio_set_hugetlb_migratable(folio); folio_unlock(folio); out: hugetlb_vma_unlock_read(vma); /* * We must check to release the per-VMA lock. __vmf_anon_prepare() is * the only way ret can be set to VM_FAULT_RETRY. */ if (unlikely(ret & VM_FAULT_RETRY)) vma_end_read(vma); mutex_unlock(&hugetlb_fault_mutex_table[hash]); return ret; backout: spin_unlock(vmf->ptl); backout_unlocked: if (new_folio && !new_pagecache_folio) restore_reserve_on_error(h, vma, vmf->address, folio); folio_unlock(folio); folio_put(folio); goto out; } #ifdef CONFIG_SMP u32 hugetlb_fault_mutex_hash(struct address_space *mapping, pgoff_t idx) { unsigned long key[2]; u32 hash; key[0] = (unsigned long) mapping; key[1] = idx; hash = jhash2((u32 *)&key, sizeof(key)/(sizeof(u32)), 0); return hash & (num_fault_mutexes - 1); } #else /* * For uniprocessor systems we always use a single mutex, so just * return 0 and avoid the hashing overhead. */ u32 hugetlb_fault_mutex_hash(struct address_space *mapping, pgoff_t idx) { return 0; } #endif vm_fault_t hugetlb_fault(struct mm_struct *mm, struct vm_area_struct *vma, unsigned long address, unsigned int flags) { vm_fault_t ret; u32 hash; struct folio *folio = NULL; struct folio *pagecache_folio = NULL; struct hstate *h = hstate_vma(vma); struct address_space *mapping; int need_wait_lock = 0; struct vm_fault vmf = { .vma = vma, .address = address & huge_page_mask(h), .real_address = address, .flags = flags, .pgoff = vma_hugecache_offset(h, vma, address & huge_page_mask(h)), /* TODO: Track hugetlb faults using vm_fault */ /* * Some fields may not be initialized, be careful as it may * be hard to debug if called functions make assumptions */ }; /* * Serialize hugepage allocation and instantiation, so that we don't * get spurious allocation failures if two CPUs race to instantiate * the same page in the page cache. */ mapping = vma->vm_file->f_mapping; hash = hugetlb_fault_mutex_hash(mapping, vmf.pgoff); mutex_lock(&hugetlb_fault_mutex_table[hash]); /* * Acquire vma lock before calling huge_pte_alloc and hold * until finished with vmf.pte. This prevents huge_pmd_unshare from * being called elsewhere and making the vmf.pte no longer valid. */ hugetlb_vma_lock_read(vma); vmf.pte = huge_pte_alloc(mm, vma, vmf.address, huge_page_size(h)); if (!vmf.pte) { hugetlb_vma_unlock_read(vma); mutex_unlock(&hugetlb_fault_mutex_table[hash]); return VM_FAULT_OOM; } vmf.orig_pte = huge_ptep_get(mm, vmf.address, vmf.pte); if (huge_pte_none_mostly(vmf.orig_pte)) { if (is_pte_marker(vmf.orig_pte)) { pte_marker marker = pte_marker_get(pte_to_swp_entry(vmf.orig_pte)); if (marker & PTE_MARKER_POISONED) { ret = VM_FAULT_HWPOISON_LARGE | VM_FAULT_SET_HINDEX(hstate_index(h)); goto out_mutex; } else if (WARN_ON_ONCE(marker & PTE_MARKER_GUARD)) { /* This isn't supported in hugetlb. */ ret = VM_FAULT_SIGSEGV; goto out_mutex; } } /* * Other PTE markers should be handled the same way as none PTE. * * hugetlb_no_page will drop vma lock and hugetlb fault * mutex internally, which make us return immediately. */ return hugetlb_no_page(mapping, &vmf); } ret = 0; /* * vmf.orig_pte could be a migration/hwpoison vmf.orig_pte at this * point, so this check prevents the kernel from going below assuming * that we have an active hugepage in pagecache. This goto expects * the 2nd page fault, and is_hugetlb_entry_(migration|hwpoisoned) * check will properly handle it. */ if (!pte_present(vmf.orig_pte)) { if (unlikely(is_hugetlb_entry_migration(vmf.orig_pte))) { /* * Release the hugetlb fault lock now, but retain * the vma lock, because it is needed to guard the * huge_pte_lockptr() later in * migration_entry_wait_huge(). The vma lock will * be released there. */ mutex_unlock(&hugetlb_fault_mutex_table[hash]); migration_entry_wait_huge(vma, vmf.address, vmf.pte); return 0; } else if (unlikely(is_hugetlb_entry_hwpoisoned(vmf.orig_pte))) ret = VM_FAULT_HWPOISON_LARGE | VM_FAULT_SET_HINDEX(hstate_index(h)); goto out_mutex; } /* * If we are going to COW/unshare the mapping later, we examine the * pending reservations for this page now. This will ensure that any * allocations necessary to record that reservation occur outside the * spinlock. Also lookup the pagecache page now as it is used to * determine if a reservation has been consumed. */ if ((flags & (FAULT_FLAG_WRITE|FAULT_FLAG_UNSHARE)) && !(vma->vm_flags & VM_MAYSHARE) && !huge_pte_write(vmf.orig_pte)) { if (vma_needs_reservation(h, vma, vmf.address) < 0) { ret = VM_FAULT_OOM; goto out_mutex; } /* Just decrements count, does not deallocate */ vma_end_reservation(h, vma, vmf.address); pagecache_folio = filemap_lock_hugetlb_folio(h, mapping, vmf.pgoff); if (IS_ERR(pagecache_folio)) pagecache_folio = NULL; } vmf.ptl = huge_pte_lock(h, mm, vmf.pte); /* Check for a racing update before calling hugetlb_wp() */ if (unlikely(!pte_same(vmf.orig_pte, huge_ptep_get(mm, vmf.address, vmf.pte)))) goto out_ptl; /* Handle userfault-wp first, before trying to lock more pages */ if (userfaultfd_wp(vma) && huge_pte_uffd_wp(huge_ptep_get(mm, vmf.address, vmf.pte)) && (flags & FAULT_FLAG_WRITE) && !huge_pte_write(vmf.orig_pte)) { if (!userfaultfd_wp_async(vma)) { spin_unlock(vmf.ptl); if (pagecache_folio) { folio_unlock(pagecache_folio); folio_put(pagecache_folio); } hugetlb_vma_unlock_read(vma); mutex_unlock(&hugetlb_fault_mutex_table[hash]); return handle_userfault(&vmf, VM_UFFD_WP); } vmf.orig_pte = huge_pte_clear_uffd_wp(vmf.orig_pte); set_huge_pte_at(mm, vmf.address, vmf.pte, vmf.orig_pte, huge_page_size(hstate_vma(vma))); /* Fallthrough to CoW */ } /* * hugetlb_wp() requires page locks of pte_page(vmf.orig_pte) and * pagecache_folio, so here we need take the former one * when folio != pagecache_folio or !pagecache_folio. */ folio = page_folio(pte_page(vmf.orig_pte)); if (folio != pagecache_folio) if (!folio_trylock(folio)) { need_wait_lock = 1; goto out_ptl; } folio_get(folio); if (flags & (FAULT_FLAG_WRITE|FAULT_FLAG_UNSHARE)) { if (!huge_pte_write(vmf.orig_pte)) { ret = hugetlb_wp(pagecache_folio, &vmf); goto out_put_page; } else if (likely(flags & FAULT_FLAG_WRITE)) { vmf.orig_pte = huge_pte_mkdirty(vmf.orig_pte); } } vmf.orig_pte = pte_mkyoung(vmf.orig_pte); if (huge_ptep_set_access_flags(vma, vmf.address, vmf.pte, vmf.orig_pte, flags & FAULT_FLAG_WRITE)) update_mmu_cache(vma, vmf.address, vmf.pte); out_put_page: if (folio != pagecache_folio) folio_unlock(folio); folio_put(folio); out_ptl: spin_unlock(vmf.ptl); if (pagecache_folio) { folio_unlock(pagecache_folio); folio_put(pagecache_folio); } out_mutex: hugetlb_vma_unlock_read(vma); /* * We must check to release the per-VMA lock. __vmf_anon_prepare() in * hugetlb_wp() is the only way ret can be set to VM_FAULT_RETRY. */ if (unlikely(ret & VM_FAULT_RETRY)) vma_end_read(vma); mutex_unlock(&hugetlb_fault_mutex_table[hash]); /* * Generally it's safe to hold refcount during waiting page lock. But * here we just wait to defer the next page fault to avoid busy loop and * the page is not used after unlocked before returning from the current * page fault. So we are safe from accessing freed page, even if we wait * here without taking refcount. */ if (need_wait_lock) folio_wait_locked(folio); return ret; } #ifdef CONFIG_USERFAULTFD /* * Can probably be eliminated, but still used by hugetlb_mfill_atomic_pte(). */ static struct folio *alloc_hugetlb_folio_vma(struct hstate *h, struct vm_area_struct *vma, unsigned long address) { struct mempolicy *mpol; nodemask_t *nodemask; struct folio *folio; gfp_t gfp_mask; int node; gfp_mask = htlb_alloc_mask(h); node = huge_node(vma, address, gfp_mask, &mpol, &nodemask); /* * This is used to allocate a temporary hugetlb to hold the copied * content, which will then be copied again to the final hugetlb * consuming a reservation. Set the alloc_fallback to false to indicate * that breaking the per-node hugetlb pool is not allowed in this case. */ folio = alloc_hugetlb_folio_nodemask(h, node, nodemask, gfp_mask, false); mpol_cond_put(mpol); return folio; } /* * Used by userfaultfd UFFDIO_* ioctls. Based on userfaultfd's mfill_atomic_pte * with modifications for hugetlb pages. */ int hugetlb_mfill_atomic_pte(pte_t *dst_pte, struct vm_area_struct *dst_vma, unsigned long dst_addr, unsigned long src_addr, uffd_flags_t flags, struct folio **foliop) { struct mm_struct *dst_mm = dst_vma->vm_mm; bool is_continue = uffd_flags_mode_is(flags, MFILL_ATOMIC_CONTINUE); bool wp_enabled = (flags & MFILL_ATOMIC_WP); struct hstate *h = hstate_vma(dst_vma); struct address_space *mapping = dst_vma->vm_file->f_mapping; pgoff_t idx = vma_hugecache_offset(h, dst_vma, dst_addr); unsigned long size = huge_page_size(h); int vm_shared = dst_vma->vm_flags & VM_SHARED; pte_t _dst_pte; spinlock_t *ptl; int ret = -ENOMEM; struct folio *folio; int writable; bool folio_in_pagecache = false; if (uffd_flags_mode_is(flags, MFILL_ATOMIC_POISON)) { ptl = huge_pte_lock(h, dst_mm, dst_pte); /* Don't overwrite any existing PTEs (even markers) */ if (!huge_pte_none(huge_ptep_get(dst_mm, dst_addr, dst_pte))) { spin_unlock(ptl); return -EEXIST; } _dst_pte = make_pte_marker(PTE_MARKER_POISONED); set_huge_pte_at(dst_mm, dst_addr, dst_pte, _dst_pte, size); /* No need to invalidate - it was non-present before */ update_mmu_cache(dst_vma, dst_addr, dst_pte); spin_unlock(ptl); return 0; } if (is_continue) { ret = -EFAULT; folio = filemap_lock_hugetlb_folio(h, mapping, idx); if (IS_ERR(folio)) goto out; folio_in_pagecache = true; } else if (!*foliop) { /* If a folio already exists, then it's UFFDIO_COPY for * a non-missing case. Return -EEXIST. */ if (vm_shared && hugetlbfs_pagecache_present(h, dst_vma, dst_addr)) { ret = -EEXIST; goto out; } folio = alloc_hugetlb_folio(dst_vma, dst_addr, 0); if (IS_ERR(folio)) { ret = -ENOMEM; goto out; } ret = copy_folio_from_user(folio, (const void __user *) src_addr, false); /* fallback to copy_from_user outside mmap_lock */ if (unlikely(ret)) { ret = -ENOENT; /* Free the allocated folio which may have * consumed a reservation. */ restore_reserve_on_error(h, dst_vma, dst_addr, folio); folio_put(folio); /* Allocate a temporary folio to hold the copied * contents. */ folio = alloc_hugetlb_folio_vma(h, dst_vma, dst_addr); if (!folio) { ret = -ENOMEM; goto out; } *foliop = folio; /* Set the outparam foliop and return to the caller to * copy the contents outside the lock. Don't free the * folio. */ goto out; } } else { if (vm_shared && hugetlbfs_pagecache_present(h, dst_vma, dst_addr)) { folio_put(*foliop); ret = -EEXIST; *foliop = NULL; goto out; } folio = alloc_hugetlb_folio(dst_vma, dst_addr, 0); if (IS_ERR(folio)) { folio_put(*foliop); ret = -ENOMEM; *foliop = NULL; goto out; } ret = copy_user_large_folio(folio, *foliop, ALIGN_DOWN(dst_addr, size), dst_vma); folio_put(*foliop); *foliop = NULL; if (ret) { folio_put(folio); goto out; } } /* * If we just allocated a new page, we need a memory barrier to ensure * that preceding stores to the page become visible before the * set_pte_at() write. The memory barrier inside __folio_mark_uptodate * is what we need. * * In the case where we have not allocated a new page (is_continue), * the page must already be uptodate. UFFDIO_CONTINUE already includes * an earlier smp_wmb() to ensure that prior stores will be visible * before the set_pte_at() write. */ if (!is_continue) __folio_mark_uptodate(folio); else WARN_ON_ONCE(!folio_test_uptodate(folio)); /* Add shared, newly allocated pages to the page cache. */ if (vm_shared && !is_continue) { ret = -EFAULT; if (idx >= (i_size_read(mapping->host) >> huge_page_shift(h))) goto out_release_nounlock; /* * Serialization between remove_inode_hugepages() and * hugetlb_add_to_page_cache() below happens through the * hugetlb_fault_mutex_table that here must be hold by * the caller. */ ret = hugetlb_add_to_page_cache(folio, mapping, idx); if (ret) goto out_release_nounlock; folio_in_pagecache = true; } ptl = huge_pte_lock(h, dst_mm, dst_pte); ret = -EIO; if (folio_test_hwpoison(folio)) goto out_release_unlock; /* * We allow to overwrite a pte marker: consider when both MISSING|WP * registered, we firstly wr-protect a none pte which has no page cache * page backing it, then access the page. */ ret = -EEXIST; if (!huge_pte_none_mostly(huge_ptep_get(dst_mm, dst_addr, dst_pte))) goto out_release_unlock; if (folio_in_pagecache) hugetlb_add_file_rmap(folio); else hugetlb_add_new_anon_rmap(folio, dst_vma, dst_addr); /* * For either: (1) CONTINUE on a non-shared VMA, or (2) UFFDIO_COPY * with wp flag set, don't set pte write bit. */ if (wp_enabled || (is_continue && !vm_shared)) writable = 0; else writable = dst_vma->vm_flags & VM_WRITE; _dst_pte = make_huge_pte(dst_vma, &folio->page, writable); /* * Always mark UFFDIO_COPY page dirty; note that this may not be * extremely important for hugetlbfs for now since swapping is not * supported, but we should still be clear in that this page cannot be * thrown away at will, even if write bit not set. */ _dst_pte = huge_pte_mkdirty(_dst_pte); _dst_pte = pte_mkyoung(_dst_pte); if (wp_enabled) _dst_pte = huge_pte_mkuffd_wp(_dst_pte); set_huge_pte_at(dst_mm, dst_addr, dst_pte, _dst_pte, size); hugetlb_count_add(pages_per_huge_page(h), dst_mm); /* No need to invalidate - it was non-present before */ update_mmu_cache(dst_vma, dst_addr, dst_pte); spin_unlock(ptl); if (!is_continue) folio_set_hugetlb_migratable(folio); if (vm_shared || is_continue) folio_unlock(folio); ret = 0; out: return ret; out_release_unlock: spin_unlock(ptl); if (vm_shared || is_continue) folio_unlock(folio); out_release_nounlock: if (!folio_in_pagecache) restore_reserve_on_error(h, dst_vma, dst_addr, folio); folio_put(folio); goto out; } #endif /* CONFIG_USERFAULTFD */ long hugetlb_change_protection(struct vm_area_struct *vma, unsigned long address, unsigned long end, pgprot_t newprot, unsigned long cp_flags) { struct mm_struct *mm = vma->vm_mm; unsigned long start = address; pte_t *ptep; pte_t pte; struct hstate *h = hstate_vma(vma); long pages = 0, psize = huge_page_size(h); bool shared_pmd = false; struct mmu_notifier_range range; unsigned long last_addr_mask; bool uffd_wp = cp_flags & MM_CP_UFFD_WP; bool uffd_wp_resolve = cp_flags & MM_CP_UFFD_WP_RESOLVE; /* * In the case of shared PMDs, the area to flush could be beyond * start/end. Set range.start/range.end to cover the maximum possible * range if PMD sharing is possible. */ mmu_notifier_range_init(&range, MMU_NOTIFY_PROTECTION_VMA, 0, mm, start, end); adjust_range_if_pmd_sharing_possible(vma, &range.start, &range.end); BUG_ON(address >= end); flush_cache_range(vma, range.start, range.end); mmu_notifier_invalidate_range_start(&range); hugetlb_vma_lock_write(vma); i_mmap_lock_write(vma->vm_file->f_mapping); last_addr_mask = hugetlb_mask_last_page(h); for (; address < end; address += psize) { spinlock_t *ptl; ptep = hugetlb_walk(vma, address, psize); if (!ptep) { if (!uffd_wp) { address |= last_addr_mask; continue; } /* * Userfaultfd wr-protect requires pgtable * pre-allocations to install pte markers. */ ptep = huge_pte_alloc(mm, vma, address, psize); if (!ptep) { pages = -ENOMEM; break; } } ptl = huge_pte_lock(h, mm, ptep); if (huge_pmd_unshare(mm, vma, address, ptep)) { /* * When uffd-wp is enabled on the vma, unshare * shouldn't happen at all. Warn about it if it * happened due to some reason. */ WARN_ON_ONCE(uffd_wp || uffd_wp_resolve); pages++; spin_unlock(ptl); shared_pmd = true; address |= last_addr_mask; continue; } pte = huge_ptep_get(mm, address, ptep); if (unlikely(is_hugetlb_entry_hwpoisoned(pte))) { /* Nothing to do. */ } else if (unlikely(is_hugetlb_entry_migration(pte))) { swp_entry_t entry = pte_to_swp_entry(pte); struct page *page = pfn_swap_entry_to_page(entry); pte_t newpte = pte; if (is_writable_migration_entry(entry)) { if (PageAnon(page)) entry = make_readable_exclusive_migration_entry( swp_offset(entry)); else entry = make_readable_migration_entry( swp_offset(entry)); newpte = swp_entry_to_pte(entry); pages++; } if (uffd_wp) newpte = pte_swp_mkuffd_wp(newpte); else if (uffd_wp_resolve) newpte = pte_swp_clear_uffd_wp(newpte); if (!pte_same(pte, newpte)) set_huge_pte_at(mm, address, ptep, newpte, psize); } else if (unlikely(is_pte_marker(pte))) { /* * Do nothing on a poison marker; page is * corrupted, permissons do not apply. Here * pte_marker_uffd_wp()==true implies !poison * because they're mutual exclusive. */ if (pte_marker_uffd_wp(pte) && uffd_wp_resolve) /* Safe to modify directly (non-present->none). */ huge_pte_clear(mm, address, ptep, psize); } else if (!huge_pte_none(pte)) { pte_t old_pte; unsigned int shift = huge_page_shift(hstate_vma(vma)); old_pte = huge_ptep_modify_prot_start(vma, address, ptep); pte = huge_pte_modify(old_pte, newprot); pte = arch_make_huge_pte(pte, shift, vma->vm_flags); if (uffd_wp) pte = huge_pte_mkuffd_wp(pte); else if (uffd_wp_resolve) pte = huge_pte_clear_uffd_wp(pte); huge_ptep_modify_prot_commit(vma, address, ptep, old_pte, pte); pages++; } else { /* None pte */ if (unlikely(uffd_wp)) /* Safe to modify directly (none->non-present). */ set_huge_pte_at(mm, address, ptep, make_pte_marker(PTE_MARKER_UFFD_WP), psize); } spin_unlock(ptl); } /* * Must flush TLB before releasing i_mmap_rwsem: x86's huge_pmd_unshare * may have cleared our pud entry and done put_page on the page table: * once we release i_mmap_rwsem, another task can do the final put_page * and that page table be reused and filled with junk. If we actually * did unshare a page of pmds, flush the range corresponding to the pud. */ if (shared_pmd) flush_hugetlb_tlb_range(vma, range.start, range.end); else flush_hugetlb_tlb_range(vma, start, end); /* * No need to call mmu_notifier_arch_invalidate_secondary_tlbs() we are * downgrading page table protection not changing it to point to a new * page. * * See Documentation/mm/mmu_notifier.rst */ i_mmap_unlock_write(vma->vm_file->f_mapping); hugetlb_vma_unlock_write(vma); mmu_notifier_invalidate_range_end(&range); return pages > 0 ? (pages << h->order) : pages; } /* Return true if reservation was successful, false otherwise. */ bool hugetlb_reserve_pages(struct inode *inode, long from, long to, struct vm_area_struct *vma, vm_flags_t vm_flags) { long chg = -1, add = -1; struct hstate *h = hstate_inode(inode); struct hugepage_subpool *spool = subpool_inode(inode); struct resv_map *resv_map; struct hugetlb_cgroup *h_cg = NULL; long gbl_reserve, regions_needed = 0; /* This should never happen */ if (from > to) { VM_WARN(1, "%s called with a negative range\n", __func__); return false; } /* * vma specific semaphore used for pmd sharing and fault/truncation * synchronization */ hugetlb_vma_lock_alloc(vma); /* * Only apply hugepage reservation if asked. At fault time, an * attempt will be made for VM_NORESERVE to allocate a page * without using reserves */ if (vm_flags & VM_NORESERVE) return true; /* * Shared mappings base their reservation on the number of pages that * are already allocated on behalf of the file. Private mappings need * to reserve the full area even if read-only as mprotect() may be * called to make the mapping read-write. Assume !vma is a shm mapping */ if (!vma || vma->vm_flags & VM_MAYSHARE) { /* * resv_map can not be NULL as hugetlb_reserve_pages is only * called for inodes for which resv_maps were created (see * hugetlbfs_get_inode). */ resv_map = inode_resv_map(inode); chg = region_chg(resv_map, from, to, ®ions_needed); } else { /* Private mapping. */ resv_map = resv_map_alloc(); if (!resv_map) goto out_err; chg = to - from; set_vma_resv_map(vma, resv_map); set_vma_resv_flags(vma, HPAGE_RESV_OWNER); } if (chg < 0) goto out_err; if (hugetlb_cgroup_charge_cgroup_rsvd(hstate_index(h), chg * pages_per_huge_page(h), &h_cg) < 0) goto out_err; if (vma && !(vma->vm_flags & VM_MAYSHARE) && h_cg) { /* For private mappings, the hugetlb_cgroup uncharge info hangs * of the resv_map. */ resv_map_set_hugetlb_cgroup_uncharge_info(resv_map, h_cg, h); } /* * There must be enough pages in the subpool for the mapping. If * the subpool has a minimum size, there may be some global * reservations already in place (gbl_reserve). */ gbl_reserve = hugepage_subpool_get_pages(spool, chg); if (gbl_reserve < 0) goto out_uncharge_cgroup; /* * Check enough hugepages are available for the reservation. * Hand the pages back to the subpool if there are not */ if (hugetlb_acct_memory(h, gbl_reserve) < 0) goto out_put_pages; /* * Account for the reservations made. Shared mappings record regions * that have reservations as they are shared by multiple VMAs. * When the last VMA disappears, the region map says how much * the reservation was and the page cache tells how much of * the reservation was consumed. Private mappings are per-VMA and * only the consumed reservations are tracked. When the VMA * disappears, the original reservation is the VMA size and the * consumed reservations are stored in the map. Hence, nothing * else has to be done for private mappings here */ if (!vma || vma->vm_flags & VM_MAYSHARE) { add = region_add(resv_map, from, to, regions_needed, h, h_cg); if (unlikely(add < 0)) { hugetlb_acct_memory(h, -gbl_reserve); goto out_put_pages; } else if (unlikely(chg > add)) { /* * pages in this range were added to the reserve * map between region_chg and region_add. This * indicates a race with alloc_hugetlb_folio. Adjust * the subpool and reserve counts modified above * based on the difference. */ long rsv_adjust; /* * hugetlb_cgroup_uncharge_cgroup_rsvd() will put the * reference to h_cg->css. See comment below for detail. */ hugetlb_cgroup_uncharge_cgroup_rsvd( hstate_index(h), (chg - add) * pages_per_huge_page(h), h_cg); rsv_adjust = hugepage_subpool_put_pages(spool, chg - add); hugetlb_acct_memory(h, -rsv_adjust); } else if (h_cg) { /* * The file_regions will hold their own reference to * h_cg->css. So we should release the reference held * via hugetlb_cgroup_charge_cgroup_rsvd() when we are * done. */ hugetlb_cgroup_put_rsvd_cgroup(h_cg); } } return true; out_put_pages: /* put back original number of pages, chg */ (void)hugepage_subpool_put_pages(spool, chg); out_uncharge_cgroup: hugetlb_cgroup_uncharge_cgroup_rsvd(hstate_index(h), chg * pages_per_huge_page(h), h_cg); out_err: hugetlb_vma_lock_free(vma); if (!vma || vma->vm_flags & VM_MAYSHARE) /* Only call region_abort if the region_chg succeeded but the * region_add failed or didn't run. */ if (chg >= 0 && add < 0) region_abort(resv_map, from, to, regions_needed); if (vma && is_vma_resv_set(vma, HPAGE_RESV_OWNER)) { kref_put(&resv_map->refs, resv_map_release); set_vma_resv_map(vma, NULL); } return false; } long hugetlb_unreserve_pages(struct inode *inode, long start, long end, long freed) { struct hstate *h = hstate_inode(inode); struct resv_map *resv_map = inode_resv_map(inode); long chg = 0; struct hugepage_subpool *spool = subpool_inode(inode); long gbl_reserve; /* * Since this routine can be called in the evict inode path for all * hugetlbfs inodes, resv_map could be NULL. */ if (resv_map) { chg = region_del(resv_map, start, end); /* * region_del() can fail in the rare case where a region * must be split and another region descriptor can not be * allocated. If end == LONG_MAX, it will not fail. */ if (chg < 0) return chg; } spin_lock(&inode->i_lock); inode->i_blocks -= (blocks_per_huge_page(h) * freed); spin_unlock(&inode->i_lock); /* * If the subpool has a minimum size, the number of global * reservations to be released may be adjusted. * * Note that !resv_map implies freed == 0. So (chg - freed) * won't go negative. */ gbl_reserve = hugepage_subpool_put_pages(spool, (chg - freed)); hugetlb_acct_memory(h, -gbl_reserve); return 0; } #ifdef CONFIG_HUGETLB_PMD_PAGE_TABLE_SHARING static unsigned long page_table_shareable(struct vm_area_struct *svma, struct vm_area_struct *vma, unsigned long addr, pgoff_t idx) { unsigned long saddr = ((idx - svma->vm_pgoff) << PAGE_SHIFT) + svma->vm_start; unsigned long sbase = saddr & PUD_MASK; unsigned long s_end = sbase + PUD_SIZE; /* Allow segments to share if only one is marked locked */ unsigned long vm_flags = vma->vm_flags & ~VM_LOCKED_MASK; unsigned long svm_flags = svma->vm_flags & ~VM_LOCKED_MASK; /* * match the virtual addresses, permission and the alignment of the * page table page. * * Also, vma_lock (vm_private_data) is required for sharing. */ if (pmd_index(addr) != pmd_index(saddr) || vm_flags != svm_flags || !range_in_vma(svma, sbase, s_end) || !svma->vm_private_data) return 0; return saddr; } bool want_pmd_share(struct vm_area_struct *vma, unsigned long addr) { unsigned long start = addr & PUD_MASK; unsigned long end = start + PUD_SIZE; #ifdef CONFIG_USERFAULTFD if (uffd_disable_huge_pmd_share(vma)) return false; #endif /* * check on proper vm_flags and page table alignment */ if (!(vma->vm_flags & VM_MAYSHARE)) return false; if (!vma->vm_private_data) /* vma lock required for sharing */ return false; if (!range_in_vma(vma, start, end)) return false; return true; } /* * Determine if start,end range within vma could be mapped by shared pmd. * If yes, adjust start and end to cover range associated with possible * shared pmd mappings. */ void adjust_range_if_pmd_sharing_possible(struct vm_area_struct *vma, unsigned long *start, unsigned long *end) { unsigned long v_start = ALIGN(vma->vm_start, PUD_SIZE), v_end = ALIGN_DOWN(vma->vm_end, PUD_SIZE); /* * vma needs to span at least one aligned PUD size, and the range * must be at least partially within in. */ if (!(vma->vm_flags & VM_MAYSHARE) || !(v_end > v_start) || (*end <= v_start) || (*start >= v_end)) return; /* Extend the range to be PUD aligned for a worst case scenario */ if (*start > v_start) *start = ALIGN_DOWN(*start, PUD_SIZE); if (*end < v_end) *end = ALIGN(*end, PUD_SIZE); } /* * Search for a shareable pmd page for hugetlb. In any case calls pmd_alloc() * and returns the corresponding pte. While this is not necessary for the * !shared pmd case because we can allocate the pmd later as well, it makes the * code much cleaner. pmd allocation is essential for the shared case because * pud has to be populated inside the same i_mmap_rwsem section - otherwise * racing tasks could either miss the sharing (see huge_pte_offset) or select a * bad pmd for sharing. */ pte_t *huge_pmd_share(struct mm_struct *mm, struct vm_area_struct *vma, unsigned long addr, pud_t *pud) { struct address_space *mapping = vma->vm_file->f_mapping; pgoff_t idx = ((addr - vma->vm_start) >> PAGE_SHIFT) + vma->vm_pgoff; struct vm_area_struct *svma; unsigned long saddr; pte_t *spte = NULL; pte_t *pte; i_mmap_lock_read(mapping); vma_interval_tree_foreach(svma, &mapping->i_mmap, idx, idx) { if (svma == vma) continue; saddr = page_table_shareable(svma, vma, addr, idx); if (saddr) { spte = hugetlb_walk(svma, saddr, vma_mmu_pagesize(svma)); if (spte) { get_page(virt_to_page(spte)); break; } } } if (!spte) goto out; spin_lock(&mm->page_table_lock); if (pud_none(*pud)) { pud_populate(mm, pud, (pmd_t *)((unsigned long)spte & PAGE_MASK)); mm_inc_nr_pmds(mm); } else { put_page(virt_to_page(spte)); } spin_unlock(&mm->page_table_lock); out: pte = (pte_t *)pmd_alloc(mm, pud, addr); i_mmap_unlock_read(mapping); return pte; } /* * unmap huge page backed by shared pte. * * Hugetlb pte page is ref counted at the time of mapping. If pte is shared * indicated by page_count > 1, unmap is achieved by clearing pud and * decrementing the ref count. If count == 1, the pte page is not shared. * * Called with page table lock held. * * returns: 1 successfully unmapped a shared pte page * 0 the underlying pte page is not shared, or it is the last user */ int huge_pmd_unshare(struct mm_struct *mm, struct vm_area_struct *vma, unsigned long addr, pte_t *ptep) { pgd_t *pgd = pgd_offset(mm, addr); p4d_t *p4d = p4d_offset(pgd, addr); pud_t *pud = pud_offset(p4d, addr); i_mmap_assert_write_locked(vma->vm_file->f_mapping); hugetlb_vma_assert_locked(vma); BUG_ON(page_count(virt_to_page(ptep)) == 0); if (page_count(virt_to_page(ptep)) == 1) return 0; pud_clear(pud); put_page(virt_to_page(ptep)); mm_dec_nr_pmds(mm); return 1; } #else /* !CONFIG_HUGETLB_PMD_PAGE_TABLE_SHARING */ pte_t *huge_pmd_share(struct mm_struct *mm, struct vm_area_struct *vma, unsigned long addr, pud_t *pud) { return NULL; } int huge_pmd_unshare(struct mm_struct *mm, struct vm_area_struct *vma, unsigned long addr, pte_t *ptep) { return 0; } void adjust_range_if_pmd_sharing_possible(struct vm_area_struct *vma, unsigned long *start, unsigned long *end) { } bool want_pmd_share(struct vm_area_struct *vma, unsigned long addr) { return false; } #endif /* CONFIG_HUGETLB_PMD_PAGE_TABLE_SHARING */ #ifdef CONFIG_ARCH_WANT_GENERAL_HUGETLB pte_t *huge_pte_alloc(struct mm_struct *mm, struct vm_area_struct *vma, unsigned long addr, unsigned long sz) { pgd_t *pgd; p4d_t *p4d; pud_t *pud; pte_t *pte = NULL; pgd = pgd_offset(mm, addr); p4d = p4d_alloc(mm, pgd, addr); if (!p4d) return NULL; pud = pud_alloc(mm, p4d, addr); if (pud) { if (sz == PUD_SIZE) { pte = (pte_t *)pud; } else { BUG_ON(sz != PMD_SIZE); if (want_pmd_share(vma, addr) && pud_none(*pud)) pte = huge_pmd_share(mm, vma, addr, pud); else pte = (pte_t *)pmd_alloc(mm, pud, addr); } } if (pte) { pte_t pteval = ptep_get_lockless(pte); BUG_ON(pte_present(pteval) && !pte_huge(pteval)); } return pte; } /* * huge_pte_offset() - Walk the page table to resolve the hugepage * entry at address @addr * * Return: Pointer to page table entry (PUD or PMD) for * address @addr, or NULL if a !p*d_present() entry is encountered and the * size @sz doesn't match the hugepage size at this level of the page * table. */ pte_t *huge_pte_offset(struct mm_struct *mm, unsigned long addr, unsigned long sz) { pgd_t *pgd; p4d_t *p4d; pud_t *pud; pmd_t *pmd; pgd = pgd_offset(mm, addr); if (!pgd_present(*pgd)) return NULL; p4d = p4d_offset(pgd, addr); if (!p4d_present(*p4d)) return NULL; pud = pud_offset(p4d, addr); if (sz == PUD_SIZE) /* must be pud huge, non-present or none */ return (pte_t *)pud; if (!pud_present(*pud)) return NULL; /* must have a valid entry and size to go further */ pmd = pmd_offset(pud, addr); /* must be pmd huge, non-present or none */ return (pte_t *)pmd; } /* * Return a mask that can be used to update an address to the last huge * page in a page table page mapping size. Used to skip non-present * page table entries when linearly scanning address ranges. Architectures * with unique huge page to page table relationships can define their own * version of this routine. */ unsigned long hugetlb_mask_last_page(struct hstate *h) { unsigned long hp_size = huge_page_size(h); if (hp_size == PUD_SIZE) return P4D_SIZE - PUD_SIZE; else if (hp_size == PMD_SIZE) return PUD_SIZE - PMD_SIZE; else return 0UL; } #else /* See description above. Architectures can provide their own version. */ __weak unsigned long hugetlb_mask_last_page(struct hstate *h) { #ifdef CONFIG_HUGETLB_PMD_PAGE_TABLE_SHARING if (huge_page_size(h) == PMD_SIZE) return PUD_SIZE - PMD_SIZE; #endif return 0UL; } #endif /* CONFIG_ARCH_WANT_GENERAL_HUGETLB */ bool isolate_hugetlb(struct folio *folio, struct list_head *list) { bool ret = true; spin_lock_irq(&hugetlb_lock); if (!folio_test_hugetlb(folio) || !folio_test_hugetlb_migratable(folio) || !folio_try_get(folio)) { ret = false; goto unlock; } folio_clear_hugetlb_migratable(folio); list_move_tail(&folio->lru, list); unlock: spin_unlock_irq(&hugetlb_lock); return ret; } int get_hwpoison_hugetlb_folio(struct folio *folio, bool *hugetlb, bool unpoison) { int ret = 0; *hugetlb = false; spin_lock_irq(&hugetlb_lock); if (folio_test_hugetlb(folio)) { *hugetlb = true; if (folio_test_hugetlb_freed(folio)) ret = 0; else if (folio_test_hugetlb_migratable(folio) || unpoison) ret = folio_try_get(folio); else ret = -EBUSY; } spin_unlock_irq(&hugetlb_lock); return ret; } int get_huge_page_for_hwpoison(unsigned long pfn, int flags, bool *migratable_cleared) { int ret; spin_lock_irq(&hugetlb_lock); ret = __get_huge_page_for_hwpoison(pfn, flags, migratable_cleared); spin_unlock_irq(&hugetlb_lock); return ret; } void folio_putback_active_hugetlb(struct folio *folio) { spin_lock_irq(&hugetlb_lock); folio_set_hugetlb_migratable(folio); list_move_tail(&folio->lru, &(folio_hstate(folio))->hugepage_activelist); spin_unlock_irq(&hugetlb_lock); folio_put(folio); } void move_hugetlb_state(struct folio *old_folio, struct folio *new_folio, int reason) { struct hstate *h = folio_hstate(old_folio); hugetlb_cgroup_migrate(old_folio, new_folio); set_page_owner_migrate_reason(&new_folio->page, reason); /* * transfer temporary state of the new hugetlb folio. This is * reverse to other transitions because the newpage is going to * be final while the old one will be freed so it takes over * the temporary status. * * Also note that we have to transfer the per-node surplus state * here as well otherwise the global surplus count will not match * the per-node's. */ if (folio_test_hugetlb_temporary(new_folio)) { int old_nid = folio_nid(old_folio); int new_nid = folio_nid(new_folio); folio_set_hugetlb_temporary(old_folio); folio_clear_hugetlb_temporary(new_folio); /* * There is no need to transfer the per-node surplus state * when we do not cross the node. */ if (new_nid == old_nid) return; spin_lock_irq(&hugetlb_lock); if (h->surplus_huge_pages_node[old_nid]) { h->surplus_huge_pages_node[old_nid]--; h->surplus_huge_pages_node[new_nid]++; } spin_unlock_irq(&hugetlb_lock); } } static void hugetlb_unshare_pmds(struct vm_area_struct *vma, unsigned long start, unsigned long end) { struct hstate *h = hstate_vma(vma); unsigned long sz = huge_page_size(h); struct mm_struct *mm = vma->vm_mm; struct mmu_notifier_range range; unsigned long address; spinlock_t *ptl; pte_t *ptep; if (!(vma->vm_flags & VM_MAYSHARE)) return; if (start >= end) return; flush_cache_range(vma, start, end); /* * No need to call adjust_range_if_pmd_sharing_possible(), because * we have already done the PUD_SIZE alignment. */ mmu_notifier_range_init(&range, MMU_NOTIFY_CLEAR, 0, mm, start, end); mmu_notifier_invalidate_range_start(&range); hugetlb_vma_lock_write(vma); i_mmap_lock_write(vma->vm_file->f_mapping); for (address = start; address < end; address += PUD_SIZE) { ptep = hugetlb_walk(vma, address, sz); if (!ptep) continue; ptl = huge_pte_lock(h, mm, ptep); huge_pmd_unshare(mm, vma, address, ptep); spin_unlock(ptl); } flush_hugetlb_tlb_range(vma, start, end); i_mmap_unlock_write(vma->vm_file->f_mapping); hugetlb_vma_unlock_write(vma); /* * No need to call mmu_notifier_arch_invalidate_secondary_tlbs(), see * Documentation/mm/mmu_notifier.rst. */ mmu_notifier_invalidate_range_end(&range); } /* * This function will unconditionally remove all the shared pmd pgtable entries * within the specific vma for a hugetlbfs memory range. */ void hugetlb_unshare_all_pmds(struct vm_area_struct *vma) { hugetlb_unshare_pmds(vma, ALIGN(vma->vm_start, PUD_SIZE), ALIGN_DOWN(vma->vm_end, PUD_SIZE)); } #ifdef CONFIG_CMA static bool cma_reserve_called __initdata; static int __init cmdline_parse_hugetlb_cma(char *p) { int nid, count = 0; unsigned long tmp; char *s = p; while (*s) { if (sscanf(s, "%lu%n", &tmp, &count) != 1) break; if (s[count] == ':') { if (tmp >= MAX_NUMNODES) break; nid = array_index_nospec(tmp, MAX_NUMNODES); s += count + 1; tmp = memparse(s, &s); hugetlb_cma_size_in_node[nid] = tmp; hugetlb_cma_size += tmp; /* * Skip the separator if have one, otherwise * break the parsing. */ if (*s == ',') s++; else break; } else { hugetlb_cma_size = memparse(p, &p); break; } } return 0; } early_param("hugetlb_cma", cmdline_parse_hugetlb_cma); void __init hugetlb_cma_reserve(int order) { unsigned long size, reserved, per_node; bool node_specific_cma_alloc = false; int nid; /* * HugeTLB CMA reservation is required for gigantic * huge pages which could not be allocated via the * page allocator. Just warn if there is any change * breaking this assumption. */ VM_WARN_ON(order <= MAX_PAGE_ORDER); cma_reserve_called = true; if (!hugetlb_cma_size) return; for (nid = 0; nid < MAX_NUMNODES; nid++) { if (hugetlb_cma_size_in_node[nid] == 0) continue; if (!node_online(nid)) { pr_warn("hugetlb_cma: invalid node %d specified\n", nid); hugetlb_cma_size -= hugetlb_cma_size_in_node[nid]; hugetlb_cma_size_in_node[nid] = 0; continue; } if (hugetlb_cma_size_in_node[nid] < (PAGE_SIZE << order)) { pr_warn("hugetlb_cma: cma area of node %d should be at least %lu MiB\n", nid, (PAGE_SIZE << order) / SZ_1M); hugetlb_cma_size -= hugetlb_cma_size_in_node[nid]; hugetlb_cma_size_in_node[nid] = 0; } else { node_specific_cma_alloc = true; } } /* Validate the CMA size again in case some invalid nodes specified. */ if (!hugetlb_cma_size) return; if (hugetlb_cma_size < (PAGE_SIZE << order)) { pr_warn("hugetlb_cma: cma area should be at least %lu MiB\n", (PAGE_SIZE << order) / SZ_1M); hugetlb_cma_size = 0; return; } if (!node_specific_cma_alloc) { /* * If 3 GB area is requested on a machine with 4 numa nodes, * let's allocate 1 GB on first three nodes and ignore the last one. */ per_node = DIV_ROUND_UP(hugetlb_cma_size, nr_online_nodes); pr_info("hugetlb_cma: reserve %lu MiB, up to %lu MiB per node\n", hugetlb_cma_size / SZ_1M, per_node / SZ_1M); } reserved = 0; for_each_online_node(nid) { int res; char name[CMA_MAX_NAME]; if (node_specific_cma_alloc) { if (hugetlb_cma_size_in_node[nid] == 0) continue; size = hugetlb_cma_size_in_node[nid]; } else { size = min(per_node, hugetlb_cma_size - reserved); } size = round_up(size, PAGE_SIZE << order); snprintf(name, sizeof(name), "hugetlb%d", nid); /* * Note that 'order per bit' is based on smallest size that * may be returned to CMA allocator in the case of * huge page demotion. */ res = cma_declare_contiguous_nid(0, size, 0, PAGE_SIZE << order, HUGETLB_PAGE_ORDER, false, name, &hugetlb_cma[nid], nid); if (res) { pr_warn("hugetlb_cma: reservation failed: err %d, node %d", res, nid); continue; } reserved += size; pr_info("hugetlb_cma: reserved %lu MiB on node %d\n", size / SZ_1M, nid); if (reserved >= hugetlb_cma_size) break; } if (!reserved) /* * hugetlb_cma_size is used to determine if allocations from * cma are possible. Set to zero if no cma regions are set up. */ hugetlb_cma_size = 0; } static void __init hugetlb_cma_check(void) { if (!hugetlb_cma_size || cma_reserve_called) return; pr_warn("hugetlb_cma: the option isn't supported by current arch\n"); } #endif /* CONFIG_CMA */ |
| 3 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 | /* SPDX-License-Identifier: GPL-2.0-only */ /* * Copyright (C) 2012,2013 - ARM Ltd * Author: Marc Zyngier <marc.zyngier@arm.com> */ #ifndef __KVM_ARM_PSCI_H__ #define __KVM_ARM_PSCI_H__ #include <linux/kvm_host.h> #include <uapi/linux/psci.h> #define KVM_ARM_PSCI_0_1 PSCI_VERSION(0, 1) #define KVM_ARM_PSCI_0_2 PSCI_VERSION(0, 2) #define KVM_ARM_PSCI_1_0 PSCI_VERSION(1, 0) #define KVM_ARM_PSCI_1_1 PSCI_VERSION(1, 1) #define KVM_ARM_PSCI_1_2 PSCI_VERSION(1, 2) #define KVM_ARM_PSCI_1_3 PSCI_VERSION(1, 3) #define KVM_ARM_PSCI_LATEST KVM_ARM_PSCI_1_3 static inline int kvm_psci_version(struct kvm_vcpu *vcpu) { /* * Our PSCI implementation stays the same across versions from * v0.2 onward, only adding the few mandatory functions (such * as FEATURES with 1.0) that are required by newer * revisions. It is thus safe to return the latest, unless * userspace has instructed us otherwise. */ if (vcpu_has_feature(vcpu, KVM_ARM_VCPU_PSCI_0_2)) { if (vcpu->kvm->arch.psci_version) return vcpu->kvm->arch.psci_version; return KVM_ARM_PSCI_LATEST; } return KVM_ARM_PSCI_0_1; } int kvm_psci_call(struct kvm_vcpu *vcpu); #endif /* __KVM_ARM_PSCI_H__ */ |
| 612 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 | // SPDX-License-Identifier: GPL-2.0 #include <linux/err.h> #include <linux/bug.h> #include <linux/atomic.h> #include <linux/errseq.h> #include <linux/log2.h> /* * An errseq_t is a way of recording errors in one place, and allowing any * number of "subscribers" to tell whether it has changed since a previous * point where it was sampled. * * It's implemented as an unsigned 32-bit value. The low order bits are * designated to hold an error code (between 0 and -MAX_ERRNO). The upper bits * are used as a counter. This is done with atomics instead of locking so that * these functions can be called from any context. * * The general idea is for consumers to sample an errseq_t value. That value * can later be used to tell whether any new errors have occurred since that * sampling was done. * * Note that there is a risk of collisions if new errors are being recorded * frequently, since we have so few bits to use as a counter. * * To mitigate this, one bit is used as a flag to tell whether the value has * been sampled since a new value was recorded. That allows us to avoid bumping * the counter if no one has sampled it since the last time an error was * recorded. * * A new errseq_t should always be zeroed out. A errseq_t value of all zeroes * is the special (but common) case where there has never been an error. An all * zero value thus serves as the "epoch" if one wishes to know whether there * has ever been an error set since it was first initialized. */ /* The low bits are designated for error code (max of MAX_ERRNO) */ #define ERRSEQ_SHIFT ilog2(MAX_ERRNO + 1) /* This bit is used as a flag to indicate whether the value has been seen */ #define ERRSEQ_SEEN (1 << ERRSEQ_SHIFT) /* The lowest bit of the counter */ #define ERRSEQ_CTR_INC (1 << (ERRSEQ_SHIFT + 1)) /** * errseq_set - set a errseq_t for later reporting * @eseq: errseq_t field that should be set * @err: error to set (must be between -1 and -MAX_ERRNO) * * This function sets the error in @eseq, and increments the sequence counter * if the last sequence was sampled at some point in the past. * * Any error set will always overwrite an existing error. * * Return: The previous value, primarily for debugging purposes. The * return value should not be used as a previously sampled value in later * calls as it will not have the SEEN flag set. */ errseq_t errseq_set(errseq_t *eseq, int err) { errseq_t cur, old; /* MAX_ERRNO must be able to serve as a mask */ BUILD_BUG_ON_NOT_POWER_OF_2(MAX_ERRNO + 1); /* * Ensure the error code actually fits where we want it to go. If it * doesn't then just throw a warning and don't record anything. We * also don't accept zero here as that would effectively clear a * previous error. */ old = READ_ONCE(*eseq); if (WARN(unlikely(err == 0 || (unsigned int)-err > MAX_ERRNO), "err = %d\n", err)) return old; for (;;) { errseq_t new; /* Clear out error bits and set new error */ new = (old & ~(MAX_ERRNO|ERRSEQ_SEEN)) | -err; /* Only increment if someone has looked at it */ if (old & ERRSEQ_SEEN) new += ERRSEQ_CTR_INC; /* If there would be no change, then call it done */ if (new == old) { cur = new; break; } /* Try to swap the new value into place */ cur = cmpxchg(eseq, old, new); /* * Call it success if we did the swap or someone else beat us * to it for the same value. */ if (likely(cur == old || cur == new)) break; /* Raced with an update, try again */ old = cur; } return cur; } EXPORT_SYMBOL(errseq_set); /** * errseq_sample() - Grab current errseq_t value. * @eseq: Pointer to errseq_t to be sampled. * * This function allows callers to initialise their errseq_t variable. * If the error has been "seen", new callers will not see an old error. * If there is an unseen error in @eseq, the caller of this function will * see it the next time it checks for an error. * * Context: Any context. * Return: The current errseq value. */ errseq_t errseq_sample(errseq_t *eseq) { errseq_t old = READ_ONCE(*eseq); /* If nobody has seen this error yet, then we can be the first. */ if (!(old & ERRSEQ_SEEN)) old = 0; return old; } EXPORT_SYMBOL(errseq_sample); /** * errseq_check() - Has an error occurred since a particular sample point? * @eseq: Pointer to errseq_t value to be checked. * @since: Previously-sampled errseq_t from which to check. * * Grab the value that eseq points to, and see if it has changed @since * the given value was sampled. The @since value is not advanced, so there * is no need to mark the value as seen. * * Return: The latest error set in the errseq_t or 0 if it hasn't changed. */ int errseq_check(errseq_t *eseq, errseq_t since) { errseq_t cur = READ_ONCE(*eseq); if (likely(cur == since)) return 0; return -(cur & MAX_ERRNO); } EXPORT_SYMBOL(errseq_check); /** * errseq_check_and_advance() - Check an errseq_t and advance to current value. * @eseq: Pointer to value being checked and reported. * @since: Pointer to previously-sampled errseq_t to check against and advance. * * Grab the eseq value, and see whether it matches the value that @since * points to. If it does, then just return 0. * * If it doesn't, then the value has changed. Set the "seen" flag, and try to * swap it into place as the new eseq value. Then, set that value as the new * "since" value, and return whatever the error portion is set to. * * Note that no locking is provided here for concurrent updates to the "since" * value. The caller must provide that if necessary. Because of this, callers * may want to do a lockless errseq_check before taking the lock and calling * this. * * Return: Negative errno if one has been stored, or 0 if no new error has * occurred. */ int errseq_check_and_advance(errseq_t *eseq, errseq_t *since) { int err = 0; errseq_t old, new; /* * Most callers will want to use the inline wrapper to check this, * so that the common case of no error is handled without needing * to take the lock that protects the "since" value. */ old = READ_ONCE(*eseq); if (old != *since) { /* * Set the flag and try to swap it into place if it has * changed. * * We don't care about the outcome of the swap here. If the * swap doesn't occur, then it has either been updated by a * writer who is altering the value in some way (updating * counter or resetting the error), or another reader who is * just setting the "seen" flag. Either outcome is OK, and we * can advance "since" and return an error based on what we * have. */ new = old | ERRSEQ_SEEN; if (new != old) cmpxchg(eseq, old, new); *since = new; err = -(new & MAX_ERRNO); } return err; } EXPORT_SYMBOL(errseq_check_and_advance); |
| 234 234 234 2 2 1 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 | // SPDX-License-Identifier: GPL-2.0-only #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt #include <linux/workqueue.h> #include <linux/rtnetlink.h> #include <linux/cache.h> #include <linux/slab.h> #include <linux/list.h> #include <linux/delay.h> #include <linux/sched.h> #include <linux/idr.h> #include <linux/rculist.h> #include <linux/nsproxy.h> #include <linux/fs.h> #include <linux/proc_ns.h> #include <linux/file.h> #include <linux/export.h> #include <linux/user_namespace.h> #include <linux/net_namespace.h> #include <linux/sched/task.h> #include <linux/uidgid.h> #include <linux/cookie.h> #include <linux/proc_fs.h> #include <net/sock.h> #include <net/netlink.h> #include <net/net_namespace.h> #include <net/netns/generic.h> /* * Our network namespace constructor/destructor lists */ static LIST_HEAD(pernet_list); static struct list_head *first_device = &pernet_list; LIST_HEAD(net_namespace_list); EXPORT_SYMBOL_GPL(net_namespace_list); /* Protects net_namespace_list. Nests iside rtnl_lock() */ DECLARE_RWSEM(net_rwsem); EXPORT_SYMBOL_GPL(net_rwsem); #ifdef CONFIG_KEYS static struct key_tag init_net_key_domain = { .usage = REFCOUNT_INIT(1) }; #endif struct net init_net; EXPORT_SYMBOL(init_net); static bool init_net_initialized; /* * pernet_ops_rwsem: protects: pernet_list, net_generic_ids, * init_net_initialized and first_device pointer. * This is internal net namespace object. Please, don't use it * outside. */ DECLARE_RWSEM(pernet_ops_rwsem); #define MIN_PERNET_OPS_ID \ ((sizeof(struct net_generic) + sizeof(void *) - 1) / sizeof(void *)) #define INITIAL_NET_GEN_PTRS 13 /* +1 for len +2 for rcu_head */ static unsigned int max_gen_ptrs = INITIAL_NET_GEN_PTRS; DEFINE_COOKIE(net_cookie); static struct net_generic *net_alloc_generic(void) { unsigned int gen_ptrs = READ_ONCE(max_gen_ptrs); unsigned int generic_size; struct net_generic *ng; generic_size = offsetof(struct net_generic, ptr[gen_ptrs]); ng = kzalloc(generic_size, GFP_KERNEL); if (ng) ng->s.len = gen_ptrs; return ng; } static int net_assign_generic(struct net *net, unsigned int id, void *data) { struct net_generic *ng, *old_ng; BUG_ON(id < MIN_PERNET_OPS_ID); old_ng = rcu_dereference_protected(net->gen, lockdep_is_held(&pernet_ops_rwsem)); if (old_ng->s.len > id) { old_ng->ptr[id] = data; return 0; } ng = net_alloc_generic(); if (!ng) return -ENOMEM; /* * Some synchronisation notes: * * The net_generic explores the net->gen array inside rcu * read section. Besides once set the net->gen->ptr[x] * pointer never changes (see rules in netns/generic.h). * * That said, we simply duplicate this array and schedule * the old copy for kfree after a grace period. */ memcpy(&ng->ptr[MIN_PERNET_OPS_ID], &old_ng->ptr[MIN_PERNET_OPS_ID], (old_ng->s.len - MIN_PERNET_OPS_ID) * sizeof(void *)); ng->ptr[id] = data; rcu_assign_pointer(net->gen, ng); kfree_rcu(old_ng, s.rcu); return 0; } static int ops_init(const struct pernet_operations *ops, struct net *net) { struct net_generic *ng; int err = -ENOMEM; void *data = NULL; if (ops->id) { data = kzalloc(ops->size, GFP_KERNEL); if (!data) goto out; err = net_assign_generic(net, *ops->id, data); if (err) goto cleanup; } err = 0; if (ops->init) err = ops->init(net); if (!err) return 0; if (ops->id) { ng = rcu_dereference_protected(net->gen, lockdep_is_held(&pernet_ops_rwsem)); ng->ptr[*ops->id] = NULL; } cleanup: kfree(data); out: return err; } static void ops_pre_exit_list(const struct pernet_operations *ops, struct list_head *net_exit_list) { struct net *net; if (ops->pre_exit) { list_for_each_entry(net, net_exit_list, exit_list) ops->pre_exit(net); } } static void ops_exit_list(const struct pernet_operations *ops, struct list_head *net_exit_list) { struct net *net; if (ops->exit) { list_for_each_entry(net, net_exit_list, exit_list) { ops->exit(net); cond_resched(); } } if (ops->exit_batch) ops->exit_batch(net_exit_list); } static void ops_free_list(const struct pernet_operations *ops, struct list_head *net_exit_list) { struct net *net; if (ops->id) { list_for_each_entry(net, net_exit_list, exit_list) kfree(net_generic(net, *ops->id)); } } /* should be called with nsid_lock held */ static int alloc_netid(struct net *net, struct net *peer, int reqid) { int min = 0, max = 0; if (reqid >= 0) { min = reqid; max = reqid + 1; } return idr_alloc(&net->netns_ids, peer, min, max, GFP_ATOMIC); } /* This function is used by idr_for_each(). If net is equal to peer, the * function returns the id so that idr_for_each() stops. Because we cannot * returns the id 0 (idr_for_each() will not stop), we return the magic value * NET_ID_ZERO (-1) for it. */ #define NET_ID_ZERO -1 static int net_eq_idr(int id, void *net, void *peer) { if (net_eq(net, peer)) return id ? : NET_ID_ZERO; return 0; } /* Must be called from RCU-critical section or with nsid_lock held */ static int __peernet2id(const struct net *net, struct net *peer) { int id = idr_for_each(&net->netns_ids, net_eq_idr, peer); /* Magic value for id 0. */ if (id == NET_ID_ZERO) return 0; if (id > 0) return id; return NETNSA_NSID_NOT_ASSIGNED; } static void rtnl_net_notifyid(struct net *net, int cmd, int id, u32 portid, struct nlmsghdr *nlh, gfp_t gfp); /* This function returns the id of a peer netns. If no id is assigned, one will * be allocated and returned. */ int peernet2id_alloc(struct net *net, struct net *peer, gfp_t gfp) { int id; if (refcount_read(&net->ns.count) == 0) return NETNSA_NSID_NOT_ASSIGNED; spin_lock_bh(&net->nsid_lock); id = __peernet2id(net, peer); if (id >= 0) { spin_unlock_bh(&net->nsid_lock); return id; } /* When peer is obtained from RCU lists, we may race with * its cleanup. Check whether it's alive, and this guarantees * we never hash a peer back to net->netns_ids, after it has * just been idr_remove()'d from there in cleanup_net(). */ if (!maybe_get_net(peer)) { spin_unlock_bh(&net->nsid_lock); return NETNSA_NSID_NOT_ASSIGNED; } id = alloc_netid(net, peer, -1); spin_unlock_bh(&net->nsid_lock); put_net(peer); if (id < 0) return NETNSA_NSID_NOT_ASSIGNED; rtnl_net_notifyid(net, RTM_NEWNSID, id, 0, NULL, gfp); return id; } EXPORT_SYMBOL_GPL(peernet2id_alloc); /* This function returns, if assigned, the id of a peer netns. */ int peernet2id(const struct net *net, struct net *peer) { int id; rcu_read_lock(); id = __peernet2id(net, peer); rcu_read_unlock(); return id; } EXPORT_SYMBOL(peernet2id); /* This function returns true is the peer netns has an id assigned into the * current netns. */ bool peernet_has_id(const struct net *net, struct net *peer) { return peernet2id(net, peer) >= 0; } struct net *get_net_ns_by_id(const struct net *net, int id) { struct net *peer; if (id < 0) return NULL; rcu_read_lock(); peer = idr_find(&net->netns_ids, id); if (peer) peer = maybe_get_net(peer); rcu_read_unlock(); return peer; } EXPORT_SYMBOL_GPL(get_net_ns_by_id); static __net_init void preinit_net_sysctl(struct net *net) { net->core.sysctl_somaxconn = SOMAXCONN; /* Limits per socket sk_omem_alloc usage. * TCP zerocopy regular usage needs 128 KB. */ net->core.sysctl_optmem_max = 128 * 1024; net->core.sysctl_txrehash = SOCK_TXREHASH_ENABLED; net->core.sysctl_tstamp_allow_data = 1; } /* init code that must occur even if setup_net() is not called. */ static __net_init void preinit_net(struct net *net, struct user_namespace *user_ns) { refcount_set(&net->passive, 1); refcount_set(&net->ns.count, 1); ref_tracker_dir_init(&net->refcnt_tracker, 128, "net refcnt"); ref_tracker_dir_init(&net->notrefcnt_tracker, 128, "net notrefcnt"); get_random_bytes(&net->hash_mix, sizeof(u32)); net->dev_base_seq = 1; net->user_ns = user_ns; idr_init(&net->netns_ids); spin_lock_init(&net->nsid_lock); mutex_init(&net->ipv4.ra_mutex); #ifdef CONFIG_DEBUG_NET_SMALL_RTNL mutex_init(&net->rtnl_mutex); lock_set_cmp_fn(&net->rtnl_mutex, rtnl_net_lock_cmp_fn, NULL); #endif preinit_net_sysctl(net); } /* * setup_net runs the initializers for the network namespace object. */ static __net_init int setup_net(struct net *net) { /* Must be called with pernet_ops_rwsem held */ const struct pernet_operations *ops, *saved_ops; LIST_HEAD(net_exit_list); LIST_HEAD(dev_kill_list); int error = 0; preempt_disable(); net->net_cookie = gen_cookie_next(&net_cookie); preempt_enable(); list_for_each_entry(ops, &pernet_list, list) { error = ops_init(ops, net); if (error < 0) goto out_undo; } down_write(&net_rwsem); list_add_tail_rcu(&net->list, &net_namespace_list); up_write(&net_rwsem); out: return error; out_undo: /* Walk through the list backwards calling the exit functions * for the pernet modules whose init functions did not fail. */ list_add(&net->exit_list, &net_exit_list); saved_ops = ops; list_for_each_entry_continue_reverse(ops, &pernet_list, list) ops_pre_exit_list(ops, &net_exit_list); synchronize_rcu(); ops = saved_ops; rtnl_lock(); list_for_each_entry_continue_reverse(ops, &pernet_list, list) { if (ops->exit_batch_rtnl) ops->exit_batch_rtnl(&net_exit_list, &dev_kill_list); } unregister_netdevice_many(&dev_kill_list); rtnl_unlock(); ops = saved_ops; list_for_each_entry_continue_reverse(ops, &pernet_list, list) ops_exit_list(ops, &net_exit_list); ops = saved_ops; list_for_each_entry_continue_reverse(ops, &pernet_list, list) ops_free_list(ops, &net_exit_list); rcu_barrier(); goto out; } #ifdef CONFIG_NET_NS static struct ucounts *inc_net_namespaces(struct user_namespace *ns) { return inc_ucount(ns, current_euid(), UCOUNT_NET_NAMESPACES); } static void dec_net_namespaces(struct ucounts *ucounts) { dec_ucount(ucounts, UCOUNT_NET_NAMESPACES); } static struct kmem_cache *net_cachep __ro_after_init; static struct workqueue_struct *netns_wq; static struct net *net_alloc(void) { struct net *net = NULL; struct net_generic *ng; ng = net_alloc_generic(); if (!ng) goto out; net = kmem_cache_zalloc(net_cachep, GFP_KERNEL); if (!net) goto out_free; #ifdef CONFIG_KEYS net->key_domain = kzalloc(sizeof(struct key_tag), GFP_KERNEL); if (!net->key_domain) goto out_free_2; refcount_set(&net->key_domain->usage, 1); #endif rcu_assign_pointer(net->gen, ng); out: return net; #ifdef CONFIG_KEYS out_free_2: kmem_cache_free(net_cachep, net); net = NULL; #endif out_free: kfree(ng); goto out; } static LLIST_HEAD(defer_free_list); static void net_complete_free(void) { struct llist_node *kill_list; struct net *net, *next; /* Get the list of namespaces to free from last round. */ kill_list = llist_del_all(&defer_free_list); llist_for_each_entry_safe(net, next, kill_list, defer_free_list) kmem_cache_free(net_cachep, net); } static void net_free(struct net *net) { if (refcount_dec_and_test(&net->passive)) { kfree(rcu_access_pointer(net->gen)); /* There should not be any trackers left there. */ ref_tracker_dir_exit(&net->notrefcnt_tracker); /* Wait for an extra rcu_barrier() before final free. */ llist_add(&net->defer_free_list, &defer_free_list); } } void net_drop_ns(void *p) { struct net *net = (struct net *)p; if (net) net_free(net); } struct net *copy_net_ns(unsigned long flags, struct user_namespace *user_ns, struct net *old_net) { struct ucounts *ucounts; struct net *net; int rv; if (!(flags & CLONE_NEWNET)) return get_net(old_net); ucounts = inc_net_namespaces(user_ns); if (!ucounts) return ERR_PTR(-ENOSPC); net = net_alloc(); if (!net) { rv = -ENOMEM; goto dec_ucounts; } preinit_net(net, user_ns); net->ucounts = ucounts; get_user_ns(user_ns); rv = down_read_killable(&pernet_ops_rwsem); if (rv < 0) goto put_userns; rv = setup_net(net); up_read(&pernet_ops_rwsem); if (rv < 0) { put_userns: #ifdef CONFIG_KEYS key_remove_domain(net->key_domain); #endif put_user_ns(user_ns); net_free(net); dec_ucounts: dec_net_namespaces(ucounts); return ERR_PTR(rv); } return net; } /** * net_ns_get_ownership - get sysfs ownership data for @net * @net: network namespace in question (can be NULL) * @uid: kernel user ID for sysfs objects * @gid: kernel group ID for sysfs objects * * Returns the uid/gid pair of root in the user namespace associated with the * given network namespace. */ void net_ns_get_ownership(const struct net *net, kuid_t *uid, kgid_t *gid) { if (net) { kuid_t ns_root_uid = make_kuid(net->user_ns, 0); kgid_t ns_root_gid = make_kgid(net->user_ns, 0); if (uid_valid(ns_root_uid)) *uid = ns_root_uid; if (gid_valid(ns_root_gid)) *gid = ns_root_gid; } else { *uid = GLOBAL_ROOT_UID; *gid = GLOBAL_ROOT_GID; } } EXPORT_SYMBOL_GPL(net_ns_get_ownership); static void unhash_nsid(struct net *net, struct net *last) { struct net *tmp; /* This function is only called from cleanup_net() work, * and this work is the only process, that may delete * a net from net_namespace_list. So, when the below * is executing, the list may only grow. Thus, we do not * use for_each_net_rcu() or net_rwsem. */ for_each_net(tmp) { int id; spin_lock_bh(&tmp->nsid_lock); id = __peernet2id(tmp, net); if (id >= 0) idr_remove(&tmp->netns_ids, id); spin_unlock_bh(&tmp->nsid_lock); if (id >= 0) rtnl_net_notifyid(tmp, RTM_DELNSID, id, 0, NULL, GFP_KERNEL); if (tmp == last) break; } spin_lock_bh(&net->nsid_lock); idr_destroy(&net->netns_ids); spin_unlock_bh(&net->nsid_lock); } static LLIST_HEAD(cleanup_list); static void cleanup_net(struct work_struct *work) { const struct pernet_operations *ops; struct net *net, *tmp, *last; struct llist_node *net_kill_list; LIST_HEAD(net_exit_list); LIST_HEAD(dev_kill_list); /* Atomically snapshot the list of namespaces to cleanup */ net_kill_list = llist_del_all(&cleanup_list); down_read(&pernet_ops_rwsem); /* Don't let anyone else find us. */ down_write(&net_rwsem); llist_for_each_entry(net, net_kill_list, cleanup_list) list_del_rcu(&net->list); /* Cache last net. After we unlock rtnl, no one new net * added to net_namespace_list can assign nsid pointer * to a net from net_kill_list (see peernet2id_alloc()). * So, we skip them in unhash_nsid(). * * Note, that unhash_nsid() does not delete nsid links * between net_kill_list's nets, as they've already * deleted from net_namespace_list. But, this would be * useless anyway, as netns_ids are destroyed there. */ last = list_last_entry(&net_namespace_list, struct net, list); up_write(&net_rwsem); llist_for_each_entry(net, net_kill_list, cleanup_list) { unhash_nsid(net, last); list_add_tail(&net->exit_list, &net_exit_list); } /* Run all of the network namespace pre_exit methods */ list_for_each_entry_reverse(ops, &pernet_list, list) ops_pre_exit_list(ops, &net_exit_list); /* * Another CPU might be rcu-iterating the list, wait for it. * This needs to be before calling the exit() notifiers, so * the rcu_barrier() below isn't sufficient alone. * Also the pre_exit() and exit() methods need this barrier. */ synchronize_rcu_expedited(); rtnl_lock(); list_for_each_entry_reverse(ops, &pernet_list, list) { if (ops->exit_batch_rtnl) ops->exit_batch_rtnl(&net_exit_list, &dev_kill_list); } unregister_netdevice_many(&dev_kill_list); rtnl_unlock(); /* Run all of the network namespace exit methods */ list_for_each_entry_reverse(ops, &pernet_list, list) ops_exit_list(ops, &net_exit_list); /* Free the net generic variables */ list_for_each_entry_reverse(ops, &pernet_list, list) ops_free_list(ops, &net_exit_list); up_read(&pernet_ops_rwsem); /* Ensure there are no outstanding rcu callbacks using this * network namespace. */ rcu_barrier(); net_complete_free(); /* Finally it is safe to free my network namespace structure */ list_for_each_entry_safe(net, tmp, &net_exit_list, exit_list) { list_del_init(&net->exit_list); dec_net_namespaces(net->ucounts); #ifdef CONFIG_KEYS key_remove_domain(net->key_domain); #endif put_user_ns(net->user_ns); net_free(net); } } /** * net_ns_barrier - wait until concurrent net_cleanup_work is done * * cleanup_net runs from work queue and will first remove namespaces * from the global list, then run net exit functions. * * Call this in module exit path to make sure that all netns * ->exit ops have been invoked before the function is removed. */ void net_ns_barrier(void) { down_write(&pernet_ops_rwsem); up_write(&pernet_ops_rwsem); } EXPORT_SYMBOL(net_ns_barrier); static DECLARE_WORK(net_cleanup_work, cleanup_net); void __put_net(struct net *net) { ref_tracker_dir_exit(&net->refcnt_tracker); /* Cleanup the network namespace in process context */ if (llist_add(&net->cleanup_list, &cleanup_list)) queue_work(netns_wq, &net_cleanup_work); } EXPORT_SYMBOL_GPL(__put_net); /** * get_net_ns - increment the refcount of the network namespace * @ns: common namespace (net) * * Returns the net's common namespace or ERR_PTR() if ref is zero. */ struct ns_common *get_net_ns(struct ns_common *ns) { struct net *net; net = maybe_get_net(container_of(ns, struct net, ns)); if (net) return &net->ns; return ERR_PTR(-EINVAL); } EXPORT_SYMBOL_GPL(get_net_ns); struct net *get_net_ns_by_fd(int fd) { CLASS(fd, f)(fd); if (fd_empty(f)) return ERR_PTR(-EBADF); if (proc_ns_file(fd_file(f))) { struct ns_common *ns = get_proc_ns(file_inode(fd_file(f))); if (ns->ops == &netns_operations) return get_net(container_of(ns, struct net, ns)); } return ERR_PTR(-EINVAL); } EXPORT_SYMBOL_GPL(get_net_ns_by_fd); #endif struct net *get_net_ns_by_pid(pid_t pid) { struct task_struct *tsk; struct net *net; /* Lookup the network namespace */ net = ERR_PTR(-ESRCH); rcu_read_lock(); tsk = find_task_by_vpid(pid); if (tsk) { struct nsproxy *nsproxy; task_lock(tsk); nsproxy = tsk->nsproxy; if (nsproxy) net = get_net(nsproxy->net_ns); task_unlock(tsk); } rcu_read_unlock(); return net; } EXPORT_SYMBOL_GPL(get_net_ns_by_pid); static __net_init int net_ns_net_init(struct net *net) { #ifdef CONFIG_NET_NS net->ns.ops = &netns_operations; #endif return ns_alloc_inum(&net->ns); } static __net_exit void net_ns_net_exit(struct net *net) { ns_free_inum(&net->ns); } static struct pernet_operations __net_initdata net_ns_ops = { .init = net_ns_net_init, .exit = net_ns_net_exit, }; static const struct nla_policy rtnl_net_policy[NETNSA_MAX + 1] = { [NETNSA_NONE] = { .type = NLA_UNSPEC }, [NETNSA_NSID] = { .type = NLA_S32 }, [NETNSA_PID] = { .type = NLA_U32 }, [NETNSA_FD] = { .type = NLA_U32 }, [NETNSA_TARGET_NSID] = { .type = NLA_S32 }, }; static int rtnl_net_newid(struct sk_buff *skb, struct nlmsghdr *nlh, struct netlink_ext_ack *extack) { struct net *net = sock_net(skb->sk); struct nlattr *tb[NETNSA_MAX + 1]; struct nlattr *nla; struct net *peer; int nsid, err; err = nlmsg_parse_deprecated(nlh, sizeof(struct rtgenmsg), tb, NETNSA_MAX, rtnl_net_policy, extack); if (err < 0) return err; if (!tb[NETNSA_NSID]) { NL_SET_ERR_MSG(extack, "nsid is missing"); return -EINVAL; } nsid = nla_get_s32(tb[NETNSA_NSID]); if (tb[NETNSA_PID]) { peer = get_net_ns_by_pid(nla_get_u32(tb[NETNSA_PID])); nla = tb[NETNSA_PID]; } else if (tb[NETNSA_FD]) { peer = get_net_ns_by_fd(nla_get_u32(tb[NETNSA_FD])); nla = tb[NETNSA_FD]; } else { NL_SET_ERR_MSG(extack, "Peer netns reference is missing"); return -EINVAL; } if (IS_ERR(peer)) { NL_SET_BAD_ATTR(extack, nla); NL_SET_ERR_MSG(extack, "Peer netns reference is invalid"); return PTR_ERR(peer); } spin_lock_bh(&net->nsid_lock); if (__peernet2id(net, peer) >= 0) { spin_unlock_bh(&net->nsid_lock); err = -EEXIST; NL_SET_BAD_ATTR(extack, nla); NL_SET_ERR_MSG(extack, "Peer netns already has a nsid assigned"); goto out; } err = alloc_netid(net, peer, nsid); spin_unlock_bh(&net->nsid_lock); if (err >= 0) { rtnl_net_notifyid(net, RTM_NEWNSID, err, NETLINK_CB(skb).portid, nlh, GFP_KERNEL); err = 0; } else if (err == -ENOSPC && nsid >= 0) { err = -EEXIST; NL_SET_BAD_ATTR(extack, tb[NETNSA_NSID]); NL_SET_ERR_MSG(extack, "The specified nsid is already used"); } out: put_net(peer); return err; } static int rtnl_net_get_size(void) { return NLMSG_ALIGN(sizeof(struct rtgenmsg)) + nla_total_size(sizeof(s32)) /* NETNSA_NSID */ + nla_total_size(sizeof(s32)) /* NETNSA_CURRENT_NSID */ ; } struct net_fill_args { u32 portid; u32 seq; int flags; int cmd; int nsid; bool add_ref; int ref_nsid; }; static int rtnl_net_fill(struct sk_buff *skb, struct net_fill_args *args) { struct nlmsghdr *nlh; struct rtgenmsg *rth; nlh = nlmsg_put(skb, args->portid, args->seq, args->cmd, sizeof(*rth), args->flags); if (!nlh) return -EMSGSIZE; rth = nlmsg_data(nlh); rth->rtgen_family = AF_UNSPEC; if (nla_put_s32(skb, NETNSA_NSID, args->nsid)) goto nla_put_failure; if (args->add_ref && nla_put_s32(skb, NETNSA_CURRENT_NSID, args->ref_nsid)) goto nla_put_failure; nlmsg_end(skb, nlh); return 0; nla_put_failure: nlmsg_cancel(skb, nlh); return -EMSGSIZE; } static int rtnl_net_valid_getid_req(struct sk_buff *skb, const struct nlmsghdr *nlh, struct nlattr **tb, struct netlink_ext_ack *extack) { int i, err; if (!netlink_strict_get_check(skb)) return nlmsg_parse_deprecated(nlh, sizeof(struct rtgenmsg), tb, NETNSA_MAX, rtnl_net_policy, extack); err = nlmsg_parse_deprecated_strict(nlh, sizeof(struct rtgenmsg), tb, NETNSA_MAX, rtnl_net_policy, extack); if (err) return err; for (i = 0; i <= NETNSA_MAX; i++) { if (!tb[i]) continue; switch (i) { case NETNSA_PID: case NETNSA_FD: case NETNSA_NSID: case NETNSA_TARGET_NSID: break; default: NL_SET_ERR_MSG(extack, "Unsupported attribute in peer netns getid request"); return -EINVAL; } } return 0; } static int rtnl_net_getid(struct sk_buff *skb, struct nlmsghdr *nlh, struct netlink_ext_ack *extack) { struct net *net = sock_net(skb->sk); struct nlattr *tb[NETNSA_MAX + 1]; struct net_fill_args fillargs = { .portid = NETLINK_CB(skb).portid, .seq = nlh->nlmsg_seq, .cmd = RTM_NEWNSID, }; struct net *peer, *target = net; struct nlattr *nla; struct sk_buff *msg; int err; err = rtnl_net_valid_getid_req(skb, nlh, tb, extack); if (err < 0) return err; if (tb[NETNSA_PID]) { peer = get_net_ns_by_pid(nla_get_u32(tb[NETNSA_PID])); nla = tb[NETNSA_PID]; } else if (tb[NETNSA_FD]) { peer = get_net_ns_by_fd(nla_get_u32(tb[NETNSA_FD])); nla = tb[NETNSA_FD]; } else if (tb[NETNSA_NSID]) { peer = get_net_ns_by_id(net, nla_get_s32(tb[NETNSA_NSID])); if (!peer) peer = ERR_PTR(-ENOENT); nla = tb[NETNSA_NSID]; } else { NL_SET_ERR_MSG(extack, "Peer netns reference is missing"); return -EINVAL; } if (IS_ERR(peer)) { NL_SET_BAD_ATTR(extack, nla); NL_SET_ERR_MSG(extack, "Peer netns reference is invalid"); return PTR_ERR(peer); } if (tb[NETNSA_TARGET_NSID]) { int id = nla_get_s32(tb[NETNSA_TARGET_NSID]); target = rtnl_get_net_ns_capable(NETLINK_CB(skb).sk, id); if (IS_ERR(target)) { NL_SET_BAD_ATTR(extack, tb[NETNSA_TARGET_NSID]); NL_SET_ERR_MSG(extack, "Target netns reference is invalid"); err = PTR_ERR(target); goto out; } fillargs.add_ref = true; fillargs.ref_nsid = peernet2id(net, peer); } msg = nlmsg_new(rtnl_net_get_size(), GFP_KERNEL); if (!msg) { err = -ENOMEM; goto out; } fillargs.nsid = peernet2id(target, peer); err = rtnl_net_fill(msg, &fillargs); if (err < 0) goto err_out; err = rtnl_unicast(msg, net, NETLINK_CB(skb).portid); goto out; err_out: nlmsg_free(msg); out: if (fillargs.add_ref) put_net(target); put_net(peer); return err; } struct rtnl_net_dump_cb { struct net *tgt_net; struct net *ref_net; struct sk_buff *skb; struct net_fill_args fillargs; int idx; int s_idx; }; /* Runs in RCU-critical section. */ static int rtnl_net_dumpid_one(int id, void *peer, void *data) { struct rtnl_net_dump_cb *net_cb = (struct rtnl_net_dump_cb *)data; int ret; if (net_cb->idx < net_cb->s_idx) goto cont; net_cb->fillargs.nsid = id; if (net_cb->fillargs.add_ref) net_cb->fillargs.ref_nsid = __peernet2id(net_cb->ref_net, peer); ret = rtnl_net_fill(net_cb->skb, &net_cb->fillargs); if (ret < 0) return ret; cont: net_cb->idx++; return 0; } static int rtnl_valid_dump_net_req(const struct nlmsghdr *nlh, struct sock *sk, struct rtnl_net_dump_cb *net_cb, struct netlink_callback *cb) { struct netlink_ext_ack *extack = cb->extack; struct nlattr *tb[NETNSA_MAX + 1]; int err, i; err = nlmsg_parse_deprecated_strict(nlh, sizeof(struct rtgenmsg), tb, NETNSA_MAX, rtnl_net_policy, extack); if (err < 0) return err; for (i = 0; i <= NETNSA_MAX; i++) { if (!tb[i]) continue; if (i == NETNSA_TARGET_NSID) { struct net *net; net = rtnl_get_net_ns_capable(sk, nla_get_s32(tb[i])); if (IS_ERR(net)) { NL_SET_BAD_ATTR(extack, tb[i]); NL_SET_ERR_MSG(extack, "Invalid target network namespace id"); return PTR_ERR(net); } net_cb->fillargs.add_ref = true; net_cb->ref_net = net_cb->tgt_net; net_cb->tgt_net = net; } else { NL_SET_BAD_ATTR(extack, tb[i]); NL_SET_ERR_MSG(extack, "Unsupported attribute in dump request"); return -EINVAL; } } return 0; } static int rtnl_net_dumpid(struct sk_buff *skb, struct netlink_callback *cb) { struct rtnl_net_dump_cb net_cb = { .tgt_net = sock_net(skb->sk), .skb = skb, .fillargs = { .portid = NETLINK_CB(cb->skb).portid, .seq = cb->nlh->nlmsg_seq, .flags = NLM_F_MULTI, .cmd = RTM_NEWNSID, }, .idx = 0, .s_idx = cb->args[0], }; int err = 0; if (cb->strict_check) { err = rtnl_valid_dump_net_req(cb->nlh, skb->sk, &net_cb, cb); if (err < 0) goto end; } rcu_read_lock(); idr_for_each(&net_cb.tgt_net->netns_ids, rtnl_net_dumpid_one, &net_cb); rcu_read_unlock(); cb->args[0] = net_cb.idx; end: if (net_cb.fillargs.add_ref) put_net(net_cb.tgt_net); return err; } static void rtnl_net_notifyid(struct net *net, int cmd, int id, u32 portid, struct nlmsghdr *nlh, gfp_t gfp) { struct net_fill_args fillargs = { .portid = portid, .seq = nlh ? nlh->nlmsg_seq : 0, .cmd = cmd, .nsid = id, }; struct sk_buff *msg; int err = -ENOMEM; msg = nlmsg_new(rtnl_net_get_size(), gfp); if (!msg) goto out; err = rtnl_net_fill(msg, &fillargs); if (err < 0) goto err_out; rtnl_notify(msg, net, portid, RTNLGRP_NSID, nlh, gfp); return; err_out: nlmsg_free(msg); out: rtnl_set_sk_err(net, RTNLGRP_NSID, err); } #ifdef CONFIG_NET_NS static void __init netns_ipv4_struct_check(void) { /* TX readonly hotpath cache lines */ CACHELINE_ASSERT_GROUP_MEMBER(struct netns_ipv4, netns_ipv4_read_tx, sysctl_tcp_early_retrans); CACHELINE_ASSERT_GROUP_MEMBER(struct netns_ipv4, netns_ipv4_read_tx, sysctl_tcp_tso_win_divisor); CACHELINE_ASSERT_GROUP_MEMBER(struct netns_ipv4, netns_ipv4_read_tx, sysctl_tcp_tso_rtt_log); CACHELINE_ASSERT_GROUP_MEMBER(struct netns_ipv4, netns_ipv4_read_tx, sysctl_tcp_autocorking); CACHELINE_ASSERT_GROUP_MEMBER(struct netns_ipv4, netns_ipv4_read_tx, sysctl_tcp_min_snd_mss); CACHELINE_ASSERT_GROUP_MEMBER(struct netns_ipv4, netns_ipv4_read_tx, sysctl_tcp_notsent_lowat); CACHELINE_ASSERT_GROUP_MEMBER(struct netns_ipv4, netns_ipv4_read_tx, sysctl_tcp_limit_output_bytes); CACHELINE_ASSERT_GROUP_MEMBER(struct netns_ipv4, netns_ipv4_read_tx, sysctl_tcp_min_rtt_wlen); CACHELINE_ASSERT_GROUP_MEMBER(struct netns_ipv4, netns_ipv4_read_tx, sysctl_tcp_wmem); CACHELINE_ASSERT_GROUP_MEMBER(struct netns_ipv4, netns_ipv4_read_tx, sysctl_ip_fwd_use_pmtu); CACHELINE_ASSERT_GROUP_SIZE(struct netns_ipv4, netns_ipv4_read_tx, 33); /* TXRX readonly hotpath cache lines */ CACHELINE_ASSERT_GROUP_MEMBER(struct netns_ipv4, netns_ipv4_read_txrx, sysctl_tcp_moderate_rcvbuf); CACHELINE_ASSERT_GROUP_SIZE(struct netns_ipv4, netns_ipv4_read_txrx, 1); /* RX readonly hotpath cache line */ CACHELINE_ASSERT_GROUP_MEMBER(struct netns_ipv4, netns_ipv4_read_rx, sysctl_ip_early_demux); CACHELINE_ASSERT_GROUP_MEMBER(struct netns_ipv4, netns_ipv4_read_rx, sysctl_tcp_early_demux); CACHELINE_ASSERT_GROUP_MEMBER(struct netns_ipv4, netns_ipv4_read_rx, sysctl_tcp_l3mdev_accept); CACHELINE_ASSERT_GROUP_MEMBER(struct netns_ipv4, netns_ipv4_read_rx, sysctl_tcp_reordering); CACHELINE_ASSERT_GROUP_MEMBER(struct netns_ipv4, netns_ipv4_read_rx, sysctl_tcp_rmem); CACHELINE_ASSERT_GROUP_SIZE(struct netns_ipv4, netns_ipv4_read_rx, 22); } #endif static const struct rtnl_msg_handler net_ns_rtnl_msg_handlers[] __initconst = { {.msgtype = RTM_NEWNSID, .doit = rtnl_net_newid, .flags = RTNL_FLAG_DOIT_UNLOCKED}, {.msgtype = RTM_GETNSID, .doit = rtnl_net_getid, .dumpit = rtnl_net_dumpid, .flags = RTNL_FLAG_DOIT_UNLOCKED | RTNL_FLAG_DUMP_UNLOCKED}, }; void __init net_ns_init(void) { struct net_generic *ng; #ifdef CONFIG_NET_NS netns_ipv4_struct_check(); net_cachep = kmem_cache_create("net_namespace", sizeof(struct net), SMP_CACHE_BYTES, SLAB_PANIC|SLAB_ACCOUNT, NULL); /* Create workqueue for cleanup */ netns_wq = create_singlethread_workqueue("netns"); if (!netns_wq) panic("Could not create netns workq"); #endif ng = net_alloc_generic(); if (!ng) panic("Could not allocate generic netns"); rcu_assign_pointer(init_net.gen, ng); #ifdef CONFIG_KEYS init_net.key_domain = &init_net_key_domain; #endif preinit_net(&init_net, &init_user_ns); down_write(&pernet_ops_rwsem); if (setup_net(&init_net)) panic("Could not setup the initial network namespace"); init_net_initialized = true; up_write(&pernet_ops_rwsem); if (register_pernet_subsys(&net_ns_ops)) panic("Could not register network namespace subsystems"); rtnl_register_many(net_ns_rtnl_msg_handlers); } static void free_exit_list(struct pernet_operations *ops, struct list_head *net_exit_list) { ops_pre_exit_list(ops, net_exit_list); synchronize_rcu(); if (ops->exit_batch_rtnl) { LIST_HEAD(dev_kill_list); rtnl_lock(); ops->exit_batch_rtnl(net_exit_list, &dev_kill_list); unregister_netdevice_many(&dev_kill_list); rtnl_unlock(); } ops_exit_list(ops, net_exit_list); ops_free_list(ops, net_exit_list); } #ifdef CONFIG_NET_NS static int __register_pernet_operations(struct list_head *list, struct pernet_operations *ops) { struct net *net; int error; LIST_HEAD(net_exit_list); list_add_tail(&ops->list, list); if (ops->init || ops->id) { /* We held write locked pernet_ops_rwsem, and parallel * setup_net() and cleanup_net() are not possible. */ for_each_net(net) { error = ops_init(ops, net); if (error) goto out_undo; list_add_tail(&net->exit_list, &net_exit_list); } } return 0; out_undo: /* If I have an error cleanup all namespaces I initialized */ list_del(&ops->list); free_exit_list(ops, &net_exit_list); return error; } static void __unregister_pernet_operations(struct pernet_operations *ops) { struct net *net; LIST_HEAD(net_exit_list); list_del(&ops->list); /* See comment in __register_pernet_operations() */ for_each_net(net) list_add_tail(&net->exit_list, &net_exit_list); free_exit_list(ops, &net_exit_list); } #else static int __register_pernet_operations(struct list_head *list, struct pernet_operations *ops) { if (!init_net_initialized) { list_add_tail(&ops->list, list); return 0; } return ops_init(ops, &init_net); } static void __unregister_pernet_operations(struct pernet_operations *ops) { if (!init_net_initialized) { list_del(&ops->list); } else { LIST_HEAD(net_exit_list); list_add(&init_net.exit_list, &net_exit_list); free_exit_list(ops, &net_exit_list); } } #endif /* CONFIG_NET_NS */ static DEFINE_IDA(net_generic_ids); static int register_pernet_operations(struct list_head *list, struct pernet_operations *ops) { int error; if (WARN_ON(!!ops->id ^ !!ops->size)) return -EINVAL; if (ops->id) { error = ida_alloc_min(&net_generic_ids, MIN_PERNET_OPS_ID, GFP_KERNEL); if (error < 0) return error; *ops->id = error; /* This does not require READ_ONCE as writers already hold * pernet_ops_rwsem. But WRITE_ONCE is needed to protect * net_alloc_generic. */ WRITE_ONCE(max_gen_ptrs, max(max_gen_ptrs, *ops->id + 1)); } error = __register_pernet_operations(list, ops); if (error) { rcu_barrier(); if (ops->id) ida_free(&net_generic_ids, *ops->id); } return error; } static void unregister_pernet_operations(struct pernet_operations *ops) { __unregister_pernet_operations(ops); rcu_barrier(); if (ops->id) ida_free(&net_generic_ids, *ops->id); } /** * register_pernet_subsys - register a network namespace subsystem * @ops: pernet operations structure for the subsystem * * Register a subsystem which has init and exit functions * that are called when network namespaces are created and * destroyed respectively. * * When registered all network namespace init functions are * called for every existing network namespace. Allowing kernel * modules to have a race free view of the set of network namespaces. * * When a new network namespace is created all of the init * methods are called in the order in which they were registered. * * When a network namespace is destroyed all of the exit methods * are called in the reverse of the order with which they were * registered. */ int register_pernet_subsys(struct pernet_operations *ops) { int error; down_write(&pernet_ops_rwsem); error = register_pernet_operations(first_device, ops); up_write(&pernet_ops_rwsem); return error; } EXPORT_SYMBOL_GPL(register_pernet_subsys); /** * unregister_pernet_subsys - unregister a network namespace subsystem * @ops: pernet operations structure to manipulate * * Remove the pernet operations structure from the list to be * used when network namespaces are created or destroyed. In * addition run the exit method for all existing network * namespaces. */ void unregister_pernet_subsys(struct pernet_operations *ops) { down_write(&pernet_ops_rwsem); unregister_pernet_operations(ops); up_write(&pernet_ops_rwsem); } EXPORT_SYMBOL_GPL(unregister_pernet_subsys); /** * register_pernet_device - register a network namespace device * @ops: pernet operations structure for the subsystem * * Register a device which has init and exit functions * that are called when network namespaces are created and * destroyed respectively. * * When registered all network namespace init functions are * called for every existing network namespace. Allowing kernel * modules to have a race free view of the set of network namespaces. * * When a new network namespace is created all of the init * methods are called in the order in which they were registered. * * When a network namespace is destroyed all of the exit methods * are called in the reverse of the order with which they were * registered. */ int register_pernet_device(struct pernet_operations *ops) { int error; down_write(&pernet_ops_rwsem); error = register_pernet_operations(&pernet_list, ops); if (!error && (first_device == &pernet_list)) first_device = &ops->list; up_write(&pernet_ops_rwsem); return error; } EXPORT_SYMBOL_GPL(register_pernet_device); /** * unregister_pernet_device - unregister a network namespace netdevice * @ops: pernet operations structure to manipulate * * Remove the pernet operations structure from the list to be * used when network namespaces are created or destroyed. In * addition run the exit method for all existing network * namespaces. */ void unregister_pernet_device(struct pernet_operations *ops) { down_write(&pernet_ops_rwsem); if (&ops->list == first_device) first_device = first_device->next; unregister_pernet_operations(ops); up_write(&pernet_ops_rwsem); } EXPORT_SYMBOL_GPL(unregister_pernet_device); #ifdef CONFIG_NET_NS static struct ns_common *netns_get(struct task_struct *task) { struct net *net = NULL; struct nsproxy *nsproxy; task_lock(task); nsproxy = task->nsproxy; if (nsproxy) net = get_net(nsproxy->net_ns); task_unlock(task); return net ? &net->ns : NULL; } static inline struct net *to_net_ns(struct ns_common *ns) { return container_of(ns, struct net, ns); } static void netns_put(struct ns_common *ns) { put_net(to_net_ns(ns)); } static int netns_install(struct nsset *nsset, struct ns_common *ns) { struct nsproxy *nsproxy = nsset->nsproxy; struct net *net = to_net_ns(ns); if (!ns_capable(net->user_ns, CAP_SYS_ADMIN) || !ns_capable(nsset->cred->user_ns, CAP_SYS_ADMIN)) return -EPERM; put_net(nsproxy->net_ns); nsproxy->net_ns = get_net(net); return 0; } static struct user_namespace *netns_owner(struct ns_common *ns) { return to_net_ns(ns)->user_ns; } const struct proc_ns_operations netns_operations = { .name = "net", .type = CLONE_NEWNET, .get = netns_get, .put = netns_put, .install = netns_install, .owner = netns_owner, }; #endif |
| 3 3 3 3 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 1522 1523 1524 1525 1526 1527 1528 1529 1530 1531 1532 1533 1534 1535 1536 1537 1538 1539 1540 1541 1542 1543 1544 1545 1546 1547 1548 1549 1550 1551 1552 1553 1554 1555 1556 1557 1558 1559 1560 1561 1562 1563 1564 1565 1566 1567 1568 1569 1570 1571 1572 1573 1574 1575 1576 1577 1578 1579 1580 1581 1582 1583 1584 1585 1586 1587 1588 1589 1590 1591 1592 1593 1594 1595 1596 1597 1598 1599 1600 1601 1602 1603 1604 1605 1606 1607 1608 1609 1610 1611 1612 1613 1614 1615 1616 1617 1618 1619 1620 1621 1622 1623 1624 1625 1626 1627 1628 1629 1630 1631 1632 1633 1634 1635 1636 1637 1638 1639 1640 1641 1642 1643 1644 1645 1646 1647 1648 1649 1650 1651 1652 1653 1654 1655 1656 1657 1658 1659 1660 1661 1662 1663 1664 1665 1666 1667 1668 1669 1670 1671 1672 1673 1674 1675 1676 1677 1678 1679 1680 1681 1682 1683 1684 1685 1686 1687 1688 1689 1690 1691 1692 1693 1694 1695 1696 1697 1698 1699 1700 1701 1702 1703 1704 1705 1706 1707 1708 1709 1710 1711 1712 1713 1714 1715 1716 1717 1718 1719 1720 1721 1722 1723 1724 1725 1726 1727 1728 1729 1730 1731 1732 1733 1734 1735 1736 1737 1738 1739 1740 1741 1742 1743 1744 1745 1746 1747 1748 1749 1750 1751 1752 1753 1754 1755 1756 1757 1758 1759 1760 1761 1762 1763 1764 1765 1766 1767 1768 1769 1770 1771 1772 1773 1774 1775 1776 1777 1778 1779 1780 1781 1782 1783 1784 1785 1786 1787 1788 1789 1790 1791 1792 1793 1794 1795 1796 1797 1798 1799 1800 1801 1802 1803 1804 1805 1806 1807 1808 1809 1810 1811 1812 1813 1814 1815 1816 1817 1818 1819 1820 1821 1822 1823 1824 1825 1826 1827 1828 1829 1830 1831 1832 1833 1834 1835 1836 1837 1838 1839 1840 1841 1842 1843 1844 1845 1846 1847 1848 1849 1850 1851 1852 1853 1854 1855 1856 1857 1858 1859 1860 1861 1862 1863 1864 1865 1866 1867 1868 1869 1870 1871 1872 1873 1874 1875 1876 1877 1878 1879 1880 1881 1882 1883 1884 1885 1886 1887 1888 1889 1890 1891 1892 1893 1894 1895 1896 1897 1898 1899 1900 1901 1902 1903 1904 1905 1906 1907 1908 1909 1910 1911 1912 1913 1914 1915 1916 1917 1918 1919 1920 1921 1922 1923 1924 1925 1926 1927 1928 1929 1930 1931 1932 1933 1934 1935 1936 1937 1938 1939 1940 1941 1942 1943 1944 1945 1946 1947 1948 1949 1950 1951 1952 1953 1954 1955 1956 1957 1958 1959 1960 1961 1962 1963 1964 1965 1966 1967 1968 1969 1970 1971 1972 1973 1974 1975 1976 1977 1978 1979 1980 1981 1982 1983 1984 1985 1986 1987 1988 1989 1990 1991 1992 1993 1994 1995 1996 1997 1998 1999 2000 2001 2002 2003 2004 2005 2006 2007 2008 2009 2010 2011 2012 2013 2014 2015 2016 2017 2018 2019 2020 2021 2022 2023 2024 2025 2026 2027 2028 2029 2030 2031 2032 2033 2034 2035 2036 2037 2038 2039 2040 2041 2042 2043 2044 2045 2046 2047 2048 2049 2050 2051 2052 2053 2054 2055 2056 2057 2058 2059 2060 2061 2062 2063 2064 2065 2066 2067 2068 2069 2070 2071 2072 2073 2074 2075 2076 2077 2078 2079 2080 2081 2082 2083 2084 2085 2086 2087 2088 2089 2090 2091 2092 2093 2094 2095 2096 2097 2098 2099 2100 2101 2102 2103 2104 2105 2106 2107 2108 2109 2110 2111 2112 2113 2114 2115 2116 2117 2118 2119 2120 2121 2122 2123 2124 2125 2126 2127 2128 2129 2130 2131 2132 2133 2134 2135 2136 2137 2138 2139 2140 2141 2142 2143 2144 2145 2146 2147 2148 2149 2150 2151 2152 2153 2154 2155 2156 2157 2158 2159 2160 2161 2162 2163 2164 2165 2166 2167 2168 2169 2170 2171 2172 2173 2174 2175 2176 2177 2178 2179 2180 2181 2182 2183 2184 2185 2186 2187 2188 2189 2190 2191 2192 2193 2194 2195 2196 2197 2198 2199 2200 2201 2202 2203 2204 2205 2206 2207 2208 2209 2210 2211 2212 2213 2214 2215 2216 2217 2218 2219 2220 2221 2222 2223 2224 2225 2226 2227 2228 2229 2230 2231 2232 2233 2234 2235 2236 2237 2238 2239 2240 2241 2242 2243 2244 2245 2246 2247 2248 2249 2250 2251 2252 2253 2254 2255 2256 2257 2258 2259 2260 2261 2262 2263 2264 2265 2266 2267 2268 2269 2270 2271 2272 2273 2274 2275 2276 2277 2278 2279 2280 2281 2282 2283 2284 2285 2286 2287 2288 2289 2290 2291 2292 2293 2294 2295 2296 2297 2298 2299 2300 2301 2302 2303 2304 2305 2306 2307 2308 2309 2310 2311 2312 2313 2314 2315 2316 2317 2318 2319 2320 2321 2322 2323 2324 2325 2326 2327 2328 2329 2330 2331 2332 2333 2334 2335 2336 2337 2338 2339 2340 2341 2342 2343 2344 2345 2346 2347 2348 2349 2350 2351 2352 2353 2354 2355 2356 2357 2358 2359 2360 2361 2362 2363 2364 2365 2366 2367 2368 2369 2370 2371 2372 2373 2374 2375 2376 2377 2378 2379 2380 2381 2382 2383 2384 2385 2386 2387 2388 2389 2390 2391 2392 2393 2394 2395 2396 2397 2398 2399 2400 2401 2402 2403 2404 2405 2406 2407 2408 2409 2410 2411 2412 2413 2414 2415 2416 2417 2418 2419 2420 2421 2422 2423 2424 2425 2426 2427 2428 2429 2430 2431 2432 2433 2434 2435 2436 2437 2438 2439 2440 2441 2442 2443 2444 2445 2446 2447 2448 2449 2450 2451 2452 2453 2454 2455 2456 2457 2458 2459 2460 2461 2462 2463 2464 2465 2466 2467 2468 2469 2470 2471 2472 2473 2474 2475 2476 2477 2478 2479 2480 2481 2482 2483 2484 2485 2486 2487 2488 2489 2490 2491 2492 2493 2494 2495 2496 2497 2498 2499 2500 2501 2502 2503 2504 2505 2506 2507 2508 2509 2510 2511 2512 2513 2514 2515 2516 2517 2518 2519 2520 2521 2522 2523 2524 2525 2526 2527 2528 2529 2530 2531 2532 2533 2534 2535 2536 2537 2538 2539 2540 2541 2542 2543 2544 2545 2546 2547 2548 2549 2550 2551 2552 2553 2554 2555 2556 2557 2558 2559 2560 2561 2562 | // SPDX-License-Identifier: GPL-2.0 /* net/sched/sch_taprio.c Time Aware Priority Scheduler * * Authors: Vinicius Costa Gomes <vinicius.gomes@intel.com> * */ #include <linux/ethtool.h> #include <linux/ethtool_netlink.h> #include <linux/types.h> #include <linux/slab.h> #include <linux/kernel.h> #include <linux/string.h> #include <linux/list.h> #include <linux/errno.h> #include <linux/skbuff.h> #include <linux/math64.h> #include <linux/module.h> #include <linux/spinlock.h> #include <linux/rcupdate.h> #include <linux/time.h> #include <net/gso.h> #include <net/netlink.h> #include <net/pkt_sched.h> #include <net/pkt_cls.h> #include <net/sch_generic.h> #include <net/sock.h> #include <net/tcp.h> #define TAPRIO_STAT_NOT_SET (~0ULL) #include "sch_mqprio_lib.h" static LIST_HEAD(taprio_list); static struct static_key_false taprio_have_broken_mqprio; static struct static_key_false taprio_have_working_mqprio; #define TAPRIO_ALL_GATES_OPEN -1 #define TXTIME_ASSIST_IS_ENABLED(flags) ((flags) & TCA_TAPRIO_ATTR_FLAG_TXTIME_ASSIST) #define FULL_OFFLOAD_IS_ENABLED(flags) ((flags) & TCA_TAPRIO_ATTR_FLAG_FULL_OFFLOAD) #define TAPRIO_SUPPORTED_FLAGS \ (TCA_TAPRIO_ATTR_FLAG_TXTIME_ASSIST | TCA_TAPRIO_ATTR_FLAG_FULL_OFFLOAD) #define TAPRIO_FLAGS_INVALID U32_MAX struct sched_entry { /* Durations between this GCL entry and the GCL entry where the * respective traffic class gate closes */ u64 gate_duration[TC_MAX_QUEUE]; atomic_t budget[TC_MAX_QUEUE]; /* The qdisc makes some effort so that no packet leaves * after this time */ ktime_t gate_close_time[TC_MAX_QUEUE]; struct list_head list; /* Used to calculate when to advance the schedule */ ktime_t end_time; ktime_t next_txtime; int index; u32 gate_mask; u32 interval; u8 command; }; struct sched_gate_list { /* Longest non-zero contiguous gate durations per traffic class, * or 0 if a traffic class gate never opens during the schedule. */ u64 max_open_gate_duration[TC_MAX_QUEUE]; u32 max_frm_len[TC_MAX_QUEUE]; /* for the fast path */ u32 max_sdu[TC_MAX_QUEUE]; /* for dump */ struct rcu_head rcu; struct list_head entries; size_t num_entries; ktime_t cycle_end_time; s64 cycle_time; s64 cycle_time_extension; s64 base_time; }; struct taprio_sched { struct Qdisc **qdiscs; struct Qdisc *root; u32 flags; enum tk_offsets tk_offset; int clockid; bool offloaded; bool detected_mqprio; bool broken_mqprio; atomic64_t picos_per_byte; /* Using picoseconds because for 10Gbps+ * speeds it's sub-nanoseconds per byte */ /* Protects the update side of the RCU protected current_entry */ spinlock_t current_entry_lock; struct sched_entry __rcu *current_entry; struct sched_gate_list __rcu *oper_sched; struct sched_gate_list __rcu *admin_sched; struct hrtimer advance_timer; struct list_head taprio_list; int cur_txq[TC_MAX_QUEUE]; u32 max_sdu[TC_MAX_QUEUE]; /* save info from the user */ u32 fp[TC_QOPT_MAX_QUEUE]; /* only for dump and offloading */ u32 txtime_delay; }; struct __tc_taprio_qopt_offload { refcount_t users; struct tc_taprio_qopt_offload offload; }; static void taprio_calculate_gate_durations(struct taprio_sched *q, struct sched_gate_list *sched) { struct net_device *dev = qdisc_dev(q->root); int num_tc = netdev_get_num_tc(dev); struct sched_entry *entry, *cur; int tc; list_for_each_entry(entry, &sched->entries, list) { u32 gates_still_open = entry->gate_mask; /* For each traffic class, calculate each open gate duration, * starting at this schedule entry and ending at the schedule * entry containing a gate close event for that TC. */ cur = entry; do { if (!gates_still_open) break; for (tc = 0; tc < num_tc; tc++) { if (!(gates_still_open & BIT(tc))) continue; if (cur->gate_mask & BIT(tc)) entry->gate_duration[tc] += cur->interval; else gates_still_open &= ~BIT(tc); } cur = list_next_entry_circular(cur, &sched->entries, list); } while (cur != entry); /* Keep track of the maximum gate duration for each traffic * class, taking care to not confuse a traffic class which is * temporarily closed with one that is always closed. */ for (tc = 0; tc < num_tc; tc++) if (entry->gate_duration[tc] && sched->max_open_gate_duration[tc] < entry->gate_duration[tc]) sched->max_open_gate_duration[tc] = entry->gate_duration[tc]; } } static bool taprio_entry_allows_tx(ktime_t skb_end_time, struct sched_entry *entry, int tc) { return ktime_before(skb_end_time, entry->gate_close_time[tc]); } static ktime_t sched_base_time(const struct sched_gate_list *sched) { if (!sched) return KTIME_MAX; return ns_to_ktime(sched->base_time); } static ktime_t taprio_mono_to_any(const struct taprio_sched *q, ktime_t mono) { /* This pairs with WRITE_ONCE() in taprio_parse_clockid() */ enum tk_offsets tk_offset = READ_ONCE(q->tk_offset); switch (tk_offset) { case TK_OFFS_MAX: return mono; default: return ktime_mono_to_any(mono, tk_offset); } } static ktime_t taprio_get_time(const struct taprio_sched *q) { return taprio_mono_to_any(q, ktime_get()); } static void taprio_free_sched_cb(struct rcu_head *head) { struct sched_gate_list *sched = container_of(head, struct sched_gate_list, rcu); struct sched_entry *entry, *n; list_for_each_entry_safe(entry, n, &sched->entries, list) { list_del(&entry->list); kfree(entry); } kfree(sched); } static void switch_schedules(struct taprio_sched *q, struct sched_gate_list **admin, struct sched_gate_list **oper) { rcu_assign_pointer(q->oper_sched, *admin); rcu_assign_pointer(q->admin_sched, NULL); if (*oper) call_rcu(&(*oper)->rcu, taprio_free_sched_cb); *oper = *admin; *admin = NULL; } /* Get how much time has been already elapsed in the current cycle. */ static s32 get_cycle_time_elapsed(struct sched_gate_list *sched, ktime_t time) { ktime_t time_since_sched_start; s32 time_elapsed; time_since_sched_start = ktime_sub(time, sched->base_time); div_s64_rem(time_since_sched_start, sched->cycle_time, &time_elapsed); return time_elapsed; } static ktime_t get_interval_end_time(struct sched_gate_list *sched, struct sched_gate_list *admin, struct sched_entry *entry, ktime_t intv_start) { s32 cycle_elapsed = get_cycle_time_elapsed(sched, intv_start); ktime_t intv_end, cycle_ext_end, cycle_end; cycle_end = ktime_add_ns(intv_start, sched->cycle_time - cycle_elapsed); intv_end = ktime_add_ns(intv_start, entry->interval); cycle_ext_end = ktime_add(cycle_end, sched->cycle_time_extension); if (ktime_before(intv_end, cycle_end)) return intv_end; else if (admin && admin != sched && ktime_after(admin->base_time, cycle_end) && ktime_before(admin->base_time, cycle_ext_end)) return admin->base_time; else return cycle_end; } static int length_to_duration(struct taprio_sched *q, int len) { return div_u64(len * atomic64_read(&q->picos_per_byte), PSEC_PER_NSEC); } static int duration_to_length(struct taprio_sched *q, u64 duration) { return div_u64(duration * PSEC_PER_NSEC, atomic64_read(&q->picos_per_byte)); } /* Sets sched->max_sdu[] and sched->max_frm_len[] to the minimum between the * q->max_sdu[] requested by the user and the max_sdu dynamically determined by * the maximum open gate durations at the given link speed. */ static void taprio_update_queue_max_sdu(struct taprio_sched *q, struct sched_gate_list *sched, struct qdisc_size_table *stab) { struct net_device *dev = qdisc_dev(q->root); int num_tc = netdev_get_num_tc(dev); u32 max_sdu_from_user; u32 max_sdu_dynamic; u32 max_sdu; int tc; for (tc = 0; tc < num_tc; tc++) { max_sdu_from_user = q->max_sdu[tc] ?: U32_MAX; /* TC gate never closes => keep the queueMaxSDU * selected by the user */ if (sched->max_open_gate_duration[tc] == sched->cycle_time) { max_sdu_dynamic = U32_MAX; } else { u32 max_frm_len; max_frm_len = duration_to_length(q, sched->max_open_gate_duration[tc]); /* Compensate for L1 overhead from size table, * but don't let the frame size go negative */ if (stab) { max_frm_len -= stab->szopts.overhead; max_frm_len = max_t(int, max_frm_len, dev->hard_header_len + 1); } max_sdu_dynamic = max_frm_len - dev->hard_header_len; if (max_sdu_dynamic > dev->max_mtu) max_sdu_dynamic = U32_MAX; } max_sdu = min(max_sdu_dynamic, max_sdu_from_user); if (max_sdu != U32_MAX) { sched->max_frm_len[tc] = max_sdu + dev->hard_header_len; sched->max_sdu[tc] = max_sdu; } else { sched->max_frm_len[tc] = U32_MAX; /* never oversized */ sched->max_sdu[tc] = 0; } } } /* Returns the entry corresponding to next available interval. If * validate_interval is set, it only validates whether the timestamp occurs * when the gate corresponding to the skb's traffic class is open. */ static struct sched_entry *find_entry_to_transmit(struct sk_buff *skb, struct Qdisc *sch, struct sched_gate_list *sched, struct sched_gate_list *admin, ktime_t time, ktime_t *interval_start, ktime_t *interval_end, bool validate_interval) { ktime_t curr_intv_start, curr_intv_end, cycle_end, packet_transmit_time; ktime_t earliest_txtime = KTIME_MAX, txtime, cycle, transmit_end_time; struct sched_entry *entry = NULL, *entry_found = NULL; struct taprio_sched *q = qdisc_priv(sch); struct net_device *dev = qdisc_dev(sch); bool entry_available = false; s32 cycle_elapsed; int tc, n; tc = netdev_get_prio_tc_map(dev, skb->priority); packet_transmit_time = length_to_duration(q, qdisc_pkt_len(skb)); *interval_start = 0; *interval_end = 0; if (!sched) return NULL; cycle = sched->cycle_time; cycle_elapsed = get_cycle_time_elapsed(sched, time); curr_intv_end = ktime_sub_ns(time, cycle_elapsed); cycle_end = ktime_add_ns(curr_intv_end, cycle); list_for_each_entry(entry, &sched->entries, list) { curr_intv_start = curr_intv_end; curr_intv_end = get_interval_end_time(sched, admin, entry, curr_intv_start); if (ktime_after(curr_intv_start, cycle_end)) break; if (!(entry->gate_mask & BIT(tc)) || packet_transmit_time > entry->interval) continue; txtime = entry->next_txtime; if (ktime_before(txtime, time) || validate_interval) { transmit_end_time = ktime_add_ns(time, packet_transmit_time); if ((ktime_before(curr_intv_start, time) && ktime_before(transmit_end_time, curr_intv_end)) || (ktime_after(curr_intv_start, time) && !validate_interval)) { entry_found = entry; *interval_start = curr_intv_start; *interval_end = curr_intv_end; break; } else if (!entry_available && !validate_interval) { /* Here, we are just trying to find out the * first available interval in the next cycle. */ entry_available = true; entry_found = entry; *interval_start = ktime_add_ns(curr_intv_start, cycle); *interval_end = ktime_add_ns(curr_intv_end, cycle); } } else if (ktime_before(txtime, earliest_txtime) && !entry_available) { earliest_txtime = txtime; entry_found = entry; n = div_s64(ktime_sub(txtime, curr_intv_start), cycle); *interval_start = ktime_add(curr_intv_start, n * cycle); *interval_end = ktime_add(curr_intv_end, n * cycle); } } return entry_found; } static bool is_valid_interval(struct sk_buff *skb, struct Qdisc *sch) { struct taprio_sched *q = qdisc_priv(sch); struct sched_gate_list *sched, *admin; ktime_t interval_start, interval_end; struct sched_entry *entry; rcu_read_lock(); sched = rcu_dereference(q->oper_sched); admin = rcu_dereference(q->admin_sched); entry = find_entry_to_transmit(skb, sch, sched, admin, skb->tstamp, &interval_start, &interval_end, true); rcu_read_unlock(); return entry; } /* This returns the tstamp value set by TCP in terms of the set clock. */ static ktime_t get_tcp_tstamp(struct taprio_sched *q, struct sk_buff *skb) { unsigned int offset = skb_network_offset(skb); const struct ipv6hdr *ipv6h; const struct iphdr *iph; struct ipv6hdr _ipv6h; ipv6h = skb_header_pointer(skb, offset, sizeof(_ipv6h), &_ipv6h); if (!ipv6h) return 0; if (ipv6h->version == 4) { iph = (struct iphdr *)ipv6h; offset += iph->ihl * 4; /* special-case 6in4 tunnelling, as that is a common way to get * v6 connectivity in the home */ if (iph->protocol == IPPROTO_IPV6) { ipv6h = skb_header_pointer(skb, offset, sizeof(_ipv6h), &_ipv6h); if (!ipv6h || ipv6h->nexthdr != IPPROTO_TCP) return 0; } else if (iph->protocol != IPPROTO_TCP) { return 0; } } else if (ipv6h->version == 6 && ipv6h->nexthdr != IPPROTO_TCP) { return 0; } return taprio_mono_to_any(q, skb->skb_mstamp_ns); } /* There are a few scenarios where we will have to modify the txtime from * what is read from next_txtime in sched_entry. They are: * 1. If txtime is in the past, * a. The gate for the traffic class is currently open and packet can be * transmitted before it closes, schedule the packet right away. * b. If the gate corresponding to the traffic class is going to open later * in the cycle, set the txtime of packet to the interval start. * 2. If txtime is in the future, there are packets corresponding to the * current traffic class waiting to be transmitted. So, the following * possibilities exist: * a. We can transmit the packet before the window containing the txtime * closes. * b. The window might close before the transmission can be completed * successfully. So, schedule the packet in the next open window. */ static long get_packet_txtime(struct sk_buff *skb, struct Qdisc *sch) { ktime_t transmit_end_time, interval_end, interval_start, tcp_tstamp; struct taprio_sched *q = qdisc_priv(sch); struct sched_gate_list *sched, *admin; ktime_t minimum_time, now, txtime; int len, packet_transmit_time; struct sched_entry *entry; bool sched_changed; now = taprio_get_time(q); minimum_time = ktime_add_ns(now, q->txtime_delay); tcp_tstamp = get_tcp_tstamp(q, skb); minimum_time = max_t(ktime_t, minimum_time, tcp_tstamp); rcu_read_lock(); admin = rcu_dereference(q->admin_sched); sched = rcu_dereference(q->oper_sched); if (admin && ktime_after(minimum_time, admin->base_time)) switch_schedules(q, &admin, &sched); /* Until the schedule starts, all the queues are open */ if (!sched || ktime_before(minimum_time, sched->base_time)) { txtime = minimum_time; goto done; } len = qdisc_pkt_len(skb); packet_transmit_time = length_to_duration(q, len); do { sched_changed = false; entry = find_entry_to_transmit(skb, sch, sched, admin, minimum_time, &interval_start, &interval_end, false); if (!entry) { txtime = 0; goto done; } txtime = entry->next_txtime; txtime = max_t(ktime_t, txtime, minimum_time); txtime = max_t(ktime_t, txtime, interval_start); if (admin && admin != sched && ktime_after(txtime, admin->base_time)) { sched = admin; sched_changed = true; continue; } transmit_end_time = ktime_add(txtime, packet_transmit_time); minimum_time = transmit_end_time; /* Update the txtime of current entry to the next time it's * interval starts. */ if (ktime_after(transmit_end_time, interval_end)) entry->next_txtime = ktime_add(interval_start, sched->cycle_time); } while (sched_changed || ktime_after(transmit_end_time, interval_end)); entry->next_txtime = transmit_end_time; done: rcu_read_unlock(); return txtime; } /* Devices with full offload are expected to honor this in hardware */ static bool taprio_skb_exceeds_queue_max_sdu(struct Qdisc *sch, struct sk_buff *skb) { struct taprio_sched *q = qdisc_priv(sch); struct net_device *dev = qdisc_dev(sch); struct sched_gate_list *sched; int prio = skb->priority; bool exceeds = false; u8 tc; tc = netdev_get_prio_tc_map(dev, prio); rcu_read_lock(); sched = rcu_dereference(q->oper_sched); if (sched && skb->len > sched->max_frm_len[tc]) exceeds = true; rcu_read_unlock(); return exceeds; } static int taprio_enqueue_one(struct sk_buff *skb, struct Qdisc *sch, struct Qdisc *child, struct sk_buff **to_free) { struct taprio_sched *q = qdisc_priv(sch); /* sk_flags are only safe to use on full sockets. */ if (skb->sk && sk_fullsock(skb->sk) && sock_flag(skb->sk, SOCK_TXTIME)) { if (!is_valid_interval(skb, sch)) return qdisc_drop(skb, sch, to_free); } else if (TXTIME_ASSIST_IS_ENABLED(q->flags)) { skb->tstamp = get_packet_txtime(skb, sch); if (!skb->tstamp) return qdisc_drop(skb, sch, to_free); } qdisc_qstats_backlog_inc(sch, skb); sch->q.qlen++; return qdisc_enqueue(skb, child, to_free); } static int taprio_enqueue_segmented(struct sk_buff *skb, struct Qdisc *sch, struct Qdisc *child, struct sk_buff **to_free) { unsigned int slen = 0, numsegs = 0, len = qdisc_pkt_len(skb); netdev_features_t features = netif_skb_features(skb); struct sk_buff *segs, *nskb; int ret; segs = skb_gso_segment(skb, features & ~NETIF_F_GSO_MASK); if (IS_ERR_OR_NULL(segs)) return qdisc_drop(skb, sch, to_free); skb_list_walk_safe(segs, segs, nskb) { skb_mark_not_on_list(segs); qdisc_skb_cb(segs)->pkt_len = segs->len; slen += segs->len; /* FIXME: we should be segmenting to a smaller size * rather than dropping these */ if (taprio_skb_exceeds_queue_max_sdu(sch, segs)) ret = qdisc_drop(segs, sch, to_free); else ret = taprio_enqueue_one(segs, sch, child, to_free); if (ret != NET_XMIT_SUCCESS) { if (net_xmit_drop_count(ret)) qdisc_qstats_drop(sch); } else { numsegs++; } } if (numsegs > 1) qdisc_tree_reduce_backlog(sch, 1 - numsegs, len - slen); consume_skb(skb); return numsegs > 0 ? NET_XMIT_SUCCESS : NET_XMIT_DROP; } /* Will not be called in the full offload case, since the TX queues are * attached to the Qdisc created using qdisc_create_dflt() */ static int taprio_enqueue(struct sk_buff *skb, struct Qdisc *sch, struct sk_buff **to_free) { struct taprio_sched *q = qdisc_priv(sch); struct Qdisc *child; int queue; queue = skb_get_queue_mapping(skb); child = q->qdiscs[queue]; if (unlikely(!child)) return qdisc_drop(skb, sch, to_free); if (taprio_skb_exceeds_queue_max_sdu(sch, skb)) { /* Large packets might not be transmitted when the transmission * duration exceeds any configured interval. Therefore, segment * the skb into smaller chunks. Drivers with full offload are * expected to handle this in hardware. */ if (skb_is_gso(skb)) return taprio_enqueue_segmented(skb, sch, child, to_free); return qdisc_drop(skb, sch, to_free); } return taprio_enqueue_one(skb, sch, child, to_free); } static struct sk_buff *taprio_peek(struct Qdisc *sch) { WARN_ONCE(1, "taprio only supports operating as root qdisc, peek() not implemented"); return NULL; } static void taprio_set_budgets(struct taprio_sched *q, struct sched_gate_list *sched, struct sched_entry *entry) { struct net_device *dev = qdisc_dev(q->root); int num_tc = netdev_get_num_tc(dev); int tc, budget; for (tc = 0; tc < num_tc; tc++) { /* Traffic classes which never close have infinite budget */ if (entry->gate_duration[tc] == sched->cycle_time) budget = INT_MAX; else budget = div64_u64((u64)entry->gate_duration[tc] * PSEC_PER_NSEC, atomic64_read(&q->picos_per_byte)); atomic_set(&entry->budget[tc], budget); } } /* When an skb is sent, it consumes from the budget of all traffic classes */ static int taprio_update_budgets(struct sched_entry *entry, size_t len, int tc_consumed, int num_tc) { int tc, budget, new_budget = 0; for (tc = 0; tc < num_tc; tc++) { budget = atomic_read(&entry->budget[tc]); /* Don't consume from infinite budget */ if (budget == INT_MAX) { if (tc == tc_consumed) new_budget = budget; continue; } if (tc == tc_consumed) new_budget = atomic_sub_return(len, &entry->budget[tc]); else atomic_sub(len, &entry->budget[tc]); } return new_budget; } static struct sk_buff *taprio_dequeue_from_txq(struct Qdisc *sch, int txq, struct sched_entry *entry, u32 gate_mask) { struct taprio_sched *q = qdisc_priv(sch); struct net_device *dev = qdisc_dev(sch); struct Qdisc *child = q->qdiscs[txq]; int num_tc = netdev_get_num_tc(dev); struct sk_buff *skb; ktime_t guard; int prio; int len; u8 tc; if (unlikely(!child)) return NULL; if (TXTIME_ASSIST_IS_ENABLED(q->flags)) goto skip_peek_checks; skb = child->ops->peek(child); if (!skb) return NULL; prio = skb->priority; tc = netdev_get_prio_tc_map(dev, prio); if (!(gate_mask & BIT(tc))) return NULL; len = qdisc_pkt_len(skb); guard = ktime_add_ns(taprio_get_time(q), length_to_duration(q, len)); /* In the case that there's no gate entry, there's no * guard band ... */ if (gate_mask != TAPRIO_ALL_GATES_OPEN && !taprio_entry_allows_tx(guard, entry, tc)) return NULL; /* ... and no budget. */ if (gate_mask != TAPRIO_ALL_GATES_OPEN && taprio_update_budgets(entry, len, tc, num_tc) < 0) return NULL; skip_peek_checks: skb = child->ops->dequeue(child); if (unlikely(!skb)) return NULL; qdisc_bstats_update(sch, skb); qdisc_qstats_backlog_dec(sch, skb); sch->q.qlen--; return skb; } static void taprio_next_tc_txq(struct net_device *dev, int tc, int *txq) { int offset = dev->tc_to_txq[tc].offset; int count = dev->tc_to_txq[tc].count; (*txq)++; if (*txq == offset + count) *txq = offset; } /* Prioritize higher traffic classes, and select among TXQs belonging to the * same TC using round robin */ static struct sk_buff *taprio_dequeue_tc_priority(struct Qdisc *sch, struct sched_entry *entry, u32 gate_mask) { struct taprio_sched *q = qdisc_priv(sch); struct net_device *dev = qdisc_dev(sch); int num_tc = netdev_get_num_tc(dev); struct sk_buff *skb; int tc; for (tc = num_tc - 1; tc >= 0; tc--) { int first_txq = q->cur_txq[tc]; if (!(gate_mask & BIT(tc))) continue; do { skb = taprio_dequeue_from_txq(sch, q->cur_txq[tc], entry, gate_mask); taprio_next_tc_txq(dev, tc, &q->cur_txq[tc]); if (q->cur_txq[tc] >= dev->num_tx_queues) q->cur_txq[tc] = first_txq; if (skb) return skb; } while (q->cur_txq[tc] != first_txq); } return NULL; } /* Broken way of prioritizing smaller TXQ indices and ignoring the traffic * class other than to determine whether the gate is open or not */ static struct sk_buff *taprio_dequeue_txq_priority(struct Qdisc *sch, struct sched_entry *entry, u32 gate_mask) { struct net_device *dev = qdisc_dev(sch); struct sk_buff *skb; int i; for (i = 0; i < dev->num_tx_queues; i++) { skb = taprio_dequeue_from_txq(sch, i, entry, gate_mask); if (skb) return skb; } return NULL; } /* Will not be called in the full offload case, since the TX queues are * attached to the Qdisc created using qdisc_create_dflt() */ static struct sk_buff *taprio_dequeue(struct Qdisc *sch) { struct taprio_sched *q = qdisc_priv(sch); struct sk_buff *skb = NULL; struct sched_entry *entry; u32 gate_mask; rcu_read_lock(); entry = rcu_dereference(q->current_entry); /* if there's no entry, it means that the schedule didn't * start yet, so force all gates to be open, this is in * accordance to IEEE 802.1Qbv-2015 Section 8.6.9.4.5 * "AdminGateStates" */ gate_mask = entry ? entry->gate_mask : TAPRIO_ALL_GATES_OPEN; if (!gate_mask) goto done; if (static_branch_unlikely(&taprio_have_broken_mqprio) && !static_branch_likely(&taprio_have_working_mqprio)) { /* Single NIC kind which is broken */ skb = taprio_dequeue_txq_priority(sch, entry, gate_mask); } else if (static_branch_likely(&taprio_have_working_mqprio) && !static_branch_unlikely(&taprio_have_broken_mqprio)) { /* Single NIC kind which prioritizes properly */ skb = taprio_dequeue_tc_priority(sch, entry, gate_mask); } else { /* Mixed NIC kinds present in system, need dynamic testing */ if (q->broken_mqprio) skb = taprio_dequeue_txq_priority(sch, entry, gate_mask); else skb = taprio_dequeue_tc_priority(sch, entry, gate_mask); } done: rcu_read_unlock(); return skb; } static bool should_restart_cycle(const struct sched_gate_list *oper, const struct sched_entry *entry) { if (list_is_last(&entry->list, &oper->entries)) return true; if (ktime_compare(entry->end_time, oper->cycle_end_time) == 0) return true; return false; } static bool should_change_schedules(const struct sched_gate_list *admin, const struct sched_gate_list *oper, ktime_t end_time) { ktime_t next_base_time, extension_time; if (!admin) return false; next_base_time = sched_base_time(admin); /* This is the simple case, the end_time would fall after * the next schedule base_time. */ if (ktime_compare(next_base_time, end_time) <= 0) return true; /* This is the cycle_time_extension case, if the end_time * plus the amount that can be extended would fall after the * next schedule base_time, we can extend the current schedule * for that amount. */ extension_time = ktime_add_ns(end_time, oper->cycle_time_extension); /* FIXME: the IEEE 802.1Q-2018 Specification isn't clear about * how precisely the extension should be made. So after * conformance testing, this logic may change. */ if (ktime_compare(next_base_time, extension_time) <= 0) return true; return false; } static enum hrtimer_restart advance_sched(struct hrtimer *timer) { struct taprio_sched *q = container_of(timer, struct taprio_sched, advance_timer); struct net_device *dev = qdisc_dev(q->root); struct sched_gate_list *oper, *admin; int num_tc = netdev_get_num_tc(dev); struct sched_entry *entry, *next; struct Qdisc *sch = q->root; ktime_t end_time; int tc; spin_lock(&q->current_entry_lock); entry = rcu_dereference_protected(q->current_entry, lockdep_is_held(&q->current_entry_lock)); oper = rcu_dereference_protected(q->oper_sched, lockdep_is_held(&q->current_entry_lock)); admin = rcu_dereference_protected(q->admin_sched, lockdep_is_held(&q->current_entry_lock)); if (!oper) switch_schedules(q, &admin, &oper); /* This can happen in two cases: 1. this is the very first run * of this function (i.e. we weren't running any schedule * previously); 2. The previous schedule just ended. The first * entry of all schedules are pre-calculated during the * schedule initialization. */ if (unlikely(!entry || entry->end_time == oper->base_time)) { next = list_first_entry(&oper->entries, struct sched_entry, list); end_time = next->end_time; goto first_run; } if (should_restart_cycle(oper, entry)) { next = list_first_entry(&oper->entries, struct sched_entry, list); oper->cycle_end_time = ktime_add_ns(oper->cycle_end_time, oper->cycle_time); } else { next = list_next_entry(entry, list); } end_time = ktime_add_ns(entry->end_time, next->interval); end_time = min_t(ktime_t, end_time, oper->cycle_end_time); for (tc = 0; tc < num_tc; tc++) { if (next->gate_duration[tc] == oper->cycle_time) next->gate_close_time[tc] = KTIME_MAX; else next->gate_close_time[tc] = ktime_add_ns(entry->end_time, next->gate_duration[tc]); } if (should_change_schedules(admin, oper, end_time)) { /* Set things so the next time this runs, the new * schedule runs. */ end_time = sched_base_time(admin); switch_schedules(q, &admin, &oper); } next->end_time = end_time; taprio_set_budgets(q, oper, next); first_run: rcu_assign_pointer(q->current_entry, next); spin_unlock(&q->current_entry_lock); hrtimer_set_expires(&q->advance_timer, end_time); rcu_read_lock(); __netif_schedule(sch); rcu_read_unlock(); return HRTIMER_RESTART; } static const struct nla_policy entry_policy[TCA_TAPRIO_SCHED_ENTRY_MAX + 1] = { [TCA_TAPRIO_SCHED_ENTRY_INDEX] = { .type = NLA_U32 }, [TCA_TAPRIO_SCHED_ENTRY_CMD] = { .type = NLA_U8 }, [TCA_TAPRIO_SCHED_ENTRY_GATE_MASK] = { .type = NLA_U32 }, [TCA_TAPRIO_SCHED_ENTRY_INTERVAL] = { .type = NLA_U32 }, }; static const struct nla_policy taprio_tc_policy[TCA_TAPRIO_TC_ENTRY_MAX + 1] = { [TCA_TAPRIO_TC_ENTRY_INDEX] = NLA_POLICY_MAX(NLA_U32, TC_QOPT_MAX_QUEUE), [TCA_TAPRIO_TC_ENTRY_MAX_SDU] = { .type = NLA_U32 }, [TCA_TAPRIO_TC_ENTRY_FP] = NLA_POLICY_RANGE(NLA_U32, TC_FP_EXPRESS, TC_FP_PREEMPTIBLE), }; static const struct netlink_range_validation_signed taprio_cycle_time_range = { .min = 0, .max = INT_MAX, }; static const struct nla_policy taprio_policy[TCA_TAPRIO_ATTR_MAX + 1] = { [TCA_TAPRIO_ATTR_PRIOMAP] = { .len = sizeof(struct tc_mqprio_qopt) }, [TCA_TAPRIO_ATTR_SCHED_ENTRY_LIST] = { .type = NLA_NESTED }, [TCA_TAPRIO_ATTR_SCHED_BASE_TIME] = { .type = NLA_S64 }, [TCA_TAPRIO_ATTR_SCHED_SINGLE_ENTRY] = { .type = NLA_NESTED }, [TCA_TAPRIO_ATTR_SCHED_CLOCKID] = { .type = NLA_S32 }, [TCA_TAPRIO_ATTR_SCHED_CYCLE_TIME] = NLA_POLICY_FULL_RANGE_SIGNED(NLA_S64, &taprio_cycle_time_range), [TCA_TAPRIO_ATTR_SCHED_CYCLE_TIME_EXTENSION] = { .type = NLA_S64 }, [TCA_TAPRIO_ATTR_FLAGS] = NLA_POLICY_MASK(NLA_U32, TAPRIO_SUPPORTED_FLAGS), [TCA_TAPRIO_ATTR_TXTIME_DELAY] = { .type = NLA_U32 }, [TCA_TAPRIO_ATTR_TC_ENTRY] = { .type = NLA_NESTED }, }; static int fill_sched_entry(struct taprio_sched *q, struct nlattr **tb, struct sched_entry *entry, struct netlink_ext_ack *extack) { int min_duration = length_to_duration(q, ETH_ZLEN); u32 interval = 0; if (tb[TCA_TAPRIO_SCHED_ENTRY_CMD]) entry->command = nla_get_u8( tb[TCA_TAPRIO_SCHED_ENTRY_CMD]); if (tb[TCA_TAPRIO_SCHED_ENTRY_GATE_MASK]) entry->gate_mask = nla_get_u32( tb[TCA_TAPRIO_SCHED_ENTRY_GATE_MASK]); if (tb[TCA_TAPRIO_SCHED_ENTRY_INTERVAL]) interval = nla_get_u32( tb[TCA_TAPRIO_SCHED_ENTRY_INTERVAL]); /* The interval should allow at least the minimum ethernet * frame to go out. */ if (interval < min_duration) { NL_SET_ERR_MSG(extack, "Invalid interval for schedule entry"); return -EINVAL; } entry->interval = interval; return 0; } static int parse_sched_entry(struct taprio_sched *q, struct nlattr *n, struct sched_entry *entry, int index, struct netlink_ext_ack *extack) { struct nlattr *tb[TCA_TAPRIO_SCHED_ENTRY_MAX + 1] = { }; int err; err = nla_parse_nested_deprecated(tb, TCA_TAPRIO_SCHED_ENTRY_MAX, n, entry_policy, NULL); if (err < 0) { NL_SET_ERR_MSG(extack, "Could not parse nested entry"); return -EINVAL; } entry->index = index; return fill_sched_entry(q, tb, entry, extack); } static int parse_sched_list(struct taprio_sched *q, struct nlattr *list, struct sched_gate_list *sched, struct netlink_ext_ack *extack) { struct nlattr *n; int err, rem; int i = 0; if (!list) return -EINVAL; nla_for_each_nested(n, list, rem) { struct sched_entry *entry; if (nla_type(n) != TCA_TAPRIO_SCHED_ENTRY) { NL_SET_ERR_MSG(extack, "Attribute is not of type 'entry'"); continue; } entry = kzalloc(sizeof(*entry), GFP_KERNEL); if (!entry) { NL_SET_ERR_MSG(extack, "Not enough memory for entry"); return -ENOMEM; } err = parse_sched_entry(q, n, entry, i, extack); if (err < 0) { kfree(entry); return err; } list_add_tail(&entry->list, &sched->entries); i++; } sched->num_entries = i; return i; } static int parse_taprio_schedule(struct taprio_sched *q, struct nlattr **tb, struct sched_gate_list *new, struct netlink_ext_ack *extack) { int err = 0; if (tb[TCA_TAPRIO_ATTR_SCHED_SINGLE_ENTRY]) { NL_SET_ERR_MSG(extack, "Adding a single entry is not supported"); return -ENOTSUPP; } if (tb[TCA_TAPRIO_ATTR_SCHED_BASE_TIME]) new->base_time = nla_get_s64(tb[TCA_TAPRIO_ATTR_SCHED_BASE_TIME]); if (tb[TCA_TAPRIO_ATTR_SCHED_CYCLE_TIME_EXTENSION]) new->cycle_time_extension = nla_get_s64(tb[TCA_TAPRIO_ATTR_SCHED_CYCLE_TIME_EXTENSION]); if (tb[TCA_TAPRIO_ATTR_SCHED_CYCLE_TIME]) new->cycle_time = nla_get_s64(tb[TCA_TAPRIO_ATTR_SCHED_CYCLE_TIME]); if (tb[TCA_TAPRIO_ATTR_SCHED_ENTRY_LIST]) err = parse_sched_list(q, tb[TCA_TAPRIO_ATTR_SCHED_ENTRY_LIST], new, extack); if (err < 0) return err; if (!new->cycle_time) { struct sched_entry *entry; ktime_t cycle = 0; list_for_each_entry(entry, &new->entries, list) cycle = ktime_add_ns(cycle, entry->interval); if (cycle < 0 || cycle > INT_MAX) { NL_SET_ERR_MSG(extack, "'cycle_time' is too big"); return -EINVAL; } new->cycle_time = cycle; } if (new->cycle_time < new->num_entries * length_to_duration(q, ETH_ZLEN)) { NL_SET_ERR_MSG(extack, "'cycle_time' is too small"); return -EINVAL; } taprio_calculate_gate_durations(q, new); return 0; } static int taprio_parse_mqprio_opt(struct net_device *dev, struct tc_mqprio_qopt *qopt, struct netlink_ext_ack *extack, u32 taprio_flags) { bool allow_overlapping_txqs = TXTIME_ASSIST_IS_ENABLED(taprio_flags); if (!qopt) { if (!dev->num_tc) { NL_SET_ERR_MSG(extack, "'mqprio' configuration is necessary"); return -EINVAL; } return 0; } /* taprio imposes that traffic classes map 1:n to tx queues */ if (qopt->num_tc > dev->num_tx_queues) { NL_SET_ERR_MSG(extack, "Number of traffic classes is greater than number of HW queues"); return -EINVAL; } /* For some reason, in txtime-assist mode, we allow TXQ ranges for * different TCs to overlap, and just validate the TXQ ranges. */ return mqprio_validate_qopt(dev, qopt, true, allow_overlapping_txqs, extack); } static int taprio_get_start_time(struct Qdisc *sch, struct sched_gate_list *sched, ktime_t *start) { struct taprio_sched *q = qdisc_priv(sch); ktime_t now, base, cycle; s64 n; base = sched_base_time(sched); now = taprio_get_time(q); if (ktime_after(base, now)) { *start = base; return 0; } cycle = sched->cycle_time; /* The qdisc is expected to have at least one sched_entry. Moreover, * any entry must have 'interval' > 0. Thus if the cycle time is zero, * something went really wrong. In that case, we should warn about this * inconsistent state and return error. */ if (WARN_ON(!cycle)) return -EFAULT; /* Schedule the start time for the beginning of the next * cycle. */ n = div64_s64(ktime_sub_ns(now, base), cycle); *start = ktime_add_ns(base, (n + 1) * cycle); return 0; } static void setup_first_end_time(struct taprio_sched *q, struct sched_gate_list *sched, ktime_t base) { struct net_device *dev = qdisc_dev(q->root); int num_tc = netdev_get_num_tc(dev); struct sched_entry *first; ktime_t cycle; int tc; first = list_first_entry(&sched->entries, struct sched_entry, list); cycle = sched->cycle_time; /* FIXME: find a better place to do this */ sched->cycle_end_time = ktime_add_ns(base, cycle); first->end_time = ktime_add_ns(base, first->interval); taprio_set_budgets(q, sched, first); for (tc = 0; tc < num_tc; tc++) { if (first->gate_duration[tc] == sched->cycle_time) first->gate_close_time[tc] = KTIME_MAX; else first->gate_close_time[tc] = ktime_add_ns(base, first->gate_duration[tc]); } rcu_assign_pointer(q->current_entry, NULL); } static void taprio_start_sched(struct Qdisc *sch, ktime_t start, struct sched_gate_list *new) { struct taprio_sched *q = qdisc_priv(sch); ktime_t expires; if (FULL_OFFLOAD_IS_ENABLED(q->flags)) return; expires = hrtimer_get_expires(&q->advance_timer); if (expires == 0) expires = KTIME_MAX; /* If the new schedule starts before the next expiration, we * reprogram it to the earliest one, so we change the admin * schedule to the operational one at the right time. */ start = min_t(ktime_t, start, expires); hrtimer_start(&q->advance_timer, start, HRTIMER_MODE_ABS); } static void taprio_set_picos_per_byte(struct net_device *dev, struct taprio_sched *q) { struct ethtool_link_ksettings ecmd; int speed = SPEED_10; int picos_per_byte; int err; err = __ethtool_get_link_ksettings(dev, &ecmd); if (err < 0) goto skip; if (ecmd.base.speed && ecmd.base.speed != SPEED_UNKNOWN) speed = ecmd.base.speed; skip: picos_per_byte = (USEC_PER_SEC * 8) / speed; atomic64_set(&q->picos_per_byte, picos_per_byte); netdev_dbg(dev, "taprio: set %s's picos_per_byte to: %lld, linkspeed: %d\n", dev->name, (long long)atomic64_read(&q->picos_per_byte), ecmd.base.speed); } static int taprio_dev_notifier(struct notifier_block *nb, unsigned long event, void *ptr) { struct net_device *dev = netdev_notifier_info_to_dev(ptr); struct sched_gate_list *oper, *admin; struct qdisc_size_table *stab; struct taprio_sched *q; ASSERT_RTNL(); if (event != NETDEV_UP && event != NETDEV_CHANGE) return NOTIFY_DONE; list_for_each_entry(q, &taprio_list, taprio_list) { if (dev != qdisc_dev(q->root)) continue; taprio_set_picos_per_byte(dev, q); stab = rtnl_dereference(q->root->stab); oper = rtnl_dereference(q->oper_sched); if (oper) taprio_update_queue_max_sdu(q, oper, stab); admin = rtnl_dereference(q->admin_sched); if (admin) taprio_update_queue_max_sdu(q, admin, stab); break; } return NOTIFY_DONE; } static void setup_txtime(struct taprio_sched *q, struct sched_gate_list *sched, ktime_t base) { struct sched_entry *entry; u64 interval = 0; list_for_each_entry(entry, &sched->entries, list) { entry->next_txtime = ktime_add_ns(base, interval); interval += entry->interval; } } static struct tc_taprio_qopt_offload *taprio_offload_alloc(int num_entries) { struct __tc_taprio_qopt_offload *__offload; __offload = kzalloc(struct_size(__offload, offload.entries, num_entries), GFP_KERNEL); if (!__offload) return NULL; refcount_set(&__offload->users, 1); return &__offload->offload; } struct tc_taprio_qopt_offload *taprio_offload_get(struct tc_taprio_qopt_offload *offload) { struct __tc_taprio_qopt_offload *__offload; __offload = container_of(offload, struct __tc_taprio_qopt_offload, offload); refcount_inc(&__offload->users); return offload; } EXPORT_SYMBOL_GPL(taprio_offload_get); void taprio_offload_free(struct tc_taprio_qopt_offload *offload) { struct __tc_taprio_qopt_offload *__offload; __offload = container_of(offload, struct __tc_taprio_qopt_offload, offload); if (!refcount_dec_and_test(&__offload->users)) return; kfree(__offload); } EXPORT_SYMBOL_GPL(taprio_offload_free); /* The function will only serve to keep the pointers to the "oper" and "admin" * schedules valid in relation to their base times, so when calling dump() the * users looks at the right schedules. * When using full offload, the admin configuration is promoted to oper at the * base_time in the PHC time domain. But because the system time is not * necessarily in sync with that, we can't just trigger a hrtimer to call * switch_schedules at the right hardware time. * At the moment we call this by hand right away from taprio, but in the future * it will be useful to create a mechanism for drivers to notify taprio of the * offload state (PENDING, ACTIVE, INACTIVE) so it can be visible in dump(). * This is left as TODO. */ static void taprio_offload_config_changed(struct taprio_sched *q) { struct sched_gate_list *oper, *admin; oper = rtnl_dereference(q->oper_sched); admin = rtnl_dereference(q->admin_sched); switch_schedules(q, &admin, &oper); } static u32 tc_map_to_queue_mask(struct net_device *dev, u32 tc_mask) { u32 i, queue_mask = 0; for (i = 0; i < dev->num_tc; i++) { u32 offset, count; if (!(tc_mask & BIT(i))) continue; offset = dev->tc_to_txq[i].offset; count = dev->tc_to_txq[i].count; queue_mask |= GENMASK(offset + count - 1, offset); } return queue_mask; } static void taprio_sched_to_offload(struct net_device *dev, struct sched_gate_list *sched, struct tc_taprio_qopt_offload *offload, const struct tc_taprio_caps *caps) { struct sched_entry *entry; int i = 0; offload->base_time = sched->base_time; offload->cycle_time = sched->cycle_time; offload->cycle_time_extension = sched->cycle_time_extension; list_for_each_entry(entry, &sched->entries, list) { struct tc_taprio_sched_entry *e = &offload->entries[i]; e->command = entry->command; e->interval = entry->interval; if (caps->gate_mask_per_txq) e->gate_mask = tc_map_to_queue_mask(dev, entry->gate_mask); else e->gate_mask = entry->gate_mask; i++; } offload->num_entries = i; } static void taprio_detect_broken_mqprio(struct taprio_sched *q) { struct net_device *dev = qdisc_dev(q->root); struct tc_taprio_caps caps; qdisc_offload_query_caps(dev, TC_SETUP_QDISC_TAPRIO, &caps, sizeof(caps)); q->broken_mqprio = caps.broken_mqprio; if (q->broken_mqprio) static_branch_inc(&taprio_have_broken_mqprio); else static_branch_inc(&taprio_have_working_mqprio); q->detected_mqprio = true; } static void taprio_cleanup_broken_mqprio(struct taprio_sched *q) { if (!q->detected_mqprio) return; if (q->broken_mqprio) static_branch_dec(&taprio_have_broken_mqprio); else static_branch_dec(&taprio_have_working_mqprio); } static int taprio_enable_offload(struct net_device *dev, struct taprio_sched *q, struct sched_gate_list *sched, struct netlink_ext_ack *extack) { const struct net_device_ops *ops = dev->netdev_ops; struct tc_taprio_qopt_offload *offload; struct tc_taprio_caps caps; int tc, err = 0; if (!ops->ndo_setup_tc) { NL_SET_ERR_MSG(extack, "Device does not support taprio offload"); return -EOPNOTSUPP; } qdisc_offload_query_caps(dev, TC_SETUP_QDISC_TAPRIO, &caps, sizeof(caps)); if (!caps.supports_queue_max_sdu) { for (tc = 0; tc < TC_MAX_QUEUE; tc++) { if (q->max_sdu[tc]) { NL_SET_ERR_MSG_MOD(extack, "Device does not handle queueMaxSDU"); return -EOPNOTSUPP; } } } offload = taprio_offload_alloc(sched->num_entries); if (!offload) { NL_SET_ERR_MSG(extack, "Not enough memory for enabling offload mode"); return -ENOMEM; } offload->cmd = TAPRIO_CMD_REPLACE; offload->extack = extack; mqprio_qopt_reconstruct(dev, &offload->mqprio.qopt); offload->mqprio.extack = extack; taprio_sched_to_offload(dev, sched, offload, &caps); mqprio_fp_to_offload(q->fp, &offload->mqprio); for (tc = 0; tc < TC_MAX_QUEUE; tc++) offload->max_sdu[tc] = q->max_sdu[tc]; err = ops->ndo_setup_tc(dev, TC_SETUP_QDISC_TAPRIO, offload); if (err < 0) { NL_SET_ERR_MSG_WEAK(extack, "Device failed to setup taprio offload"); goto done; } q->offloaded = true; done: /* The offload structure may linger around via a reference taken by the * device driver, so clear up the netlink extack pointer so that the * driver isn't tempted to dereference data which stopped being valid */ offload->extack = NULL; offload->mqprio.extack = NULL; taprio_offload_free(offload); return err; } static int taprio_disable_offload(struct net_device *dev, struct taprio_sched *q, struct netlink_ext_ack *extack) { const struct net_device_ops *ops = dev->netdev_ops; struct tc_taprio_qopt_offload *offload; int err; if (!q->offloaded) return 0; offload = taprio_offload_alloc(0); if (!offload) { NL_SET_ERR_MSG(extack, "Not enough memory to disable offload mode"); return -ENOMEM; } offload->cmd = TAPRIO_CMD_DESTROY; err = ops->ndo_setup_tc(dev, TC_SETUP_QDISC_TAPRIO, offload); if (err < 0) { NL_SET_ERR_MSG(extack, "Device failed to disable offload"); goto out; } q->offloaded = false; out: taprio_offload_free(offload); return err; } /* If full offload is enabled, the only possible clockid is the net device's * PHC. For that reason, specifying a clockid through netlink is incorrect. * For txtime-assist, it is implicitly assumed that the device's PHC is kept * in sync with the specified clockid via a user space daemon such as phc2sys. * For both software taprio and txtime-assist, the clockid is used for the * hrtimer that advances the schedule and hence mandatory. */ static int taprio_parse_clockid(struct Qdisc *sch, struct nlattr **tb, struct netlink_ext_ack *extack) { struct taprio_sched *q = qdisc_priv(sch); struct net_device *dev = qdisc_dev(sch); int err = -EINVAL; if (FULL_OFFLOAD_IS_ENABLED(q->flags)) { const struct ethtool_ops *ops = dev->ethtool_ops; struct kernel_ethtool_ts_info info = { .cmd = ETHTOOL_GET_TS_INFO, .phc_index = -1, }; if (tb[TCA_TAPRIO_ATTR_SCHED_CLOCKID]) { NL_SET_ERR_MSG(extack, "The 'clockid' cannot be specified for full offload"); goto out; } if (ops && ops->get_ts_info) err = ops->get_ts_info(dev, &info); if (err || info.phc_index < 0) { NL_SET_ERR_MSG(extack, "Device does not have a PTP clock"); err = -ENOTSUPP; goto out; } } else if (tb[TCA_TAPRIO_ATTR_SCHED_CLOCKID]) { int clockid = nla_get_s32(tb[TCA_TAPRIO_ATTR_SCHED_CLOCKID]); enum tk_offsets tk_offset; /* We only support static clockids and we don't allow * for it to be modified after the first init. */ if (clockid < 0 || (q->clockid != -1 && q->clockid != clockid)) { NL_SET_ERR_MSG(extack, "Changing the 'clockid' of a running schedule is not supported"); err = -ENOTSUPP; goto out; } switch (clockid) { case CLOCK_REALTIME: tk_offset = TK_OFFS_REAL; break; case CLOCK_MONOTONIC: tk_offset = TK_OFFS_MAX; break; case CLOCK_BOOTTIME: tk_offset = TK_OFFS_BOOT; break; case CLOCK_TAI: tk_offset = TK_OFFS_TAI; break; default: NL_SET_ERR_MSG(extack, "Invalid 'clockid'"); err = -EINVAL; goto out; } /* This pairs with READ_ONCE() in taprio_mono_to_any */ WRITE_ONCE(q->tk_offset, tk_offset); q->clockid = clockid; } else { NL_SET_ERR_MSG(extack, "Specifying a 'clockid' is mandatory"); goto out; } /* Everything went ok, return success. */ err = 0; out: return err; } static int taprio_parse_tc_entry(struct Qdisc *sch, struct nlattr *opt, u32 max_sdu[TC_QOPT_MAX_QUEUE], u32 fp[TC_QOPT_MAX_QUEUE], unsigned long *seen_tcs, struct netlink_ext_ack *extack) { struct nlattr *tb[TCA_TAPRIO_TC_ENTRY_MAX + 1] = { }; struct net_device *dev = qdisc_dev(sch); int err, tc; u32 val; err = nla_parse_nested(tb, TCA_TAPRIO_TC_ENTRY_MAX, opt, taprio_tc_policy, extack); if (err < 0) return err; if (!tb[TCA_TAPRIO_TC_ENTRY_INDEX]) { NL_SET_ERR_MSG_MOD(extack, "TC entry index missing"); return -EINVAL; } tc = nla_get_u32(tb[TCA_TAPRIO_TC_ENTRY_INDEX]); if (tc >= TC_QOPT_MAX_QUEUE) { NL_SET_ERR_MSG_MOD(extack, "TC entry index out of range"); return -ERANGE; } if (*seen_tcs & BIT(tc)) { NL_SET_ERR_MSG_MOD(extack, "Duplicate TC entry"); return -EINVAL; } *seen_tcs |= BIT(tc); if (tb[TCA_TAPRIO_TC_ENTRY_MAX_SDU]) { val = nla_get_u32(tb[TCA_TAPRIO_TC_ENTRY_MAX_SDU]); if (val > dev->max_mtu) { NL_SET_ERR_MSG_MOD(extack, "TC max SDU exceeds device max MTU"); return -ERANGE; } max_sdu[tc] = val; } if (tb[TCA_TAPRIO_TC_ENTRY_FP]) fp[tc] = nla_get_u32(tb[TCA_TAPRIO_TC_ENTRY_FP]); return 0; } static int taprio_parse_tc_entries(struct Qdisc *sch, struct nlattr *opt, struct netlink_ext_ack *extack) { struct taprio_sched *q = qdisc_priv(sch); struct net_device *dev = qdisc_dev(sch); u32 max_sdu[TC_QOPT_MAX_QUEUE]; bool have_preemption = false; unsigned long seen_tcs = 0; u32 fp[TC_QOPT_MAX_QUEUE]; struct nlattr *n; int tc, rem; int err = 0; for (tc = 0; tc < TC_QOPT_MAX_QUEUE; tc++) { max_sdu[tc] = q->max_sdu[tc]; fp[tc] = q->fp[tc]; } nla_for_each_nested_type(n, TCA_TAPRIO_ATTR_TC_ENTRY, opt, rem) { err = taprio_parse_tc_entry(sch, n, max_sdu, fp, &seen_tcs, extack); if (err) return err; } for (tc = 0; tc < TC_QOPT_MAX_QUEUE; tc++) { q->max_sdu[tc] = max_sdu[tc]; q->fp[tc] = fp[tc]; if (fp[tc] != TC_FP_EXPRESS) have_preemption = true; } if (have_preemption) { if (!FULL_OFFLOAD_IS_ENABLED(q->flags)) { NL_SET_ERR_MSG(extack, "Preemption only supported with full offload"); return -EOPNOTSUPP; } if (!ethtool_dev_mm_supported(dev)) { NL_SET_ERR_MSG(extack, "Device does not support preemption"); return -EOPNOTSUPP; } } return err; } static int taprio_mqprio_cmp(const struct net_device *dev, const struct tc_mqprio_qopt *mqprio) { int i; if (!mqprio || mqprio->num_tc != dev->num_tc) return -1; for (i = 0; i < mqprio->num_tc; i++) if (dev->tc_to_txq[i].count != mqprio->count[i] || dev->tc_to_txq[i].offset != mqprio->offset[i]) return -1; for (i = 0; i <= TC_BITMASK; i++) if (dev->prio_tc_map[i] != mqprio->prio_tc_map[i]) return -1; return 0; } static int taprio_change(struct Qdisc *sch, struct nlattr *opt, struct netlink_ext_ack *extack) { struct qdisc_size_table *stab = rtnl_dereference(sch->stab); struct nlattr *tb[TCA_TAPRIO_ATTR_MAX + 1] = { }; struct sched_gate_list *oper, *admin, *new_admin; struct taprio_sched *q = qdisc_priv(sch); struct net_device *dev = qdisc_dev(sch); struct tc_mqprio_qopt *mqprio = NULL; unsigned long flags; u32 taprio_flags; ktime_t start; int i, err; err = nla_parse_nested_deprecated(tb, TCA_TAPRIO_ATTR_MAX, opt, taprio_policy, extack); if (err < 0) return err; if (tb[TCA_TAPRIO_ATTR_PRIOMAP]) mqprio = nla_data(tb[TCA_TAPRIO_ATTR_PRIOMAP]); /* The semantics of the 'flags' argument in relation to 'change()' * requests, are interpreted following two rules (which are applied in * this order): (1) an omitted 'flags' argument is interpreted as * zero; (2) the 'flags' of a "running" taprio instance cannot be * changed. */ taprio_flags = nla_get_u32_default(tb[TCA_TAPRIO_ATTR_FLAGS], 0); /* txtime-assist and full offload are mutually exclusive */ if ((taprio_flags & TCA_TAPRIO_ATTR_FLAG_TXTIME_ASSIST) && (taprio_flags & TCA_TAPRIO_ATTR_FLAG_FULL_OFFLOAD)) { NL_SET_ERR_MSG_ATTR(extack, tb[TCA_TAPRIO_ATTR_FLAGS], "TXTIME_ASSIST and FULL_OFFLOAD are mutually exclusive"); return -EINVAL; } if (q->flags != TAPRIO_FLAGS_INVALID && q->flags != taprio_flags) { NL_SET_ERR_MSG_MOD(extack, "Changing 'flags' of a running schedule is not supported"); return -EOPNOTSUPP; } q->flags = taprio_flags; /* Needed for length_to_duration() during netlink attribute parsing */ taprio_set_picos_per_byte(dev, q); err = taprio_parse_mqprio_opt(dev, mqprio, extack, q->flags); if (err < 0) return err; err = taprio_parse_tc_entries(sch, opt, extack); if (err) return err; new_admin = kzalloc(sizeof(*new_admin), GFP_KERNEL); if (!new_admin) { NL_SET_ERR_MSG(extack, "Not enough memory for a new schedule"); return -ENOMEM; } INIT_LIST_HEAD(&new_admin->entries); oper = rtnl_dereference(q->oper_sched); admin = rtnl_dereference(q->admin_sched); /* no changes - no new mqprio settings */ if (!taprio_mqprio_cmp(dev, mqprio)) mqprio = NULL; if (mqprio && (oper || admin)) { NL_SET_ERR_MSG(extack, "Changing the traffic mapping of a running schedule is not supported"); err = -ENOTSUPP; goto free_sched; } if (mqprio) { err = netdev_set_num_tc(dev, mqprio->num_tc); if (err) goto free_sched; for (i = 0; i < mqprio->num_tc; i++) { netdev_set_tc_queue(dev, i, mqprio->count[i], mqprio->offset[i]); q->cur_txq[i] = mqprio->offset[i]; } /* Always use supplied priority mappings */ for (i = 0; i <= TC_BITMASK; i++) netdev_set_prio_tc_map(dev, i, mqprio->prio_tc_map[i]); } err = parse_taprio_schedule(q, tb, new_admin, extack); if (err < 0) goto free_sched; if (new_admin->num_entries == 0) { NL_SET_ERR_MSG(extack, "There should be at least one entry in the schedule"); err = -EINVAL; goto free_sched; } err = taprio_parse_clockid(sch, tb, extack); if (err < 0) goto free_sched; taprio_update_queue_max_sdu(q, new_admin, stab); if (FULL_OFFLOAD_IS_ENABLED(q->flags)) err = taprio_enable_offload(dev, q, new_admin, extack); else err = taprio_disable_offload(dev, q, extack); if (err) goto free_sched; /* Protects against enqueue()/dequeue() */ spin_lock_bh(qdisc_lock(sch)); if (tb[TCA_TAPRIO_ATTR_TXTIME_DELAY]) { if (!TXTIME_ASSIST_IS_ENABLED(q->flags)) { NL_SET_ERR_MSG_MOD(extack, "txtime-delay can only be set when txtime-assist mode is enabled"); err = -EINVAL; goto unlock; } q->txtime_delay = nla_get_u32(tb[TCA_TAPRIO_ATTR_TXTIME_DELAY]); } if (!TXTIME_ASSIST_IS_ENABLED(q->flags) && !FULL_OFFLOAD_IS_ENABLED(q->flags) && !hrtimer_active(&q->advance_timer)) { hrtimer_init(&q->advance_timer, q->clockid, HRTIMER_MODE_ABS); q->advance_timer.function = advance_sched; } err = taprio_get_start_time(sch, new_admin, &start); if (err < 0) { NL_SET_ERR_MSG(extack, "Internal error: failed get start time"); goto unlock; } setup_txtime(q, new_admin, start); if (TXTIME_ASSIST_IS_ENABLED(q->flags)) { if (!oper) { rcu_assign_pointer(q->oper_sched, new_admin); err = 0; new_admin = NULL; goto unlock; } /* Not going to race against advance_sched(), but still */ admin = rcu_replace_pointer(q->admin_sched, new_admin, lockdep_rtnl_is_held()); if (admin) call_rcu(&admin->rcu, taprio_free_sched_cb); } else { setup_first_end_time(q, new_admin, start); /* Protects against advance_sched() */ spin_lock_irqsave(&q->current_entry_lock, flags); taprio_start_sched(sch, start, new_admin); admin = rcu_replace_pointer(q->admin_sched, new_admin, lockdep_rtnl_is_held()); if (admin) call_rcu(&admin->rcu, taprio_free_sched_cb); spin_unlock_irqrestore(&q->current_entry_lock, flags); if (FULL_OFFLOAD_IS_ENABLED(q->flags)) taprio_offload_config_changed(q); } new_admin = NULL; err = 0; if (!stab) NL_SET_ERR_MSG_MOD(extack, "Size table not specified, frame length estimations may be inaccurate"); unlock: spin_unlock_bh(qdisc_lock(sch)); free_sched: if (new_admin) call_rcu(&new_admin->rcu, taprio_free_sched_cb); return err; } static void taprio_reset(struct Qdisc *sch) { struct taprio_sched *q = qdisc_priv(sch); struct net_device *dev = qdisc_dev(sch); int i; hrtimer_cancel(&q->advance_timer); if (q->qdiscs) { for (i = 0; i < dev->num_tx_queues; i++) if (q->qdiscs[i]) qdisc_reset(q->qdiscs[i]); } } static void taprio_destroy(struct Qdisc *sch) { struct taprio_sched *q = qdisc_priv(sch); struct net_device *dev = qdisc_dev(sch); struct sched_gate_list *oper, *admin; unsigned int i; list_del(&q->taprio_list); /* Note that taprio_reset() might not be called if an error * happens in qdisc_create(), after taprio_init() has been called. */ hrtimer_cancel(&q->advance_timer); qdisc_synchronize(sch); taprio_disable_offload(dev, q, NULL); if (q->qdiscs) { for (i = 0; i < dev->num_tx_queues; i++) qdisc_put(q->qdiscs[i]); kfree(q->qdiscs); } q->qdiscs = NULL; netdev_reset_tc(dev); oper = rtnl_dereference(q->oper_sched); admin = rtnl_dereference(q->admin_sched); if (oper) call_rcu(&oper->rcu, taprio_free_sched_cb); if (admin) call_rcu(&admin->rcu, taprio_free_sched_cb); taprio_cleanup_broken_mqprio(q); } static int taprio_init(struct Qdisc *sch, struct nlattr *opt, struct netlink_ext_ack *extack) { struct taprio_sched *q = qdisc_priv(sch); struct net_device *dev = qdisc_dev(sch); int i, tc; spin_lock_init(&q->current_entry_lock); hrtimer_init(&q->advance_timer, CLOCK_TAI, HRTIMER_MODE_ABS); q->advance_timer.function = advance_sched; q->root = sch; /* We only support static clockids. Use an invalid value as default * and get the valid one on taprio_change(). */ q->clockid = -1; q->flags = TAPRIO_FLAGS_INVALID; list_add(&q->taprio_list, &taprio_list); if (sch->parent != TC_H_ROOT) { NL_SET_ERR_MSG_MOD(extack, "Can only be attached as root qdisc"); return -EOPNOTSUPP; } if (!netif_is_multiqueue(dev)) { NL_SET_ERR_MSG_MOD(extack, "Multi-queue device is required"); return -EOPNOTSUPP; } q->qdiscs = kcalloc(dev->num_tx_queues, sizeof(q->qdiscs[0]), GFP_KERNEL); if (!q->qdiscs) return -ENOMEM; if (!opt) return -EINVAL; for (i = 0; i < dev->num_tx_queues; i++) { struct netdev_queue *dev_queue; struct Qdisc *qdisc; dev_queue = netdev_get_tx_queue(dev, i); qdisc = qdisc_create_dflt(dev_queue, &pfifo_qdisc_ops, TC_H_MAKE(TC_H_MAJ(sch->handle), TC_H_MIN(i + 1)), extack); if (!qdisc) return -ENOMEM; if (i < dev->real_num_tx_queues) qdisc_hash_add(qdisc, false); q->qdiscs[i] = qdisc; } for (tc = 0; tc < TC_QOPT_MAX_QUEUE; tc++) q->fp[tc] = TC_FP_EXPRESS; taprio_detect_broken_mqprio(q); return taprio_change(sch, opt, extack); } static void taprio_attach(struct Qdisc *sch) { struct taprio_sched *q = qdisc_priv(sch); struct net_device *dev = qdisc_dev(sch); unsigned int ntx; /* Attach underlying qdisc */ for (ntx = 0; ntx < dev->num_tx_queues; ntx++) { struct netdev_queue *dev_queue = netdev_get_tx_queue(dev, ntx); struct Qdisc *old, *dev_queue_qdisc; if (FULL_OFFLOAD_IS_ENABLED(q->flags)) { struct Qdisc *qdisc = q->qdiscs[ntx]; /* In offload mode, the root taprio qdisc is bypassed * and the netdev TX queues see the children directly */ qdisc->flags |= TCQ_F_ONETXQUEUE | TCQ_F_NOPARENT; dev_queue_qdisc = qdisc; } else { /* In software mode, attach the root taprio qdisc * to all netdev TX queues, so that dev_qdisc_enqueue() * goes through taprio_enqueue(). */ dev_queue_qdisc = sch; } old = dev_graft_qdisc(dev_queue, dev_queue_qdisc); /* The qdisc's refcount requires to be elevated once * for each netdev TX queue it is grafted onto */ qdisc_refcount_inc(dev_queue_qdisc); if (old) qdisc_put(old); } } static struct netdev_queue *taprio_queue_get(struct Qdisc *sch, unsigned long cl) { struct net_device *dev = qdisc_dev(sch); unsigned long ntx = cl - 1; if (ntx >= dev->num_tx_queues) return NULL; return netdev_get_tx_queue(dev, ntx); } static int taprio_graft(struct Qdisc *sch, unsigned long cl, struct Qdisc *new, struct Qdisc **old, struct netlink_ext_ack *extack) { struct taprio_sched *q = qdisc_priv(sch); struct net_device *dev = qdisc_dev(sch); struct netdev_queue *dev_queue = taprio_queue_get(sch, cl); if (!dev_queue) return -EINVAL; if (dev->flags & IFF_UP) dev_deactivate(dev); /* In offload mode, the child Qdisc is directly attached to the netdev * TX queue, and thus, we need to keep its refcount elevated in order * to counteract qdisc_graft()'s call to qdisc_put() once per TX queue. * However, save the reference to the new qdisc in the private array in * both software and offload cases, to have an up-to-date reference to * our children. */ *old = q->qdiscs[cl - 1]; if (FULL_OFFLOAD_IS_ENABLED(q->flags)) { WARN_ON_ONCE(dev_graft_qdisc(dev_queue, new) != *old); if (new) qdisc_refcount_inc(new); if (*old) qdisc_put(*old); } q->qdiscs[cl - 1] = new; if (new) new->flags |= TCQ_F_ONETXQUEUE | TCQ_F_NOPARENT; if (dev->flags & IFF_UP) dev_activate(dev); return 0; } static int dump_entry(struct sk_buff *msg, const struct sched_entry *entry) { struct nlattr *item; item = nla_nest_start_noflag(msg, TCA_TAPRIO_SCHED_ENTRY); if (!item) return -ENOSPC; if (nla_put_u32(msg, TCA_TAPRIO_SCHED_ENTRY_INDEX, entry->index)) goto nla_put_failure; if (nla_put_u8(msg, TCA_TAPRIO_SCHED_ENTRY_CMD, entry->command)) goto nla_put_failure; if (nla_put_u32(msg, TCA_TAPRIO_SCHED_ENTRY_GATE_MASK, entry->gate_mask)) goto nla_put_failure; if (nla_put_u32(msg, TCA_TAPRIO_SCHED_ENTRY_INTERVAL, entry->interval)) goto nla_put_failure; return nla_nest_end(msg, item); nla_put_failure: nla_nest_cancel(msg, item); return -1; } static int dump_schedule(struct sk_buff *msg, const struct sched_gate_list *root) { struct nlattr *entry_list; struct sched_entry *entry; if (nla_put_s64(msg, TCA_TAPRIO_ATTR_SCHED_BASE_TIME, root->base_time, TCA_TAPRIO_PAD)) return -1; if (nla_put_s64(msg, TCA_TAPRIO_ATTR_SCHED_CYCLE_TIME, root->cycle_time, TCA_TAPRIO_PAD)) return -1; if (nla_put_s64(msg, TCA_TAPRIO_ATTR_SCHED_CYCLE_TIME_EXTENSION, root->cycle_time_extension, TCA_TAPRIO_PAD)) return -1; entry_list = nla_nest_start_noflag(msg, TCA_TAPRIO_ATTR_SCHED_ENTRY_LIST); if (!entry_list) goto error_nest; list_for_each_entry(entry, &root->entries, list) { if (dump_entry(msg, entry) < 0) goto error_nest; } nla_nest_end(msg, entry_list); return 0; error_nest: nla_nest_cancel(msg, entry_list); return -1; } static int taprio_dump_tc_entries(struct sk_buff *skb, struct taprio_sched *q, struct sched_gate_list *sched) { struct nlattr *n; int tc; for (tc = 0; tc < TC_MAX_QUEUE; tc++) { n = nla_nest_start(skb, TCA_TAPRIO_ATTR_TC_ENTRY); if (!n) return -EMSGSIZE; if (nla_put_u32(skb, TCA_TAPRIO_TC_ENTRY_INDEX, tc)) goto nla_put_failure; if (nla_put_u32(skb, TCA_TAPRIO_TC_ENTRY_MAX_SDU, sched->max_sdu[tc])) goto nla_put_failure; if (nla_put_u32(skb, TCA_TAPRIO_TC_ENTRY_FP, q->fp[tc])) goto nla_put_failure; nla_nest_end(skb, n); } return 0; nla_put_failure: nla_nest_cancel(skb, n); return -EMSGSIZE; } static int taprio_put_stat(struct sk_buff *skb, u64 val, u16 attrtype) { if (val == TAPRIO_STAT_NOT_SET) return 0; if (nla_put_u64_64bit(skb, attrtype, val, TCA_TAPRIO_OFFLOAD_STATS_PAD)) return -EMSGSIZE; return 0; } static int taprio_dump_xstats(struct Qdisc *sch, struct gnet_dump *d, struct tc_taprio_qopt_offload *offload, struct tc_taprio_qopt_stats *stats) { struct net_device *dev = qdisc_dev(sch); const struct net_device_ops *ops; struct sk_buff *skb = d->skb; struct nlattr *xstats; int err; ops = qdisc_dev(sch)->netdev_ops; /* FIXME I could use qdisc_offload_dump_helper(), but that messes * with sch->flags depending on whether the device reports taprio * stats, and I'm not sure whether that's a good idea, considering * that stats are optional to the offload itself */ if (!ops->ndo_setup_tc) return 0; memset(stats, 0xff, sizeof(*stats)); err = ops->ndo_setup_tc(dev, TC_SETUP_QDISC_TAPRIO, offload); if (err == -EOPNOTSUPP) return 0; if (err) return err; xstats = nla_nest_start(skb, TCA_STATS_APP); if (!xstats) goto err; if (taprio_put_stat(skb, stats->window_drops, TCA_TAPRIO_OFFLOAD_STATS_WINDOW_DROPS) || taprio_put_stat(skb, stats->tx_overruns, TCA_TAPRIO_OFFLOAD_STATS_TX_OVERRUNS)) goto err_cancel; nla_nest_end(skb, xstats); return 0; err_cancel: nla_nest_cancel(skb, xstats); err: return -EMSGSIZE; } static int taprio_dump_stats(struct Qdisc *sch, struct gnet_dump *d) { struct tc_taprio_qopt_offload offload = { .cmd = TAPRIO_CMD_STATS, }; return taprio_dump_xstats(sch, d, &offload, &offload.stats); } static int taprio_dump(struct Qdisc *sch, struct sk_buff *skb) { struct taprio_sched *q = qdisc_priv(sch); struct net_device *dev = qdisc_dev(sch); struct sched_gate_list *oper, *admin; struct tc_mqprio_qopt opt = { 0 }; struct nlattr *nest, *sched_nest; mqprio_qopt_reconstruct(dev, &opt); nest = nla_nest_start_noflag(skb, TCA_OPTIONS); if (!nest) goto start_error; if (nla_put(skb, TCA_TAPRIO_ATTR_PRIOMAP, sizeof(opt), &opt)) goto options_error; if (!FULL_OFFLOAD_IS_ENABLED(q->flags) && nla_put_s32(skb, TCA_TAPRIO_ATTR_SCHED_CLOCKID, q->clockid)) goto options_error; if (q->flags && nla_put_u32(skb, TCA_TAPRIO_ATTR_FLAGS, q->flags)) goto options_error; if (q->txtime_delay && nla_put_u32(skb, TCA_TAPRIO_ATTR_TXTIME_DELAY, q->txtime_delay)) goto options_error; rcu_read_lock(); oper = rtnl_dereference(q->oper_sched); admin = rtnl_dereference(q->admin_sched); if (oper && taprio_dump_tc_entries(skb, q, oper)) goto options_error_rcu; if (oper && dump_schedule(skb, oper)) goto options_error_rcu; if (!admin) goto done; sched_nest = nla_nest_start_noflag(skb, TCA_TAPRIO_ATTR_ADMIN_SCHED); if (!sched_nest) goto options_error_rcu; if (dump_schedule(skb, admin)) goto admin_error; nla_nest_end(skb, sched_nest); done: rcu_read_unlock(); return nla_nest_end(skb, nest); admin_error: nla_nest_cancel(skb, sched_nest); options_error_rcu: rcu_read_unlock(); options_error: nla_nest_cancel(skb, nest); start_error: return -ENOSPC; } static struct Qdisc *taprio_leaf(struct Qdisc *sch, unsigned long cl) { struct taprio_sched *q = qdisc_priv(sch); struct net_device *dev = qdisc_dev(sch); unsigned int ntx = cl - 1; if (ntx >= dev->num_tx_queues) return NULL; return q->qdiscs[ntx]; } static unsigned long taprio_find(struct Qdisc *sch, u32 classid) { unsigned int ntx = TC_H_MIN(classid); if (!taprio_queue_get(sch, ntx)) return 0; return ntx; } static int taprio_dump_class(struct Qdisc *sch, unsigned long cl, struct sk_buff *skb, struct tcmsg *tcm) { struct Qdisc *child = taprio_leaf(sch, cl); tcm->tcm_parent = TC_H_ROOT; tcm->tcm_handle |= TC_H_MIN(cl); tcm->tcm_info = child->handle; return 0; } static int taprio_dump_class_stats(struct Qdisc *sch, unsigned long cl, struct gnet_dump *d) __releases(d->lock) __acquires(d->lock) { struct Qdisc *child = taprio_leaf(sch, cl); struct tc_taprio_qopt_offload offload = { .cmd = TAPRIO_CMD_QUEUE_STATS, .queue_stats = { .queue = cl - 1, }, }; if (gnet_stats_copy_basic(d, NULL, &child->bstats, true) < 0 || qdisc_qstats_copy(d, child) < 0) return -1; return taprio_dump_xstats(sch, d, &offload, &offload.queue_stats.stats); } static void taprio_walk(struct Qdisc *sch, struct qdisc_walker *arg) { struct net_device *dev = qdisc_dev(sch); unsigned long ntx; if (arg->stop) return; arg->count = arg->skip; for (ntx = arg->skip; ntx < dev->num_tx_queues; ntx++) { if (!tc_qdisc_stats_dump(sch, ntx + 1, arg)) break; } } static struct netdev_queue *taprio_select_queue(struct Qdisc *sch, struct tcmsg *tcm) { return taprio_queue_get(sch, TC_H_MIN(tcm->tcm_parent)); } static const struct Qdisc_class_ops taprio_class_ops = { .graft = taprio_graft, .leaf = taprio_leaf, .find = taprio_find, .walk = taprio_walk, .dump = taprio_dump_class, .dump_stats = taprio_dump_class_stats, .select_queue = taprio_select_queue, }; static struct Qdisc_ops taprio_qdisc_ops __read_mostly = { .cl_ops = &taprio_class_ops, .id = "taprio", .priv_size = sizeof(struct taprio_sched), .init = taprio_init, .change = taprio_change, .destroy = taprio_destroy, .reset = taprio_reset, .attach = taprio_attach, .peek = taprio_peek, .dequeue = taprio_dequeue, .enqueue = taprio_enqueue, .dump = taprio_dump, .dump_stats = taprio_dump_stats, .owner = THIS_MODULE, }; MODULE_ALIAS_NET_SCH("taprio"); static struct notifier_block taprio_device_notifier = { .notifier_call = taprio_dev_notifier, }; static int __init taprio_module_init(void) { int err = register_netdevice_notifier(&taprio_device_notifier); if (err) return err; return register_qdisc(&taprio_qdisc_ops); } static void __exit taprio_module_exit(void) { unregister_qdisc(&taprio_qdisc_ops); unregister_netdevice_notifier(&taprio_device_notifier); } module_init(taprio_module_init); module_exit(taprio_module_exit); MODULE_LICENSE("GPL"); MODULE_DESCRIPTION("Time Aware Priority qdisc"); |
| 3 3 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 1522 1523 1524 1525 1526 1527 1528 1529 1530 1531 1532 1533 1534 1535 1536 1537 1538 1539 1540 1541 1542 1543 1544 1545 1546 1547 1548 1549 1550 1551 1552 1553 1554 1555 1556 1557 1558 1559 1560 1561 1562 1563 1564 1565 1566 1567 1568 1569 1570 1571 1572 1573 1574 1575 1576 1577 1578 1579 1580 1581 1582 1583 1584 1585 1586 1587 1588 1589 1590 1591 1592 1593 1594 1595 1596 1597 1598 1599 1600 1601 1602 1603 1604 1605 1606 1607 1608 1609 1610 1611 1612 1613 1614 1615 1616 1617 1618 1619 1620 1621 1622 1623 1624 1625 1626 1627 1628 1629 1630 1631 1632 1633 1634 1635 1636 1637 1638 1639 1640 1641 1642 1643 1644 1645 1646 1647 1648 1649 1650 1651 1652 1653 1654 1655 1656 1657 1658 1659 1660 1661 1662 1663 1664 1665 1666 1667 1668 1669 1670 1671 1672 1673 1674 1675 1676 1677 1678 1679 1680 1681 1682 1683 1684 1685 1686 1687 1688 1689 1690 1691 1692 1693 1694 1695 1696 1697 1698 1699 1700 1701 1702 1703 1704 1705 1706 1707 1708 1709 1710 1711 1712 1713 1714 1715 1716 1717 1718 1719 1720 1721 1722 1723 1724 1725 1726 1727 1728 1729 1730 1731 1732 1733 1734 1735 1736 1737 1738 1739 1740 1741 1742 1743 1744 1745 1746 1747 1748 1749 1750 1751 1752 1753 1754 1755 1756 1757 1758 1759 1760 1761 1762 1763 1764 1765 1766 1767 1768 1769 1770 1771 1772 1773 1774 1775 1776 1777 1778 1779 1780 1781 1782 1783 1784 1785 1786 1787 1788 1789 1790 1791 1792 1793 1794 1795 1796 1797 1798 1799 1800 1801 1802 1803 1804 1805 1806 1807 1808 1809 1810 1811 1812 1813 1814 1815 1816 1817 1818 1819 1820 1821 1822 1823 1824 1825 1826 1827 1828 1829 1830 1831 1832 1833 1834 1835 1836 1837 1838 1839 1840 1841 1842 1843 1844 1845 1846 1847 1848 1849 1850 1851 1852 1853 1854 1855 1856 1857 1858 1859 1860 1861 1862 1863 1864 1865 1866 1867 1868 1869 1870 1871 1872 1873 1874 1875 1876 1877 1878 1879 1880 1881 1882 1883 1884 1885 1886 1887 1888 1889 1890 1891 1892 1893 1894 1895 1896 1897 1898 1899 1900 1901 1902 1903 1904 1905 1906 1907 1908 1909 1910 1911 1912 1913 1914 1915 1916 1917 1918 1919 1920 1921 1922 1923 1924 1925 1926 1927 1928 1929 1930 1931 1932 1933 1934 1935 1936 1937 1938 1939 1940 1941 1942 1943 1944 1945 1946 1947 1948 1949 1950 1951 1952 1953 1954 1955 1956 1957 1958 1959 1960 1961 1962 1963 1964 1965 1966 1967 1968 1969 1970 1971 1972 1973 1974 1975 1976 1977 1978 1979 1980 1981 1982 1983 1984 1985 1986 1987 1988 1989 1990 1991 1992 1993 1994 1995 1996 1997 1998 1999 2000 2001 2002 2003 2004 2005 2006 2007 2008 2009 2010 2011 2012 2013 2014 2015 2016 2017 2018 2019 2020 2021 2022 2023 2024 2025 2026 2027 2028 2029 2030 2031 2032 2033 2034 2035 2036 2037 2038 2039 2040 2041 2042 2043 2044 2045 2046 2047 2048 2049 2050 2051 2052 2053 2054 2055 2056 2057 2058 2059 2060 2061 2062 2063 2064 2065 2066 2067 2068 2069 2070 2071 2072 2073 2074 2075 2076 2077 2078 2079 2080 2081 2082 2083 2084 2085 2086 2087 2088 2089 2090 2091 2092 2093 2094 2095 2096 2097 2098 2099 2100 2101 2102 2103 2104 2105 2106 2107 2108 2109 2110 2111 2112 2113 2114 2115 2116 2117 2118 2119 2120 2121 2122 2123 2124 2125 2126 2127 2128 2129 2130 2131 2132 2133 2134 2135 2136 2137 2138 2139 2140 2141 2142 2143 2144 2145 2146 2147 2148 2149 2150 2151 2152 2153 2154 2155 2156 2157 2158 2159 2160 2161 2162 2163 2164 2165 2166 2167 2168 2169 2170 2171 2172 2173 2174 2175 2176 2177 2178 2179 2180 2181 2182 2183 2184 2185 2186 2187 2188 2189 2190 2191 2192 2193 2194 2195 2196 2197 2198 2199 2200 2201 2202 2203 2204 2205 2206 2207 2208 2209 2210 2211 2212 2213 2214 2215 2216 2217 2218 2219 2220 2221 2222 2223 2224 2225 2226 2227 2228 2229 2230 2231 2232 2233 2234 2235 2236 2237 2238 2239 2240 2241 2242 2243 2244 2245 2246 2247 2248 2249 2250 2251 2252 2253 2254 2255 2256 2257 2258 2259 2260 2261 2262 2263 2264 2265 2266 2267 2268 2269 2270 2271 2272 2273 2274 2275 2276 2277 2278 2279 2280 2281 2282 2283 2284 2285 2286 2287 2288 2289 2290 2291 2292 2293 2294 2295 2296 2297 2298 2299 2300 2301 2302 2303 2304 2305 2306 2307 2308 2309 2310 2311 2312 2313 2314 2315 2316 2317 2318 2319 2320 2321 2322 2323 2324 2325 2326 2327 2328 2329 2330 2331 2332 2333 2334 2335 2336 2337 2338 2339 2340 2341 2342 2343 2344 2345 2346 2347 2348 2349 2350 2351 2352 2353 2354 2355 2356 2357 2358 2359 2360 2361 2362 2363 2364 2365 2366 2367 2368 2369 2370 2371 2372 2373 2374 2375 2376 2377 2378 2379 2380 2381 2382 2383 2384 2385 2386 2387 2388 2389 2390 2391 2392 2393 2394 2395 2396 2397 2398 2399 2400 2401 2402 2403 2404 2405 2406 2407 2408 2409 2410 2411 2412 2413 2414 2415 2416 2417 2418 2419 2420 2421 2422 2423 2424 2425 2426 2427 2428 2429 2430 2431 2432 2433 2434 2435 2436 2437 2438 2439 2440 2441 2442 2443 2444 2445 2446 2447 2448 2449 2450 2451 2452 2453 2454 2455 2456 2457 2458 2459 2460 2461 2462 2463 2464 2465 2466 2467 2468 2469 2470 2471 2472 2473 2474 2475 2476 2477 2478 2479 2480 2481 2482 2483 2484 2485 2486 2487 2488 2489 2490 2491 2492 2493 2494 2495 2496 2497 2498 2499 2500 2501 2502 2503 2504 2505 2506 2507 2508 2509 2510 2511 2512 2513 2514 2515 2516 2517 2518 2519 2520 2521 2522 2523 2524 2525 2526 2527 2528 2529 2530 2531 2532 2533 2534 2535 2536 2537 2538 2539 2540 2541 2542 2543 2544 2545 2546 2547 2548 2549 2550 2551 2552 2553 2554 2555 2556 2557 2558 2559 2560 2561 2562 2563 2564 2565 2566 2567 2568 2569 2570 2571 2572 2573 2574 2575 2576 2577 2578 2579 2580 2581 2582 2583 2584 2585 2586 2587 2588 2589 2590 2591 2592 2593 2594 2595 2596 2597 2598 2599 2600 2601 2602 2603 2604 2605 2606 2607 2608 2609 2610 2611 2612 2613 2614 2615 2616 2617 2618 2619 2620 2621 2622 2623 2624 2625 2626 2627 2628 2629 2630 2631 2632 2633 2634 2635 2636 2637 2638 2639 2640 2641 2642 2643 2644 2645 2646 2647 2648 2649 2650 2651 2652 2653 2654 2655 2656 2657 2658 2659 2660 2661 2662 2663 2664 2665 2666 2667 2668 2669 2670 2671 2672 2673 2674 2675 2676 2677 2678 2679 2680 2681 2682 2683 2684 2685 2686 2687 2688 2689 2690 2691 2692 2693 2694 2695 2696 2697 2698 2699 2700 2701 2702 2703 2704 2705 2706 2707 2708 2709 2710 2711 2712 2713 2714 2715 2716 2717 2718 2719 2720 2721 2722 2723 2724 2725 2726 2727 2728 2729 2730 2731 2732 2733 2734 2735 2736 2737 2738 2739 2740 2741 2742 2743 2744 2745 2746 2747 2748 2749 2750 2751 2752 2753 2754 2755 2756 2757 2758 2759 2760 2761 2762 2763 2764 2765 2766 2767 2768 2769 2770 2771 2772 2773 2774 2775 2776 2777 2778 2779 2780 2781 2782 2783 2784 2785 2786 2787 2788 2789 2790 2791 2792 2793 2794 2795 2796 2797 2798 2799 2800 2801 2802 2803 2804 2805 2806 2807 2808 2809 2810 2811 2812 2813 2814 2815 2816 2817 2818 2819 2820 2821 2822 2823 2824 2825 2826 2827 2828 2829 2830 2831 2832 2833 2834 2835 2836 2837 2838 2839 2840 2841 2842 2843 2844 2845 2846 2847 2848 2849 2850 2851 2852 2853 2854 2855 2856 2857 2858 2859 2860 2861 2862 2863 2864 2865 2866 2867 2868 2869 2870 2871 2872 2873 2874 2875 2876 2877 2878 2879 2880 2881 2882 2883 2884 2885 2886 2887 2888 2889 2890 2891 2892 2893 2894 2895 2896 2897 2898 2899 2900 2901 2902 2903 2904 2905 2906 2907 2908 2909 2910 2911 2912 2913 2914 2915 2916 2917 2918 2919 2920 2921 2922 2923 2924 2925 2926 2927 2928 2929 2930 2931 2932 2933 2934 2935 2936 2937 2938 2939 2940 2941 2942 2943 2944 2945 2946 2947 2948 2949 2950 2951 2952 2953 2954 2955 2956 2957 2958 2959 2960 2961 2962 2963 2964 2965 2966 2967 2968 2969 2970 2971 2972 2973 2974 2975 2976 2977 2978 2979 2980 2981 2982 2983 2984 2985 2986 2987 2988 2989 2990 2991 2992 2993 2994 2995 2996 2997 2998 2999 3000 3001 3002 3003 3004 3005 3006 3007 3008 3009 3010 3011 3012 3013 3014 3015 3016 3017 3018 3019 3020 3021 3022 3023 3024 3025 3026 3027 3028 3029 3030 3031 3032 3033 3034 3035 3036 3037 3038 3039 3040 3041 3042 3043 3044 3045 3046 3047 3048 3049 3050 3051 3052 3053 3054 3055 3056 3057 3058 3059 3060 3061 3062 3063 3064 3065 3066 3067 3068 3069 3070 3071 3072 3073 3074 3075 3076 3077 3078 3079 3080 3081 3082 3083 3084 3085 3086 3087 3088 3089 3090 3091 3092 3093 3094 3095 3096 3097 3098 3099 3100 3101 3102 3103 3104 3105 3106 3107 3108 3109 3110 3111 3112 3113 3114 3115 3116 3117 3118 3119 3120 3121 3122 3123 3124 3125 3126 3127 3128 3129 3130 3131 3132 3133 3134 3135 3136 3137 3138 3139 3140 3141 3142 3143 3144 3145 3146 3147 3148 3149 3150 3151 3152 3153 3154 3155 3156 3157 3158 3159 3160 3161 3162 3163 3164 3165 3166 3167 3168 3169 3170 3171 3172 3173 3174 3175 3176 3177 3178 3179 3180 3181 3182 3183 3184 3185 3186 3187 3188 3189 3190 3191 3192 3193 3194 3195 3196 3197 3198 3199 3200 3201 3202 3203 3204 3205 3206 3207 3208 3209 3210 3211 3212 3213 3214 | // SPDX-License-Identifier: GPL-2.0-or-later /* * IP multicast routing support for mrouted 3.6/3.8 * * (c) 1995 Alan Cox, <alan@lxorguk.ukuu.org.uk> * Linux Consultancy and Custom Driver Development * * Fixes: * Michael Chastain : Incorrect size of copying. * Alan Cox : Added the cache manager code * Alan Cox : Fixed the clone/copy bug and device race. * Mike McLagan : Routing by source * Malcolm Beattie : Buffer handling fixes. * Alexey Kuznetsov : Double buffer free and other fixes. * SVR Anand : Fixed several multicast bugs and problems. * Alexey Kuznetsov : Status, optimisations and more. * Brad Parker : Better behaviour on mrouted upcall * overflow. * Carlos Picoto : PIMv1 Support * Pavlin Ivanov Radoslavov: PIMv2 Registers must checksum only PIM header * Relax this requirement to work with older peers. */ #include <linux/uaccess.h> #include <linux/types.h> #include <linux/cache.h> #include <linux/capability.h> #include <linux/errno.h> #include <linux/mm.h> #include <linux/kernel.h> #include <linux/fcntl.h> #include <linux/stat.h> #include <linux/socket.h> #include <linux/in.h> #include <linux/inet.h> #include <linux/netdevice.h> #include <linux/inetdevice.h> #include <linux/igmp.h> #include <linux/proc_fs.h> #include <linux/seq_file.h> #include <linux/mroute.h> #include <linux/init.h> #include <linux/if_ether.h> #include <linux/slab.h> #include <net/net_namespace.h> #include <net/ip.h> #include <net/protocol.h> #include <linux/skbuff.h> #include <net/route.h> #include <net/icmp.h> #include <net/udp.h> #include <net/raw.h> #include <linux/notifier.h> #include <linux/if_arp.h> #include <linux/netfilter_ipv4.h> #include <linux/compat.h> #include <linux/export.h> #include <linux/rhashtable.h> #include <net/ip_tunnels.h> #include <net/checksum.h> #include <net/netlink.h> #include <net/fib_rules.h> #include <linux/netconf.h> #include <net/rtnh.h> #include <net/inet_dscp.h> #include <linux/nospec.h> struct ipmr_rule { struct fib_rule common; }; struct ipmr_result { struct mr_table *mrt; }; /* Big lock, protecting vif table, mrt cache and mroute socket state. * Note that the changes are semaphored via rtnl_lock. */ static DEFINE_SPINLOCK(mrt_lock); static struct net_device *vif_dev_read(const struct vif_device *vif) { return rcu_dereference(vif->dev); } /* Multicast router control variables */ /* Special spinlock for queue of unresolved entries */ static DEFINE_SPINLOCK(mfc_unres_lock); /* We return to original Alan's scheme. Hash table of resolved * entries is changed only in process context and protected * with weak lock mrt_lock. Queue of unresolved entries is protected * with strong spinlock mfc_unres_lock. * * In this case data path is free of exclusive locks at all. */ static struct kmem_cache *mrt_cachep __ro_after_init; static struct mr_table *ipmr_new_table(struct net *net, u32 id); static void ipmr_free_table(struct mr_table *mrt); static void ip_mr_forward(struct net *net, struct mr_table *mrt, struct net_device *dev, struct sk_buff *skb, struct mfc_cache *cache, int local); static int ipmr_cache_report(const struct mr_table *mrt, struct sk_buff *pkt, vifi_t vifi, int assert); static void mroute_netlink_event(struct mr_table *mrt, struct mfc_cache *mfc, int cmd); static void igmpmsg_netlink_event(const struct mr_table *mrt, struct sk_buff *pkt); static void mroute_clean_tables(struct mr_table *mrt, int flags); static void ipmr_expire_process(struct timer_list *t); #ifdef CONFIG_IP_MROUTE_MULTIPLE_TABLES #define ipmr_for_each_table(mrt, net) \ list_for_each_entry_rcu(mrt, &net->ipv4.mr_tables, list, \ lockdep_rtnl_is_held() || \ list_empty(&net->ipv4.mr_tables)) static bool ipmr_can_free_table(struct net *net) { return !check_net(net) || !net_initialized(net); } static struct mr_table *ipmr_mr_table_iter(struct net *net, struct mr_table *mrt) { struct mr_table *ret; if (!mrt) ret = list_entry_rcu(net->ipv4.mr_tables.next, struct mr_table, list); else ret = list_entry_rcu(mrt->list.next, struct mr_table, list); if (&ret->list == &net->ipv4.mr_tables) return NULL; return ret; } static struct mr_table *__ipmr_get_table(struct net *net, u32 id) { struct mr_table *mrt; ipmr_for_each_table(mrt, net) { if (mrt->id == id) return mrt; } return NULL; } static struct mr_table *ipmr_get_table(struct net *net, u32 id) { struct mr_table *mrt; rcu_read_lock(); mrt = __ipmr_get_table(net, id); rcu_read_unlock(); return mrt; } static int ipmr_fib_lookup(struct net *net, struct flowi4 *flp4, struct mr_table **mrt) { int err; struct ipmr_result res; struct fib_lookup_arg arg = { .result = &res, .flags = FIB_LOOKUP_NOREF, }; /* update flow if oif or iif point to device enslaved to l3mdev */ l3mdev_update_flow(net, flowi4_to_flowi(flp4)); err = fib_rules_lookup(net->ipv4.mr_rules_ops, flowi4_to_flowi(flp4), 0, &arg); if (err < 0) return err; *mrt = res.mrt; return 0; } static int ipmr_rule_action(struct fib_rule *rule, struct flowi *flp, int flags, struct fib_lookup_arg *arg) { struct ipmr_result *res = arg->result; struct mr_table *mrt; switch (rule->action) { case FR_ACT_TO_TBL: break; case FR_ACT_UNREACHABLE: return -ENETUNREACH; case FR_ACT_PROHIBIT: return -EACCES; case FR_ACT_BLACKHOLE: default: return -EINVAL; } arg->table = fib_rule_get_table(rule, arg); mrt = __ipmr_get_table(rule->fr_net, arg->table); if (!mrt) return -EAGAIN; res->mrt = mrt; return 0; } static int ipmr_rule_match(struct fib_rule *rule, struct flowi *fl, int flags) { return 1; } static int ipmr_rule_configure(struct fib_rule *rule, struct sk_buff *skb, struct fib_rule_hdr *frh, struct nlattr **tb, struct netlink_ext_ack *extack) { return 0; } static int ipmr_rule_compare(struct fib_rule *rule, struct fib_rule_hdr *frh, struct nlattr **tb) { return 1; } static int ipmr_rule_fill(struct fib_rule *rule, struct sk_buff *skb, struct fib_rule_hdr *frh) { frh->dst_len = 0; frh->src_len = 0; frh->tos = 0; return 0; } static const struct fib_rules_ops __net_initconst ipmr_rules_ops_template = { .family = RTNL_FAMILY_IPMR, .rule_size = sizeof(struct ipmr_rule), .addr_size = sizeof(u32), .action = ipmr_rule_action, .match = ipmr_rule_match, .configure = ipmr_rule_configure, .compare = ipmr_rule_compare, .fill = ipmr_rule_fill, .nlgroup = RTNLGRP_IPV4_RULE, .owner = THIS_MODULE, }; static int __net_init ipmr_rules_init(struct net *net) { struct fib_rules_ops *ops; struct mr_table *mrt; int err; ops = fib_rules_register(&ipmr_rules_ops_template, net); if (IS_ERR(ops)) return PTR_ERR(ops); INIT_LIST_HEAD(&net->ipv4.mr_tables); mrt = ipmr_new_table(net, RT_TABLE_DEFAULT); if (IS_ERR(mrt)) { err = PTR_ERR(mrt); goto err1; } err = fib_default_rule_add(ops, 0x7fff, RT_TABLE_DEFAULT); if (err < 0) goto err2; net->ipv4.mr_rules_ops = ops; return 0; err2: rtnl_lock(); ipmr_free_table(mrt); rtnl_unlock(); err1: fib_rules_unregister(ops); return err; } static void __net_exit ipmr_rules_exit(struct net *net) { struct mr_table *mrt, *next; ASSERT_RTNL(); list_for_each_entry_safe(mrt, next, &net->ipv4.mr_tables, list) { list_del(&mrt->list); ipmr_free_table(mrt); } fib_rules_unregister(net->ipv4.mr_rules_ops); } static int ipmr_rules_dump(struct net *net, struct notifier_block *nb, struct netlink_ext_ack *extack) { return fib_rules_dump(net, nb, RTNL_FAMILY_IPMR, extack); } static unsigned int ipmr_rules_seq_read(const struct net *net) { return fib_rules_seq_read(net, RTNL_FAMILY_IPMR); } bool ipmr_rule_default(const struct fib_rule *rule) { return fib_rule_matchall(rule) && rule->table == RT_TABLE_DEFAULT; } EXPORT_SYMBOL(ipmr_rule_default); #else #define ipmr_for_each_table(mrt, net) \ for (mrt = net->ipv4.mrt; mrt; mrt = NULL) static bool ipmr_can_free_table(struct net *net) { return !check_net(net); } static struct mr_table *ipmr_mr_table_iter(struct net *net, struct mr_table *mrt) { if (!mrt) return net->ipv4.mrt; return NULL; } static struct mr_table *ipmr_get_table(struct net *net, u32 id) { return net->ipv4.mrt; } #define __ipmr_get_table ipmr_get_table static int ipmr_fib_lookup(struct net *net, struct flowi4 *flp4, struct mr_table **mrt) { *mrt = net->ipv4.mrt; return 0; } static int __net_init ipmr_rules_init(struct net *net) { struct mr_table *mrt; mrt = ipmr_new_table(net, RT_TABLE_DEFAULT); if (IS_ERR(mrt)) return PTR_ERR(mrt); net->ipv4.mrt = mrt; return 0; } static void __net_exit ipmr_rules_exit(struct net *net) { ASSERT_RTNL(); ipmr_free_table(net->ipv4.mrt); net->ipv4.mrt = NULL; } static int ipmr_rules_dump(struct net *net, struct notifier_block *nb, struct netlink_ext_ack *extack) { return 0; } static unsigned int ipmr_rules_seq_read(const struct net *net) { return 0; } bool ipmr_rule_default(const struct fib_rule *rule) { return true; } EXPORT_SYMBOL(ipmr_rule_default); #endif static inline int ipmr_hash_cmp(struct rhashtable_compare_arg *arg, const void *ptr) { const struct mfc_cache_cmp_arg *cmparg = arg->key; const struct mfc_cache *c = ptr; return cmparg->mfc_mcastgrp != c->mfc_mcastgrp || cmparg->mfc_origin != c->mfc_origin; } static const struct rhashtable_params ipmr_rht_params = { .head_offset = offsetof(struct mr_mfc, mnode), .key_offset = offsetof(struct mfc_cache, cmparg), .key_len = sizeof(struct mfc_cache_cmp_arg), .nelem_hint = 3, .obj_cmpfn = ipmr_hash_cmp, .automatic_shrinking = true, }; static void ipmr_new_table_set(struct mr_table *mrt, struct net *net) { #ifdef CONFIG_IP_MROUTE_MULTIPLE_TABLES list_add_tail_rcu(&mrt->list, &net->ipv4.mr_tables); #endif } static struct mfc_cache_cmp_arg ipmr_mr_table_ops_cmparg_any = { .mfc_mcastgrp = htonl(INADDR_ANY), .mfc_origin = htonl(INADDR_ANY), }; static struct mr_table_ops ipmr_mr_table_ops = { .rht_params = &ipmr_rht_params, .cmparg_any = &ipmr_mr_table_ops_cmparg_any, }; static struct mr_table *ipmr_new_table(struct net *net, u32 id) { struct mr_table *mrt; /* "pimreg%u" should not exceed 16 bytes (IFNAMSIZ) */ if (id != RT_TABLE_DEFAULT && id >= 1000000000) return ERR_PTR(-EINVAL); mrt = __ipmr_get_table(net, id); if (mrt) return mrt; return mr_table_alloc(net, id, &ipmr_mr_table_ops, ipmr_expire_process, ipmr_new_table_set); } static void ipmr_free_table(struct mr_table *mrt) { struct net *net = read_pnet(&mrt->net); WARN_ON_ONCE(!ipmr_can_free_table(net)); timer_shutdown_sync(&mrt->ipmr_expire_timer); mroute_clean_tables(mrt, MRT_FLUSH_VIFS | MRT_FLUSH_VIFS_STATIC | MRT_FLUSH_MFC | MRT_FLUSH_MFC_STATIC); rhltable_destroy(&mrt->mfc_hash); kfree(mrt); } /* Service routines creating virtual interfaces: DVMRP tunnels and PIMREG */ /* Initialize ipmr pimreg/tunnel in_device */ static bool ipmr_init_vif_indev(const struct net_device *dev) { struct in_device *in_dev; ASSERT_RTNL(); in_dev = __in_dev_get_rtnl(dev); if (!in_dev) return false; ipv4_devconf_setall(in_dev); neigh_parms_data_state_setall(in_dev->arp_parms); IPV4_DEVCONF(in_dev->cnf, RP_FILTER) = 0; return true; } static struct net_device *ipmr_new_tunnel(struct net *net, struct vifctl *v) { struct net_device *tunnel_dev, *new_dev; struct ip_tunnel_parm_kern p = { }; int err; tunnel_dev = __dev_get_by_name(net, "tunl0"); if (!tunnel_dev) goto out; p.iph.daddr = v->vifc_rmt_addr.s_addr; p.iph.saddr = v->vifc_lcl_addr.s_addr; p.iph.version = 4; p.iph.ihl = 5; p.iph.protocol = IPPROTO_IPIP; sprintf(p.name, "dvmrp%d", v->vifc_vifi); if (!tunnel_dev->netdev_ops->ndo_tunnel_ctl) goto out; err = tunnel_dev->netdev_ops->ndo_tunnel_ctl(tunnel_dev, &p, SIOCADDTUNNEL); if (err) goto out; new_dev = __dev_get_by_name(net, p.name); if (!new_dev) goto out; new_dev->flags |= IFF_MULTICAST; if (!ipmr_init_vif_indev(new_dev)) goto out_unregister; if (dev_open(new_dev, NULL)) goto out_unregister; dev_hold(new_dev); err = dev_set_allmulti(new_dev, 1); if (err) { dev_close(new_dev); tunnel_dev->netdev_ops->ndo_tunnel_ctl(tunnel_dev, &p, SIOCDELTUNNEL); dev_put(new_dev); new_dev = ERR_PTR(err); } return new_dev; out_unregister: unregister_netdevice(new_dev); out: return ERR_PTR(-ENOBUFS); } #if defined(CONFIG_IP_PIMSM_V1) || defined(CONFIG_IP_PIMSM_V2) static netdev_tx_t reg_vif_xmit(struct sk_buff *skb, struct net_device *dev) { struct net *net = dev_net(dev); struct mr_table *mrt; struct flowi4 fl4 = { .flowi4_oif = dev->ifindex, .flowi4_iif = skb->skb_iif ? : LOOPBACK_IFINDEX, .flowi4_mark = skb->mark, }; int err; err = ipmr_fib_lookup(net, &fl4, &mrt); if (err < 0) { kfree_skb(skb); return err; } DEV_STATS_ADD(dev, tx_bytes, skb->len); DEV_STATS_INC(dev, tx_packets); rcu_read_lock(); /* Pairs with WRITE_ONCE() in vif_add() and vif_delete() */ ipmr_cache_report(mrt, skb, READ_ONCE(mrt->mroute_reg_vif_num), IGMPMSG_WHOLEPKT); rcu_read_unlock(); kfree_skb(skb); return NETDEV_TX_OK; } static int reg_vif_get_iflink(const struct net_device *dev) { return 0; } static const struct net_device_ops reg_vif_netdev_ops = { .ndo_start_xmit = reg_vif_xmit, .ndo_get_iflink = reg_vif_get_iflink, }; static void reg_vif_setup(struct net_device *dev) { dev->type = ARPHRD_PIMREG; dev->mtu = ETH_DATA_LEN - sizeof(struct iphdr) - 8; dev->flags = IFF_NOARP; dev->netdev_ops = ®_vif_netdev_ops; dev->needs_free_netdev = true; dev->netns_local = true; } static struct net_device *ipmr_reg_vif(struct net *net, struct mr_table *mrt) { struct net_device *dev; char name[IFNAMSIZ]; if (mrt->id == RT_TABLE_DEFAULT) sprintf(name, "pimreg"); else sprintf(name, "pimreg%u", mrt->id); dev = alloc_netdev(0, name, NET_NAME_UNKNOWN, reg_vif_setup); if (!dev) return NULL; dev_net_set(dev, net); if (register_netdevice(dev)) { free_netdev(dev); return NULL; } if (!ipmr_init_vif_indev(dev)) goto failure; if (dev_open(dev, NULL)) goto failure; dev_hold(dev); return dev; failure: unregister_netdevice(dev); return NULL; } /* called with rcu_read_lock() */ static int __pim_rcv(struct mr_table *mrt, struct sk_buff *skb, unsigned int pimlen) { struct net_device *reg_dev = NULL; struct iphdr *encap; int vif_num; encap = (struct iphdr *)(skb_transport_header(skb) + pimlen); /* Check that: * a. packet is really sent to a multicast group * b. packet is not a NULL-REGISTER * c. packet is not truncated */ if (!ipv4_is_multicast(encap->daddr) || encap->tot_len == 0 || ntohs(encap->tot_len) + pimlen > skb->len) return 1; /* Pairs with WRITE_ONCE() in vif_add()/vid_delete() */ vif_num = READ_ONCE(mrt->mroute_reg_vif_num); if (vif_num >= 0) reg_dev = vif_dev_read(&mrt->vif_table[vif_num]); if (!reg_dev) return 1; skb->mac_header = skb->network_header; skb_pull(skb, (u8 *)encap - skb->data); skb_reset_network_header(skb); skb->protocol = htons(ETH_P_IP); skb->ip_summed = CHECKSUM_NONE; skb_tunnel_rx(skb, reg_dev, dev_net(reg_dev)); netif_rx(skb); return NET_RX_SUCCESS; } #else static struct net_device *ipmr_reg_vif(struct net *net, struct mr_table *mrt) { return NULL; } #endif static int call_ipmr_vif_entry_notifiers(struct net *net, enum fib_event_type event_type, struct vif_device *vif, struct net_device *vif_dev, vifi_t vif_index, u32 tb_id) { return mr_call_vif_notifiers(net, RTNL_FAMILY_IPMR, event_type, vif, vif_dev, vif_index, tb_id, &net->ipv4.ipmr_seq); } static int call_ipmr_mfc_entry_notifiers(struct net *net, enum fib_event_type event_type, struct mfc_cache *mfc, u32 tb_id) { return mr_call_mfc_notifiers(net, RTNL_FAMILY_IPMR, event_type, &mfc->_c, tb_id, &net->ipv4.ipmr_seq); } /** * vif_delete - Delete a VIF entry * @mrt: Table to delete from * @vifi: VIF identifier to delete * @notify: Set to 1, if the caller is a notifier_call * @head: if unregistering the VIF, place it on this queue */ static int vif_delete(struct mr_table *mrt, int vifi, int notify, struct list_head *head) { struct net *net = read_pnet(&mrt->net); struct vif_device *v; struct net_device *dev; struct in_device *in_dev; if (vifi < 0 || vifi >= mrt->maxvif) return -EADDRNOTAVAIL; v = &mrt->vif_table[vifi]; dev = rtnl_dereference(v->dev); if (!dev) return -EADDRNOTAVAIL; spin_lock(&mrt_lock); call_ipmr_vif_entry_notifiers(net, FIB_EVENT_VIF_DEL, v, dev, vifi, mrt->id); RCU_INIT_POINTER(v->dev, NULL); if (vifi == mrt->mroute_reg_vif_num) { /* Pairs with READ_ONCE() in ipmr_cache_report() and reg_vif_xmit() */ WRITE_ONCE(mrt->mroute_reg_vif_num, -1); } if (vifi + 1 == mrt->maxvif) { int tmp; for (tmp = vifi - 1; tmp >= 0; tmp--) { if (VIF_EXISTS(mrt, tmp)) break; } WRITE_ONCE(mrt->maxvif, tmp + 1); } spin_unlock(&mrt_lock); dev_set_allmulti(dev, -1); in_dev = __in_dev_get_rtnl(dev); if (in_dev) { IPV4_DEVCONF(in_dev->cnf, MC_FORWARDING)--; inet_netconf_notify_devconf(dev_net(dev), RTM_NEWNETCONF, NETCONFA_MC_FORWARDING, dev->ifindex, &in_dev->cnf); ip_rt_multicast_event(in_dev); } if (v->flags & (VIFF_TUNNEL | VIFF_REGISTER) && !notify) unregister_netdevice_queue(dev, head); netdev_put(dev, &v->dev_tracker); return 0; } static void ipmr_cache_free_rcu(struct rcu_head *head) { struct mr_mfc *c = container_of(head, struct mr_mfc, rcu); kmem_cache_free(mrt_cachep, (struct mfc_cache *)c); } static void ipmr_cache_free(struct mfc_cache *c) { call_rcu(&c->_c.rcu, ipmr_cache_free_rcu); } /* Destroy an unresolved cache entry, killing queued skbs * and reporting error to netlink readers. */ static void ipmr_destroy_unres(struct mr_table *mrt, struct mfc_cache *c) { struct net *net = read_pnet(&mrt->net); struct sk_buff *skb; struct nlmsgerr *e; atomic_dec(&mrt->cache_resolve_queue_len); while ((skb = skb_dequeue(&c->_c.mfc_un.unres.unresolved))) { if (ip_hdr(skb)->version == 0) { struct nlmsghdr *nlh = skb_pull(skb, sizeof(struct iphdr)); nlh->nlmsg_type = NLMSG_ERROR; nlh->nlmsg_len = nlmsg_msg_size(sizeof(struct nlmsgerr)); skb_trim(skb, nlh->nlmsg_len); e = nlmsg_data(nlh); e->error = -ETIMEDOUT; memset(&e->msg, 0, sizeof(e->msg)); rtnl_unicast(skb, net, NETLINK_CB(skb).portid); } else { kfree_skb(skb); } } ipmr_cache_free(c); } /* Timer process for the unresolved queue. */ static void ipmr_expire_process(struct timer_list *t) { struct mr_table *mrt = from_timer(mrt, t, ipmr_expire_timer); struct mr_mfc *c, *next; unsigned long expires; unsigned long now; if (!spin_trylock(&mfc_unres_lock)) { mod_timer(&mrt->ipmr_expire_timer, jiffies+HZ/10); return; } if (list_empty(&mrt->mfc_unres_queue)) goto out; now = jiffies; expires = 10*HZ; list_for_each_entry_safe(c, next, &mrt->mfc_unres_queue, list) { if (time_after(c->mfc_un.unres.expires, now)) { unsigned long interval = c->mfc_un.unres.expires - now; if (interval < expires) expires = interval; continue; } list_del(&c->list); mroute_netlink_event(mrt, (struct mfc_cache *)c, RTM_DELROUTE); ipmr_destroy_unres(mrt, (struct mfc_cache *)c); } if (!list_empty(&mrt->mfc_unres_queue)) mod_timer(&mrt->ipmr_expire_timer, jiffies + expires); out: spin_unlock(&mfc_unres_lock); } /* Fill oifs list. It is called under locked mrt_lock. */ static void ipmr_update_thresholds(struct mr_table *mrt, struct mr_mfc *cache, unsigned char *ttls) { int vifi; cache->mfc_un.res.minvif = MAXVIFS; cache->mfc_un.res.maxvif = 0; memset(cache->mfc_un.res.ttls, 255, MAXVIFS); for (vifi = 0; vifi < mrt->maxvif; vifi++) { if (VIF_EXISTS(mrt, vifi) && ttls[vifi] && ttls[vifi] < 255) { cache->mfc_un.res.ttls[vifi] = ttls[vifi]; if (cache->mfc_un.res.minvif > vifi) cache->mfc_un.res.minvif = vifi; if (cache->mfc_un.res.maxvif <= vifi) cache->mfc_un.res.maxvif = vifi + 1; } } cache->mfc_un.res.lastuse = jiffies; } static int vif_add(struct net *net, struct mr_table *mrt, struct vifctl *vifc, int mrtsock) { struct netdev_phys_item_id ppid = { }; int vifi = vifc->vifc_vifi; struct vif_device *v = &mrt->vif_table[vifi]; struct net_device *dev; struct in_device *in_dev; int err; /* Is vif busy ? */ if (VIF_EXISTS(mrt, vifi)) return -EADDRINUSE; switch (vifc->vifc_flags) { case VIFF_REGISTER: if (!ipmr_pimsm_enabled()) return -EINVAL; /* Special Purpose VIF in PIM * All the packets will be sent to the daemon */ if (mrt->mroute_reg_vif_num >= 0) return -EADDRINUSE; dev = ipmr_reg_vif(net, mrt); if (!dev) return -ENOBUFS; err = dev_set_allmulti(dev, 1); if (err) { unregister_netdevice(dev); dev_put(dev); return err; } break; case VIFF_TUNNEL: dev = ipmr_new_tunnel(net, vifc); if (IS_ERR(dev)) return PTR_ERR(dev); break; case VIFF_USE_IFINDEX: case 0: if (vifc->vifc_flags == VIFF_USE_IFINDEX) { dev = dev_get_by_index(net, vifc->vifc_lcl_ifindex); if (dev && !__in_dev_get_rtnl(dev)) { dev_put(dev); return -EADDRNOTAVAIL; } } else { dev = ip_dev_find(net, vifc->vifc_lcl_addr.s_addr); } if (!dev) return -EADDRNOTAVAIL; err = dev_set_allmulti(dev, 1); if (err) { dev_put(dev); return err; } break; default: return -EINVAL; } in_dev = __in_dev_get_rtnl(dev); if (!in_dev) { dev_put(dev); return -EADDRNOTAVAIL; } IPV4_DEVCONF(in_dev->cnf, MC_FORWARDING)++; inet_netconf_notify_devconf(net, RTM_NEWNETCONF, NETCONFA_MC_FORWARDING, dev->ifindex, &in_dev->cnf); ip_rt_multicast_event(in_dev); /* Fill in the VIF structures */ vif_device_init(v, dev, vifc->vifc_rate_limit, vifc->vifc_threshold, vifc->vifc_flags | (!mrtsock ? VIFF_STATIC : 0), (VIFF_TUNNEL | VIFF_REGISTER)); err = dev_get_port_parent_id(dev, &ppid, true); if (err == 0) { memcpy(v->dev_parent_id.id, ppid.id, ppid.id_len); v->dev_parent_id.id_len = ppid.id_len; } else { v->dev_parent_id.id_len = 0; } v->local = vifc->vifc_lcl_addr.s_addr; v->remote = vifc->vifc_rmt_addr.s_addr; /* And finish update writing critical data */ spin_lock(&mrt_lock); rcu_assign_pointer(v->dev, dev); netdev_tracker_alloc(dev, &v->dev_tracker, GFP_ATOMIC); if (v->flags & VIFF_REGISTER) { /* Pairs with READ_ONCE() in ipmr_cache_report() and reg_vif_xmit() */ WRITE_ONCE(mrt->mroute_reg_vif_num, vifi); } if (vifi+1 > mrt->maxvif) WRITE_ONCE(mrt->maxvif, vifi + 1); spin_unlock(&mrt_lock); call_ipmr_vif_entry_notifiers(net, FIB_EVENT_VIF_ADD, v, dev, vifi, mrt->id); return 0; } /* called with rcu_read_lock() */ static struct mfc_cache *ipmr_cache_find(struct mr_table *mrt, __be32 origin, __be32 mcastgrp) { struct mfc_cache_cmp_arg arg = { .mfc_mcastgrp = mcastgrp, .mfc_origin = origin }; return mr_mfc_find(mrt, &arg); } /* Look for a (*,G) entry */ static struct mfc_cache *ipmr_cache_find_any(struct mr_table *mrt, __be32 mcastgrp, int vifi) { struct mfc_cache_cmp_arg arg = { .mfc_mcastgrp = mcastgrp, .mfc_origin = htonl(INADDR_ANY) }; if (mcastgrp == htonl(INADDR_ANY)) return mr_mfc_find_any_parent(mrt, vifi); return mr_mfc_find_any(mrt, vifi, &arg); } /* Look for a (S,G,iif) entry if parent != -1 */ static struct mfc_cache *ipmr_cache_find_parent(struct mr_table *mrt, __be32 origin, __be32 mcastgrp, int parent) { struct mfc_cache_cmp_arg arg = { .mfc_mcastgrp = mcastgrp, .mfc_origin = origin, }; return mr_mfc_find_parent(mrt, &arg, parent); } /* Allocate a multicast cache entry */ static struct mfc_cache *ipmr_cache_alloc(void) { struct mfc_cache *c = kmem_cache_zalloc(mrt_cachep, GFP_KERNEL); if (c) { c->_c.mfc_un.res.last_assert = jiffies - MFC_ASSERT_THRESH - 1; c->_c.mfc_un.res.minvif = MAXVIFS; c->_c.free = ipmr_cache_free_rcu; refcount_set(&c->_c.mfc_un.res.refcount, 1); } return c; } static struct mfc_cache *ipmr_cache_alloc_unres(void) { struct mfc_cache *c = kmem_cache_zalloc(mrt_cachep, GFP_ATOMIC); if (c) { skb_queue_head_init(&c->_c.mfc_un.unres.unresolved); c->_c.mfc_un.unres.expires = jiffies + 10 * HZ; } return c; } /* A cache entry has gone into a resolved state from queued */ static void ipmr_cache_resolve(struct net *net, struct mr_table *mrt, struct mfc_cache *uc, struct mfc_cache *c) { struct sk_buff *skb; struct nlmsgerr *e; /* Play the pending entries through our router */ while ((skb = __skb_dequeue(&uc->_c.mfc_un.unres.unresolved))) { if (ip_hdr(skb)->version == 0) { struct nlmsghdr *nlh = skb_pull(skb, sizeof(struct iphdr)); if (mr_fill_mroute(mrt, skb, &c->_c, nlmsg_data(nlh)) > 0) { nlh->nlmsg_len = skb_tail_pointer(skb) - (u8 *)nlh; } else { nlh->nlmsg_type = NLMSG_ERROR; nlh->nlmsg_len = nlmsg_msg_size(sizeof(struct nlmsgerr)); skb_trim(skb, nlh->nlmsg_len); e = nlmsg_data(nlh); e->error = -EMSGSIZE; memset(&e->msg, 0, sizeof(e->msg)); } rtnl_unicast(skb, net, NETLINK_CB(skb).portid); } else { rcu_read_lock(); ip_mr_forward(net, mrt, skb->dev, skb, c, 0); rcu_read_unlock(); } } } /* Bounce a cache query up to mrouted and netlink. * * Called under rcu_read_lock(). */ static int ipmr_cache_report(const struct mr_table *mrt, struct sk_buff *pkt, vifi_t vifi, int assert) { const int ihl = ip_hdrlen(pkt); struct sock *mroute_sk; struct igmphdr *igmp; struct igmpmsg *msg; struct sk_buff *skb; int ret; mroute_sk = rcu_dereference(mrt->mroute_sk); if (!mroute_sk) return -EINVAL; if (assert == IGMPMSG_WHOLEPKT || assert == IGMPMSG_WRVIFWHOLE) skb = skb_realloc_headroom(pkt, sizeof(struct iphdr)); else skb = alloc_skb(128, GFP_ATOMIC); if (!skb) return -ENOBUFS; if (assert == IGMPMSG_WHOLEPKT || assert == IGMPMSG_WRVIFWHOLE) { /* Ugly, but we have no choice with this interface. * Duplicate old header, fix ihl, length etc. * And all this only to mangle msg->im_msgtype and * to set msg->im_mbz to "mbz" :-) */ skb_push(skb, sizeof(struct iphdr)); skb_reset_network_header(skb); skb_reset_transport_header(skb); msg = (struct igmpmsg *)skb_network_header(skb); memcpy(msg, skb_network_header(pkt), sizeof(struct iphdr)); msg->im_msgtype = assert; msg->im_mbz = 0; if (assert == IGMPMSG_WRVIFWHOLE) { msg->im_vif = vifi; msg->im_vif_hi = vifi >> 8; } else { /* Pairs with WRITE_ONCE() in vif_add() and vif_delete() */ int vif_num = READ_ONCE(mrt->mroute_reg_vif_num); msg->im_vif = vif_num; msg->im_vif_hi = vif_num >> 8; } ip_hdr(skb)->ihl = sizeof(struct iphdr) >> 2; ip_hdr(skb)->tot_len = htons(ntohs(ip_hdr(pkt)->tot_len) + sizeof(struct iphdr)); } else { /* Copy the IP header */ skb_set_network_header(skb, skb->len); skb_put(skb, ihl); skb_copy_to_linear_data(skb, pkt->data, ihl); /* Flag to the kernel this is a route add */ ip_hdr(skb)->protocol = 0; msg = (struct igmpmsg *)skb_network_header(skb); msg->im_vif = vifi; msg->im_vif_hi = vifi >> 8; ipv4_pktinfo_prepare(mroute_sk, pkt, false); memcpy(skb->cb, pkt->cb, sizeof(skb->cb)); /* Add our header */ igmp = skb_put(skb, sizeof(struct igmphdr)); igmp->type = assert; msg->im_msgtype = assert; igmp->code = 0; ip_hdr(skb)->tot_len = htons(skb->len); /* Fix the length */ skb->transport_header = skb->network_header; } igmpmsg_netlink_event(mrt, skb); /* Deliver to mrouted */ ret = sock_queue_rcv_skb(mroute_sk, skb); if (ret < 0) { net_warn_ratelimited("mroute: pending queue full, dropping entries\n"); kfree_skb(skb); } return ret; } /* Queue a packet for resolution. It gets locked cache entry! */ /* Called under rcu_read_lock() */ static int ipmr_cache_unresolved(struct mr_table *mrt, vifi_t vifi, struct sk_buff *skb, struct net_device *dev) { const struct iphdr *iph = ip_hdr(skb); struct mfc_cache *c; bool found = false; int err; spin_lock_bh(&mfc_unres_lock); list_for_each_entry(c, &mrt->mfc_unres_queue, _c.list) { if (c->mfc_mcastgrp == iph->daddr && c->mfc_origin == iph->saddr) { found = true; break; } } if (!found) { /* Create a new entry if allowable */ c = ipmr_cache_alloc_unres(); if (!c) { spin_unlock_bh(&mfc_unres_lock); kfree_skb(skb); return -ENOBUFS; } /* Fill in the new cache entry */ c->_c.mfc_parent = -1; c->mfc_origin = iph->saddr; c->mfc_mcastgrp = iph->daddr; /* Reflect first query at mrouted. */ err = ipmr_cache_report(mrt, skb, vifi, IGMPMSG_NOCACHE); if (err < 0) { /* If the report failed throw the cache entry out - Brad Parker */ spin_unlock_bh(&mfc_unres_lock); ipmr_cache_free(c); kfree_skb(skb); return err; } atomic_inc(&mrt->cache_resolve_queue_len); list_add(&c->_c.list, &mrt->mfc_unres_queue); mroute_netlink_event(mrt, c, RTM_NEWROUTE); if (atomic_read(&mrt->cache_resolve_queue_len) == 1) mod_timer(&mrt->ipmr_expire_timer, c->_c.mfc_un.unres.expires); } /* See if we can append the packet */ if (c->_c.mfc_un.unres.unresolved.qlen > 3) { kfree_skb(skb); err = -ENOBUFS; } else { if (dev) { skb->dev = dev; skb->skb_iif = dev->ifindex; } skb_queue_tail(&c->_c.mfc_un.unres.unresolved, skb); err = 0; } spin_unlock_bh(&mfc_unres_lock); return err; } /* MFC cache manipulation by user space mroute daemon */ static int ipmr_mfc_delete(struct mr_table *mrt, struct mfcctl *mfc, int parent) { struct net *net = read_pnet(&mrt->net); struct mfc_cache *c; /* The entries are added/deleted only under RTNL */ rcu_read_lock(); c = ipmr_cache_find_parent(mrt, mfc->mfcc_origin.s_addr, mfc->mfcc_mcastgrp.s_addr, parent); rcu_read_unlock(); if (!c) return -ENOENT; rhltable_remove(&mrt->mfc_hash, &c->_c.mnode, ipmr_rht_params); list_del_rcu(&c->_c.list); call_ipmr_mfc_entry_notifiers(net, FIB_EVENT_ENTRY_DEL, c, mrt->id); mroute_netlink_event(mrt, c, RTM_DELROUTE); mr_cache_put(&c->_c); return 0; } static int ipmr_mfc_add(struct net *net, struct mr_table *mrt, struct mfcctl *mfc, int mrtsock, int parent) { struct mfc_cache *uc, *c; struct mr_mfc *_uc; bool found; int ret; if (mfc->mfcc_parent >= MAXVIFS) return -ENFILE; /* The entries are added/deleted only under RTNL */ rcu_read_lock(); c = ipmr_cache_find_parent(mrt, mfc->mfcc_origin.s_addr, mfc->mfcc_mcastgrp.s_addr, parent); rcu_read_unlock(); if (c) { spin_lock(&mrt_lock); c->_c.mfc_parent = mfc->mfcc_parent; ipmr_update_thresholds(mrt, &c->_c, mfc->mfcc_ttls); if (!mrtsock) c->_c.mfc_flags |= MFC_STATIC; spin_unlock(&mrt_lock); call_ipmr_mfc_entry_notifiers(net, FIB_EVENT_ENTRY_REPLACE, c, mrt->id); mroute_netlink_event(mrt, c, RTM_NEWROUTE); return 0; } if (mfc->mfcc_mcastgrp.s_addr != htonl(INADDR_ANY) && !ipv4_is_multicast(mfc->mfcc_mcastgrp.s_addr)) return -EINVAL; c = ipmr_cache_alloc(); if (!c) return -ENOMEM; c->mfc_origin = mfc->mfcc_origin.s_addr; c->mfc_mcastgrp = mfc->mfcc_mcastgrp.s_addr; c->_c.mfc_parent = mfc->mfcc_parent; ipmr_update_thresholds(mrt, &c->_c, mfc->mfcc_ttls); if (!mrtsock) c->_c.mfc_flags |= MFC_STATIC; ret = rhltable_insert_key(&mrt->mfc_hash, &c->cmparg, &c->_c.mnode, ipmr_rht_params); if (ret) { pr_err("ipmr: rhtable insert error %d\n", ret); ipmr_cache_free(c); return ret; } list_add_tail_rcu(&c->_c.list, &mrt->mfc_cache_list); /* Check to see if we resolved a queued list. If so we * need to send on the frames and tidy up. */ found = false; spin_lock_bh(&mfc_unres_lock); list_for_each_entry(_uc, &mrt->mfc_unres_queue, list) { uc = (struct mfc_cache *)_uc; if (uc->mfc_origin == c->mfc_origin && uc->mfc_mcastgrp == c->mfc_mcastgrp) { list_del(&_uc->list); atomic_dec(&mrt->cache_resolve_queue_len); found = true; break; } } if (list_empty(&mrt->mfc_unres_queue)) del_timer(&mrt->ipmr_expire_timer); spin_unlock_bh(&mfc_unres_lock); if (found) { ipmr_cache_resolve(net, mrt, uc, c); ipmr_cache_free(uc); } call_ipmr_mfc_entry_notifiers(net, FIB_EVENT_ENTRY_ADD, c, mrt->id); mroute_netlink_event(mrt, c, RTM_NEWROUTE); return 0; } /* Close the multicast socket, and clear the vif tables etc */ static void mroute_clean_tables(struct mr_table *mrt, int flags) { struct net *net = read_pnet(&mrt->net); struct mr_mfc *c, *tmp; struct mfc_cache *cache; LIST_HEAD(list); int i; /* Shut down all active vif entries */ if (flags & (MRT_FLUSH_VIFS | MRT_FLUSH_VIFS_STATIC)) { for (i = 0; i < mrt->maxvif; i++) { if (((mrt->vif_table[i].flags & VIFF_STATIC) && !(flags & MRT_FLUSH_VIFS_STATIC)) || (!(mrt->vif_table[i].flags & VIFF_STATIC) && !(flags & MRT_FLUSH_VIFS))) continue; vif_delete(mrt, i, 0, &list); } unregister_netdevice_many(&list); } /* Wipe the cache */ if (flags & (MRT_FLUSH_MFC | MRT_FLUSH_MFC_STATIC)) { list_for_each_entry_safe(c, tmp, &mrt->mfc_cache_list, list) { if (((c->mfc_flags & MFC_STATIC) && !(flags & MRT_FLUSH_MFC_STATIC)) || (!(c->mfc_flags & MFC_STATIC) && !(flags & MRT_FLUSH_MFC))) continue; rhltable_remove(&mrt->mfc_hash, &c->mnode, ipmr_rht_params); list_del_rcu(&c->list); cache = (struct mfc_cache *)c; call_ipmr_mfc_entry_notifiers(net, FIB_EVENT_ENTRY_DEL, cache, mrt->id); mroute_netlink_event(mrt, cache, RTM_DELROUTE); mr_cache_put(c); } } if (flags & MRT_FLUSH_MFC) { if (atomic_read(&mrt->cache_resolve_queue_len) != 0) { spin_lock_bh(&mfc_unres_lock); list_for_each_entry_safe(c, tmp, &mrt->mfc_unres_queue, list) { list_del(&c->list); cache = (struct mfc_cache *)c; mroute_netlink_event(mrt, cache, RTM_DELROUTE); ipmr_destroy_unres(mrt, cache); } spin_unlock_bh(&mfc_unres_lock); } } } /* called from ip_ra_control(), before an RCU grace period, * we don't need to call synchronize_rcu() here */ static void mrtsock_destruct(struct sock *sk) { struct net *net = sock_net(sk); struct mr_table *mrt; rtnl_lock(); ipmr_for_each_table(mrt, net) { if (sk == rtnl_dereference(mrt->mroute_sk)) { IPV4_DEVCONF_ALL(net, MC_FORWARDING)--; inet_netconf_notify_devconf(net, RTM_NEWNETCONF, NETCONFA_MC_FORWARDING, NETCONFA_IFINDEX_ALL, net->ipv4.devconf_all); RCU_INIT_POINTER(mrt->mroute_sk, NULL); mroute_clean_tables(mrt, MRT_FLUSH_VIFS | MRT_FLUSH_MFC); } } rtnl_unlock(); } /* Socket options and virtual interface manipulation. The whole * virtual interface system is a complete heap, but unfortunately * that's how BSD mrouted happens to think. Maybe one day with a proper * MOSPF/PIM router set up we can clean this up. */ int ip_mroute_setsockopt(struct sock *sk, int optname, sockptr_t optval, unsigned int optlen) { struct net *net = sock_net(sk); int val, ret = 0, parent = 0; struct mr_table *mrt; struct vifctl vif; struct mfcctl mfc; bool do_wrvifwhole; u32 uval; /* There's one exception to the lock - MRT_DONE which needs to unlock */ rtnl_lock(); if (sk->sk_type != SOCK_RAW || inet_sk(sk)->inet_num != IPPROTO_IGMP) { ret = -EOPNOTSUPP; goto out_unlock; } mrt = __ipmr_get_table(net, raw_sk(sk)->ipmr_table ? : RT_TABLE_DEFAULT); if (!mrt) { ret = -ENOENT; goto out_unlock; } if (optname != MRT_INIT) { if (sk != rcu_access_pointer(mrt->mroute_sk) && !ns_capable(net->user_ns, CAP_NET_ADMIN)) { ret = -EACCES; goto out_unlock; } } switch (optname) { case MRT_INIT: if (optlen != sizeof(int)) { ret = -EINVAL; break; } if (rtnl_dereference(mrt->mroute_sk)) { ret = -EADDRINUSE; break; } ret = ip_ra_control(sk, 1, mrtsock_destruct); if (ret == 0) { rcu_assign_pointer(mrt->mroute_sk, sk); IPV4_DEVCONF_ALL(net, MC_FORWARDING)++; inet_netconf_notify_devconf(net, RTM_NEWNETCONF, NETCONFA_MC_FORWARDING, NETCONFA_IFINDEX_ALL, net->ipv4.devconf_all); } break; case MRT_DONE: if (sk != rcu_access_pointer(mrt->mroute_sk)) { ret = -EACCES; } else { /* We need to unlock here because mrtsock_destruct takes * care of rtnl itself and we can't change that due to * the IP_ROUTER_ALERT setsockopt which runs without it. */ rtnl_unlock(); ret = ip_ra_control(sk, 0, NULL); goto out; } break; case MRT_ADD_VIF: case MRT_DEL_VIF: if (optlen != sizeof(vif)) { ret = -EINVAL; break; } if (copy_from_sockptr(&vif, optval, sizeof(vif))) { ret = -EFAULT; break; } if (vif.vifc_vifi >= MAXVIFS) { ret = -ENFILE; break; } if (optname == MRT_ADD_VIF) { ret = vif_add(net, mrt, &vif, sk == rtnl_dereference(mrt->mroute_sk)); } else { ret = vif_delete(mrt, vif.vifc_vifi, 0, NULL); } break; /* Manipulate the forwarding caches. These live * in a sort of kernel/user symbiosis. */ case MRT_ADD_MFC: case MRT_DEL_MFC: parent = -1; fallthrough; case MRT_ADD_MFC_PROXY: case MRT_DEL_MFC_PROXY: if (optlen != sizeof(mfc)) { ret = -EINVAL; break; } if (copy_from_sockptr(&mfc, optval, sizeof(mfc))) { ret = -EFAULT; break; } if (parent == 0) parent = mfc.mfcc_parent; if (optname == MRT_DEL_MFC || optname == MRT_DEL_MFC_PROXY) ret = ipmr_mfc_delete(mrt, &mfc, parent); else ret = ipmr_mfc_add(net, mrt, &mfc, sk == rtnl_dereference(mrt->mroute_sk), parent); break; case MRT_FLUSH: if (optlen != sizeof(val)) { ret = -EINVAL; break; } if (copy_from_sockptr(&val, optval, sizeof(val))) { ret = -EFAULT; break; } mroute_clean_tables(mrt, val); break; /* Control PIM assert. */ case MRT_ASSERT: if (optlen != sizeof(val)) { ret = -EINVAL; break; } if (copy_from_sockptr(&val, optval, sizeof(val))) { ret = -EFAULT; break; } mrt->mroute_do_assert = val; break; case MRT_PIM: if (!ipmr_pimsm_enabled()) { ret = -ENOPROTOOPT; break; } if (optlen != sizeof(val)) { ret = -EINVAL; break; } if (copy_from_sockptr(&val, optval, sizeof(val))) { ret = -EFAULT; break; } do_wrvifwhole = (val == IGMPMSG_WRVIFWHOLE); val = !!val; if (val != mrt->mroute_do_pim) { mrt->mroute_do_pim = val; mrt->mroute_do_assert = val; mrt->mroute_do_wrvifwhole = do_wrvifwhole; } break; case MRT_TABLE: if (!IS_BUILTIN(CONFIG_IP_MROUTE_MULTIPLE_TABLES)) { ret = -ENOPROTOOPT; break; } if (optlen != sizeof(uval)) { ret = -EINVAL; break; } if (copy_from_sockptr(&uval, optval, sizeof(uval))) { ret = -EFAULT; break; } if (sk == rtnl_dereference(mrt->mroute_sk)) { ret = -EBUSY; } else { mrt = ipmr_new_table(net, uval); if (IS_ERR(mrt)) ret = PTR_ERR(mrt); else raw_sk(sk)->ipmr_table = uval; } break; /* Spurious command, or MRT_VERSION which you cannot set. */ default: ret = -ENOPROTOOPT; } out_unlock: rtnl_unlock(); out: return ret; } /* Execute if this ioctl is a special mroute ioctl */ int ipmr_sk_ioctl(struct sock *sk, unsigned int cmd, void __user *arg) { switch (cmd) { /* These userspace buffers will be consumed by ipmr_ioctl() */ case SIOCGETVIFCNT: { struct sioc_vif_req buffer; return sock_ioctl_inout(sk, cmd, arg, &buffer, sizeof(buffer)); } case SIOCGETSGCNT: { struct sioc_sg_req buffer; return sock_ioctl_inout(sk, cmd, arg, &buffer, sizeof(buffer)); } } /* return code > 0 means that the ioctl was not executed */ return 1; } /* Getsock opt support for the multicast routing system. */ int ip_mroute_getsockopt(struct sock *sk, int optname, sockptr_t optval, sockptr_t optlen) { int olr; int val; struct net *net = sock_net(sk); struct mr_table *mrt; if (sk->sk_type != SOCK_RAW || inet_sk(sk)->inet_num != IPPROTO_IGMP) return -EOPNOTSUPP; mrt = ipmr_get_table(net, raw_sk(sk)->ipmr_table ? : RT_TABLE_DEFAULT); if (!mrt) return -ENOENT; switch (optname) { case MRT_VERSION: val = 0x0305; break; case MRT_PIM: if (!ipmr_pimsm_enabled()) return -ENOPROTOOPT; val = mrt->mroute_do_pim; break; case MRT_ASSERT: val = mrt->mroute_do_assert; break; default: return -ENOPROTOOPT; } if (copy_from_sockptr(&olr, optlen, sizeof(int))) return -EFAULT; if (olr < 0) return -EINVAL; olr = min_t(unsigned int, olr, sizeof(int)); if (copy_to_sockptr(optlen, &olr, sizeof(int))) return -EFAULT; if (copy_to_sockptr(optval, &val, olr)) return -EFAULT; return 0; } /* The IP multicast ioctl support routines. */ int ipmr_ioctl(struct sock *sk, int cmd, void *arg) { struct vif_device *vif; struct mfc_cache *c; struct net *net = sock_net(sk); struct sioc_vif_req *vr; struct sioc_sg_req *sr; struct mr_table *mrt; mrt = ipmr_get_table(net, raw_sk(sk)->ipmr_table ? : RT_TABLE_DEFAULT); if (!mrt) return -ENOENT; switch (cmd) { case SIOCGETVIFCNT: vr = (struct sioc_vif_req *)arg; if (vr->vifi >= mrt->maxvif) return -EINVAL; vr->vifi = array_index_nospec(vr->vifi, mrt->maxvif); rcu_read_lock(); vif = &mrt->vif_table[vr->vifi]; if (VIF_EXISTS(mrt, vr->vifi)) { vr->icount = READ_ONCE(vif->pkt_in); vr->ocount = READ_ONCE(vif->pkt_out); vr->ibytes = READ_ONCE(vif->bytes_in); vr->obytes = READ_ONCE(vif->bytes_out); rcu_read_unlock(); return 0; } rcu_read_unlock(); return -EADDRNOTAVAIL; case SIOCGETSGCNT: sr = (struct sioc_sg_req *)arg; rcu_read_lock(); c = ipmr_cache_find(mrt, sr->src.s_addr, sr->grp.s_addr); if (c) { sr->pktcnt = c->_c.mfc_un.res.pkt; sr->bytecnt = c->_c.mfc_un.res.bytes; sr->wrong_if = c->_c.mfc_un.res.wrong_if; rcu_read_unlock(); return 0; } rcu_read_unlock(); return -EADDRNOTAVAIL; default: return -ENOIOCTLCMD; } } #ifdef CONFIG_COMPAT struct compat_sioc_sg_req { struct in_addr src; struct in_addr grp; compat_ulong_t pktcnt; compat_ulong_t bytecnt; compat_ulong_t wrong_if; }; struct compat_sioc_vif_req { vifi_t vifi; /* Which iface */ compat_ulong_t icount; compat_ulong_t ocount; compat_ulong_t ibytes; compat_ulong_t obytes; }; int ipmr_compat_ioctl(struct sock *sk, unsigned int cmd, void __user *arg) { struct compat_sioc_sg_req sr; struct compat_sioc_vif_req vr; struct vif_device *vif; struct mfc_cache *c; struct net *net = sock_net(sk); struct mr_table *mrt; mrt = ipmr_get_table(net, raw_sk(sk)->ipmr_table ? : RT_TABLE_DEFAULT); if (!mrt) return -ENOENT; switch (cmd) { case SIOCGETVIFCNT: if (copy_from_user(&vr, arg, sizeof(vr))) return -EFAULT; if (vr.vifi >= mrt->maxvif) return -EINVAL; vr.vifi = array_index_nospec(vr.vifi, mrt->maxvif); rcu_read_lock(); vif = &mrt->vif_table[vr.vifi]; if (VIF_EXISTS(mrt, vr.vifi)) { vr.icount = READ_ONCE(vif->pkt_in); vr.ocount = READ_ONCE(vif->pkt_out); vr.ibytes = READ_ONCE(vif->bytes_in); vr.obytes = READ_ONCE(vif->bytes_out); rcu_read_unlock(); if (copy_to_user(arg, &vr, sizeof(vr))) return -EFAULT; return 0; } rcu_read_unlock(); return -EADDRNOTAVAIL; case SIOCGETSGCNT: if (copy_from_user(&sr, arg, sizeof(sr))) return -EFAULT; rcu_read_lock(); c = ipmr_cache_find(mrt, sr.src.s_addr, sr.grp.s_addr); if (c) { sr.pktcnt = c->_c.mfc_un.res.pkt; sr.bytecnt = c->_c.mfc_un.res.bytes; sr.wrong_if = c->_c.mfc_un.res.wrong_if; rcu_read_unlock(); if (copy_to_user(arg, &sr, sizeof(sr))) return -EFAULT; return 0; } rcu_read_unlock(); return -EADDRNOTAVAIL; default: return -ENOIOCTLCMD; } } #endif static int ipmr_device_event(struct notifier_block *this, unsigned long event, void *ptr) { struct net_device *dev = netdev_notifier_info_to_dev(ptr); struct net *net = dev_net(dev); struct mr_table *mrt; struct vif_device *v; int ct; if (event != NETDEV_UNREGISTER) return NOTIFY_DONE; ipmr_for_each_table(mrt, net) { v = &mrt->vif_table[0]; for (ct = 0; ct < mrt->maxvif; ct++, v++) { if (rcu_access_pointer(v->dev) == dev) vif_delete(mrt, ct, 1, NULL); } } return NOTIFY_DONE; } static struct notifier_block ip_mr_notifier = { .notifier_call = ipmr_device_event, }; /* Encapsulate a packet by attaching a valid IPIP header to it. * This avoids tunnel drivers and other mess and gives us the speed so * important for multicast video. */ static void ip_encap(struct net *net, struct sk_buff *skb, __be32 saddr, __be32 daddr) { struct iphdr *iph; const struct iphdr *old_iph = ip_hdr(skb); skb_push(skb, sizeof(struct iphdr)); skb->transport_header = skb->network_header; skb_reset_network_header(skb); iph = ip_hdr(skb); iph->version = 4; iph->tos = old_iph->tos; iph->ttl = old_iph->ttl; iph->frag_off = 0; iph->daddr = daddr; iph->saddr = saddr; iph->protocol = IPPROTO_IPIP; iph->ihl = 5; iph->tot_len = htons(skb->len); ip_select_ident(net, skb, NULL); ip_send_check(iph); memset(&(IPCB(skb)->opt), 0, sizeof(IPCB(skb)->opt)); nf_reset_ct(skb); } static inline int ipmr_forward_finish(struct net *net, struct sock *sk, struct sk_buff *skb) { struct ip_options *opt = &(IPCB(skb)->opt); IP_INC_STATS(net, IPSTATS_MIB_OUTFORWDATAGRAMS); if (unlikely(opt->optlen)) ip_forward_options(skb); return dst_output(net, sk, skb); } #ifdef CONFIG_NET_SWITCHDEV static bool ipmr_forward_offloaded(struct sk_buff *skb, struct mr_table *mrt, int in_vifi, int out_vifi) { struct vif_device *out_vif = &mrt->vif_table[out_vifi]; struct vif_device *in_vif = &mrt->vif_table[in_vifi]; if (!skb->offload_l3_fwd_mark) return false; if (!out_vif->dev_parent_id.id_len || !in_vif->dev_parent_id.id_len) return false; return netdev_phys_item_id_same(&out_vif->dev_parent_id, &in_vif->dev_parent_id); } #else static bool ipmr_forward_offloaded(struct sk_buff *skb, struct mr_table *mrt, int in_vifi, int out_vifi) { return false; } #endif /* Processing handlers for ipmr_forward, under rcu_read_lock() */ static void ipmr_queue_xmit(struct net *net, struct mr_table *mrt, int in_vifi, struct sk_buff *skb, int vifi) { const struct iphdr *iph = ip_hdr(skb); struct vif_device *vif = &mrt->vif_table[vifi]; struct net_device *vif_dev; struct net_device *dev; struct rtable *rt; struct flowi4 fl4; int encap = 0; vif_dev = vif_dev_read(vif); if (!vif_dev) goto out_free; if (vif->flags & VIFF_REGISTER) { WRITE_ONCE(vif->pkt_out, vif->pkt_out + 1); WRITE_ONCE(vif->bytes_out, vif->bytes_out + skb->len); DEV_STATS_ADD(vif_dev, tx_bytes, skb->len); DEV_STATS_INC(vif_dev, tx_packets); ipmr_cache_report(mrt, skb, vifi, IGMPMSG_WHOLEPKT); goto out_free; } if (ipmr_forward_offloaded(skb, mrt, in_vifi, vifi)) goto out_free; if (vif->flags & VIFF_TUNNEL) { rt = ip_route_output_ports(net, &fl4, NULL, vif->remote, vif->local, 0, 0, IPPROTO_IPIP, iph->tos & INET_DSCP_MASK, vif->link); if (IS_ERR(rt)) goto out_free; encap = sizeof(struct iphdr); } else { rt = ip_route_output_ports(net, &fl4, NULL, iph->daddr, 0, 0, 0, IPPROTO_IPIP, iph->tos & INET_DSCP_MASK, vif->link); if (IS_ERR(rt)) goto out_free; } dev = rt->dst.dev; if (skb->len+encap > dst_mtu(&rt->dst) && (ntohs(iph->frag_off) & IP_DF)) { /* Do not fragment multicasts. Alas, IPv4 does not * allow to send ICMP, so that packets will disappear * to blackhole. */ IP_INC_STATS(net, IPSTATS_MIB_FRAGFAILS); ip_rt_put(rt); goto out_free; } encap += LL_RESERVED_SPACE(dev) + rt->dst.header_len; if (skb_cow(skb, encap)) { ip_rt_put(rt); goto out_free; } WRITE_ONCE(vif->pkt_out, vif->pkt_out + 1); WRITE_ONCE(vif->bytes_out, vif->bytes_out + skb->len); skb_dst_drop(skb); skb_dst_set(skb, &rt->dst); ip_decrease_ttl(ip_hdr(skb)); /* FIXME: forward and output firewalls used to be called here. * What do we do with netfilter? -- RR */ if (vif->flags & VIFF_TUNNEL) { ip_encap(net, skb, vif->local, vif->remote); /* FIXME: extra output firewall step used to be here. --RR */ DEV_STATS_INC(vif_dev, tx_packets); DEV_STATS_ADD(vif_dev, tx_bytes, skb->len); } IPCB(skb)->flags |= IPSKB_FORWARDED; /* RFC1584 teaches, that DVMRP/PIM router must deliver packets locally * not only before forwarding, but after forwarding on all output * interfaces. It is clear, if mrouter runs a multicasting * program, it should receive packets not depending to what interface * program is joined. * If we will not make it, the program will have to join on all * interfaces. On the other hand, multihoming host (or router, but * not mrouter) cannot join to more than one interface - it will * result in receiving multiple packets. */ NF_HOOK(NFPROTO_IPV4, NF_INET_FORWARD, net, NULL, skb, skb->dev, dev, ipmr_forward_finish); return; out_free: kfree_skb(skb); } /* Called with mrt_lock or rcu_read_lock() */ static int ipmr_find_vif(const struct mr_table *mrt, struct net_device *dev) { int ct; /* Pairs with WRITE_ONCE() in vif_delete()/vif_add() */ for (ct = READ_ONCE(mrt->maxvif) - 1; ct >= 0; ct--) { if (rcu_access_pointer(mrt->vif_table[ct].dev) == dev) break; } return ct; } /* "local" means that we should preserve one skb (for local delivery) */ /* Called uner rcu_read_lock() */ static void ip_mr_forward(struct net *net, struct mr_table *mrt, struct net_device *dev, struct sk_buff *skb, struct mfc_cache *c, int local) { int true_vifi = ipmr_find_vif(mrt, dev); int psend = -1; int vif, ct; vif = c->_c.mfc_parent; c->_c.mfc_un.res.pkt++; c->_c.mfc_un.res.bytes += skb->len; c->_c.mfc_un.res.lastuse = jiffies; if (c->mfc_origin == htonl(INADDR_ANY) && true_vifi >= 0) { struct mfc_cache *cache_proxy; /* For an (*,G) entry, we only check that the incoming * interface is part of the static tree. */ cache_proxy = mr_mfc_find_any_parent(mrt, vif); if (cache_proxy && cache_proxy->_c.mfc_un.res.ttls[true_vifi] < 255) goto forward; } /* Wrong interface: drop packet and (maybe) send PIM assert. */ if (rcu_access_pointer(mrt->vif_table[vif].dev) != dev) { if (rt_is_output_route(skb_rtable(skb))) { /* It is our own packet, looped back. * Very complicated situation... * * The best workaround until routing daemons will be * fixed is not to redistribute packet, if it was * send through wrong interface. It means, that * multicast applications WILL NOT work for * (S,G), which have default multicast route pointing * to wrong oif. In any case, it is not a good * idea to use multicasting applications on router. */ goto dont_forward; } c->_c.mfc_un.res.wrong_if++; if (true_vifi >= 0 && mrt->mroute_do_assert && /* pimsm uses asserts, when switching from RPT to SPT, * so that we cannot check that packet arrived on an oif. * It is bad, but otherwise we would need to move pretty * large chunk of pimd to kernel. Ough... --ANK */ (mrt->mroute_do_pim || c->_c.mfc_un.res.ttls[true_vifi] < 255) && time_after(jiffies, c->_c.mfc_un.res.last_assert + MFC_ASSERT_THRESH)) { c->_c.mfc_un.res.last_assert = jiffies; ipmr_cache_report(mrt, skb, true_vifi, IGMPMSG_WRONGVIF); if (mrt->mroute_do_wrvifwhole) ipmr_cache_report(mrt, skb, true_vifi, IGMPMSG_WRVIFWHOLE); } goto dont_forward; } forward: WRITE_ONCE(mrt->vif_table[vif].pkt_in, mrt->vif_table[vif].pkt_in + 1); WRITE_ONCE(mrt->vif_table[vif].bytes_in, mrt->vif_table[vif].bytes_in + skb->len); /* Forward the frame */ if (c->mfc_origin == htonl(INADDR_ANY) && c->mfc_mcastgrp == htonl(INADDR_ANY)) { if (true_vifi >= 0 && true_vifi != c->_c.mfc_parent && ip_hdr(skb)->ttl > c->_c.mfc_un.res.ttls[c->_c.mfc_parent]) { /* It's an (*,*) entry and the packet is not coming from * the upstream: forward the packet to the upstream * only. */ psend = c->_c.mfc_parent; goto last_forward; } goto dont_forward; } for (ct = c->_c.mfc_un.res.maxvif - 1; ct >= c->_c.mfc_un.res.minvif; ct--) { /* For (*,G) entry, don't forward to the incoming interface */ if ((c->mfc_origin != htonl(INADDR_ANY) || ct != true_vifi) && ip_hdr(skb)->ttl > c->_c.mfc_un.res.ttls[ct]) { if (psend != -1) { struct sk_buff *skb2 = skb_clone(skb, GFP_ATOMIC); if (skb2) ipmr_queue_xmit(net, mrt, true_vifi, skb2, psend); } psend = ct; } } last_forward: if (psend != -1) { if (local) { struct sk_buff *skb2 = skb_clone(skb, GFP_ATOMIC); if (skb2) ipmr_queue_xmit(net, mrt, true_vifi, skb2, psend); } else { ipmr_queue_xmit(net, mrt, true_vifi, skb, psend); return; } } dont_forward: if (!local) kfree_skb(skb); } static struct mr_table *ipmr_rt_fib_lookup(struct net *net, struct sk_buff *skb) { struct rtable *rt = skb_rtable(skb); struct iphdr *iph = ip_hdr(skb); struct flowi4 fl4 = { .daddr = iph->daddr, .saddr = iph->saddr, .flowi4_tos = inet_dscp_to_dsfield(ip4h_dscp(iph)), .flowi4_oif = (rt_is_output_route(rt) ? skb->dev->ifindex : 0), .flowi4_iif = (rt_is_output_route(rt) ? LOOPBACK_IFINDEX : skb->dev->ifindex), .flowi4_mark = skb->mark, }; struct mr_table *mrt; int err; err = ipmr_fib_lookup(net, &fl4, &mrt); if (err) return ERR_PTR(err); return mrt; } /* Multicast packets for forwarding arrive here * Called with rcu_read_lock(); */ int ip_mr_input(struct sk_buff *skb) { struct mfc_cache *cache; struct net *net = dev_net(skb->dev); int local = skb_rtable(skb)->rt_flags & RTCF_LOCAL; struct mr_table *mrt; struct net_device *dev; /* skb->dev passed in is the loX master dev for vrfs. * As there are no vifs associated with loopback devices, * get the proper interface that does have a vif associated with it. */ dev = skb->dev; if (netif_is_l3_master(skb->dev)) { dev = dev_get_by_index_rcu(net, IPCB(skb)->iif); if (!dev) { kfree_skb(skb); return -ENODEV; } } /* Packet is looped back after forward, it should not be * forwarded second time, but still can be delivered locally. */ if (IPCB(skb)->flags & IPSKB_FORWARDED) goto dont_forward; mrt = ipmr_rt_fib_lookup(net, skb); if (IS_ERR(mrt)) { kfree_skb(skb); return PTR_ERR(mrt); } if (!local) { if (IPCB(skb)->opt.router_alert) { if (ip_call_ra_chain(skb)) return 0; } else if (ip_hdr(skb)->protocol == IPPROTO_IGMP) { /* IGMPv1 (and broken IGMPv2 implementations sort of * Cisco IOS <= 11.2(8)) do not put router alert * option to IGMP packets destined to routable * groups. It is very bad, because it means * that we can forward NO IGMP messages. */ struct sock *mroute_sk; mroute_sk = rcu_dereference(mrt->mroute_sk); if (mroute_sk) { nf_reset_ct(skb); raw_rcv(mroute_sk, skb); return 0; } } } /* already under rcu_read_lock() */ cache = ipmr_cache_find(mrt, ip_hdr(skb)->saddr, ip_hdr(skb)->daddr); if (!cache) { int vif = ipmr_find_vif(mrt, dev); if (vif >= 0) cache = ipmr_cache_find_any(mrt, ip_hdr(skb)->daddr, vif); } /* No usable cache entry */ if (!cache) { int vif; if (local) { struct sk_buff *skb2 = skb_clone(skb, GFP_ATOMIC); ip_local_deliver(skb); if (!skb2) return -ENOBUFS; skb = skb2; } vif = ipmr_find_vif(mrt, dev); if (vif >= 0) return ipmr_cache_unresolved(mrt, vif, skb, dev); kfree_skb(skb); return -ENODEV; } ip_mr_forward(net, mrt, dev, skb, cache, local); if (local) return ip_local_deliver(skb); return 0; dont_forward: if (local) return ip_local_deliver(skb); kfree_skb(skb); return 0; } #ifdef CONFIG_IP_PIMSM_V1 /* Handle IGMP messages of PIMv1 */ int pim_rcv_v1(struct sk_buff *skb) { struct igmphdr *pim; struct net *net = dev_net(skb->dev); struct mr_table *mrt; if (!pskb_may_pull(skb, sizeof(*pim) + sizeof(struct iphdr))) goto drop; pim = igmp_hdr(skb); mrt = ipmr_rt_fib_lookup(net, skb); if (IS_ERR(mrt)) goto drop; if (!mrt->mroute_do_pim || pim->group != PIM_V1_VERSION || pim->code != PIM_V1_REGISTER) goto drop; if (__pim_rcv(mrt, skb, sizeof(*pim))) { drop: kfree_skb(skb); } return 0; } #endif #ifdef CONFIG_IP_PIMSM_V2 static int pim_rcv(struct sk_buff *skb) { struct pimreghdr *pim; struct net *net = dev_net(skb->dev); struct mr_table *mrt; if (!pskb_may_pull(skb, sizeof(*pim) + sizeof(struct iphdr))) goto drop; pim = (struct pimreghdr *)skb_transport_header(skb); if (pim->type != ((PIM_VERSION << 4) | (PIM_TYPE_REGISTER)) || (pim->flags & PIM_NULL_REGISTER) || (ip_compute_csum((void *)pim, sizeof(*pim)) != 0 && csum_fold(skb_checksum(skb, 0, skb->len, 0)))) goto drop; mrt = ipmr_rt_fib_lookup(net, skb); if (IS_ERR(mrt)) goto drop; if (__pim_rcv(mrt, skb, sizeof(*pim))) { drop: kfree_skb(skb); } return 0; } #endif int ipmr_get_route(struct net *net, struct sk_buff *skb, __be32 saddr, __be32 daddr, struct rtmsg *rtm, u32 portid) { struct mfc_cache *cache; struct mr_table *mrt; int err; rcu_read_lock(); mrt = __ipmr_get_table(net, RT_TABLE_DEFAULT); if (!mrt) { rcu_read_unlock(); return -ENOENT; } cache = ipmr_cache_find(mrt, saddr, daddr); if (!cache && skb->dev) { int vif = ipmr_find_vif(mrt, skb->dev); if (vif >= 0) cache = ipmr_cache_find_any(mrt, daddr, vif); } if (!cache) { struct sk_buff *skb2; struct iphdr *iph; struct net_device *dev; int vif = -1; dev = skb->dev; if (dev) vif = ipmr_find_vif(mrt, dev); if (vif < 0) { rcu_read_unlock(); return -ENODEV; } skb2 = skb_realloc_headroom(skb, sizeof(struct iphdr)); if (!skb2) { rcu_read_unlock(); return -ENOMEM; } NETLINK_CB(skb2).portid = portid; skb_push(skb2, sizeof(struct iphdr)); skb_reset_network_header(skb2); iph = ip_hdr(skb2); iph->ihl = sizeof(struct iphdr) >> 2; iph->saddr = saddr; iph->daddr = daddr; iph->version = 0; err = ipmr_cache_unresolved(mrt, vif, skb2, dev); rcu_read_unlock(); return err; } err = mr_fill_mroute(mrt, skb, &cache->_c, rtm); rcu_read_unlock(); return err; } static int ipmr_fill_mroute(struct mr_table *mrt, struct sk_buff *skb, u32 portid, u32 seq, struct mfc_cache *c, int cmd, int flags) { struct nlmsghdr *nlh; struct rtmsg *rtm; int err; nlh = nlmsg_put(skb, portid, seq, cmd, sizeof(*rtm), flags); if (!nlh) return -EMSGSIZE; rtm = nlmsg_data(nlh); rtm->rtm_family = RTNL_FAMILY_IPMR; rtm->rtm_dst_len = 32; rtm->rtm_src_len = 32; rtm->rtm_tos = 0; rtm->rtm_table = mrt->id; if (nla_put_u32(skb, RTA_TABLE, mrt->id)) goto nla_put_failure; rtm->rtm_type = RTN_MULTICAST; rtm->rtm_scope = RT_SCOPE_UNIVERSE; if (c->_c.mfc_flags & MFC_STATIC) rtm->rtm_protocol = RTPROT_STATIC; else rtm->rtm_protocol = RTPROT_MROUTED; rtm->rtm_flags = 0; if (nla_put_in_addr(skb, RTA_SRC, c->mfc_origin) || nla_put_in_addr(skb, RTA_DST, c->mfc_mcastgrp)) goto nla_put_failure; err = mr_fill_mroute(mrt, skb, &c->_c, rtm); /* do not break the dump if cache is unresolved */ if (err < 0 && err != -ENOENT) goto nla_put_failure; nlmsg_end(skb, nlh); return 0; nla_put_failure: nlmsg_cancel(skb, nlh); return -EMSGSIZE; } static int _ipmr_fill_mroute(struct mr_table *mrt, struct sk_buff *skb, u32 portid, u32 seq, struct mr_mfc *c, int cmd, int flags) { return ipmr_fill_mroute(mrt, skb, portid, seq, (struct mfc_cache *)c, cmd, flags); } static size_t mroute_msgsize(bool unresolved, int maxvif) { size_t len = NLMSG_ALIGN(sizeof(struct rtmsg)) + nla_total_size(4) /* RTA_TABLE */ + nla_total_size(4) /* RTA_SRC */ + nla_total_size(4) /* RTA_DST */ ; if (!unresolved) len = len + nla_total_size(4) /* RTA_IIF */ + nla_total_size(0) /* RTA_MULTIPATH */ + maxvif * NLA_ALIGN(sizeof(struct rtnexthop)) /* RTA_MFC_STATS */ + nla_total_size_64bit(sizeof(struct rta_mfc_stats)) ; return len; } static void mroute_netlink_event(struct mr_table *mrt, struct mfc_cache *mfc, int cmd) { struct net *net = read_pnet(&mrt->net); struct sk_buff *skb; int err = -ENOBUFS; skb = nlmsg_new(mroute_msgsize(mfc->_c.mfc_parent >= MAXVIFS, mrt->maxvif), GFP_ATOMIC); if (!skb) goto errout; err = ipmr_fill_mroute(mrt, skb, 0, 0, mfc, cmd, 0); if (err < 0) goto errout; rtnl_notify(skb, net, 0, RTNLGRP_IPV4_MROUTE, NULL, GFP_ATOMIC); return; errout: kfree_skb(skb); rtnl_set_sk_err(net, RTNLGRP_IPV4_MROUTE, err); } static size_t igmpmsg_netlink_msgsize(size_t payloadlen) { size_t len = NLMSG_ALIGN(sizeof(struct rtgenmsg)) + nla_total_size(1) /* IPMRA_CREPORT_MSGTYPE */ + nla_total_size(4) /* IPMRA_CREPORT_VIF_ID */ + nla_total_size(4) /* IPMRA_CREPORT_SRC_ADDR */ + nla_total_size(4) /* IPMRA_CREPORT_DST_ADDR */ + nla_total_size(4) /* IPMRA_CREPORT_TABLE */ /* IPMRA_CREPORT_PKT */ + nla_total_size(payloadlen) ; return len; } static void igmpmsg_netlink_event(const struct mr_table *mrt, struct sk_buff *pkt) { struct net *net = read_pnet(&mrt->net); struct nlmsghdr *nlh; struct rtgenmsg *rtgenm; struct igmpmsg *msg; struct sk_buff *skb; struct nlattr *nla; int payloadlen; payloadlen = pkt->len - sizeof(struct igmpmsg); msg = (struct igmpmsg *)skb_network_header(pkt); skb = nlmsg_new(igmpmsg_netlink_msgsize(payloadlen), GFP_ATOMIC); if (!skb) goto errout; nlh = nlmsg_put(skb, 0, 0, RTM_NEWCACHEREPORT, sizeof(struct rtgenmsg), 0); if (!nlh) goto errout; rtgenm = nlmsg_data(nlh); rtgenm->rtgen_family = RTNL_FAMILY_IPMR; if (nla_put_u8(skb, IPMRA_CREPORT_MSGTYPE, msg->im_msgtype) || nla_put_u32(skb, IPMRA_CREPORT_VIF_ID, msg->im_vif | (msg->im_vif_hi << 8)) || nla_put_in_addr(skb, IPMRA_CREPORT_SRC_ADDR, msg->im_src.s_addr) || nla_put_in_addr(skb, IPMRA_CREPORT_DST_ADDR, msg->im_dst.s_addr) || nla_put_u32(skb, IPMRA_CREPORT_TABLE, mrt->id)) goto nla_put_failure; nla = nla_reserve(skb, IPMRA_CREPORT_PKT, payloadlen); if (!nla || skb_copy_bits(pkt, sizeof(struct igmpmsg), nla_data(nla), payloadlen)) goto nla_put_failure; nlmsg_end(skb, nlh); rtnl_notify(skb, net, 0, RTNLGRP_IPV4_MROUTE_R, NULL, GFP_ATOMIC); return; nla_put_failure: nlmsg_cancel(skb, nlh); errout: kfree_skb(skb); rtnl_set_sk_err(net, RTNLGRP_IPV4_MROUTE_R, -ENOBUFS); } static int ipmr_rtm_valid_getroute_req(struct sk_buff *skb, const struct nlmsghdr *nlh, struct nlattr **tb, struct netlink_ext_ack *extack) { struct rtmsg *rtm; int i, err; if (nlh->nlmsg_len < nlmsg_msg_size(sizeof(*rtm))) { NL_SET_ERR_MSG(extack, "ipv4: Invalid header for multicast route get request"); return -EINVAL; } if (!netlink_strict_get_check(skb)) return nlmsg_parse_deprecated(nlh, sizeof(*rtm), tb, RTA_MAX, rtm_ipv4_policy, extack); rtm = nlmsg_data(nlh); if ((rtm->rtm_src_len && rtm->rtm_src_len != 32) || (rtm->rtm_dst_len && rtm->rtm_dst_len != 32) || rtm->rtm_tos || rtm->rtm_table || rtm->rtm_protocol || rtm->rtm_scope || rtm->rtm_type || rtm->rtm_flags) { NL_SET_ERR_MSG(extack, "ipv4: Invalid values in header for multicast route get request"); return -EINVAL; } err = nlmsg_parse_deprecated_strict(nlh, sizeof(*rtm), tb, RTA_MAX, rtm_ipv4_policy, extack); if (err) return err; if ((tb[RTA_SRC] && !rtm->rtm_src_len) || (tb[RTA_DST] && !rtm->rtm_dst_len)) { NL_SET_ERR_MSG(extack, "ipv4: rtm_src_len and rtm_dst_len must be 32 for IPv4"); return -EINVAL; } for (i = 0; i <= RTA_MAX; i++) { if (!tb[i]) continue; switch (i) { case RTA_SRC: case RTA_DST: case RTA_TABLE: break; default: NL_SET_ERR_MSG(extack, "ipv4: Unsupported attribute in multicast route get request"); return -EINVAL; } } return 0; } static int ipmr_rtm_getroute(struct sk_buff *in_skb, struct nlmsghdr *nlh, struct netlink_ext_ack *extack) { struct net *net = sock_net(in_skb->sk); struct nlattr *tb[RTA_MAX + 1]; struct sk_buff *skb = NULL; struct mfc_cache *cache; struct mr_table *mrt; __be32 src, grp; u32 tableid; int err; err = ipmr_rtm_valid_getroute_req(in_skb, nlh, tb, extack); if (err < 0) goto errout; src = nla_get_in_addr_default(tb[RTA_SRC], 0); grp = nla_get_in_addr_default(tb[RTA_DST], 0); tableid = nla_get_u32_default(tb[RTA_TABLE], 0); mrt = __ipmr_get_table(net, tableid ? tableid : RT_TABLE_DEFAULT); if (!mrt) { err = -ENOENT; goto errout_free; } /* entries are added/deleted only under RTNL */ rcu_read_lock(); cache = ipmr_cache_find(mrt, src, grp); rcu_read_unlock(); if (!cache) { err = -ENOENT; goto errout_free; } skb = nlmsg_new(mroute_msgsize(false, mrt->maxvif), GFP_KERNEL); if (!skb) { err = -ENOBUFS; goto errout_free; } err = ipmr_fill_mroute(mrt, skb, NETLINK_CB(in_skb).portid, nlh->nlmsg_seq, cache, RTM_NEWROUTE, 0); if (err < 0) goto errout_free; err = rtnl_unicast(skb, net, NETLINK_CB(in_skb).portid); errout: return err; errout_free: kfree_skb(skb); goto errout; } static int ipmr_rtm_dumproute(struct sk_buff *skb, struct netlink_callback *cb) { struct fib_dump_filter filter = { .rtnl_held = true, }; int err; if (cb->strict_check) { err = ip_valid_fib_dump_req(sock_net(skb->sk), cb->nlh, &filter, cb); if (err < 0) return err; } if (filter.table_id) { struct mr_table *mrt; mrt = __ipmr_get_table(sock_net(skb->sk), filter.table_id); if (!mrt) { if (rtnl_msg_family(cb->nlh) != RTNL_FAMILY_IPMR) return skb->len; NL_SET_ERR_MSG(cb->extack, "ipv4: MR table does not exist"); return -ENOENT; } err = mr_table_dump(mrt, skb, cb, _ipmr_fill_mroute, &mfc_unres_lock, &filter); return skb->len ? : err; } return mr_rtm_dumproute(skb, cb, ipmr_mr_table_iter, _ipmr_fill_mroute, &mfc_unres_lock, &filter); } static const struct nla_policy rtm_ipmr_policy[RTA_MAX + 1] = { [RTA_SRC] = { .type = NLA_U32 }, [RTA_DST] = { .type = NLA_U32 }, [RTA_IIF] = { .type = NLA_U32 }, [RTA_TABLE] = { .type = NLA_U32 }, [RTA_MULTIPATH] = { .len = sizeof(struct rtnexthop) }, }; static bool ipmr_rtm_validate_proto(unsigned char rtm_protocol) { switch (rtm_protocol) { case RTPROT_STATIC: case RTPROT_MROUTED: return true; } return false; } static int ipmr_nla_get_ttls(const struct nlattr *nla, struct mfcctl *mfcc) { struct rtnexthop *rtnh = nla_data(nla); int remaining = nla_len(nla), vifi = 0; while (rtnh_ok(rtnh, remaining)) { mfcc->mfcc_ttls[vifi] = rtnh->rtnh_hops; if (++vifi == MAXVIFS) break; rtnh = rtnh_next(rtnh, &remaining); } return remaining > 0 ? -EINVAL : vifi; } /* returns < 0 on error, 0 for ADD_MFC and 1 for ADD_MFC_PROXY */ static int rtm_to_ipmr_mfcc(struct net *net, struct nlmsghdr *nlh, struct mfcctl *mfcc, int *mrtsock, struct mr_table **mrtret, struct netlink_ext_ack *extack) { struct net_device *dev = NULL; u32 tblid = RT_TABLE_DEFAULT; struct mr_table *mrt; struct nlattr *attr; struct rtmsg *rtm; int ret, rem; ret = nlmsg_validate_deprecated(nlh, sizeof(*rtm), RTA_MAX, rtm_ipmr_policy, extack); if (ret < 0) goto out; rtm = nlmsg_data(nlh); ret = -EINVAL; if (rtm->rtm_family != RTNL_FAMILY_IPMR || rtm->rtm_dst_len != 32 || rtm->rtm_type != RTN_MULTICAST || rtm->rtm_scope != RT_SCOPE_UNIVERSE || !ipmr_rtm_validate_proto(rtm->rtm_protocol)) goto out; memset(mfcc, 0, sizeof(*mfcc)); mfcc->mfcc_parent = -1; ret = 0; nlmsg_for_each_attr(attr, nlh, sizeof(struct rtmsg), rem) { switch (nla_type(attr)) { case RTA_SRC: mfcc->mfcc_origin.s_addr = nla_get_be32(attr); break; case RTA_DST: mfcc->mfcc_mcastgrp.s_addr = nla_get_be32(attr); break; case RTA_IIF: dev = __dev_get_by_index(net, nla_get_u32(attr)); if (!dev) { ret = -ENODEV; goto out; } break; case RTA_MULTIPATH: if (ipmr_nla_get_ttls(attr, mfcc) < 0) { ret = -EINVAL; goto out; } break; case RTA_PREFSRC: ret = 1; break; case RTA_TABLE: tblid = nla_get_u32(attr); break; } } mrt = __ipmr_get_table(net, tblid); if (!mrt) { ret = -ENOENT; goto out; } *mrtret = mrt; *mrtsock = rtm->rtm_protocol == RTPROT_MROUTED ? 1 : 0; if (dev) mfcc->mfcc_parent = ipmr_find_vif(mrt, dev); out: return ret; } /* takes care of both newroute and delroute */ static int ipmr_rtm_route(struct sk_buff *skb, struct nlmsghdr *nlh, struct netlink_ext_ack *extack) { struct net *net = sock_net(skb->sk); int ret, mrtsock, parent; struct mr_table *tbl; struct mfcctl mfcc; mrtsock = 0; tbl = NULL; ret = rtm_to_ipmr_mfcc(net, nlh, &mfcc, &mrtsock, &tbl, extack); if (ret < 0) return ret; parent = ret ? mfcc.mfcc_parent : -1; if (nlh->nlmsg_type == RTM_NEWROUTE) return ipmr_mfc_add(net, tbl, &mfcc, mrtsock, parent); else return ipmr_mfc_delete(tbl, &mfcc, parent); } static bool ipmr_fill_table(struct mr_table *mrt, struct sk_buff *skb) { u32 queue_len = atomic_read(&mrt->cache_resolve_queue_len); if (nla_put_u32(skb, IPMRA_TABLE_ID, mrt->id) || nla_put_u32(skb, IPMRA_TABLE_CACHE_RES_QUEUE_LEN, queue_len) || nla_put_s32(skb, IPMRA_TABLE_MROUTE_REG_VIF_NUM, mrt->mroute_reg_vif_num) || nla_put_u8(skb, IPMRA_TABLE_MROUTE_DO_ASSERT, mrt->mroute_do_assert) || nla_put_u8(skb, IPMRA_TABLE_MROUTE_DO_PIM, mrt->mroute_do_pim) || nla_put_u8(skb, IPMRA_TABLE_MROUTE_DO_WRVIFWHOLE, mrt->mroute_do_wrvifwhole)) return false; return true; } static bool ipmr_fill_vif(struct mr_table *mrt, u32 vifid, struct sk_buff *skb) { struct net_device *vif_dev; struct nlattr *vif_nest; struct vif_device *vif; vif = &mrt->vif_table[vifid]; vif_dev = rtnl_dereference(vif->dev); /* if the VIF doesn't exist just continue */ if (!vif_dev) return true; vif_nest = nla_nest_start_noflag(skb, IPMRA_VIF); if (!vif_nest) return false; if (nla_put_u32(skb, IPMRA_VIFA_IFINDEX, vif_dev->ifindex) || nla_put_u32(skb, IPMRA_VIFA_VIF_ID, vifid) || nla_put_u16(skb, IPMRA_VIFA_FLAGS, vif->flags) || nla_put_u64_64bit(skb, IPMRA_VIFA_BYTES_IN, vif->bytes_in, IPMRA_VIFA_PAD) || nla_put_u64_64bit(skb, IPMRA_VIFA_BYTES_OUT, vif->bytes_out, IPMRA_VIFA_PAD) || nla_put_u64_64bit(skb, IPMRA_VIFA_PACKETS_IN, vif->pkt_in, IPMRA_VIFA_PAD) || nla_put_u64_64bit(skb, IPMRA_VIFA_PACKETS_OUT, vif->pkt_out, IPMRA_VIFA_PAD) || nla_put_be32(skb, IPMRA_VIFA_LOCAL_ADDR, vif->local) || nla_put_be32(skb, IPMRA_VIFA_REMOTE_ADDR, vif->remote)) { nla_nest_cancel(skb, vif_nest); return false; } nla_nest_end(skb, vif_nest); return true; } static int ipmr_valid_dumplink(const struct nlmsghdr *nlh, struct netlink_ext_ack *extack) { struct ifinfomsg *ifm; if (nlh->nlmsg_len < nlmsg_msg_size(sizeof(*ifm))) { NL_SET_ERR_MSG(extack, "ipv4: Invalid header for ipmr link dump"); return -EINVAL; } if (nlmsg_attrlen(nlh, sizeof(*ifm))) { NL_SET_ERR_MSG(extack, "Invalid data after header in ipmr link dump"); return -EINVAL; } ifm = nlmsg_data(nlh); if (ifm->__ifi_pad || ifm->ifi_type || ifm->ifi_flags || ifm->ifi_change || ifm->ifi_index) { NL_SET_ERR_MSG(extack, "Invalid values in header for ipmr link dump request"); return -EINVAL; } return 0; } static int ipmr_rtm_dumplink(struct sk_buff *skb, struct netlink_callback *cb) { struct net *net = sock_net(skb->sk); struct nlmsghdr *nlh = NULL; unsigned int t = 0, s_t; unsigned int e = 0, s_e; struct mr_table *mrt; if (cb->strict_check) { int err = ipmr_valid_dumplink(cb->nlh, cb->extack); if (err < 0) return err; } s_t = cb->args[0]; s_e = cb->args[1]; ipmr_for_each_table(mrt, net) { struct nlattr *vifs, *af; struct ifinfomsg *hdr; u32 i; if (t < s_t) goto skip_table; nlh = nlmsg_put(skb, NETLINK_CB(cb->skb).portid, cb->nlh->nlmsg_seq, RTM_NEWLINK, sizeof(*hdr), NLM_F_MULTI); if (!nlh) break; hdr = nlmsg_data(nlh); memset(hdr, 0, sizeof(*hdr)); hdr->ifi_family = RTNL_FAMILY_IPMR; af = nla_nest_start_noflag(skb, IFLA_AF_SPEC); if (!af) { nlmsg_cancel(skb, nlh); goto out; } if (!ipmr_fill_table(mrt, skb)) { nlmsg_cancel(skb, nlh); goto out; } vifs = nla_nest_start_noflag(skb, IPMRA_TABLE_VIFS); if (!vifs) { nla_nest_end(skb, af); nlmsg_end(skb, nlh); goto out; } for (i = 0; i < mrt->maxvif; i++) { if (e < s_e) goto skip_entry; if (!ipmr_fill_vif(mrt, i, skb)) { nla_nest_end(skb, vifs); nla_nest_end(skb, af); nlmsg_end(skb, nlh); goto out; } skip_entry: e++; } s_e = 0; e = 0; nla_nest_end(skb, vifs); nla_nest_end(skb, af); nlmsg_end(skb, nlh); skip_table: t++; } out: cb->args[1] = e; cb->args[0] = t; return skb->len; } #ifdef CONFIG_PROC_FS /* The /proc interfaces to multicast routing : * /proc/net/ip_mr_cache & /proc/net/ip_mr_vif */ static void *ipmr_vif_seq_start(struct seq_file *seq, loff_t *pos) __acquires(RCU) { struct mr_vif_iter *iter = seq->private; struct net *net = seq_file_net(seq); struct mr_table *mrt; rcu_read_lock(); mrt = __ipmr_get_table(net, RT_TABLE_DEFAULT); if (!mrt) { rcu_read_unlock(); return ERR_PTR(-ENOENT); } iter->mrt = mrt; return mr_vif_seq_start(seq, pos); } static void ipmr_vif_seq_stop(struct seq_file *seq, void *v) __releases(RCU) { rcu_read_unlock(); } static int ipmr_vif_seq_show(struct seq_file *seq, void *v) { struct mr_vif_iter *iter = seq->private; struct mr_table *mrt = iter->mrt; if (v == SEQ_START_TOKEN) { seq_puts(seq, "Interface BytesIn PktsIn BytesOut PktsOut Flags Local Remote\n"); } else { const struct vif_device *vif = v; const struct net_device *vif_dev; const char *name; vif_dev = vif_dev_read(vif); name = vif_dev ? vif_dev->name : "none"; seq_printf(seq, "%2td %-10s %8ld %7ld %8ld %7ld %05X %08X %08X\n", vif - mrt->vif_table, name, vif->bytes_in, vif->pkt_in, vif->bytes_out, vif->pkt_out, vif->flags, vif->local, vif->remote); } return 0; } static const struct seq_operations ipmr_vif_seq_ops = { .start = ipmr_vif_seq_start, .next = mr_vif_seq_next, .stop = ipmr_vif_seq_stop, .show = ipmr_vif_seq_show, }; static void *ipmr_mfc_seq_start(struct seq_file *seq, loff_t *pos) { struct net *net = seq_file_net(seq); struct mr_table *mrt; mrt = ipmr_get_table(net, RT_TABLE_DEFAULT); if (!mrt) return ERR_PTR(-ENOENT); return mr_mfc_seq_start(seq, pos, mrt, &mfc_unres_lock); } static int ipmr_mfc_seq_show(struct seq_file *seq, void *v) { int n; if (v == SEQ_START_TOKEN) { seq_puts(seq, "Group Origin Iif Pkts Bytes Wrong Oifs\n"); } else { const struct mfc_cache *mfc = v; const struct mr_mfc_iter *it = seq->private; const struct mr_table *mrt = it->mrt; seq_printf(seq, "%08X %08X %-3hd", (__force u32) mfc->mfc_mcastgrp, (__force u32) mfc->mfc_origin, mfc->_c.mfc_parent); if (it->cache != &mrt->mfc_unres_queue) { seq_printf(seq, " %8lu %8lu %8lu", mfc->_c.mfc_un.res.pkt, mfc->_c.mfc_un.res.bytes, mfc->_c.mfc_un.res.wrong_if); for (n = mfc->_c.mfc_un.res.minvif; n < mfc->_c.mfc_un.res.maxvif; n++) { if (VIF_EXISTS(mrt, n) && mfc->_c.mfc_un.res.ttls[n] < 255) seq_printf(seq, " %2d:%-3d", n, mfc->_c.mfc_un.res.ttls[n]); } } else { /* unresolved mfc_caches don't contain * pkt, bytes and wrong_if values */ seq_printf(seq, " %8lu %8lu %8lu", 0ul, 0ul, 0ul); } seq_putc(seq, '\n'); } return 0; } static const struct seq_operations ipmr_mfc_seq_ops = { .start = ipmr_mfc_seq_start, .next = mr_mfc_seq_next, .stop = mr_mfc_seq_stop, .show = ipmr_mfc_seq_show, }; #endif #ifdef CONFIG_IP_PIMSM_V2 static const struct net_protocol pim_protocol = { .handler = pim_rcv, }; #endif static unsigned int ipmr_seq_read(const struct net *net) { return READ_ONCE(net->ipv4.ipmr_seq) + ipmr_rules_seq_read(net); } static int ipmr_dump(struct net *net, struct notifier_block *nb, struct netlink_ext_ack *extack) { return mr_dump(net, nb, RTNL_FAMILY_IPMR, ipmr_rules_dump, ipmr_mr_table_iter, extack); } static const struct fib_notifier_ops ipmr_notifier_ops_template = { .family = RTNL_FAMILY_IPMR, .fib_seq_read = ipmr_seq_read, .fib_dump = ipmr_dump, .owner = THIS_MODULE, }; static int __net_init ipmr_notifier_init(struct net *net) { struct fib_notifier_ops *ops; net->ipv4.ipmr_seq = 0; ops = fib_notifier_ops_register(&ipmr_notifier_ops_template, net); if (IS_ERR(ops)) return PTR_ERR(ops); net->ipv4.ipmr_notifier_ops = ops; return 0; } static void __net_exit ipmr_notifier_exit(struct net *net) { fib_notifier_ops_unregister(net->ipv4.ipmr_notifier_ops); net->ipv4.ipmr_notifier_ops = NULL; } /* Setup for IP multicast routing */ static int __net_init ipmr_net_init(struct net *net) { int err; err = ipmr_notifier_init(net); if (err) goto ipmr_notifier_fail; err = ipmr_rules_init(net); if (err < 0) goto ipmr_rules_fail; #ifdef CONFIG_PROC_FS err = -ENOMEM; if (!proc_create_net("ip_mr_vif", 0, net->proc_net, &ipmr_vif_seq_ops, sizeof(struct mr_vif_iter))) goto proc_vif_fail; if (!proc_create_net("ip_mr_cache", 0, net->proc_net, &ipmr_mfc_seq_ops, sizeof(struct mr_mfc_iter))) goto proc_cache_fail; #endif return 0; #ifdef CONFIG_PROC_FS proc_cache_fail: remove_proc_entry("ip_mr_vif", net->proc_net); proc_vif_fail: rtnl_lock(); ipmr_rules_exit(net); rtnl_unlock(); #endif ipmr_rules_fail: ipmr_notifier_exit(net); ipmr_notifier_fail: return err; } static void __net_exit ipmr_net_exit(struct net *net) { #ifdef CONFIG_PROC_FS remove_proc_entry("ip_mr_cache", net->proc_net); remove_proc_entry("ip_mr_vif", net->proc_net); #endif ipmr_notifier_exit(net); } static void __net_exit ipmr_net_exit_batch(struct list_head *net_list) { struct net *net; rtnl_lock(); list_for_each_entry(net, net_list, exit_list) ipmr_rules_exit(net); rtnl_unlock(); } static struct pernet_operations ipmr_net_ops = { .init = ipmr_net_init, .exit = ipmr_net_exit, .exit_batch = ipmr_net_exit_batch, }; static const struct rtnl_msg_handler ipmr_rtnl_msg_handlers[] __initconst = { {.protocol = RTNL_FAMILY_IPMR, .msgtype = RTM_GETLINK, .dumpit = ipmr_rtm_dumplink}, {.protocol = RTNL_FAMILY_IPMR, .msgtype = RTM_NEWROUTE, .doit = ipmr_rtm_route}, {.protocol = RTNL_FAMILY_IPMR, .msgtype = RTM_DELROUTE, .doit = ipmr_rtm_route}, {.protocol = RTNL_FAMILY_IPMR, .msgtype = RTM_GETROUTE, .doit = ipmr_rtm_getroute, .dumpit = ipmr_rtm_dumproute}, }; int __init ip_mr_init(void) { int err; mrt_cachep = KMEM_CACHE(mfc_cache, SLAB_HWCACHE_ALIGN | SLAB_PANIC); err = register_pernet_subsys(&ipmr_net_ops); if (err) goto reg_pernet_fail; err = register_netdevice_notifier(&ip_mr_notifier); if (err) goto reg_notif_fail; #ifdef CONFIG_IP_PIMSM_V2 if (inet_add_protocol(&pim_protocol, IPPROTO_PIM) < 0) { pr_err("%s: can't add PIM protocol\n", __func__); err = -EAGAIN; goto add_proto_fail; } #endif rtnl_register_many(ipmr_rtnl_msg_handlers); return 0; #ifdef CONFIG_IP_PIMSM_V2 add_proto_fail: unregister_netdevice_notifier(&ip_mr_notifier); #endif reg_notif_fail: unregister_pernet_subsys(&ipmr_net_ops); reg_pernet_fail: kmem_cache_destroy(mrt_cachep); return err; } |
| 192 194 136 137 137 473 475 475 132 132 132 22 22 22 22 22 22 23 23 23 23 389 389 5 5 5 5 15 15 64 64 616 614 617 148 149 163 163 162 948 954 298 65 334 335 332 332 179 179 175 175 5 5 351 353 513 514 405 234 234 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 1522 1523 1524 1525 1526 1527 1528 1529 1530 1531 1532 1533 1534 1535 1536 1537 1538 1539 1540 1541 1542 1543 1544 1545 1546 1547 1548 1549 1550 1551 1552 1553 1554 1555 1556 1557 1558 1559 1560 1561 1562 1563 1564 1565 1566 1567 1568 1569 1570 1571 1572 1573 1574 1575 1576 1577 1578 1579 1580 1581 1582 1583 1584 1585 1586 1587 1588 1589 1590 1591 1592 1593 1594 1595 1596 1597 1598 1599 1600 1601 1602 1603 1604 1605 1606 1607 1608 1609 1610 1611 1612 1613 1614 1615 1616 1617 1618 1619 1620 1621 1622 1623 1624 1625 1626 1627 1628 1629 1630 1631 1632 1633 1634 1635 1636 1637 1638 1639 1640 1641 1642 1643 1644 1645 1646 1647 1648 1649 1650 1651 1652 1653 1654 1655 1656 1657 1658 1659 1660 1661 1662 1663 1664 1665 1666 1667 1668 1669 1670 1671 1672 1673 1674 1675 1676 1677 1678 1679 1680 1681 1682 1683 1684 1685 1686 1687 1688 1689 1690 1691 1692 1693 1694 1695 1696 1697 1698 1699 1700 1701 1702 1703 1704 1705 1706 1707 1708 1709 1710 1711 1712 1713 1714 1715 1716 1717 1718 1719 1720 1721 1722 1723 1724 1725 1726 1727 1728 1729 1730 1731 1732 1733 1734 1735 1736 1737 1738 1739 1740 1741 1742 1743 1744 1745 1746 1747 1748 1749 1750 1751 1752 1753 1754 1755 1756 1757 1758 1759 1760 1761 1762 1763 1764 1765 1766 1767 1768 1769 1770 1771 1772 1773 1774 1775 1776 1777 1778 1779 1780 1781 1782 1783 1784 1785 1786 1787 1788 1789 1790 1791 1792 1793 1794 1795 1796 1797 1798 1799 1800 1801 1802 1803 1804 1805 1806 1807 1808 1809 1810 1811 1812 1813 1814 1815 1816 1817 1818 1819 1820 1821 1822 1823 1824 1825 1826 1827 1828 1829 1830 1831 1832 1833 1834 1835 1836 1837 1838 1839 1840 1841 1842 1843 1844 1845 1846 1847 1848 1849 1850 1851 1852 1853 1854 1855 1856 1857 1858 1859 1860 1861 1862 1863 1864 1865 1866 1867 1868 1869 1870 1871 1872 1873 1874 1875 1876 1877 1878 1879 1880 1881 1882 1883 1884 1885 1886 1887 1888 1889 1890 1891 1892 1893 1894 1895 1896 1897 1898 1899 1900 1901 1902 1903 1904 1905 1906 1907 1908 1909 1910 1911 1912 1913 1914 1915 1916 1917 1918 1919 1920 1921 1922 1923 1924 1925 1926 1927 1928 1929 1930 1931 1932 1933 1934 1935 1936 1937 1938 1939 1940 1941 1942 1943 1944 1945 1946 1947 1948 1949 1950 1951 1952 1953 1954 1955 1956 1957 1958 1959 1960 1961 1962 1963 1964 1965 1966 1967 1968 1969 1970 1971 1972 1973 1974 1975 1976 1977 1978 1979 1980 1981 1982 1983 1984 1985 1986 1987 1988 1989 1990 1991 1992 1993 1994 1995 1996 1997 1998 1999 2000 2001 2002 2003 2004 2005 2006 2007 2008 2009 2010 2011 2012 2013 2014 2015 2016 2017 2018 2019 2020 2021 2022 2023 2024 2025 2026 2027 2028 2029 2030 2031 2032 2033 2034 2035 2036 2037 2038 2039 2040 2041 2042 2043 2044 2045 2046 2047 2048 2049 2050 2051 2052 2053 2054 2055 2056 2057 2058 2059 2060 2061 2062 2063 2064 2065 2066 2067 2068 2069 2070 2071 2072 2073 2074 2075 2076 2077 2078 2079 2080 2081 2082 2083 2084 2085 2086 2087 2088 2089 2090 2091 2092 2093 2094 2095 2096 2097 2098 2099 2100 2101 2102 2103 2104 2105 2106 2107 2108 2109 2110 2111 2112 2113 2114 2115 2116 2117 2118 2119 2120 2121 2122 2123 2124 2125 2126 2127 2128 2129 2130 2131 2132 2133 2134 2135 2136 2137 2138 2139 2140 2141 2142 2143 2144 2145 2146 2147 2148 2149 2150 2151 2152 2153 2154 2155 2156 2157 2158 2159 2160 2161 2162 2163 2164 2165 2166 2167 2168 2169 2170 2171 2172 2173 2174 2175 2176 2177 2178 2179 2180 2181 2182 2183 2184 2185 2186 2187 2188 2189 2190 2191 2192 2193 2194 2195 2196 2197 2198 2199 2200 2201 2202 2203 2204 2205 2206 2207 2208 2209 2210 2211 2212 2213 2214 2215 2216 2217 2218 2219 2220 2221 2222 2223 2224 2225 2226 2227 2228 2229 2230 2231 2232 2233 2234 2235 2236 2237 2238 2239 2240 2241 2242 2243 2244 2245 2246 2247 2248 2249 2250 2251 2252 2253 2254 2255 2256 2257 2258 2259 2260 2261 2262 2263 2264 2265 2266 2267 2268 2269 2270 2271 2272 2273 2274 2275 2276 2277 2278 2279 2280 2281 2282 2283 2284 2285 2286 2287 2288 2289 2290 2291 2292 2293 2294 2295 2296 2297 2298 2299 2300 2301 2302 2303 2304 2305 2306 2307 2308 2309 2310 2311 2312 2313 2314 2315 2316 2317 2318 2319 2320 2321 2322 2323 2324 2325 2326 2327 2328 2329 2330 2331 2332 2333 2334 2335 2336 2337 2338 2339 2340 2341 2342 2343 2344 2345 2346 2347 2348 2349 2350 2351 2352 2353 2354 2355 2356 2357 2358 2359 2360 2361 2362 2363 2364 2365 2366 2367 2368 2369 2370 2371 2372 2373 2374 2375 2376 2377 2378 2379 2380 2381 2382 2383 2384 2385 2386 2387 2388 2389 2390 2391 2392 2393 2394 2395 2396 2397 2398 2399 2400 2401 2402 2403 2404 2405 2406 2407 2408 2409 2410 2411 2412 2413 2414 2415 2416 2417 2418 2419 2420 2421 2422 2423 2424 2425 2426 2427 2428 2429 2430 2431 2432 2433 2434 2435 2436 2437 2438 2439 2440 2441 2442 2443 2444 2445 2446 2447 2448 2449 2450 2451 2452 2453 2454 2455 2456 2457 2458 2459 2460 2461 2462 2463 2464 2465 2466 2467 2468 2469 2470 2471 2472 2473 2474 2475 2476 2477 2478 2479 2480 2481 2482 2483 2484 2485 2486 2487 2488 2489 2490 2491 2492 2493 2494 2495 2496 2497 2498 2499 2500 2501 2502 2503 2504 2505 2506 2507 2508 2509 2510 2511 2512 2513 2514 2515 2516 2517 2518 2519 2520 2521 2522 2523 2524 2525 2526 2527 2528 2529 2530 2531 2532 2533 2534 2535 2536 2537 2538 2539 2540 2541 2542 2543 2544 2545 2546 2547 2548 2549 2550 2551 2552 2553 2554 2555 2556 2557 2558 2559 2560 2561 2562 2563 2564 2565 2566 2567 2568 2569 2570 2571 2572 2573 2574 2575 2576 2577 2578 2579 2580 2581 2582 2583 2584 2585 2586 2587 2588 2589 2590 2591 2592 2593 2594 2595 2596 2597 2598 2599 2600 2601 2602 2603 2604 2605 2606 2607 2608 2609 2610 2611 2612 2613 2614 2615 2616 2617 2618 2619 2620 2621 2622 2623 2624 2625 2626 2627 2628 2629 2630 2631 2632 2633 2634 2635 2636 2637 2638 2639 2640 2641 2642 2643 2644 2645 2646 2647 2648 2649 2650 2651 2652 2653 2654 2655 2656 2657 2658 2659 2660 2661 2662 2663 2664 2665 2666 2667 2668 2669 2670 2671 2672 2673 2674 2675 2676 2677 2678 2679 2680 2681 2682 2683 2684 2685 2686 2687 2688 2689 2690 2691 2692 2693 2694 2695 2696 2697 2698 2699 2700 2701 2702 2703 2704 2705 2706 2707 2708 2709 2710 2711 2712 2713 2714 2715 2716 2717 2718 2719 2720 2721 2722 2723 2724 2725 2726 2727 2728 2729 2730 2731 2732 2733 2734 2735 2736 2737 2738 2739 2740 2741 2742 2743 2744 2745 2746 2747 2748 2749 2750 2751 2752 2753 2754 2755 2756 2757 2758 2759 2760 2761 2762 2763 2764 2765 2766 2767 2768 2769 2770 2771 2772 2773 2774 2775 2776 2777 2778 2779 2780 2781 2782 2783 2784 2785 2786 2787 2788 2789 2790 2791 2792 2793 2794 2795 2796 2797 2798 2799 2800 2801 2802 2803 2804 2805 2806 2807 2808 2809 2810 2811 2812 2813 2814 2815 2816 2817 2818 2819 2820 2821 2822 2823 2824 2825 2826 2827 2828 2829 2830 2831 2832 2833 2834 2835 2836 2837 2838 2839 2840 2841 2842 2843 2844 2845 2846 2847 2848 2849 2850 2851 2852 2853 2854 2855 2856 2857 2858 2859 2860 2861 2862 2863 2864 2865 2866 2867 2868 2869 2870 2871 2872 2873 2874 2875 2876 2877 2878 2879 2880 2881 2882 2883 2884 2885 2886 2887 2888 2889 2890 2891 2892 2893 2894 2895 2896 2897 2898 2899 2900 2901 2902 2903 2904 2905 2906 2907 2908 2909 2910 2911 2912 2913 2914 2915 2916 2917 2918 2919 2920 2921 2922 2923 2924 2925 2926 2927 2928 2929 2930 2931 2932 2933 2934 2935 2936 2937 2938 2939 2940 2941 2942 2943 2944 2945 2946 2947 2948 2949 2950 2951 2952 2953 2954 2955 2956 2957 2958 2959 2960 2961 2962 2963 2964 2965 2966 2967 2968 2969 2970 2971 2972 2973 2974 2975 2976 2977 2978 2979 2980 2981 2982 2983 2984 2985 2986 2987 2988 2989 2990 2991 2992 2993 2994 2995 2996 2997 2998 2999 3000 3001 3002 3003 3004 3005 3006 3007 3008 3009 3010 3011 3012 3013 3014 3015 3016 3017 3018 3019 3020 3021 3022 3023 3024 3025 3026 3027 3028 3029 3030 3031 3032 3033 3034 3035 3036 3037 3038 3039 3040 3041 3042 3043 3044 3045 3046 3047 3048 3049 3050 3051 3052 3053 3054 3055 3056 3057 3058 3059 3060 3061 3062 3063 3064 3065 3066 3067 3068 3069 3070 3071 3072 3073 3074 3075 3076 3077 3078 3079 3080 3081 3082 3083 3084 3085 3086 3087 3088 3089 3090 3091 3092 3093 3094 3095 3096 3097 3098 3099 3100 3101 3102 3103 3104 3105 3106 3107 3108 3109 3110 3111 3112 3113 3114 3115 3116 3117 3118 3119 3120 3121 3122 3123 3124 3125 3126 3127 3128 3129 3130 3131 3132 3133 3134 3135 3136 3137 3138 3139 3140 3141 3142 3143 3144 3145 3146 3147 3148 3149 3150 3151 3152 3153 3154 3155 3156 3157 3158 3159 3160 3161 3162 3163 3164 3165 3166 3167 3168 3169 3170 3171 3172 3173 3174 3175 3176 3177 3178 3179 3180 3181 3182 3183 3184 3185 3186 3187 3188 3189 3190 3191 3192 3193 3194 3195 3196 3197 3198 3199 3200 3201 3202 3203 3204 3205 3206 3207 3208 3209 3210 3211 3212 3213 3214 3215 3216 3217 3218 3219 3220 3221 3222 3223 3224 3225 3226 3227 3228 3229 3230 3231 3232 3233 3234 3235 3236 3237 3238 3239 3240 3241 3242 3243 3244 3245 3246 3247 3248 3249 3250 3251 3252 3253 3254 3255 3256 3257 3258 3259 3260 3261 3262 3263 3264 3265 3266 3267 3268 3269 3270 3271 3272 3273 3274 3275 3276 3277 3278 3279 3280 3281 3282 3283 3284 3285 3286 3287 3288 3289 3290 3291 3292 3293 3294 3295 3296 3297 3298 3299 3300 3301 3302 3303 3304 3305 3306 3307 3308 3309 3310 3311 3312 3313 3314 3315 3316 3317 3318 3319 3320 3321 3322 3323 3324 3325 3326 3327 3328 3329 3330 3331 3332 3333 3334 3335 3336 3337 3338 3339 3340 3341 3342 3343 3344 3345 3346 3347 3348 3349 3350 3351 3352 3353 3354 3355 3356 3357 3358 3359 3360 3361 3362 3363 3364 3365 3366 3367 3368 3369 3370 3371 3372 3373 3374 3375 3376 3377 3378 3379 3380 3381 3382 3383 3384 3385 3386 3387 3388 3389 3390 3391 3392 3393 3394 3395 3396 3397 3398 3399 3400 3401 3402 3403 3404 3405 3406 3407 3408 3409 3410 3411 3412 3413 3414 3415 3416 3417 3418 3419 3420 3421 3422 3423 3424 3425 3426 3427 3428 3429 3430 3431 3432 3433 3434 3435 3436 3437 3438 3439 3440 3441 3442 3443 3444 3445 3446 3447 3448 3449 3450 3451 3452 3453 3454 3455 3456 3457 3458 3459 3460 3461 3462 3463 3464 3465 3466 3467 3468 3469 3470 3471 3472 3473 3474 3475 3476 3477 3478 3479 3480 3481 3482 3483 3484 3485 3486 3487 3488 3489 3490 3491 3492 3493 3494 3495 3496 3497 3498 3499 3500 3501 3502 3503 3504 3505 3506 3507 3508 3509 3510 3511 3512 3513 3514 3515 3516 3517 3518 3519 3520 3521 3522 3523 3524 3525 3526 3527 3528 3529 3530 3531 3532 3533 3534 3535 3536 3537 3538 3539 3540 3541 3542 3543 3544 3545 3546 3547 3548 3549 3550 3551 3552 3553 3554 3555 3556 3557 3558 3559 3560 3561 3562 3563 3564 3565 3566 3567 3568 3569 3570 3571 3572 3573 3574 3575 3576 3577 3578 3579 3580 3581 3582 3583 3584 3585 3586 3587 3588 3589 3590 3591 3592 3593 3594 3595 3596 3597 3598 3599 3600 3601 3602 3603 3604 3605 3606 3607 3608 3609 3610 3611 3612 3613 3614 3615 3616 3617 3618 3619 3620 3621 3622 3623 3624 3625 3626 3627 3628 3629 3630 3631 3632 3633 3634 3635 3636 3637 3638 3639 3640 3641 3642 3643 3644 3645 3646 3647 3648 3649 3650 3651 3652 3653 3654 3655 3656 3657 3658 3659 3660 3661 3662 3663 3664 3665 3666 3667 3668 3669 3670 3671 3672 3673 3674 3675 3676 3677 3678 3679 3680 3681 3682 3683 3684 3685 3686 3687 3688 3689 3690 3691 3692 3693 3694 3695 3696 3697 3698 3699 3700 3701 3702 3703 3704 3705 3706 3707 3708 3709 3710 3711 3712 3713 3714 3715 3716 3717 3718 3719 3720 3721 3722 3723 3724 3725 3726 3727 3728 3729 3730 3731 3732 3733 3734 3735 3736 3737 3738 3739 3740 3741 3742 3743 3744 3745 3746 3747 3748 3749 3750 3751 3752 3753 3754 3755 3756 3757 3758 3759 3760 3761 3762 3763 3764 3765 3766 3767 3768 3769 3770 3771 3772 3773 3774 3775 3776 3777 3778 3779 3780 3781 3782 3783 3784 3785 3786 3787 3788 3789 3790 3791 3792 3793 3794 3795 3796 3797 3798 3799 3800 3801 3802 3803 3804 3805 3806 3807 3808 3809 3810 3811 3812 3813 3814 3815 3816 3817 3818 3819 3820 3821 3822 3823 3824 3825 3826 3827 3828 3829 3830 3831 3832 3833 3834 3835 3836 3837 3838 3839 3840 3841 3842 3843 3844 3845 3846 3847 3848 3849 3850 3851 3852 3853 3854 3855 3856 3857 3858 3859 3860 3861 3862 3863 3864 3865 3866 3867 3868 3869 3870 3871 3872 3873 3874 3875 3876 3877 3878 3879 3880 3881 3882 3883 3884 3885 3886 3887 3888 3889 3890 3891 3892 3893 3894 3895 3896 3897 3898 3899 3900 3901 3902 3903 3904 3905 3906 3907 3908 3909 3910 3911 3912 3913 3914 3915 3916 3917 3918 3919 3920 3921 3922 3923 3924 3925 3926 3927 3928 3929 3930 3931 3932 3933 3934 3935 3936 3937 3938 3939 3940 3941 3942 3943 3944 3945 3946 3947 3948 3949 3950 3951 3952 3953 3954 3955 3956 3957 3958 3959 3960 3961 3962 3963 3964 3965 3966 3967 3968 3969 3970 3971 3972 3973 3974 3975 3976 3977 3978 3979 3980 3981 3982 3983 3984 3985 3986 3987 3988 3989 3990 3991 3992 3993 3994 3995 3996 3997 3998 3999 4000 4001 4002 4003 4004 4005 4006 4007 4008 4009 4010 4011 4012 4013 4014 4015 4016 4017 4018 4019 4020 4021 4022 4023 4024 4025 4026 4027 4028 4029 4030 4031 4032 4033 4034 4035 4036 4037 4038 4039 4040 4041 4042 4043 4044 4045 4046 4047 4048 4049 4050 4051 4052 4053 4054 4055 4056 4057 4058 4059 4060 4061 4062 4063 4064 4065 4066 4067 4068 4069 4070 4071 4072 4073 4074 4075 4076 4077 4078 4079 4080 4081 4082 4083 4084 4085 4086 4087 4088 4089 4090 4091 4092 4093 4094 4095 4096 4097 4098 4099 4100 4101 4102 4103 4104 4105 4106 4107 4108 4109 4110 4111 4112 4113 4114 4115 4116 4117 4118 4119 4120 4121 4122 4123 4124 4125 4126 4127 4128 4129 4130 4131 4132 4133 4134 4135 4136 4137 4138 4139 4140 4141 4142 4143 4144 4145 4146 4147 4148 4149 4150 4151 4152 4153 4154 4155 4156 4157 4158 4159 4160 4161 4162 4163 4164 4165 4166 4167 4168 4169 4170 4171 4172 4173 4174 4175 4176 4177 4178 4179 4180 4181 4182 4183 4184 4185 4186 4187 4188 4189 4190 4191 4192 4193 4194 4195 4196 4197 4198 4199 4200 4201 4202 4203 4204 4205 4206 4207 4208 4209 4210 4211 4212 4213 4214 4215 4216 4217 4218 4219 4220 4221 4222 4223 4224 4225 4226 4227 4228 4229 4230 4231 4232 4233 4234 4235 4236 4237 4238 4239 4240 4241 4242 4243 4244 4245 4246 4247 4248 4249 4250 4251 4252 4253 4254 4255 4256 4257 4258 4259 4260 4261 4262 4263 4264 4265 4266 4267 4268 4269 4270 4271 4272 4273 4274 4275 4276 4277 4278 4279 4280 4281 4282 4283 4284 4285 4286 4287 4288 4289 4290 4291 4292 4293 4294 4295 4296 4297 4298 4299 4300 4301 4302 4303 4304 4305 4306 4307 4308 4309 4310 4311 4312 4313 4314 4315 4316 4317 4318 4319 4320 4321 4322 4323 4324 4325 4326 4327 4328 4329 4330 4331 4332 4333 4334 4335 4336 4337 4338 4339 4340 4341 4342 4343 4344 4345 4346 4347 4348 4349 4350 4351 4352 4353 4354 4355 4356 4357 4358 4359 4360 4361 4362 4363 4364 4365 4366 4367 4368 4369 4370 4371 4372 4373 4374 4375 4376 4377 4378 4379 4380 4381 4382 4383 4384 4385 4386 4387 4388 4389 4390 4391 4392 4393 4394 4395 4396 4397 4398 4399 4400 4401 4402 4403 4404 4405 4406 4407 4408 4409 4410 4411 4412 4413 4414 4415 4416 4417 4418 4419 4420 4421 4422 4423 4424 4425 4426 4427 4428 4429 4430 4431 4432 4433 4434 4435 4436 4437 4438 4439 4440 4441 4442 4443 4444 4445 4446 4447 4448 4449 4450 4451 4452 4453 4454 4455 4456 4457 4458 4459 4460 4461 4462 4463 4464 4465 4466 4467 4468 4469 4470 4471 4472 4473 4474 4475 4476 4477 4478 4479 4480 4481 4482 4483 4484 4485 4486 4487 4488 4489 4490 4491 4492 4493 4494 4495 4496 4497 4498 4499 4500 4501 4502 4503 4504 4505 4506 4507 4508 4509 4510 4511 4512 4513 4514 4515 4516 4517 4518 4519 4520 4521 4522 4523 4524 4525 4526 4527 4528 4529 4530 4531 4532 4533 4534 4535 4536 4537 4538 4539 4540 4541 4542 4543 4544 4545 4546 4547 4548 4549 4550 4551 4552 4553 4554 4555 4556 4557 4558 4559 4560 4561 4562 4563 4564 4565 4566 4567 4568 4569 4570 4571 4572 4573 4574 4575 4576 4577 4578 4579 4580 4581 4582 4583 4584 4585 4586 4587 4588 4589 4590 4591 4592 4593 4594 4595 4596 4597 4598 4599 4600 4601 4602 4603 4604 4605 4606 4607 4608 4609 4610 4611 4612 4613 4614 4615 4616 4617 4618 4619 4620 4621 4622 4623 4624 4625 4626 4627 4628 4629 4630 4631 4632 4633 4634 4635 4636 4637 4638 4639 4640 4641 4642 4643 4644 4645 4646 4647 4648 4649 4650 4651 4652 4653 4654 4655 4656 4657 4658 4659 4660 4661 4662 4663 4664 4665 4666 4667 4668 4669 4670 4671 4672 4673 4674 4675 4676 4677 4678 4679 4680 4681 4682 4683 4684 4685 4686 4687 4688 4689 4690 4691 4692 4693 4694 4695 4696 4697 4698 4699 4700 4701 4702 4703 4704 4705 4706 4707 4708 4709 4710 4711 4712 4713 4714 4715 4716 4717 4718 4719 4720 4721 4722 4723 4724 4725 4726 4727 4728 4729 4730 4731 4732 4733 4734 4735 4736 4737 4738 4739 4740 4741 4742 4743 4744 4745 4746 4747 4748 4749 4750 4751 4752 4753 4754 4755 4756 4757 4758 4759 4760 4761 4762 4763 4764 4765 4766 4767 4768 4769 4770 4771 4772 4773 4774 4775 4776 4777 4778 4779 4780 4781 4782 4783 4784 4785 4786 4787 4788 4789 4790 4791 4792 4793 4794 4795 4796 4797 4798 4799 4800 4801 4802 4803 4804 4805 4806 4807 4808 4809 4810 4811 4812 4813 4814 4815 4816 4817 4818 4819 4820 4821 4822 4823 4824 4825 4826 4827 4828 4829 4830 4831 4832 4833 4834 4835 4836 4837 4838 4839 4840 4841 4842 4843 4844 4845 4846 4847 4848 4849 4850 4851 4852 4853 4854 4855 4856 4857 4858 4859 4860 4861 4862 4863 4864 4865 4866 4867 4868 4869 4870 4871 4872 4873 4874 4875 4876 4877 4878 4879 4880 4881 4882 4883 4884 4885 4886 4887 4888 4889 4890 4891 4892 4893 4894 4895 4896 4897 4898 4899 4900 4901 4902 4903 4904 4905 4906 4907 4908 4909 4910 4911 4912 4913 4914 4915 4916 4917 4918 4919 4920 4921 4922 4923 4924 4925 4926 4927 4928 4929 4930 4931 4932 4933 4934 4935 4936 4937 4938 4939 4940 4941 4942 4943 4944 4945 4946 4947 4948 4949 4950 4951 4952 4953 4954 4955 4956 4957 4958 4959 4960 4961 4962 4963 4964 4965 4966 4967 4968 4969 4970 4971 4972 4973 4974 4975 4976 4977 4978 4979 4980 4981 4982 4983 4984 4985 4986 4987 4988 4989 4990 4991 4992 4993 4994 4995 4996 4997 4998 4999 5000 5001 5002 5003 5004 5005 5006 5007 5008 5009 5010 5011 5012 5013 5014 5015 5016 5017 5018 5019 5020 5021 5022 5023 5024 5025 5026 5027 5028 5029 5030 5031 5032 5033 5034 5035 5036 5037 5038 5039 5040 5041 5042 5043 5044 5045 5046 5047 5048 5049 5050 5051 5052 5053 5054 5055 5056 5057 5058 5059 5060 5061 5062 5063 5064 5065 5066 5067 5068 5069 5070 5071 5072 5073 5074 5075 5076 5077 5078 5079 5080 5081 5082 5083 5084 5085 5086 5087 5088 5089 5090 5091 5092 5093 5094 5095 5096 5097 5098 5099 5100 5101 5102 5103 5104 5105 5106 5107 5108 5109 5110 5111 5112 5113 5114 5115 5116 5117 5118 5119 5120 5121 5122 5123 5124 5125 5126 5127 5128 5129 5130 5131 5132 5133 5134 5135 5136 5137 5138 5139 5140 5141 5142 5143 5144 5145 5146 5147 5148 5149 5150 5151 5152 5153 5154 5155 5156 5157 5158 5159 5160 5161 5162 5163 5164 5165 5166 5167 5168 5169 5170 5171 5172 5173 5174 5175 5176 5177 5178 5179 5180 5181 5182 5183 5184 5185 5186 5187 5188 5189 5190 5191 5192 5193 5194 5195 5196 5197 5198 5199 5200 5201 5202 5203 5204 5205 5206 5207 5208 5209 5210 5211 5212 5213 5214 5215 5216 5217 5218 5219 5220 5221 5222 5223 5224 5225 5226 5227 5228 5229 5230 5231 5232 5233 5234 5235 5236 5237 5238 5239 5240 5241 5242 5243 5244 5245 5246 5247 5248 5249 5250 5251 5252 5253 5254 5255 5256 5257 5258 5259 5260 5261 5262 5263 5264 5265 5266 5267 5268 5269 5270 5271 5272 5273 5274 5275 5276 5277 5278 5279 5280 5281 5282 5283 5284 5285 5286 5287 5288 5289 5290 5291 5292 5293 5294 5295 5296 5297 5298 5299 5300 5301 5302 5303 5304 5305 5306 5307 5308 5309 5310 5311 5312 5313 5314 5315 5316 5317 5318 5319 5320 5321 5322 5323 5324 5325 5326 5327 5328 5329 5330 5331 5332 5333 5334 5335 5336 5337 5338 5339 5340 5341 5342 5343 5344 5345 5346 5347 5348 5349 5350 5351 5352 5353 5354 5355 5356 5357 5358 5359 5360 5361 5362 5363 5364 5365 5366 5367 5368 5369 5370 5371 5372 5373 5374 5375 5376 5377 5378 5379 5380 5381 5382 5383 5384 5385 5386 5387 5388 5389 5390 5391 5392 5393 5394 5395 5396 5397 5398 5399 5400 5401 5402 5403 5404 5405 5406 5407 5408 5409 5410 5411 5412 5413 5414 5415 5416 5417 5418 5419 5420 5421 5422 5423 5424 5425 5426 5427 5428 5429 5430 5431 5432 5433 5434 5435 5436 5437 5438 5439 5440 5441 5442 5443 5444 5445 5446 5447 5448 5449 5450 5451 5452 5453 5454 5455 5456 5457 5458 5459 5460 5461 5462 5463 5464 5465 5466 5467 5468 5469 5470 5471 5472 5473 5474 5475 5476 5477 5478 5479 5480 5481 5482 5483 5484 5485 5486 5487 5488 5489 5490 5491 5492 5493 5494 5495 5496 5497 5498 5499 5500 5501 5502 5503 5504 5505 5506 5507 5508 5509 5510 5511 5512 5513 5514 5515 5516 5517 5518 5519 5520 5521 5522 5523 5524 5525 5526 5527 5528 5529 5530 5531 5532 5533 5534 5535 5536 5537 5538 5539 5540 5541 5542 5543 5544 5545 5546 5547 5548 5549 5550 5551 5552 5553 5554 5555 5556 5557 5558 5559 5560 5561 5562 5563 5564 5565 5566 5567 5568 5569 5570 5571 5572 5573 5574 5575 5576 5577 5578 5579 5580 5581 5582 5583 5584 5585 5586 5587 5588 5589 5590 5591 5592 5593 5594 5595 5596 5597 5598 5599 5600 5601 5602 5603 5604 5605 5606 5607 5608 5609 5610 5611 5612 5613 5614 5615 5616 5617 5618 5619 5620 5621 5622 5623 5624 5625 5626 5627 5628 5629 5630 5631 5632 5633 5634 5635 5636 5637 5638 5639 5640 5641 5642 5643 5644 5645 5646 5647 5648 5649 5650 5651 5652 5653 5654 5655 5656 5657 5658 5659 5660 5661 5662 5663 5664 5665 5666 5667 5668 5669 5670 5671 5672 5673 5674 5675 5676 5677 5678 5679 5680 5681 5682 5683 5684 5685 5686 5687 5688 5689 5690 5691 5692 5693 5694 5695 5696 5697 5698 5699 5700 5701 5702 5703 5704 5705 5706 5707 5708 5709 5710 5711 5712 5713 5714 5715 5716 5717 5718 5719 5720 5721 5722 5723 5724 5725 5726 5727 5728 5729 5730 5731 5732 5733 5734 5735 5736 5737 5738 5739 5740 5741 5742 5743 5744 5745 5746 5747 5748 5749 5750 5751 5752 5753 5754 5755 5756 5757 5758 5759 5760 5761 5762 5763 5764 5765 5766 5767 5768 5769 5770 5771 5772 5773 5774 5775 5776 5777 5778 5779 5780 5781 5782 5783 5784 5785 5786 5787 5788 5789 5790 5791 5792 5793 5794 5795 5796 5797 5798 5799 5800 5801 5802 5803 5804 5805 5806 5807 5808 5809 5810 5811 5812 5813 5814 5815 5816 5817 5818 5819 5820 5821 5822 5823 5824 5825 5826 5827 5828 5829 5830 5831 5832 5833 5834 5835 5836 5837 5838 5839 5840 5841 5842 5843 5844 5845 5846 5847 5848 5849 5850 5851 5852 5853 5854 5855 5856 5857 5858 5859 5860 5861 5862 5863 5864 5865 5866 5867 5868 5869 5870 5871 5872 5873 5874 5875 5876 5877 5878 5879 5880 5881 5882 5883 5884 5885 5886 5887 5888 5889 5890 5891 5892 5893 5894 5895 5896 5897 5898 5899 5900 5901 5902 5903 5904 5905 5906 5907 5908 5909 5910 5911 5912 5913 5914 5915 5916 5917 5918 5919 5920 5921 5922 5923 5924 5925 5926 5927 5928 5929 5930 5931 5932 5933 5934 5935 5936 5937 5938 5939 5940 5941 5942 5943 5944 5945 5946 5947 5948 5949 5950 5951 5952 5953 5954 5955 5956 5957 5958 5959 5960 5961 5962 5963 5964 5965 5966 5967 5968 5969 5970 5971 5972 5973 5974 5975 5976 5977 5978 5979 5980 5981 5982 5983 5984 5985 5986 5987 5988 5989 5990 5991 5992 5993 5994 5995 5996 5997 5998 5999 6000 6001 6002 6003 6004 6005 6006 6007 6008 6009 | // SPDX-License-Identifier: GPL-2.0-or-later /* * Security plug functions * * Copyright (C) 2001 WireX Communications, Inc <chris@wirex.com> * Copyright (C) 2001-2002 Greg Kroah-Hartman <greg@kroah.com> * Copyright (C) 2001 Networks Associates Technology, Inc <ssmalley@nai.com> * Copyright (C) 2016 Mellanox Technologies * Copyright (C) 2023 Microsoft Corporation <paul@paul-moore.com> */ #define pr_fmt(fmt) "LSM: " fmt #include <linux/bpf.h> #include <linux/capability.h> #include <linux/dcache.h> #include <linux/export.h> #include <linux/init.h> #include <linux/kernel.h> #include <linux/kernel_read_file.h> #include <linux/lsm_hooks.h> #include <linux/mman.h> #include <linux/mount.h> #include <linux/personality.h> #include <linux/backing-dev.h> #include <linux/string.h> #include <linux/xattr.h> #include <linux/msg.h> #include <linux/overflow.h> #include <linux/perf_event.h> #include <linux/fs.h> #include <net/flow.h> #include <net/sock.h> #define SECURITY_HOOK_ACTIVE_KEY(HOOK, IDX) security_hook_active_##HOOK##_##IDX /* * Identifier for the LSM static calls. * HOOK is an LSM hook as defined in linux/lsm_hookdefs.h * IDX is the index of the static call. 0 <= NUM < MAX_LSM_COUNT */ #define LSM_STATIC_CALL(HOOK, IDX) lsm_static_call_##HOOK##_##IDX /* * Call the macro M for each LSM hook MAX_LSM_COUNT times. */ #define LSM_LOOP_UNROLL(M, ...) \ do { \ UNROLL(MAX_LSM_COUNT, M, __VA_ARGS__) \ } while (0) #define LSM_DEFINE_UNROLL(M, ...) UNROLL(MAX_LSM_COUNT, M, __VA_ARGS__) /* * These are descriptions of the reasons that can be passed to the * security_locked_down() LSM hook. Placing this array here allows * all security modules to use the same descriptions for auditing * purposes. */ const char *const lockdown_reasons[LOCKDOWN_CONFIDENTIALITY_MAX + 1] = { [LOCKDOWN_NONE] = "none", [LOCKDOWN_MODULE_SIGNATURE] = "unsigned module loading", [LOCKDOWN_DEV_MEM] = "/dev/mem,kmem,port", [LOCKDOWN_EFI_TEST] = "/dev/efi_test access", [LOCKDOWN_KEXEC] = "kexec of unsigned images", [LOCKDOWN_HIBERNATION] = "hibernation", [LOCKDOWN_PCI_ACCESS] = "direct PCI access", [LOCKDOWN_IOPORT] = "raw io port access", [LOCKDOWN_MSR] = "raw MSR access", [LOCKDOWN_ACPI_TABLES] = "modifying ACPI tables", [LOCKDOWN_DEVICE_TREE] = "modifying device tree contents", [LOCKDOWN_PCMCIA_CIS] = "direct PCMCIA CIS storage", [LOCKDOWN_TIOCSSERIAL] = "reconfiguration of serial port IO", [LOCKDOWN_MODULE_PARAMETERS] = "unsafe module parameters", [LOCKDOWN_MMIOTRACE] = "unsafe mmio", [LOCKDOWN_DEBUGFS] = "debugfs access", [LOCKDOWN_XMON_WR] = "xmon write access", [LOCKDOWN_BPF_WRITE_USER] = "use of bpf to write user RAM", [LOCKDOWN_DBG_WRITE_KERNEL] = "use of kgdb/kdb to write kernel RAM", [LOCKDOWN_RTAS_ERROR_INJECTION] = "RTAS error injection", [LOCKDOWN_INTEGRITY_MAX] = "integrity", [LOCKDOWN_KCORE] = "/proc/kcore access", [LOCKDOWN_KPROBES] = "use of kprobes", [LOCKDOWN_BPF_READ_KERNEL] = "use of bpf to read kernel RAM", [LOCKDOWN_DBG_READ_KERNEL] = "use of kgdb/kdb to read kernel RAM", [LOCKDOWN_PERF] = "unsafe use of perf", [LOCKDOWN_TRACEFS] = "use of tracefs", [LOCKDOWN_XMON_RW] = "xmon read and write access", [LOCKDOWN_XFRM_SECRET] = "xfrm SA secret", [LOCKDOWN_CONFIDENTIALITY_MAX] = "confidentiality", }; static BLOCKING_NOTIFIER_HEAD(blocking_lsm_notifier_chain); static struct kmem_cache *lsm_file_cache; static struct kmem_cache *lsm_inode_cache; char *lsm_names; static struct lsm_blob_sizes blob_sizes __ro_after_init; /* Boot-time LSM user choice */ static __initdata const char *chosen_lsm_order; static __initdata const char *chosen_major_lsm; static __initconst const char *const builtin_lsm_order = CONFIG_LSM; /* Ordered list of LSMs to initialize. */ static __initdata struct lsm_info *ordered_lsms[MAX_LSM_COUNT + 1]; static __initdata struct lsm_info *exclusive; #ifdef CONFIG_HAVE_STATIC_CALL #define LSM_HOOK_TRAMP(NAME, NUM) \ &STATIC_CALL_TRAMP(LSM_STATIC_CALL(NAME, NUM)) #else #define LSM_HOOK_TRAMP(NAME, NUM) NULL #endif /* * Define static calls and static keys for each LSM hook. */ #define DEFINE_LSM_STATIC_CALL(NUM, NAME, RET, ...) \ DEFINE_STATIC_CALL_NULL(LSM_STATIC_CALL(NAME, NUM), \ *((RET(*)(__VA_ARGS__))NULL)); \ DEFINE_STATIC_KEY_FALSE(SECURITY_HOOK_ACTIVE_KEY(NAME, NUM)); #define LSM_HOOK(RET, DEFAULT, NAME, ...) \ LSM_DEFINE_UNROLL(DEFINE_LSM_STATIC_CALL, NAME, RET, __VA_ARGS__) #include <linux/lsm_hook_defs.h> #undef LSM_HOOK #undef DEFINE_LSM_STATIC_CALL /* * Initialise a table of static calls for each LSM hook. * DEFINE_STATIC_CALL_NULL invocation above generates a key (STATIC_CALL_KEY) * and a trampoline (STATIC_CALL_TRAMP) which are used to call * __static_call_update when updating the static call. * * The static calls table is used by early LSMs, some architectures can fault on * unaligned accesses and the fault handling code may not be ready by then. * Thus, the static calls table should be aligned to avoid any unhandled faults * in early init. */ struct lsm_static_calls_table static_calls_table __ro_after_init __aligned(sizeof(u64)) = { #define INIT_LSM_STATIC_CALL(NUM, NAME) \ (struct lsm_static_call) { \ .key = &STATIC_CALL_KEY(LSM_STATIC_CALL(NAME, NUM)), \ .trampoline = LSM_HOOK_TRAMP(NAME, NUM), \ .active = &SECURITY_HOOK_ACTIVE_KEY(NAME, NUM), \ }, #define LSM_HOOK(RET, DEFAULT, NAME, ...) \ .NAME = { \ LSM_DEFINE_UNROLL(INIT_LSM_STATIC_CALL, NAME) \ }, #include <linux/lsm_hook_defs.h> #undef LSM_HOOK #undef INIT_LSM_STATIC_CALL }; static __initdata bool debug; #define init_debug(...) \ do { \ if (debug) \ pr_info(__VA_ARGS__); \ } while (0) static bool __init is_enabled(struct lsm_info *lsm) { if (!lsm->enabled) return false; return *lsm->enabled; } /* Mark an LSM's enabled flag. */ static int lsm_enabled_true __initdata = 1; static int lsm_enabled_false __initdata = 0; static void __init set_enabled(struct lsm_info *lsm, bool enabled) { /* * When an LSM hasn't configured an enable variable, we can use * a hard-coded location for storing the default enabled state. */ if (!lsm->enabled) { if (enabled) lsm->enabled = &lsm_enabled_true; else lsm->enabled = &lsm_enabled_false; } else if (lsm->enabled == &lsm_enabled_true) { if (!enabled) lsm->enabled = &lsm_enabled_false; } else if (lsm->enabled == &lsm_enabled_false) { if (enabled) lsm->enabled = &lsm_enabled_true; } else { *lsm->enabled = enabled; } } /* Is an LSM already listed in the ordered LSMs list? */ static bool __init exists_ordered_lsm(struct lsm_info *lsm) { struct lsm_info **check; for (check = ordered_lsms; *check; check++) if (*check == lsm) return true; return false; } /* Append an LSM to the list of ordered LSMs to initialize. */ static int last_lsm __initdata; static void __init append_ordered_lsm(struct lsm_info *lsm, const char *from) { /* Ignore duplicate selections. */ if (exists_ordered_lsm(lsm)) return; if (WARN(last_lsm == MAX_LSM_COUNT, "%s: out of LSM static calls!?\n", from)) return; /* Enable this LSM, if it is not already set. */ if (!lsm->enabled) lsm->enabled = &lsm_enabled_true; ordered_lsms[last_lsm++] = lsm; init_debug("%s ordered: %s (%s)\n", from, lsm->name, is_enabled(lsm) ? "enabled" : "disabled"); } /* Is an LSM allowed to be initialized? */ static bool __init lsm_allowed(struct lsm_info *lsm) { /* Skip if the LSM is disabled. */ if (!is_enabled(lsm)) return false; /* Not allowed if another exclusive LSM already initialized. */ if ((lsm->flags & LSM_FLAG_EXCLUSIVE) && exclusive) { init_debug("exclusive disabled: %s\n", lsm->name); return false; } return true; } static void __init lsm_set_blob_size(int *need, int *lbs) { int offset; if (*need <= 0) return; offset = ALIGN(*lbs, sizeof(void *)); *lbs = offset + *need; *need = offset; } static void __init lsm_set_blob_sizes(struct lsm_blob_sizes *needed) { if (!needed) return; lsm_set_blob_size(&needed->lbs_cred, &blob_sizes.lbs_cred); lsm_set_blob_size(&needed->lbs_file, &blob_sizes.lbs_file); lsm_set_blob_size(&needed->lbs_ib, &blob_sizes.lbs_ib); /* * The inode blob gets an rcu_head in addition to * what the modules might need. */ if (needed->lbs_inode && blob_sizes.lbs_inode == 0) blob_sizes.lbs_inode = sizeof(struct rcu_head); lsm_set_blob_size(&needed->lbs_inode, &blob_sizes.lbs_inode); lsm_set_blob_size(&needed->lbs_ipc, &blob_sizes.lbs_ipc); lsm_set_blob_size(&needed->lbs_key, &blob_sizes.lbs_key); lsm_set_blob_size(&needed->lbs_msg_msg, &blob_sizes.lbs_msg_msg); lsm_set_blob_size(&needed->lbs_perf_event, &blob_sizes.lbs_perf_event); lsm_set_blob_size(&needed->lbs_sock, &blob_sizes.lbs_sock); lsm_set_blob_size(&needed->lbs_superblock, &blob_sizes.lbs_superblock); lsm_set_blob_size(&needed->lbs_task, &blob_sizes.lbs_task); lsm_set_blob_size(&needed->lbs_tun_dev, &blob_sizes.lbs_tun_dev); lsm_set_blob_size(&needed->lbs_xattr_count, &blob_sizes.lbs_xattr_count); lsm_set_blob_size(&needed->lbs_bdev, &blob_sizes.lbs_bdev); } /* Prepare LSM for initialization. */ static void __init prepare_lsm(struct lsm_info *lsm) { int enabled = lsm_allowed(lsm); /* Record enablement (to handle any following exclusive LSMs). */ set_enabled(lsm, enabled); /* If enabled, do pre-initialization work. */ if (enabled) { if ((lsm->flags & LSM_FLAG_EXCLUSIVE) && !exclusive) { exclusive = lsm; init_debug("exclusive chosen: %s\n", lsm->name); } lsm_set_blob_sizes(lsm->blobs); } } /* Initialize a given LSM, if it is enabled. */ static void __init initialize_lsm(struct lsm_info *lsm) { if (is_enabled(lsm)) { int ret; init_debug("initializing %s\n", lsm->name); ret = lsm->init(); WARN(ret, "%s failed to initialize: %d\n", lsm->name, ret); } } /* * Current index to use while initializing the lsm id list. */ u32 lsm_active_cnt __ro_after_init; const struct lsm_id *lsm_idlist[MAX_LSM_COUNT]; /* Populate ordered LSMs list from comma-separated LSM name list. */ static void __init ordered_lsm_parse(const char *order, const char *origin) { struct lsm_info *lsm; char *sep, *name, *next; /* LSM_ORDER_FIRST is always first. */ for (lsm = __start_lsm_info; lsm < __end_lsm_info; lsm++) { if (lsm->order == LSM_ORDER_FIRST) append_ordered_lsm(lsm, " first"); } /* Process "security=", if given. */ if (chosen_major_lsm) { struct lsm_info *major; /* * To match the original "security=" behavior, this * explicitly does NOT fallback to another Legacy Major * if the selected one was separately disabled: disable * all non-matching Legacy Major LSMs. */ for (major = __start_lsm_info; major < __end_lsm_info; major++) { if ((major->flags & LSM_FLAG_LEGACY_MAJOR) && strcmp(major->name, chosen_major_lsm) != 0) { set_enabled(major, false); init_debug("security=%s disabled: %s (only one legacy major LSM)\n", chosen_major_lsm, major->name); } } } sep = kstrdup(order, GFP_KERNEL); next = sep; /* Walk the list, looking for matching LSMs. */ while ((name = strsep(&next, ",")) != NULL) { bool found = false; for (lsm = __start_lsm_info; lsm < __end_lsm_info; lsm++) { if (strcmp(lsm->name, name) == 0) { if (lsm->order == LSM_ORDER_MUTABLE) append_ordered_lsm(lsm, origin); found = true; } } if (!found) init_debug("%s ignored: %s (not built into kernel)\n", origin, name); } /* Process "security=", if given. */ if (chosen_major_lsm) { for (lsm = __start_lsm_info; lsm < __end_lsm_info; lsm++) { if (exists_ordered_lsm(lsm)) continue; if (strcmp(lsm->name, chosen_major_lsm) == 0) append_ordered_lsm(lsm, "security="); } } /* LSM_ORDER_LAST is always last. */ for (lsm = __start_lsm_info; lsm < __end_lsm_info; lsm++) { if (lsm->order == LSM_ORDER_LAST) append_ordered_lsm(lsm, " last"); } /* Disable all LSMs not in the ordered list. */ for (lsm = __start_lsm_info; lsm < __end_lsm_info; lsm++) { if (exists_ordered_lsm(lsm)) continue; set_enabled(lsm, false); init_debug("%s skipped: %s (not in requested order)\n", origin, lsm->name); } kfree(sep); } static void __init lsm_static_call_init(struct security_hook_list *hl) { struct lsm_static_call *scall = hl->scalls; int i; for (i = 0; i < MAX_LSM_COUNT; i++) { /* Update the first static call that is not used yet */ if (!scall->hl) { __static_call_update(scall->key, scall->trampoline, hl->hook.lsm_func_addr); scall->hl = hl; static_branch_enable(scall->active); return; } scall++; } panic("%s - Ran out of static slots.\n", __func__); } static void __init lsm_early_cred(struct cred *cred); static void __init lsm_early_task(struct task_struct *task); static int lsm_append(const char *new, char **result); static void __init report_lsm_order(void) { struct lsm_info **lsm, *early; int first = 0; pr_info("initializing lsm="); /* Report each enabled LSM name, comma separated. */ for (early = __start_early_lsm_info; early < __end_early_lsm_info; early++) if (is_enabled(early)) pr_cont("%s%s", first++ == 0 ? "" : ",", early->name); for (lsm = ordered_lsms; *lsm; lsm++) if (is_enabled(*lsm)) pr_cont("%s%s", first++ == 0 ? "" : ",", (*lsm)->name); pr_cont("\n"); } static void __init ordered_lsm_init(void) { struct lsm_info **lsm; if (chosen_lsm_order) { if (chosen_major_lsm) { pr_warn("security=%s is ignored because it is superseded by lsm=%s\n", chosen_major_lsm, chosen_lsm_order); chosen_major_lsm = NULL; } ordered_lsm_parse(chosen_lsm_order, "cmdline"); } else ordered_lsm_parse(builtin_lsm_order, "builtin"); for (lsm = ordered_lsms; *lsm; lsm++) prepare_lsm(*lsm); report_lsm_order(); init_debug("cred blob size = %d\n", blob_sizes.lbs_cred); init_debug("file blob size = %d\n", blob_sizes.lbs_file); init_debug("ib blob size = %d\n", blob_sizes.lbs_ib); init_debug("inode blob size = %d\n", blob_sizes.lbs_inode); init_debug("ipc blob size = %d\n", blob_sizes.lbs_ipc); #ifdef CONFIG_KEYS init_debug("key blob size = %d\n", blob_sizes.lbs_key); #endif /* CONFIG_KEYS */ init_debug("msg_msg blob size = %d\n", blob_sizes.lbs_msg_msg); init_debug("sock blob size = %d\n", blob_sizes.lbs_sock); init_debug("superblock blob size = %d\n", blob_sizes.lbs_superblock); init_debug("perf event blob size = %d\n", blob_sizes.lbs_perf_event); init_debug("task blob size = %d\n", blob_sizes.lbs_task); init_debug("tun device blob size = %d\n", blob_sizes.lbs_tun_dev); init_debug("xattr slots = %d\n", blob_sizes.lbs_xattr_count); init_debug("bdev blob size = %d\n", blob_sizes.lbs_bdev); /* * Create any kmem_caches needed for blobs */ if (blob_sizes.lbs_file) lsm_file_cache = kmem_cache_create("lsm_file_cache", blob_sizes.lbs_file, 0, SLAB_PANIC, NULL); if (blob_sizes.lbs_inode) lsm_inode_cache = kmem_cache_create("lsm_inode_cache", blob_sizes.lbs_inode, 0, SLAB_PANIC, NULL); lsm_early_cred((struct cred *) current->cred); lsm_early_task(current); for (lsm = ordered_lsms; *lsm; lsm++) initialize_lsm(*lsm); } int __init early_security_init(void) { struct lsm_info *lsm; for (lsm = __start_early_lsm_info; lsm < __end_early_lsm_info; lsm++) { if (!lsm->enabled) lsm->enabled = &lsm_enabled_true; prepare_lsm(lsm); initialize_lsm(lsm); } return 0; } /** * security_init - initializes the security framework * * This should be called early in the kernel initialization sequence. */ int __init security_init(void) { struct lsm_info *lsm; init_debug("legacy security=%s\n", chosen_major_lsm ? : " *unspecified*"); init_debug(" CONFIG_LSM=%s\n", builtin_lsm_order); init_debug("boot arg lsm=%s\n", chosen_lsm_order ? : " *unspecified*"); /* * Append the names of the early LSM modules now that kmalloc() is * available */ for (lsm = __start_early_lsm_info; lsm < __end_early_lsm_info; lsm++) { init_debug(" early started: %s (%s)\n", lsm->name, is_enabled(lsm) ? "enabled" : "disabled"); if (lsm->enabled) lsm_append(lsm->name, &lsm_names); } /* Load LSMs in specified order. */ ordered_lsm_init(); return 0; } /* Save user chosen LSM */ static int __init choose_major_lsm(char *str) { chosen_major_lsm = str; return 1; } __setup("security=", choose_major_lsm); /* Explicitly choose LSM initialization order. */ static int __init choose_lsm_order(char *str) { chosen_lsm_order = str; return 1; } __setup("lsm=", choose_lsm_order); /* Enable LSM order debugging. */ static int __init enable_debug(char *str) { debug = true; return 1; } __setup("lsm.debug", enable_debug); static bool match_last_lsm(const char *list, const char *lsm) { const char *last; if (WARN_ON(!list || !lsm)) return false; last = strrchr(list, ','); if (last) /* Pass the comma, strcmp() will check for '\0' */ last++; else last = list; return !strcmp(last, lsm); } static int lsm_append(const char *new, char **result) { char *cp; if (*result == NULL) { *result = kstrdup(new, GFP_KERNEL); if (*result == NULL) return -ENOMEM; } else { /* Check if it is the last registered name */ if (match_last_lsm(*result, new)) return 0; cp = kasprintf(GFP_KERNEL, "%s,%s", *result, new); if (cp == NULL) return -ENOMEM; kfree(*result); *result = cp; } return 0; } /** * security_add_hooks - Add a modules hooks to the hook lists. * @hooks: the hooks to add * @count: the number of hooks to add * @lsmid: the identification information for the security module * * Each LSM has to register its hooks with the infrastructure. */ void __init security_add_hooks(struct security_hook_list *hooks, int count, const struct lsm_id *lsmid) { int i; /* * A security module may call security_add_hooks() more * than once during initialization, and LSM initialization * is serialized. Landlock is one such case. * Look at the previous entry, if there is one, for duplication. */ if (lsm_active_cnt == 0 || lsm_idlist[lsm_active_cnt - 1] != lsmid) { if (lsm_active_cnt >= MAX_LSM_COUNT) panic("%s Too many LSMs registered.\n", __func__); lsm_idlist[lsm_active_cnt++] = lsmid; } for (i = 0; i < count; i++) { hooks[i].lsmid = lsmid; lsm_static_call_init(&hooks[i]); } /* * Don't try to append during early_security_init(), we'll come back * and fix this up afterwards. */ if (slab_is_available()) { if (lsm_append(lsmid->name, &lsm_names) < 0) panic("%s - Cannot get early memory.\n", __func__); } } int call_blocking_lsm_notifier(enum lsm_event event, void *data) { return blocking_notifier_call_chain(&blocking_lsm_notifier_chain, event, data); } EXPORT_SYMBOL(call_blocking_lsm_notifier); int register_blocking_lsm_notifier(struct notifier_block *nb) { return blocking_notifier_chain_register(&blocking_lsm_notifier_chain, nb); } EXPORT_SYMBOL(register_blocking_lsm_notifier); int unregister_blocking_lsm_notifier(struct notifier_block *nb) { return blocking_notifier_chain_unregister(&blocking_lsm_notifier_chain, nb); } EXPORT_SYMBOL(unregister_blocking_lsm_notifier); /** * lsm_blob_alloc - allocate a composite blob * @dest: the destination for the blob * @size: the size of the blob * @gfp: allocation type * * Allocate a blob for all the modules * * Returns 0, or -ENOMEM if memory can't be allocated. */ static int lsm_blob_alloc(void **dest, size_t size, gfp_t gfp) { if (size == 0) { *dest = NULL; return 0; } *dest = kzalloc(size, gfp); if (*dest == NULL) return -ENOMEM; return 0; } /** * lsm_cred_alloc - allocate a composite cred blob * @cred: the cred that needs a blob * @gfp: allocation type * * Allocate the cred blob for all the modules * * Returns 0, or -ENOMEM if memory can't be allocated. */ static int lsm_cred_alloc(struct cred *cred, gfp_t gfp) { return lsm_blob_alloc(&cred->security, blob_sizes.lbs_cred, gfp); } /** * lsm_early_cred - during initialization allocate a composite cred blob * @cred: the cred that needs a blob * * Allocate the cred blob for all the modules */ static void __init lsm_early_cred(struct cred *cred) { int rc = lsm_cred_alloc(cred, GFP_KERNEL); if (rc) panic("%s: Early cred alloc failed.\n", __func__); } /** * lsm_file_alloc - allocate a composite file blob * @file: the file that needs a blob * * Allocate the file blob for all the modules * * Returns 0, or -ENOMEM if memory can't be allocated. */ static int lsm_file_alloc(struct file *file) { if (!lsm_file_cache) { file->f_security = NULL; return 0; } file->f_security = kmem_cache_zalloc(lsm_file_cache, GFP_KERNEL); if (file->f_security == NULL) return -ENOMEM; return 0; } /** * lsm_inode_alloc - allocate a composite inode blob * @inode: the inode that needs a blob * @gfp: allocation flags * * Allocate the inode blob for all the modules * * Returns 0, or -ENOMEM if memory can't be allocated. */ static int lsm_inode_alloc(struct inode *inode, gfp_t gfp) { if (!lsm_inode_cache) { inode->i_security = NULL; return 0; } inode->i_security = kmem_cache_zalloc(lsm_inode_cache, gfp); if (inode->i_security == NULL) return -ENOMEM; return 0; } /** * lsm_task_alloc - allocate a composite task blob * @task: the task that needs a blob * * Allocate the task blob for all the modules * * Returns 0, or -ENOMEM if memory can't be allocated. */ static int lsm_task_alloc(struct task_struct *task) { return lsm_blob_alloc(&task->security, blob_sizes.lbs_task, GFP_KERNEL); } /** * lsm_ipc_alloc - allocate a composite ipc blob * @kip: the ipc that needs a blob * * Allocate the ipc blob for all the modules * * Returns 0, or -ENOMEM if memory can't be allocated. */ static int lsm_ipc_alloc(struct kern_ipc_perm *kip) { return lsm_blob_alloc(&kip->security, blob_sizes.lbs_ipc, GFP_KERNEL); } #ifdef CONFIG_KEYS /** * lsm_key_alloc - allocate a composite key blob * @key: the key that needs a blob * * Allocate the key blob for all the modules * * Returns 0, or -ENOMEM if memory can't be allocated. */ static int lsm_key_alloc(struct key *key) { return lsm_blob_alloc(&key->security, blob_sizes.lbs_key, GFP_KERNEL); } #endif /* CONFIG_KEYS */ /** * lsm_msg_msg_alloc - allocate a composite msg_msg blob * @mp: the msg_msg that needs a blob * * Allocate the ipc blob for all the modules * * Returns 0, or -ENOMEM if memory can't be allocated. */ static int lsm_msg_msg_alloc(struct msg_msg *mp) { return lsm_blob_alloc(&mp->security, blob_sizes.lbs_msg_msg, GFP_KERNEL); } /** * lsm_bdev_alloc - allocate a composite block_device blob * @bdev: the block_device that needs a blob * * Allocate the block_device blob for all the modules * * Returns 0, or -ENOMEM if memory can't be allocated. */ static int lsm_bdev_alloc(struct block_device *bdev) { if (blob_sizes.lbs_bdev == 0) { bdev->bd_security = NULL; return 0; } bdev->bd_security = kzalloc(blob_sizes.lbs_bdev, GFP_KERNEL); if (!bdev->bd_security) return -ENOMEM; return 0; } /** * lsm_early_task - during initialization allocate a composite task blob * @task: the task that needs a blob * * Allocate the task blob for all the modules */ static void __init lsm_early_task(struct task_struct *task) { int rc = lsm_task_alloc(task); if (rc) panic("%s: Early task alloc failed.\n", __func__); } /** * lsm_superblock_alloc - allocate a composite superblock blob * @sb: the superblock that needs a blob * * Allocate the superblock blob for all the modules * * Returns 0, or -ENOMEM if memory can't be allocated. */ static int lsm_superblock_alloc(struct super_block *sb) { return lsm_blob_alloc(&sb->s_security, blob_sizes.lbs_superblock, GFP_KERNEL); } /** * lsm_fill_user_ctx - Fill a user space lsm_ctx structure * @uctx: a userspace LSM context to be filled * @uctx_len: available uctx size (input), used uctx size (output) * @val: the new LSM context value * @val_len: the size of the new LSM context value * @id: LSM id * @flags: LSM defined flags * * Fill all of the fields in a userspace lsm_ctx structure. If @uctx is NULL * simply calculate the required size to output via @utc_len and return * success. * * Returns 0 on success, -E2BIG if userspace buffer is not large enough, * -EFAULT on a copyout error, -ENOMEM if memory can't be allocated. */ int lsm_fill_user_ctx(struct lsm_ctx __user *uctx, u32 *uctx_len, void *val, size_t val_len, u64 id, u64 flags) { struct lsm_ctx *nctx = NULL; size_t nctx_len; int rc = 0; nctx_len = ALIGN(struct_size(nctx, ctx, val_len), sizeof(void *)); if (nctx_len > *uctx_len) { rc = -E2BIG; goto out; } /* no buffer - return success/0 and set @uctx_len to the req size */ if (!uctx) goto out; nctx = kzalloc(nctx_len, GFP_KERNEL); if (nctx == NULL) { rc = -ENOMEM; goto out; } nctx->id = id; nctx->flags = flags; nctx->len = nctx_len; nctx->ctx_len = val_len; memcpy(nctx->ctx, val, val_len); if (copy_to_user(uctx, nctx, nctx_len)) rc = -EFAULT; out: kfree(nctx); *uctx_len = nctx_len; return rc; } /* * The default value of the LSM hook is defined in linux/lsm_hook_defs.h and * can be accessed with: * * LSM_RET_DEFAULT(<hook_name>) * * The macros below define static constants for the default value of each * LSM hook. */ #define LSM_RET_DEFAULT(NAME) (NAME##_default) #define DECLARE_LSM_RET_DEFAULT_void(DEFAULT, NAME) #define DECLARE_LSM_RET_DEFAULT_int(DEFAULT, NAME) \ static const int __maybe_unused LSM_RET_DEFAULT(NAME) = (DEFAULT); #define LSM_HOOK(RET, DEFAULT, NAME, ...) \ DECLARE_LSM_RET_DEFAULT_##RET(DEFAULT, NAME) #include <linux/lsm_hook_defs.h> #undef LSM_HOOK /* * Hook list operation macros. * * call_void_hook: * This is a hook that does not return a value. * * call_int_hook: * This is a hook that returns a value. */ #define __CALL_STATIC_VOID(NUM, HOOK, ...) \ do { \ if (static_branch_unlikely(&SECURITY_HOOK_ACTIVE_KEY(HOOK, NUM))) { \ static_call(LSM_STATIC_CALL(HOOK, NUM))(__VA_ARGS__); \ } \ } while (0); #define call_void_hook(HOOK, ...) \ do { \ LSM_LOOP_UNROLL(__CALL_STATIC_VOID, HOOK, __VA_ARGS__); \ } while (0) #define __CALL_STATIC_INT(NUM, R, HOOK, LABEL, ...) \ do { \ if (static_branch_unlikely(&SECURITY_HOOK_ACTIVE_KEY(HOOK, NUM))) { \ R = static_call(LSM_STATIC_CALL(HOOK, NUM))(__VA_ARGS__); \ if (R != LSM_RET_DEFAULT(HOOK)) \ goto LABEL; \ } \ } while (0); #define call_int_hook(HOOK, ...) \ ({ \ __label__ OUT; \ int RC = LSM_RET_DEFAULT(HOOK); \ \ LSM_LOOP_UNROLL(__CALL_STATIC_INT, RC, HOOK, OUT, __VA_ARGS__); \ OUT: \ RC; \ }) #define lsm_for_each_hook(scall, NAME) \ for (scall = static_calls_table.NAME; \ scall - static_calls_table.NAME < MAX_LSM_COUNT; scall++) \ if (static_key_enabled(&scall->active->key)) /* Security operations */ /** * security_binder_set_context_mgr() - Check if becoming binder ctx mgr is ok * @mgr: task credentials of current binder process * * Check whether @mgr is allowed to be the binder context manager. * * Return: Return 0 if permission is granted. */ int security_binder_set_context_mgr(const struct cred *mgr) { return call_int_hook(binder_set_context_mgr, mgr); } /** * security_binder_transaction() - Check if a binder transaction is allowed * @from: sending process * @to: receiving process * * Check whether @from is allowed to invoke a binder transaction call to @to. * * Return: Returns 0 if permission is granted. */ int security_binder_transaction(const struct cred *from, const struct cred *to) { return call_int_hook(binder_transaction, from, to); } /** * security_binder_transfer_binder() - Check if a binder transfer is allowed * @from: sending process * @to: receiving process * * Check whether @from is allowed to transfer a binder reference to @to. * * Return: Returns 0 if permission is granted. */ int security_binder_transfer_binder(const struct cred *from, const struct cred *to) { return call_int_hook(binder_transfer_binder, from, to); } /** * security_binder_transfer_file() - Check if a binder file xfer is allowed * @from: sending process * @to: receiving process * @file: file being transferred * * Check whether @from is allowed to transfer @file to @to. * * Return: Returns 0 if permission is granted. */ int security_binder_transfer_file(const struct cred *from, const struct cred *to, const struct file *file) { return call_int_hook(binder_transfer_file, from, to, file); } /** * security_ptrace_access_check() - Check if tracing is allowed * @child: target process * @mode: PTRACE_MODE flags * * Check permission before allowing the current process to trace the @child * process. Security modules may also want to perform a process tracing check * during an execve in the set_security or apply_creds hooks of tracing check * during an execve in the bprm_set_creds hook of binprm_security_ops if the * process is being traced and its security attributes would be changed by the * execve. * * Return: Returns 0 if permission is granted. */ int security_ptrace_access_check(struct task_struct *child, unsigned int mode) { return call_int_hook(ptrace_access_check, child, mode); } /** * security_ptrace_traceme() - Check if tracing is allowed * @parent: tracing process * * Check that the @parent process has sufficient permission to trace the * current process before allowing the current process to present itself to the * @parent process for tracing. * * Return: Returns 0 if permission is granted. */ int security_ptrace_traceme(struct task_struct *parent) { return call_int_hook(ptrace_traceme, parent); } /** * security_capget() - Get the capability sets for a process * @target: target process * @effective: effective capability set * @inheritable: inheritable capability set * @permitted: permitted capability set * * Get the @effective, @inheritable, and @permitted capability sets for the * @target process. The hook may also perform permission checking to determine * if the current process is allowed to see the capability sets of the @target * process. * * Return: Returns 0 if the capability sets were successfully obtained. */ int security_capget(const struct task_struct *target, kernel_cap_t *effective, kernel_cap_t *inheritable, kernel_cap_t *permitted) { return call_int_hook(capget, target, effective, inheritable, permitted); } /** * security_capset() - Set the capability sets for a process * @new: new credentials for the target process * @old: current credentials of the target process * @effective: effective capability set * @inheritable: inheritable capability set * @permitted: permitted capability set * * Set the @effective, @inheritable, and @permitted capability sets for the * current process. * * Return: Returns 0 and update @new if permission is granted. */ int security_capset(struct cred *new, const struct cred *old, const kernel_cap_t *effective, const kernel_cap_t *inheritable, const kernel_cap_t *permitted) { return call_int_hook(capset, new, old, effective, inheritable, permitted); } /** * security_capable() - Check if a process has the necessary capability * @cred: credentials to examine * @ns: user namespace * @cap: capability requested * @opts: capability check options * * Check whether the @tsk process has the @cap capability in the indicated * credentials. @cap contains the capability <include/linux/capability.h>. * @opts contains options for the capable check <include/linux/security.h>. * * Return: Returns 0 if the capability is granted. */ int security_capable(const struct cred *cred, struct user_namespace *ns, int cap, unsigned int opts) { return call_int_hook(capable, cred, ns, cap, opts); } /** * security_quotactl() - Check if a quotactl() syscall is allowed for this fs * @cmds: commands * @type: type * @id: id * @sb: filesystem * * Check whether the quotactl syscall is allowed for this @sb. * * Return: Returns 0 if permission is granted. */ int security_quotactl(int cmds, int type, int id, const struct super_block *sb) { return call_int_hook(quotactl, cmds, type, id, sb); } /** * security_quota_on() - Check if QUOTAON is allowed for a dentry * @dentry: dentry * * Check whether QUOTAON is allowed for @dentry. * * Return: Returns 0 if permission is granted. */ int security_quota_on(struct dentry *dentry) { return call_int_hook(quota_on, dentry); } /** * security_syslog() - Check if accessing the kernel message ring is allowed * @type: SYSLOG_ACTION_* type * * Check permission before accessing the kernel message ring or changing * logging to the console. See the syslog(2) manual page for an explanation of * the @type values. * * Return: Return 0 if permission is granted. */ int security_syslog(int type) { return call_int_hook(syslog, type); } /** * security_settime64() - Check if changing the system time is allowed * @ts: new time * @tz: timezone * * Check permission to change the system time, struct timespec64 is defined in * <include/linux/time64.h> and timezone is defined in <include/linux/time.h>. * * Return: Returns 0 if permission is granted. */ int security_settime64(const struct timespec64 *ts, const struct timezone *tz) { return call_int_hook(settime, ts, tz); } /** * security_vm_enough_memory_mm() - Check if allocating a new mem map is allowed * @mm: mm struct * @pages: number of pages * * Check permissions for allocating a new virtual mapping. If all LSMs return * a positive value, __vm_enough_memory() will be called with cap_sys_admin * set. If at least one LSM returns 0 or negative, __vm_enough_memory() will be * called with cap_sys_admin cleared. * * Return: Returns 0 if permission is granted by the LSM infrastructure to the * caller. */ int security_vm_enough_memory_mm(struct mm_struct *mm, long pages) { struct lsm_static_call *scall; int cap_sys_admin = 1; int rc; /* * The module will respond with 0 if it thinks the __vm_enough_memory() * call should be made with the cap_sys_admin set. If all of the modules * agree that it should be set it will. If any module thinks it should * not be set it won't. */ lsm_for_each_hook(scall, vm_enough_memory) { rc = scall->hl->hook.vm_enough_memory(mm, pages); if (rc < 0) { cap_sys_admin = 0; break; } } return __vm_enough_memory(mm, pages, cap_sys_admin); } /** * security_bprm_creds_for_exec() - Prepare the credentials for exec() * @bprm: binary program information * * If the setup in prepare_exec_creds did not setup @bprm->cred->security * properly for executing @bprm->file, update the LSM's portion of * @bprm->cred->security to be what commit_creds needs to install for the new * program. This hook may also optionally check permissions (e.g. for * transitions between security domains). The hook must set @bprm->secureexec * to 1 if AT_SECURE should be set to request libc enable secure mode. @bprm * contains the linux_binprm structure. * * Return: Returns 0 if the hook is successful and permission is granted. */ int security_bprm_creds_for_exec(struct linux_binprm *bprm) { return call_int_hook(bprm_creds_for_exec, bprm); } /** * security_bprm_creds_from_file() - Update linux_binprm creds based on file * @bprm: binary program information * @file: associated file * * If @file is setpcap, suid, sgid or otherwise marked to change privilege upon * exec, update @bprm->cred to reflect that change. This is called after * finding the binary that will be executed without an interpreter. This * ensures that the credentials will not be derived from a script that the * binary will need to reopen, which when reopend may end up being a completely * different file. This hook may also optionally check permissions (e.g. for * transitions between security domains). The hook must set @bprm->secureexec * to 1 if AT_SECURE should be set to request libc enable secure mode. The * hook must add to @bprm->per_clear any personality flags that should be * cleared from current->personality. @bprm contains the linux_binprm * structure. * * Return: Returns 0 if the hook is successful and permission is granted. */ int security_bprm_creds_from_file(struct linux_binprm *bprm, const struct file *file) { return call_int_hook(bprm_creds_from_file, bprm, file); } /** * security_bprm_check() - Mediate binary handler search * @bprm: binary program information * * This hook mediates the point when a search for a binary handler will begin. * It allows a check against the @bprm->cred->security value which was set in * the preceding creds_for_exec call. The argv list and envp list are reliably * available in @bprm. This hook may be called multiple times during a single * execve. @bprm contains the linux_binprm structure. * * Return: Returns 0 if the hook is successful and permission is granted. */ int security_bprm_check(struct linux_binprm *bprm) { return call_int_hook(bprm_check_security, bprm); } /** * security_bprm_committing_creds() - Install creds for a process during exec() * @bprm: binary program information * * Prepare to install the new security attributes of a process being * transformed by an execve operation, based on the old credentials pointed to * by @current->cred and the information set in @bprm->cred by the * bprm_creds_for_exec hook. @bprm points to the linux_binprm structure. This * hook is a good place to perform state changes on the process such as closing * open file descriptors to which access will no longer be granted when the * attributes are changed. This is called immediately before commit_creds(). */ void security_bprm_committing_creds(const struct linux_binprm *bprm) { call_void_hook(bprm_committing_creds, bprm); } /** * security_bprm_committed_creds() - Tidy up after cred install during exec() * @bprm: binary program information * * Tidy up after the installation of the new security attributes of a process * being transformed by an execve operation. The new credentials have, by this * point, been set to @current->cred. @bprm points to the linux_binprm * structure. This hook is a good place to perform state changes on the * process such as clearing out non-inheritable signal state. This is called * immediately after commit_creds(). */ void security_bprm_committed_creds(const struct linux_binprm *bprm) { call_void_hook(bprm_committed_creds, bprm); } /** * security_fs_context_submount() - Initialise fc->security * @fc: new filesystem context * @reference: dentry reference for submount/remount * * Fill out the ->security field for a new fs_context. * * Return: Returns 0 on success or negative error code on failure. */ int security_fs_context_submount(struct fs_context *fc, struct super_block *reference) { return call_int_hook(fs_context_submount, fc, reference); } /** * security_fs_context_dup() - Duplicate a fs_context LSM blob * @fc: destination filesystem context * @src_fc: source filesystem context * * Allocate and attach a security structure to sc->security. This pointer is * initialised to NULL by the caller. @fc indicates the new filesystem context. * @src_fc indicates the original filesystem context. * * Return: Returns 0 on success or a negative error code on failure. */ int security_fs_context_dup(struct fs_context *fc, struct fs_context *src_fc) { return call_int_hook(fs_context_dup, fc, src_fc); } /** * security_fs_context_parse_param() - Configure a filesystem context * @fc: filesystem context * @param: filesystem parameter * * Userspace provided a parameter to configure a superblock. The LSM can * consume the parameter or return it to the caller for use elsewhere. * * Return: If the parameter is used by the LSM it should return 0, if it is * returned to the caller -ENOPARAM is returned, otherwise a negative * error code is returned. */ int security_fs_context_parse_param(struct fs_context *fc, struct fs_parameter *param) { struct lsm_static_call *scall; int trc; int rc = -ENOPARAM; lsm_for_each_hook(scall, fs_context_parse_param) { trc = scall->hl->hook.fs_context_parse_param(fc, param); if (trc == 0) rc = 0; else if (trc != -ENOPARAM) return trc; } return rc; } /** * security_sb_alloc() - Allocate a super_block LSM blob * @sb: filesystem superblock * * Allocate and attach a security structure to the sb->s_security field. The * s_security field is initialized to NULL when the structure is allocated. * @sb contains the super_block structure to be modified. * * Return: Returns 0 if operation was successful. */ int security_sb_alloc(struct super_block *sb) { int rc = lsm_superblock_alloc(sb); if (unlikely(rc)) return rc; rc = call_int_hook(sb_alloc_security, sb); if (unlikely(rc)) security_sb_free(sb); return rc; } /** * security_sb_delete() - Release super_block LSM associated objects * @sb: filesystem superblock * * Release objects tied to a superblock (e.g. inodes). @sb contains the * super_block structure being released. */ void security_sb_delete(struct super_block *sb) { call_void_hook(sb_delete, sb); } /** * security_sb_free() - Free a super_block LSM blob * @sb: filesystem superblock * * Deallocate and clear the sb->s_security field. @sb contains the super_block * structure to be modified. */ void security_sb_free(struct super_block *sb) { call_void_hook(sb_free_security, sb); kfree(sb->s_security); sb->s_security = NULL; } /** * security_free_mnt_opts() - Free memory associated with mount options * @mnt_opts: LSM processed mount options * * Free memory associated with @mnt_ops. */ void security_free_mnt_opts(void **mnt_opts) { if (!*mnt_opts) return; call_void_hook(sb_free_mnt_opts, *mnt_opts); *mnt_opts = NULL; } EXPORT_SYMBOL(security_free_mnt_opts); /** * security_sb_eat_lsm_opts() - Consume LSM mount options * @options: mount options * @mnt_opts: LSM processed mount options * * Eat (scan @options) and save them in @mnt_opts. * * Return: Returns 0 on success, negative values on failure. */ int security_sb_eat_lsm_opts(char *options, void **mnt_opts) { return call_int_hook(sb_eat_lsm_opts, options, mnt_opts); } EXPORT_SYMBOL(security_sb_eat_lsm_opts); /** * security_sb_mnt_opts_compat() - Check if new mount options are allowed * @sb: filesystem superblock * @mnt_opts: new mount options * * Determine if the new mount options in @mnt_opts are allowed given the * existing mounted filesystem at @sb. @sb superblock being compared. * * Return: Returns 0 if options are compatible. */ int security_sb_mnt_opts_compat(struct super_block *sb, void *mnt_opts) { return call_int_hook(sb_mnt_opts_compat, sb, mnt_opts); } EXPORT_SYMBOL(security_sb_mnt_opts_compat); /** * security_sb_remount() - Verify no incompatible mount changes during remount * @sb: filesystem superblock * @mnt_opts: (re)mount options * * Extracts security system specific mount options and verifies no changes are * being made to those options. * * Return: Returns 0 if permission is granted. */ int security_sb_remount(struct super_block *sb, void *mnt_opts) { return call_int_hook(sb_remount, sb, mnt_opts); } EXPORT_SYMBOL(security_sb_remount); /** * security_sb_kern_mount() - Check if a kernel mount is allowed * @sb: filesystem superblock * * Mount this @sb if allowed by permissions. * * Return: Returns 0 if permission is granted. */ int security_sb_kern_mount(const struct super_block *sb) { return call_int_hook(sb_kern_mount, sb); } /** * security_sb_show_options() - Output the mount options for a superblock * @m: output file * @sb: filesystem superblock * * Show (print on @m) mount options for this @sb. * * Return: Returns 0 on success, negative values on failure. */ int security_sb_show_options(struct seq_file *m, struct super_block *sb) { return call_int_hook(sb_show_options, m, sb); } /** * security_sb_statfs() - Check if accessing fs stats is allowed * @dentry: superblock handle * * Check permission before obtaining filesystem statistics for the @mnt * mountpoint. @dentry is a handle on the superblock for the filesystem. * * Return: Returns 0 if permission is granted. */ int security_sb_statfs(struct dentry *dentry) { return call_int_hook(sb_statfs, dentry); } /** * security_sb_mount() - Check permission for mounting a filesystem * @dev_name: filesystem backing device * @path: mount point * @type: filesystem type * @flags: mount flags * @data: filesystem specific data * * Check permission before an object specified by @dev_name is mounted on the * mount point named by @nd. For an ordinary mount, @dev_name identifies a * device if the file system type requires a device. For a remount * (@flags & MS_REMOUNT), @dev_name is irrelevant. For a loopback/bind mount * (@flags & MS_BIND), @dev_name identifies the pathname of the object being * mounted. * * Return: Returns 0 if permission is granted. */ int security_sb_mount(const char *dev_name, const struct path *path, const char *type, unsigned long flags, void *data) { return call_int_hook(sb_mount, dev_name, path, type, flags, data); } /** * security_sb_umount() - Check permission for unmounting a filesystem * @mnt: mounted filesystem * @flags: unmount flags * * Check permission before the @mnt file system is unmounted. * * Return: Returns 0 if permission is granted. */ int security_sb_umount(struct vfsmount *mnt, int flags) { return call_int_hook(sb_umount, mnt, flags); } /** * security_sb_pivotroot() - Check permissions for pivoting the rootfs * @old_path: new location for current rootfs * @new_path: location of the new rootfs * * Check permission before pivoting the root filesystem. * * Return: Returns 0 if permission is granted. */ int security_sb_pivotroot(const struct path *old_path, const struct path *new_path) { return call_int_hook(sb_pivotroot, old_path, new_path); } /** * security_sb_set_mnt_opts() - Set the mount options for a filesystem * @sb: filesystem superblock * @mnt_opts: binary mount options * @kern_flags: kernel flags (in) * @set_kern_flags: kernel flags (out) * * Set the security relevant mount options used for a superblock. * * Return: Returns 0 on success, error on failure. */ int security_sb_set_mnt_opts(struct super_block *sb, void *mnt_opts, unsigned long kern_flags, unsigned long *set_kern_flags) { struct lsm_static_call *scall; int rc = mnt_opts ? -EOPNOTSUPP : LSM_RET_DEFAULT(sb_set_mnt_opts); lsm_for_each_hook(scall, sb_set_mnt_opts) { rc = scall->hl->hook.sb_set_mnt_opts(sb, mnt_opts, kern_flags, set_kern_flags); if (rc != LSM_RET_DEFAULT(sb_set_mnt_opts)) break; } return rc; } EXPORT_SYMBOL(security_sb_set_mnt_opts); /** * security_sb_clone_mnt_opts() - Duplicate superblock mount options * @oldsb: source superblock * @newsb: destination superblock * @kern_flags: kernel flags (in) * @set_kern_flags: kernel flags (out) * * Copy all security options from a given superblock to another. * * Return: Returns 0 on success, error on failure. */ int security_sb_clone_mnt_opts(const struct super_block *oldsb, struct super_block *newsb, unsigned long kern_flags, unsigned long *set_kern_flags) { return call_int_hook(sb_clone_mnt_opts, oldsb, newsb, kern_flags, set_kern_flags); } EXPORT_SYMBOL(security_sb_clone_mnt_opts); /** * security_move_mount() - Check permissions for moving a mount * @from_path: source mount point * @to_path: destination mount point * * Check permission before a mount is moved. * * Return: Returns 0 if permission is granted. */ int security_move_mount(const struct path *from_path, const struct path *to_path) { return call_int_hook(move_mount, from_path, to_path); } /** * security_path_notify() - Check if setting a watch is allowed * @path: file path * @mask: event mask * @obj_type: file path type * * Check permissions before setting a watch on events as defined by @mask, on * an object at @path, whose type is defined by @obj_type. * * Return: Returns 0 if permission is granted. */ int security_path_notify(const struct path *path, u64 mask, unsigned int obj_type) { return call_int_hook(path_notify, path, mask, obj_type); } /** * security_inode_alloc() - Allocate an inode LSM blob * @inode: the inode * @gfp: allocation flags * * Allocate and attach a security structure to @inode->i_security. The * i_security field is initialized to NULL when the inode structure is * allocated. * * Return: Return 0 if operation was successful. */ int security_inode_alloc(struct inode *inode, gfp_t gfp) { int rc = lsm_inode_alloc(inode, gfp); if (unlikely(rc)) return rc; rc = call_int_hook(inode_alloc_security, inode); if (unlikely(rc)) security_inode_free(inode); return rc; } static void inode_free_by_rcu(struct rcu_head *head) { /* The rcu head is at the start of the inode blob */ call_void_hook(inode_free_security_rcu, head); kmem_cache_free(lsm_inode_cache, head); } /** * security_inode_free() - Free an inode's LSM blob * @inode: the inode * * Release any LSM resources associated with @inode, although due to the * inode's RCU protections it is possible that the resources will not be * fully released until after the current RCU grace period has elapsed. * * It is important for LSMs to note that despite being present in a call to * security_inode_free(), @inode may still be referenced in a VFS path walk * and calls to security_inode_permission() may be made during, or after, * a call to security_inode_free(). For this reason the inode->i_security * field is released via a call_rcu() callback and any LSMs which need to * retain inode state for use in security_inode_permission() should only * release that state in the inode_free_security_rcu() LSM hook callback. */ void security_inode_free(struct inode *inode) { call_void_hook(inode_free_security, inode); if (!inode->i_security) return; call_rcu((struct rcu_head *)inode->i_security, inode_free_by_rcu); } /** * security_dentry_init_security() - Perform dentry initialization * @dentry: the dentry to initialize * @mode: mode used to determine resource type * @name: name of the last path component * @xattr_name: name of the security/LSM xattr * @ctx: pointer to the resulting LSM context * @ctxlen: length of @ctx * * Compute a context for a dentry as the inode is not yet available since NFSv4 * has no label backed by an EA anyway. It is important to note that * @xattr_name does not need to be free'd by the caller, it is a static string. * * Return: Returns 0 on success, negative values on failure. */ int security_dentry_init_security(struct dentry *dentry, int mode, const struct qstr *name, const char **xattr_name, void **ctx, u32 *ctxlen) { return call_int_hook(dentry_init_security, dentry, mode, name, xattr_name, ctx, ctxlen); } EXPORT_SYMBOL(security_dentry_init_security); /** * security_dentry_create_files_as() - Perform dentry initialization * @dentry: the dentry to initialize * @mode: mode used to determine resource type * @name: name of the last path component * @old: creds to use for LSM context calculations * @new: creds to modify * * Compute a context for a dentry as the inode is not yet available and set * that context in passed in creds so that new files are created using that * context. Context is calculated using the passed in creds and not the creds * of the caller. * * Return: Returns 0 on success, error on failure. */ int security_dentry_create_files_as(struct dentry *dentry, int mode, struct qstr *name, const struct cred *old, struct cred *new) { return call_int_hook(dentry_create_files_as, dentry, mode, name, old, new); } EXPORT_SYMBOL(security_dentry_create_files_as); /** * security_inode_init_security() - Initialize an inode's LSM context * @inode: the inode * @dir: parent directory * @qstr: last component of the pathname * @initxattrs: callback function to write xattrs * @fs_data: filesystem specific data * * Obtain the security attribute name suffix and value to set on a newly * created inode and set up the incore security field for the new inode. This * hook is called by the fs code as part of the inode creation transaction and * provides for atomic labeling of the inode, unlike the post_create/mkdir/... * hooks called by the VFS. * * The hook function is expected to populate the xattrs array, by calling * lsm_get_xattr_slot() to retrieve the slots reserved by the security module * with the lbs_xattr_count field of the lsm_blob_sizes structure. For each * slot, the hook function should set ->name to the attribute name suffix * (e.g. selinux), to allocate ->value (will be freed by the caller) and set it * to the attribute value, to set ->value_len to the length of the value. If * the security module does not use security attributes or does not wish to put * a security attribute on this particular inode, then it should return * -EOPNOTSUPP to skip this processing. * * Return: Returns 0 if the LSM successfully initialized all of the inode * security attributes that are required, negative values otherwise. */ int security_inode_init_security(struct inode *inode, struct inode *dir, const struct qstr *qstr, const initxattrs initxattrs, void *fs_data) { struct lsm_static_call *scall; struct xattr *new_xattrs = NULL; int ret = -EOPNOTSUPP, xattr_count = 0; if (unlikely(IS_PRIVATE(inode))) return 0; if (!blob_sizes.lbs_xattr_count) return 0; if (initxattrs) { /* Allocate +1 as terminator. */ new_xattrs = kcalloc(blob_sizes.lbs_xattr_count + 1, sizeof(*new_xattrs), GFP_NOFS); if (!new_xattrs) return -ENOMEM; } lsm_for_each_hook(scall, inode_init_security) { ret = scall->hl->hook.inode_init_security(inode, dir, qstr, new_xattrs, &xattr_count); if (ret && ret != -EOPNOTSUPP) goto out; /* * As documented in lsm_hooks.h, -EOPNOTSUPP in this context * means that the LSM is not willing to provide an xattr, not * that it wants to signal an error. Thus, continue to invoke * the remaining LSMs. */ } /* If initxattrs() is NULL, xattr_count is zero, skip the call. */ if (!xattr_count) goto out; ret = initxattrs(inode, new_xattrs, fs_data); out: for (; xattr_count > 0; xattr_count--) kfree(new_xattrs[xattr_count - 1].value); kfree(new_xattrs); return (ret == -EOPNOTSUPP) ? 0 : ret; } EXPORT_SYMBOL(security_inode_init_security); /** * security_inode_init_security_anon() - Initialize an anonymous inode * @inode: the inode * @name: the anonymous inode class * @context_inode: an optional related inode * * Set up the incore security field for the new anonymous inode and return * whether the inode creation is permitted by the security module or not. * * Return: Returns 0 on success, -EACCES if the security module denies the * creation of this inode, or another -errno upon other errors. */ int security_inode_init_security_anon(struct inode *inode, const struct qstr *name, const struct inode *context_inode) { return call_int_hook(inode_init_security_anon, inode, name, context_inode); } #ifdef CONFIG_SECURITY_PATH /** * security_path_mknod() - Check if creating a special file is allowed * @dir: parent directory * @dentry: new file * @mode: new file mode * @dev: device number * * Check permissions when creating a file. Note that this hook is called even * if mknod operation is being done for a regular file. * * Return: Returns 0 if permission is granted. */ int security_path_mknod(const struct path *dir, struct dentry *dentry, umode_t mode, unsigned int dev) { if (unlikely(IS_PRIVATE(d_backing_inode(dir->dentry)))) return 0; return call_int_hook(path_mknod, dir, dentry, mode, dev); } EXPORT_SYMBOL(security_path_mknod); /** * security_path_post_mknod() - Update inode security after reg file creation * @idmap: idmap of the mount * @dentry: new file * * Update inode security field after a regular file has been created. */ void security_path_post_mknod(struct mnt_idmap *idmap, struct dentry *dentry) { if (unlikely(IS_PRIVATE(d_backing_inode(dentry)))) return; call_void_hook(path_post_mknod, idmap, dentry); } /** * security_path_mkdir() - Check if creating a new directory is allowed * @dir: parent directory * @dentry: new directory * @mode: new directory mode * * Check permissions to create a new directory in the existing directory. * * Return: Returns 0 if permission is granted. */ int security_path_mkdir(const struct path *dir, struct dentry *dentry, umode_t mode) { if (unlikely(IS_PRIVATE(d_backing_inode(dir->dentry)))) return 0; return call_int_hook(path_mkdir, dir, dentry, mode); } EXPORT_SYMBOL(security_path_mkdir); /** * security_path_rmdir() - Check if removing a directory is allowed * @dir: parent directory * @dentry: directory to remove * * Check the permission to remove a directory. * * Return: Returns 0 if permission is granted. */ int security_path_rmdir(const struct path *dir, struct dentry *dentry) { if (unlikely(IS_PRIVATE(d_backing_inode(dir->dentry)))) return 0; return call_int_hook(path_rmdir, dir, dentry); } /** * security_path_unlink() - Check if removing a hard link is allowed * @dir: parent directory * @dentry: file * * Check the permission to remove a hard link to a file. * * Return: Returns 0 if permission is granted. */ int security_path_unlink(const struct path *dir, struct dentry *dentry) { if (unlikely(IS_PRIVATE(d_backing_inode(dir->dentry)))) return 0; return call_int_hook(path_unlink, dir, dentry); } EXPORT_SYMBOL(security_path_unlink); /** * security_path_symlink() - Check if creating a symbolic link is allowed * @dir: parent directory * @dentry: symbolic link * @old_name: file pathname * * Check the permission to create a symbolic link to a file. * * Return: Returns 0 if permission is granted. */ int security_path_symlink(const struct path *dir, struct dentry *dentry, const char *old_name) { if (unlikely(IS_PRIVATE(d_backing_inode(dir->dentry)))) return 0; return call_int_hook(path_symlink, dir, dentry, old_name); } /** * security_path_link - Check if creating a hard link is allowed * @old_dentry: existing file * @new_dir: new parent directory * @new_dentry: new link * * Check permission before creating a new hard link to a file. * * Return: Returns 0 if permission is granted. */ int security_path_link(struct dentry *old_dentry, const struct path *new_dir, struct dentry *new_dentry) { if (unlikely(IS_PRIVATE(d_backing_inode(old_dentry)))) return 0; return call_int_hook(path_link, old_dentry, new_dir, new_dentry); } /** * security_path_rename() - Check if renaming a file is allowed * @old_dir: parent directory of the old file * @old_dentry: the old file * @new_dir: parent directory of the new file * @new_dentry: the new file * @flags: flags * * Check for permission to rename a file or directory. * * Return: Returns 0 if permission is granted. */ int security_path_rename(const struct path *old_dir, struct dentry *old_dentry, const struct path *new_dir, struct dentry *new_dentry, unsigned int flags) { if (unlikely(IS_PRIVATE(d_backing_inode(old_dentry)) || (d_is_positive(new_dentry) && IS_PRIVATE(d_backing_inode(new_dentry))))) return 0; return call_int_hook(path_rename, old_dir, old_dentry, new_dir, new_dentry, flags); } EXPORT_SYMBOL(security_path_rename); /** * security_path_truncate() - Check if truncating a file is allowed * @path: file * * Check permission before truncating the file indicated by path. Note that * truncation permissions may also be checked based on already opened files, * using the security_file_truncate() hook. * * Return: Returns 0 if permission is granted. */ int security_path_truncate(const struct path *path) { if (unlikely(IS_PRIVATE(d_backing_inode(path->dentry)))) return 0; return call_int_hook(path_truncate, path); } /** * security_path_chmod() - Check if changing the file's mode is allowed * @path: file * @mode: new mode * * Check for permission to change a mode of the file @path. The new mode is * specified in @mode which is a bitmask of constants from * <include/uapi/linux/stat.h>. * * Return: Returns 0 if permission is granted. */ int security_path_chmod(const struct path *path, umode_t mode) { if (unlikely(IS_PRIVATE(d_backing_inode(path->dentry)))) return 0; return call_int_hook(path_chmod, path, mode); } /** * security_path_chown() - Check if changing the file's owner/group is allowed * @path: file * @uid: file owner * @gid: file group * * Check for permission to change owner/group of a file or directory. * * Return: Returns 0 if permission is granted. */ int security_path_chown(const struct path *path, kuid_t uid, kgid_t gid) { if (unlikely(IS_PRIVATE(d_backing_inode(path->dentry)))) return 0; return call_int_hook(path_chown, path, uid, gid); } /** * security_path_chroot() - Check if changing the root directory is allowed * @path: directory * * Check for permission to change root directory. * * Return: Returns 0 if permission is granted. */ int security_path_chroot(const struct path *path) { return call_int_hook(path_chroot, path); } #endif /* CONFIG_SECURITY_PATH */ /** * security_inode_create() - Check if creating a file is allowed * @dir: the parent directory * @dentry: the file being created * @mode: requested file mode * * Check permission to create a regular file. * * Return: Returns 0 if permission is granted. */ int security_inode_create(struct inode *dir, struct dentry *dentry, umode_t mode) { if (unlikely(IS_PRIVATE(dir))) return 0; return call_int_hook(inode_create, dir, dentry, mode); } EXPORT_SYMBOL_GPL(security_inode_create); /** * security_inode_post_create_tmpfile() - Update inode security of new tmpfile * @idmap: idmap of the mount * @inode: inode of the new tmpfile * * Update inode security data after a tmpfile has been created. */ void security_inode_post_create_tmpfile(struct mnt_idmap *idmap, struct inode *inode) { if (unlikely(IS_PRIVATE(inode))) return; call_void_hook(inode_post_create_tmpfile, idmap, inode); } /** * security_inode_link() - Check if creating a hard link is allowed * @old_dentry: existing file * @dir: new parent directory * @new_dentry: new link * * Check permission before creating a new hard link to a file. * * Return: Returns 0 if permission is granted. */ int security_inode_link(struct dentry *old_dentry, struct inode *dir, struct dentry *new_dentry) { if (unlikely(IS_PRIVATE(d_backing_inode(old_dentry)))) return 0; return call_int_hook(inode_link, old_dentry, dir, new_dentry); } /** * security_inode_unlink() - Check if removing a hard link is allowed * @dir: parent directory * @dentry: file * * Check the permission to remove a hard link to a file. * * Return: Returns 0 if permission is granted. */ int security_inode_unlink(struct inode *dir, struct dentry *dentry) { if (unlikely(IS_PRIVATE(d_backing_inode(dentry)))) return 0; return call_int_hook(inode_unlink, dir, dentry); } /** * security_inode_symlink() - Check if creating a symbolic link is allowed * @dir: parent directory * @dentry: symbolic link * @old_name: existing filename * * Check the permission to create a symbolic link to a file. * * Return: Returns 0 if permission is granted. */ int security_inode_symlink(struct inode *dir, struct dentry *dentry, const char *old_name) { if (unlikely(IS_PRIVATE(dir))) return 0; return call_int_hook(inode_symlink, dir, dentry, old_name); } /** * security_inode_mkdir() - Check if creation a new director is allowed * @dir: parent directory * @dentry: new directory * @mode: new directory mode * * Check permissions to create a new directory in the existing directory * associated with inode structure @dir. * * Return: Returns 0 if permission is granted. */ int security_inode_mkdir(struct inode *dir, struct dentry *dentry, umode_t mode) { if (unlikely(IS_PRIVATE(dir))) return 0; return call_int_hook(inode_mkdir, dir, dentry, mode); } EXPORT_SYMBOL_GPL(security_inode_mkdir); /** * security_inode_rmdir() - Check if removing a directory is allowed * @dir: parent directory * @dentry: directory to be removed * * Check the permission to remove a directory. * * Return: Returns 0 if permission is granted. */ int security_inode_rmdir(struct inode *dir, struct dentry *dentry) { if (unlikely(IS_PRIVATE(d_backing_inode(dentry)))) return 0; return call_int_hook(inode_rmdir, dir, dentry); } /** * security_inode_mknod() - Check if creating a special file is allowed * @dir: parent directory * @dentry: new file * @mode: new file mode * @dev: device number * * Check permissions when creating a special file (or a socket or a fifo file * created via the mknod system call). Note that if mknod operation is being * done for a regular file, then the create hook will be called and not this * hook. * * Return: Returns 0 if permission is granted. */ int security_inode_mknod(struct inode *dir, struct dentry *dentry, umode_t mode, dev_t dev) { if (unlikely(IS_PRIVATE(dir))) return 0; return call_int_hook(inode_mknod, dir, dentry, mode, dev); } /** * security_inode_rename() - Check if renaming a file is allowed * @old_dir: parent directory of the old file * @old_dentry: the old file * @new_dir: parent directory of the new file * @new_dentry: the new file * @flags: flags * * Check for permission to rename a file or directory. * * Return: Returns 0 if permission is granted. */ int security_inode_rename(struct inode *old_dir, struct dentry *old_dentry, struct inode *new_dir, struct dentry *new_dentry, unsigned int flags) { if (unlikely(IS_PRIVATE(d_backing_inode(old_dentry)) || (d_is_positive(new_dentry) && IS_PRIVATE(d_backing_inode(new_dentry))))) return 0; if (flags & RENAME_EXCHANGE) { int err = call_int_hook(inode_rename, new_dir, new_dentry, old_dir, old_dentry); if (err) return err; } return call_int_hook(inode_rename, old_dir, old_dentry, new_dir, new_dentry); } /** * security_inode_readlink() - Check if reading a symbolic link is allowed * @dentry: link * * Check the permission to read the symbolic link. * * Return: Returns 0 if permission is granted. */ int security_inode_readlink(struct dentry *dentry) { if (unlikely(IS_PRIVATE(d_backing_inode(dentry)))) return 0; return call_int_hook(inode_readlink, dentry); } /** * security_inode_follow_link() - Check if following a symbolic link is allowed * @dentry: link dentry * @inode: link inode * @rcu: true if in RCU-walk mode * * Check permission to follow a symbolic link when looking up a pathname. If * @rcu is true, @inode is not stable. * * Return: Returns 0 if permission is granted. */ int security_inode_follow_link(struct dentry *dentry, struct inode *inode, bool rcu) { if (unlikely(IS_PRIVATE(inode))) return 0; return call_int_hook(inode_follow_link, dentry, inode, rcu); } /** * security_inode_permission() - Check if accessing an inode is allowed * @inode: inode * @mask: access mask * * Check permission before accessing an inode. This hook is called by the * existing Linux permission function, so a security module can use it to * provide additional checking for existing Linux permission checks. Notice * that this hook is called when a file is opened (as well as many other * operations), whereas the file_security_ops permission hook is called when * the actual read/write operations are performed. * * Return: Returns 0 if permission is granted. */ int security_inode_permission(struct inode *inode, int mask) { if (unlikely(IS_PRIVATE(inode))) return 0; return call_int_hook(inode_permission, inode, mask); } /** * security_inode_setattr() - Check if setting file attributes is allowed * @idmap: idmap of the mount * @dentry: file * @attr: new attributes * * Check permission before setting file attributes. Note that the kernel call * to notify_change is performed from several locations, whenever file * attributes change (such as when a file is truncated, chown/chmod operations, * transferring disk quotas, etc). * * Return: Returns 0 if permission is granted. */ int security_inode_setattr(struct mnt_idmap *idmap, struct dentry *dentry, struct iattr *attr) { if (unlikely(IS_PRIVATE(d_backing_inode(dentry)))) return 0; return call_int_hook(inode_setattr, idmap, dentry, attr); } EXPORT_SYMBOL_GPL(security_inode_setattr); /** * security_inode_post_setattr() - Update the inode after a setattr operation * @idmap: idmap of the mount * @dentry: file * @ia_valid: file attributes set * * Update inode security field after successful setting file attributes. */ void security_inode_post_setattr(struct mnt_idmap *idmap, struct dentry *dentry, int ia_valid) { if (unlikely(IS_PRIVATE(d_backing_inode(dentry)))) return; call_void_hook(inode_post_setattr, idmap, dentry, ia_valid); } /** * security_inode_getattr() - Check if getting file attributes is allowed * @path: file * * Check permission before obtaining file attributes. * * Return: Returns 0 if permission is granted. */ int security_inode_getattr(const struct path *path) { if (unlikely(IS_PRIVATE(d_backing_inode(path->dentry)))) return 0; return call_int_hook(inode_getattr, path); } /** * security_inode_setxattr() - Check if setting file xattrs is allowed * @idmap: idmap of the mount * @dentry: file * @name: xattr name * @value: xattr value * @size: size of xattr value * @flags: flags * * This hook performs the desired permission checks before setting the extended * attributes (xattrs) on @dentry. It is important to note that we have some * additional logic before the main LSM implementation calls to detect if we * need to perform an additional capability check at the LSM layer. * * Normally we enforce a capability check prior to executing the various LSM * hook implementations, but if a LSM wants to avoid this capability check, * it can register a 'inode_xattr_skipcap' hook and return a value of 1 for * xattrs that it wants to avoid the capability check, leaving the LSM fully * responsible for enforcing the access control for the specific xattr. If all * of the enabled LSMs refrain from registering a 'inode_xattr_skipcap' hook, * or return a 0 (the default return value), the capability check is still * performed. If no 'inode_xattr_skipcap' hooks are registered the capability * check is performed. * * Return: Returns 0 if permission is granted. */ int security_inode_setxattr(struct mnt_idmap *idmap, struct dentry *dentry, const char *name, const void *value, size_t size, int flags) { int rc; if (unlikely(IS_PRIVATE(d_backing_inode(dentry)))) return 0; /* enforce the capability checks at the lsm layer, if needed */ if (!call_int_hook(inode_xattr_skipcap, name)) { rc = cap_inode_setxattr(dentry, name, value, size, flags); if (rc) return rc; } return call_int_hook(inode_setxattr, idmap, dentry, name, value, size, flags); } /** * security_inode_set_acl() - Check if setting posix acls is allowed * @idmap: idmap of the mount * @dentry: file * @acl_name: acl name * @kacl: acl struct * * Check permission before setting posix acls, the posix acls in @kacl are * identified by @acl_name. * * Return: Returns 0 if permission is granted. */ int security_inode_set_acl(struct mnt_idmap *idmap, struct dentry *dentry, const char *acl_name, struct posix_acl *kacl) { if (unlikely(IS_PRIVATE(d_backing_inode(dentry)))) return 0; return call_int_hook(inode_set_acl, idmap, dentry, acl_name, kacl); } /** * security_inode_post_set_acl() - Update inode security from posix acls set * @dentry: file * @acl_name: acl name * @kacl: acl struct * * Update inode security data after successfully setting posix acls on @dentry. * The posix acls in @kacl are identified by @acl_name. */ void security_inode_post_set_acl(struct dentry *dentry, const char *acl_name, struct posix_acl *kacl) { if (unlikely(IS_PRIVATE(d_backing_inode(dentry)))) return; call_void_hook(inode_post_set_acl, dentry, acl_name, kacl); } /** * security_inode_get_acl() - Check if reading posix acls is allowed * @idmap: idmap of the mount * @dentry: file * @acl_name: acl name * * Check permission before getting osix acls, the posix acls are identified by * @acl_name. * * Return: Returns 0 if permission is granted. */ int security_inode_get_acl(struct mnt_idmap *idmap, struct dentry *dentry, const char *acl_name) { if (unlikely(IS_PRIVATE(d_backing_inode(dentry)))) return 0; return call_int_hook(inode_get_acl, idmap, dentry, acl_name); } /** * security_inode_remove_acl() - Check if removing a posix acl is allowed * @idmap: idmap of the mount * @dentry: file * @acl_name: acl name * * Check permission before removing posix acls, the posix acls are identified * by @acl_name. * * Return: Returns 0 if permission is granted. */ int security_inode_remove_acl(struct mnt_idmap *idmap, struct dentry *dentry, const char *acl_name) { if (unlikely(IS_PRIVATE(d_backing_inode(dentry)))) return 0; return call_int_hook(inode_remove_acl, idmap, dentry, acl_name); } /** * security_inode_post_remove_acl() - Update inode security after rm posix acls * @idmap: idmap of the mount * @dentry: file * @acl_name: acl name * * Update inode security data after successfully removing posix acls on * @dentry in @idmap. The posix acls are identified by @acl_name. */ void security_inode_post_remove_acl(struct mnt_idmap *idmap, struct dentry *dentry, const char *acl_name) { if (unlikely(IS_PRIVATE(d_backing_inode(dentry)))) return; call_void_hook(inode_post_remove_acl, idmap, dentry, acl_name); } /** * security_inode_post_setxattr() - Update the inode after a setxattr operation * @dentry: file * @name: xattr name * @value: xattr value * @size: xattr value size * @flags: flags * * Update inode security field after successful setxattr operation. */ void security_inode_post_setxattr(struct dentry *dentry, const char *name, const void *value, size_t size, int flags) { if (unlikely(IS_PRIVATE(d_backing_inode(dentry)))) return; call_void_hook(inode_post_setxattr, dentry, name, value, size, flags); } /** * security_inode_getxattr() - Check if xattr access is allowed * @dentry: file * @name: xattr name * * Check permission before obtaining the extended attributes identified by * @name for @dentry. * * Return: Returns 0 if permission is granted. */ int security_inode_getxattr(struct dentry *dentry, const char *name) { if (unlikely(IS_PRIVATE(d_backing_inode(dentry)))) return 0; return call_int_hook(inode_getxattr, dentry, name); } /** * security_inode_listxattr() - Check if listing xattrs is allowed * @dentry: file * * Check permission before obtaining the list of extended attribute names for * @dentry. * * Return: Returns 0 if permission is granted. */ int security_inode_listxattr(struct dentry *dentry) { if (unlikely(IS_PRIVATE(d_backing_inode(dentry)))) return 0; return call_int_hook(inode_listxattr, dentry); } /** * security_inode_removexattr() - Check if removing an xattr is allowed * @idmap: idmap of the mount * @dentry: file * @name: xattr name * * This hook performs the desired permission checks before setting the extended * attributes (xattrs) on @dentry. It is important to note that we have some * additional logic before the main LSM implementation calls to detect if we * need to perform an additional capability check at the LSM layer. * * Normally we enforce a capability check prior to executing the various LSM * hook implementations, but if a LSM wants to avoid this capability check, * it can register a 'inode_xattr_skipcap' hook and return a value of 1 for * xattrs that it wants to avoid the capability check, leaving the LSM fully * responsible for enforcing the access control for the specific xattr. If all * of the enabled LSMs refrain from registering a 'inode_xattr_skipcap' hook, * or return a 0 (the default return value), the capability check is still * performed. If no 'inode_xattr_skipcap' hooks are registered the capability * check is performed. * * Return: Returns 0 if permission is granted. */ int security_inode_removexattr(struct mnt_idmap *idmap, struct dentry *dentry, const char *name) { int rc; if (unlikely(IS_PRIVATE(d_backing_inode(dentry)))) return 0; /* enforce the capability checks at the lsm layer, if needed */ if (!call_int_hook(inode_xattr_skipcap, name)) { rc = cap_inode_removexattr(idmap, dentry, name); if (rc) return rc; } return call_int_hook(inode_removexattr, idmap, dentry, name); } /** * security_inode_post_removexattr() - Update the inode after a removexattr op * @dentry: file * @name: xattr name * * Update the inode after a successful removexattr operation. */ void security_inode_post_removexattr(struct dentry *dentry, const char *name) { if (unlikely(IS_PRIVATE(d_backing_inode(dentry)))) return; call_void_hook(inode_post_removexattr, dentry, name); } /** * security_inode_need_killpriv() - Check if security_inode_killpriv() required * @dentry: associated dentry * * Called when an inode has been changed to determine if * security_inode_killpriv() should be called. * * Return: Return <0 on error to abort the inode change operation, return 0 if * security_inode_killpriv() does not need to be called, return >0 if * security_inode_killpriv() does need to be called. */ int security_inode_need_killpriv(struct dentry *dentry) { return call_int_hook(inode_need_killpriv, dentry); } /** * security_inode_killpriv() - The setuid bit is removed, update LSM state * @idmap: idmap of the mount * @dentry: associated dentry * * The @dentry's setuid bit is being removed. Remove similar security labels. * Called with the dentry->d_inode->i_mutex held. * * Return: Return 0 on success. If error is returned, then the operation * causing setuid bit removal is failed. */ int security_inode_killpriv(struct mnt_idmap *idmap, struct dentry *dentry) { return call_int_hook(inode_killpriv, idmap, dentry); } /** * security_inode_getsecurity() - Get the xattr security label of an inode * @idmap: idmap of the mount * @inode: inode * @name: xattr name * @buffer: security label buffer * @alloc: allocation flag * * Retrieve a copy of the extended attribute representation of the security * label associated with @name for @inode via @buffer. Note that @name is the * remainder of the attribute name after the security prefix has been removed. * @alloc is used to specify if the call should return a value via the buffer * or just the value length. * * Return: Returns size of buffer on success. */ int security_inode_getsecurity(struct mnt_idmap *idmap, struct inode *inode, const char *name, void **buffer, bool alloc) { if (unlikely(IS_PRIVATE(inode))) return LSM_RET_DEFAULT(inode_getsecurity); return call_int_hook(inode_getsecurity, idmap, inode, name, buffer, alloc); } /** * security_inode_setsecurity() - Set the xattr security label of an inode * @inode: inode * @name: xattr name * @value: security label * @size: length of security label * @flags: flags * * Set the security label associated with @name for @inode from the extended * attribute value @value. @size indicates the size of the @value in bytes. * @flags may be XATTR_CREATE, XATTR_REPLACE, or 0. Note that @name is the * remainder of the attribute name after the security. prefix has been removed. * * Return: Returns 0 on success. */ int security_inode_setsecurity(struct inode *inode, const char *name, const void *value, size_t size, int flags) { if (unlikely(IS_PRIVATE(inode))) return LSM_RET_DEFAULT(inode_setsecurity); return call_int_hook(inode_setsecurity, inode, name, value, size, flags); } /** * security_inode_listsecurity() - List the xattr security label names * @inode: inode * @buffer: buffer * @buffer_size: size of buffer * * Copy the extended attribute names for the security labels associated with * @inode into @buffer. The maximum size of @buffer is specified by * @buffer_size. @buffer may be NULL to request the size of the buffer * required. * * Return: Returns number of bytes used/required on success. */ int security_inode_listsecurity(struct inode *inode, char *buffer, size_t buffer_size) { if (unlikely(IS_PRIVATE(inode))) return 0; return call_int_hook(inode_listsecurity, inode, buffer, buffer_size); } EXPORT_SYMBOL(security_inode_listsecurity); /** * security_inode_getlsmprop() - Get an inode's LSM data * @inode: inode * @prop: lsm specific information to return * * Get the lsm specific information associated with the node. */ void security_inode_getlsmprop(struct inode *inode, struct lsm_prop *prop) { call_void_hook(inode_getlsmprop, inode, prop); } /** * security_inode_copy_up() - Create new creds for an overlayfs copy-up op * @src: union dentry of copy-up file * @new: newly created creds * * A file is about to be copied up from lower layer to upper layer of overlay * filesystem. Security module can prepare a set of new creds and modify as * need be and return new creds. Caller will switch to new creds temporarily to * create new file and release newly allocated creds. * * Return: Returns 0 on success or a negative error code on error. */ int security_inode_copy_up(struct dentry *src, struct cred **new) { return call_int_hook(inode_copy_up, src, new); } EXPORT_SYMBOL(security_inode_copy_up); /** * security_inode_copy_up_xattr() - Filter xattrs in an overlayfs copy-up op * @src: union dentry of copy-up file * @name: xattr name * * Filter the xattrs being copied up when a unioned file is copied up from a * lower layer to the union/overlay layer. The caller is responsible for * reading and writing the xattrs, this hook is merely a filter. * * Return: Returns 0 to accept the xattr, -ECANCELED to discard the xattr, * -EOPNOTSUPP if the security module does not know about attribute, * or a negative error code to abort the copy up. */ int security_inode_copy_up_xattr(struct dentry *src, const char *name) { int rc; rc = call_int_hook(inode_copy_up_xattr, src, name); if (rc != LSM_RET_DEFAULT(inode_copy_up_xattr)) return rc; return LSM_RET_DEFAULT(inode_copy_up_xattr); } EXPORT_SYMBOL(security_inode_copy_up_xattr); /** * security_inode_setintegrity() - Set the inode's integrity data * @inode: inode * @type: type of integrity, e.g. hash digest, signature, etc * @value: the integrity value * @size: size of the integrity value * * Register a verified integrity measurement of a inode with LSMs. * LSMs should free the previously saved data if @value is NULL. * * Return: Returns 0 on success, negative values on failure. */ int security_inode_setintegrity(const struct inode *inode, enum lsm_integrity_type type, const void *value, size_t size) { return call_int_hook(inode_setintegrity, inode, type, value, size); } EXPORT_SYMBOL(security_inode_setintegrity); /** * security_kernfs_init_security() - Init LSM context for a kernfs node * @kn_dir: parent kernfs node * @kn: the kernfs node to initialize * * Initialize the security context of a newly created kernfs node based on its * own and its parent's attributes. * * Return: Returns 0 if permission is granted. */ int security_kernfs_init_security(struct kernfs_node *kn_dir, struct kernfs_node *kn) { return call_int_hook(kernfs_init_security, kn_dir, kn); } /** * security_file_permission() - Check file permissions * @file: file * @mask: requested permissions * * Check file permissions before accessing an open file. This hook is called * by various operations that read or write files. A security module can use * this hook to perform additional checking on these operations, e.g. to * revalidate permissions on use to support privilege bracketing or policy * changes. Notice that this hook is used when the actual read/write * operations are performed, whereas the inode_security_ops hook is called when * a file is opened (as well as many other operations). Although this hook can * be used to revalidate permissions for various system call operations that * read or write files, it does not address the revalidation of permissions for * memory-mapped files. Security modules must handle this separately if they * need such revalidation. * * Return: Returns 0 if permission is granted. */ int security_file_permission(struct file *file, int mask) { return call_int_hook(file_permission, file, mask); } /** * security_file_alloc() - Allocate and init a file's LSM blob * @file: the file * * Allocate and attach a security structure to the file->f_security field. The * security field is initialized to NULL when the structure is first created. * * Return: Return 0 if the hook is successful and permission is granted. */ int security_file_alloc(struct file *file) { int rc = lsm_file_alloc(file); if (rc) return rc; rc = call_int_hook(file_alloc_security, file); if (unlikely(rc)) security_file_free(file); return rc; } /** * security_file_release() - Perform actions before releasing the file ref * @file: the file * * Perform actions before releasing the last reference to a file. */ void security_file_release(struct file *file) { call_void_hook(file_release, file); } /** * security_file_free() - Free a file's LSM blob * @file: the file * * Deallocate and free any security structures stored in file->f_security. */ void security_file_free(struct file *file) { void *blob; call_void_hook(file_free_security, file); blob = file->f_security; if (blob) { file->f_security = NULL; kmem_cache_free(lsm_file_cache, blob); } } /** * security_file_ioctl() - Check if an ioctl is allowed * @file: associated file * @cmd: ioctl cmd * @arg: ioctl arguments * * Check permission for an ioctl operation on @file. Note that @arg sometimes * represents a user space pointer; in other cases, it may be a simple integer * value. When @arg represents a user space pointer, it should never be used * by the security module. * * Return: Returns 0 if permission is granted. */ int security_file_ioctl(struct file *file, unsigned int cmd, unsigned long arg) { return call_int_hook(file_ioctl, file, cmd, arg); } EXPORT_SYMBOL_GPL(security_file_ioctl); /** * security_file_ioctl_compat() - Check if an ioctl is allowed in compat mode * @file: associated file * @cmd: ioctl cmd * @arg: ioctl arguments * * Compat version of security_file_ioctl() that correctly handles 32-bit * processes running on 64-bit kernels. * * Return: Returns 0 if permission is granted. */ int security_file_ioctl_compat(struct file *file, unsigned int cmd, unsigned long arg) { return call_int_hook(file_ioctl_compat, file, cmd, arg); } EXPORT_SYMBOL_GPL(security_file_ioctl_compat); static inline unsigned long mmap_prot(struct file *file, unsigned long prot) { /* * Does we have PROT_READ and does the application expect * it to imply PROT_EXEC? If not, nothing to talk about... */ if ((prot & (PROT_READ | PROT_EXEC)) != PROT_READ) return prot; if (!(current->personality & READ_IMPLIES_EXEC)) return prot; /* * if that's an anonymous mapping, let it. */ if (!file) return prot | PROT_EXEC; /* * ditto if it's not on noexec mount, except that on !MMU we need * NOMMU_MAP_EXEC (== VM_MAYEXEC) in this case */ if (!path_noexec(&file->f_path)) { #ifndef CONFIG_MMU if (file->f_op->mmap_capabilities) { unsigned caps = file->f_op->mmap_capabilities(file); if (!(caps & NOMMU_MAP_EXEC)) return prot; } #endif return prot | PROT_EXEC; } /* anything on noexec mount won't get PROT_EXEC */ return prot; } /** * security_mmap_file() - Check if mmap'ing a file is allowed * @file: file * @prot: protection applied by the kernel * @flags: flags * * Check permissions for a mmap operation. The @file may be NULL, e.g. if * mapping anonymous memory. * * Return: Returns 0 if permission is granted. */ int security_mmap_file(struct file *file, unsigned long prot, unsigned long flags) { return call_int_hook(mmap_file, file, prot, mmap_prot(file, prot), flags); } /** * security_mmap_addr() - Check if mmap'ing an address is allowed * @addr: address * * Check permissions for a mmap operation at @addr. * * Return: Returns 0 if permission is granted. */ int security_mmap_addr(unsigned long addr) { return call_int_hook(mmap_addr, addr); } /** * security_file_mprotect() - Check if changing memory protections is allowed * @vma: memory region * @reqprot: application requested protection * @prot: protection applied by the kernel * * Check permissions before changing memory access permissions. * * Return: Returns 0 if permission is granted. */ int security_file_mprotect(struct vm_area_struct *vma, unsigned long reqprot, unsigned long prot) { return call_int_hook(file_mprotect, vma, reqprot, prot); } /** * security_file_lock() - Check if a file lock is allowed * @file: file * @cmd: lock operation (e.g. F_RDLCK, F_WRLCK) * * Check permission before performing file locking operations. Note the hook * mediates both flock and fcntl style locks. * * Return: Returns 0 if permission is granted. */ int security_file_lock(struct file *file, unsigned int cmd) { return call_int_hook(file_lock, file, cmd); } /** * security_file_fcntl() - Check if fcntl() op is allowed * @file: file * @cmd: fcntl command * @arg: command argument * * Check permission before allowing the file operation specified by @cmd from * being performed on the file @file. Note that @arg sometimes represents a * user space pointer; in other cases, it may be a simple integer value. When * @arg represents a user space pointer, it should never be used by the * security module. * * Return: Returns 0 if permission is granted. */ int security_file_fcntl(struct file *file, unsigned int cmd, unsigned long arg) { return call_int_hook(file_fcntl, file, cmd, arg); } /** * security_file_set_fowner() - Set the file owner info in the LSM blob * @file: the file * * Save owner security information (typically from current->security) in * file->f_security for later use by the send_sigiotask hook. * * This hook is called with file->f_owner.lock held. * * Return: Returns 0 on success. */ void security_file_set_fowner(struct file *file) { call_void_hook(file_set_fowner, file); } /** * security_file_send_sigiotask() - Check if sending SIGIO/SIGURG is allowed * @tsk: target task * @fown: signal sender * @sig: signal to be sent, SIGIO is sent if 0 * * Check permission for the file owner @fown to send SIGIO or SIGURG to the * process @tsk. Note that this hook is sometimes called from interrupt. Note * that the fown_struct, @fown, is never outside the context of a struct file, * so the file structure (and associated security information) can always be * obtained: container_of(fown, struct file, f_owner). * * Return: Returns 0 if permission is granted. */ int security_file_send_sigiotask(struct task_struct *tsk, struct fown_struct *fown, int sig) { return call_int_hook(file_send_sigiotask, tsk, fown, sig); } /** * security_file_receive() - Check if receiving a file via IPC is allowed * @file: file being received * * This hook allows security modules to control the ability of a process to * receive an open file descriptor via socket IPC. * * Return: Returns 0 if permission is granted. */ int security_file_receive(struct file *file) { return call_int_hook(file_receive, file); } /** * security_file_open() - Save open() time state for late use by the LSM * @file: * * Save open-time permission checking state for later use upon file_permission, * and recheck access if anything has changed since inode_permission. * * Return: Returns 0 if permission is granted. */ int security_file_open(struct file *file) { return call_int_hook(file_open, file); } /** * security_file_post_open() - Evaluate a file after it has been opened * @file: the file * @mask: access mask * * Evaluate an opened file and the access mask requested with open(). The hook * is useful for LSMs that require the file content to be available in order to * make decisions. * * Return: Returns 0 if permission is granted. */ int security_file_post_open(struct file *file, int mask) { return call_int_hook(file_post_open, file, mask); } EXPORT_SYMBOL_GPL(security_file_post_open); /** * security_file_truncate() - Check if truncating a file is allowed * @file: file * * Check permission before truncating a file, i.e. using ftruncate. Note that * truncation permission may also be checked based on the path, using the * @path_truncate hook. * * Return: Returns 0 if permission is granted. */ int security_file_truncate(struct file *file) { return call_int_hook(file_truncate, file); } /** * security_task_alloc() - Allocate a task's LSM blob * @task: the task * @clone_flags: flags indicating what is being shared * * Handle allocation of task-related resources. * * Return: Returns a zero on success, negative values on failure. */ int security_task_alloc(struct task_struct *task, unsigned long clone_flags) { int rc = lsm_task_alloc(task); if (rc) return rc; rc = call_int_hook(task_alloc, task, clone_flags); if (unlikely(rc)) security_task_free(task); return rc; } /** * security_task_free() - Free a task's LSM blob and related resources * @task: task * * Handle release of task-related resources. Note that this can be called from * interrupt context. */ void security_task_free(struct task_struct *task) { call_void_hook(task_free, task); kfree(task->security); task->security = NULL; } /** * security_cred_alloc_blank() - Allocate the min memory to allow cred_transfer * @cred: credentials * @gfp: gfp flags * * Only allocate sufficient memory and attach to @cred such that * cred_transfer() will not get ENOMEM. * * Return: Returns 0 on success, negative values on failure. */ int security_cred_alloc_blank(struct cred *cred, gfp_t gfp) { int rc = lsm_cred_alloc(cred, gfp); if (rc) return rc; rc = call_int_hook(cred_alloc_blank, cred, gfp); if (unlikely(rc)) security_cred_free(cred); return rc; } /** * security_cred_free() - Free the cred's LSM blob and associated resources * @cred: credentials * * Deallocate and clear the cred->security field in a set of credentials. */ void security_cred_free(struct cred *cred) { /* * There is a failure case in prepare_creds() that * may result in a call here with ->security being NULL. */ if (unlikely(cred->security == NULL)) return; call_void_hook(cred_free, cred); kfree(cred->security); cred->security = NULL; } /** * security_prepare_creds() - Prepare a new set of credentials * @new: new credentials * @old: original credentials * @gfp: gfp flags * * Prepare a new set of credentials by copying the data from the old set. * * Return: Returns 0 on success, negative values on failure. */ int security_prepare_creds(struct cred *new, const struct cred *old, gfp_t gfp) { int rc = lsm_cred_alloc(new, gfp); if (rc) return rc; rc = call_int_hook(cred_prepare, new, old, gfp); if (unlikely(rc)) security_cred_free(new); return rc; } /** * security_transfer_creds() - Transfer creds * @new: target credentials * @old: original credentials * * Transfer data from original creds to new creds. */ void security_transfer_creds(struct cred *new, const struct cred *old) { call_void_hook(cred_transfer, new, old); } /** * security_cred_getsecid() - Get the secid from a set of credentials * @c: credentials * @secid: secid value * * Retrieve the security identifier of the cred structure @c. In case of * failure, @secid will be set to zero. */ void security_cred_getsecid(const struct cred *c, u32 *secid) { *secid = 0; call_void_hook(cred_getsecid, c, secid); } EXPORT_SYMBOL(security_cred_getsecid); /** * security_cred_getlsmprop() - Get the LSM data from a set of credentials * @c: credentials * @prop: destination for the LSM data * * Retrieve the security data of the cred structure @c. In case of * failure, @prop will be cleared. */ void security_cred_getlsmprop(const struct cred *c, struct lsm_prop *prop) { lsmprop_init(prop); call_void_hook(cred_getlsmprop, c, prop); } EXPORT_SYMBOL(security_cred_getlsmprop); /** * security_kernel_act_as() - Set the kernel credentials to act as secid * @new: credentials * @secid: secid * * Set the credentials for a kernel service to act as (subjective context). * The current task must be the one that nominated @secid. * * Return: Returns 0 if successful. */ int security_kernel_act_as(struct cred *new, u32 secid) { return call_int_hook(kernel_act_as, new, secid); } /** * security_kernel_create_files_as() - Set file creation context using an inode * @new: target credentials * @inode: reference inode * * Set the file creation context in a set of credentials to be the same as the * objective context of the specified inode. The current task must be the one * that nominated @inode. * * Return: Returns 0 if successful. */ int security_kernel_create_files_as(struct cred *new, struct inode *inode) { return call_int_hook(kernel_create_files_as, new, inode); } /** * security_kernel_module_request() - Check if loading a module is allowed * @kmod_name: module name * * Ability to trigger the kernel to automatically upcall to userspace for * userspace to load a kernel module with the given name. * * Return: Returns 0 if successful. */ int security_kernel_module_request(char *kmod_name) { return call_int_hook(kernel_module_request, kmod_name); } /** * security_kernel_read_file() - Read a file specified by userspace * @file: file * @id: file identifier * @contents: trust if security_kernel_post_read_file() will be called * * Read a file specified by userspace. * * Return: Returns 0 if permission is granted. */ int security_kernel_read_file(struct file *file, enum kernel_read_file_id id, bool contents) { return call_int_hook(kernel_read_file, file, id, contents); } EXPORT_SYMBOL_GPL(security_kernel_read_file); /** * security_kernel_post_read_file() - Read a file specified by userspace * @file: file * @buf: file contents * @size: size of file contents * @id: file identifier * * Read a file specified by userspace. This must be paired with a prior call * to security_kernel_read_file() call that indicated this hook would also be * called, see security_kernel_read_file() for more information. * * Return: Returns 0 if permission is granted. */ int security_kernel_post_read_file(struct file *file, char *buf, loff_t size, enum kernel_read_file_id id) { return call_int_hook(kernel_post_read_file, file, buf, size, id); } EXPORT_SYMBOL_GPL(security_kernel_post_read_file); /** * security_kernel_load_data() - Load data provided by userspace * @id: data identifier * @contents: true if security_kernel_post_load_data() will be called * * Load data provided by userspace. * * Return: Returns 0 if permission is granted. */ int security_kernel_load_data(enum kernel_load_data_id id, bool contents) { return call_int_hook(kernel_load_data, id, contents); } EXPORT_SYMBOL_GPL(security_kernel_load_data); /** * security_kernel_post_load_data() - Load userspace data from a non-file source * @buf: data * @size: size of data * @id: data identifier * @description: text description of data, specific to the id value * * Load data provided by a non-file source (usually userspace buffer). This * must be paired with a prior security_kernel_load_data() call that indicated * this hook would also be called, see security_kernel_load_data() for more * information. * * Return: Returns 0 if permission is granted. */ int security_kernel_post_load_data(char *buf, loff_t size, enum kernel_load_data_id id, char *description) { return call_int_hook(kernel_post_load_data, buf, size, id, description); } EXPORT_SYMBOL_GPL(security_kernel_post_load_data); /** * security_task_fix_setuid() - Update LSM with new user id attributes * @new: updated credentials * @old: credentials being replaced * @flags: LSM_SETID_* flag values * * Update the module's state after setting one or more of the user identity * attributes of the current process. The @flags parameter indicates which of * the set*uid system calls invoked this hook. If @new is the set of * credentials that will be installed. Modifications should be made to this * rather than to @current->cred. * * Return: Returns 0 on success. */ int security_task_fix_setuid(struct cred *new, const struct cred *old, int flags) { return call_int_hook(task_fix_setuid, new, old, flags); } /** * security_task_fix_setgid() - Update LSM with new group id attributes * @new: updated credentials * @old: credentials being replaced * @flags: LSM_SETID_* flag value * * Update the module's state after setting one or more of the group identity * attributes of the current process. The @flags parameter indicates which of * the set*gid system calls invoked this hook. @new is the set of credentials * that will be installed. Modifications should be made to this rather than to * @current->cred. * * Return: Returns 0 on success. */ int security_task_fix_setgid(struct cred *new, const struct cred *old, int flags) { return call_int_hook(task_fix_setgid, new, old, flags); } /** * security_task_fix_setgroups() - Update LSM with new supplementary groups * @new: updated credentials * @old: credentials being replaced * * Update the module's state after setting the supplementary group identity * attributes of the current process. @new is the set of credentials that will * be installed. Modifications should be made to this rather than to * @current->cred. * * Return: Returns 0 on success. */ int security_task_fix_setgroups(struct cred *new, const struct cred *old) { return call_int_hook(task_fix_setgroups, new, old); } /** * security_task_setpgid() - Check if setting the pgid is allowed * @p: task being modified * @pgid: new pgid * * Check permission before setting the process group identifier of the process * @p to @pgid. * * Return: Returns 0 if permission is granted. */ int security_task_setpgid(struct task_struct *p, pid_t pgid) { return call_int_hook(task_setpgid, p, pgid); } /** * security_task_getpgid() - Check if getting the pgid is allowed * @p: task * * Check permission before getting the process group identifier of the process * @p. * * Return: Returns 0 if permission is granted. */ int security_task_getpgid(struct task_struct *p) { return call_int_hook(task_getpgid, p); } /** * security_task_getsid() - Check if getting the session id is allowed * @p: task * * Check permission before getting the session identifier of the process @p. * * Return: Returns 0 if permission is granted. */ int security_task_getsid(struct task_struct *p) { return call_int_hook(task_getsid, p); } /** * security_current_getlsmprop_subj() - Current task's subjective LSM data * @prop: lsm specific information * * Retrieve the subjective security identifier of the current task and return * it in @prop. */ void security_current_getlsmprop_subj(struct lsm_prop *prop) { lsmprop_init(prop); call_void_hook(current_getlsmprop_subj, prop); } EXPORT_SYMBOL(security_current_getlsmprop_subj); /** * security_task_getlsmprop_obj() - Get a task's objective LSM data * @p: target task * @prop: lsm specific information * * Retrieve the objective security identifier of the task_struct in @p and * return it in @prop. */ void security_task_getlsmprop_obj(struct task_struct *p, struct lsm_prop *prop) { lsmprop_init(prop); call_void_hook(task_getlsmprop_obj, p, prop); } EXPORT_SYMBOL(security_task_getlsmprop_obj); /** * security_task_setnice() - Check if setting a task's nice value is allowed * @p: target task * @nice: nice value * * Check permission before setting the nice value of @p to @nice. * * Return: Returns 0 if permission is granted. */ int security_task_setnice(struct task_struct *p, int nice) { return call_int_hook(task_setnice, p, nice); } /** * security_task_setioprio() - Check if setting a task's ioprio is allowed * @p: target task * @ioprio: ioprio value * * Check permission before setting the ioprio value of @p to @ioprio. * * Return: Returns 0 if permission is granted. */ int security_task_setioprio(struct task_struct *p, int ioprio) { return call_int_hook(task_setioprio, p, ioprio); } /** * security_task_getioprio() - Check if getting a task's ioprio is allowed * @p: task * * Check permission before getting the ioprio value of @p. * * Return: Returns 0 if permission is granted. */ int security_task_getioprio(struct task_struct *p) { return call_int_hook(task_getioprio, p); } /** * security_task_prlimit() - Check if get/setting resources limits is allowed * @cred: current task credentials * @tcred: target task credentials * @flags: LSM_PRLIMIT_* flag bits indicating a get/set/both * * Check permission before getting and/or setting the resource limits of * another task. * * Return: Returns 0 if permission is granted. */ int security_task_prlimit(const struct cred *cred, const struct cred *tcred, unsigned int flags) { return call_int_hook(task_prlimit, cred, tcred, flags); } /** * security_task_setrlimit() - Check if setting a new rlimit value is allowed * @p: target task's group leader * @resource: resource whose limit is being set * @new_rlim: new resource limit * * Check permission before setting the resource limits of process @p for * @resource to @new_rlim. The old resource limit values can be examined by * dereferencing (p->signal->rlim + resource). * * Return: Returns 0 if permission is granted. */ int security_task_setrlimit(struct task_struct *p, unsigned int resource, struct rlimit *new_rlim) { return call_int_hook(task_setrlimit, p, resource, new_rlim); } /** * security_task_setscheduler() - Check if setting sched policy/param is allowed * @p: target task * * Check permission before setting scheduling policy and/or parameters of * process @p. * * Return: Returns 0 if permission is granted. */ int security_task_setscheduler(struct task_struct *p) { return call_int_hook(task_setscheduler, p); } /** * security_task_getscheduler() - Check if getting scheduling info is allowed * @p: target task * * Check permission before obtaining scheduling information for process @p. * * Return: Returns 0 if permission is granted. */ int security_task_getscheduler(struct task_struct *p) { return call_int_hook(task_getscheduler, p); } /** * security_task_movememory() - Check if moving memory is allowed * @p: task * * Check permission before moving memory owned by process @p. * * Return: Returns 0 if permission is granted. */ int security_task_movememory(struct task_struct *p) { return call_int_hook(task_movememory, p); } /** * security_task_kill() - Check if sending a signal is allowed * @p: target process * @info: signal information * @sig: signal value * @cred: credentials of the signal sender, NULL if @current * * Check permission before sending signal @sig to @p. @info can be NULL, the * constant 1, or a pointer to a kernel_siginfo structure. If @info is 1 or * SI_FROMKERNEL(info) is true, then the signal should be viewed as coming from * the kernel and should typically be permitted. SIGIO signals are handled * separately by the send_sigiotask hook in file_security_ops. * * Return: Returns 0 if permission is granted. */ int security_task_kill(struct task_struct *p, struct kernel_siginfo *info, int sig, const struct cred *cred) { return call_int_hook(task_kill, p, info, sig, cred); } /** * security_task_prctl() - Check if a prctl op is allowed * @option: operation * @arg2: argument * @arg3: argument * @arg4: argument * @arg5: argument * * Check permission before performing a process control operation on the * current process. * * Return: Return -ENOSYS if no-one wanted to handle this op, any other value * to cause prctl() to return immediately with that value. */ int security_task_prctl(int option, unsigned long arg2, unsigned long arg3, unsigned long arg4, unsigned long arg5) { int thisrc; int rc = LSM_RET_DEFAULT(task_prctl); struct lsm_static_call *scall; lsm_for_each_hook(scall, task_prctl) { thisrc = scall->hl->hook.task_prctl(option, arg2, arg3, arg4, arg5); if (thisrc != LSM_RET_DEFAULT(task_prctl)) { rc = thisrc; if (thisrc != 0) break; } } return rc; } /** * security_task_to_inode() - Set the security attributes of a task's inode * @p: task * @inode: inode * * Set the security attributes for an inode based on an associated task's * security attributes, e.g. for /proc/pid inodes. */ void security_task_to_inode(struct task_struct *p, struct inode *inode) { call_void_hook(task_to_inode, p, inode); } /** * security_create_user_ns() - Check if creating a new userns is allowed * @cred: prepared creds * * Check permission prior to creating a new user namespace. * * Return: Returns 0 if successful, otherwise < 0 error code. */ int security_create_user_ns(const struct cred *cred) { return call_int_hook(userns_create, cred); } /** * security_ipc_permission() - Check if sysv ipc access is allowed * @ipcp: ipc permission structure * @flag: requested permissions * * Check permissions for access to IPC. * * Return: Returns 0 if permission is granted. */ int security_ipc_permission(struct kern_ipc_perm *ipcp, short flag) { return call_int_hook(ipc_permission, ipcp, flag); } /** * security_ipc_getlsmprop() - Get the sysv ipc object LSM data * @ipcp: ipc permission structure * @prop: pointer to lsm information * * Get the lsm information associated with the ipc object. */ void security_ipc_getlsmprop(struct kern_ipc_perm *ipcp, struct lsm_prop *prop) { lsmprop_init(prop); call_void_hook(ipc_getlsmprop, ipcp, prop); } /** * security_msg_msg_alloc() - Allocate a sysv ipc message LSM blob * @msg: message structure * * Allocate and attach a security structure to the msg->security field. The * security field is initialized to NULL when the structure is first created. * * Return: Return 0 if operation was successful and permission is granted. */ int security_msg_msg_alloc(struct msg_msg *msg) { int rc = lsm_msg_msg_alloc(msg); if (unlikely(rc)) return rc; rc = call_int_hook(msg_msg_alloc_security, msg); if (unlikely(rc)) security_msg_msg_free(msg); return rc; } /** * security_msg_msg_free() - Free a sysv ipc message LSM blob * @msg: message structure * * Deallocate the security structure for this message. */ void security_msg_msg_free(struct msg_msg *msg) { call_void_hook(msg_msg_free_security, msg); kfree(msg->security); msg->security = NULL; } /** * security_msg_queue_alloc() - Allocate a sysv ipc msg queue LSM blob * @msq: sysv ipc permission structure * * Allocate and attach a security structure to @msg. The security field is * initialized to NULL when the structure is first created. * * Return: Returns 0 if operation was successful and permission is granted. */ int security_msg_queue_alloc(struct kern_ipc_perm *msq) { int rc = lsm_ipc_alloc(msq); if (unlikely(rc)) return rc; rc = call_int_hook(msg_queue_alloc_security, msq); if (unlikely(rc)) security_msg_queue_free(msq); return rc; } /** * security_msg_queue_free() - Free a sysv ipc msg queue LSM blob * @msq: sysv ipc permission structure * * Deallocate security field @perm->security for the message queue. */ void security_msg_queue_free(struct kern_ipc_perm *msq) { call_void_hook(msg_queue_free_security, msq); kfree(msq->security); msq->security = NULL; } /** * security_msg_queue_associate() - Check if a msg queue operation is allowed * @msq: sysv ipc permission structure * @msqflg: operation flags * * Check permission when a message queue is requested through the msgget system * call. This hook is only called when returning the message queue identifier * for an existing message queue, not when a new message queue is created. * * Return: Return 0 if permission is granted. */ int security_msg_queue_associate(struct kern_ipc_perm *msq, int msqflg) { return call_int_hook(msg_queue_associate, msq, msqflg); } /** * security_msg_queue_msgctl() - Check if a msg queue operation is allowed * @msq: sysv ipc permission structure * @cmd: operation * * Check permission when a message control operation specified by @cmd is to be * performed on the message queue with permissions. * * Return: Returns 0 if permission is granted. */ int security_msg_queue_msgctl(struct kern_ipc_perm *msq, int cmd) { return call_int_hook(msg_queue_msgctl, msq, cmd); } /** * security_msg_queue_msgsnd() - Check if sending a sysv ipc message is allowed * @msq: sysv ipc permission structure * @msg: message * @msqflg: operation flags * * Check permission before a message, @msg, is enqueued on the message queue * with permissions specified in @msq. * * Return: Returns 0 if permission is granted. */ int security_msg_queue_msgsnd(struct kern_ipc_perm *msq, struct msg_msg *msg, int msqflg) { return call_int_hook(msg_queue_msgsnd, msq, msg, msqflg); } /** * security_msg_queue_msgrcv() - Check if receiving a sysv ipc msg is allowed * @msq: sysv ipc permission structure * @msg: message * @target: target task * @type: type of message requested * @mode: operation flags * * Check permission before a message, @msg, is removed from the message queue. * The @target task structure contains a pointer to the process that will be * receiving the message (not equal to the current process when inline receives * are being performed). * * Return: Returns 0 if permission is granted. */ int security_msg_queue_msgrcv(struct kern_ipc_perm *msq, struct msg_msg *msg, struct task_struct *target, long type, int mode) { return call_int_hook(msg_queue_msgrcv, msq, msg, target, type, mode); } /** * security_shm_alloc() - Allocate a sysv shm LSM blob * @shp: sysv ipc permission structure * * Allocate and attach a security structure to the @shp security field. The * security field is initialized to NULL when the structure is first created. * * Return: Returns 0 if operation was successful and permission is granted. */ int security_shm_alloc(struct kern_ipc_perm *shp) { int rc = lsm_ipc_alloc(shp); if (unlikely(rc)) return rc; rc = call_int_hook(shm_alloc_security, shp); if (unlikely(rc)) security_shm_free(shp); return rc; } /** * security_shm_free() - Free a sysv shm LSM blob * @shp: sysv ipc permission structure * * Deallocate the security structure @perm->security for the memory segment. */ void security_shm_free(struct kern_ipc_perm *shp) { call_void_hook(shm_free_security, shp); kfree(shp->security); shp->security = NULL; } /** * security_shm_associate() - Check if a sysv shm operation is allowed * @shp: sysv ipc permission structure * @shmflg: operation flags * * Check permission when a shared memory region is requested through the shmget * system call. This hook is only called when returning the shared memory * region identifier for an existing region, not when a new shared memory * region is created. * * Return: Returns 0 if permission is granted. */ int security_shm_associate(struct kern_ipc_perm *shp, int shmflg) { return call_int_hook(shm_associate, shp, shmflg); } /** * security_shm_shmctl() - Check if a sysv shm operation is allowed * @shp: sysv ipc permission structure * @cmd: operation * * Check permission when a shared memory control operation specified by @cmd is * to be performed on the shared memory region with permissions in @shp. * * Return: Return 0 if permission is granted. */ int security_shm_shmctl(struct kern_ipc_perm *shp, int cmd) { return call_int_hook(shm_shmctl, shp, cmd); } /** * security_shm_shmat() - Check if a sysv shm attach operation is allowed * @shp: sysv ipc permission structure * @shmaddr: address of memory region to attach * @shmflg: operation flags * * Check permissions prior to allowing the shmat system call to attach the * shared memory segment with permissions @shp to the data segment of the * calling process. The attaching address is specified by @shmaddr. * * Return: Returns 0 if permission is granted. */ int security_shm_shmat(struct kern_ipc_perm *shp, char __user *shmaddr, int shmflg) { return call_int_hook(shm_shmat, shp, shmaddr, shmflg); } /** * security_sem_alloc() - Allocate a sysv semaphore LSM blob * @sma: sysv ipc permission structure * * Allocate and attach a security structure to the @sma security field. The * security field is initialized to NULL when the structure is first created. * * Return: Returns 0 if operation was successful and permission is granted. */ int security_sem_alloc(struct kern_ipc_perm *sma) { int rc = lsm_ipc_alloc(sma); if (unlikely(rc)) return rc; rc = call_int_hook(sem_alloc_security, sma); if (unlikely(rc)) security_sem_free(sma); return rc; } /** * security_sem_free() - Free a sysv semaphore LSM blob * @sma: sysv ipc permission structure * * Deallocate security structure @sma->security for the semaphore. */ void security_sem_free(struct kern_ipc_perm *sma) { call_void_hook(sem_free_security, sma); kfree(sma->security); sma->security = NULL; } /** * security_sem_associate() - Check if a sysv semaphore operation is allowed * @sma: sysv ipc permission structure * @semflg: operation flags * * Check permission when a semaphore is requested through the semget system * call. This hook is only called when returning the semaphore identifier for * an existing semaphore, not when a new one must be created. * * Return: Returns 0 if permission is granted. */ int security_sem_associate(struct kern_ipc_perm *sma, int semflg) { return call_int_hook(sem_associate, sma, semflg); } /** * security_sem_semctl() - Check if a sysv semaphore operation is allowed * @sma: sysv ipc permission structure * @cmd: operation * * Check permission when a semaphore operation specified by @cmd is to be * performed on the semaphore. * * Return: Returns 0 if permission is granted. */ int security_sem_semctl(struct kern_ipc_perm *sma, int cmd) { return call_int_hook(sem_semctl, sma, cmd); } /** * security_sem_semop() - Check if a sysv semaphore operation is allowed * @sma: sysv ipc permission structure * @sops: operations to perform * @nsops: number of operations * @alter: flag indicating changes will be made * * Check permissions before performing operations on members of the semaphore * set. If the @alter flag is nonzero, the semaphore set may be modified. * * Return: Returns 0 if permission is granted. */ int security_sem_semop(struct kern_ipc_perm *sma, struct sembuf *sops, unsigned nsops, int alter) { return call_int_hook(sem_semop, sma, sops, nsops, alter); } /** * security_d_instantiate() - Populate an inode's LSM state based on a dentry * @dentry: dentry * @inode: inode * * Fill in @inode security information for a @dentry if allowed. */ void security_d_instantiate(struct dentry *dentry, struct inode *inode) { if (unlikely(inode && IS_PRIVATE(inode))) return; call_void_hook(d_instantiate, dentry, inode); } EXPORT_SYMBOL(security_d_instantiate); /* * Please keep this in sync with it's counterpart in security/lsm_syscalls.c */ /** * security_getselfattr - Read an LSM attribute of the current process. * @attr: which attribute to return * @uctx: the user-space destination for the information, or NULL * @size: pointer to the size of space available to receive the data * @flags: special handling options. LSM_FLAG_SINGLE indicates that only * attributes associated with the LSM identified in the passed @ctx be * reported. * * A NULL value for @uctx can be used to get both the number of attributes * and the size of the data. * * Returns the number of attributes found on success, negative value * on error. @size is reset to the total size of the data. * If @size is insufficient to contain the data -E2BIG is returned. */ int security_getselfattr(unsigned int attr, struct lsm_ctx __user *uctx, u32 __user *size, u32 flags) { struct lsm_static_call *scall; struct lsm_ctx lctx = { .id = LSM_ID_UNDEF, }; u8 __user *base = (u8 __user *)uctx; u32 entrysize; u32 total = 0; u32 left; bool toobig = false; bool single = false; int count = 0; int rc; if (attr == LSM_ATTR_UNDEF) return -EINVAL; if (size == NULL) return -EINVAL; if (get_user(left, size)) return -EFAULT; if (flags) { /* * Only flag supported is LSM_FLAG_SINGLE */ if (flags != LSM_FLAG_SINGLE || !uctx) return -EINVAL; if (copy_from_user(&lctx, uctx, sizeof(lctx))) return -EFAULT; /* * If the LSM ID isn't specified it is an error. */ if (lctx.id == LSM_ID_UNDEF) return -EINVAL; single = true; } /* * In the usual case gather all the data from the LSMs. * In the single case only get the data from the LSM specified. */ lsm_for_each_hook(scall, getselfattr) { if (single && lctx.id != scall->hl->lsmid->id) continue; entrysize = left; if (base) uctx = (struct lsm_ctx __user *)(base + total); rc = scall->hl->hook.getselfattr(attr, uctx, &entrysize, flags); if (rc == -EOPNOTSUPP) { rc = 0; continue; } if (rc == -E2BIG) { rc = 0; left = 0; toobig = true; } else if (rc < 0) return rc; else left -= entrysize; total += entrysize; count += rc; if (single) break; } if (put_user(total, size)) return -EFAULT; if (toobig) return -E2BIG; if (count == 0) return LSM_RET_DEFAULT(getselfattr); return count; } /* * Please keep this in sync with it's counterpart in security/lsm_syscalls.c */ /** * security_setselfattr - Set an LSM attribute on the current process. * @attr: which attribute to set * @uctx: the user-space source for the information * @size: the size of the data * @flags: reserved for future use, must be 0 * * Set an LSM attribute for the current process. The LSM, attribute * and new value are included in @uctx. * * Returns 0 on success, -EINVAL if the input is inconsistent, -EFAULT * if the user buffer is inaccessible, E2BIG if size is too big, or an * LSM specific failure. */ int security_setselfattr(unsigned int attr, struct lsm_ctx __user *uctx, u32 size, u32 flags) { struct lsm_static_call *scall; struct lsm_ctx *lctx; int rc = LSM_RET_DEFAULT(setselfattr); u64 required_len; if (flags) return -EINVAL; if (size < sizeof(*lctx)) return -EINVAL; if (size > PAGE_SIZE) return -E2BIG; lctx = memdup_user(uctx, size); if (IS_ERR(lctx)) return PTR_ERR(lctx); if (size < lctx->len || check_add_overflow(sizeof(*lctx), lctx->ctx_len, &required_len) || lctx->len < required_len) { rc = -EINVAL; goto free_out; } lsm_for_each_hook(scall, setselfattr) if ((scall->hl->lsmid->id) == lctx->id) { rc = scall->hl->hook.setselfattr(attr, lctx, size, flags); break; } free_out: kfree(lctx); return rc; } /** * security_getprocattr() - Read an attribute for a task * @p: the task * @lsmid: LSM identification * @name: attribute name * @value: attribute value * * Read attribute @name for task @p and store it into @value if allowed. * * Return: Returns the length of @value on success, a negative value otherwise. */ int security_getprocattr(struct task_struct *p, int lsmid, const char *name, char **value) { struct lsm_static_call *scall; lsm_for_each_hook(scall, getprocattr) { if (lsmid != 0 && lsmid != scall->hl->lsmid->id) continue; return scall->hl->hook.getprocattr(p, name, value); } return LSM_RET_DEFAULT(getprocattr); } /** * security_setprocattr() - Set an attribute for a task * @lsmid: LSM identification * @name: attribute name * @value: attribute value * @size: attribute value size * * Write (set) the current task's attribute @name to @value, size @size if * allowed. * * Return: Returns bytes written on success, a negative value otherwise. */ int security_setprocattr(int lsmid, const char *name, void *value, size_t size) { struct lsm_static_call *scall; lsm_for_each_hook(scall, setprocattr) { if (lsmid != 0 && lsmid != scall->hl->lsmid->id) continue; return scall->hl->hook.setprocattr(name, value, size); } return LSM_RET_DEFAULT(setprocattr); } /** * security_netlink_send() - Save info and check if netlink sending is allowed * @sk: sending socket * @skb: netlink message * * Save security information for a netlink message so that permission checking * can be performed when the message is processed. The security information * can be saved using the eff_cap field of the netlink_skb_parms structure. * Also may be used to provide fine grained control over message transmission. * * Return: Returns 0 if the information was successfully saved and message is * allowed to be transmitted. */ int security_netlink_send(struct sock *sk, struct sk_buff *skb) { return call_int_hook(netlink_send, sk, skb); } /** * security_ismaclabel() - Check if the named attribute is a MAC label * @name: full extended attribute name * * Check if the extended attribute specified by @name represents a MAC label. * * Return: Returns 1 if name is a MAC attribute otherwise returns 0. */ int security_ismaclabel(const char *name) { return call_int_hook(ismaclabel, name); } EXPORT_SYMBOL(security_ismaclabel); /** * security_secid_to_secctx() - Convert a secid to a secctx * @secid: secid * @secdata: secctx * @seclen: secctx length * * Convert secid to security context. If @secdata is NULL the length of the * result will be returned in @seclen, but no @secdata will be returned. This * does mean that the length could change between calls to check the length and * the next call which actually allocates and returns the @secdata. * * Return: Return 0 on success, error on failure. */ int security_secid_to_secctx(u32 secid, char **secdata, u32 *seclen) { return call_int_hook(secid_to_secctx, secid, secdata, seclen); } EXPORT_SYMBOL(security_secid_to_secctx); /** * security_lsmprop_to_secctx() - Convert a lsm_prop to a secctx * @prop: lsm specific information * @secdata: secctx * @seclen: secctx length * * Convert a @prop entry to security context. If @secdata is NULL the * length of the result will be returned in @seclen, but no @secdata * will be returned. This does mean that the length could change between * calls to check the length and the next call which actually allocates * and returns the @secdata. * * Return: Return 0 on success, error on failure. */ int security_lsmprop_to_secctx(struct lsm_prop *prop, char **secdata, u32 *seclen) { return call_int_hook(lsmprop_to_secctx, prop, secdata, seclen); } EXPORT_SYMBOL(security_lsmprop_to_secctx); /** * security_secctx_to_secid() - Convert a secctx to a secid * @secdata: secctx * @seclen: length of secctx * @secid: secid * * Convert security context to secid. * * Return: Returns 0 on success, error on failure. */ int security_secctx_to_secid(const char *secdata, u32 seclen, u32 *secid) { *secid = 0; return call_int_hook(secctx_to_secid, secdata, seclen, secid); } EXPORT_SYMBOL(security_secctx_to_secid); /** * security_release_secctx() - Free a secctx buffer * @secdata: secctx * @seclen: length of secctx * * Release the security context. */ void security_release_secctx(char *secdata, u32 seclen) { call_void_hook(release_secctx, secdata, seclen); } EXPORT_SYMBOL(security_release_secctx); /** * security_inode_invalidate_secctx() - Invalidate an inode's security label * @inode: inode * * Notify the security module that it must revalidate the security context of * an inode. */ void security_inode_invalidate_secctx(struct inode *inode) { call_void_hook(inode_invalidate_secctx, inode); } EXPORT_SYMBOL(security_inode_invalidate_secctx); /** * security_inode_notifysecctx() - Notify the LSM of an inode's security label * @inode: inode * @ctx: secctx * @ctxlen: length of secctx * * Notify the security module of what the security context of an inode should * be. Initializes the incore security context managed by the security module * for this inode. Example usage: NFS client invokes this hook to initialize * the security context in its incore inode to the value provided by the server * for the file when the server returned the file's attributes to the client. * Must be called with inode->i_mutex locked. * * Return: Returns 0 on success, error on failure. */ int security_inode_notifysecctx(struct inode *inode, void *ctx, u32 ctxlen) { return call_int_hook(inode_notifysecctx, inode, ctx, ctxlen); } EXPORT_SYMBOL(security_inode_notifysecctx); /** * security_inode_setsecctx() - Change the security label of an inode * @dentry: inode * @ctx: secctx * @ctxlen: length of secctx * * Change the security context of an inode. Updates the incore security * context managed by the security module and invokes the fs code as needed * (via __vfs_setxattr_noperm) to update any backing xattrs that represent the * context. Example usage: NFS server invokes this hook to change the security * context in its incore inode and on the backing filesystem to a value * provided by the client on a SETATTR operation. Must be called with * inode->i_mutex locked. * * Return: Returns 0 on success, error on failure. */ int security_inode_setsecctx(struct dentry *dentry, void *ctx, u32 ctxlen) { return call_int_hook(inode_setsecctx, dentry, ctx, ctxlen); } EXPORT_SYMBOL(security_inode_setsecctx); /** * security_inode_getsecctx() - Get the security label of an inode * @inode: inode * @ctx: secctx * @ctxlen: length of secctx * * On success, returns 0 and fills out @ctx and @ctxlen with the security * context for the given @inode. * * Return: Returns 0 on success, error on failure. */ int security_inode_getsecctx(struct inode *inode, void **ctx, u32 *ctxlen) { return call_int_hook(inode_getsecctx, inode, ctx, ctxlen); } EXPORT_SYMBOL(security_inode_getsecctx); #ifdef CONFIG_WATCH_QUEUE /** * security_post_notification() - Check if a watch notification can be posted * @w_cred: credentials of the task that set the watch * @cred: credentials of the task which triggered the watch * @n: the notification * * Check to see if a watch notification can be posted to a particular queue. * * Return: Returns 0 if permission is granted. */ int security_post_notification(const struct cred *w_cred, const struct cred *cred, struct watch_notification *n) { return call_int_hook(post_notification, w_cred, cred, n); } #endif /* CONFIG_WATCH_QUEUE */ #ifdef CONFIG_KEY_NOTIFICATIONS /** * security_watch_key() - Check if a task is allowed to watch for key events * @key: the key to watch * * Check to see if a process is allowed to watch for event notifications from * a key or keyring. * * Return: Returns 0 if permission is granted. */ int security_watch_key(struct key *key) { return call_int_hook(watch_key, key); } #endif /* CONFIG_KEY_NOTIFICATIONS */ #ifdef CONFIG_SECURITY_NETWORK /** * security_unix_stream_connect() - Check if a AF_UNIX stream is allowed * @sock: originating sock * @other: peer sock * @newsk: new sock * * Check permissions before establishing a Unix domain stream connection * between @sock and @other. * * The @unix_stream_connect and @unix_may_send hooks were necessary because * Linux provides an alternative to the conventional file name space for Unix * domain sockets. Whereas binding and connecting to sockets in the file name * space is mediated by the typical file permissions (and caught by the mknod * and permission hooks in inode_security_ops), binding and connecting to * sockets in the abstract name space is completely unmediated. Sufficient * control of Unix domain sockets in the abstract name space isn't possible * using only the socket layer hooks, since we need to know the actual target * socket, which is not looked up until we are inside the af_unix code. * * Return: Returns 0 if permission is granted. */ int security_unix_stream_connect(struct sock *sock, struct sock *other, struct sock *newsk) { return call_int_hook(unix_stream_connect, sock, other, newsk); } EXPORT_SYMBOL(security_unix_stream_connect); /** * security_unix_may_send() - Check if AF_UNIX socket can send datagrams * @sock: originating sock * @other: peer sock * * Check permissions before connecting or sending datagrams from @sock to * @other. * * The @unix_stream_connect and @unix_may_send hooks were necessary because * Linux provides an alternative to the conventional file name space for Unix * domain sockets. Whereas binding and connecting to sockets in the file name * space is mediated by the typical file permissions (and caught by the mknod * and permission hooks in inode_security_ops), binding and connecting to * sockets in the abstract name space is completely unmediated. Sufficient * control of Unix domain sockets in the abstract name space isn't possible * using only the socket layer hooks, since we need to know the actual target * socket, which is not looked up until we are inside the af_unix code. * * Return: Returns 0 if permission is granted. */ int security_unix_may_send(struct socket *sock, struct socket *other) { return call_int_hook(unix_may_send, sock, other); } EXPORT_SYMBOL(security_unix_may_send); /** * security_socket_create() - Check if creating a new socket is allowed * @family: protocol family * @type: communications type * @protocol: requested protocol * @kern: set to 1 if a kernel socket is requested * * Check permissions prior to creating a new socket. * * Return: Returns 0 if permission is granted. */ int security_socket_create(int family, int type, int protocol, int kern) { return call_int_hook(socket_create, family, type, protocol, kern); } /** * security_socket_post_create() - Initialize a newly created socket * @sock: socket * @family: protocol family * @type: communications type * @protocol: requested protocol * @kern: set to 1 if a kernel socket is requested * * This hook allows a module to update or allocate a per-socket security * structure. Note that the security field was not added directly to the socket * structure, but rather, the socket security information is stored in the * associated inode. Typically, the inode alloc_security hook will allocate * and attach security information to SOCK_INODE(sock)->i_security. This hook * may be used to update the SOCK_INODE(sock)->i_security field with additional * information that wasn't available when the inode was allocated. * * Return: Returns 0 if permission is granted. */ int security_socket_post_create(struct socket *sock, int family, int type, int protocol, int kern) { return call_int_hook(socket_post_create, sock, family, type, protocol, kern); } /** * security_socket_socketpair() - Check if creating a socketpair is allowed * @socka: first socket * @sockb: second socket * * Check permissions before creating a fresh pair of sockets. * * Return: Returns 0 if permission is granted and the connection was * established. */ int security_socket_socketpair(struct socket *socka, struct socket *sockb) { return call_int_hook(socket_socketpair, socka, sockb); } EXPORT_SYMBOL(security_socket_socketpair); /** * security_socket_bind() - Check if a socket bind operation is allowed * @sock: socket * @address: requested bind address * @addrlen: length of address * * Check permission before socket protocol layer bind operation is performed * and the socket @sock is bound to the address specified in the @address * parameter. * * Return: Returns 0 if permission is granted. */ int security_socket_bind(struct socket *sock, struct sockaddr *address, int addrlen) { return call_int_hook(socket_bind, sock, address, addrlen); } /** * security_socket_connect() - Check if a socket connect operation is allowed * @sock: socket * @address: address of remote connection point * @addrlen: length of address * * Check permission before socket protocol layer connect operation attempts to * connect socket @sock to a remote address, @address. * * Return: Returns 0 if permission is granted. */ int security_socket_connect(struct socket *sock, struct sockaddr *address, int addrlen) { return call_int_hook(socket_connect, sock, address, addrlen); } /** * security_socket_listen() - Check if a socket is allowed to listen * @sock: socket * @backlog: connection queue size * * Check permission before socket protocol layer listen operation. * * Return: Returns 0 if permission is granted. */ int security_socket_listen(struct socket *sock, int backlog) { return call_int_hook(socket_listen, sock, backlog); } /** * security_socket_accept() - Check if a socket is allowed to accept connections * @sock: listening socket * @newsock: newly creation connection socket * * Check permission before accepting a new connection. Note that the new * socket, @newsock, has been created and some information copied to it, but * the accept operation has not actually been performed. * * Return: Returns 0 if permission is granted. */ int security_socket_accept(struct socket *sock, struct socket *newsock) { return call_int_hook(socket_accept, sock, newsock); } /** * security_socket_sendmsg() - Check if sending a message is allowed * @sock: sending socket * @msg: message to send * @size: size of message * * Check permission before transmitting a message to another socket. * * Return: Returns 0 if permission is granted. */ int security_socket_sendmsg(struct socket *sock, struct msghdr *msg, int size) { return call_int_hook(socket_sendmsg, sock, msg, size); } /** * security_socket_recvmsg() - Check if receiving a message is allowed * @sock: receiving socket * @msg: message to receive * @size: size of message * @flags: operational flags * * Check permission before receiving a message from a socket. * * Return: Returns 0 if permission is granted. */ int security_socket_recvmsg(struct socket *sock, struct msghdr *msg, int size, int flags) { return call_int_hook(socket_recvmsg, sock, msg, size, flags); } /** * security_socket_getsockname() - Check if reading the socket addr is allowed * @sock: socket * * Check permission before reading the local address (name) of the socket * object. * * Return: Returns 0 if permission is granted. */ int security_socket_getsockname(struct socket *sock) { return call_int_hook(socket_getsockname, sock); } /** * security_socket_getpeername() - Check if reading the peer's addr is allowed * @sock: socket * * Check permission before the remote address (name) of a socket object. * * Return: Returns 0 if permission is granted. */ int security_socket_getpeername(struct socket *sock) { return call_int_hook(socket_getpeername, sock); } /** * security_socket_getsockopt() - Check if reading a socket option is allowed * @sock: socket * @level: option's protocol level * @optname: option name * * Check permissions before retrieving the options associated with socket * @sock. * * Return: Returns 0 if permission is granted. */ int security_socket_getsockopt(struct socket *sock, int level, int optname) { return call_int_hook(socket_getsockopt, sock, level, optname); } /** * security_socket_setsockopt() - Check if setting a socket option is allowed * @sock: socket * @level: option's protocol level * @optname: option name * * Check permissions before setting the options associated with socket @sock. * * Return: Returns 0 if permission is granted. */ int security_socket_setsockopt(struct socket *sock, int level, int optname) { return call_int_hook(socket_setsockopt, sock, level, optname); } /** * security_socket_shutdown() - Checks if shutting down the socket is allowed * @sock: socket * @how: flag indicating how sends and receives are handled * * Checks permission before all or part of a connection on the socket @sock is * shut down. * * Return: Returns 0 if permission is granted. */ int security_socket_shutdown(struct socket *sock, int how) { return call_int_hook(socket_shutdown, sock, how); } /** * security_sock_rcv_skb() - Check if an incoming network packet is allowed * @sk: destination sock * @skb: incoming packet * * Check permissions on incoming network packets. This hook is distinct from * Netfilter's IP input hooks since it is the first time that the incoming * sk_buff @skb has been associated with a particular socket, @sk. Must not * sleep inside this hook because some callers hold spinlocks. * * Return: Returns 0 if permission is granted. */ int security_sock_rcv_skb(struct sock *sk, struct sk_buff *skb) { return call_int_hook(socket_sock_rcv_skb, sk, skb); } EXPORT_SYMBOL(security_sock_rcv_skb); /** * security_socket_getpeersec_stream() - Get the remote peer label * @sock: socket * @optval: destination buffer * @optlen: size of peer label copied into the buffer * @len: maximum size of the destination buffer * * This hook allows the security module to provide peer socket security state * for unix or connected tcp sockets to userspace via getsockopt SO_GETPEERSEC. * For tcp sockets this can be meaningful if the socket is associated with an * ipsec SA. * * Return: Returns 0 if all is well, otherwise, typical getsockopt return * values. */ int security_socket_getpeersec_stream(struct socket *sock, sockptr_t optval, sockptr_t optlen, unsigned int len) { return call_int_hook(socket_getpeersec_stream, sock, optval, optlen, len); } /** * security_socket_getpeersec_dgram() - Get the remote peer label * @sock: socket * @skb: datagram packet * @secid: remote peer label secid * * This hook allows the security module to provide peer socket security state * for udp sockets on a per-packet basis to userspace via getsockopt * SO_GETPEERSEC. The application must first have indicated the IP_PASSSEC * option via getsockopt. It can then retrieve the security state returned by * this hook for a packet via the SCM_SECURITY ancillary message type. * * Return: Returns 0 on success, error on failure. */ int security_socket_getpeersec_dgram(struct socket *sock, struct sk_buff *skb, u32 *secid) { return call_int_hook(socket_getpeersec_dgram, sock, skb, secid); } EXPORT_SYMBOL(security_socket_getpeersec_dgram); /** * lsm_sock_alloc - allocate a composite sock blob * @sock: the sock that needs a blob * @gfp: allocation mode * * Allocate the sock blob for all the modules * * Returns 0, or -ENOMEM if memory can't be allocated. */ static int lsm_sock_alloc(struct sock *sock, gfp_t gfp) { return lsm_blob_alloc(&sock->sk_security, blob_sizes.lbs_sock, gfp); } /** * security_sk_alloc() - Allocate and initialize a sock's LSM blob * @sk: sock * @family: protocol family * @priority: gfp flags * * Allocate and attach a security structure to the sk->sk_security field, which * is used to copy security attributes between local stream sockets. * * Return: Returns 0 on success, error on failure. */ int security_sk_alloc(struct sock *sk, int family, gfp_t priority) { int rc = lsm_sock_alloc(sk, priority); if (unlikely(rc)) return rc; rc = call_int_hook(sk_alloc_security, sk, family, priority); if (unlikely(rc)) security_sk_free(sk); return rc; } /** * security_sk_free() - Free the sock's LSM blob * @sk: sock * * Deallocate security structure. */ void security_sk_free(struct sock *sk) { call_void_hook(sk_free_security, sk); kfree(sk->sk_security); sk->sk_security = NULL; } /** * security_sk_clone() - Clone a sock's LSM state * @sk: original sock * @newsk: target sock * * Clone/copy security structure. */ void security_sk_clone(const struct sock *sk, struct sock *newsk) { call_void_hook(sk_clone_security, sk, newsk); } EXPORT_SYMBOL(security_sk_clone); /** * security_sk_classify_flow() - Set a flow's secid based on socket * @sk: original socket * @flic: target flow * * Set the target flow's secid to socket's secid. */ void security_sk_classify_flow(const struct sock *sk, struct flowi_common *flic) { call_void_hook(sk_getsecid, sk, &flic->flowic_secid); } EXPORT_SYMBOL(security_sk_classify_flow); /** * security_req_classify_flow() - Set a flow's secid based on request_sock * @req: request_sock * @flic: target flow * * Sets @flic's secid to @req's secid. */ void security_req_classify_flow(const struct request_sock *req, struct flowi_common *flic) { call_void_hook(req_classify_flow, req, flic); } EXPORT_SYMBOL(security_req_classify_flow); /** * security_sock_graft() - Reconcile LSM state when grafting a sock on a socket * @sk: sock being grafted * @parent: target parent socket * * Sets @parent's inode secid to @sk's secid and update @sk with any necessary * LSM state from @parent. */ void security_sock_graft(struct sock *sk, struct socket *parent) { call_void_hook(sock_graft, sk, parent); } EXPORT_SYMBOL(security_sock_graft); /** * security_inet_conn_request() - Set request_sock state using incoming connect * @sk: parent listening sock * @skb: incoming connection * @req: new request_sock * * Initialize the @req LSM state based on @sk and the incoming connect in @skb. * * Return: Returns 0 if permission is granted. */ int security_inet_conn_request(const struct sock *sk, struct sk_buff *skb, struct request_sock *req) { return call_int_hook(inet_conn_request, sk, skb, req); } EXPORT_SYMBOL(security_inet_conn_request); /** * security_inet_csk_clone() - Set new sock LSM state based on request_sock * @newsk: new sock * @req: connection request_sock * * Set that LSM state of @sock using the LSM state from @req. */ void security_inet_csk_clone(struct sock *newsk, const struct request_sock *req) { call_void_hook(inet_csk_clone, newsk, req); } /** * security_inet_conn_established() - Update sock's LSM state with connection * @sk: sock * @skb: connection packet * * Update @sock's LSM state to represent a new connection from @skb. */ void security_inet_conn_established(struct sock *sk, struct sk_buff *skb) { call_void_hook(inet_conn_established, sk, skb); } EXPORT_SYMBOL(security_inet_conn_established); /** * security_secmark_relabel_packet() - Check if setting a secmark is allowed * @secid: new secmark value * * Check if the process should be allowed to relabel packets to @secid. * * Return: Returns 0 if permission is granted. */ int security_secmark_relabel_packet(u32 secid) { return call_int_hook(secmark_relabel_packet, secid); } EXPORT_SYMBOL(security_secmark_relabel_packet); /** * security_secmark_refcount_inc() - Increment the secmark labeling rule count * * Tells the LSM to increment the number of secmark labeling rules loaded. */ void security_secmark_refcount_inc(void) { call_void_hook(secmark_refcount_inc); } EXPORT_SYMBOL(security_secmark_refcount_inc); /** * security_secmark_refcount_dec() - Decrement the secmark labeling rule count * * Tells the LSM to decrement the number of secmark labeling rules loaded. */ void security_secmark_refcount_dec(void) { call_void_hook(secmark_refcount_dec); } EXPORT_SYMBOL(security_secmark_refcount_dec); /** * security_tun_dev_alloc_security() - Allocate a LSM blob for a TUN device * @security: pointer to the LSM blob * * This hook allows a module to allocate a security structure for a TUN device, * returning the pointer in @security. * * Return: Returns a zero on success, negative values on failure. */ int security_tun_dev_alloc_security(void **security) { int rc; rc = lsm_blob_alloc(security, blob_sizes.lbs_tun_dev, GFP_KERNEL); if (rc) return rc; rc = call_int_hook(tun_dev_alloc_security, *security); if (rc) { kfree(*security); *security = NULL; } return rc; } EXPORT_SYMBOL(security_tun_dev_alloc_security); /** * security_tun_dev_free_security() - Free a TUN device LSM blob * @security: LSM blob * * This hook allows a module to free the security structure for a TUN device. */ void security_tun_dev_free_security(void *security) { kfree(security); } EXPORT_SYMBOL(security_tun_dev_free_security); /** * security_tun_dev_create() - Check if creating a TUN device is allowed * * Check permissions prior to creating a new TUN device. * * Return: Returns 0 if permission is granted. */ int security_tun_dev_create(void) { return call_int_hook(tun_dev_create); } EXPORT_SYMBOL(security_tun_dev_create); /** * security_tun_dev_attach_queue() - Check if attaching a TUN queue is allowed * @security: TUN device LSM blob * * Check permissions prior to attaching to a TUN device queue. * * Return: Returns 0 if permission is granted. */ int security_tun_dev_attach_queue(void *security) { return call_int_hook(tun_dev_attach_queue, security); } EXPORT_SYMBOL(security_tun_dev_attach_queue); /** * security_tun_dev_attach() - Update TUN device LSM state on attach * @sk: associated sock * @security: TUN device LSM blob * * This hook can be used by the module to update any security state associated * with the TUN device's sock structure. * * Return: Returns 0 if permission is granted. */ int security_tun_dev_attach(struct sock *sk, void *security) { return call_int_hook(tun_dev_attach, sk, security); } EXPORT_SYMBOL(security_tun_dev_attach); /** * security_tun_dev_open() - Update TUN device LSM state on open * @security: TUN device LSM blob * * This hook can be used by the module to update any security state associated * with the TUN device's security structure. * * Return: Returns 0 if permission is granted. */ int security_tun_dev_open(void *security) { return call_int_hook(tun_dev_open, security); } EXPORT_SYMBOL(security_tun_dev_open); /** * security_sctp_assoc_request() - Update the LSM on a SCTP association req * @asoc: SCTP association * @skb: packet requesting the association * * Passes the @asoc and @chunk->skb of the association INIT packet to the LSM. * * Return: Returns 0 on success, error on failure. */ int security_sctp_assoc_request(struct sctp_association *asoc, struct sk_buff *skb) { return call_int_hook(sctp_assoc_request, asoc, skb); } EXPORT_SYMBOL(security_sctp_assoc_request); /** * security_sctp_bind_connect() - Validate a list of addrs for a SCTP option * @sk: socket * @optname: SCTP option to validate * @address: list of IP addresses to validate * @addrlen: length of the address list * * Validiate permissions required for each address associated with sock @sk. * Depending on @optname, the addresses will be treated as either a connect or * bind service. The @addrlen is calculated on each IPv4 and IPv6 address using * sizeof(struct sockaddr_in) or sizeof(struct sockaddr_in6). * * Return: Returns 0 on success, error on failure. */ int security_sctp_bind_connect(struct sock *sk, int optname, struct sockaddr *address, int addrlen) { return call_int_hook(sctp_bind_connect, sk, optname, address, addrlen); } EXPORT_SYMBOL(security_sctp_bind_connect); /** * security_sctp_sk_clone() - Clone a SCTP sock's LSM state * @asoc: SCTP association * @sk: original sock * @newsk: target sock * * Called whenever a new socket is created by accept(2) (i.e. a TCP style * socket) or when a socket is 'peeled off' e.g userspace calls * sctp_peeloff(3). */ void security_sctp_sk_clone(struct sctp_association *asoc, struct sock *sk, struct sock *newsk) { call_void_hook(sctp_sk_clone, asoc, sk, newsk); } EXPORT_SYMBOL(security_sctp_sk_clone); /** * security_sctp_assoc_established() - Update LSM state when assoc established * @asoc: SCTP association * @skb: packet establishing the association * * Passes the @asoc and @chunk->skb of the association COOKIE_ACK packet to the * security module. * * Return: Returns 0 if permission is granted. */ int security_sctp_assoc_established(struct sctp_association *asoc, struct sk_buff *skb) { return call_int_hook(sctp_assoc_established, asoc, skb); } EXPORT_SYMBOL(security_sctp_assoc_established); /** * security_mptcp_add_subflow() - Inherit the LSM label from the MPTCP socket * @sk: the owning MPTCP socket * @ssk: the new subflow * * Update the labeling for the given MPTCP subflow, to match the one of the * owning MPTCP socket. This hook has to be called after the socket creation and * initialization via the security_socket_create() and * security_socket_post_create() LSM hooks. * * Return: Returns 0 on success or a negative error code on failure. */ int security_mptcp_add_subflow(struct sock *sk, struct sock *ssk) { return call_int_hook(mptcp_add_subflow, sk, ssk); } #endif /* CONFIG_SECURITY_NETWORK */ #ifdef CONFIG_SECURITY_INFINIBAND /** * security_ib_pkey_access() - Check if access to an IB pkey is allowed * @sec: LSM blob * @subnet_prefix: subnet prefix of the port * @pkey: IB pkey * * Check permission to access a pkey when modifying a QP. * * Return: Returns 0 if permission is granted. */ int security_ib_pkey_access(void *sec, u64 subnet_prefix, u16 pkey) { return call_int_hook(ib_pkey_access, sec, subnet_prefix, pkey); } EXPORT_SYMBOL(security_ib_pkey_access); /** * security_ib_endport_manage_subnet() - Check if SMPs traffic is allowed * @sec: LSM blob * @dev_name: IB device name * @port_num: port number * * Check permissions to send and receive SMPs on a end port. * * Return: Returns 0 if permission is granted. */ int security_ib_endport_manage_subnet(void *sec, const char *dev_name, u8 port_num) { return call_int_hook(ib_endport_manage_subnet, sec, dev_name, port_num); } EXPORT_SYMBOL(security_ib_endport_manage_subnet); /** * security_ib_alloc_security() - Allocate an Infiniband LSM blob * @sec: LSM blob * * Allocate a security structure for Infiniband objects. * * Return: Returns 0 on success, non-zero on failure. */ int security_ib_alloc_security(void **sec) { int rc; rc = lsm_blob_alloc(sec, blob_sizes.lbs_ib, GFP_KERNEL); if (rc) return rc; rc = call_int_hook(ib_alloc_security, *sec); if (rc) { kfree(*sec); *sec = NULL; } return rc; } EXPORT_SYMBOL(security_ib_alloc_security); /** * security_ib_free_security() - Free an Infiniband LSM blob * @sec: LSM blob * * Deallocate an Infiniband security structure. */ void security_ib_free_security(void *sec) { kfree(sec); } EXPORT_SYMBOL(security_ib_free_security); #endif /* CONFIG_SECURITY_INFINIBAND */ #ifdef CONFIG_SECURITY_NETWORK_XFRM /** * security_xfrm_policy_alloc() - Allocate a xfrm policy LSM blob * @ctxp: xfrm security context being added to the SPD * @sec_ctx: security label provided by userspace * @gfp: gfp flags * * Allocate a security structure to the xp->security field; the security field * is initialized to NULL when the xfrm_policy is allocated. * * Return: Return 0 if operation was successful. */ int security_xfrm_policy_alloc(struct xfrm_sec_ctx **ctxp, struct xfrm_user_sec_ctx *sec_ctx, gfp_t gfp) { return call_int_hook(xfrm_policy_alloc_security, ctxp, sec_ctx, gfp); } EXPORT_SYMBOL(security_xfrm_policy_alloc); /** * security_xfrm_policy_clone() - Clone xfrm policy LSM state * @old_ctx: xfrm security context * @new_ctxp: target xfrm security context * * Allocate a security structure in new_ctxp that contains the information from * the old_ctx structure. * * Return: Return 0 if operation was successful. */ int security_xfrm_policy_clone(struct xfrm_sec_ctx *old_ctx, struct xfrm_sec_ctx **new_ctxp) { return call_int_hook(xfrm_policy_clone_security, old_ctx, new_ctxp); } /** * security_xfrm_policy_free() - Free a xfrm security context * @ctx: xfrm security context * * Free LSM resources associated with @ctx. */ void security_xfrm_policy_free(struct xfrm_sec_ctx *ctx) { call_void_hook(xfrm_policy_free_security, ctx); } EXPORT_SYMBOL(security_xfrm_policy_free); /** * security_xfrm_policy_delete() - Check if deleting a xfrm policy is allowed * @ctx: xfrm security context * * Authorize deletion of a SPD entry. * * Return: Returns 0 if permission is granted. */ int security_xfrm_policy_delete(struct xfrm_sec_ctx *ctx) { return call_int_hook(xfrm_policy_delete_security, ctx); } /** * security_xfrm_state_alloc() - Allocate a xfrm state LSM blob * @x: xfrm state being added to the SAD * @sec_ctx: security label provided by userspace * * Allocate a security structure to the @x->security field; the security field * is initialized to NULL when the xfrm_state is allocated. Set the context to * correspond to @sec_ctx. * * Return: Return 0 if operation was successful. */ int security_xfrm_state_alloc(struct xfrm_state *x, struct xfrm_user_sec_ctx *sec_ctx) { return call_int_hook(xfrm_state_alloc, x, sec_ctx); } EXPORT_SYMBOL(security_xfrm_state_alloc); /** * security_xfrm_state_alloc_acquire() - Allocate a xfrm state LSM blob * @x: xfrm state being added to the SAD * @polsec: associated policy's security context * @secid: secid from the flow * * Allocate a security structure to the x->security field; the security field * is initialized to NULL when the xfrm_state is allocated. Set the context to * correspond to secid. * * Return: Returns 0 if operation was successful. */ int security_xfrm_state_alloc_acquire(struct xfrm_state *x, struct xfrm_sec_ctx *polsec, u32 secid) { return call_int_hook(xfrm_state_alloc_acquire, x, polsec, secid); } /** * security_xfrm_state_delete() - Check if deleting a xfrm state is allowed * @x: xfrm state * * Authorize deletion of x->security. * * Return: Returns 0 if permission is granted. */ int security_xfrm_state_delete(struct xfrm_state *x) { return call_int_hook(xfrm_state_delete_security, x); } EXPORT_SYMBOL(security_xfrm_state_delete); /** * security_xfrm_state_free() - Free a xfrm state * @x: xfrm state * * Deallocate x->security. */ void security_xfrm_state_free(struct xfrm_state *x) { call_void_hook(xfrm_state_free_security, x); } /** * security_xfrm_policy_lookup() - Check if using a xfrm policy is allowed * @ctx: target xfrm security context * @fl_secid: flow secid used to authorize access * * Check permission when a flow selects a xfrm_policy for processing XFRMs on a * packet. The hook is called when selecting either a per-socket policy or a * generic xfrm policy. * * Return: Return 0 if permission is granted, -ESRCH otherwise, or -errno on * other errors. */ int security_xfrm_policy_lookup(struct xfrm_sec_ctx *ctx, u32 fl_secid) { return call_int_hook(xfrm_policy_lookup, ctx, fl_secid); } /** * security_xfrm_state_pol_flow_match() - Check for a xfrm match * @x: xfrm state to match * @xp: xfrm policy to check for a match * @flic: flow to check for a match. * * Check @xp and @flic for a match with @x. * * Return: Returns 1 if there is a match. */ int security_xfrm_state_pol_flow_match(struct xfrm_state *x, struct xfrm_policy *xp, const struct flowi_common *flic) { struct lsm_static_call *scall; int rc = LSM_RET_DEFAULT(xfrm_state_pol_flow_match); /* * Since this function is expected to return 0 or 1, the judgment * becomes difficult if multiple LSMs supply this call. Fortunately, * we can use the first LSM's judgment because currently only SELinux * supplies this call. * * For speed optimization, we explicitly break the loop rather than * using the macro */ lsm_for_each_hook(scall, xfrm_state_pol_flow_match) { rc = scall->hl->hook.xfrm_state_pol_flow_match(x, xp, flic); break; } return rc; } /** * security_xfrm_decode_session() - Determine the xfrm secid for a packet * @skb: xfrm packet * @secid: secid * * Decode the packet in @skb and return the security label in @secid. * * Return: Return 0 if all xfrms used have the same secid. */ int security_xfrm_decode_session(struct sk_buff *skb, u32 *secid) { return call_int_hook(xfrm_decode_session, skb, secid, 1); } void security_skb_classify_flow(struct sk_buff *skb, struct flowi_common *flic) { int rc = call_int_hook(xfrm_decode_session, skb, &flic->flowic_secid, 0); BUG_ON(rc); } EXPORT_SYMBOL(security_skb_classify_flow); #endif /* CONFIG_SECURITY_NETWORK_XFRM */ #ifdef CONFIG_KEYS /** * security_key_alloc() - Allocate and initialize a kernel key LSM blob * @key: key * @cred: credentials * @flags: allocation flags * * Permit allocation of a key and assign security data. Note that key does not * have a serial number assigned at this point. * * Return: Return 0 if permission is granted, -ve error otherwise. */ int security_key_alloc(struct key *key, const struct cred *cred, unsigned long flags) { int rc = lsm_key_alloc(key); if (unlikely(rc)) return rc; rc = call_int_hook(key_alloc, key, cred, flags); if (unlikely(rc)) security_key_free(key); return rc; } /** * security_key_free() - Free a kernel key LSM blob * @key: key * * Notification of destruction; free security data. */ void security_key_free(struct key *key) { kfree(key->security); key->security = NULL; } /** * security_key_permission() - Check if a kernel key operation is allowed * @key_ref: key reference * @cred: credentials of actor requesting access * @need_perm: requested permissions * * See whether a specific operational right is granted to a process on a key. * * Return: Return 0 if permission is granted, -ve error otherwise. */ int security_key_permission(key_ref_t key_ref, const struct cred *cred, enum key_need_perm need_perm) { return call_int_hook(key_permission, key_ref, cred, need_perm); } /** * security_key_getsecurity() - Get the key's security label * @key: key * @buffer: security label buffer * * Get a textual representation of the security context attached to a key for * the purposes of honouring KEYCTL_GETSECURITY. This function allocates the * storage for the NUL-terminated string and the caller should free it. * * Return: Returns the length of @buffer (including terminating NUL) or -ve if * an error occurs. May also return 0 (and a NULL buffer pointer) if * there is no security label assigned to the key. */ int security_key_getsecurity(struct key *key, char **buffer) { *buffer = NULL; return call_int_hook(key_getsecurity, key, buffer); } /** * security_key_post_create_or_update() - Notification of key create or update * @keyring: keyring to which the key is linked to * @key: created or updated key * @payload: data used to instantiate or update the key * @payload_len: length of payload * @flags: key flags * @create: flag indicating whether the key was created or updated * * Notify the caller of a key creation or update. */ void security_key_post_create_or_update(struct key *keyring, struct key *key, const void *payload, size_t payload_len, unsigned long flags, bool create) { call_void_hook(key_post_create_or_update, keyring, key, payload, payload_len, flags, create); } #endif /* CONFIG_KEYS */ #ifdef CONFIG_AUDIT /** * security_audit_rule_init() - Allocate and init an LSM audit rule struct * @field: audit action * @op: rule operator * @rulestr: rule context * @lsmrule: receive buffer for audit rule struct * @gfp: GFP flag used for kmalloc * * Allocate and initialize an LSM audit rule structure. * * Return: Return 0 if @lsmrule has been successfully set, -EINVAL in case of * an invalid rule. */ int security_audit_rule_init(u32 field, u32 op, char *rulestr, void **lsmrule, gfp_t gfp) { return call_int_hook(audit_rule_init, field, op, rulestr, lsmrule, gfp); } /** * security_audit_rule_known() - Check if an audit rule contains LSM fields * @krule: audit rule * * Specifies whether given @krule contains any fields related to the current * LSM. * * Return: Returns 1 in case of relation found, 0 otherwise. */ int security_audit_rule_known(struct audit_krule *krule) { return call_int_hook(audit_rule_known, krule); } /** * security_audit_rule_free() - Free an LSM audit rule struct * @lsmrule: audit rule struct * * Deallocate the LSM audit rule structure previously allocated by * audit_rule_init(). */ void security_audit_rule_free(void *lsmrule) { call_void_hook(audit_rule_free, lsmrule); } /** * security_audit_rule_match() - Check if a label matches an audit rule * @prop: security label * @field: LSM audit field * @op: matching operator * @lsmrule: audit rule * * Determine if given @secid matches a rule previously approved by * security_audit_rule_known(). * * Return: Returns 1 if secid matches the rule, 0 if it does not, -ERRNO on * failure. */ int security_audit_rule_match(struct lsm_prop *prop, u32 field, u32 op, void *lsmrule) { return call_int_hook(audit_rule_match, prop, field, op, lsmrule); } #endif /* CONFIG_AUDIT */ #ifdef CONFIG_BPF_SYSCALL /** * security_bpf() - Check if the bpf syscall operation is allowed * @cmd: command * @attr: bpf attribute * @size: size * * Do a initial check for all bpf syscalls after the attribute is copied into * the kernel. The actual security module can implement their own rules to * check the specific cmd they need. * * Return: Returns 0 if permission is granted. */ int security_bpf(int cmd, union bpf_attr *attr, unsigned int size) { return call_int_hook(bpf, cmd, attr, size); } /** * security_bpf_map() - Check if access to a bpf map is allowed * @map: bpf map * @fmode: mode * * Do a check when the kernel generates and returns a file descriptor for eBPF * maps. * * Return: Returns 0 if permission is granted. */ int security_bpf_map(struct bpf_map *map, fmode_t fmode) { return call_int_hook(bpf_map, map, fmode); } /** * security_bpf_prog() - Check if access to a bpf program is allowed * @prog: bpf program * * Do a check when the kernel generates and returns a file descriptor for eBPF * programs. * * Return: Returns 0 if permission is granted. */ int security_bpf_prog(struct bpf_prog *prog) { return call_int_hook(bpf_prog, prog); } /** * security_bpf_map_create() - Check if BPF map creation is allowed * @map: BPF map object * @attr: BPF syscall attributes used to create BPF map * @token: BPF token used to grant user access * * Do a check when the kernel creates a new BPF map. This is also the * point where LSM blob is allocated for LSMs that need them. * * Return: Returns 0 on success, error on failure. */ int security_bpf_map_create(struct bpf_map *map, union bpf_attr *attr, struct bpf_token *token) { return call_int_hook(bpf_map_create, map, attr, token); } /** * security_bpf_prog_load() - Check if loading of BPF program is allowed * @prog: BPF program object * @attr: BPF syscall attributes used to create BPF program * @token: BPF token used to grant user access to BPF subsystem * * Perform an access control check when the kernel loads a BPF program and * allocates associated BPF program object. This hook is also responsible for * allocating any required LSM state for the BPF program. * * Return: Returns 0 on success, error on failure. */ int security_bpf_prog_load(struct bpf_prog *prog, union bpf_attr *attr, struct bpf_token *token) { return call_int_hook(bpf_prog_load, prog, attr, token); } /** * security_bpf_token_create() - Check if creating of BPF token is allowed * @token: BPF token object * @attr: BPF syscall attributes used to create BPF token * @path: path pointing to BPF FS mount point from which BPF token is created * * Do a check when the kernel instantiates a new BPF token object from BPF FS * instance. This is also the point where LSM blob can be allocated for LSMs. * * Return: Returns 0 on success, error on failure. */ int security_bpf_token_create(struct bpf_token *token, union bpf_attr *attr, const struct path *path) { return call_int_hook(bpf_token_create, token, attr, path); } /** * security_bpf_token_cmd() - Check if BPF token is allowed to delegate * requested BPF syscall command * @token: BPF token object * @cmd: BPF syscall command requested to be delegated by BPF token * * Do a check when the kernel decides whether provided BPF token should allow * delegation of requested BPF syscall command. * * Return: Returns 0 on success, error on failure. */ int security_bpf_token_cmd(const struct bpf_token *token, enum bpf_cmd cmd) { return call_int_hook(bpf_token_cmd, token, cmd); } /** * security_bpf_token_capable() - Check if BPF token is allowed to delegate * requested BPF-related capability * @token: BPF token object * @cap: capabilities requested to be delegated by BPF token * * Do a check when the kernel decides whether provided BPF token should allow * delegation of requested BPF-related capabilities. * * Return: Returns 0 on success, error on failure. */ int security_bpf_token_capable(const struct bpf_token *token, int cap) { return call_int_hook(bpf_token_capable, token, cap); } /** * security_bpf_map_free() - Free a bpf map's LSM blob * @map: bpf map * * Clean up the security information stored inside bpf map. */ void security_bpf_map_free(struct bpf_map *map) { call_void_hook(bpf_map_free, map); } /** * security_bpf_prog_free() - Free a BPF program's LSM blob * @prog: BPF program struct * * Clean up the security information stored inside BPF program. */ void security_bpf_prog_free(struct bpf_prog *prog) { call_void_hook(bpf_prog_free, prog); } /** * security_bpf_token_free() - Free a BPF token's LSM blob * @token: BPF token struct * * Clean up the security information stored inside BPF token. */ void security_bpf_token_free(struct bpf_token *token) { call_void_hook(bpf_token_free, token); } #endif /* CONFIG_BPF_SYSCALL */ /** * security_locked_down() - Check if a kernel feature is allowed * @what: requested kernel feature * * Determine whether a kernel feature that potentially enables arbitrary code * execution in kernel space should be permitted. * * Return: Returns 0 if permission is granted. */ int security_locked_down(enum lockdown_reason what) { return call_int_hook(locked_down, what); } EXPORT_SYMBOL(security_locked_down); /** * security_bdev_alloc() - Allocate a block device LSM blob * @bdev: block device * * Allocate and attach a security structure to @bdev->bd_security. The * security field is initialized to NULL when the bdev structure is * allocated. * * Return: Return 0 if operation was successful. */ int security_bdev_alloc(struct block_device *bdev) { int rc = 0; rc = lsm_bdev_alloc(bdev); if (unlikely(rc)) return rc; rc = call_int_hook(bdev_alloc_security, bdev); if (unlikely(rc)) security_bdev_free(bdev); return rc; } EXPORT_SYMBOL(security_bdev_alloc); /** * security_bdev_free() - Free a block device's LSM blob * @bdev: block device * * Deallocate the bdev security structure and set @bdev->bd_security to NULL. */ void security_bdev_free(struct block_device *bdev) { if (!bdev->bd_security) return; call_void_hook(bdev_free_security, bdev); kfree(bdev->bd_security); bdev->bd_security = NULL; } EXPORT_SYMBOL(security_bdev_free); /** * security_bdev_setintegrity() - Set the device's integrity data * @bdev: block device * @type: type of integrity, e.g. hash digest, signature, etc * @value: the integrity value * @size: size of the integrity value * * Register a verified integrity measurement of a bdev with LSMs. * LSMs should free the previously saved data if @value is NULL. * Please note that the new hook should be invoked every time the security * information is updated to keep these data current. For example, in dm-verity, * if the mapping table is reloaded and configured to use a different dm-verity * target with a new roothash and signing information, the previously stored * data in the LSM blob will become obsolete. It is crucial to re-invoke the * hook to refresh these data and ensure they are up to date. This necessity * arises from the design of device-mapper, where a device-mapper device is * first created, and then targets are subsequently loaded into it. These * targets can be modified multiple times during the device's lifetime. * Therefore, while the LSM blob is allocated during the creation of the block * device, its actual contents are not initialized at this stage and can change * substantially over time. This includes alterations from data that the LSMs * 'trusts' to those they do not, making it essential to handle these changes * correctly. Failure to address this dynamic aspect could potentially allow * for bypassing LSM checks. * * Return: Returns 0 on success, negative values on failure. */ int security_bdev_setintegrity(struct block_device *bdev, enum lsm_integrity_type type, const void *value, size_t size) { return call_int_hook(bdev_setintegrity, bdev, type, value, size); } EXPORT_SYMBOL(security_bdev_setintegrity); #ifdef CONFIG_PERF_EVENTS /** * security_perf_event_open() - Check if a perf event open is allowed * @attr: perf event attribute * @type: type of event * * Check whether the @type of perf_event_open syscall is allowed. * * Return: Returns 0 if permission is granted. */ int security_perf_event_open(struct perf_event_attr *attr, int type) { return call_int_hook(perf_event_open, attr, type); } /** * security_perf_event_alloc() - Allocate a perf event LSM blob * @event: perf event * * Allocate and save perf_event security info. * * Return: Returns 0 on success, error on failure. */ int security_perf_event_alloc(struct perf_event *event) { int rc; rc = lsm_blob_alloc(&event->security, blob_sizes.lbs_perf_event, GFP_KERNEL); if (rc) return rc; rc = call_int_hook(perf_event_alloc, event); if (rc) { kfree(event->security); event->security = NULL; } return rc; } /** * security_perf_event_free() - Free a perf event LSM blob * @event: perf event * * Release (free) perf_event security info. */ void security_perf_event_free(struct perf_event *event) { kfree(event->security); event->security = NULL; } /** * security_perf_event_read() - Check if reading a perf event label is allowed * @event: perf event * * Read perf_event security info if allowed. * * Return: Returns 0 if permission is granted. */ int security_perf_event_read(struct perf_event *event) { return call_int_hook(perf_event_read, event); } /** * security_perf_event_write() - Check if writing a perf event label is allowed * @event: perf event * * Write perf_event security info if allowed. * * Return: Returns 0 if permission is granted. */ int security_perf_event_write(struct perf_event *event) { return call_int_hook(perf_event_write, event); } #endif /* CONFIG_PERF_EVENTS */ #ifdef CONFIG_IO_URING /** * security_uring_override_creds() - Check if overriding creds is allowed * @new: new credentials * * Check if the current task, executing an io_uring operation, is allowed to * override it's credentials with @new. * * Return: Returns 0 if permission is granted. */ int security_uring_override_creds(const struct cred *new) { return call_int_hook(uring_override_creds, new); } /** * security_uring_sqpoll() - Check if IORING_SETUP_SQPOLL is allowed * * Check whether the current task is allowed to spawn a io_uring polling thread * (IORING_SETUP_SQPOLL). * * Return: Returns 0 if permission is granted. */ int security_uring_sqpoll(void) { return call_int_hook(uring_sqpoll); } /** * security_uring_cmd() - Check if a io_uring passthrough command is allowed * @ioucmd: command * * Check whether the file_operations uring_cmd is allowed to run. * * Return: Returns 0 if permission is granted. */ int security_uring_cmd(struct io_uring_cmd *ioucmd) { return call_int_hook(uring_cmd, ioucmd); } #endif /* CONFIG_IO_URING */ /** * security_initramfs_populated() - Notify LSMs that initramfs has been loaded * * Tells the LSMs the initramfs has been unpacked into the rootfs. */ void security_initramfs_populated(void) { call_void_hook(initramfs_populated); } |
| 390 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 | /* SPDX-License-Identifier: GPL-2.0 */ #undef TRACE_SYSTEM #define TRACE_SYSTEM kmem #if !defined(_TRACE_KMEM_H) || defined(TRACE_HEADER_MULTI_READ) #define _TRACE_KMEM_H #include <linux/types.h> #include <linux/tracepoint.h> #include <trace/events/mmflags.h> TRACE_EVENT(kmem_cache_alloc, TP_PROTO(unsigned long call_site, const void *ptr, struct kmem_cache *s, gfp_t gfp_flags, int node), TP_ARGS(call_site, ptr, s, gfp_flags, node), TP_STRUCT__entry( __field( unsigned long, call_site ) __field( const void *, ptr ) __field( size_t, bytes_req ) __field( size_t, bytes_alloc ) __field( unsigned long, gfp_flags ) __field( int, node ) __field( bool, accounted ) ), TP_fast_assign( __entry->call_site = call_site; __entry->ptr = ptr; __entry->bytes_req = s->object_size; __entry->bytes_alloc = s->size; __entry->gfp_flags = (__force unsigned long)gfp_flags; __entry->node = node; __entry->accounted = IS_ENABLED(CONFIG_MEMCG) ? ((gfp_flags & __GFP_ACCOUNT) || (s->flags & SLAB_ACCOUNT)) : false; ), TP_printk("call_site=%pS ptr=%p bytes_req=%zu bytes_alloc=%zu gfp_flags=%s node=%d accounted=%s", (void *)__entry->call_site, __entry->ptr, __entry->bytes_req, __entry->bytes_alloc, show_gfp_flags(__entry->gfp_flags), __entry->node, __entry->accounted ? "true" : "false") ); TRACE_EVENT(kmalloc, TP_PROTO(unsigned long call_site, const void *ptr, size_t bytes_req, size_t bytes_alloc, gfp_t gfp_flags, int node), TP_ARGS(call_site, ptr, bytes_req, bytes_alloc, gfp_flags, node), TP_STRUCT__entry( __field( unsigned long, call_site ) __field( const void *, ptr ) __field( size_t, bytes_req ) __field( size_t, bytes_alloc ) __field( unsigned long, gfp_flags ) __field( int, node ) ), TP_fast_assign( __entry->call_site = call_site; __entry->ptr = ptr; __entry->bytes_req = bytes_req; __entry->bytes_alloc = bytes_alloc; __entry->gfp_flags = (__force unsigned long)gfp_flags; __entry->node = node; ), TP_printk("call_site=%pS ptr=%p bytes_req=%zu bytes_alloc=%zu gfp_flags=%s node=%d accounted=%s", (void *)__entry->call_site, __entry->ptr, __entry->bytes_req, __entry->bytes_alloc, show_gfp_flags(__entry->gfp_flags), __entry->node, (IS_ENABLED(CONFIG_MEMCG) && (__entry->gfp_flags & (__force unsigned long)__GFP_ACCOUNT)) ? "true" : "false") ); TRACE_EVENT(kfree, TP_PROTO(unsigned long call_site, const void *ptr), TP_ARGS(call_site, ptr), TP_STRUCT__entry( __field( unsigned long, call_site ) __field( const void *, ptr ) ), TP_fast_assign( __entry->call_site = call_site; __entry->ptr = ptr; ), TP_printk("call_site=%pS ptr=%p", (void *)__entry->call_site, __entry->ptr) ); TRACE_EVENT(kmem_cache_free, TP_PROTO(unsigned long call_site, const void *ptr, const struct kmem_cache *s), TP_ARGS(call_site, ptr, s), TP_STRUCT__entry( __field( unsigned long, call_site ) __field( const void *, ptr ) __string( name, s->name ) ), TP_fast_assign( __entry->call_site = call_site; __entry->ptr = ptr; __assign_str(name); ), TP_printk("call_site=%pS ptr=%p name=%s", (void *)__entry->call_site, __entry->ptr, __get_str(name)) ); TRACE_EVENT(mm_page_free, TP_PROTO(struct page *page, unsigned int order), TP_ARGS(page, order), TP_STRUCT__entry( __field( unsigned long, pfn ) __field( unsigned int, order ) ), TP_fast_assign( __entry->pfn = page_to_pfn(page); __entry->order = order; ), TP_printk("page=%p pfn=0x%lx order=%d", pfn_to_page(__entry->pfn), __entry->pfn, __entry->order) ); TRACE_EVENT(mm_page_free_batched, TP_PROTO(struct page *page), TP_ARGS(page), TP_STRUCT__entry( __field( unsigned long, pfn ) ), TP_fast_assign( __entry->pfn = page_to_pfn(page); ), TP_printk("page=%p pfn=0x%lx order=0", pfn_to_page(__entry->pfn), __entry->pfn) ); TRACE_EVENT(mm_page_alloc, TP_PROTO(struct page *page, unsigned int order, gfp_t gfp_flags, int migratetype), TP_ARGS(page, order, gfp_flags, migratetype), TP_STRUCT__entry( __field( unsigned long, pfn ) __field( unsigned int, order ) __field( unsigned long, gfp_flags ) __field( int, migratetype ) ), TP_fast_assign( __entry->pfn = page ? page_to_pfn(page) : -1UL; __entry->order = order; __entry->gfp_flags = (__force unsigned long)gfp_flags; __entry->migratetype = migratetype; ), TP_printk("page=%p pfn=0x%lx order=%d migratetype=%d gfp_flags=%s", __entry->pfn != -1UL ? pfn_to_page(__entry->pfn) : NULL, __entry->pfn != -1UL ? __entry->pfn : 0, __entry->order, __entry->migratetype, show_gfp_flags(__entry->gfp_flags)) ); DECLARE_EVENT_CLASS(mm_page, TP_PROTO(struct page *page, unsigned int order, int migratetype, int percpu_refill), TP_ARGS(page, order, migratetype, percpu_refill), TP_STRUCT__entry( __field( unsigned long, pfn ) __field( unsigned int, order ) __field( int, migratetype ) __field( int, percpu_refill ) ), TP_fast_assign( __entry->pfn = page ? page_to_pfn(page) : -1UL; __entry->order = order; __entry->migratetype = migratetype; __entry->percpu_refill = percpu_refill; ), TP_printk("page=%p pfn=0x%lx order=%u migratetype=%d percpu_refill=%d", __entry->pfn != -1UL ? pfn_to_page(__entry->pfn) : NULL, __entry->pfn != -1UL ? __entry->pfn : 0, __entry->order, __entry->migratetype, __entry->percpu_refill) ); DEFINE_EVENT(mm_page, mm_page_alloc_zone_locked, TP_PROTO(struct page *page, unsigned int order, int migratetype, int percpu_refill), TP_ARGS(page, order, migratetype, percpu_refill) ); TRACE_EVENT(mm_page_pcpu_drain, TP_PROTO(struct page *page, unsigned int order, int migratetype), TP_ARGS(page, order, migratetype), TP_STRUCT__entry( __field( unsigned long, pfn ) __field( unsigned int, order ) __field( int, migratetype ) ), TP_fast_assign( __entry->pfn = page ? page_to_pfn(page) : -1UL; __entry->order = order; __entry->migratetype = migratetype; ), TP_printk("page=%p pfn=0x%lx order=%d migratetype=%d", pfn_to_page(__entry->pfn), __entry->pfn, __entry->order, __entry->migratetype) ); TRACE_EVENT(mm_page_alloc_extfrag, TP_PROTO(struct page *page, int alloc_order, int fallback_order, int alloc_migratetype, int fallback_migratetype), TP_ARGS(page, alloc_order, fallback_order, alloc_migratetype, fallback_migratetype), TP_STRUCT__entry( __field( unsigned long, pfn ) __field( int, alloc_order ) __field( int, fallback_order ) __field( int, alloc_migratetype ) __field( int, fallback_migratetype ) __field( int, change_ownership ) ), TP_fast_assign( __entry->pfn = page_to_pfn(page); __entry->alloc_order = alloc_order; __entry->fallback_order = fallback_order; __entry->alloc_migratetype = alloc_migratetype; __entry->fallback_migratetype = fallback_migratetype; __entry->change_ownership = (alloc_migratetype == get_pageblock_migratetype(page)); ), TP_printk("page=%p pfn=0x%lx alloc_order=%d fallback_order=%d pageblock_order=%d alloc_migratetype=%d fallback_migratetype=%d fragmenting=%d change_ownership=%d", pfn_to_page(__entry->pfn), __entry->pfn, __entry->alloc_order, __entry->fallback_order, pageblock_order, __entry->alloc_migratetype, __entry->fallback_migratetype, __entry->fallback_order < pageblock_order, __entry->change_ownership) ); TRACE_EVENT(mm_alloc_contig_migrate_range_info, TP_PROTO(unsigned long start, unsigned long end, unsigned long nr_migrated, unsigned long nr_reclaimed, unsigned long nr_mapped, int migratetype), TP_ARGS(start, end, nr_migrated, nr_reclaimed, nr_mapped, migratetype), TP_STRUCT__entry( __field(unsigned long, start) __field(unsigned long, end) __field(unsigned long, nr_migrated) __field(unsigned long, nr_reclaimed) __field(unsigned long, nr_mapped) __field(int, migratetype) ), TP_fast_assign( __entry->start = start; __entry->end = end; __entry->nr_migrated = nr_migrated; __entry->nr_reclaimed = nr_reclaimed; __entry->nr_mapped = nr_mapped; __entry->migratetype = migratetype; ), TP_printk("start=0x%lx end=0x%lx migratetype=%d nr_migrated=%lu nr_reclaimed=%lu nr_mapped=%lu", __entry->start, __entry->end, __entry->migratetype, __entry->nr_migrated, __entry->nr_reclaimed, __entry->nr_mapped) ); /* * Required for uniquely and securely identifying mm in rss_stat tracepoint. */ #ifndef __PTR_TO_HASHVAL static unsigned int __maybe_unused mm_ptr_to_hash(const void *ptr) { int ret; unsigned long hashval; ret = ptr_to_hashval(ptr, &hashval); if (ret) return 0; /* The hashed value is only 32-bit */ return (unsigned int)hashval; } #define __PTR_TO_HASHVAL #endif #define TRACE_MM_PAGES \ EM(MM_FILEPAGES) \ EM(MM_ANONPAGES) \ EM(MM_SWAPENTS) \ EMe(MM_SHMEMPAGES) #undef EM #undef EMe #define EM(a) TRACE_DEFINE_ENUM(a); #define EMe(a) TRACE_DEFINE_ENUM(a); TRACE_MM_PAGES #undef EM #undef EMe #define EM(a) { a, #a }, #define EMe(a) { a, #a } TRACE_EVENT(rss_stat, TP_PROTO(struct mm_struct *mm, int member), TP_ARGS(mm, member), TP_STRUCT__entry( __field(unsigned int, mm_id) __field(unsigned int, curr) __field(int, member) __field(long, size) ), TP_fast_assign( __entry->mm_id = mm_ptr_to_hash(mm); __entry->curr = !!(current->mm == mm); __entry->member = member; __entry->size = (percpu_counter_sum_positive(&mm->rss_stat[member]) << PAGE_SHIFT); ), TP_printk("mm_id=%u curr=%d type=%s size=%ldB", __entry->mm_id, __entry->curr, __print_symbolic(__entry->member, TRACE_MM_PAGES), __entry->size) ); #endif /* _TRACE_KMEM_H */ /* This part must be outside protection */ #include <trace/define_trace.h> |
| 2 2 2 51 51 55 54 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 | // SPDX-License-Identifier: GPL-2.0-only /* * Copyright (C) 2017 ARM Ltd. * Author: Marc Zyngier <marc.zyngier@arm.com> */ #include <linux/interrupt.h> #include <linux/irq.h> #include <linux/irqdomain.h> #include <linux/kvm_host.h> #include <linux/irqchip/arm-gic-v3.h> #include "vgic.h" /* * How KVM uses GICv4 (insert rude comments here): * * The vgic-v4 layer acts as a bridge between several entities: * - The GICv4 ITS representation offered by the ITS driver * - VFIO, which is in charge of the PCI endpoint * - The virtual ITS, which is the only thing the guest sees * * The configuration of VLPIs is triggered by a callback from VFIO, * instructing KVM that a PCI device has been configured to deliver * MSIs to a vITS. * * kvm_vgic_v4_set_forwarding() is thus called with the routing entry, * and this is used to find the corresponding vITS data structures * (ITS instance, device, event and irq) using a process that is * extremely similar to the injection of an MSI. * * At this stage, we can link the guest's view of an LPI (uniquely * identified by the routing entry) and the host irq, using the GICv4 * driver mapping operation. Should the mapping succeed, we've then * successfully upgraded the guest's LPI to a VLPI. We can then start * with updating GICv4's view of the property table and generating an * INValidation in order to kickstart the delivery of this VLPI to the * guest directly, without software intervention. Well, almost. * * When the PCI endpoint is deconfigured, this operation is reversed * with VFIO calling kvm_vgic_v4_unset_forwarding(). * * Once the VLPI has been mapped, it needs to follow any change the * guest performs on its LPI through the vITS. For that, a number of * command handlers have hooks to communicate these changes to the HW: * - Any invalidation triggers a call to its_prop_update_vlpi() * - The INT command results in a irq_set_irqchip_state(), which * generates an INT on the corresponding VLPI. * - The CLEAR command results in a irq_set_irqchip_state(), which * generates an CLEAR on the corresponding VLPI. * - DISCARD translates into an unmap, similar to a call to * kvm_vgic_v4_unset_forwarding(). * - MOVI is translated by an update of the existing mapping, changing * the target vcpu, resulting in a VMOVI being generated. * - MOVALL is translated by a string of mapping updates (similar to * the handling of MOVI). MOVALL is horrible. * * Note that a DISCARD/MAPTI sequence emitted from the guest without * reprogramming the PCI endpoint after MAPTI does not result in a * VLPI being mapped, as there is no callback from VFIO (the guest * will get the interrupt via the normal SW injection). Fixing this is * not trivial, and requires some horrible messing with the VFIO * internals. Not fun. Don't do that. * * Then there is the scheduling. Each time a vcpu is about to run on a * physical CPU, KVM must tell the corresponding redistributor about * it. And if we've migrated our vcpu from one CPU to another, we must * tell the ITS (so that the messages reach the right redistributor). * This is done in two steps: first issue a irq_set_affinity() on the * irq corresponding to the vcpu, then call its_make_vpe_resident(). * You must be in a non-preemptible context. On exit, a call to * its_make_vpe_non_resident() tells the redistributor that we're done * with the vcpu. * * Finally, the doorbell handling: Each vcpu is allocated an interrupt * which will fire each time a VLPI is made pending whilst the vcpu is * not running. Each time the vcpu gets blocked, the doorbell * interrupt gets enabled. When the vcpu is unblocked (for whatever * reason), the doorbell interrupt is disabled. */ #define DB_IRQ_FLAGS (IRQ_NOAUTOEN | IRQ_DISABLE_UNLAZY | IRQ_NO_BALANCING) static irqreturn_t vgic_v4_doorbell_handler(int irq, void *info) { struct kvm_vcpu *vcpu = info; /* We got the message, no need to fire again */ if (!kvm_vgic_global_state.has_gicv4_1 && !irqd_irq_disabled(&irq_to_desc(irq)->irq_data)) disable_irq_nosync(irq); /* * The v4.1 doorbell can fire concurrently with the vPE being * made non-resident. Ensure we only update pending_last * *after* the non-residency sequence has completed. */ raw_spin_lock(&vcpu->arch.vgic_cpu.vgic_v3.its_vpe.vpe_lock); vcpu->arch.vgic_cpu.vgic_v3.its_vpe.pending_last = true; raw_spin_unlock(&vcpu->arch.vgic_cpu.vgic_v3.its_vpe.vpe_lock); kvm_make_request(KVM_REQ_IRQ_PENDING, vcpu); kvm_vcpu_kick(vcpu); return IRQ_HANDLED; } static void vgic_v4_sync_sgi_config(struct its_vpe *vpe, struct vgic_irq *irq) { vpe->sgi_config[irq->intid].enabled = irq->enabled; vpe->sgi_config[irq->intid].group = irq->group; vpe->sgi_config[irq->intid].priority = irq->priority; } static void vgic_v4_enable_vsgis(struct kvm_vcpu *vcpu) { struct its_vpe *vpe = &vcpu->arch.vgic_cpu.vgic_v3.its_vpe; int i; /* * With GICv4.1, every virtual SGI can be directly injected. So * let's pretend that they are HW interrupts, tied to a host * IRQ. The SGI code will do its magic. */ for (i = 0; i < VGIC_NR_SGIS; i++) { struct vgic_irq *irq = vgic_get_vcpu_irq(vcpu, i); struct irq_desc *desc; unsigned long flags; int ret; raw_spin_lock_irqsave(&irq->irq_lock, flags); if (irq->hw) goto unlock; irq->hw = true; irq->host_irq = irq_find_mapping(vpe->sgi_domain, i); /* Transfer the full irq state to the vPE */ vgic_v4_sync_sgi_config(vpe, irq); desc = irq_to_desc(irq->host_irq); ret = irq_domain_activate_irq(irq_desc_get_irq_data(desc), false); if (!WARN_ON(ret)) { /* Transfer pending state */ ret = irq_set_irqchip_state(irq->host_irq, IRQCHIP_STATE_PENDING, irq->pending_latch); WARN_ON(ret); irq->pending_latch = false; } unlock: raw_spin_unlock_irqrestore(&irq->irq_lock, flags); vgic_put_irq(vcpu->kvm, irq); } } static void vgic_v4_disable_vsgis(struct kvm_vcpu *vcpu) { int i; for (i = 0; i < VGIC_NR_SGIS; i++) { struct vgic_irq *irq = vgic_get_vcpu_irq(vcpu, i); struct irq_desc *desc; unsigned long flags; int ret; raw_spin_lock_irqsave(&irq->irq_lock, flags); if (!irq->hw) goto unlock; irq->hw = false; ret = irq_get_irqchip_state(irq->host_irq, IRQCHIP_STATE_PENDING, &irq->pending_latch); WARN_ON(ret); desc = irq_to_desc(irq->host_irq); irq_domain_deactivate_irq(irq_desc_get_irq_data(desc)); unlock: raw_spin_unlock_irqrestore(&irq->irq_lock, flags); vgic_put_irq(vcpu->kvm, irq); } } void vgic_v4_configure_vsgis(struct kvm *kvm) { struct vgic_dist *dist = &kvm->arch.vgic; struct kvm_vcpu *vcpu; unsigned long i; lockdep_assert_held(&kvm->arch.config_lock); kvm_arm_halt_guest(kvm); kvm_for_each_vcpu(i, vcpu, kvm) { if (dist->nassgireq) vgic_v4_enable_vsgis(vcpu); else vgic_v4_disable_vsgis(vcpu); } kvm_arm_resume_guest(kvm); } /* * Must be called with GICv4.1 and the vPE unmapped, which * indicates the invalidation of any VPT caches associated * with the vPE, thus we can get the VLPI state by peeking * at the VPT. */ void vgic_v4_get_vlpi_state(struct vgic_irq *irq, bool *val) { struct its_vpe *vpe = &irq->target_vcpu->arch.vgic_cpu.vgic_v3.its_vpe; int mask = BIT(irq->intid % BITS_PER_BYTE); void *va; u8 *ptr; va = page_address(vpe->vpt_page); ptr = va + irq->intid / BITS_PER_BYTE; *val = !!(*ptr & mask); } int vgic_v4_request_vpe_irq(struct kvm_vcpu *vcpu, int irq) { return request_irq(irq, vgic_v4_doorbell_handler, 0, "vcpu", vcpu); } /** * vgic_v4_init - Initialize the GICv4 data structures * @kvm: Pointer to the VM being initialized * * We may be called each time a vITS is created, or when the * vgic is initialized. In both cases, the number of vcpus * should now be fixed. */ int vgic_v4_init(struct kvm *kvm) { struct vgic_dist *dist = &kvm->arch.vgic; struct kvm_vcpu *vcpu; int nr_vcpus, ret; unsigned long i; lockdep_assert_held(&kvm->arch.config_lock); if (!kvm_vgic_global_state.has_gicv4) return 0; /* Nothing to see here... move along. */ if (dist->its_vm.vpes) return 0; nr_vcpus = atomic_read(&kvm->online_vcpus); dist->its_vm.vpes = kcalloc(nr_vcpus, sizeof(*dist->its_vm.vpes), GFP_KERNEL_ACCOUNT); if (!dist->its_vm.vpes) return -ENOMEM; dist->its_vm.nr_vpes = nr_vcpus; kvm_for_each_vcpu(i, vcpu, kvm) dist->its_vm.vpes[i] = &vcpu->arch.vgic_cpu.vgic_v3.its_vpe; ret = its_alloc_vcpu_irqs(&dist->its_vm); if (ret < 0) { kvm_err("VPE IRQ allocation failure\n"); kfree(dist->its_vm.vpes); dist->its_vm.nr_vpes = 0; dist->its_vm.vpes = NULL; return ret; } kvm_for_each_vcpu(i, vcpu, kvm) { int irq = dist->its_vm.vpes[i]->irq; unsigned long irq_flags = DB_IRQ_FLAGS; /* * Don't automatically enable the doorbell, as we're * flipping it back and forth when the vcpu gets * blocked. Also disable the lazy disabling, as the * doorbell could kick us out of the guest too * early... * * On GICv4.1, the doorbell is managed in HW and must * be left enabled. */ if (kvm_vgic_global_state.has_gicv4_1) irq_flags &= ~IRQ_NOAUTOEN; irq_set_status_flags(irq, irq_flags); ret = vgic_v4_request_vpe_irq(vcpu, irq); if (ret) { kvm_err("failed to allocate vcpu IRQ%d\n", irq); /* * Trick: adjust the number of vpes so we know * how many to nuke on teardown... */ dist->its_vm.nr_vpes = i; break; } } if (ret) vgic_v4_teardown(kvm); return ret; } /** * vgic_v4_teardown - Free the GICv4 data structures * @kvm: Pointer to the VM being destroyed */ void vgic_v4_teardown(struct kvm *kvm) { struct its_vm *its_vm = &kvm->arch.vgic.its_vm; int i; lockdep_assert_held(&kvm->arch.config_lock); if (!its_vm->vpes) return; for (i = 0; i < its_vm->nr_vpes; i++) { struct kvm_vcpu *vcpu = kvm_get_vcpu(kvm, i); int irq = its_vm->vpes[i]->irq; irq_clear_status_flags(irq, DB_IRQ_FLAGS); free_irq(irq, vcpu); } its_free_vcpu_irqs(its_vm); kfree(its_vm->vpes); its_vm->nr_vpes = 0; its_vm->vpes = NULL; } int vgic_v4_put(struct kvm_vcpu *vcpu) { struct its_vpe *vpe = &vcpu->arch.vgic_cpu.vgic_v3.its_vpe; if (!vgic_supports_direct_msis(vcpu->kvm) || !vpe->resident) return 0; return its_make_vpe_non_resident(vpe, !!vcpu_get_flag(vcpu, IN_WFI)); } int vgic_v4_load(struct kvm_vcpu *vcpu) { struct its_vpe *vpe = &vcpu->arch.vgic_cpu.vgic_v3.its_vpe; int err; if (!vgic_supports_direct_msis(vcpu->kvm) || vpe->resident) return 0; if (vcpu_get_flag(vcpu, IN_WFI)) return 0; /* * Before making the VPE resident, make sure the redistributor * corresponding to our current CPU expects us here. See the * doc in drivers/irqchip/irq-gic-v4.c to understand how this * turns into a VMOVP command at the ITS level. */ err = irq_set_affinity(vpe->irq, cpumask_of(smp_processor_id())); if (err) return err; err = its_make_vpe_resident(vpe, false, vcpu->kvm->arch.vgic.enabled); if (err) return err; /* * Now that the VPE is resident, let's get rid of a potential * doorbell interrupt that would still be pending. This is a * GICv4.0 only "feature"... */ if (!kvm_vgic_global_state.has_gicv4_1) err = irq_set_irqchip_state(vpe->irq, IRQCHIP_STATE_PENDING, false); return err; } void vgic_v4_commit(struct kvm_vcpu *vcpu) { struct its_vpe *vpe = &vcpu->arch.vgic_cpu.vgic_v3.its_vpe; /* * No need to wait for the vPE to be ready across a shallow guest * exit, as only a vcpu_put will invalidate it. */ if (!vpe->ready) its_commit_vpe(vpe); } static struct vgic_its *vgic_get_its(struct kvm *kvm, struct kvm_kernel_irq_routing_entry *irq_entry) { struct kvm_msi msi = (struct kvm_msi) { .address_lo = irq_entry->msi.address_lo, .address_hi = irq_entry->msi.address_hi, .data = irq_entry->msi.data, .flags = irq_entry->msi.flags, .devid = irq_entry->msi.devid, }; return vgic_msi_to_its(kvm, &msi); } int kvm_vgic_v4_set_forwarding(struct kvm *kvm, int virq, struct kvm_kernel_irq_routing_entry *irq_entry) { struct vgic_its *its; struct vgic_irq *irq; struct its_vlpi_map map; unsigned long flags; int ret; if (!vgic_supports_direct_msis(kvm)) return 0; /* * Get the ITS, and escape early on error (not a valid * doorbell for any of our vITSs). */ its = vgic_get_its(kvm, irq_entry); if (IS_ERR(its)) return 0; mutex_lock(&its->its_lock); /* Perform the actual DevID/EventID -> LPI translation. */ ret = vgic_its_resolve_lpi(kvm, its, irq_entry->msi.devid, irq_entry->msi.data, &irq); if (ret) goto out; /* Silently exit if the vLPI is already mapped */ if (irq->hw) goto out; /* * Emit the mapping request. If it fails, the ITS probably * isn't v4 compatible, so let's silently bail out. Holding * the ITS lock should ensure that nothing can modify the * target vcpu. */ map = (struct its_vlpi_map) { .vm = &kvm->arch.vgic.its_vm, .vpe = &irq->target_vcpu->arch.vgic_cpu.vgic_v3.its_vpe, .vintid = irq->intid, .properties = ((irq->priority & 0xfc) | (irq->enabled ? LPI_PROP_ENABLED : 0) | LPI_PROP_GROUP1), .db_enabled = true, }; ret = its_map_vlpi(virq, &map); if (ret) goto out; irq->hw = true; irq->host_irq = virq; atomic_inc(&map.vpe->vlpi_count); /* Transfer pending state */ raw_spin_lock_irqsave(&irq->irq_lock, flags); if (irq->pending_latch) { ret = irq_set_irqchip_state(irq->host_irq, IRQCHIP_STATE_PENDING, irq->pending_latch); WARN_RATELIMIT(ret, "IRQ %d", irq->host_irq); /* * Clear pending_latch and communicate this state * change via vgic_queue_irq_unlock. */ irq->pending_latch = false; vgic_queue_irq_unlock(kvm, irq, flags); } else { raw_spin_unlock_irqrestore(&irq->irq_lock, flags); } out: mutex_unlock(&its->its_lock); return ret; } int kvm_vgic_v4_unset_forwarding(struct kvm *kvm, int virq, struct kvm_kernel_irq_routing_entry *irq_entry) { struct vgic_its *its; struct vgic_irq *irq; int ret; if (!vgic_supports_direct_msis(kvm)) return 0; /* * Get the ITS, and escape early on error (not a valid * doorbell for any of our vITSs). */ its = vgic_get_its(kvm, irq_entry); if (IS_ERR(its)) return 0; mutex_lock(&its->its_lock); ret = vgic_its_resolve_lpi(kvm, its, irq_entry->msi.devid, irq_entry->msi.data, &irq); if (ret) goto out; WARN_ON(!(irq->hw && irq->host_irq == virq)); if (irq->hw) { atomic_dec(&irq->target_vcpu->arch.vgic_cpu.vgic_v3.its_vpe.vlpi_count); irq->hw = false; ret = its_unmap_vlpi(virq); } out: mutex_unlock(&its->its_lock); return ret; } |
| 198 198 3 3 27 10 10 27 197 198 197 197 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 | /* SPDX-License-Identifier: GPL-2.0 */ /* * Implementation of the extensible bitmap type. * * Author : Stephen Smalley, <stephen.smalley.work@gmail.com> */ /* * Updated: Hewlett-Packard <paul@paul-moore.com> * Added support to import/export the NetLabel category bitmap * (c) Copyright Hewlett-Packard Development Company, L.P., 2006 * * Updated: KaiGai Kohei <kaigai@ak.jp.nec.com> * Applied standard bit operations to improve bitmap scanning. */ #include <linux/kernel.h> #include <linux/slab.h> #include <linux/errno.h> #include <linux/jhash.h> #include <net/netlabel.h> #include "ebitmap.h" #include "policydb.h" #define BITS_PER_U64 ((u32)(sizeof(u64) * 8)) static struct kmem_cache *ebitmap_node_cachep __ro_after_init; int ebitmap_cmp(const struct ebitmap *e1, const struct ebitmap *e2) { const struct ebitmap_node *n1, *n2; if (e1->highbit != e2->highbit) return 0; n1 = e1->node; n2 = e2->node; while (n1 && n2 && (n1->startbit == n2->startbit) && !memcmp(n1->maps, n2->maps, EBITMAP_SIZE / 8)) { n1 = n1->next; n2 = n2->next; } if (n1 || n2) return 0; return 1; } int ebitmap_cpy(struct ebitmap *dst, const struct ebitmap *src) { struct ebitmap_node *new, *prev; const struct ebitmap_node *n; ebitmap_init(dst); n = src->node; prev = NULL; while (n) { new = kmem_cache_zalloc(ebitmap_node_cachep, GFP_ATOMIC); if (!new) { ebitmap_destroy(dst); return -ENOMEM; } new->startbit = n->startbit; memcpy(new->maps, n->maps, EBITMAP_SIZE / 8); new->next = NULL; if (prev) prev->next = new; else dst->node = new; prev = new; n = n->next; } dst->highbit = src->highbit; return 0; } int ebitmap_and(struct ebitmap *dst, const struct ebitmap *e1, const struct ebitmap *e2) { struct ebitmap_node *n; u32 bit; int rc; ebitmap_init(dst); ebitmap_for_each_positive_bit(e1, n, bit) { if (ebitmap_get_bit(e2, bit)) { rc = ebitmap_set_bit(dst, bit, 1); if (rc < 0) return rc; } } return 0; } #ifdef CONFIG_NETLABEL /** * ebitmap_netlbl_export - Export an ebitmap into a NetLabel category bitmap * @ebmap: the ebitmap to export * @catmap: the NetLabel category bitmap * * Description: * Export a SELinux extensibile bitmap into a NetLabel category bitmap. * Returns zero on success, negative values on error. * */ int ebitmap_netlbl_export(struct ebitmap *ebmap, struct netlbl_lsm_catmap **catmap) { struct ebitmap_node *e_iter = ebmap->node; unsigned long e_map; u32 offset; unsigned int iter; int rc; if (e_iter == NULL) { *catmap = NULL; return 0; } if (*catmap != NULL) netlbl_catmap_free(*catmap); *catmap = NULL; while (e_iter) { offset = e_iter->startbit; for (iter = 0; iter < EBITMAP_UNIT_NUMS; iter++) { e_map = e_iter->maps[iter]; if (e_map != 0) { rc = netlbl_catmap_setlong(catmap, offset, e_map, GFP_ATOMIC); if (rc != 0) goto netlbl_export_failure; } offset += EBITMAP_UNIT_SIZE; } e_iter = e_iter->next; } return 0; netlbl_export_failure: netlbl_catmap_free(*catmap); return -ENOMEM; } /** * ebitmap_netlbl_import - Import a NetLabel category bitmap into an ebitmap * @ebmap: the ebitmap to import * @catmap: the NetLabel category bitmap * * Description: * Import a NetLabel category bitmap into a SELinux extensibile bitmap. * Returns zero on success, negative values on error. * */ int ebitmap_netlbl_import(struct ebitmap *ebmap, struct netlbl_lsm_catmap *catmap) { int rc; struct ebitmap_node *e_iter = NULL; struct ebitmap_node *e_prev = NULL; u32 offset = 0, idx; unsigned long bitmap; for (;;) { rc = netlbl_catmap_getlong(catmap, &offset, &bitmap); if (rc < 0) goto netlbl_import_failure; if (offset == (u32)-1) return 0; /* don't waste ebitmap space if the netlabel bitmap is empty */ if (bitmap == 0) { offset += EBITMAP_UNIT_SIZE; continue; } if (e_iter == NULL || offset >= e_iter->startbit + EBITMAP_SIZE) { e_prev = e_iter; e_iter = kmem_cache_zalloc(ebitmap_node_cachep, GFP_ATOMIC); if (e_iter == NULL) goto netlbl_import_failure; e_iter->startbit = offset - (offset % EBITMAP_SIZE); if (e_prev == NULL) ebmap->node = e_iter; else e_prev->next = e_iter; ebmap->highbit = e_iter->startbit + EBITMAP_SIZE; } /* offset will always be aligned to an unsigned long */ idx = EBITMAP_NODE_INDEX(e_iter, offset); e_iter->maps[idx] = bitmap; /* next */ offset += EBITMAP_UNIT_SIZE; } /* NOTE: we should never reach this return */ return 0; netlbl_import_failure: ebitmap_destroy(ebmap); return -ENOMEM; } #endif /* CONFIG_NETLABEL */ /* * Check to see if all the bits set in e2 are also set in e1. Optionally, * if last_e2bit is non-zero, the highest set bit in e2 cannot exceed * last_e2bit. */ int ebitmap_contains(const struct ebitmap *e1, const struct ebitmap *e2, u32 last_e2bit) { const struct ebitmap_node *n1, *n2; int i; if (e1->highbit < e2->highbit) return 0; n1 = e1->node; n2 = e2->node; while (n1 && n2 && (n1->startbit <= n2->startbit)) { if (n1->startbit < n2->startbit) { n1 = n1->next; continue; } for (i = EBITMAP_UNIT_NUMS - 1; (i >= 0) && !n2->maps[i];) i--; /* Skip trailing NULL map entries */ if (last_e2bit && (i >= 0)) { u32 lastsetbit = n2->startbit + i * EBITMAP_UNIT_SIZE + __fls(n2->maps[i]); if (lastsetbit > last_e2bit) return 0; } while (i >= 0) { if ((n1->maps[i] & n2->maps[i]) != n2->maps[i]) return 0; i--; } n1 = n1->next; n2 = n2->next; } if (n2) return 0; return 1; } int ebitmap_get_bit(const struct ebitmap *e, u32 bit) { const struct ebitmap_node *n; if (e->highbit < bit) return 0; n = e->node; while (n && (n->startbit <= bit)) { if ((n->startbit + EBITMAP_SIZE) > bit) return ebitmap_node_get_bit(n, bit); n = n->next; } return 0; } int ebitmap_set_bit(struct ebitmap *e, u32 bit, int value) { struct ebitmap_node *n, *prev, *new; prev = NULL; n = e->node; while (n && n->startbit <= bit) { if ((n->startbit + EBITMAP_SIZE) > bit) { if (value) { ebitmap_node_set_bit(n, bit); } else { u32 s; ebitmap_node_clr_bit(n, bit); s = find_first_bit(n->maps, EBITMAP_SIZE); if (s < EBITMAP_SIZE) return 0; /* drop this node from the bitmap */ if (!n->next) { /* * this was the highest map * within the bitmap */ if (prev) e->highbit = prev->startbit + EBITMAP_SIZE; else e->highbit = 0; } if (prev) prev->next = n->next; else e->node = n->next; kmem_cache_free(ebitmap_node_cachep, n); } return 0; } prev = n; n = n->next; } if (!value) return 0; new = kmem_cache_zalloc(ebitmap_node_cachep, GFP_ATOMIC); if (!new) return -ENOMEM; new->startbit = bit - (bit % EBITMAP_SIZE); ebitmap_node_set_bit(new, bit); if (!n) /* this node will be the highest map within the bitmap */ e->highbit = new->startbit + EBITMAP_SIZE; if (prev) { new->next = prev->next; prev->next = new; } else { new->next = e->node; e->node = new; } return 0; } void ebitmap_destroy(struct ebitmap *e) { struct ebitmap_node *n, *temp; if (!e) return; n = e->node; while (n) { temp = n; n = n->next; kmem_cache_free(ebitmap_node_cachep, temp); } e->highbit = 0; e->node = NULL; } int ebitmap_read(struct ebitmap *e, void *fp) { struct ebitmap_node *n = NULL; u32 mapunit, count, startbit, index, i; __le32 ebitmap_start; u64 map; __le64 mapbits; __le32 buf[3]; int rc; ebitmap_init(e); rc = next_entry(buf, fp, sizeof buf); if (rc < 0) goto out; mapunit = le32_to_cpu(buf[0]); e->highbit = le32_to_cpu(buf[1]); count = le32_to_cpu(buf[2]); if (mapunit != BITS_PER_U64) { pr_err("SELinux: ebitmap: map size %u does not " "match my size %u (high bit was %u)\n", mapunit, BITS_PER_U64, e->highbit); goto bad; } /* round up e->highbit */ e->highbit += EBITMAP_SIZE - 1; e->highbit -= (e->highbit % EBITMAP_SIZE); if (!e->highbit) { e->node = NULL; goto ok; } if (e->highbit && !count) goto bad; for (i = 0; i < count; i++) { rc = next_entry(&ebitmap_start, fp, sizeof(u32)); if (rc < 0) { pr_err("SELinux: ebitmap: truncated map\n"); goto bad; } startbit = le32_to_cpu(ebitmap_start); if (startbit & (mapunit - 1)) { pr_err("SELinux: ebitmap start bit (%u) is " "not a multiple of the map unit size (%u)\n", startbit, mapunit); goto bad; } if (startbit > e->highbit - mapunit) { pr_err("SELinux: ebitmap start bit (%u) is " "beyond the end of the bitmap (%u)\n", startbit, (e->highbit - mapunit)); goto bad; } if (!n || startbit >= n->startbit + EBITMAP_SIZE) { struct ebitmap_node *tmp; tmp = kmem_cache_zalloc(ebitmap_node_cachep, GFP_KERNEL); if (!tmp) { pr_err("SELinux: ebitmap: out of memory\n"); rc = -ENOMEM; goto bad; } /* round down */ tmp->startbit = startbit - (startbit % EBITMAP_SIZE); if (n) n->next = tmp; else e->node = tmp; n = tmp; } else if (startbit <= n->startbit) { pr_err("SELinux: ebitmap: start bit %u" " comes after start bit %u\n", startbit, n->startbit); goto bad; } rc = next_entry(&mapbits, fp, sizeof(u64)); if (rc < 0) { pr_err("SELinux: ebitmap: truncated map\n"); goto bad; } map = le64_to_cpu(mapbits); if (!map) { pr_err("SELinux: ebitmap: empty map\n"); goto bad; } index = (startbit - n->startbit) / EBITMAP_UNIT_SIZE; while (map) { n->maps[index++] = map & (-1UL); map = EBITMAP_SHIFT_UNIT_SIZE(map); } } if (n && n->startbit + EBITMAP_SIZE != e->highbit) { pr_err("SELinux: ebitmap: high bit %u is not equal to the expected value %zu\n", e->highbit, n->startbit + EBITMAP_SIZE); goto bad; } ok: rc = 0; out: return rc; bad: if (!rc) rc = -EINVAL; ebitmap_destroy(e); goto out; } int ebitmap_write(const struct ebitmap *e, void *fp) { struct ebitmap_node *n; u32 bit, count, last_bit, last_startbit; __le32 buf[3]; u64 map; int rc; buf[0] = cpu_to_le32(BITS_PER_U64); count = 0; last_bit = 0; last_startbit = U32_MAX; ebitmap_for_each_positive_bit(e, n, bit) { if (last_startbit == U32_MAX || rounddown(bit, BITS_PER_U64) > last_startbit) { count++; last_startbit = rounddown(bit, BITS_PER_U64); } last_bit = roundup(bit + 1, BITS_PER_U64); } buf[1] = cpu_to_le32(last_bit); buf[2] = cpu_to_le32(count); rc = put_entry(buf, sizeof(u32), 3, fp); if (rc) return rc; map = 0; last_startbit = U32_MAX; ebitmap_for_each_positive_bit(e, n, bit) { if (last_startbit == U32_MAX || rounddown(bit, BITS_PER_U64) > last_startbit) { __le64 buf64[1]; /* this is the very first bit */ if (!map) { last_startbit = rounddown(bit, BITS_PER_U64); map = (u64)1 << (bit - last_startbit); continue; } /* write the last node */ buf[0] = cpu_to_le32(last_startbit); rc = put_entry(buf, sizeof(u32), 1, fp); if (rc) return rc; buf64[0] = cpu_to_le64(map); rc = put_entry(buf64, sizeof(u64), 1, fp); if (rc) return rc; /* set up for the next node */ map = 0; last_startbit = rounddown(bit, BITS_PER_U64); } map |= (u64)1 << (bit - last_startbit); } /* write the last node */ if (map) { __le64 buf64[1]; /* write the last node */ buf[0] = cpu_to_le32(last_startbit); rc = put_entry(buf, sizeof(u32), 1, fp); if (rc) return rc; buf64[0] = cpu_to_le64(map); rc = put_entry(buf64, sizeof(u64), 1, fp); if (rc) return rc; } return 0; } u32 ebitmap_hash(const struct ebitmap *e, u32 hash) { struct ebitmap_node *node; /* need to change hash even if ebitmap is empty */ hash = jhash_1word(e->highbit, hash); for (node = e->node; node; node = node->next) { hash = jhash_1word(node->startbit, hash); hash = jhash(node->maps, sizeof(node->maps), hash); } return hash; } void __init ebitmap_cache_init(void) { ebitmap_node_cachep = KMEM_CACHE(ebitmap_node, SLAB_PANIC); } |
| 52 15 238 209 94 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _LINUX_HUGE_MM_H #define _LINUX_HUGE_MM_H #include <linux/mm_types.h> #include <linux/fs.h> /* only for vma_is_dax() */ #include <linux/kobject.h> vm_fault_t do_huge_pmd_anonymous_page(struct vm_fault *vmf); int copy_huge_pmd(struct mm_struct *dst_mm, struct mm_struct *src_mm, pmd_t *dst_pmd, pmd_t *src_pmd, unsigned long addr, struct vm_area_struct *dst_vma, struct vm_area_struct *src_vma); void huge_pmd_set_accessed(struct vm_fault *vmf); int copy_huge_pud(struct mm_struct *dst_mm, struct mm_struct *src_mm, pud_t *dst_pud, pud_t *src_pud, unsigned long addr, struct vm_area_struct *vma); #ifdef CONFIG_HAVE_ARCH_TRANSPARENT_HUGEPAGE_PUD void huge_pud_set_accessed(struct vm_fault *vmf, pud_t orig_pud); #else static inline void huge_pud_set_accessed(struct vm_fault *vmf, pud_t orig_pud) { } #endif vm_fault_t do_huge_pmd_wp_page(struct vm_fault *vmf); bool madvise_free_huge_pmd(struct mmu_gather *tlb, struct vm_area_struct *vma, pmd_t *pmd, unsigned long addr, unsigned long next); int zap_huge_pmd(struct mmu_gather *tlb, struct vm_area_struct *vma, pmd_t *pmd, unsigned long addr); int zap_huge_pud(struct mmu_gather *tlb, struct vm_area_struct *vma, pud_t *pud, unsigned long addr); bool move_huge_pmd(struct vm_area_struct *vma, unsigned long old_addr, unsigned long new_addr, pmd_t *old_pmd, pmd_t *new_pmd); int change_huge_pmd(struct mmu_gather *tlb, struct vm_area_struct *vma, pmd_t *pmd, unsigned long addr, pgprot_t newprot, unsigned long cp_flags); vm_fault_t vmf_insert_pfn_pmd(struct vm_fault *vmf, pfn_t pfn, bool write); vm_fault_t vmf_insert_pfn_pud(struct vm_fault *vmf, pfn_t pfn, bool write); enum transparent_hugepage_flag { TRANSPARENT_HUGEPAGE_UNSUPPORTED, TRANSPARENT_HUGEPAGE_FLAG, TRANSPARENT_HUGEPAGE_REQ_MADV_FLAG, TRANSPARENT_HUGEPAGE_DEFRAG_DIRECT_FLAG, TRANSPARENT_HUGEPAGE_DEFRAG_KSWAPD_FLAG, TRANSPARENT_HUGEPAGE_DEFRAG_KSWAPD_OR_MADV_FLAG, TRANSPARENT_HUGEPAGE_DEFRAG_REQ_MADV_FLAG, TRANSPARENT_HUGEPAGE_DEFRAG_KHUGEPAGED_FLAG, TRANSPARENT_HUGEPAGE_USE_ZERO_PAGE_FLAG, }; struct kobject; struct kobj_attribute; ssize_t single_hugepage_flag_store(struct kobject *kobj, struct kobj_attribute *attr, const char *buf, size_t count, enum transparent_hugepage_flag flag); ssize_t single_hugepage_flag_show(struct kobject *kobj, struct kobj_attribute *attr, char *buf, enum transparent_hugepage_flag flag); extern struct kobj_attribute shmem_enabled_attr; extern struct kobj_attribute thpsize_shmem_enabled_attr; /* * Mask of all large folio orders supported for anonymous THP; all orders up to * and including PMD_ORDER, except order-0 (which is not "huge") and order-1 * (which is a limitation of the THP implementation). */ #define THP_ORDERS_ALL_ANON ((BIT(PMD_ORDER + 1) - 1) & ~(BIT(0) | BIT(1))) /* * Mask of all large folio orders supported for file THP. Folios in a DAX * file is never split and the MAX_PAGECACHE_ORDER limit does not apply to * it. Same to PFNMAPs where there's neither page* nor pagecache. */ #define THP_ORDERS_ALL_SPECIAL \ (BIT(PMD_ORDER) | BIT(PUD_ORDER)) #define THP_ORDERS_ALL_FILE_DEFAULT \ ((BIT(MAX_PAGECACHE_ORDER + 1) - 1) & ~BIT(0)) /* * Mask of all large folio orders supported for THP. */ #define THP_ORDERS_ALL \ (THP_ORDERS_ALL_ANON | THP_ORDERS_ALL_SPECIAL | THP_ORDERS_ALL_FILE_DEFAULT) #define TVA_SMAPS (1 << 0) /* Will be used for procfs */ #define TVA_IN_PF (1 << 1) /* Page fault handler */ #define TVA_ENFORCE_SYSFS (1 << 2) /* Obey sysfs configuration */ #define thp_vma_allowable_order(vma, vm_flags, tva_flags, order) \ (!!thp_vma_allowable_orders(vma, vm_flags, tva_flags, BIT(order))) #define split_folio(f) split_folio_to_list(f, NULL) #ifdef CONFIG_PGTABLE_HAS_HUGE_LEAVES #define HPAGE_PMD_SHIFT PMD_SHIFT #define HPAGE_PUD_SHIFT PUD_SHIFT #else #define HPAGE_PMD_SHIFT ({ BUILD_BUG(); 0; }) #define HPAGE_PUD_SHIFT ({ BUILD_BUG(); 0; }) #endif #define HPAGE_PMD_ORDER (HPAGE_PMD_SHIFT-PAGE_SHIFT) #define HPAGE_PMD_NR (1<<HPAGE_PMD_ORDER) #define HPAGE_PMD_MASK (~(HPAGE_PMD_SIZE - 1)) #define HPAGE_PMD_SIZE ((1UL) << HPAGE_PMD_SHIFT) #define HPAGE_PUD_ORDER (HPAGE_PUD_SHIFT-PAGE_SHIFT) #define HPAGE_PUD_NR (1<<HPAGE_PUD_ORDER) #define HPAGE_PUD_MASK (~(HPAGE_PUD_SIZE - 1)) #define HPAGE_PUD_SIZE ((1UL) << HPAGE_PUD_SHIFT) enum mthp_stat_item { MTHP_STAT_ANON_FAULT_ALLOC, MTHP_STAT_ANON_FAULT_FALLBACK, MTHP_STAT_ANON_FAULT_FALLBACK_CHARGE, MTHP_STAT_ZSWPOUT, MTHP_STAT_SWPIN, MTHP_STAT_SWPOUT, MTHP_STAT_SWPOUT_FALLBACK, MTHP_STAT_SHMEM_ALLOC, MTHP_STAT_SHMEM_FALLBACK, MTHP_STAT_SHMEM_FALLBACK_CHARGE, MTHP_STAT_SPLIT, MTHP_STAT_SPLIT_FAILED, MTHP_STAT_SPLIT_DEFERRED, MTHP_STAT_NR_ANON, MTHP_STAT_NR_ANON_PARTIALLY_MAPPED, __MTHP_STAT_COUNT }; #if defined(CONFIG_TRANSPARENT_HUGEPAGE) && defined(CONFIG_SYSFS) struct mthp_stat { unsigned long stats[ilog2(MAX_PTRS_PER_PTE) + 1][__MTHP_STAT_COUNT]; }; DECLARE_PER_CPU(struct mthp_stat, mthp_stats); static inline void mod_mthp_stat(int order, enum mthp_stat_item item, int delta) { if (order <= 0 || order > PMD_ORDER) return; this_cpu_add(mthp_stats.stats[order][item], delta); } static inline void count_mthp_stat(int order, enum mthp_stat_item item) { mod_mthp_stat(order, item, 1); } #else static inline void mod_mthp_stat(int order, enum mthp_stat_item item, int delta) { } static inline void count_mthp_stat(int order, enum mthp_stat_item item) { } #endif #ifdef CONFIG_TRANSPARENT_HUGEPAGE extern unsigned long transparent_hugepage_flags; extern unsigned long huge_anon_orders_always; extern unsigned long huge_anon_orders_madvise; extern unsigned long huge_anon_orders_inherit; static inline bool hugepage_global_enabled(void) { return transparent_hugepage_flags & ((1<<TRANSPARENT_HUGEPAGE_FLAG) | (1<<TRANSPARENT_HUGEPAGE_REQ_MADV_FLAG)); } static inline bool hugepage_global_always(void) { return transparent_hugepage_flags & (1<<TRANSPARENT_HUGEPAGE_FLAG); } static inline int highest_order(unsigned long orders) { return fls_long(orders) - 1; } static inline int next_order(unsigned long *orders, int prev) { *orders &= ~BIT(prev); return highest_order(*orders); } /* * Do the below checks: * - For file vma, check if the linear page offset of vma is * order-aligned within the file. The hugepage is * guaranteed to be order-aligned within the file, but we must * check that the order-aligned addresses in the VMA map to * order-aligned offsets within the file, else the hugepage will * not be mappable. * - For all vmas, check if the haddr is in an aligned hugepage * area. */ static inline bool thp_vma_suitable_order(struct vm_area_struct *vma, unsigned long addr, int order) { unsigned long hpage_size = PAGE_SIZE << order; unsigned long haddr; /* Don't have to check pgoff for anonymous vma */ if (!vma_is_anonymous(vma)) { if (!IS_ALIGNED((vma->vm_start >> PAGE_SHIFT) - vma->vm_pgoff, hpage_size >> PAGE_SHIFT)) return false; } haddr = ALIGN_DOWN(addr, hpage_size); if (haddr < vma->vm_start || haddr + hpage_size > vma->vm_end) return false; return true; } /* * Filter the bitfield of input orders to the ones suitable for use in the vma. * See thp_vma_suitable_order(). * All orders that pass the checks are returned as a bitfield. */ static inline unsigned long thp_vma_suitable_orders(struct vm_area_struct *vma, unsigned long addr, unsigned long orders) { int order; /* * Iterate over orders, highest to lowest, removing orders that don't * meet alignment requirements from the set. Exit loop at first order * that meets requirements, since all lower orders must also meet * requirements. */ order = highest_order(orders); while (orders) { if (thp_vma_suitable_order(vma, addr, order)) break; order = next_order(&orders, order); } return orders; } unsigned long __thp_vma_allowable_orders(struct vm_area_struct *vma, unsigned long vm_flags, unsigned long tva_flags, unsigned long orders); /** * thp_vma_allowable_orders - determine hugepage orders that are allowed for vma * @vma: the vm area to check * @vm_flags: use these vm_flags instead of vma->vm_flags * @tva_flags: Which TVA flags to honour * @orders: bitfield of all orders to consider * * Calculates the intersection of the requested hugepage orders and the allowed * hugepage orders for the provided vma. Permitted orders are encoded as a set * bit at the corresponding bit position (bit-2 corresponds to order-2, bit-3 * corresponds to order-3, etc). Order-0 is never considered a hugepage order. * * Return: bitfield of orders allowed for hugepage in the vma. 0 if no hugepage * orders are allowed. */ static inline unsigned long thp_vma_allowable_orders(struct vm_area_struct *vma, unsigned long vm_flags, unsigned long tva_flags, unsigned long orders) { /* Optimization to check if required orders are enabled early. */ if ((tva_flags & TVA_ENFORCE_SYSFS) && vma_is_anonymous(vma)) { unsigned long mask = READ_ONCE(huge_anon_orders_always); if (vm_flags & VM_HUGEPAGE) mask |= READ_ONCE(huge_anon_orders_madvise); if (hugepage_global_always() || ((vm_flags & VM_HUGEPAGE) && hugepage_global_enabled())) mask |= READ_ONCE(huge_anon_orders_inherit); orders &= mask; if (!orders) return 0; } return __thp_vma_allowable_orders(vma, vm_flags, tva_flags, orders); } struct thpsize { struct kobject kobj; struct list_head node; int order; }; #define to_thpsize(kobj) container_of(kobj, struct thpsize, kobj) #define transparent_hugepage_use_zero_page() \ (transparent_hugepage_flags & \ (1<<TRANSPARENT_HUGEPAGE_USE_ZERO_PAGE_FLAG)) static inline bool vma_thp_disabled(struct vm_area_struct *vma, unsigned long vm_flags) { /* * Explicitly disabled through madvise or prctl, or some * architectures may disable THP for some mappings, for * example, s390 kvm. */ return (vm_flags & VM_NOHUGEPAGE) || test_bit(MMF_DISABLE_THP, &vma->vm_mm->flags); } static inline bool thp_disabled_by_hw(void) { /* If the hardware/firmware marked hugepage support disabled. */ return transparent_hugepage_flags & (1 << TRANSPARENT_HUGEPAGE_UNSUPPORTED); } unsigned long thp_get_unmapped_area(struct file *filp, unsigned long addr, unsigned long len, unsigned long pgoff, unsigned long flags); unsigned long thp_get_unmapped_area_vmflags(struct file *filp, unsigned long addr, unsigned long len, unsigned long pgoff, unsigned long flags, vm_flags_t vm_flags); bool can_split_folio(struct folio *folio, int caller_pins, int *pextra_pins); int split_huge_page_to_list_to_order(struct page *page, struct list_head *list, unsigned int new_order); int min_order_for_split(struct folio *folio); int split_folio_to_list(struct folio *folio, struct list_head *list); static inline int split_huge_page(struct page *page) { struct folio *folio = page_folio(page); int ret = min_order_for_split(folio); if (ret < 0) return ret; /* * split_huge_page() locks the page before splitting and * expects the same page that has been split to be locked when * returned. split_folio(page_folio(page)) cannot be used here * because it converts the page to folio and passes the head * page to be split. */ return split_huge_page_to_list_to_order(page, NULL, ret); } void deferred_split_folio(struct folio *folio, bool partially_mapped); void __split_huge_pmd(struct vm_area_struct *vma, pmd_t *pmd, unsigned long address, bool freeze, struct folio *folio); #define split_huge_pmd(__vma, __pmd, __address) \ do { \ pmd_t *____pmd = (__pmd); \ if (is_swap_pmd(*____pmd) || pmd_trans_huge(*____pmd) \ || pmd_devmap(*____pmd)) \ __split_huge_pmd(__vma, __pmd, __address, \ false, NULL); \ } while (0) void split_huge_pmd_address(struct vm_area_struct *vma, unsigned long address, bool freeze, struct folio *folio); void __split_huge_pud(struct vm_area_struct *vma, pud_t *pud, unsigned long address); #ifdef CONFIG_HAVE_ARCH_TRANSPARENT_HUGEPAGE_PUD int change_huge_pud(struct mmu_gather *tlb, struct vm_area_struct *vma, pud_t *pudp, unsigned long addr, pgprot_t newprot, unsigned long cp_flags); #else static inline int change_huge_pud(struct mmu_gather *tlb, struct vm_area_struct *vma, pud_t *pudp, unsigned long addr, pgprot_t newprot, unsigned long cp_flags) { return 0; } #endif #define split_huge_pud(__vma, __pud, __address) \ do { \ pud_t *____pud = (__pud); \ if (pud_trans_huge(*____pud) \ || pud_devmap(*____pud)) \ __split_huge_pud(__vma, __pud, __address); \ } while (0) int hugepage_madvise(struct vm_area_struct *vma, unsigned long *vm_flags, int advice); int madvise_collapse(struct vm_area_struct *vma, struct vm_area_struct **prev, unsigned long start, unsigned long end); void vma_adjust_trans_huge(struct vm_area_struct *vma, unsigned long start, unsigned long end, long adjust_next); spinlock_t *__pmd_trans_huge_lock(pmd_t *pmd, struct vm_area_struct *vma); spinlock_t *__pud_trans_huge_lock(pud_t *pud, struct vm_area_struct *vma); static inline int is_swap_pmd(pmd_t pmd) { return !pmd_none(pmd) && !pmd_present(pmd); } /* mmap_lock must be held on entry */ static inline spinlock_t *pmd_trans_huge_lock(pmd_t *pmd, struct vm_area_struct *vma) { if (is_swap_pmd(*pmd) || pmd_trans_huge(*pmd) || pmd_devmap(*pmd)) return __pmd_trans_huge_lock(pmd, vma); else return NULL; } static inline spinlock_t *pud_trans_huge_lock(pud_t *pud, struct vm_area_struct *vma) { if (pud_trans_huge(*pud) || pud_devmap(*pud)) return __pud_trans_huge_lock(pud, vma); else return NULL; } /** * folio_test_pmd_mappable - Can we map this folio with a PMD? * @folio: The folio to test */ static inline bool folio_test_pmd_mappable(struct folio *folio) { return folio_order(folio) >= HPAGE_PMD_ORDER; } struct page *follow_devmap_pmd(struct vm_area_struct *vma, unsigned long addr, pmd_t *pmd, int flags, struct dev_pagemap **pgmap); vm_fault_t do_huge_pmd_numa_page(struct vm_fault *vmf); extern struct folio *huge_zero_folio; extern unsigned long huge_zero_pfn; static inline bool is_huge_zero_folio(const struct folio *folio) { return READ_ONCE(huge_zero_folio) == folio; } static inline bool is_huge_zero_pmd(pmd_t pmd) { return pmd_present(pmd) && READ_ONCE(huge_zero_pfn) == pmd_pfn(pmd); } struct folio *mm_get_huge_zero_folio(struct mm_struct *mm); void mm_put_huge_zero_folio(struct mm_struct *mm); #define mk_huge_pmd(page, prot) pmd_mkhuge(mk_pmd(page, prot)) static inline bool thp_migration_supported(void) { return IS_ENABLED(CONFIG_ARCH_ENABLE_THP_MIGRATION); } void split_huge_pmd_locked(struct vm_area_struct *vma, unsigned long address, pmd_t *pmd, bool freeze, struct folio *folio); bool unmap_huge_pmd_locked(struct vm_area_struct *vma, unsigned long addr, pmd_t *pmdp, struct folio *folio); #else /* CONFIG_TRANSPARENT_HUGEPAGE */ static inline bool folio_test_pmd_mappable(struct folio *folio) { return false; } static inline bool thp_vma_suitable_order(struct vm_area_struct *vma, unsigned long addr, int order) { return false; } static inline unsigned long thp_vma_suitable_orders(struct vm_area_struct *vma, unsigned long addr, unsigned long orders) { return 0; } static inline unsigned long thp_vma_allowable_orders(struct vm_area_struct *vma, unsigned long vm_flags, unsigned long tva_flags, unsigned long orders) { return 0; } #define transparent_hugepage_flags 0UL #define thp_get_unmapped_area NULL static inline unsigned long thp_get_unmapped_area_vmflags(struct file *filp, unsigned long addr, unsigned long len, unsigned long pgoff, unsigned long flags, vm_flags_t vm_flags) { return 0; } static inline bool can_split_folio(struct folio *folio, int caller_pins, int *pextra_pins) { return false; } static inline int split_huge_page_to_list_to_order(struct page *page, struct list_head *list, unsigned int new_order) { return 0; } static inline int split_huge_page(struct page *page) { return 0; } static inline int split_folio_to_list(struct folio *folio, struct list_head *list) { return 0; } static inline void deferred_split_folio(struct folio *folio, bool partially_mapped) {} #define split_huge_pmd(__vma, __pmd, __address) \ do { } while (0) static inline void __split_huge_pmd(struct vm_area_struct *vma, pmd_t *pmd, unsigned long address, bool freeze, struct folio *folio) {} static inline void split_huge_pmd_address(struct vm_area_struct *vma, unsigned long address, bool freeze, struct folio *folio) {} static inline void split_huge_pmd_locked(struct vm_area_struct *vma, unsigned long address, pmd_t *pmd, bool freeze, struct folio *folio) {} static inline bool unmap_huge_pmd_locked(struct vm_area_struct *vma, unsigned long addr, pmd_t *pmdp, struct folio *folio) { return false; } #define split_huge_pud(__vma, __pmd, __address) \ do { } while (0) static inline int hugepage_madvise(struct vm_area_struct *vma, unsigned long *vm_flags, int advice) { return -EINVAL; } static inline int madvise_collapse(struct vm_area_struct *vma, struct vm_area_struct **prev, unsigned long start, unsigned long end) { return -EINVAL; } static inline void vma_adjust_trans_huge(struct vm_area_struct *vma, unsigned long start, unsigned long end, long adjust_next) { } static inline int is_swap_pmd(pmd_t pmd) { return 0; } static inline spinlock_t *pmd_trans_huge_lock(pmd_t *pmd, struct vm_area_struct *vma) { return NULL; } static inline spinlock_t *pud_trans_huge_lock(pud_t *pud, struct vm_area_struct *vma) { return NULL; } static inline vm_fault_t do_huge_pmd_numa_page(struct vm_fault *vmf) { return 0; } static inline bool is_huge_zero_folio(const struct folio *folio) { return false; } static inline bool is_huge_zero_pmd(pmd_t pmd) { return false; } static inline void mm_put_huge_zero_folio(struct mm_struct *mm) { return; } static inline struct page *follow_devmap_pmd(struct vm_area_struct *vma, unsigned long addr, pmd_t *pmd, int flags, struct dev_pagemap **pgmap) { return NULL; } static inline bool thp_migration_supported(void) { return false; } static inline int highest_order(unsigned long orders) { return 0; } static inline int next_order(unsigned long *orders, int prev) { return 0; } static inline void __split_huge_pud(struct vm_area_struct *vma, pud_t *pud, unsigned long address) { } static inline int change_huge_pud(struct mmu_gather *tlb, struct vm_area_struct *vma, pud_t *pudp, unsigned long addr, pgprot_t newprot, unsigned long cp_flags) { return 0; } #endif /* CONFIG_TRANSPARENT_HUGEPAGE */ static inline int split_folio_to_list_to_order(struct folio *folio, struct list_head *list, int new_order) { return split_huge_page_to_list_to_order(&folio->page, list, new_order); } static inline int split_folio_to_order(struct folio *folio, int new_order) { return split_folio_to_list_to_order(folio, NULL, new_order); } #endif /* _LINUX_HUGE_MM_H */ |
| 3 3 3 3 3 3 3 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 1522 1523 1524 1525 1526 1527 1528 1529 1530 1531 1532 1533 1534 1535 1536 1537 1538 1539 1540 1541 1542 1543 1544 1545 1546 1547 1548 1549 1550 1551 1552 1553 1554 1555 1556 1557 1558 1559 1560 1561 1562 1563 1564 1565 1566 1567 1568 1569 1570 1571 1572 1573 1574 1575 1576 1577 1578 1579 1580 1581 1582 1583 1584 1585 1586 1587 1588 1589 1590 1591 1592 1593 1594 1595 1596 1597 1598 1599 1600 1601 1602 1603 1604 1605 1606 1607 1608 1609 1610 1611 1612 1613 1614 1615 1616 1617 1618 1619 1620 1621 1622 1623 1624 1625 1626 1627 1628 1629 1630 1631 1632 1633 1634 1635 1636 1637 1638 1639 1640 1641 1642 1643 1644 1645 1646 1647 1648 1649 1650 1651 1652 1653 1654 1655 1656 1657 1658 1659 1660 1661 1662 1663 1664 1665 1666 1667 1668 1669 1670 1671 1672 1673 1674 1675 1676 1677 1678 1679 1680 1681 1682 1683 1684 1685 1686 1687 1688 1689 1690 1691 1692 1693 1694 1695 1696 1697 1698 1699 1700 1701 1702 1703 1704 1705 1706 1707 1708 1709 1710 1711 1712 1713 1714 1715 1716 1717 1718 1719 1720 1721 1722 1723 1724 1725 1726 1727 1728 1729 1730 1731 1732 1733 1734 1735 1736 1737 1738 1739 1740 1741 1742 1743 1744 1745 1746 1747 1748 1749 1750 1751 1752 1753 1754 1755 1756 1757 1758 1759 1760 1761 1762 1763 1764 1765 1766 1767 1768 1769 1770 1771 1772 1773 1774 1775 1776 1777 1778 1779 1780 1781 1782 1783 1784 1785 1786 1787 1788 1789 1790 1791 1792 1793 1794 1795 1796 1797 1798 1799 1800 1801 1802 1803 1804 1805 1806 1807 1808 1809 1810 1811 1812 1813 1814 1815 1816 1817 1818 1819 1820 1821 1822 1823 1824 1825 1826 1827 1828 1829 1830 1831 1832 1833 1834 1835 1836 1837 1838 1839 1840 1841 1842 1843 1844 1845 1846 1847 1848 1849 1850 1851 1852 1853 1854 1855 1856 1857 1858 1859 1860 1861 1862 1863 1864 1865 1866 1867 1868 1869 1870 1871 1872 1873 1874 1875 1876 1877 1878 1879 1880 1881 1882 1883 1884 1885 1886 1887 1888 1889 1890 1891 1892 1893 1894 1895 1896 1897 1898 1899 1900 1901 1902 1903 1904 1905 1906 1907 1908 1909 1910 1911 1912 1913 1914 1915 1916 1917 1918 1919 1920 1921 1922 1923 1924 1925 1926 1927 1928 1929 1930 1931 1932 1933 1934 1935 1936 1937 1938 1939 1940 1941 1942 1943 1944 1945 1946 1947 1948 1949 1950 1951 1952 1953 1954 1955 1956 1957 1958 1959 1960 1961 1962 1963 1964 1965 1966 1967 1968 1969 1970 1971 1972 1973 1974 1975 1976 1977 1978 1979 1980 1981 1982 1983 1984 1985 1986 1987 1988 1989 1990 1991 1992 1993 1994 1995 1996 1997 1998 1999 2000 2001 2002 2003 2004 2005 2006 2007 2008 2009 2010 2011 2012 2013 2014 2015 2016 2017 2018 2019 2020 2021 2022 2023 2024 2025 2026 2027 2028 2029 2030 2031 2032 2033 2034 2035 2036 2037 2038 2039 2040 2041 2042 2043 2044 2045 2046 2047 2048 2049 2050 2051 2052 2053 2054 2055 2056 2057 2058 2059 2060 2061 2062 2063 2064 2065 2066 2067 2068 2069 2070 2071 2072 2073 2074 2075 2076 2077 2078 2079 2080 2081 2082 2083 2084 2085 2086 2087 2088 2089 2090 2091 2092 2093 2094 2095 2096 2097 2098 2099 2100 2101 2102 2103 2104 2105 2106 2107 2108 2109 2110 2111 2112 2113 2114 2115 2116 2117 2118 2119 2120 2121 2122 2123 2124 2125 2126 2127 2128 2129 2130 2131 2132 2133 2134 2135 2136 2137 2138 2139 2140 2141 2142 2143 2144 2145 2146 2147 2148 2149 2150 2151 2152 2153 2154 2155 2156 2157 2158 2159 2160 2161 2162 2163 2164 2165 2166 2167 2168 2169 2170 2171 2172 2173 2174 2175 2176 2177 2178 2179 2180 2181 2182 2183 2184 2185 2186 2187 2188 2189 2190 2191 2192 2193 2194 2195 2196 2197 2198 2199 2200 2201 2202 2203 2204 2205 2206 2207 2208 2209 2210 2211 2212 2213 2214 2215 2216 2217 2218 2219 2220 2221 2222 2223 2224 2225 2226 2227 2228 2229 2230 2231 2232 2233 2234 2235 2236 2237 2238 2239 2240 2241 2242 2243 2244 2245 2246 2247 2248 2249 2250 2251 2252 2253 2254 2255 2256 2257 2258 2259 2260 2261 2262 2263 2264 2265 2266 2267 2268 2269 2270 2271 2272 2273 2274 2275 2276 2277 2278 2279 2280 2281 2282 2283 2284 2285 2286 2287 2288 2289 2290 2291 2292 2293 2294 2295 2296 2297 2298 2299 2300 2301 2302 2303 2304 2305 2306 2307 2308 2309 2310 2311 2312 2313 2314 2315 2316 2317 2318 2319 2320 2321 2322 2323 2324 2325 2326 2327 2328 2329 2330 2331 2332 2333 2334 2335 2336 2337 2338 2339 2340 2341 2342 2343 2344 2345 2346 2347 2348 2349 2350 2351 2352 2353 2354 2355 2356 2357 2358 2359 2360 2361 2362 2363 2364 2365 2366 2367 2368 2369 2370 2371 2372 2373 2374 2375 2376 2377 2378 2379 2380 2381 2382 2383 2384 2385 2386 2387 2388 2389 2390 2391 2392 2393 2394 2395 2396 2397 2398 2399 2400 2401 2402 2403 2404 2405 2406 2407 2408 2409 2410 2411 2412 2413 2414 2415 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef __NET_NETLINK_H #define __NET_NETLINK_H #include <linux/types.h> #include <linux/netlink.h> #include <linux/jiffies.h> #include <linux/in6.h> /* ======================================================================== * Netlink Messages and Attributes Interface (As Seen On TV) * ------------------------------------------------------------------------ * Messages Interface * ------------------------------------------------------------------------ * * Message Format: * <--- nlmsg_total_size(payload) ---> * <-- nlmsg_msg_size(payload) -> * +----------+- - -+-------------+- - -+-------- - - * | nlmsghdr | Pad | Payload | Pad | nlmsghdr * +----------+- - -+-------------+- - -+-------- - - * nlmsg_data(nlh)---^ ^ * nlmsg_next(nlh)-----------------------+ * * Payload Format: * <---------------------- nlmsg_len(nlh) ---------------------> * <------ hdrlen ------> <- nlmsg_attrlen(nlh, hdrlen) -> * +----------------------+- - -+--------------------------------+ * | Family Header | Pad | Attributes | * +----------------------+- - -+--------------------------------+ * nlmsg_attrdata(nlh, hdrlen)---^ * * Data Structures: * struct nlmsghdr netlink message header * * Message Construction: * nlmsg_new() create a new netlink message * nlmsg_put() add a netlink message to an skb * nlmsg_put_answer() callback based nlmsg_put() * nlmsg_end() finalize netlink message * nlmsg_get_pos() return current position in message * nlmsg_trim() trim part of message * nlmsg_cancel() cancel message construction * nlmsg_consume() free a netlink message (expected) * nlmsg_free() free a netlink message (drop) * * Message Sending: * nlmsg_multicast() multicast message to several groups * nlmsg_unicast() unicast a message to a single socket * nlmsg_notify() send notification message * * Message Length Calculations: * nlmsg_msg_size(payload) length of message w/o padding * nlmsg_total_size(payload) length of message w/ padding * nlmsg_padlen(payload) length of padding at tail * * Message Payload Access: * nlmsg_data(nlh) head of message payload * nlmsg_len(nlh) length of message payload * nlmsg_attrdata(nlh, hdrlen) head of attributes data * nlmsg_attrlen(nlh, hdrlen) length of attributes data * * Message Parsing: * nlmsg_ok(nlh, remaining) does nlh fit into remaining bytes? * nlmsg_next(nlh, remaining) get next netlink message * nlmsg_parse() parse attributes of a message * nlmsg_find_attr() find an attribute in a message * nlmsg_for_each_msg() loop over all messages * nlmsg_validate() validate netlink message incl. attrs * nlmsg_for_each_attr() loop over all attributes * * Misc: * nlmsg_report() report back to application? * * ------------------------------------------------------------------------ * Attributes Interface * ------------------------------------------------------------------------ * * Attribute Format: * <------- nla_total_size(payload) -------> * <---- nla_attr_size(payload) -----> * +----------+- - -+- - - - - - - - - +- - -+-------- - - * | Header | Pad | Payload | Pad | Header * +----------+- - -+- - - - - - - - - +- - -+-------- - - * <- nla_len(nla) -> ^ * nla_data(nla)----^ | * nla_next(nla)-----------------------------' * * Data Structures: * struct nlattr netlink attribute header * * Attribute Construction: * nla_reserve(skb, type, len) reserve room for an attribute * nla_reserve_nohdr(skb, len) reserve room for an attribute w/o hdr * nla_put(skb, type, len, data) add attribute to skb * nla_put_nohdr(skb, len, data) add attribute w/o hdr * nla_append(skb, len, data) append data to skb * * Attribute Construction for Basic Types: * nla_put_u8(skb, type, value) add u8 attribute to skb * nla_put_u16(skb, type, value) add u16 attribute to skb * nla_put_u32(skb, type, value) add u32 attribute to skb * nla_put_u64_64bit(skb, type, * value, padattr) add u64 attribute to skb * nla_put_s8(skb, type, value) add s8 attribute to skb * nla_put_s16(skb, type, value) add s16 attribute to skb * nla_put_s32(skb, type, value) add s32 attribute to skb * nla_put_s64(skb, type, value, * padattr) add s64 attribute to skb * nla_put_string(skb, type, str) add string attribute to skb * nla_put_flag(skb, type) add flag attribute to skb * nla_put_msecs(skb, type, jiffies, * padattr) add msecs attribute to skb * nla_put_in_addr(skb, type, addr) add IPv4 address attribute to skb * nla_put_in6_addr(skb, type, addr) add IPv6 address attribute to skb * * Nested Attributes Construction: * nla_nest_start(skb, type) start a nested attribute * nla_nest_end(skb, nla) finalize a nested attribute * nla_nest_cancel(skb, nla) cancel nested attribute construction * * Attribute Length Calculations: * nla_attr_size(payload) length of attribute w/o padding * nla_total_size(payload) length of attribute w/ padding * nla_padlen(payload) length of padding * * Attribute Payload Access: * nla_data(nla) head of attribute payload * nla_len(nla) length of attribute payload * * Attribute Payload Access for Basic Types: * nla_get_uint(nla) get payload for a uint attribute * nla_get_sint(nla) get payload for a sint attribute * nla_get_u8(nla) get payload for a u8 attribute * nla_get_u16(nla) get payload for a u16 attribute * nla_get_u32(nla) get payload for a u32 attribute * nla_get_u64(nla) get payload for a u64 attribute * nla_get_s8(nla) get payload for a s8 attribute * nla_get_s16(nla) get payload for a s16 attribute * nla_get_s32(nla) get payload for a s32 attribute * nla_get_s64(nla) get payload for a s64 attribute * nla_get_flag(nla) return 1 if flag is true * nla_get_msecs(nla) get payload for a msecs attribute * * The same functions also exist with _default(). * * Attribute Misc: * nla_memcpy(dest, nla, count) copy attribute into memory * nla_memcmp(nla, data, size) compare attribute with memory area * nla_strscpy(dst, nla, size) copy attribute to a sized string * nla_strcmp(nla, str) compare attribute with string * * Attribute Parsing: * nla_ok(nla, remaining) does nla fit into remaining bytes? * nla_next(nla, remaining) get next netlink attribute * nla_validate() validate a stream of attributes * nla_validate_nested() validate a stream of nested attributes * nla_find() find attribute in stream of attributes * nla_find_nested() find attribute in nested attributes * nla_parse() parse and validate stream of attrs * nla_parse_nested() parse nested attributes * nla_for_each_attr() loop over all attributes * nla_for_each_attr_type() loop over all attributes with the * given type * nla_for_each_nested() loop over the nested attributes * nla_for_each_nested_type() loop over the nested attributes with * the given type *========================================================================= */ /** * Standard attribute types to specify validation policy */ enum { NLA_UNSPEC, NLA_U8, NLA_U16, NLA_U32, NLA_U64, NLA_STRING, NLA_FLAG, NLA_MSECS, NLA_NESTED, NLA_NESTED_ARRAY, NLA_NUL_STRING, NLA_BINARY, NLA_S8, NLA_S16, NLA_S32, NLA_S64, NLA_BITFIELD32, NLA_REJECT, NLA_BE16, NLA_BE32, NLA_SINT, NLA_UINT, __NLA_TYPE_MAX, }; #define NLA_TYPE_MAX (__NLA_TYPE_MAX - 1) struct netlink_range_validation { u64 min, max; }; struct netlink_range_validation_signed { s64 min, max; }; enum nla_policy_validation { NLA_VALIDATE_NONE, NLA_VALIDATE_RANGE, NLA_VALIDATE_RANGE_WARN_TOO_LONG, NLA_VALIDATE_MIN, NLA_VALIDATE_MAX, NLA_VALIDATE_MASK, NLA_VALIDATE_RANGE_PTR, NLA_VALIDATE_FUNCTION, }; /** * struct nla_policy - attribute validation policy * @type: Type of attribute or NLA_UNSPEC * @validation_type: type of attribute validation done in addition to * type-specific validation (e.g. range, function call), see * &enum nla_policy_validation * @len: Type specific length of payload * * Policies are defined as arrays of this struct, the array must be * accessible by attribute type up to the highest identifier to be expected. * * Meaning of `len' field: * NLA_STRING Maximum length of string * NLA_NUL_STRING Maximum length of string (excluding NUL) * NLA_FLAG Unused * NLA_BINARY Maximum length of attribute payload * (but see also below with the validation type) * NLA_NESTED, * NLA_NESTED_ARRAY Length verification is done by checking len of * nested header (or empty); len field is used if * nested_policy is also used, for the max attr * number in the nested policy. * NLA_SINT, NLA_UINT, * NLA_U8, NLA_U16, * NLA_U32, NLA_U64, * NLA_S8, NLA_S16, * NLA_S32, NLA_S64, * NLA_BE16, NLA_BE32, * NLA_MSECS Leaving the length field zero will verify the * given type fits, using it verifies minimum length * just like "All other" * NLA_BITFIELD32 Unused * NLA_REJECT Unused * All other Minimum length of attribute payload * * Meaning of validation union: * NLA_BITFIELD32 This is a 32-bit bitmap/bitselector attribute and * `bitfield32_valid' is the u32 value of valid flags * NLA_REJECT This attribute is always rejected and `reject_message' * may point to a string to report as the error instead * of the generic one in extended ACK. * NLA_NESTED `nested_policy' to a nested policy to validate, must * also set `len' to the max attribute number. Use the * provided NLA_POLICY_NESTED() macro. * Note that nla_parse() will validate, but of course not * parse, the nested sub-policies. * NLA_NESTED_ARRAY `nested_policy' points to a nested policy to validate, * must also set `len' to the max attribute number. Use * the provided NLA_POLICY_NESTED_ARRAY() macro. * The difference to NLA_NESTED is the structure: * NLA_NESTED has the nested attributes directly inside * while an array has the nested attributes at another * level down and the attribute types directly in the * nesting don't matter. * NLA_UINT, * NLA_U8, * NLA_U16, * NLA_U32, * NLA_U64, * NLA_BE16, * NLA_BE32, * NLA_SINT, * NLA_S8, * NLA_S16, * NLA_S32, * NLA_S64 The `min' and `max' fields are used depending on the * validation_type field, if that is min/max/range then * the min, max or both are used (respectively) to check * the value of the integer attribute. * Note that in the interest of code simplicity and * struct size both limits are s16, so you cannot * enforce a range that doesn't fall within the range * of s16 - do that using the NLA_POLICY_FULL_RANGE() * or NLA_POLICY_FULL_RANGE_SIGNED() macros instead. * Use the NLA_POLICY_MIN(), NLA_POLICY_MAX() and * NLA_POLICY_RANGE() macros. * NLA_UINT, * NLA_U8, * NLA_U16, * NLA_U32, * NLA_U64 If the validation_type field instead is set to * NLA_VALIDATE_RANGE_PTR, `range' must be a pointer * to a struct netlink_range_validation that indicates * the min/max values. * Use NLA_POLICY_FULL_RANGE(). * NLA_SINT, * NLA_S8, * NLA_S16, * NLA_S32, * NLA_S64 If the validation_type field instead is set to * NLA_VALIDATE_RANGE_PTR, `range_signed' must be a * pointer to a struct netlink_range_validation_signed * that indicates the min/max values. * Use NLA_POLICY_FULL_RANGE_SIGNED(). * * NLA_BINARY If the validation type is like the ones for integers * above, then the min/max length (not value like for * integers) of the attribute is enforced. * * All other Unused - but note that it's a union * * Meaning of `validate' field, use via NLA_POLICY_VALIDATE_FN: * NLA_BINARY Validation function called for the attribute. * All other Unused - but note that it's a union * * Example: * * static const u32 myvalidflags = 0xff231023; * * static const struct nla_policy my_policy[ATTR_MAX+1] = { * [ATTR_FOO] = { .type = NLA_U16 }, * [ATTR_BAR] = { .type = NLA_STRING, .len = BARSIZ }, * [ATTR_BAZ] = NLA_POLICY_EXACT_LEN(sizeof(struct mystruct)), * [ATTR_GOO] = NLA_POLICY_BITFIELD32(myvalidflags), * }; */ struct nla_policy { u8 type; u8 validation_type; u16 len; union { /** * @strict_start_type: first attribute to validate strictly * * This entry is special, and used for the attribute at index 0 * only, and specifies special data about the policy, namely it * specifies the "boundary type" where strict length validation * starts for any attribute types >= this value, also, strict * nesting validation starts here. * * Additionally, it means that NLA_UNSPEC is actually NLA_REJECT * for any types >= this, so need to use NLA_POLICY_MIN_LEN() to * get the previous pure { .len = xyz } behaviour. The advantage * of this is that types not specified in the policy will be * rejected. * * For completely new families it should be set to 1 so that the * validation is enforced for all attributes. For existing ones * it should be set at least when new attributes are added to * the enum used by the policy, and be set to the new value that * was added to enforce strict validation from thereon. */ u16 strict_start_type; /* private: use NLA_POLICY_*() to set */ const u32 bitfield32_valid; const u32 mask; const char *reject_message; const struct nla_policy *nested_policy; const struct netlink_range_validation *range; const struct netlink_range_validation_signed *range_signed; struct { s16 min, max; }; int (*validate)(const struct nlattr *attr, struct netlink_ext_ack *extack); }; }; #define NLA_POLICY_ETH_ADDR NLA_POLICY_EXACT_LEN(ETH_ALEN) #define NLA_POLICY_ETH_ADDR_COMPAT NLA_POLICY_EXACT_LEN_WARN(ETH_ALEN) #define _NLA_POLICY_NESTED(maxattr, policy) \ { .type = NLA_NESTED, .nested_policy = policy, .len = maxattr } #define _NLA_POLICY_NESTED_ARRAY(maxattr, policy) \ { .type = NLA_NESTED_ARRAY, .nested_policy = policy, .len = maxattr } #define NLA_POLICY_NESTED(policy) \ _NLA_POLICY_NESTED(ARRAY_SIZE(policy) - 1, policy) #define NLA_POLICY_NESTED_ARRAY(policy) \ _NLA_POLICY_NESTED_ARRAY(ARRAY_SIZE(policy) - 1, policy) #define NLA_POLICY_BITFIELD32(valid) \ { .type = NLA_BITFIELD32, .bitfield32_valid = valid } #define __NLA_IS_UINT_TYPE(tp) \ (tp == NLA_U8 || tp == NLA_U16 || tp == NLA_U32 || \ tp == NLA_U64 || tp == NLA_UINT || \ tp == NLA_BE16 || tp == NLA_BE32) #define __NLA_IS_SINT_TYPE(tp) \ (tp == NLA_S8 || tp == NLA_S16 || tp == NLA_S32 || tp == NLA_S64 || \ tp == NLA_SINT) #define __NLA_ENSURE(condition) BUILD_BUG_ON_ZERO(!(condition)) #define NLA_ENSURE_UINT_TYPE(tp) \ (__NLA_ENSURE(__NLA_IS_UINT_TYPE(tp)) + tp) #define NLA_ENSURE_UINT_OR_BINARY_TYPE(tp) \ (__NLA_ENSURE(__NLA_IS_UINT_TYPE(tp) || \ tp == NLA_MSECS || \ tp == NLA_BINARY) + tp) #define NLA_ENSURE_SINT_TYPE(tp) \ (__NLA_ENSURE(__NLA_IS_SINT_TYPE(tp)) + tp) #define NLA_ENSURE_INT_OR_BINARY_TYPE(tp) \ (__NLA_ENSURE(__NLA_IS_UINT_TYPE(tp) || \ __NLA_IS_SINT_TYPE(tp) || \ tp == NLA_MSECS || \ tp == NLA_BINARY) + tp) #define NLA_ENSURE_NO_VALIDATION_PTR(tp) \ (__NLA_ENSURE(tp != NLA_BITFIELD32 && \ tp != NLA_REJECT && \ tp != NLA_NESTED && \ tp != NLA_NESTED_ARRAY) + tp) #define NLA_POLICY_RANGE(tp, _min, _max) { \ .type = NLA_ENSURE_INT_OR_BINARY_TYPE(tp), \ .validation_type = NLA_VALIDATE_RANGE, \ .min = _min, \ .max = _max \ } #define NLA_POLICY_FULL_RANGE(tp, _range) { \ .type = NLA_ENSURE_UINT_OR_BINARY_TYPE(tp), \ .validation_type = NLA_VALIDATE_RANGE_PTR, \ .range = _range, \ } #define NLA_POLICY_FULL_RANGE_SIGNED(tp, _range) { \ .type = NLA_ENSURE_SINT_TYPE(tp), \ .validation_type = NLA_VALIDATE_RANGE_PTR, \ .range_signed = _range, \ } #define NLA_POLICY_MIN(tp, _min) { \ .type = NLA_ENSURE_INT_OR_BINARY_TYPE(tp), \ .validation_type = NLA_VALIDATE_MIN, \ .min = _min, \ } #define NLA_POLICY_MAX(tp, _max) { \ .type = NLA_ENSURE_INT_OR_BINARY_TYPE(tp), \ .validation_type = NLA_VALIDATE_MAX, \ .max = _max, \ } #define NLA_POLICY_MASK(tp, _mask) { \ .type = NLA_ENSURE_UINT_TYPE(tp), \ .validation_type = NLA_VALIDATE_MASK, \ .mask = _mask, \ } #define NLA_POLICY_VALIDATE_FN(tp, fn, ...) { \ .type = NLA_ENSURE_NO_VALIDATION_PTR(tp), \ .validation_type = NLA_VALIDATE_FUNCTION, \ .validate = fn, \ .len = __VA_ARGS__ + 0, \ } #define NLA_POLICY_EXACT_LEN(_len) NLA_POLICY_RANGE(NLA_BINARY, _len, _len) #define NLA_POLICY_EXACT_LEN_WARN(_len) { \ .type = NLA_BINARY, \ .validation_type = NLA_VALIDATE_RANGE_WARN_TOO_LONG, \ .min = _len, \ .max = _len \ } #define NLA_POLICY_MIN_LEN(_len) NLA_POLICY_MIN(NLA_BINARY, _len) #define NLA_POLICY_MAX_LEN(_len) NLA_POLICY_MAX(NLA_BINARY, _len) /** * struct nl_info - netlink source information * @nlh: Netlink message header of original request * @nl_net: Network namespace * @portid: Netlink PORTID of requesting application * @skip_notify: Skip netlink notifications to user space * @skip_notify_kernel: Skip selected in-kernel notifications */ struct nl_info { struct nlmsghdr *nlh; struct net *nl_net; u32 portid; u8 skip_notify:1, skip_notify_kernel:1; }; /** * enum netlink_validation - netlink message/attribute validation levels * @NL_VALIDATE_LIBERAL: Old-style "be liberal" validation, not caring about * extra data at the end of the message, attributes being longer than * they should be, or unknown attributes being present. * @NL_VALIDATE_TRAILING: Reject junk data encountered after attribute parsing. * @NL_VALIDATE_MAXTYPE: Reject attributes > max type; Together with _TRAILING * this is equivalent to the old nla_parse_strict()/nlmsg_parse_strict(). * @NL_VALIDATE_UNSPEC: Reject attributes with NLA_UNSPEC in the policy. * This can safely be set by the kernel when the given policy has no * NLA_UNSPEC anymore, and can thus be used to ensure policy entries * are enforced going forward. * @NL_VALIDATE_STRICT_ATTRS: strict attribute policy parsing (e.g. * U8, U16, U32 must have exact size, etc.) * @NL_VALIDATE_NESTED: Check that NLA_F_NESTED is set for NLA_NESTED(_ARRAY) * and unset for other policies. */ enum netlink_validation { NL_VALIDATE_LIBERAL = 0, NL_VALIDATE_TRAILING = BIT(0), NL_VALIDATE_MAXTYPE = BIT(1), NL_VALIDATE_UNSPEC = BIT(2), NL_VALIDATE_STRICT_ATTRS = BIT(3), NL_VALIDATE_NESTED = BIT(4), }; #define NL_VALIDATE_DEPRECATED_STRICT (NL_VALIDATE_TRAILING |\ NL_VALIDATE_MAXTYPE) #define NL_VALIDATE_STRICT (NL_VALIDATE_TRAILING |\ NL_VALIDATE_MAXTYPE |\ NL_VALIDATE_UNSPEC |\ NL_VALIDATE_STRICT_ATTRS |\ NL_VALIDATE_NESTED) int netlink_rcv_skb(struct sk_buff *skb, int (*cb)(struct sk_buff *, struct nlmsghdr *, struct netlink_ext_ack *)); int nlmsg_notify(struct sock *sk, struct sk_buff *skb, u32 portid, unsigned int group, int report, gfp_t flags); int __nla_validate(const struct nlattr *head, int len, int maxtype, const struct nla_policy *policy, unsigned int validate, struct netlink_ext_ack *extack); int __nla_parse(struct nlattr **tb, int maxtype, const struct nlattr *head, int len, const struct nla_policy *policy, unsigned int validate, struct netlink_ext_ack *extack); int nla_policy_len(const struct nla_policy *, int); struct nlattr *nla_find(const struct nlattr *head, int len, int attrtype); ssize_t nla_strscpy(char *dst, const struct nlattr *nla, size_t dstsize); char *nla_strdup(const struct nlattr *nla, gfp_t flags); int nla_memcpy(void *dest, const struct nlattr *src, int count); int nla_memcmp(const struct nlattr *nla, const void *data, size_t size); int nla_strcmp(const struct nlattr *nla, const char *str); struct nlattr *__nla_reserve(struct sk_buff *skb, int attrtype, int attrlen); struct nlattr *__nla_reserve_64bit(struct sk_buff *skb, int attrtype, int attrlen, int padattr); void *__nla_reserve_nohdr(struct sk_buff *skb, int attrlen); struct nlattr *nla_reserve(struct sk_buff *skb, int attrtype, int attrlen); struct nlattr *nla_reserve_64bit(struct sk_buff *skb, int attrtype, int attrlen, int padattr); void *nla_reserve_nohdr(struct sk_buff *skb, int attrlen); void __nla_put(struct sk_buff *skb, int attrtype, int attrlen, const void *data); void __nla_put_64bit(struct sk_buff *skb, int attrtype, int attrlen, const void *data, int padattr); void __nla_put_nohdr(struct sk_buff *skb, int attrlen, const void *data); int nla_put(struct sk_buff *skb, int attrtype, int attrlen, const void *data); int nla_put_64bit(struct sk_buff *skb, int attrtype, int attrlen, const void *data, int padattr); int nla_put_nohdr(struct sk_buff *skb, int attrlen, const void *data); int nla_append(struct sk_buff *skb, int attrlen, const void *data); /************************************************************************** * Netlink Messages **************************************************************************/ /** * nlmsg_msg_size - length of netlink message not including padding * @payload: length of message payload */ static inline int nlmsg_msg_size(int payload) { return NLMSG_HDRLEN + payload; } /** * nlmsg_total_size - length of netlink message including padding * @payload: length of message payload */ static inline int nlmsg_total_size(int payload) { return NLMSG_ALIGN(nlmsg_msg_size(payload)); } /** * nlmsg_padlen - length of padding at the message's tail * @payload: length of message payload */ static inline int nlmsg_padlen(int payload) { return nlmsg_total_size(payload) - nlmsg_msg_size(payload); } /** * nlmsg_data - head of message payload * @nlh: netlink message header */ static inline void *nlmsg_data(const struct nlmsghdr *nlh) { return (unsigned char *) nlh + NLMSG_HDRLEN; } /** * nlmsg_len - length of message payload * @nlh: netlink message header */ static inline int nlmsg_len(const struct nlmsghdr *nlh) { return nlh->nlmsg_len - NLMSG_HDRLEN; } /** * nlmsg_attrdata - head of attributes data * @nlh: netlink message header * @hdrlen: length of family specific header */ static inline struct nlattr *nlmsg_attrdata(const struct nlmsghdr *nlh, int hdrlen) { unsigned char *data = nlmsg_data(nlh); return (struct nlattr *) (data + NLMSG_ALIGN(hdrlen)); } /** * nlmsg_attrlen - length of attributes data * @nlh: netlink message header * @hdrlen: length of family specific header */ static inline int nlmsg_attrlen(const struct nlmsghdr *nlh, int hdrlen) { return nlmsg_len(nlh) - NLMSG_ALIGN(hdrlen); } /** * nlmsg_ok - check if the netlink message fits into the remaining bytes * @nlh: netlink message header * @remaining: number of bytes remaining in message stream */ static inline int nlmsg_ok(const struct nlmsghdr *nlh, int remaining) { return (remaining >= (int) sizeof(struct nlmsghdr) && nlh->nlmsg_len >= sizeof(struct nlmsghdr) && nlh->nlmsg_len <= remaining); } /** * nlmsg_next - next netlink message in message stream * @nlh: netlink message header * @remaining: number of bytes remaining in message stream * * Returns the next netlink message in the message stream and * decrements remaining by the size of the current message. */ static inline struct nlmsghdr * nlmsg_next(const struct nlmsghdr *nlh, int *remaining) { int totlen = NLMSG_ALIGN(nlh->nlmsg_len); *remaining -= totlen; return (struct nlmsghdr *) ((unsigned char *) nlh + totlen); } /** * nla_parse - Parse a stream of attributes into a tb buffer * @tb: destination array with maxtype+1 elements * @maxtype: maximum attribute type to be expected * @head: head of attribute stream * @len: length of attribute stream * @policy: validation policy * @extack: extended ACK pointer * * Parses a stream of attributes and stores a pointer to each attribute in * the tb array accessible via the attribute type. Attributes with a type * exceeding maxtype will be rejected, policy must be specified, attributes * will be validated in the strictest way possible. * * Returns 0 on success or a negative error code. */ static inline int nla_parse(struct nlattr **tb, int maxtype, const struct nlattr *head, int len, const struct nla_policy *policy, struct netlink_ext_ack *extack) { return __nla_parse(tb, maxtype, head, len, policy, NL_VALIDATE_STRICT, extack); } /** * nla_parse_deprecated - Parse a stream of attributes into a tb buffer * @tb: destination array with maxtype+1 elements * @maxtype: maximum attribute type to be expected * @head: head of attribute stream * @len: length of attribute stream * @policy: validation policy * @extack: extended ACK pointer * * Parses a stream of attributes and stores a pointer to each attribute in * the tb array accessible via the attribute type. Attributes with a type * exceeding maxtype will be ignored and attributes from the policy are not * always strictly validated (only for new attributes). * * Returns 0 on success or a negative error code. */ static inline int nla_parse_deprecated(struct nlattr **tb, int maxtype, const struct nlattr *head, int len, const struct nla_policy *policy, struct netlink_ext_ack *extack) { return __nla_parse(tb, maxtype, head, len, policy, NL_VALIDATE_LIBERAL, extack); } /** * nla_parse_deprecated_strict - Parse a stream of attributes into a tb buffer * @tb: destination array with maxtype+1 elements * @maxtype: maximum attribute type to be expected * @head: head of attribute stream * @len: length of attribute stream * @policy: validation policy * @extack: extended ACK pointer * * Parses a stream of attributes and stores a pointer to each attribute in * the tb array accessible via the attribute type. Attributes with a type * exceeding maxtype will be rejected as well as trailing data, but the * policy is not completely strictly validated (only for new attributes). * * Returns 0 on success or a negative error code. */ static inline int nla_parse_deprecated_strict(struct nlattr **tb, int maxtype, const struct nlattr *head, int len, const struct nla_policy *policy, struct netlink_ext_ack *extack) { return __nla_parse(tb, maxtype, head, len, policy, NL_VALIDATE_DEPRECATED_STRICT, extack); } /** * __nlmsg_parse - parse attributes of a netlink message * @nlh: netlink message header * @hdrlen: length of family specific header * @tb: destination array with maxtype+1 elements * @maxtype: maximum attribute type to be expected * @policy: validation policy * @validate: validation strictness * @extack: extended ACK report struct * * See nla_parse() */ static inline int __nlmsg_parse(const struct nlmsghdr *nlh, int hdrlen, struct nlattr *tb[], int maxtype, const struct nla_policy *policy, unsigned int validate, struct netlink_ext_ack *extack) { if (nlh->nlmsg_len < nlmsg_msg_size(hdrlen)) { NL_SET_ERR_MSG(extack, "Invalid header length"); return -EINVAL; } return __nla_parse(tb, maxtype, nlmsg_attrdata(nlh, hdrlen), nlmsg_attrlen(nlh, hdrlen), policy, validate, extack); } /** * nlmsg_parse - parse attributes of a netlink message * @nlh: netlink message header * @hdrlen: length of family specific header * @tb: destination array with maxtype+1 elements * @maxtype: maximum attribute type to be expected * @policy: validation policy * @extack: extended ACK report struct * * See nla_parse() */ static inline int nlmsg_parse(const struct nlmsghdr *nlh, int hdrlen, struct nlattr *tb[], int maxtype, const struct nla_policy *policy, struct netlink_ext_ack *extack) { return __nlmsg_parse(nlh, hdrlen, tb, maxtype, policy, NL_VALIDATE_STRICT, extack); } /** * nlmsg_parse_deprecated - parse attributes of a netlink message * @nlh: netlink message header * @hdrlen: length of family specific header * @tb: destination array with maxtype+1 elements * @maxtype: maximum attribute type to be expected * @policy: validation policy * @extack: extended ACK report struct * * See nla_parse_deprecated() */ static inline int nlmsg_parse_deprecated(const struct nlmsghdr *nlh, int hdrlen, struct nlattr *tb[], int maxtype, const struct nla_policy *policy, struct netlink_ext_ack *extack) { return __nlmsg_parse(nlh, hdrlen, tb, maxtype, policy, NL_VALIDATE_LIBERAL, extack); } /** * nlmsg_parse_deprecated_strict - parse attributes of a netlink message * @nlh: netlink message header * @hdrlen: length of family specific header * @tb: destination array with maxtype+1 elements * @maxtype: maximum attribute type to be expected * @policy: validation policy * @extack: extended ACK report struct * * See nla_parse_deprecated_strict() */ static inline int nlmsg_parse_deprecated_strict(const struct nlmsghdr *nlh, int hdrlen, struct nlattr *tb[], int maxtype, const struct nla_policy *policy, struct netlink_ext_ack *extack) { return __nlmsg_parse(nlh, hdrlen, tb, maxtype, policy, NL_VALIDATE_DEPRECATED_STRICT, extack); } /** * nlmsg_find_attr - find a specific attribute in a netlink message * @nlh: netlink message header * @hdrlen: length of family specific header * @attrtype: type of attribute to look for * * Returns the first attribute which matches the specified type. */ static inline struct nlattr *nlmsg_find_attr(const struct nlmsghdr *nlh, int hdrlen, int attrtype) { return nla_find(nlmsg_attrdata(nlh, hdrlen), nlmsg_attrlen(nlh, hdrlen), attrtype); } /** * nla_validate_deprecated - Validate a stream of attributes * @head: head of attribute stream * @len: length of attribute stream * @maxtype: maximum attribute type to be expected * @policy: validation policy * @extack: extended ACK report struct * * Validates all attributes in the specified attribute stream against the * specified policy. Validation is done in liberal mode. * See documentation of struct nla_policy for more details. * * Returns 0 on success or a negative error code. */ static inline int nla_validate_deprecated(const struct nlattr *head, int len, int maxtype, const struct nla_policy *policy, struct netlink_ext_ack *extack) { return __nla_validate(head, len, maxtype, policy, NL_VALIDATE_LIBERAL, extack); } /** * nla_validate - Validate a stream of attributes * @head: head of attribute stream * @len: length of attribute stream * @maxtype: maximum attribute type to be expected * @policy: validation policy * @extack: extended ACK report struct * * Validates all attributes in the specified attribute stream against the * specified policy. Validation is done in strict mode. * See documentation of struct nla_policy for more details. * * Returns 0 on success or a negative error code. */ static inline int nla_validate(const struct nlattr *head, int len, int maxtype, const struct nla_policy *policy, struct netlink_ext_ack *extack) { return __nla_validate(head, len, maxtype, policy, NL_VALIDATE_STRICT, extack); } /** * nlmsg_validate_deprecated - validate a netlink message including attributes * @nlh: netlinket message header * @hdrlen: length of family specific header * @maxtype: maximum attribute type to be expected * @policy: validation policy * @extack: extended ACK report struct */ static inline int nlmsg_validate_deprecated(const struct nlmsghdr *nlh, int hdrlen, int maxtype, const struct nla_policy *policy, struct netlink_ext_ack *extack) { if (nlh->nlmsg_len < nlmsg_msg_size(hdrlen)) return -EINVAL; return __nla_validate(nlmsg_attrdata(nlh, hdrlen), nlmsg_attrlen(nlh, hdrlen), maxtype, policy, NL_VALIDATE_LIBERAL, extack); } /** * nlmsg_report - need to report back to application? * @nlh: netlink message header * * Returns 1 if a report back to the application is requested. */ static inline int nlmsg_report(const struct nlmsghdr *nlh) { return nlh ? !!(nlh->nlmsg_flags & NLM_F_ECHO) : 0; } /** * nlmsg_seq - return the seq number of netlink message * @nlh: netlink message header * * Returns 0 if netlink message is NULL */ static inline u32 nlmsg_seq(const struct nlmsghdr *nlh) { return nlh ? nlh->nlmsg_seq : 0; } /** * nlmsg_for_each_attr - iterate over a stream of attributes * @pos: loop counter, set to current attribute * @nlh: netlink message header * @hdrlen: length of family specific header * @rem: initialized to len, holds bytes currently remaining in stream */ #define nlmsg_for_each_attr(pos, nlh, hdrlen, rem) \ nla_for_each_attr(pos, nlmsg_attrdata(nlh, hdrlen), \ nlmsg_attrlen(nlh, hdrlen), rem) /** * nlmsg_put - Add a new netlink message to an skb * @skb: socket buffer to store message in * @portid: netlink PORTID of requesting application * @seq: sequence number of message * @type: message type * @payload: length of message payload * @flags: message flags * * Returns NULL if the tailroom of the skb is insufficient to store * the message header and payload. */ static inline struct nlmsghdr *nlmsg_put(struct sk_buff *skb, u32 portid, u32 seq, int type, int payload, int flags) { if (unlikely(skb_tailroom(skb) < nlmsg_total_size(payload))) return NULL; return __nlmsg_put(skb, portid, seq, type, payload, flags); } /** * nlmsg_append - Add more data to a nlmsg in a skb * @skb: socket buffer to store message in * @size: length of message payload * * Append data to an existing nlmsg, used when constructing a message * with multiple fixed-format headers (which is rare). * Returns NULL if the tailroom of the skb is insufficient to store * the extra payload. */ static inline void *nlmsg_append(struct sk_buff *skb, u32 size) { if (unlikely(skb_tailroom(skb) < NLMSG_ALIGN(size))) return NULL; if (NLMSG_ALIGN(size) - size) memset(skb_tail_pointer(skb) + size, 0, NLMSG_ALIGN(size) - size); return __skb_put(skb, NLMSG_ALIGN(size)); } /** * nlmsg_put_answer - Add a new callback based netlink message to an skb * @skb: socket buffer to store message in * @cb: netlink callback * @type: message type * @payload: length of message payload * @flags: message flags * * Returns NULL if the tailroom of the skb is insufficient to store * the message header and payload. */ static inline struct nlmsghdr *nlmsg_put_answer(struct sk_buff *skb, struct netlink_callback *cb, int type, int payload, int flags) { return nlmsg_put(skb, NETLINK_CB(cb->skb).portid, cb->nlh->nlmsg_seq, type, payload, flags); } /** * nlmsg_new - Allocate a new netlink message * @payload: size of the message payload * @flags: the type of memory to allocate. * * Use NLMSG_DEFAULT_SIZE if the size of the payload isn't known * and a good default is needed. */ static inline struct sk_buff *nlmsg_new(size_t payload, gfp_t flags) { return alloc_skb(nlmsg_total_size(payload), flags); } /** * nlmsg_new_large - Allocate a new netlink message with non-contiguous * physical memory * @payload: size of the message payload * * The allocated skb is unable to have frag page for shinfo->frags*, * as the NULL setting for skb->head in netlink_skb_destructor() will * bypass most of the handling in skb_release_data() */ static inline struct sk_buff *nlmsg_new_large(size_t payload) { return netlink_alloc_large_skb(nlmsg_total_size(payload), 0); } /** * nlmsg_end - Finalize a netlink message * @skb: socket buffer the message is stored in * @nlh: netlink message header * * Corrects the netlink message header to include the appended * attributes. Only necessary if attributes have been added to * the message. */ static inline void nlmsg_end(struct sk_buff *skb, struct nlmsghdr *nlh) { nlh->nlmsg_len = skb_tail_pointer(skb) - (unsigned char *)nlh; } /** * nlmsg_get_pos - return current position in netlink message * @skb: socket buffer the message is stored in * * Returns a pointer to the current tail of the message. */ static inline void *nlmsg_get_pos(struct sk_buff *skb) { return skb_tail_pointer(skb); } /** * nlmsg_trim - Trim message to a mark * @skb: socket buffer the message is stored in * @mark: mark to trim to * * Trims the message to the provided mark. */ static inline void nlmsg_trim(struct sk_buff *skb, const void *mark) { if (mark) { WARN_ON((unsigned char *) mark < skb->data); skb_trim(skb, (unsigned char *) mark - skb->data); } } /** * nlmsg_cancel - Cancel construction of a netlink message * @skb: socket buffer the message is stored in * @nlh: netlink message header * * Removes the complete netlink message including all * attributes from the socket buffer again. */ static inline void nlmsg_cancel(struct sk_buff *skb, struct nlmsghdr *nlh) { nlmsg_trim(skb, nlh); } /** * nlmsg_free - drop a netlink message * @skb: socket buffer of netlink message */ static inline void nlmsg_free(struct sk_buff *skb) { kfree_skb(skb); } /** * nlmsg_consume - free a netlink message * @skb: socket buffer of netlink message */ static inline void nlmsg_consume(struct sk_buff *skb) { consume_skb(skb); } /** * nlmsg_multicast_filtered - multicast a netlink message with filter function * @sk: netlink socket to spread messages to * @skb: netlink message as socket buffer * @portid: own netlink portid to avoid sending to yourself * @group: multicast group id * @flags: allocation flags * @filter: filter function * @filter_data: filter function private data * * Return: 0 on success, negative error code for failure. */ static inline int nlmsg_multicast_filtered(struct sock *sk, struct sk_buff *skb, u32 portid, unsigned int group, gfp_t flags, netlink_filter_fn filter, void *filter_data) { int err; NETLINK_CB(skb).dst_group = group; err = netlink_broadcast_filtered(sk, skb, portid, group, flags, filter, filter_data); if (err > 0) err = 0; return err; } /** * nlmsg_multicast - multicast a netlink message * @sk: netlink socket to spread messages to * @skb: netlink message as socket buffer * @portid: own netlink portid to avoid sending to yourself * @group: multicast group id * @flags: allocation flags */ static inline int nlmsg_multicast(struct sock *sk, struct sk_buff *skb, u32 portid, unsigned int group, gfp_t flags) { return nlmsg_multicast_filtered(sk, skb, portid, group, flags, NULL, NULL); } /** * nlmsg_unicast - unicast a netlink message * @sk: netlink socket to spread message to * @skb: netlink message as socket buffer * @portid: netlink portid of the destination socket */ static inline int nlmsg_unicast(struct sock *sk, struct sk_buff *skb, u32 portid) { int err; err = netlink_unicast(sk, skb, portid, MSG_DONTWAIT); if (err > 0) err = 0; return err; } /** * nlmsg_for_each_msg - iterate over a stream of messages * @pos: loop counter, set to current message * @head: head of message stream * @len: length of message stream * @rem: initialized to len, holds bytes currently remaining in stream */ #define nlmsg_for_each_msg(pos, head, len, rem) \ for (pos = head, rem = len; \ nlmsg_ok(pos, rem); \ pos = nlmsg_next(pos, &(rem))) /** * nl_dump_check_consistent - check if sequence is consistent and advertise if not * @cb: netlink callback structure that stores the sequence number * @nlh: netlink message header to write the flag to * * This function checks if the sequence (generation) number changed during dump * and if it did, advertises it in the netlink message header. * * The correct way to use it is to set cb->seq to the generation counter when * all locks for dumping have been acquired, and then call this function for * each message that is generated. * * Note that due to initialisation concerns, 0 is an invalid sequence number * and must not be used by code that uses this functionality. */ static inline void nl_dump_check_consistent(struct netlink_callback *cb, struct nlmsghdr *nlh) { if (cb->prev_seq && cb->seq != cb->prev_seq) nlh->nlmsg_flags |= NLM_F_DUMP_INTR; cb->prev_seq = cb->seq; } /************************************************************************** * Netlink Attributes **************************************************************************/ /** * nla_attr_size - length of attribute not including padding * @payload: length of payload */ static inline int nla_attr_size(int payload) { return NLA_HDRLEN + payload; } /** * nla_total_size - total length of attribute including padding * @payload: length of payload */ static inline int nla_total_size(int payload) { return NLA_ALIGN(nla_attr_size(payload)); } /** * nla_padlen - length of padding at the tail of attribute * @payload: length of payload */ static inline int nla_padlen(int payload) { return nla_total_size(payload) - nla_attr_size(payload); } /** * nla_type - attribute type * @nla: netlink attribute */ static inline int nla_type(const struct nlattr *nla) { return nla->nla_type & NLA_TYPE_MASK; } /** * nla_data - head of payload * @nla: netlink attribute */ static inline void *nla_data(const struct nlattr *nla) { return (char *) nla + NLA_HDRLEN; } /** * nla_len - length of payload * @nla: netlink attribute */ static inline u16 nla_len(const struct nlattr *nla) { return nla->nla_len - NLA_HDRLEN; } /** * nla_ok - check if the netlink attribute fits into the remaining bytes * @nla: netlink attribute * @remaining: number of bytes remaining in attribute stream */ static inline int nla_ok(const struct nlattr *nla, int remaining) { return remaining >= (int) sizeof(*nla) && nla->nla_len >= sizeof(*nla) && nla->nla_len <= remaining; } /** * nla_next - next netlink attribute in attribute stream * @nla: netlink attribute * @remaining: number of bytes remaining in attribute stream * * Returns the next netlink attribute in the attribute stream and * decrements remaining by the size of the current attribute. */ static inline struct nlattr *nla_next(const struct nlattr *nla, int *remaining) { unsigned int totlen = NLA_ALIGN(nla->nla_len); *remaining -= totlen; return (struct nlattr *) ((char *) nla + totlen); } /** * nla_find_nested - find attribute in a set of nested attributes * @nla: attribute containing the nested attributes * @attrtype: type of attribute to look for * * Returns the first attribute which matches the specified type. */ static inline struct nlattr * nla_find_nested(const struct nlattr *nla, int attrtype) { return nla_find(nla_data(nla), nla_len(nla), attrtype); } /** * nla_parse_nested - parse nested attributes * @tb: destination array with maxtype+1 elements * @maxtype: maximum attribute type to be expected * @nla: attribute containing the nested attributes * @policy: validation policy * @extack: extended ACK report struct * * See nla_parse() */ static inline int nla_parse_nested(struct nlattr *tb[], int maxtype, const struct nlattr *nla, const struct nla_policy *policy, struct netlink_ext_ack *extack) { if (!(nla->nla_type & NLA_F_NESTED)) { NL_SET_ERR_MSG_ATTR(extack, nla, "NLA_F_NESTED is missing"); return -EINVAL; } return __nla_parse(tb, maxtype, nla_data(nla), nla_len(nla), policy, NL_VALIDATE_STRICT, extack); } /** * nla_parse_nested_deprecated - parse nested attributes * @tb: destination array with maxtype+1 elements * @maxtype: maximum attribute type to be expected * @nla: attribute containing the nested attributes * @policy: validation policy * @extack: extended ACK report struct * * See nla_parse_deprecated() */ static inline int nla_parse_nested_deprecated(struct nlattr *tb[], int maxtype, const struct nlattr *nla, const struct nla_policy *policy, struct netlink_ext_ack *extack) { return __nla_parse(tb, maxtype, nla_data(nla), nla_len(nla), policy, NL_VALIDATE_LIBERAL, extack); } /** * nla_put_u8 - Add a u8 netlink attribute to a socket buffer * @skb: socket buffer to add attribute to * @attrtype: attribute type * @value: numeric value */ static inline int nla_put_u8(struct sk_buff *skb, int attrtype, u8 value) { /* temporary variables to work around GCC PR81715 with asan-stack=1 */ u8 tmp = value; return nla_put(skb, attrtype, sizeof(u8), &tmp); } /** * nla_put_u16 - Add a u16 netlink attribute to a socket buffer * @skb: socket buffer to add attribute to * @attrtype: attribute type * @value: numeric value */ static inline int nla_put_u16(struct sk_buff *skb, int attrtype, u16 value) { u16 tmp = value; return nla_put(skb, attrtype, sizeof(u16), &tmp); } /** * nla_put_be16 - Add a __be16 netlink attribute to a socket buffer * @skb: socket buffer to add attribute to * @attrtype: attribute type * @value: numeric value */ static inline int nla_put_be16(struct sk_buff *skb, int attrtype, __be16 value) { __be16 tmp = value; return nla_put(skb, attrtype, sizeof(__be16), &tmp); } /** * nla_put_net16 - Add 16-bit network byte order netlink attribute to a socket buffer * @skb: socket buffer to add attribute to * @attrtype: attribute type * @value: numeric value */ static inline int nla_put_net16(struct sk_buff *skb, int attrtype, __be16 value) { __be16 tmp = value; return nla_put_be16(skb, attrtype | NLA_F_NET_BYTEORDER, tmp); } /** * nla_put_le16 - Add a __le16 netlink attribute to a socket buffer * @skb: socket buffer to add attribute to * @attrtype: attribute type * @value: numeric value */ static inline int nla_put_le16(struct sk_buff *skb, int attrtype, __le16 value) { __le16 tmp = value; return nla_put(skb, attrtype, sizeof(__le16), &tmp); } /** * nla_put_u32 - Add a u32 netlink attribute to a socket buffer * @skb: socket buffer to add attribute to * @attrtype: attribute type * @value: numeric value */ static inline int nla_put_u32(struct sk_buff *skb, int attrtype, u32 value) { u32 tmp = value; return nla_put(skb, attrtype, sizeof(u32), &tmp); } /** * nla_put_uint - Add a variable-size unsigned int to a socket buffer * @skb: socket buffer to add attribute to * @attrtype: attribute type * @value: numeric value */ static inline int nla_put_uint(struct sk_buff *skb, int attrtype, u64 value) { u64 tmp64 = value; u32 tmp32 = value; if (tmp64 == tmp32) return nla_put_u32(skb, attrtype, tmp32); return nla_put(skb, attrtype, sizeof(u64), &tmp64); } /** * nla_put_be32 - Add a __be32 netlink attribute to a socket buffer * @skb: socket buffer to add attribute to * @attrtype: attribute type * @value: numeric value */ static inline int nla_put_be32(struct sk_buff *skb, int attrtype, __be32 value) { __be32 tmp = value; return nla_put(skb, attrtype, sizeof(__be32), &tmp); } /** * nla_put_net32 - Add 32-bit network byte order netlink attribute to a socket buffer * @skb: socket buffer to add attribute to * @attrtype: attribute type * @value: numeric value */ static inline int nla_put_net32(struct sk_buff *skb, int attrtype, __be32 value) { __be32 tmp = value; return nla_put_be32(skb, attrtype | NLA_F_NET_BYTEORDER, tmp); } /** * nla_put_le32 - Add a __le32 netlink attribute to a socket buffer * @skb: socket buffer to add attribute to * @attrtype: attribute type * @value: numeric value */ static inline int nla_put_le32(struct sk_buff *skb, int attrtype, __le32 value) { __le32 tmp = value; return nla_put(skb, attrtype, sizeof(__le32), &tmp); } /** * nla_put_u64_64bit - Add a u64 netlink attribute to a skb and align it * @skb: socket buffer to add attribute to * @attrtype: attribute type * @value: numeric value * @padattr: attribute type for the padding */ static inline int nla_put_u64_64bit(struct sk_buff *skb, int attrtype, u64 value, int padattr) { u64 tmp = value; return nla_put_64bit(skb, attrtype, sizeof(u64), &tmp, padattr); } /** * nla_put_be64 - Add a __be64 netlink attribute to a socket buffer and align it * @skb: socket buffer to add attribute to * @attrtype: attribute type * @value: numeric value * @padattr: attribute type for the padding */ static inline int nla_put_be64(struct sk_buff *skb, int attrtype, __be64 value, int padattr) { __be64 tmp = value; return nla_put_64bit(skb, attrtype, sizeof(__be64), &tmp, padattr); } /** * nla_put_net64 - Add 64-bit network byte order nlattr to a skb and align it * @skb: socket buffer to add attribute to * @attrtype: attribute type * @value: numeric value * @padattr: attribute type for the padding */ static inline int nla_put_net64(struct sk_buff *skb, int attrtype, __be64 value, int padattr) { __be64 tmp = value; return nla_put_be64(skb, attrtype | NLA_F_NET_BYTEORDER, tmp, padattr); } /** * nla_put_le64 - Add a __le64 netlink attribute to a socket buffer and align it * @skb: socket buffer to add attribute to * @attrtype: attribute type * @value: numeric value * @padattr: attribute type for the padding */ static inline int nla_put_le64(struct sk_buff *skb, int attrtype, __le64 value, int padattr) { __le64 tmp = value; return nla_put_64bit(skb, attrtype, sizeof(__le64), &tmp, padattr); } /** * nla_put_s8 - Add a s8 netlink attribute to a socket buffer * @skb: socket buffer to add attribute to * @attrtype: attribute type * @value: numeric value */ static inline int nla_put_s8(struct sk_buff *skb, int attrtype, s8 value) { s8 tmp = value; return nla_put(skb, attrtype, sizeof(s8), &tmp); } /** * nla_put_s16 - Add a s16 netlink attribute to a socket buffer * @skb: socket buffer to add attribute to * @attrtype: attribute type * @value: numeric value */ static inline int nla_put_s16(struct sk_buff *skb, int attrtype, s16 value) { s16 tmp = value; return nla_put(skb, attrtype, sizeof(s16), &tmp); } /** * nla_put_s32 - Add a s32 netlink attribute to a socket buffer * @skb: socket buffer to add attribute to * @attrtype: attribute type * @value: numeric value */ static inline int nla_put_s32(struct sk_buff *skb, int attrtype, s32 value) { s32 tmp = value; return nla_put(skb, attrtype, sizeof(s32), &tmp); } /** * nla_put_s64 - Add a s64 netlink attribute to a socket buffer and align it * @skb: socket buffer to add attribute to * @attrtype: attribute type * @value: numeric value * @padattr: attribute type for the padding */ static inline int nla_put_s64(struct sk_buff *skb, int attrtype, s64 value, int padattr) { s64 tmp = value; return nla_put_64bit(skb, attrtype, sizeof(s64), &tmp, padattr); } /** * nla_put_sint - Add a variable-size signed int to a socket buffer * @skb: socket buffer to add attribute to * @attrtype: attribute type * @value: numeric value */ static inline int nla_put_sint(struct sk_buff *skb, int attrtype, s64 value) { s64 tmp64 = value; s32 tmp32 = value; if (tmp64 == tmp32) return nla_put_s32(skb, attrtype, tmp32); return nla_put(skb, attrtype, sizeof(s64), &tmp64); } /** * nla_put_string - Add a string netlink attribute to a socket buffer * @skb: socket buffer to add attribute to * @attrtype: attribute type * @str: NUL terminated string */ static inline int nla_put_string(struct sk_buff *skb, int attrtype, const char *str) { return nla_put(skb, attrtype, strlen(str) + 1, str); } /** * nla_put_flag - Add a flag netlink attribute to a socket buffer * @skb: socket buffer to add attribute to * @attrtype: attribute type */ static inline int nla_put_flag(struct sk_buff *skb, int attrtype) { return nla_put(skb, attrtype, 0, NULL); } /** * nla_put_msecs - Add a msecs netlink attribute to a skb and align it * @skb: socket buffer to add attribute to * @attrtype: attribute type * @njiffies: number of jiffies to convert to msecs * @padattr: attribute type for the padding */ static inline int nla_put_msecs(struct sk_buff *skb, int attrtype, unsigned long njiffies, int padattr) { u64 tmp = jiffies_to_msecs(njiffies); return nla_put_64bit(skb, attrtype, sizeof(u64), &tmp, padattr); } /** * nla_put_in_addr - Add an IPv4 address netlink attribute to a socket * buffer * @skb: socket buffer to add attribute to * @attrtype: attribute type * @addr: IPv4 address */ static inline int nla_put_in_addr(struct sk_buff *skb, int attrtype, __be32 addr) { __be32 tmp = addr; return nla_put_be32(skb, attrtype, tmp); } /** * nla_put_in6_addr - Add an IPv6 address netlink attribute to a socket * buffer * @skb: socket buffer to add attribute to * @attrtype: attribute type * @addr: IPv6 address */ static inline int nla_put_in6_addr(struct sk_buff *skb, int attrtype, const struct in6_addr *addr) { return nla_put(skb, attrtype, sizeof(*addr), addr); } /** * nla_put_bitfield32 - Add a bitfield32 netlink attribute to a socket buffer * @skb: socket buffer to add attribute to * @attrtype: attribute type * @value: value carrying bits * @selector: selector of valid bits */ static inline int nla_put_bitfield32(struct sk_buff *skb, int attrtype, __u32 value, __u32 selector) { struct nla_bitfield32 tmp = { value, selector, }; return nla_put(skb, attrtype, sizeof(tmp), &tmp); } /** * nla_get_u32 - return payload of u32 attribute * @nla: u32 netlink attribute */ static inline u32 nla_get_u32(const struct nlattr *nla) { return *(u32 *) nla_data(nla); } /** * nla_get_u32_default - return payload of u32 attribute or default * @nla: u32 netlink attribute, may be %NULL * @defvalue: default value to use if @nla is %NULL * * Return: the value of the attribute, or the default value if not present */ static inline u32 nla_get_u32_default(const struct nlattr *nla, u32 defvalue) { if (!nla) return defvalue; return nla_get_u32(nla); } /** * nla_get_be32 - return payload of __be32 attribute * @nla: __be32 netlink attribute */ static inline __be32 nla_get_be32(const struct nlattr *nla) { return *(__be32 *) nla_data(nla); } /** * nla_get_be32_default - return payload of be32 attribute or default * @nla: __be32 netlink attribute, may be %NULL * @defvalue: default value to use if @nla is %NULL * * Return: the value of the attribute, or the default value if not present */ static inline __be32 nla_get_be32_default(const struct nlattr *nla, __be32 defvalue) { if (!nla) return defvalue; return nla_get_be32(nla); } /** * nla_get_le32 - return payload of __le32 attribute * @nla: __le32 netlink attribute */ static inline __le32 nla_get_le32(const struct nlattr *nla) { return *(__le32 *) nla_data(nla); } /** * nla_get_le32_default - return payload of le32 attribute or default * @nla: __le32 netlink attribute, may be %NULL * @defvalue: default value to use if @nla is %NULL * * Return: the value of the attribute, or the default value if not present */ static inline __le32 nla_get_le32_default(const struct nlattr *nla, __le32 defvalue) { if (!nla) return defvalue; return nla_get_le32(nla); } /** * nla_get_u16 - return payload of u16 attribute * @nla: u16 netlink attribute */ static inline u16 nla_get_u16(const struct nlattr *nla) { return *(u16 *) nla_data(nla); } /** * nla_get_u16_default - return payload of u16 attribute or default * @nla: u16 netlink attribute, may be %NULL * @defvalue: default value to use if @nla is %NULL * * Return: the value of the attribute, or the default value if not present */ static inline u16 nla_get_u16_default(const struct nlattr *nla, u16 defvalue) { if (!nla) return defvalue; return nla_get_u16(nla); } /** * nla_get_be16 - return payload of __be16 attribute * @nla: __be16 netlink attribute */ static inline __be16 nla_get_be16(const struct nlattr *nla) { return *(__be16 *) nla_data(nla); } /** * nla_get_be16_default - return payload of be16 attribute or default * @nla: __be16 netlink attribute, may be %NULL * @defvalue: default value to use if @nla is %NULL * * Return: the value of the attribute, or the default value if not present */ static inline __be16 nla_get_be16_default(const struct nlattr *nla, __be16 defvalue) { if (!nla) return defvalue; return nla_get_be16(nla); } /** * nla_get_le16 - return payload of __le16 attribute * @nla: __le16 netlink attribute */ static inline __le16 nla_get_le16(const struct nlattr *nla) { return *(__le16 *) nla_data(nla); } /** * nla_get_le16_default - return payload of le16 attribute or default * @nla: __le16 netlink attribute, may be %NULL * @defvalue: default value to use if @nla is %NULL * * Return: the value of the attribute, or the default value if not present */ static inline __le16 nla_get_le16_default(const struct nlattr *nla, __le16 defvalue) { if (!nla) return defvalue; return nla_get_le16(nla); } /** * nla_get_u8 - return payload of u8 attribute * @nla: u8 netlink attribute */ static inline u8 nla_get_u8(const struct nlattr *nla) { return *(u8 *) nla_data(nla); } /** * nla_get_u8_default - return payload of u8 attribute or default * @nla: u8 netlink attribute, may be %NULL * @defvalue: default value to use if @nla is %NULL * * Return: the value of the attribute, or the default value if not present */ static inline u8 nla_get_u8_default(const struct nlattr *nla, u8 defvalue) { if (!nla) return defvalue; return nla_get_u8(nla); } /** * nla_get_u64 - return payload of u64 attribute * @nla: u64 netlink attribute */ static inline u64 nla_get_u64(const struct nlattr *nla) { u64 tmp; nla_memcpy(&tmp, nla, sizeof(tmp)); return tmp; } /** * nla_get_u64_default - return payload of u64 attribute or default * @nla: u64 netlink attribute, may be %NULL * @defvalue: default value to use if @nla is %NULL * * Return: the value of the attribute, or the default value if not present */ static inline u64 nla_get_u64_default(const struct nlattr *nla, u64 defvalue) { if (!nla) return defvalue; return nla_get_u64(nla); } /** * nla_get_uint - return payload of uint attribute * @nla: uint netlink attribute */ static inline u64 nla_get_uint(const struct nlattr *nla) { if (nla_len(nla) == sizeof(u32)) return nla_get_u32(nla); return nla_get_u64(nla); } /** * nla_get_uint_default - return payload of uint attribute or default * @nla: uint netlink attribute, may be %NULL * @defvalue: default value to use if @nla is %NULL * * Return: the value of the attribute, or the default value if not present */ static inline u64 nla_get_uint_default(const struct nlattr *nla, u64 defvalue) { if (!nla) return defvalue; return nla_get_uint(nla); } /** * nla_get_be64 - return payload of __be64 attribute * @nla: __be64 netlink attribute */ static inline __be64 nla_get_be64(const struct nlattr *nla) { __be64 tmp; nla_memcpy(&tmp, nla, sizeof(tmp)); return tmp; } /** * nla_get_be64_default - return payload of be64 attribute or default * @nla: __be64 netlink attribute, may be %NULL * @defvalue: default value to use if @nla is %NULL * * Return: the value of the attribute, or the default value if not present */ static inline __be64 nla_get_be64_default(const struct nlattr *nla, __be64 defvalue) { if (!nla) return defvalue; return nla_get_be64(nla); } /** * nla_get_le64 - return payload of __le64 attribute * @nla: __le64 netlink attribute */ static inline __le64 nla_get_le64(const struct nlattr *nla) { return *(__le64 *) nla_data(nla); } /** * nla_get_le64_default - return payload of le64 attribute or default * @nla: __le64 netlink attribute, may be %NULL * @defvalue: default value to use if @nla is %NULL * * Return: the value of the attribute, or the default value if not present */ static inline __le64 nla_get_le64_default(const struct nlattr *nla, __le64 defvalue) { if (!nla) return defvalue; return nla_get_le64(nla); } /** * nla_get_s32 - return payload of s32 attribute * @nla: s32 netlink attribute */ static inline s32 nla_get_s32(const struct nlattr *nla) { return *(s32 *) nla_data(nla); } /** * nla_get_s32_default - return payload of s32 attribute or default * @nla: s32 netlink attribute, may be %NULL * @defvalue: default value to use if @nla is %NULL * * Return: the value of the attribute, or the default value if not present */ static inline s32 nla_get_s32_default(const struct nlattr *nla, s32 defvalue) { if (!nla) return defvalue; return nla_get_s32(nla); } /** * nla_get_s16 - return payload of s16 attribute * @nla: s16 netlink attribute */ static inline s16 nla_get_s16(const struct nlattr *nla) { return *(s16 *) nla_data(nla); } /** * nla_get_s16_default - return payload of s16 attribute or default * @nla: s16 netlink attribute, may be %NULL * @defvalue: default value to use if @nla is %NULL * * Return: the value of the attribute, or the default value if not present */ static inline s16 nla_get_s16_default(const struct nlattr *nla, s16 defvalue) { if (!nla) return defvalue; return nla_get_s16(nla); } /** * nla_get_s8 - return payload of s8 attribute * @nla: s8 netlink attribute */ static inline s8 nla_get_s8(const struct nlattr *nla) { return *(s8 *) nla_data(nla); } /** * nla_get_s8_default - return payload of s8 attribute or default * @nla: s8 netlink attribute, may be %NULL * @defvalue: default value to use if @nla is %NULL * * Return: the value of the attribute, or the default value if not present */ static inline s8 nla_get_s8_default(const struct nlattr *nla, s8 defvalue) { if (!nla) return defvalue; return nla_get_s8(nla); } /** * nla_get_s64 - return payload of s64 attribute * @nla: s64 netlink attribute */ static inline s64 nla_get_s64(const struct nlattr *nla) { s64 tmp; nla_memcpy(&tmp, nla, sizeof(tmp)); return tmp; } /** * nla_get_s64_default - return payload of s64 attribute or default * @nla: s64 netlink attribute, may be %NULL * @defvalue: default value to use if @nla is %NULL * * Return: the value of the attribute, or the default value if not present */ static inline s64 nla_get_s64_default(const struct nlattr *nla, s64 defvalue) { if (!nla) return defvalue; return nla_get_s64(nla); } /** * nla_get_sint - return payload of uint attribute * @nla: uint netlink attribute */ static inline s64 nla_get_sint(const struct nlattr *nla) { if (nla_len(nla) == sizeof(s32)) return nla_get_s32(nla); return nla_get_s64(nla); } /** * nla_get_sint_default - return payload of sint attribute or default * @nla: sint netlink attribute, may be %NULL * @defvalue: default value to use if @nla is %NULL * * Return: the value of the attribute, or the default value if not present */ static inline s64 nla_get_sint_default(const struct nlattr *nla, s64 defvalue) { if (!nla) return defvalue; return nla_get_sint(nla); } /** * nla_get_flag - return payload of flag attribute * @nla: flag netlink attribute */ static inline int nla_get_flag(const struct nlattr *nla) { return !!nla; } /** * nla_get_msecs - return payload of msecs attribute * @nla: msecs netlink attribute * * Returns the number of milliseconds in jiffies. */ static inline unsigned long nla_get_msecs(const struct nlattr *nla) { u64 msecs = nla_get_u64(nla); return msecs_to_jiffies((unsigned long) msecs); } /** * nla_get_msecs_default - return payload of msecs attribute or default * @nla: msecs netlink attribute, may be %NULL * @defvalue: default value to use if @nla is %NULL * * Return: the value of the attribute, or the default value if not present */ static inline unsigned long nla_get_msecs_default(const struct nlattr *nla, unsigned long defvalue) { if (!nla) return defvalue; return nla_get_msecs(nla); } /** * nla_get_in_addr - return payload of IPv4 address attribute * @nla: IPv4 address netlink attribute */ static inline __be32 nla_get_in_addr(const struct nlattr *nla) { return *(__be32 *) nla_data(nla); } /** * nla_get_in_addr_default - return payload of be32 attribute or default * @nla: IPv4 address netlink attribute, may be %NULL * @defvalue: default value to use if @nla is %NULL * * Return: the value of the attribute, or the default value if not present */ static inline __be32 nla_get_in_addr_default(const struct nlattr *nla, __be32 defvalue) { if (!nla) return defvalue; return nla_get_in_addr(nla); } /** * nla_get_in6_addr - return payload of IPv6 address attribute * @nla: IPv6 address netlink attribute */ static inline struct in6_addr nla_get_in6_addr(const struct nlattr *nla) { struct in6_addr tmp; nla_memcpy(&tmp, nla, sizeof(tmp)); return tmp; } /** * nla_get_bitfield32 - return payload of 32 bitfield attribute * @nla: nla_bitfield32 attribute */ static inline struct nla_bitfield32 nla_get_bitfield32(const struct nlattr *nla) { struct nla_bitfield32 tmp; nla_memcpy(&tmp, nla, sizeof(tmp)); return tmp; } /** * nla_memdup - duplicate attribute memory (kmemdup) * @src: netlink attribute to duplicate from * @gfp: GFP mask */ static inline void *nla_memdup_noprof(const struct nlattr *src, gfp_t gfp) { return kmemdup_noprof(nla_data(src), nla_len(src), gfp); } #define nla_memdup(...) alloc_hooks(nla_memdup_noprof(__VA_ARGS__)) /** * nla_nest_start_noflag - Start a new level of nested attributes * @skb: socket buffer to add attributes to * @attrtype: attribute type of container * * This function exists for backward compatibility to use in APIs which never * marked their nest attributes with NLA_F_NESTED flag. New APIs should use * nla_nest_start() which sets the flag. * * Returns the container attribute or NULL on error */ static inline struct nlattr *nla_nest_start_noflag(struct sk_buff *skb, int attrtype) { struct nlattr *start = (struct nlattr *)skb_tail_pointer(skb); if (nla_put(skb, attrtype, 0, NULL) < 0) return NULL; return start; } /** * nla_nest_start - Start a new level of nested attributes, with NLA_F_NESTED * @skb: socket buffer to add attributes to * @attrtype: attribute type of container * * Unlike nla_nest_start_noflag(), mark the nest attribute with NLA_F_NESTED * flag. This is the preferred function to use in new code. * * Returns the container attribute or NULL on error */ static inline struct nlattr *nla_nest_start(struct sk_buff *skb, int attrtype) { return nla_nest_start_noflag(skb, attrtype | NLA_F_NESTED); } /** * nla_nest_end - Finalize nesting of attributes * @skb: socket buffer the attributes are stored in * @start: container attribute * * Corrects the container attribute header to include the all * appended attributes. * * Returns the total data length of the skb. */ static inline int nla_nest_end(struct sk_buff *skb, struct nlattr *start) { start->nla_len = skb_tail_pointer(skb) - (unsigned char *)start; return skb->len; } /** * nla_nest_cancel - Cancel nesting of attributes * @skb: socket buffer the message is stored in * @start: container attribute * * Removes the container attribute and including all nested * attributes. Returns -EMSGSIZE */ static inline void nla_nest_cancel(struct sk_buff *skb, struct nlattr *start) { nlmsg_trim(skb, start); } /** * __nla_validate_nested - Validate a stream of nested attributes * @start: container attribute * @maxtype: maximum attribute type to be expected * @policy: validation policy * @validate: validation strictness * @extack: extended ACK report struct * * Validates all attributes in the nested attribute stream against the * specified policy. Attributes with a type exceeding maxtype will be * ignored. See documentation of struct nla_policy for more details. * * Returns 0 on success or a negative error code. */ static inline int __nla_validate_nested(const struct nlattr *start, int maxtype, const struct nla_policy *policy, unsigned int validate, struct netlink_ext_ack *extack) { return __nla_validate(nla_data(start), nla_len(start), maxtype, policy, validate, extack); } static inline int nla_validate_nested(const struct nlattr *start, int maxtype, const struct nla_policy *policy, struct netlink_ext_ack *extack) { return __nla_validate_nested(start, maxtype, policy, NL_VALIDATE_STRICT, extack); } static inline int nla_validate_nested_deprecated(const struct nlattr *start, int maxtype, const struct nla_policy *policy, struct netlink_ext_ack *extack) { return __nla_validate_nested(start, maxtype, policy, NL_VALIDATE_LIBERAL, extack); } /** * nla_need_padding_for_64bit - test 64-bit alignment of the next attribute * @skb: socket buffer the message is stored in * * Return true if padding is needed to align the next attribute (nla_data()) to * a 64-bit aligned area. */ static inline bool nla_need_padding_for_64bit(struct sk_buff *skb) { #ifndef CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS /* The nlattr header is 4 bytes in size, that's why we test * if the skb->data _is_ aligned. A NOP attribute, plus * nlattr header for next attribute, will make nla_data() * 8-byte aligned. */ if (IS_ALIGNED((unsigned long)skb_tail_pointer(skb), 8)) return true; #endif return false; } /** * nla_align_64bit - 64-bit align the nla_data() of next attribute * @skb: socket buffer the message is stored in * @padattr: attribute type for the padding * * Conditionally emit a padding netlink attribute in order to make * the next attribute we emit have a 64-bit aligned nla_data() area. * This will only be done in architectures which do not have * CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS defined. * * Returns zero on success or a negative error code. */ static inline int nla_align_64bit(struct sk_buff *skb, int padattr) { if (nla_need_padding_for_64bit(skb) && !nla_reserve(skb, padattr, 0)) return -EMSGSIZE; return 0; } /** * nla_total_size_64bit - total length of attribute including padding * @payload: length of payload */ static inline int nla_total_size_64bit(int payload) { return NLA_ALIGN(nla_attr_size(payload)) #ifndef CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS + NLA_ALIGN(nla_attr_size(0)) #endif ; } /** * nla_for_each_attr - iterate over a stream of attributes * @pos: loop counter, set to current attribute * @head: head of attribute stream * @len: length of attribute stream * @rem: initialized to len, holds bytes currently remaining in stream */ #define nla_for_each_attr(pos, head, len, rem) \ for (pos = head, rem = len; \ nla_ok(pos, rem); \ pos = nla_next(pos, &(rem))) /** * nla_for_each_attr_type - iterate over a stream of attributes * @pos: loop counter, set to current attribute * @type: required attribute type for @pos * @head: head of attribute stream * @len: length of attribute stream * @rem: initialized to len, holds bytes currently remaining in stream */ #define nla_for_each_attr_type(pos, type, head, len, rem) \ nla_for_each_attr(pos, head, len, rem) \ if (nla_type(pos) == type) /** * nla_for_each_nested - iterate over nested attributes * @pos: loop counter, set to current attribute * @nla: attribute containing the nested attributes * @rem: initialized to len, holds bytes currently remaining in stream */ #define nla_for_each_nested(pos, nla, rem) \ nla_for_each_attr(pos, nla_data(nla), nla_len(nla), rem) /** * nla_for_each_nested_type - iterate over nested attributes * @pos: loop counter, set to current attribute * @type: required attribute type for @pos * @nla: attribute containing the nested attributes * @rem: initialized to len, holds bytes currently remaining in stream */ #define nla_for_each_nested_type(pos, type, nla, rem) \ nla_for_each_nested(pos, nla, rem) \ if (nla_type(pos) == type) /** * nla_is_last - Test if attribute is last in stream * @nla: attribute to test * @rem: bytes remaining in stream */ static inline bool nla_is_last(const struct nlattr *nla, int rem) { return nla->nla_len == rem; } void nla_get_range_unsigned(const struct nla_policy *pt, struct netlink_range_validation *range); void nla_get_range_signed(const struct nla_policy *pt, struct netlink_range_validation_signed *range); struct netlink_policy_dump_state; int netlink_policy_dump_add_policy(struct netlink_policy_dump_state **pstate, const struct nla_policy *policy, unsigned int maxtype); int netlink_policy_dump_get_policy_idx(struct netlink_policy_dump_state *state, const struct nla_policy *policy, unsigned int maxtype); bool netlink_policy_dump_loop(struct netlink_policy_dump_state *state); int netlink_policy_dump_write(struct sk_buff *skb, struct netlink_policy_dump_state *state); int netlink_policy_dump_attr_size_estimate(const struct nla_policy *pt); int netlink_policy_dump_write_attr(struct sk_buff *skb, const struct nla_policy *pt, int nestattr); void netlink_policy_dump_free(struct netlink_policy_dump_state *state); #endif |
| 1046 1083 737 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef __ASM_ALTERNATIVE_MACROS_H #define __ASM_ALTERNATIVE_MACROS_H #include <linux/const.h> #include <vdso/bits.h> #include <asm/cpucaps.h> #include <asm/insn-def.h> /* * Binutils 2.27.0 can't handle a 'UL' suffix on constants, so for the assembly * macros below we must use we must use `(1 << ARM64_CB_SHIFT)`. */ #define ARM64_CB_SHIFT 15 #define ARM64_CB_BIT BIT(ARM64_CB_SHIFT) #if ARM64_NCAPS >= ARM64_CB_BIT #error "cpucaps have overflown ARM64_CB_BIT" #endif #ifndef __ASSEMBLY__ #include <linux/stringify.h> #define ALTINSTR_ENTRY(cpucap) \ " .word 661b - .\n" /* label */ \ " .word 663f - .\n" /* new instruction */ \ " .hword " __stringify(cpucap) "\n" /* cpucap */ \ " .byte 662b-661b\n" /* source len */ \ " .byte 664f-663f\n" /* replacement len */ #define ALTINSTR_ENTRY_CB(cpucap, cb) \ " .word 661b - .\n" /* label */ \ " .word " __stringify(cb) "- .\n" /* callback */ \ " .hword " __stringify(cpucap) "\n" /* cpucap */ \ " .byte 662b-661b\n" /* source len */ \ " .byte 664f-663f\n" /* replacement len */ /* * alternative assembly primitive: * * If any of these .org directive fail, it means that insn1 and insn2 * don't have the same length. This used to be written as * * .if ((664b-663b) != (662b-661b)) * .error "Alternatives instruction length mismatch" * .endif * * but most assemblers die if insn1 or insn2 have a .inst. This should * be fixed in a binutils release posterior to 2.25.51.0.2 (anything * containing commit 4e4d08cf7399b606 or c1baaddf8861). * * Alternatives with callbacks do not generate replacement instructions. */ #define __ALTERNATIVE_CFG(oldinstr, newinstr, cpucap, cfg_enabled) \ ".if "__stringify(cfg_enabled)" == 1\n" \ "661:\n\t" \ oldinstr "\n" \ "662:\n" \ ".pushsection .altinstructions,\"a\"\n" \ ALTINSTR_ENTRY(cpucap) \ ".popsection\n" \ ".subsection 1\n" \ "663:\n\t" \ newinstr "\n" \ "664:\n\t" \ ".org . - (664b-663b) + (662b-661b)\n\t" \ ".org . - (662b-661b) + (664b-663b)\n\t" \ ".previous\n" \ ".endif\n" #define __ALTERNATIVE_CFG_CB(oldinstr, cpucap, cfg_enabled, cb) \ ".if "__stringify(cfg_enabled)" == 1\n" \ "661:\n\t" \ oldinstr "\n" \ "662:\n" \ ".pushsection .altinstructions,\"a\"\n" \ ALTINSTR_ENTRY_CB(cpucap, cb) \ ".popsection\n" \ "663:\n\t" \ "664:\n\t" \ ".endif\n" #define _ALTERNATIVE_CFG(oldinstr, newinstr, cpucap, cfg, ...) \ __ALTERNATIVE_CFG(oldinstr, newinstr, cpucap, IS_ENABLED(cfg)) #define ALTERNATIVE_CB(oldinstr, cpucap, cb) \ __ALTERNATIVE_CFG_CB(oldinstr, (1 << ARM64_CB_SHIFT) | (cpucap), 1, cb) #else #include <asm/assembler.h> .macro altinstruction_entry orig_offset alt_offset cpucap orig_len alt_len .word \orig_offset - . .word \alt_offset - . .hword (\cpucap) .byte \orig_len .byte \alt_len .endm .macro alternative_insn insn1, insn2, cap, enable = 1 .if \enable 661: \insn1 662: .pushsection .altinstructions, "a" altinstruction_entry 661b, 663f, \cap, 662b-661b, 664f-663f .popsection .subsection 1 663: \insn2 664: .org . - (664b-663b) + (662b-661b) .org . - (662b-661b) + (664b-663b) .previous .endif .endm /* * Alternative sequences * * The code for the case where the capability is not present will be * assembled and linked as normal. There are no restrictions on this * code. * * The code for the case where the capability is present will be * assembled into a special section to be used for dynamic patching. * Code for that case must: * * 1. Be exactly the same length (in bytes) as the default code * sequence. * * 2. Not contain a branch target that is used outside of the * alternative sequence it is defined in (branches into an * alternative sequence are not fixed up). */ /* * Begin an alternative code sequence. */ .macro alternative_if_not cap .set .Lasm_alt_mode, 0 .pushsection .altinstructions, "a" altinstruction_entry 661f, 663f, \cap, 662f-661f, 664f-663f .popsection 661: .endm .macro alternative_if cap .set .Lasm_alt_mode, 1 .pushsection .altinstructions, "a" altinstruction_entry 663f, 661f, \cap, 664f-663f, 662f-661f .popsection .subsection 1 .align 2 /* So GAS knows label 661 is suitably aligned */ 661: .endm .macro alternative_cb cap, cb .set .Lasm_alt_mode, 0 .pushsection .altinstructions, "a" altinstruction_entry 661f, \cb, (1 << ARM64_CB_SHIFT) | \cap, 662f-661f, 0 .popsection 661: .endm /* * Provide the other half of the alternative code sequence. */ .macro alternative_else 662: .if .Lasm_alt_mode==0 .subsection 1 .else .previous .endif 663: .endm /* * Complete an alternative code sequence. */ .macro alternative_endif 664: .org . - (664b-663b) + (662b-661b) .org . - (662b-661b) + (664b-663b) .if .Lasm_alt_mode==0 .previous .endif .endm /* * Callback-based alternative epilogue */ .macro alternative_cb_end 662: .endm /* * Provides a trivial alternative or default sequence consisting solely * of NOPs. The number of NOPs is chosen automatically to match the * previous case. */ .macro alternative_else_nop_endif alternative_else nops (662b-661b) / AARCH64_INSN_SIZE alternative_endif .endm #define _ALTERNATIVE_CFG(insn1, insn2, cap, cfg, ...) \ alternative_insn insn1, insn2, cap, IS_ENABLED(cfg) #endif /* __ASSEMBLY__ */ /* * Usage: asm(ALTERNATIVE(oldinstr, newinstr, cpucap)); * * Usage: asm(ALTERNATIVE(oldinstr, newinstr, cpucap, CONFIG_FOO)); * N.B. If CONFIG_FOO is specified, but not selected, the whole block * will be omitted, including oldinstr. */ #define ALTERNATIVE(oldinstr, newinstr, ...) \ _ALTERNATIVE_CFG(oldinstr, newinstr, __VA_ARGS__, 1) #ifndef __ASSEMBLY__ #include <linux/types.h> static __always_inline bool alternative_has_cap_likely(const unsigned long cpucap) { if (!cpucap_is_possible(cpucap)) return false; asm goto( #ifdef BUILD_VDSO ALTERNATIVE("b %l[l_no]", "nop", %[cpucap]) #else ALTERNATIVE_CB("b %l[l_no]", %[cpucap], alt_cb_patch_nops) #endif : : [cpucap] "i" (cpucap) : : l_no); return true; l_no: return false; } static __always_inline bool alternative_has_cap_unlikely(const unsigned long cpucap) { if (!cpucap_is_possible(cpucap)) return false; asm goto( ALTERNATIVE("nop", "b %l[l_yes]", %[cpucap]) : : [cpucap] "i" (cpucap) : : l_yes); return false; l_yes: return true; } #endif /* __ASSEMBLY__ */ #endif /* __ASM_ALTERNATIVE_MACROS_H */ |
| 977 982 976 977 982 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 | // SPDX-License-Identifier: GPL-2.0 /* * security/tomoyo/domain.c * * Copyright (C) 2005-2011 NTT DATA CORPORATION */ #include "common.h" #include <linux/binfmts.h> #include <linux/slab.h> #include <linux/rculist.h> /* Variables definitions.*/ /* The initial domain. */ struct tomoyo_domain_info tomoyo_kernel_domain; /** * tomoyo_update_policy - Update an entry for exception policy. * * @new_entry: Pointer to "struct tomoyo_acl_info". * @size: Size of @new_entry in bytes. * @param: Pointer to "struct tomoyo_acl_param". * @check_duplicate: Callback function to find duplicated entry. * * Returns 0 on success, negative value otherwise. * * Caller holds tomoyo_read_lock(). */ int tomoyo_update_policy(struct tomoyo_acl_head *new_entry, const int size, struct tomoyo_acl_param *param, bool (*check_duplicate)(const struct tomoyo_acl_head *, const struct tomoyo_acl_head *)) { int error = param->is_delete ? -ENOENT : -ENOMEM; struct tomoyo_acl_head *entry; struct list_head *list = param->list; if (mutex_lock_interruptible(&tomoyo_policy_lock)) return -ENOMEM; list_for_each_entry_rcu(entry, list, list, srcu_read_lock_held(&tomoyo_ss)) { if (entry->is_deleted == TOMOYO_GC_IN_PROGRESS) continue; if (!check_duplicate(entry, new_entry)) continue; entry->is_deleted = param->is_delete; error = 0; break; } if (error && !param->is_delete) { entry = tomoyo_commit_ok(new_entry, size); if (entry) { list_add_tail_rcu(&entry->list, list); error = 0; } } mutex_unlock(&tomoyo_policy_lock); return error; } /** * tomoyo_same_acl_head - Check for duplicated "struct tomoyo_acl_info" entry. * * @a: Pointer to "struct tomoyo_acl_info". * @b: Pointer to "struct tomoyo_acl_info". * * Returns true if @a == @b, false otherwise. */ static inline bool tomoyo_same_acl_head(const struct tomoyo_acl_info *a, const struct tomoyo_acl_info *b) { return a->type == b->type && a->cond == b->cond; } /** * tomoyo_update_domain - Update an entry for domain policy. * * @new_entry: Pointer to "struct tomoyo_acl_info". * @size: Size of @new_entry in bytes. * @param: Pointer to "struct tomoyo_acl_param". * @check_duplicate: Callback function to find duplicated entry. * @merge_duplicate: Callback function to merge duplicated entry. * * Returns 0 on success, negative value otherwise. * * Caller holds tomoyo_read_lock(). */ int tomoyo_update_domain(struct tomoyo_acl_info *new_entry, const int size, struct tomoyo_acl_param *param, bool (*check_duplicate)(const struct tomoyo_acl_info *, const struct tomoyo_acl_info *), bool (*merge_duplicate)(struct tomoyo_acl_info *, struct tomoyo_acl_info *, const bool)) { const bool is_delete = param->is_delete; int error = is_delete ? -ENOENT : -ENOMEM; struct tomoyo_acl_info *entry; struct list_head * const list = param->list; if (param->data[0]) { new_entry->cond = tomoyo_get_condition(param); if (!new_entry->cond) return -EINVAL; /* * Domain transition preference is allowed for only * "file execute" entries. */ if (new_entry->cond->transit && !(new_entry->type == TOMOYO_TYPE_PATH_ACL && container_of(new_entry, struct tomoyo_path_acl, head) ->perm == 1 << TOMOYO_TYPE_EXECUTE)) goto out; } if (mutex_lock_interruptible(&tomoyo_policy_lock)) goto out; list_for_each_entry_rcu(entry, list, list, srcu_read_lock_held(&tomoyo_ss)) { if (entry->is_deleted == TOMOYO_GC_IN_PROGRESS) continue; if (!tomoyo_same_acl_head(entry, new_entry) || !check_duplicate(entry, new_entry)) continue; if (merge_duplicate) entry->is_deleted = merge_duplicate(entry, new_entry, is_delete); else entry->is_deleted = is_delete; error = 0; break; } if (error && !is_delete) { entry = tomoyo_commit_ok(new_entry, size); if (entry) { list_add_tail_rcu(&entry->list, list); error = 0; } } mutex_unlock(&tomoyo_policy_lock); out: tomoyo_put_condition(new_entry->cond); return error; } /** * tomoyo_check_acl - Do permission check. * * @r: Pointer to "struct tomoyo_request_info". * @check_entry: Callback function to check type specific parameters. * * Returns 0 on success, negative value otherwise. * * Caller holds tomoyo_read_lock(). */ void tomoyo_check_acl(struct tomoyo_request_info *r, bool (*check_entry)(struct tomoyo_request_info *, const struct tomoyo_acl_info *)) { const struct tomoyo_domain_info *domain = r->domain; struct tomoyo_acl_info *ptr; const struct list_head *list = &domain->acl_info_list; u16 i = 0; retry: list_for_each_entry_rcu(ptr, list, list, srcu_read_lock_held(&tomoyo_ss)) { if (ptr->is_deleted || ptr->type != r->param_type) continue; if (!check_entry(r, ptr)) continue; if (!tomoyo_condition(r, ptr->cond)) continue; r->matched_acl = ptr; r->granted = true; return; } for (; i < TOMOYO_MAX_ACL_GROUPS; i++) { if (!test_bit(i, domain->group)) continue; list = &domain->ns->acl_group[i++]; goto retry; } r->granted = false; } /* The list for "struct tomoyo_domain_info". */ LIST_HEAD(tomoyo_domain_list); /** * tomoyo_last_word - Get last component of a domainname. * * @name: Domainname to check. * * Returns the last word of @domainname. */ static const char *tomoyo_last_word(const char *name) { const char *cp = strrchr(name, ' '); if (cp) return cp + 1; return name; } /** * tomoyo_same_transition_control - Check for duplicated "struct tomoyo_transition_control" entry. * * @a: Pointer to "struct tomoyo_acl_head". * @b: Pointer to "struct tomoyo_acl_head". * * Returns true if @a == @b, false otherwise. */ static bool tomoyo_same_transition_control(const struct tomoyo_acl_head *a, const struct tomoyo_acl_head *b) { const struct tomoyo_transition_control *p1 = container_of(a, typeof(*p1), head); const struct tomoyo_transition_control *p2 = container_of(b, typeof(*p2), head); return p1->type == p2->type && p1->is_last_name == p2->is_last_name && p1->domainname == p2->domainname && p1->program == p2->program; } /** * tomoyo_write_transition_control - Write "struct tomoyo_transition_control" list. * * @param: Pointer to "struct tomoyo_acl_param". * @type: Type of this entry. * * Returns 0 on success, negative value otherwise. */ int tomoyo_write_transition_control(struct tomoyo_acl_param *param, const u8 type) { struct tomoyo_transition_control e = { .type = type }; int error = param->is_delete ? -ENOENT : -ENOMEM; char *program = param->data; char *domainname = strstr(program, " from "); if (domainname) { *domainname = '\0'; domainname += 6; } else if (type == TOMOYO_TRANSITION_CONTROL_NO_KEEP || type == TOMOYO_TRANSITION_CONTROL_KEEP) { domainname = program; program = NULL; } if (program && strcmp(program, "any")) { if (!tomoyo_correct_path(program)) return -EINVAL; e.program = tomoyo_get_name(program); if (!e.program) goto out; } if (domainname && strcmp(domainname, "any")) { if (!tomoyo_correct_domain(domainname)) { if (!tomoyo_correct_path(domainname)) goto out; e.is_last_name = true; } e.domainname = tomoyo_get_name(domainname); if (!e.domainname) goto out; } param->list = ¶m->ns->policy_list[TOMOYO_ID_TRANSITION_CONTROL]; error = tomoyo_update_policy(&e.head, sizeof(e), param, tomoyo_same_transition_control); out: tomoyo_put_name(e.domainname); tomoyo_put_name(e.program); return error; } /** * tomoyo_scan_transition - Try to find specific domain transition type. * * @list: Pointer to "struct list_head". * @domainname: The name of current domain. * @program: The name of requested program. * @last_name: The last component of @domainname. * @type: One of values in "enum tomoyo_transition_type". * * Returns true if found one, false otherwise. * * Caller holds tomoyo_read_lock(). */ static inline bool tomoyo_scan_transition (const struct list_head *list, const struct tomoyo_path_info *domainname, const struct tomoyo_path_info *program, const char *last_name, const enum tomoyo_transition_type type) { const struct tomoyo_transition_control *ptr; list_for_each_entry_rcu(ptr, list, head.list, srcu_read_lock_held(&tomoyo_ss)) { if (ptr->head.is_deleted || ptr->type != type) continue; if (ptr->domainname) { if (!ptr->is_last_name) { if (ptr->domainname != domainname) continue; } else { /* * Use direct strcmp() since this is * unlikely used. */ if (strcmp(ptr->domainname->name, last_name)) continue; } } if (ptr->program && tomoyo_pathcmp(ptr->program, program)) continue; return true; } return false; } /** * tomoyo_transition_type - Get domain transition type. * * @ns: Pointer to "struct tomoyo_policy_namespace". * @domainname: The name of current domain. * @program: The name of requested program. * * Returns TOMOYO_TRANSITION_CONTROL_TRANSIT if executing @program causes * domain transition across namespaces, TOMOYO_TRANSITION_CONTROL_INITIALIZE if * executing @program reinitializes domain transition within that namespace, * TOMOYO_TRANSITION_CONTROL_KEEP if executing @program stays at @domainname , * others otherwise. * * Caller holds tomoyo_read_lock(). */ static enum tomoyo_transition_type tomoyo_transition_type (const struct tomoyo_policy_namespace *ns, const struct tomoyo_path_info *domainname, const struct tomoyo_path_info *program) { const char *last_name = tomoyo_last_word(domainname->name); enum tomoyo_transition_type type = TOMOYO_TRANSITION_CONTROL_NO_RESET; while (type < TOMOYO_MAX_TRANSITION_TYPE) { const struct list_head * const list = &ns->policy_list[TOMOYO_ID_TRANSITION_CONTROL]; if (!tomoyo_scan_transition(list, domainname, program, last_name, type)) { type++; continue; } if (type != TOMOYO_TRANSITION_CONTROL_NO_RESET && type != TOMOYO_TRANSITION_CONTROL_NO_INITIALIZE) break; /* * Do not check for reset_domain if no_reset_domain matched. * Do not check for initialize_domain if no_initialize_domain * matched. */ type++; type++; } return type; } /** * tomoyo_same_aggregator - Check for duplicated "struct tomoyo_aggregator" entry. * * @a: Pointer to "struct tomoyo_acl_head". * @b: Pointer to "struct tomoyo_acl_head". * * Returns true if @a == @b, false otherwise. */ static bool tomoyo_same_aggregator(const struct tomoyo_acl_head *a, const struct tomoyo_acl_head *b) { const struct tomoyo_aggregator *p1 = container_of(a, typeof(*p1), head); const struct tomoyo_aggregator *p2 = container_of(b, typeof(*p2), head); return p1->original_name == p2->original_name && p1->aggregated_name == p2->aggregated_name; } /** * tomoyo_write_aggregator - Write "struct tomoyo_aggregator" list. * * @param: Pointer to "struct tomoyo_acl_param". * * Returns 0 on success, negative value otherwise. * * Caller holds tomoyo_read_lock(). */ int tomoyo_write_aggregator(struct tomoyo_acl_param *param) { struct tomoyo_aggregator e = { }; int error = param->is_delete ? -ENOENT : -ENOMEM; const char *original_name = tomoyo_read_token(param); const char *aggregated_name = tomoyo_read_token(param); if (!tomoyo_correct_word(original_name) || !tomoyo_correct_path(aggregated_name)) return -EINVAL; e.original_name = tomoyo_get_name(original_name); e.aggregated_name = tomoyo_get_name(aggregated_name); if (!e.original_name || !e.aggregated_name || e.aggregated_name->is_patterned) /* No patterns allowed. */ goto out; param->list = ¶m->ns->policy_list[TOMOYO_ID_AGGREGATOR]; error = tomoyo_update_policy(&e.head, sizeof(e), param, tomoyo_same_aggregator); out: tomoyo_put_name(e.original_name); tomoyo_put_name(e.aggregated_name); return error; } /** * tomoyo_find_namespace - Find specified namespace. * * @name: Name of namespace to find. * @len: Length of @name. * * Returns pointer to "struct tomoyo_policy_namespace" if found, * NULL otherwise. * * Caller holds tomoyo_read_lock(). */ static struct tomoyo_policy_namespace *tomoyo_find_namespace (const char *name, const unsigned int len) { struct tomoyo_policy_namespace *ns; list_for_each_entry(ns, &tomoyo_namespace_list, namespace_list) { if (strncmp(name, ns->name, len) || (name[len] && name[len] != ' ')) continue; return ns; } return NULL; } /** * tomoyo_assign_namespace - Create a new namespace. * * @domainname: Name of namespace to create. * * Returns pointer to "struct tomoyo_policy_namespace" on success, * NULL otherwise. * * Caller holds tomoyo_read_lock(). */ struct tomoyo_policy_namespace *tomoyo_assign_namespace(const char *domainname) { struct tomoyo_policy_namespace *ptr; struct tomoyo_policy_namespace *entry; const char *cp = domainname; unsigned int len = 0; while (*cp && *cp++ != ' ') len++; ptr = tomoyo_find_namespace(domainname, len); if (ptr) return ptr; if (len >= TOMOYO_EXEC_TMPSIZE - 10 || !tomoyo_domain_def(domainname)) return NULL; entry = kzalloc(sizeof(*entry) + len + 1, GFP_NOFS | __GFP_NOWARN); if (mutex_lock_interruptible(&tomoyo_policy_lock)) goto out; ptr = tomoyo_find_namespace(domainname, len); if (!ptr && tomoyo_memory_ok(entry)) { char *name = (char *) (entry + 1); ptr = entry; memmove(name, domainname, len); name[len] = '\0'; entry->name = name; tomoyo_init_policy_namespace(entry); entry = NULL; } mutex_unlock(&tomoyo_policy_lock); out: kfree(entry); return ptr; } /** * tomoyo_namespace_jump - Check for namespace jump. * * @domainname: Name of domain. * * Returns true if namespace differs, false otherwise. */ static bool tomoyo_namespace_jump(const char *domainname) { const char *namespace = tomoyo_current_namespace()->name; const int len = strlen(namespace); return strncmp(domainname, namespace, len) || (domainname[len] && domainname[len] != ' '); } /** * tomoyo_assign_domain - Create a domain or a namespace. * * @domainname: The name of domain. * @transit: True if transit to domain found or created. * * Returns pointer to "struct tomoyo_domain_info" on success, NULL otherwise. * * Caller holds tomoyo_read_lock(). */ struct tomoyo_domain_info *tomoyo_assign_domain(const char *domainname, const bool transit) { struct tomoyo_domain_info e = { }; struct tomoyo_domain_info *entry = tomoyo_find_domain(domainname); bool created = false; if (entry) { if (transit) { /* * Since namespace is created at runtime, profiles may * not be created by the moment the process transits to * that domain. Do not perform domain transition if * profile for that domain is not yet created. */ if (tomoyo_policy_loaded && !entry->ns->profile_ptr[entry->profile]) return NULL; } return entry; } /* Requested domain does not exist. */ /* Don't create requested domain if domainname is invalid. */ if (strlen(domainname) >= TOMOYO_EXEC_TMPSIZE - 10 || !tomoyo_correct_domain(domainname)) return NULL; /* * Since definition of profiles and acl_groups may differ across * namespaces, do not inherit "use_profile" and "use_group" settings * by automatically creating requested domain upon domain transition. */ if (transit && tomoyo_namespace_jump(domainname)) return NULL; e.ns = tomoyo_assign_namespace(domainname); if (!e.ns) return NULL; /* * "use_profile" and "use_group" settings for automatically created * domains are inherited from current domain. These are 0 for manually * created domains. */ if (transit) { const struct tomoyo_domain_info *domain = tomoyo_domain(); e.profile = domain->profile; memcpy(e.group, domain->group, sizeof(e.group)); } e.domainname = tomoyo_get_name(domainname); if (!e.domainname) return NULL; if (mutex_lock_interruptible(&tomoyo_policy_lock)) goto out; entry = tomoyo_find_domain(domainname); if (!entry) { entry = tomoyo_commit_ok(&e, sizeof(e)); if (entry) { INIT_LIST_HEAD(&entry->acl_info_list); list_add_tail_rcu(&entry->list, &tomoyo_domain_list); created = true; } } mutex_unlock(&tomoyo_policy_lock); out: tomoyo_put_name(e.domainname); if (entry && transit) { if (created) { struct tomoyo_request_info r; int i; tomoyo_init_request_info(&r, entry, TOMOYO_MAC_FILE_EXECUTE); r.granted = false; tomoyo_write_log(&r, "use_profile %u\n", entry->profile); for (i = 0; i < TOMOYO_MAX_ACL_GROUPS; i++) if (test_bit(i, entry->group)) tomoyo_write_log(&r, "use_group %u\n", i); tomoyo_update_stat(TOMOYO_STAT_POLICY_UPDATES); } } return entry; } /** * tomoyo_environ - Check permission for environment variable names. * * @ee: Pointer to "struct tomoyo_execve". * * Returns 0 on success, negative value otherwise. */ static int tomoyo_environ(struct tomoyo_execve *ee) { struct tomoyo_request_info *r = &ee->r; struct linux_binprm *bprm = ee->bprm; /* env_page.data is allocated by tomoyo_dump_page(). */ struct tomoyo_page_dump env_page = { }; char *arg_ptr; /* Size is TOMOYO_EXEC_TMPSIZE bytes */ int arg_len = 0; unsigned long pos = bprm->p; int offset = pos % PAGE_SIZE; int argv_count = bprm->argc; int envp_count = bprm->envc; int error = -ENOMEM; ee->r.type = TOMOYO_MAC_ENVIRON; ee->r.profile = r->domain->profile; ee->r.mode = tomoyo_get_mode(r->domain->ns, ee->r.profile, TOMOYO_MAC_ENVIRON); if (!r->mode || !envp_count) return 0; arg_ptr = kzalloc(TOMOYO_EXEC_TMPSIZE, GFP_NOFS); if (!arg_ptr) goto out; while (error == -ENOMEM) { if (!tomoyo_dump_page(bprm, pos, &env_page)) goto out; pos += PAGE_SIZE - offset; /* Read. */ while (argv_count && offset < PAGE_SIZE) { if (!env_page.data[offset++]) argv_count--; } if (argv_count) { offset = 0; continue; } while (offset < PAGE_SIZE) { const unsigned char c = env_page.data[offset++]; if (c && arg_len < TOMOYO_EXEC_TMPSIZE - 10) { if (c == '=') { arg_ptr[arg_len++] = '\0'; } else if (c == '\\') { arg_ptr[arg_len++] = '\\'; arg_ptr[arg_len++] = '\\'; } else if (c > ' ' && c < 127) { arg_ptr[arg_len++] = c; } else { arg_ptr[arg_len++] = '\\'; arg_ptr[arg_len++] = (c >> 6) + '0'; arg_ptr[arg_len++] = ((c >> 3) & 7) + '0'; arg_ptr[arg_len++] = (c & 7) + '0'; } } else { arg_ptr[arg_len] = '\0'; } if (c) continue; if (tomoyo_env_perm(r, arg_ptr)) { error = -EPERM; break; } if (!--envp_count) { error = 0; break; } arg_len = 0; } offset = 0; } out: if (r->mode != TOMOYO_CONFIG_ENFORCING) error = 0; kfree(env_page.data); kfree(arg_ptr); return error; } /** * tomoyo_find_next_domain - Find a domain. * * @bprm: Pointer to "struct linux_binprm". * * Returns 0 on success, negative value otherwise. * * Caller holds tomoyo_read_lock(). */ int tomoyo_find_next_domain(struct linux_binprm *bprm) { struct tomoyo_domain_info *old_domain = tomoyo_domain(); struct tomoyo_domain_info *domain = NULL; const char *original_name = bprm->filename; int retval = -ENOMEM; bool reject_on_transition_failure = false; const struct tomoyo_path_info *candidate; struct tomoyo_path_info exename; struct tomoyo_execve *ee = kzalloc(sizeof(*ee), GFP_NOFS); if (!ee) return -ENOMEM; ee->tmp = kzalloc(TOMOYO_EXEC_TMPSIZE, GFP_NOFS); if (!ee->tmp) { kfree(ee); return -ENOMEM; } /* ee->dump->data is allocated by tomoyo_dump_page(). */ tomoyo_init_request_info(&ee->r, NULL, TOMOYO_MAC_FILE_EXECUTE); ee->r.ee = ee; ee->bprm = bprm; ee->r.obj = &ee->obj; ee->obj.path1 = bprm->file->f_path; /* Get symlink's pathname of program. */ exename.name = tomoyo_realpath_nofollow(original_name); if (!exename.name) { /* Fallback to realpath if symlink's pathname does not exist. */ exename.name = tomoyo_realpath_from_path(&bprm->file->f_path); if (!exename.name) goto out; } tomoyo_fill_path_info(&exename); retry: /* Check 'aggregator' directive. */ { struct tomoyo_aggregator *ptr; struct list_head *list = &old_domain->ns->policy_list[TOMOYO_ID_AGGREGATOR]; /* Check 'aggregator' directive. */ candidate = &exename; list_for_each_entry_rcu(ptr, list, head.list, srcu_read_lock_held(&tomoyo_ss)) { if (ptr->head.is_deleted || !tomoyo_path_matches_pattern(&exename, ptr->original_name)) continue; candidate = ptr->aggregated_name; break; } } /* Check execute permission. */ retval = tomoyo_execute_permission(&ee->r, candidate); if (retval == TOMOYO_RETRY_REQUEST) goto retry; if (retval < 0) goto out; /* * To be able to specify domainnames with wildcards, use the * pathname specified in the policy (which may contain * wildcard) rather than the pathname passed to execve() * (which never contains wildcard). */ if (ee->r.param.path.matched_path) candidate = ee->r.param.path.matched_path; /* * Check for domain transition preference if "file execute" matched. * If preference is given, make execve() fail if domain transition * has failed, for domain transition preference should be used with * destination domain defined. */ if (ee->transition) { const char *domainname = ee->transition->name; reject_on_transition_failure = true; if (!strcmp(domainname, "keep")) goto force_keep_domain; if (!strcmp(domainname, "child")) goto force_child_domain; if (!strcmp(domainname, "reset")) goto force_reset_domain; if (!strcmp(domainname, "initialize")) goto force_initialize_domain; if (!strcmp(domainname, "parent")) { char *cp; strscpy(ee->tmp, old_domain->domainname->name, TOMOYO_EXEC_TMPSIZE); cp = strrchr(ee->tmp, ' '); if (cp) *cp = '\0'; } else if (*domainname == '<') strscpy(ee->tmp, domainname, TOMOYO_EXEC_TMPSIZE); else snprintf(ee->tmp, TOMOYO_EXEC_TMPSIZE - 1, "%s %s", old_domain->domainname->name, domainname); goto force_jump_domain; } /* * No domain transition preference specified. * Calculate domain to transit to. */ switch (tomoyo_transition_type(old_domain->ns, old_domain->domainname, candidate)) { case TOMOYO_TRANSITION_CONTROL_RESET: force_reset_domain: /* Transit to the root of specified namespace. */ snprintf(ee->tmp, TOMOYO_EXEC_TMPSIZE - 1, "<%s>", candidate->name); /* * Make execve() fail if domain transition across namespaces * has failed. */ reject_on_transition_failure = true; break; case TOMOYO_TRANSITION_CONTROL_INITIALIZE: force_initialize_domain: /* Transit to the child of current namespace's root. */ snprintf(ee->tmp, TOMOYO_EXEC_TMPSIZE - 1, "%s %s", old_domain->ns->name, candidate->name); break; case TOMOYO_TRANSITION_CONTROL_KEEP: force_keep_domain: /* Keep current domain. */ domain = old_domain; break; default: if (old_domain == &tomoyo_kernel_domain && !tomoyo_policy_loaded) { /* * Needn't to transit from kernel domain before * starting /sbin/init. But transit from kernel domain * if executing initializers because they might start * before /sbin/init. */ domain = old_domain; break; } force_child_domain: /* Normal domain transition. */ snprintf(ee->tmp, TOMOYO_EXEC_TMPSIZE - 1, "%s %s", old_domain->domainname->name, candidate->name); break; } force_jump_domain: if (!domain) domain = tomoyo_assign_domain(ee->tmp, true); if (domain) retval = 0; else if (reject_on_transition_failure) { pr_warn("ERROR: Domain '%s' not ready.\n", ee->tmp); retval = -ENOMEM; } else if (ee->r.mode == TOMOYO_CONFIG_ENFORCING) retval = -ENOMEM; else { retval = 0; if (!old_domain->flags[TOMOYO_DIF_TRANSITION_FAILED]) { old_domain->flags[TOMOYO_DIF_TRANSITION_FAILED] = true; ee->r.granted = false; tomoyo_write_log(&ee->r, "%s", tomoyo_dif [TOMOYO_DIF_TRANSITION_FAILED]); pr_warn("ERROR: Domain '%s' not defined.\n", ee->tmp); } } out: if (!domain) domain = old_domain; /* Update reference count on "struct tomoyo_domain_info". */ { struct tomoyo_task *s = tomoyo_task(current); s->old_domain_info = s->domain_info; s->domain_info = domain; atomic_inc(&domain->users); } kfree(exename.name); if (!retval) { ee->r.domain = domain; retval = tomoyo_environ(ee); } kfree(ee->tmp); kfree(ee->dump.data); kfree(ee); return retval; } /** * tomoyo_dump_page - Dump a page to buffer. * * @bprm: Pointer to "struct linux_binprm". * @pos: Location to dump. * @dump: Pointer to "struct tomoyo_page_dump". * * Returns true on success, false otherwise. */ bool tomoyo_dump_page(struct linux_binprm *bprm, unsigned long pos, struct tomoyo_page_dump *dump) { struct page *page; #ifdef CONFIG_MMU int ret; #endif /* dump->data is released by tomoyo_find_next_domain(). */ if (!dump->data) { dump->data = kzalloc(PAGE_SIZE, GFP_NOFS); if (!dump->data) return false; } /* Same with get_arg_page(bprm, pos, 0) in fs/exec.c */ #ifdef CONFIG_MMU /* * This is called at execve() time in order to dig around * in the argv/environment of the new proceess * (represented by bprm). */ mmap_read_lock(bprm->mm); ret = get_user_pages_remote(bprm->mm, pos, 1, FOLL_FORCE, &page, NULL); mmap_read_unlock(bprm->mm); if (ret <= 0) return false; #else page = bprm->page[pos / PAGE_SIZE]; #endif if (page != dump->page) { const unsigned int offset = pos % PAGE_SIZE; /* * Maybe kmap()/kunmap() should be used here. * But remove_arg_zero() uses kmap_atomic()/kunmap_atomic(). * So do I. */ char *kaddr = kmap_atomic(page); dump->page = page; memcpy(dump->data + offset, kaddr + offset, PAGE_SIZE - offset); kunmap_atomic(kaddr); } /* Same with put_arg_page(page) in fs/exec.c */ #ifdef CONFIG_MMU put_page(page); #endif return true; } |
| 3 3 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 1522 1523 1524 1525 1526 1527 1528 1529 1530 1531 1532 1533 1534 1535 1536 1537 1538 1539 1540 1541 1542 1543 1544 1545 1546 1547 1548 1549 1550 1551 1552 1553 1554 1555 1556 1557 1558 1559 1560 1561 1562 1563 1564 1565 1566 1567 1568 1569 1570 1571 1572 1573 1574 1575 1576 1577 1578 1579 1580 1581 1582 1583 1584 1585 1586 1587 1588 1589 1590 1591 1592 1593 1594 1595 1596 1597 1598 1599 1600 1601 1602 1603 1604 1605 1606 1607 1608 1609 1610 1611 1612 1613 1614 1615 1616 1617 1618 1619 1620 1621 1622 1623 1624 1625 1626 1627 1628 1629 1630 1631 1632 1633 1634 1635 1636 1637 1638 1639 1640 1641 1642 1643 1644 1645 1646 1647 1648 1649 1650 1651 1652 1653 1654 1655 1656 1657 1658 1659 1660 1661 1662 1663 1664 1665 1666 1667 1668 1669 1670 1671 1672 1673 1674 1675 1676 1677 1678 1679 1680 1681 1682 1683 1684 1685 1686 1687 1688 1689 1690 1691 1692 1693 1694 1695 1696 1697 1698 1699 1700 1701 1702 1703 1704 1705 1706 1707 1708 1709 1710 1711 1712 1713 1714 1715 1716 1717 1718 1719 1720 1721 1722 1723 1724 1725 1726 1727 1728 1729 1730 1731 1732 1733 1734 1735 1736 1737 1738 1739 1740 1741 1742 1743 1744 1745 1746 1747 1748 1749 1750 1751 1752 1753 1754 1755 1756 1757 1758 1759 1760 1761 1762 1763 1764 1765 1766 1767 1768 1769 1770 1771 1772 1773 1774 1775 1776 1777 1778 1779 1780 1781 1782 1783 1784 1785 1786 1787 1788 1789 1790 1791 1792 1793 1794 1795 1796 1797 1798 1799 1800 1801 1802 1803 1804 1805 1806 1807 1808 1809 1810 1811 1812 1813 1814 1815 1816 1817 1818 1819 1820 1821 1822 1823 1824 1825 1826 1827 1828 1829 1830 1831 1832 1833 1834 1835 1836 1837 1838 1839 1840 1841 1842 1843 1844 1845 1846 1847 1848 1849 1850 1851 1852 1853 1854 1855 1856 1857 1858 1859 1860 1861 1862 1863 1864 1865 1866 1867 1868 1869 1870 1871 1872 1873 1874 1875 1876 1877 1878 1879 1880 1881 1882 1883 1884 1885 1886 1887 1888 1889 1890 1891 1892 1893 1894 1895 1896 1897 1898 1899 1900 1901 1902 1903 1904 1905 1906 1907 1908 1909 1910 1911 1912 1913 1914 1915 1916 1917 1918 1919 1920 1921 1922 1923 1924 1925 1926 1927 1928 1929 1930 1931 1932 1933 1934 1935 1936 1937 1938 1939 1940 1941 1942 1943 1944 1945 1946 1947 1948 1949 1950 1951 1952 1953 1954 1955 1956 1957 1958 1959 1960 1961 1962 1963 1964 1965 1966 1967 1968 1969 1970 1971 1972 1973 1974 1975 1976 1977 1978 1979 1980 1981 1982 1983 1984 1985 1986 1987 1988 1989 1990 1991 1992 1993 1994 1995 1996 1997 1998 1999 2000 2001 2002 2003 2004 2005 2006 2007 2008 2009 2010 2011 2012 2013 2014 2015 2016 2017 2018 2019 2020 2021 2022 2023 2024 2025 2026 2027 2028 2029 2030 2031 2032 2033 2034 2035 2036 2037 2038 2039 2040 2041 2042 2043 2044 2045 2046 2047 2048 2049 2050 2051 2052 2053 2054 2055 2056 2057 2058 2059 2060 2061 2062 2063 2064 2065 2066 2067 2068 2069 2070 2071 2072 2073 2074 2075 2076 2077 2078 2079 2080 2081 2082 2083 2084 2085 2086 2087 2088 2089 2090 2091 2092 2093 2094 2095 2096 2097 2098 2099 2100 2101 2102 2103 2104 2105 2106 2107 2108 2109 2110 2111 2112 2113 2114 2115 2116 2117 2118 2119 2120 2121 2122 2123 2124 2125 2126 2127 2128 2129 2130 2131 2132 2133 2134 2135 2136 2137 2138 2139 2140 2141 2142 2143 2144 2145 2146 2147 2148 2149 2150 2151 2152 2153 2154 2155 2156 2157 2158 2159 2160 2161 2162 2163 2164 2165 2166 2167 2168 2169 2170 2171 2172 2173 2174 2175 2176 2177 2178 2179 2180 2181 2182 2183 2184 2185 2186 2187 2188 2189 2190 2191 2192 2193 2194 2195 2196 2197 2198 2199 2200 2201 2202 2203 2204 2205 2206 2207 2208 2209 2210 2211 2212 2213 2214 2215 2216 2217 2218 2219 2220 2221 2222 2223 2224 2225 2226 2227 2228 2229 2230 2231 2232 2233 2234 2235 2236 2237 2238 2239 2240 2241 2242 2243 2244 2245 2246 2247 2248 2249 2250 2251 2252 2253 2254 2255 2256 2257 2258 2259 2260 2261 2262 2263 2264 2265 2266 2267 2268 2269 2270 2271 2272 2273 2274 2275 2276 2277 2278 2279 2280 2281 2282 2283 2284 2285 2286 2287 2288 2289 2290 2291 2292 2293 2294 2295 2296 2297 2298 2299 2300 2301 2302 2303 2304 2305 2306 2307 2308 2309 2310 2311 2312 2313 2314 2315 2316 2317 2318 2319 2320 2321 2322 2323 2324 2325 2326 2327 2328 2329 2330 2331 2332 2333 2334 2335 2336 2337 2338 2339 2340 2341 2342 2343 2344 2345 2346 2347 2348 2349 2350 2351 2352 2353 2354 2355 2356 2357 2358 2359 2360 2361 2362 2363 2364 2365 2366 2367 2368 2369 2370 2371 2372 2373 2374 2375 2376 2377 2378 2379 2380 2381 2382 2383 2384 2385 2386 2387 2388 2389 2390 2391 2392 2393 2394 2395 2396 2397 2398 2399 2400 2401 2402 2403 2404 2405 2406 2407 2408 2409 2410 2411 2412 2413 2414 2415 2416 2417 2418 2419 2420 2421 2422 2423 2424 2425 2426 2427 2428 2429 2430 2431 2432 2433 2434 2435 2436 2437 2438 2439 2440 2441 2442 2443 2444 2445 2446 2447 2448 2449 2450 2451 2452 2453 2454 2455 2456 2457 2458 2459 2460 2461 2462 2463 2464 2465 2466 2467 2468 2469 2470 2471 2472 2473 2474 2475 2476 2477 2478 2479 2480 2481 2482 2483 2484 2485 2486 2487 2488 2489 2490 2491 2492 2493 2494 2495 2496 2497 2498 2499 2500 2501 2502 2503 2504 2505 2506 2507 2508 2509 2510 2511 2512 2513 2514 2515 2516 2517 2518 2519 2520 2521 2522 2523 2524 2525 2526 2527 2528 2529 2530 2531 2532 2533 2534 2535 2536 2537 2538 2539 2540 2541 2542 2543 2544 2545 2546 2547 2548 2549 2550 2551 2552 2553 2554 2555 2556 2557 2558 2559 2560 2561 2562 2563 2564 2565 2566 2567 2568 2569 2570 2571 2572 2573 2574 2575 2576 2577 2578 2579 2580 2581 2582 2583 2584 2585 2586 2587 2588 2589 2590 2591 2592 2593 2594 2595 2596 2597 2598 2599 2600 2601 2602 2603 2604 2605 2606 2607 2608 2609 2610 2611 2612 2613 2614 2615 2616 2617 2618 2619 2620 2621 2622 2623 2624 2625 2626 2627 2628 2629 2630 2631 2632 2633 2634 2635 2636 2637 2638 2639 2640 2641 2642 2643 2644 2645 2646 2647 2648 2649 2650 2651 2652 2653 2654 2655 2656 2657 2658 2659 2660 2661 2662 2663 2664 2665 2666 2667 2668 2669 2670 2671 2672 2673 2674 2675 2676 2677 2678 2679 2680 2681 2682 2683 2684 2685 2686 2687 2688 2689 2690 2691 2692 2693 2694 2695 2696 2697 2698 2699 2700 2701 2702 2703 2704 2705 2706 2707 2708 2709 2710 2711 2712 2713 2714 2715 2716 2717 2718 2719 2720 2721 2722 2723 2724 2725 2726 | /* * Copyright (c) 2004 Topspin Communications. All rights reserved. * Copyright (c) 2005 Sun Microsystems, Inc. All rights reserved. * Copyright (c) 2004 Voltaire, Inc. All rights reserved. * * This software is available to you under a choice of one of two * licenses. You may choose to be licensed under the terms of the GNU * General Public License (GPL) Version 2, available from the file * COPYING in the main directory of this source tree, or the * OpenIB.org BSD license below: * * Redistribution and use in source and binary forms, with or * without modification, are permitted provided that the following * conditions are met: * * - Redistributions of source code must retain the above * copyright notice, this list of conditions and the following * disclaimer. * * - Redistributions in binary form must reproduce the above * copyright notice, this list of conditions and the following * disclaimer in the documentation and/or other materials * provided with the distribution. * * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND * NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS * BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN * ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN * CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE * SOFTWARE. */ #include "ipoib.h" #include <linux/module.h> #include <linux/init.h> #include <linux/slab.h> #include <linux/kernel.h> #include <linux/vmalloc.h> #include <linux/if_arp.h> /* For ARPHRD_xxx */ #include <linux/ip.h> #include <linux/in.h> #include <linux/jhash.h> #include <net/arp.h> #include <net/addrconf.h> #include <net/pkt_sched.h> #include <linux/inetdevice.h> #include <rdma/ib_cache.h> MODULE_AUTHOR("Roland Dreier"); MODULE_DESCRIPTION("IP-over-InfiniBand net driver"); MODULE_LICENSE("Dual BSD/GPL"); int ipoib_sendq_size __read_mostly = IPOIB_TX_RING_SIZE; int ipoib_recvq_size __read_mostly = IPOIB_RX_RING_SIZE; module_param_named(send_queue_size, ipoib_sendq_size, int, 0444); MODULE_PARM_DESC(send_queue_size, "Number of descriptors in send queue"); module_param_named(recv_queue_size, ipoib_recvq_size, int, 0444); MODULE_PARM_DESC(recv_queue_size, "Number of descriptors in receive queue"); #ifdef CONFIG_INFINIBAND_IPOIB_DEBUG int ipoib_debug_level; module_param_named(debug_level, ipoib_debug_level, int, 0644); MODULE_PARM_DESC(debug_level, "Enable debug tracing if > 0"); #endif struct ipoib_path_iter { struct net_device *dev; struct ipoib_path path; }; static const u8 ipv4_bcast_addr[] = { 0x00, 0xff, 0xff, 0xff, 0xff, 0x12, 0x40, 0x1b, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0xff, 0xff, 0xff, 0xff }; struct workqueue_struct *ipoib_workqueue; struct ib_sa_client ipoib_sa_client; static int ipoib_add_one(struct ib_device *device); static void ipoib_remove_one(struct ib_device *device, void *client_data); static void ipoib_neigh_reclaim(struct rcu_head *rp); static struct net_device *ipoib_get_net_dev_by_params( struct ib_device *dev, u32 port, u16 pkey, const union ib_gid *gid, const struct sockaddr *addr, void *client_data); static int ipoib_set_mac(struct net_device *dev, void *addr); static int ipoib_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd); static struct ib_client ipoib_client = { .name = "ipoib", .add = ipoib_add_one, .remove = ipoib_remove_one, .get_net_dev_by_params = ipoib_get_net_dev_by_params, }; #ifdef CONFIG_INFINIBAND_IPOIB_DEBUG static int ipoib_netdev_event(struct notifier_block *this, unsigned long event, void *ptr) { struct netdev_notifier_info *ni = ptr; struct net_device *dev = ni->dev; if (dev->netdev_ops->ndo_open != ipoib_open) return NOTIFY_DONE; switch (event) { case NETDEV_REGISTER: ipoib_create_debug_files(dev); break; case NETDEV_CHANGENAME: ipoib_delete_debug_files(dev); ipoib_create_debug_files(dev); break; case NETDEV_UNREGISTER: ipoib_delete_debug_files(dev); break; } return NOTIFY_DONE; } #endif int ipoib_open(struct net_device *dev) { struct ipoib_dev_priv *priv = ipoib_priv(dev); ipoib_dbg(priv, "bringing up interface\n"); netif_carrier_off(dev); set_bit(IPOIB_FLAG_ADMIN_UP, &priv->flags); if (ipoib_ib_dev_open(dev)) { if (!test_bit(IPOIB_PKEY_ASSIGNED, &priv->flags)) return 0; goto err_disable; } ipoib_ib_dev_up(dev); if (!test_bit(IPOIB_FLAG_SUBINTERFACE, &priv->flags)) { struct ipoib_dev_priv *cpriv; /* Bring up any child interfaces too */ down_read(&priv->vlan_rwsem); list_for_each_entry(cpriv, &priv->child_intfs, list) { int flags; flags = cpriv->dev->flags; if (flags & IFF_UP) continue; dev_change_flags(cpriv->dev, flags | IFF_UP, NULL); } up_read(&priv->vlan_rwsem); } else if (priv->parent) { struct ipoib_dev_priv *ppriv = ipoib_priv(priv->parent); if (!test_bit(IPOIB_FLAG_ADMIN_UP, &ppriv->flags)) ipoib_dbg(priv, "parent device %s is not up, so child device may be not functioning.\n", ppriv->dev->name); } netif_start_queue(dev); return 0; err_disable: clear_bit(IPOIB_FLAG_ADMIN_UP, &priv->flags); return -EINVAL; } static int ipoib_stop(struct net_device *dev) { struct ipoib_dev_priv *priv = ipoib_priv(dev); ipoib_dbg(priv, "stopping interface\n"); clear_bit(IPOIB_FLAG_ADMIN_UP, &priv->flags); netif_stop_queue(dev); ipoib_ib_dev_down(dev); ipoib_ib_dev_stop(dev); if (!test_bit(IPOIB_FLAG_SUBINTERFACE, &priv->flags)) { struct ipoib_dev_priv *cpriv; /* Bring down any child interfaces too */ down_read(&priv->vlan_rwsem); list_for_each_entry(cpriv, &priv->child_intfs, list) { int flags; flags = cpriv->dev->flags; if (!(flags & IFF_UP)) continue; dev_change_flags(cpriv->dev, flags & ~IFF_UP, NULL); } up_read(&priv->vlan_rwsem); } return 0; } static netdev_features_t ipoib_fix_features(struct net_device *dev, netdev_features_t features) { struct ipoib_dev_priv *priv = ipoib_priv(dev); if (test_bit(IPOIB_FLAG_ADMIN_CM, &priv->flags)) features &= ~(NETIF_F_IP_CSUM | NETIF_F_TSO); return features; } static int ipoib_change_mtu(struct net_device *dev, int new_mtu) { struct ipoib_dev_priv *priv = ipoib_priv(dev); int ret = 0; /* dev->mtu > 2K ==> connected mode */ if (ipoib_cm_admin_enabled(dev)) { if (new_mtu > ipoib_cm_max_mtu(dev)) return -EINVAL; if (new_mtu > priv->mcast_mtu) ipoib_warn(priv, "mtu > %d will cause multicast packet drops.\n", priv->mcast_mtu); WRITE_ONCE(dev->mtu, new_mtu); return 0; } if (new_mtu < (ETH_MIN_MTU + IPOIB_ENCAP_LEN) || new_mtu > IPOIB_UD_MTU(priv->max_ib_mtu)) return -EINVAL; priv->admin_mtu = new_mtu; if (priv->mcast_mtu < priv->admin_mtu) ipoib_dbg(priv, "MTU must be smaller than the underlying " "link layer MTU - 4 (%u)\n", priv->mcast_mtu); new_mtu = min(priv->mcast_mtu, priv->admin_mtu); if (priv->rn_ops->ndo_change_mtu) { bool carrier_status = netif_carrier_ok(dev); netif_carrier_off(dev); /* notify lower level on the real mtu */ ret = priv->rn_ops->ndo_change_mtu(dev, new_mtu); if (carrier_status) netif_carrier_on(dev); } else { WRITE_ONCE(dev->mtu, new_mtu); } return ret; } static void ipoib_get_stats(struct net_device *dev, struct rtnl_link_stats64 *stats) { struct ipoib_dev_priv *priv = ipoib_priv(dev); if (priv->rn_ops->ndo_get_stats64) priv->rn_ops->ndo_get_stats64(dev, stats); else netdev_stats_to_stats64(stats, &dev->stats); } /* Called with an RCU read lock taken */ static bool ipoib_is_dev_match_addr_rcu(const struct sockaddr *addr, struct net_device *dev) { struct net *net = dev_net(dev); struct in_device *in_dev; struct sockaddr_in *addr_in = (struct sockaddr_in *)addr; struct sockaddr_in6 *addr_in6 = (struct sockaddr_in6 *)addr; __be32 ret_addr; switch (addr->sa_family) { case AF_INET: in_dev = in_dev_get(dev); if (!in_dev) return false; ret_addr = inet_confirm_addr(net, in_dev, 0, addr_in->sin_addr.s_addr, RT_SCOPE_HOST); in_dev_put(in_dev); if (ret_addr) return true; break; case AF_INET6: if (IS_ENABLED(CONFIG_IPV6) && ipv6_chk_addr(net, &addr_in6->sin6_addr, dev, 1)) return true; break; } return false; } /* * Find the master net_device on top of the given net_device. * @dev: base IPoIB net_device * * Returns the master net_device with a reference held, or the same net_device * if no master exists. */ static struct net_device *ipoib_get_master_net_dev(struct net_device *dev) { struct net_device *master; rcu_read_lock(); master = netdev_master_upper_dev_get_rcu(dev); dev_hold(master); rcu_read_unlock(); if (master) return master; dev_hold(dev); return dev; } struct ipoib_walk_data { const struct sockaddr *addr; struct net_device *result; }; static int ipoib_upper_walk(struct net_device *upper, struct netdev_nested_priv *priv) { struct ipoib_walk_data *data = (struct ipoib_walk_data *)priv->data; int ret = 0; if (ipoib_is_dev_match_addr_rcu(data->addr, upper)) { dev_hold(upper); data->result = upper; ret = 1; } return ret; } /** * ipoib_get_net_dev_match_addr - Find a net_device matching * the given address, which is an upper device of the given net_device. * * @addr: IP address to look for. * @dev: base IPoIB net_device * * If found, returns the net_device with a reference held. Otherwise return * NULL. */ static struct net_device *ipoib_get_net_dev_match_addr( const struct sockaddr *addr, struct net_device *dev) { struct netdev_nested_priv priv; struct ipoib_walk_data data = { .addr = addr, }; priv.data = (void *)&data; rcu_read_lock(); if (ipoib_is_dev_match_addr_rcu(addr, dev)) { dev_hold(dev); data.result = dev; goto out; } netdev_walk_all_upper_dev_rcu(dev, ipoib_upper_walk, &priv); out: rcu_read_unlock(); return data.result; } /* returns the number of IPoIB netdevs on top a given ipoib device matching a * pkey_index and address, if one exists. * * @found_net_dev: contains a matching net_device if the return value >= 1, * with a reference held. */ static int ipoib_match_gid_pkey_addr(struct ipoib_dev_priv *priv, const union ib_gid *gid, u16 pkey_index, const struct sockaddr *addr, int nesting, struct net_device **found_net_dev) { struct ipoib_dev_priv *child_priv; struct net_device *net_dev = NULL; int matches = 0; if (priv->pkey_index == pkey_index && (!gid || !memcmp(gid, &priv->local_gid, sizeof(*gid)))) { if (!addr) { net_dev = ipoib_get_master_net_dev(priv->dev); } else { /* Verify the net_device matches the IP address, as * IPoIB child devices currently share a GID. */ net_dev = ipoib_get_net_dev_match_addr(addr, priv->dev); } if (net_dev) { if (!*found_net_dev) *found_net_dev = net_dev; else dev_put(net_dev); ++matches; } } /* Check child interfaces */ down_read_nested(&priv->vlan_rwsem, nesting); list_for_each_entry(child_priv, &priv->child_intfs, list) { matches += ipoib_match_gid_pkey_addr(child_priv, gid, pkey_index, addr, nesting + 1, found_net_dev); if (matches > 1) break; } up_read(&priv->vlan_rwsem); return matches; } /* Returns the number of matching net_devs found (between 0 and 2). Also * return the matching net_device in the @net_dev parameter, holding a * reference to the net_device, if the number of matches >= 1 */ static int __ipoib_get_net_dev_by_params(struct list_head *dev_list, u32 port, u16 pkey_index, const union ib_gid *gid, const struct sockaddr *addr, struct net_device **net_dev) { struct ipoib_dev_priv *priv; int matches = 0; *net_dev = NULL; list_for_each_entry(priv, dev_list, list) { if (priv->port != port) continue; matches += ipoib_match_gid_pkey_addr(priv, gid, pkey_index, addr, 0, net_dev); if (matches > 1) break; } return matches; } static struct net_device *ipoib_get_net_dev_by_params( struct ib_device *dev, u32 port, u16 pkey, const union ib_gid *gid, const struct sockaddr *addr, void *client_data) { struct net_device *net_dev; struct list_head *dev_list = client_data; u16 pkey_index; int matches; int ret; if (!rdma_protocol_ib(dev, port)) return NULL; ret = ib_find_cached_pkey(dev, port, pkey, &pkey_index); if (ret) return NULL; /* See if we can find a unique device matching the L2 parameters */ matches = __ipoib_get_net_dev_by_params(dev_list, port, pkey_index, gid, NULL, &net_dev); switch (matches) { case 0: return NULL; case 1: return net_dev; } dev_put(net_dev); /* Couldn't find a unique device with L2 parameters only. Use L3 * address to uniquely match the net device */ matches = __ipoib_get_net_dev_by_params(dev_list, port, pkey_index, gid, addr, &net_dev); switch (matches) { case 0: return NULL; default: dev_warn_ratelimited(&dev->dev, "duplicate IP address detected\n"); fallthrough; case 1: return net_dev; } } int ipoib_set_mode(struct net_device *dev, const char *buf) { struct ipoib_dev_priv *priv = ipoib_priv(dev); if ((test_bit(IPOIB_FLAG_ADMIN_CM, &priv->flags) && !strcmp(buf, "connected\n")) || (!test_bit(IPOIB_FLAG_ADMIN_CM, &priv->flags) && !strcmp(buf, "datagram\n"))) { return 0; } /* flush paths if we switch modes so that connections are restarted */ if (IPOIB_CM_SUPPORTED(dev->dev_addr) && !strcmp(buf, "connected\n")) { set_bit(IPOIB_FLAG_ADMIN_CM, &priv->flags); ipoib_warn(priv, "enabling connected mode " "will cause multicast packet drops\n"); netdev_update_features(dev); dev_set_mtu(dev, ipoib_cm_max_mtu(dev)); netif_set_real_num_tx_queues(dev, 1); rtnl_unlock(); priv->tx_wr.wr.send_flags &= ~IB_SEND_IP_CSUM; ipoib_flush_paths(dev); return (!rtnl_trylock()) ? -EBUSY : 0; } if (!strcmp(buf, "datagram\n")) { clear_bit(IPOIB_FLAG_ADMIN_CM, &priv->flags); netdev_update_features(dev); dev_set_mtu(dev, min(priv->mcast_mtu, dev->mtu)); netif_set_real_num_tx_queues(dev, dev->num_tx_queues); rtnl_unlock(); ipoib_flush_paths(dev); return (!rtnl_trylock()) ? -EBUSY : 0; } return -EINVAL; } struct ipoib_path *__path_find(struct net_device *dev, void *gid) { struct ipoib_dev_priv *priv = ipoib_priv(dev); struct rb_node *n = priv->path_tree.rb_node; struct ipoib_path *path; int ret; while (n) { path = rb_entry(n, struct ipoib_path, rb_node); ret = memcmp(gid, path->pathrec.dgid.raw, sizeof (union ib_gid)); if (ret < 0) n = n->rb_left; else if (ret > 0) n = n->rb_right; else return path; } return NULL; } static int __path_add(struct net_device *dev, struct ipoib_path *path) { struct ipoib_dev_priv *priv = ipoib_priv(dev); struct rb_node **n = &priv->path_tree.rb_node; struct rb_node *pn = NULL; struct ipoib_path *tpath; int ret; while (*n) { pn = *n; tpath = rb_entry(pn, struct ipoib_path, rb_node); ret = memcmp(path->pathrec.dgid.raw, tpath->pathrec.dgid.raw, sizeof (union ib_gid)); if (ret < 0) n = &pn->rb_left; else if (ret > 0) n = &pn->rb_right; else return -EEXIST; } rb_link_node(&path->rb_node, pn, n); rb_insert_color(&path->rb_node, &priv->path_tree); list_add_tail(&path->list, &priv->path_list); return 0; } static void path_free(struct net_device *dev, struct ipoib_path *path) { struct sk_buff *skb; while ((skb = __skb_dequeue(&path->queue))) dev_kfree_skb_irq(skb); ipoib_dbg(ipoib_priv(dev), "%s\n", __func__); /* remove all neigh connected to this path */ ipoib_del_neighs_by_gid(dev, path->pathrec.dgid.raw); if (path->ah) ipoib_put_ah(path->ah); kfree(path); } #ifdef CONFIG_INFINIBAND_IPOIB_DEBUG struct ipoib_path_iter *ipoib_path_iter_init(struct net_device *dev) { struct ipoib_path_iter *iter; iter = kmalloc(sizeof(*iter), GFP_KERNEL); if (!iter) return NULL; iter->dev = dev; memset(iter->path.pathrec.dgid.raw, 0, 16); if (ipoib_path_iter_next(iter)) { kfree(iter); return NULL; } return iter; } int ipoib_path_iter_next(struct ipoib_path_iter *iter) { struct ipoib_dev_priv *priv = ipoib_priv(iter->dev); struct rb_node *n; struct ipoib_path *path; int ret = 1; spin_lock_irq(&priv->lock); n = rb_first(&priv->path_tree); while (n) { path = rb_entry(n, struct ipoib_path, rb_node); if (memcmp(iter->path.pathrec.dgid.raw, path->pathrec.dgid.raw, sizeof (union ib_gid)) < 0) { iter->path = *path; ret = 0; break; } n = rb_next(n); } spin_unlock_irq(&priv->lock); return ret; } void ipoib_path_iter_read(struct ipoib_path_iter *iter, struct ipoib_path *path) { *path = iter->path; } #endif /* CONFIG_INFINIBAND_IPOIB_DEBUG */ void ipoib_mark_paths_invalid(struct net_device *dev) { struct ipoib_dev_priv *priv = ipoib_priv(dev); struct ipoib_path *path, *tp; spin_lock_irq(&priv->lock); list_for_each_entry_safe(path, tp, &priv->path_list, list) { ipoib_dbg(priv, "mark path LID 0x%08x GID %pI6 invalid\n", be32_to_cpu(sa_path_get_dlid(&path->pathrec)), path->pathrec.dgid.raw); if (path->ah) path->ah->valid = 0; } spin_unlock_irq(&priv->lock); } static void push_pseudo_header(struct sk_buff *skb, const char *daddr) { struct ipoib_pseudo_header *phdr; phdr = skb_push(skb, sizeof(*phdr)); memcpy(phdr->hwaddr, daddr, INFINIBAND_ALEN); } void ipoib_flush_paths(struct net_device *dev) { struct ipoib_dev_priv *priv = ipoib_priv(dev); struct ipoib_path *path, *tp; LIST_HEAD(remove_list); unsigned long flags; netif_tx_lock_bh(dev); spin_lock_irqsave(&priv->lock, flags); list_splice_init(&priv->path_list, &remove_list); list_for_each_entry(path, &remove_list, list) rb_erase(&path->rb_node, &priv->path_tree); list_for_each_entry_safe(path, tp, &remove_list, list) { if (path->query) ib_sa_cancel_query(path->query_id, path->query); spin_unlock_irqrestore(&priv->lock, flags); netif_tx_unlock_bh(dev); wait_for_completion(&path->done); path_free(dev, path); netif_tx_lock_bh(dev); spin_lock_irqsave(&priv->lock, flags); } spin_unlock_irqrestore(&priv->lock, flags); netif_tx_unlock_bh(dev); } static void path_rec_completion(int status, struct sa_path_rec *pathrec, unsigned int num_prs, void *path_ptr) { struct ipoib_path *path = path_ptr; struct net_device *dev = path->dev; struct ipoib_dev_priv *priv = ipoib_priv(dev); struct ipoib_ah *ah = NULL; struct ipoib_ah *old_ah = NULL; struct ipoib_neigh *neigh, *tn; struct sk_buff_head skqueue; struct sk_buff *skb; unsigned long flags; if (!status) ipoib_dbg(priv, "PathRec LID 0x%04x for GID %pI6\n", be32_to_cpu(sa_path_get_dlid(pathrec)), pathrec->dgid.raw); else ipoib_dbg(priv, "PathRec status %d for GID %pI6\n", status, path->pathrec.dgid.raw); skb_queue_head_init(&skqueue); if (!status) { struct rdma_ah_attr av; if (!ib_init_ah_attr_from_path(priv->ca, priv->port, pathrec, &av, NULL)) { ah = ipoib_create_ah(dev, priv->pd, &av); rdma_destroy_ah_attr(&av); } } spin_lock_irqsave(&priv->lock, flags); if (!IS_ERR_OR_NULL(ah)) { /* * pathrec.dgid is used as the database key from the LLADDR, * it must remain unchanged even if the SA returns a different * GID to use in the AH. */ if (memcmp(pathrec->dgid.raw, path->pathrec.dgid.raw, sizeof(union ib_gid))) { ipoib_dbg( priv, "%s got PathRec for gid %pI6 while asked for %pI6\n", dev->name, pathrec->dgid.raw, path->pathrec.dgid.raw); memcpy(pathrec->dgid.raw, path->pathrec.dgid.raw, sizeof(union ib_gid)); } path->pathrec = *pathrec; old_ah = path->ah; path->ah = ah; ipoib_dbg(priv, "created address handle %p for LID 0x%04x, SL %d\n", ah, be32_to_cpu(sa_path_get_dlid(pathrec)), pathrec->sl); while ((skb = __skb_dequeue(&path->queue))) __skb_queue_tail(&skqueue, skb); list_for_each_entry_safe(neigh, tn, &path->neigh_list, list) { if (neigh->ah) { WARN_ON(neigh->ah != old_ah); /* * Dropping the ah reference inside * priv->lock is safe here, because we * will hold one more reference from * the original value of path->ah (ie * old_ah). */ ipoib_put_ah(neigh->ah); } kref_get(&path->ah->ref); neigh->ah = path->ah; if (ipoib_cm_enabled(dev, neigh->daddr)) { if (!ipoib_cm_get(neigh)) ipoib_cm_set(neigh, ipoib_cm_create_tx(dev, path, neigh)); if (!ipoib_cm_get(neigh)) { ipoib_neigh_free(neigh); continue; } } while ((skb = __skb_dequeue(&neigh->queue))) __skb_queue_tail(&skqueue, skb); } path->ah->valid = 1; } path->query = NULL; complete(&path->done); spin_unlock_irqrestore(&priv->lock, flags); if (IS_ERR_OR_NULL(ah)) ipoib_del_neighs_by_gid(dev, path->pathrec.dgid.raw); if (old_ah) ipoib_put_ah(old_ah); while ((skb = __skb_dequeue(&skqueue))) { int ret; skb->dev = dev; ret = dev_queue_xmit(skb); if (ret) ipoib_warn(priv, "%s: dev_queue_xmit failed to re-queue packet, ret:%d\n", __func__, ret); } } static void init_path_rec(struct ipoib_dev_priv *priv, struct ipoib_path *path, void *gid) { path->dev = priv->dev; if (rdma_cap_opa_ah(priv->ca, priv->port)) path->pathrec.rec_type = SA_PATH_REC_TYPE_OPA; else path->pathrec.rec_type = SA_PATH_REC_TYPE_IB; memcpy(path->pathrec.dgid.raw, gid, sizeof(union ib_gid)); path->pathrec.sgid = priv->local_gid; path->pathrec.pkey = cpu_to_be16(priv->pkey); path->pathrec.numb_path = 1; path->pathrec.traffic_class = priv->broadcast->mcmember.traffic_class; } static struct ipoib_path *path_rec_create(struct net_device *dev, void *gid) { struct ipoib_dev_priv *priv = ipoib_priv(dev); struct ipoib_path *path; if (!priv->broadcast) return NULL; path = kzalloc(sizeof(*path), GFP_ATOMIC); if (!path) return NULL; skb_queue_head_init(&path->queue); INIT_LIST_HEAD(&path->neigh_list); init_path_rec(priv, path, gid); return path; } static int path_rec_start(struct net_device *dev, struct ipoib_path *path) { struct ipoib_dev_priv *priv = ipoib_priv(dev); ipoib_dbg(priv, "Start path record lookup for %pI6\n", path->pathrec.dgid.raw); init_completion(&path->done); path->query_id = ib_sa_path_rec_get(&ipoib_sa_client, priv->ca, priv->port, &path->pathrec, IB_SA_PATH_REC_DGID | IB_SA_PATH_REC_SGID | IB_SA_PATH_REC_NUMB_PATH | IB_SA_PATH_REC_TRAFFIC_CLASS | IB_SA_PATH_REC_PKEY, 1000, GFP_ATOMIC, path_rec_completion, path, &path->query); if (path->query_id < 0) { ipoib_warn(priv, "ib_sa_path_rec_get failed: %d\n", path->query_id); path->query = NULL; complete(&path->done); return path->query_id; } return 0; } static void neigh_refresh_path(struct ipoib_neigh *neigh, u8 *daddr, struct net_device *dev) { struct ipoib_dev_priv *priv = ipoib_priv(dev); struct ipoib_path *path; unsigned long flags; spin_lock_irqsave(&priv->lock, flags); path = __path_find(dev, daddr + 4); if (!path) goto out; if (!path->query) path_rec_start(dev, path); out: spin_unlock_irqrestore(&priv->lock, flags); } static struct ipoib_neigh *neigh_add_path(struct sk_buff *skb, u8 *daddr, struct net_device *dev) { struct ipoib_dev_priv *priv = ipoib_priv(dev); struct rdma_netdev *rn = netdev_priv(dev); struct ipoib_path *path; struct ipoib_neigh *neigh; unsigned long flags; spin_lock_irqsave(&priv->lock, flags); neigh = ipoib_neigh_alloc(daddr, dev); if (!neigh) { spin_unlock_irqrestore(&priv->lock, flags); ++dev->stats.tx_dropped; dev_kfree_skb_any(skb); return NULL; } /* To avoid race condition, make sure that the * neigh will be added only once. */ if (unlikely(!list_empty(&neigh->list))) { spin_unlock_irqrestore(&priv->lock, flags); return neigh; } path = __path_find(dev, daddr + 4); if (!path) { path = path_rec_create(dev, daddr + 4); if (!path) goto err_path; __path_add(dev, path); } list_add_tail(&neigh->list, &path->neigh_list); if (path->ah && path->ah->valid) { kref_get(&path->ah->ref); neigh->ah = path->ah; if (ipoib_cm_enabled(dev, neigh->daddr)) { if (!ipoib_cm_get(neigh)) ipoib_cm_set(neigh, ipoib_cm_create_tx(dev, path, neigh)); if (!ipoib_cm_get(neigh)) { ipoib_neigh_free(neigh); goto err_drop; } if (skb_queue_len(&neigh->queue) < IPOIB_MAX_PATH_REC_QUEUE) { push_pseudo_header(skb, neigh->daddr); __skb_queue_tail(&neigh->queue, skb); } else { ipoib_warn(priv, "queue length limit %d. Packet drop.\n", skb_queue_len(&neigh->queue)); goto err_drop; } } else { spin_unlock_irqrestore(&priv->lock, flags); path->ah->last_send = rn->send(dev, skb, path->ah->ah, IPOIB_QPN(daddr)); ipoib_neigh_put(neigh); return NULL; } } else { neigh->ah = NULL; if (!path->query && path_rec_start(dev, path)) goto err_path; if (skb_queue_len(&neigh->queue) < IPOIB_MAX_PATH_REC_QUEUE) { push_pseudo_header(skb, neigh->daddr); __skb_queue_tail(&neigh->queue, skb); } else { goto err_drop; } } spin_unlock_irqrestore(&priv->lock, flags); ipoib_neigh_put(neigh); return NULL; err_path: ipoib_neigh_free(neigh); err_drop: ++dev->stats.tx_dropped; dev_kfree_skb_any(skb); spin_unlock_irqrestore(&priv->lock, flags); ipoib_neigh_put(neigh); return NULL; } static void unicast_arp_send(struct sk_buff *skb, struct net_device *dev, struct ipoib_pseudo_header *phdr) { struct ipoib_dev_priv *priv = ipoib_priv(dev); struct rdma_netdev *rn = netdev_priv(dev); struct ipoib_path *path; unsigned long flags; spin_lock_irqsave(&priv->lock, flags); /* no broadcast means that all paths are (going to be) not valid */ if (!priv->broadcast) goto drop_and_unlock; path = __path_find(dev, phdr->hwaddr + 4); if (!path || !path->ah || !path->ah->valid) { if (!path) { path = path_rec_create(dev, phdr->hwaddr + 4); if (!path) goto drop_and_unlock; __path_add(dev, path); } else { /* * make sure there are no changes in the existing * path record */ init_path_rec(priv, path, phdr->hwaddr + 4); } if (!path->query && path_rec_start(dev, path)) { goto drop_and_unlock; } if (skb_queue_len(&path->queue) < IPOIB_MAX_PATH_REC_QUEUE) { push_pseudo_header(skb, phdr->hwaddr); __skb_queue_tail(&path->queue, skb); goto unlock; } else { goto drop_and_unlock; } } spin_unlock_irqrestore(&priv->lock, flags); ipoib_dbg(priv, "Send unicast ARP to %08x\n", be32_to_cpu(sa_path_get_dlid(&path->pathrec))); path->ah->last_send = rn->send(dev, skb, path->ah->ah, IPOIB_QPN(phdr->hwaddr)); return; drop_and_unlock: ++dev->stats.tx_dropped; dev_kfree_skb_any(skb); unlock: spin_unlock_irqrestore(&priv->lock, flags); } static netdev_tx_t ipoib_start_xmit(struct sk_buff *skb, struct net_device *dev) { struct ipoib_dev_priv *priv = ipoib_priv(dev); struct rdma_netdev *rn = netdev_priv(dev); struct ipoib_neigh *neigh; struct ipoib_pseudo_header *phdr; struct ipoib_header *header; unsigned long flags; phdr = (struct ipoib_pseudo_header *) skb->data; skb_pull(skb, sizeof(*phdr)); header = (struct ipoib_header *) skb->data; if (unlikely(phdr->hwaddr[4] == 0xff)) { /* multicast, arrange "if" according to probability */ if ((header->proto != htons(ETH_P_IP)) && (header->proto != htons(ETH_P_IPV6)) && (header->proto != htons(ETH_P_ARP)) && (header->proto != htons(ETH_P_RARP)) && (header->proto != htons(ETH_P_TIPC))) { /* ethertype not supported by IPoIB */ ++dev->stats.tx_dropped; dev_kfree_skb_any(skb); return NETDEV_TX_OK; } /* Add in the P_Key for multicast*/ phdr->hwaddr[8] = (priv->pkey >> 8) & 0xff; phdr->hwaddr[9] = priv->pkey & 0xff; neigh = ipoib_neigh_get(dev, phdr->hwaddr); if (likely(neigh)) goto send_using_neigh; ipoib_mcast_send(dev, phdr->hwaddr, skb); return NETDEV_TX_OK; } /* unicast, arrange "switch" according to probability */ switch (header->proto) { case htons(ETH_P_IP): case htons(ETH_P_IPV6): case htons(ETH_P_TIPC): neigh = ipoib_neigh_get(dev, phdr->hwaddr); if (unlikely(!neigh)) { neigh = neigh_add_path(skb, phdr->hwaddr, dev); if (likely(!neigh)) return NETDEV_TX_OK; } break; case htons(ETH_P_ARP): case htons(ETH_P_RARP): /* for unicast ARP and RARP should always perform path find */ unicast_arp_send(skb, dev, phdr); return NETDEV_TX_OK; default: /* ethertype not supported by IPoIB */ ++dev->stats.tx_dropped; dev_kfree_skb_any(skb); return NETDEV_TX_OK; } send_using_neigh: /* note we now hold a ref to neigh */ if (ipoib_cm_get(neigh)) { if (ipoib_cm_up(neigh)) { ipoib_cm_send(dev, skb, ipoib_cm_get(neigh)); goto unref; } } else if (neigh->ah && neigh->ah->valid) { neigh->ah->last_send = rn->send(dev, skb, neigh->ah->ah, IPOIB_QPN(phdr->hwaddr)); goto unref; } else if (neigh->ah) { neigh_refresh_path(neigh, phdr->hwaddr, dev); } if (skb_queue_len(&neigh->queue) < IPOIB_MAX_PATH_REC_QUEUE) { push_pseudo_header(skb, phdr->hwaddr); spin_lock_irqsave(&priv->lock, flags); __skb_queue_tail(&neigh->queue, skb); spin_unlock_irqrestore(&priv->lock, flags); } else { ++dev->stats.tx_dropped; dev_kfree_skb_any(skb); } unref: ipoib_neigh_put(neigh); return NETDEV_TX_OK; } static void ipoib_timeout(struct net_device *dev, unsigned int txqueue) { struct ipoib_dev_priv *priv = ipoib_priv(dev); struct rdma_netdev *rn = netdev_priv(dev); if (rn->tx_timeout) { rn->tx_timeout(dev, txqueue); return; } ipoib_warn(priv, "transmit timeout: latency %d msecs\n", jiffies_to_msecs(jiffies - dev_trans_start(dev))); ipoib_warn(priv, "queue stopped %d, tx_head %u, tx_tail %u, global_tx_head %u, global_tx_tail %u\n", netif_queue_stopped(dev), priv->tx_head, priv->tx_tail, priv->global_tx_head, priv->global_tx_tail); schedule_work(&priv->tx_timeout_work); } void ipoib_ib_tx_timeout_work(struct work_struct *work) { struct ipoib_dev_priv *priv = container_of(work, struct ipoib_dev_priv, tx_timeout_work); int err; rtnl_lock(); if (!test_bit(IPOIB_FLAG_ADMIN_UP, &priv->flags)) goto unlock; ipoib_stop(priv->dev); err = ipoib_open(priv->dev); if (err) { ipoib_warn(priv, "ipoib_open failed recovering from a tx_timeout, err(%d).\n", err); goto unlock; } netif_tx_wake_all_queues(priv->dev); unlock: rtnl_unlock(); } static int ipoib_hard_header(struct sk_buff *skb, struct net_device *dev, unsigned short type, const void *daddr, const void *saddr, unsigned int len) { struct ipoib_header *header; header = skb_push(skb, sizeof(*header)); header->proto = htons(type); header->reserved = 0; /* * we don't rely on dst_entry structure, always stuff the * destination address into skb hard header so we can figure out where * to send the packet later. */ push_pseudo_header(skb, daddr); return IPOIB_HARD_LEN; } static void ipoib_set_mcast_list(struct net_device *dev) { struct ipoib_dev_priv *priv = ipoib_priv(dev); if (!test_bit(IPOIB_FLAG_OPER_UP, &priv->flags)) { ipoib_dbg(priv, "IPOIB_FLAG_OPER_UP not set"); return; } queue_work(priv->wq, &priv->restart_task); } static int ipoib_get_iflink(const struct net_device *dev) { struct ipoib_dev_priv *priv = ipoib_priv(dev); /* parent interface */ if (!test_bit(IPOIB_FLAG_SUBINTERFACE, &priv->flags)) return READ_ONCE(dev->ifindex); /* child/vlan interface */ return READ_ONCE(priv->parent->ifindex); } static u32 ipoib_addr_hash(struct ipoib_neigh_hash *htbl, u8 *daddr) { /* * Use only the address parts that contributes to spreading * The subnet prefix is not used as one can not connect to * same remote port (GUID) using the same remote QPN via two * different subnets. */ /* qpn octets[1:4) & port GUID octets[12:20) */ u32 *d32 = (u32 *) daddr; u32 hv; hv = jhash_3words(d32[3], d32[4], IPOIB_QPN_MASK & d32[0], 0); return hv & htbl->mask; } struct ipoib_neigh *ipoib_neigh_get(struct net_device *dev, u8 *daddr) { struct ipoib_dev_priv *priv = ipoib_priv(dev); struct ipoib_neigh_table *ntbl = &priv->ntbl; struct ipoib_neigh_hash *htbl; struct ipoib_neigh *neigh = NULL; u32 hash_val; rcu_read_lock_bh(); htbl = rcu_dereference_bh(ntbl->htbl); if (!htbl) goto out_unlock; hash_val = ipoib_addr_hash(htbl, daddr); for (neigh = rcu_dereference_bh(htbl->buckets[hash_val]); neigh != NULL; neigh = rcu_dereference_bh(neigh->hnext)) { if (memcmp(daddr, neigh->daddr, INFINIBAND_ALEN) == 0) { /* found, take one ref on behalf of the caller */ if (!refcount_inc_not_zero(&neigh->refcnt)) { /* deleted */ neigh = NULL; goto out_unlock; } if (likely(skb_queue_len(&neigh->queue) < IPOIB_MAX_PATH_REC_QUEUE)) neigh->alive = jiffies; goto out_unlock; } } out_unlock: rcu_read_unlock_bh(); return neigh; } static void __ipoib_reap_neigh(struct ipoib_dev_priv *priv) { struct ipoib_neigh_table *ntbl = &priv->ntbl; struct ipoib_neigh_hash *htbl; unsigned long neigh_obsolete; unsigned long dt; unsigned long flags; int i; LIST_HEAD(remove_list); spin_lock_irqsave(&priv->lock, flags); htbl = rcu_dereference_protected(ntbl->htbl, lockdep_is_held(&priv->lock)); if (!htbl) goto out_unlock; /* neigh is obsolete if it was idle for two GC periods */ dt = 2 * arp_tbl.gc_interval; neigh_obsolete = jiffies - dt; for (i = 0; i < htbl->size; i++) { struct ipoib_neigh *neigh; struct ipoib_neigh __rcu **np = &htbl->buckets[i]; while ((neigh = rcu_dereference_protected(*np, lockdep_is_held(&priv->lock))) != NULL) { /* was the neigh idle for two GC periods */ if (time_after(neigh_obsolete, neigh->alive)) { ipoib_check_and_add_mcast_sendonly(priv, neigh->daddr + 4, &remove_list); rcu_assign_pointer(*np, rcu_dereference_protected(neigh->hnext, lockdep_is_held(&priv->lock))); /* remove from path/mc list */ list_del_init(&neigh->list); call_rcu(&neigh->rcu, ipoib_neigh_reclaim); } else { np = &neigh->hnext; } } } out_unlock: spin_unlock_irqrestore(&priv->lock, flags); ipoib_mcast_remove_list(&remove_list); } static void ipoib_reap_neigh(struct work_struct *work) { struct ipoib_dev_priv *priv = container_of(work, struct ipoib_dev_priv, neigh_reap_task.work); __ipoib_reap_neigh(priv); queue_delayed_work(priv->wq, &priv->neigh_reap_task, arp_tbl.gc_interval); } static struct ipoib_neigh *ipoib_neigh_ctor(u8 *daddr, struct net_device *dev) { struct ipoib_neigh *neigh; neigh = kzalloc(sizeof(*neigh), GFP_ATOMIC); if (!neigh) return NULL; neigh->dev = dev; memcpy(&neigh->daddr, daddr, sizeof(neigh->daddr)); skb_queue_head_init(&neigh->queue); INIT_LIST_HEAD(&neigh->list); ipoib_cm_set(neigh, NULL); /* one ref on behalf of the caller */ refcount_set(&neigh->refcnt, 1); return neigh; } struct ipoib_neigh *ipoib_neigh_alloc(u8 *daddr, struct net_device *dev) { struct ipoib_dev_priv *priv = ipoib_priv(dev); struct ipoib_neigh_table *ntbl = &priv->ntbl; struct ipoib_neigh_hash *htbl; struct ipoib_neigh *neigh; u32 hash_val; htbl = rcu_dereference_protected(ntbl->htbl, lockdep_is_held(&priv->lock)); if (!htbl) { neigh = NULL; goto out_unlock; } /* need to add a new neigh, but maybe some other thread succeeded? * recalc hash, maybe hash resize took place so we do a search */ hash_val = ipoib_addr_hash(htbl, daddr); for (neigh = rcu_dereference_protected(htbl->buckets[hash_val], lockdep_is_held(&priv->lock)); neigh != NULL; neigh = rcu_dereference_protected(neigh->hnext, lockdep_is_held(&priv->lock))) { if (memcmp(daddr, neigh->daddr, INFINIBAND_ALEN) == 0) { /* found, take one ref on behalf of the caller */ if (!refcount_inc_not_zero(&neigh->refcnt)) { /* deleted */ neigh = NULL; break; } neigh->alive = jiffies; goto out_unlock; } } neigh = ipoib_neigh_ctor(daddr, dev); if (!neigh) goto out_unlock; /* one ref on behalf of the hash table */ refcount_inc(&neigh->refcnt); neigh->alive = jiffies; /* put in hash */ rcu_assign_pointer(neigh->hnext, rcu_dereference_protected(htbl->buckets[hash_val], lockdep_is_held(&priv->lock))); rcu_assign_pointer(htbl->buckets[hash_val], neigh); atomic_inc(&ntbl->entries); out_unlock: return neigh; } void ipoib_neigh_dtor(struct ipoib_neigh *neigh) { /* neigh reference count was dropprd to zero */ struct net_device *dev = neigh->dev; struct ipoib_dev_priv *priv = ipoib_priv(dev); struct sk_buff *skb; if (neigh->ah) ipoib_put_ah(neigh->ah); while ((skb = __skb_dequeue(&neigh->queue))) { ++dev->stats.tx_dropped; dev_kfree_skb_any(skb); } if (ipoib_cm_get(neigh)) ipoib_cm_destroy_tx(ipoib_cm_get(neigh)); ipoib_dbg(ipoib_priv(dev), "neigh free for %06x %pI6\n", IPOIB_QPN(neigh->daddr), neigh->daddr + 4); kfree(neigh); if (atomic_dec_and_test(&priv->ntbl.entries)) { if (test_bit(IPOIB_NEIGH_TBL_FLUSH, &priv->flags)) complete(&priv->ntbl.flushed); } } static void ipoib_neigh_reclaim(struct rcu_head *rp) { /* Called as a result of removal from hash table */ struct ipoib_neigh *neigh = container_of(rp, struct ipoib_neigh, rcu); /* note TX context may hold another ref */ ipoib_neigh_put(neigh); } void ipoib_neigh_free(struct ipoib_neigh *neigh) { struct net_device *dev = neigh->dev; struct ipoib_dev_priv *priv = ipoib_priv(dev); struct ipoib_neigh_table *ntbl = &priv->ntbl; struct ipoib_neigh_hash *htbl; struct ipoib_neigh __rcu **np; struct ipoib_neigh *n; u32 hash_val; htbl = rcu_dereference_protected(ntbl->htbl, lockdep_is_held(&priv->lock)); if (!htbl) return; hash_val = ipoib_addr_hash(htbl, neigh->daddr); np = &htbl->buckets[hash_val]; for (n = rcu_dereference_protected(*np, lockdep_is_held(&priv->lock)); n != NULL; n = rcu_dereference_protected(*np, lockdep_is_held(&priv->lock))) { if (n == neigh) { /* found */ rcu_assign_pointer(*np, rcu_dereference_protected(neigh->hnext, lockdep_is_held(&priv->lock))); /* remove from parent list */ list_del_init(&neigh->list); call_rcu(&neigh->rcu, ipoib_neigh_reclaim); return; } else { np = &n->hnext; } } } static int ipoib_neigh_hash_init(struct ipoib_dev_priv *priv) { struct ipoib_neigh_table *ntbl = &priv->ntbl; struct ipoib_neigh_hash *htbl; struct ipoib_neigh __rcu **buckets; u32 size; clear_bit(IPOIB_NEIGH_TBL_FLUSH, &priv->flags); ntbl->htbl = NULL; htbl = kzalloc(sizeof(*htbl), GFP_KERNEL); if (!htbl) return -ENOMEM; size = roundup_pow_of_two(arp_tbl.gc_thresh3); buckets = kvcalloc(size, sizeof(*buckets), GFP_KERNEL); if (!buckets) { kfree(htbl); return -ENOMEM; } htbl->size = size; htbl->mask = (size - 1); htbl->buckets = buckets; RCU_INIT_POINTER(ntbl->htbl, htbl); htbl->ntbl = ntbl; atomic_set(&ntbl->entries, 0); /* start garbage collection */ queue_delayed_work(priv->wq, &priv->neigh_reap_task, arp_tbl.gc_interval); return 0; } static void neigh_hash_free_rcu(struct rcu_head *head) { struct ipoib_neigh_hash *htbl = container_of(head, struct ipoib_neigh_hash, rcu); struct ipoib_neigh __rcu **buckets = htbl->buckets; struct ipoib_neigh_table *ntbl = htbl->ntbl; kvfree(buckets); kfree(htbl); complete(&ntbl->deleted); } void ipoib_del_neighs_by_gid(struct net_device *dev, u8 *gid) { struct ipoib_dev_priv *priv = ipoib_priv(dev); struct ipoib_neigh_table *ntbl = &priv->ntbl; struct ipoib_neigh_hash *htbl; unsigned long flags; int i; /* remove all neigh connected to a given path or mcast */ spin_lock_irqsave(&priv->lock, flags); htbl = rcu_dereference_protected(ntbl->htbl, lockdep_is_held(&priv->lock)); if (!htbl) goto out_unlock; for (i = 0; i < htbl->size; i++) { struct ipoib_neigh *neigh; struct ipoib_neigh __rcu **np = &htbl->buckets[i]; while ((neigh = rcu_dereference_protected(*np, lockdep_is_held(&priv->lock))) != NULL) { /* delete neighs belong to this parent */ if (!memcmp(gid, neigh->daddr + 4, sizeof (union ib_gid))) { rcu_assign_pointer(*np, rcu_dereference_protected(neigh->hnext, lockdep_is_held(&priv->lock))); /* remove from parent list */ list_del_init(&neigh->list); call_rcu(&neigh->rcu, ipoib_neigh_reclaim); } else { np = &neigh->hnext; } } } out_unlock: spin_unlock_irqrestore(&priv->lock, flags); } static void ipoib_flush_neighs(struct ipoib_dev_priv *priv) { struct ipoib_neigh_table *ntbl = &priv->ntbl; struct ipoib_neigh_hash *htbl; unsigned long flags; int i, wait_flushed = 0; init_completion(&priv->ntbl.flushed); set_bit(IPOIB_NEIGH_TBL_FLUSH, &priv->flags); spin_lock_irqsave(&priv->lock, flags); htbl = rcu_dereference_protected(ntbl->htbl, lockdep_is_held(&priv->lock)); if (!htbl) goto out_unlock; wait_flushed = atomic_read(&priv->ntbl.entries); if (!wait_flushed) goto free_htbl; for (i = 0; i < htbl->size; i++) { struct ipoib_neigh *neigh; struct ipoib_neigh __rcu **np = &htbl->buckets[i]; while ((neigh = rcu_dereference_protected(*np, lockdep_is_held(&priv->lock))) != NULL) { rcu_assign_pointer(*np, rcu_dereference_protected(neigh->hnext, lockdep_is_held(&priv->lock))); /* remove from path/mc list */ list_del_init(&neigh->list); call_rcu(&neigh->rcu, ipoib_neigh_reclaim); } } free_htbl: rcu_assign_pointer(ntbl->htbl, NULL); call_rcu(&htbl->rcu, neigh_hash_free_rcu); out_unlock: spin_unlock_irqrestore(&priv->lock, flags); if (wait_flushed) wait_for_completion(&priv->ntbl.flushed); } static void ipoib_neigh_hash_uninit(struct net_device *dev) { struct ipoib_dev_priv *priv = ipoib_priv(dev); ipoib_dbg(priv, "%s\n", __func__); init_completion(&priv->ntbl.deleted); cancel_delayed_work_sync(&priv->neigh_reap_task); ipoib_flush_neighs(priv); wait_for_completion(&priv->ntbl.deleted); } static void ipoib_napi_add(struct net_device *dev) { struct ipoib_dev_priv *priv = ipoib_priv(dev); netif_napi_add_weight(dev, &priv->recv_napi, ipoib_rx_poll, IPOIB_NUM_WC); netif_napi_add_weight(dev, &priv->send_napi, ipoib_tx_poll, MAX_SEND_CQE); } static void ipoib_napi_del(struct net_device *dev) { struct ipoib_dev_priv *priv = ipoib_priv(dev); netif_napi_del(&priv->recv_napi); netif_napi_del(&priv->send_napi); } static void ipoib_dev_uninit_default(struct net_device *dev) { struct ipoib_dev_priv *priv = ipoib_priv(dev); ipoib_transport_dev_cleanup(dev); ipoib_napi_del(dev); ipoib_cm_dev_cleanup(dev); kfree(priv->rx_ring); vfree(priv->tx_ring); priv->rx_ring = NULL; priv->tx_ring = NULL; } static int ipoib_dev_init_default(struct net_device *dev) { struct ipoib_dev_priv *priv = ipoib_priv(dev); u8 addr_mod[3]; ipoib_napi_add(dev); /* Allocate RX/TX "rings" to hold queued skbs */ priv->rx_ring = kcalloc(ipoib_recvq_size, sizeof(*priv->rx_ring), GFP_KERNEL); if (!priv->rx_ring) goto out; priv->tx_ring = vzalloc(array_size(ipoib_sendq_size, sizeof(*priv->tx_ring))); if (!priv->tx_ring) { pr_warn("%s: failed to allocate TX ring (%d entries)\n", priv->ca->name, ipoib_sendq_size); goto out_rx_ring_cleanup; } /* priv->tx_head, tx_tail and global_tx_tail/head are already 0 */ if (ipoib_transport_dev_init(dev, priv->ca)) { pr_warn("%s: ipoib_transport_dev_init failed\n", priv->ca->name); goto out_tx_ring_cleanup; } /* after qp created set dev address */ addr_mod[0] = (priv->qp->qp_num >> 16) & 0xff; addr_mod[1] = (priv->qp->qp_num >> 8) & 0xff; addr_mod[2] = (priv->qp->qp_num) & 0xff; dev_addr_mod(priv->dev, 1, addr_mod, sizeof(addr_mod)); return 0; out_tx_ring_cleanup: vfree(priv->tx_ring); out_rx_ring_cleanup: kfree(priv->rx_ring); out: ipoib_napi_del(dev); return -ENOMEM; } static int ipoib_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd) { struct ipoib_dev_priv *priv = ipoib_priv(dev); if (!priv->rn_ops->ndo_eth_ioctl) return -EOPNOTSUPP; return priv->rn_ops->ndo_eth_ioctl(dev, ifr, cmd); } static int ipoib_dev_init(struct net_device *dev) { struct ipoib_dev_priv *priv = ipoib_priv(dev); int ret = -ENOMEM; priv->qp = NULL; /* * the various IPoIB tasks assume they will never race against * themselves, so always use a single thread workqueue */ priv->wq = alloc_ordered_workqueue("ipoib_wq", WQ_MEM_RECLAIM); if (!priv->wq) { pr_warn("%s: failed to allocate device WQ\n", dev->name); goto out; } /* create pd, which used both for control and datapath*/ priv->pd = ib_alloc_pd(priv->ca, 0); if (IS_ERR(priv->pd)) { pr_warn("%s: failed to allocate PD\n", priv->ca->name); goto clean_wq; } ret = priv->rn_ops->ndo_init(dev); if (ret) { pr_warn("%s failed to init HW resource\n", dev->name); goto out_free_pd; } ret = ipoib_neigh_hash_init(priv); if (ret) { pr_warn("%s failed to init neigh hash\n", dev->name); goto out_dev_uninit; } if (dev->flags & IFF_UP) { if (ipoib_ib_dev_open(dev)) { pr_warn("%s failed to open device\n", dev->name); ret = -ENODEV; goto out_hash_uninit; } } return 0; out_hash_uninit: ipoib_neigh_hash_uninit(dev); out_dev_uninit: ipoib_ib_dev_cleanup(dev); out_free_pd: if (priv->pd) { ib_dealloc_pd(priv->pd); priv->pd = NULL; } clean_wq: if (priv->wq) { destroy_workqueue(priv->wq); priv->wq = NULL; } out: return ret; } /* * This must be called before doing an unregister_netdev on a parent device to * shutdown the IB event handler. */ static void ipoib_parent_unregister_pre(struct net_device *ndev) { struct ipoib_dev_priv *priv = ipoib_priv(ndev); /* * ipoib_set_mac checks netif_running before pushing work, clearing * running ensures the it will not add more work. */ rtnl_lock(); dev_change_flags(priv->dev, priv->dev->flags & ~IFF_UP, NULL); rtnl_unlock(); /* ipoib_event() cannot be running once this returns */ ib_unregister_event_handler(&priv->event_handler); /* * Work on the queue grabs the rtnl lock, so this cannot be done while * also holding it. */ flush_workqueue(ipoib_workqueue); } static void ipoib_set_dev_features(struct ipoib_dev_priv *priv) { priv->hca_caps = priv->ca->attrs.device_cap_flags; priv->kernel_caps = priv->ca->attrs.kernel_cap_flags; if (priv->hca_caps & IB_DEVICE_UD_IP_CSUM) { priv->dev->hw_features |= NETIF_F_IP_CSUM | NETIF_F_RXCSUM; if (priv->kernel_caps & IBK_UD_TSO) priv->dev->hw_features |= NETIF_F_TSO; priv->dev->features |= priv->dev->hw_features; } } static int ipoib_parent_init(struct net_device *ndev) { struct ipoib_dev_priv *priv = ipoib_priv(ndev); struct ib_port_attr attr; int result; result = ib_query_port(priv->ca, priv->port, &attr); if (result) { pr_warn("%s: ib_query_port %d failed\n", priv->ca->name, priv->port); return result; } priv->max_ib_mtu = rdma_mtu_from_attr(priv->ca, priv->port, &attr); result = ib_query_pkey(priv->ca, priv->port, 0, &priv->pkey); if (result) { pr_warn("%s: ib_query_pkey port %d failed (ret = %d)\n", priv->ca->name, priv->port, result); return result; } result = rdma_query_gid(priv->ca, priv->port, 0, &priv->local_gid); if (result) { pr_warn("%s: rdma_query_gid port %d failed (ret = %d)\n", priv->ca->name, priv->port, result); return result; } dev_addr_mod(priv->dev, 4, priv->local_gid.raw, sizeof(union ib_gid)); SET_NETDEV_DEV(priv->dev, priv->ca->dev.parent); priv->dev->dev_port = priv->port - 1; /* Let's set this one too for backwards compatibility. */ priv->dev->dev_id = priv->port - 1; return 0; } static void ipoib_child_init(struct net_device *ndev) { struct ipoib_dev_priv *priv = ipoib_priv(ndev); struct ipoib_dev_priv *ppriv = ipoib_priv(priv->parent); priv->max_ib_mtu = ppriv->max_ib_mtu; set_bit(IPOIB_FLAG_SUBINTERFACE, &priv->flags); if (memchr_inv(priv->dev->dev_addr, 0, INFINIBAND_ALEN)) memcpy(&priv->local_gid, priv->dev->dev_addr + 4, sizeof(priv->local_gid)); else { __dev_addr_set(priv->dev, ppriv->dev->dev_addr, INFINIBAND_ALEN); memcpy(&priv->local_gid, &ppriv->local_gid, sizeof(priv->local_gid)); } } static int ipoib_ndo_init(struct net_device *ndev) { struct ipoib_dev_priv *priv = ipoib_priv(ndev); int rc; struct rdma_netdev *rn = netdev_priv(ndev); if (priv->parent) { ipoib_child_init(ndev); } else { rc = ipoib_parent_init(ndev); if (rc) return rc; } /* MTU will be reset when mcast join happens */ ndev->mtu = IPOIB_UD_MTU(priv->max_ib_mtu); priv->mcast_mtu = priv->admin_mtu = ndev->mtu; rn->mtu = priv->mcast_mtu; ndev->max_mtu = IPOIB_CM_MTU; ndev->neigh_priv_len = sizeof(struct ipoib_neigh); /* * Set the full membership bit, so that we join the right * broadcast group, etc. */ priv->pkey |= 0x8000; ndev->broadcast[8] = priv->pkey >> 8; ndev->broadcast[9] = priv->pkey & 0xff; set_bit(IPOIB_FLAG_DEV_ADDR_SET, &priv->flags); ipoib_set_dev_features(priv); rc = ipoib_dev_init(ndev); if (rc) { pr_warn("%s: failed to initialize device: %s port %d (ret = %d)\n", priv->ca->name, priv->dev->name, priv->port, rc); return rc; } if (priv->parent) { struct ipoib_dev_priv *ppriv = ipoib_priv(priv->parent); dev_hold(priv->parent); down_write(&ppriv->vlan_rwsem); list_add_tail(&priv->list, &ppriv->child_intfs); up_write(&ppriv->vlan_rwsem); } return 0; } static void ipoib_ndo_uninit(struct net_device *dev) { struct ipoib_dev_priv *priv = ipoib_priv(dev); ASSERT_RTNL(); /* * ipoib_remove_one guarantees the children are removed before the * parent, and that is the only place where a parent can be removed. */ WARN_ON(!list_empty(&priv->child_intfs)); if (priv->parent) { struct ipoib_dev_priv *ppriv = ipoib_priv(priv->parent); down_write(&ppriv->vlan_rwsem); list_del(&priv->list); up_write(&ppriv->vlan_rwsem); } ipoib_neigh_hash_uninit(dev); ipoib_ib_dev_cleanup(dev); /* no more works over the priv->wq */ if (priv->wq) { /* See ipoib_mcast_carrier_on_task() */ WARN_ON(test_bit(IPOIB_FLAG_OPER_UP, &priv->flags)); destroy_workqueue(priv->wq); priv->wq = NULL; } dev_put(priv->parent); } static int ipoib_set_vf_link_state(struct net_device *dev, int vf, int link_state) { struct ipoib_dev_priv *priv = ipoib_priv(dev); return ib_set_vf_link_state(priv->ca, vf, priv->port, link_state); } static int ipoib_get_vf_config(struct net_device *dev, int vf, struct ifla_vf_info *ivf) { struct ipoib_dev_priv *priv = ipoib_priv(dev); int err; err = ib_get_vf_config(priv->ca, vf, priv->port, ivf); if (err) return err; ivf->vf = vf; memcpy(ivf->mac, dev->dev_addr, dev->addr_len); return 0; } static int ipoib_set_vf_guid(struct net_device *dev, int vf, u64 guid, int type) { struct ipoib_dev_priv *priv = ipoib_priv(dev); if (type != IFLA_VF_IB_NODE_GUID && type != IFLA_VF_IB_PORT_GUID) return -EINVAL; return ib_set_vf_guid(priv->ca, vf, priv->port, guid, type); } static int ipoib_get_vf_guid(struct net_device *dev, int vf, struct ifla_vf_guid *node_guid, struct ifla_vf_guid *port_guid) { struct ipoib_dev_priv *priv = ipoib_priv(dev); return ib_get_vf_guid(priv->ca, vf, priv->port, node_guid, port_guid); } static int ipoib_get_vf_stats(struct net_device *dev, int vf, struct ifla_vf_stats *vf_stats) { struct ipoib_dev_priv *priv = ipoib_priv(dev); return ib_get_vf_stats(priv->ca, vf, priv->port, vf_stats); } static const struct header_ops ipoib_header_ops = { .create = ipoib_hard_header, }; static const struct net_device_ops ipoib_netdev_ops_pf = { .ndo_init = ipoib_ndo_init, .ndo_uninit = ipoib_ndo_uninit, .ndo_open = ipoib_open, .ndo_stop = ipoib_stop, .ndo_change_mtu = ipoib_change_mtu, .ndo_fix_features = ipoib_fix_features, .ndo_start_xmit = ipoib_start_xmit, .ndo_tx_timeout = ipoib_timeout, .ndo_set_rx_mode = ipoib_set_mcast_list, .ndo_get_iflink = ipoib_get_iflink, .ndo_set_vf_link_state = ipoib_set_vf_link_state, .ndo_get_vf_config = ipoib_get_vf_config, .ndo_get_vf_stats = ipoib_get_vf_stats, .ndo_get_vf_guid = ipoib_get_vf_guid, .ndo_set_vf_guid = ipoib_set_vf_guid, .ndo_set_mac_address = ipoib_set_mac, .ndo_get_stats64 = ipoib_get_stats, .ndo_eth_ioctl = ipoib_ioctl, }; static const struct net_device_ops ipoib_netdev_ops_vf = { .ndo_init = ipoib_ndo_init, .ndo_uninit = ipoib_ndo_uninit, .ndo_open = ipoib_open, .ndo_stop = ipoib_stop, .ndo_change_mtu = ipoib_change_mtu, .ndo_fix_features = ipoib_fix_features, .ndo_start_xmit = ipoib_start_xmit, .ndo_tx_timeout = ipoib_timeout, .ndo_set_rx_mode = ipoib_set_mcast_list, .ndo_get_iflink = ipoib_get_iflink, .ndo_get_stats64 = ipoib_get_stats, .ndo_eth_ioctl = ipoib_ioctl, }; static const struct net_device_ops ipoib_netdev_default_pf = { .ndo_init = ipoib_dev_init_default, .ndo_uninit = ipoib_dev_uninit_default, .ndo_open = ipoib_ib_dev_open_default, .ndo_stop = ipoib_ib_dev_stop_default, }; void ipoib_setup_common(struct net_device *dev) { dev->header_ops = &ipoib_header_ops; dev->netdev_ops = &ipoib_netdev_default_pf; ipoib_set_ethtool_ops(dev); dev->watchdog_timeo = 10 * HZ; dev->flags |= IFF_BROADCAST | IFF_MULTICAST; dev->hard_header_len = IPOIB_HARD_LEN; dev->addr_len = INFINIBAND_ALEN; dev->type = ARPHRD_INFINIBAND; dev->tx_queue_len = DEFAULT_TX_QUEUE_LEN; dev->features = (NETIF_F_VLAN_CHALLENGED | NETIF_F_HIGHDMA); netif_keep_dst(dev); memcpy(dev->broadcast, ipv4_bcast_addr, INFINIBAND_ALEN); /* * unregister_netdev always frees the netdev, we use this mode * consistently to unify all the various unregister paths, including * those connected to rtnl_link_ops which require it. */ dev->needs_free_netdev = true; } static void ipoib_build_priv(struct net_device *dev) { struct ipoib_dev_priv *priv = ipoib_priv(dev); priv->dev = dev; spin_lock_init(&priv->lock); init_rwsem(&priv->vlan_rwsem); mutex_init(&priv->mcast_mutex); INIT_LIST_HEAD(&priv->path_list); INIT_LIST_HEAD(&priv->child_intfs); INIT_LIST_HEAD(&priv->dead_ahs); INIT_LIST_HEAD(&priv->multicast_list); INIT_DELAYED_WORK(&priv->mcast_task, ipoib_mcast_join_task); INIT_WORK(&priv->carrier_on_task, ipoib_mcast_carrier_on_task); INIT_WORK(&priv->reschedule_napi_work, ipoib_napi_schedule_work); INIT_WORK(&priv->flush_light, ipoib_ib_dev_flush_light); INIT_WORK(&priv->flush_normal, ipoib_ib_dev_flush_normal); INIT_WORK(&priv->flush_heavy, ipoib_ib_dev_flush_heavy); INIT_WORK(&priv->restart_task, ipoib_mcast_restart_task); INIT_WORK(&priv->tx_timeout_work, ipoib_ib_tx_timeout_work); INIT_DELAYED_WORK(&priv->ah_reap_task, ipoib_reap_ah); INIT_DELAYED_WORK(&priv->neigh_reap_task, ipoib_reap_neigh); } static struct net_device *ipoib_alloc_netdev(struct ib_device *hca, u32 port, const char *name) { struct net_device *dev; dev = rdma_alloc_netdev(hca, port, RDMA_NETDEV_IPOIB, name, NET_NAME_UNKNOWN, ipoib_setup_common); if (!IS_ERR(dev) || PTR_ERR(dev) != -EOPNOTSUPP) return dev; dev = alloc_netdev(sizeof(struct rdma_netdev), name, NET_NAME_UNKNOWN, ipoib_setup_common); if (!dev) return ERR_PTR(-ENOMEM); return dev; } int ipoib_intf_init(struct ib_device *hca, u32 port, const char *name, struct net_device *dev) { struct rdma_netdev *rn = netdev_priv(dev); struct ipoib_dev_priv *priv; int rc; priv = kzalloc(sizeof(*priv), GFP_KERNEL); if (!priv) return -ENOMEM; priv->ca = hca; priv->port = port; rc = rdma_init_netdev(hca, port, RDMA_NETDEV_IPOIB, name, NET_NAME_UNKNOWN, ipoib_setup_common, dev); if (rc) { if (rc != -EOPNOTSUPP) goto out; rn->send = ipoib_send; rn->attach_mcast = ipoib_mcast_attach; rn->detach_mcast = ipoib_mcast_detach; rn->hca = hca; rc = netif_set_real_num_tx_queues(dev, 1); if (rc) goto out; rc = netif_set_real_num_rx_queues(dev, 1); if (rc) goto out; } priv->rn_ops = dev->netdev_ops; if (hca->attrs.kernel_cap_flags & IBK_VIRTUAL_FUNCTION) dev->netdev_ops = &ipoib_netdev_ops_vf; else dev->netdev_ops = &ipoib_netdev_ops_pf; rn->clnt_priv = priv; /* * Only the child register_netdev flows can handle priv_destructor * being set, so we force it to NULL here and handle manually until it * is safe to turn on. */ priv->next_priv_destructor = dev->priv_destructor; dev->priv_destructor = NULL; ipoib_build_priv(dev); return 0; out: kfree(priv); return rc; } struct net_device *ipoib_intf_alloc(struct ib_device *hca, u32 port, const char *name) { struct net_device *dev; int rc; dev = ipoib_alloc_netdev(hca, port, name); if (IS_ERR(dev)) return dev; rc = ipoib_intf_init(hca, port, name, dev); if (rc) { free_netdev(dev); return ERR_PTR(rc); } /* * Upon success the caller must ensure ipoib_intf_free is called or * register_netdevice succeed'd and priv_destructor is set to * ipoib_intf_free. */ return dev; } void ipoib_intf_free(struct net_device *dev) { struct ipoib_dev_priv *priv = ipoib_priv(dev); struct rdma_netdev *rn = netdev_priv(dev); dev->priv_destructor = priv->next_priv_destructor; if (dev->priv_destructor) dev->priv_destructor(dev); /* * There are some error flows around register_netdev failing that may * attempt to call priv_destructor twice, prevent that from happening. */ dev->priv_destructor = NULL; /* unregister/destroy is very complicated. Make bugs more obvious. */ rn->clnt_priv = NULL; kfree(priv); } static ssize_t pkey_show(struct device *dev, struct device_attribute *attr, char *buf) { struct net_device *ndev = to_net_dev(dev); struct ipoib_dev_priv *priv = ipoib_priv(ndev); return sysfs_emit(buf, "0x%04x\n", priv->pkey); } static DEVICE_ATTR_RO(pkey); static ssize_t umcast_show(struct device *dev, struct device_attribute *attr, char *buf) { struct net_device *ndev = to_net_dev(dev); struct ipoib_dev_priv *priv = ipoib_priv(ndev); return sysfs_emit(buf, "%d\n", test_bit(IPOIB_FLAG_UMCAST, &priv->flags)); } void ipoib_set_umcast(struct net_device *ndev, int umcast_val) { struct ipoib_dev_priv *priv = ipoib_priv(ndev); if (umcast_val > 0) { set_bit(IPOIB_FLAG_UMCAST, &priv->flags); ipoib_warn(priv, "ignoring multicast groups joined directly " "by userspace\n"); } else clear_bit(IPOIB_FLAG_UMCAST, &priv->flags); } static ssize_t umcast_store(struct device *dev, struct device_attribute *attr, const char *buf, size_t count) { unsigned long umcast_val = simple_strtoul(buf, NULL, 0); ipoib_set_umcast(to_net_dev(dev), umcast_val); return count; } static DEVICE_ATTR_RW(umcast); int ipoib_add_umcast_attr(struct net_device *dev) { return device_create_file(&dev->dev, &dev_attr_umcast); } static void set_base_guid(struct ipoib_dev_priv *priv, union ib_gid *gid) { struct ipoib_dev_priv *child_priv; struct net_device *netdev = priv->dev; netif_addr_lock_bh(netdev); memcpy(&priv->local_gid.global.interface_id, &gid->global.interface_id, sizeof(gid->global.interface_id)); dev_addr_mod(netdev, 4, (u8 *)&priv->local_gid, sizeof(priv->local_gid)); clear_bit(IPOIB_FLAG_DEV_ADDR_SET, &priv->flags); netif_addr_unlock_bh(netdev); if (!test_bit(IPOIB_FLAG_SUBINTERFACE, &priv->flags)) { down_read(&priv->vlan_rwsem); list_for_each_entry(child_priv, &priv->child_intfs, list) set_base_guid(child_priv, gid); up_read(&priv->vlan_rwsem); } } static int ipoib_check_lladdr(struct net_device *dev, struct sockaddr_storage *ss) { union ib_gid *gid = (union ib_gid *)(ss->__data + 4); int ret = 0; netif_addr_lock_bh(dev); /* Make sure the QPN, reserved and subnet prefix match the current * lladdr, it also makes sure the lladdr is unicast. */ if (memcmp(dev->dev_addr, ss->__data, 4 + sizeof(gid->global.subnet_prefix)) || gid->global.interface_id == 0) ret = -EINVAL; netif_addr_unlock_bh(dev); return ret; } static int ipoib_set_mac(struct net_device *dev, void *addr) { struct ipoib_dev_priv *priv = ipoib_priv(dev); struct sockaddr_storage *ss = addr; int ret; if (!(dev->priv_flags & IFF_LIVE_ADDR_CHANGE) && netif_running(dev)) return -EBUSY; ret = ipoib_check_lladdr(dev, ss); if (ret) return ret; set_base_guid(priv, (union ib_gid *)(ss->__data + 4)); queue_work(ipoib_workqueue, &priv->flush_light); return 0; } static ssize_t create_child_store(struct device *dev, struct device_attribute *attr, const char *buf, size_t count) { int pkey; int ret; if (sscanf(buf, "%i", &pkey) != 1) return -EINVAL; if (pkey <= 0 || pkey > 0xffff || pkey == 0x8000) return -EINVAL; ret = ipoib_vlan_add(to_net_dev(dev), pkey); return ret ? ret : count; } static DEVICE_ATTR_WO(create_child); static ssize_t delete_child_store(struct device *dev, struct device_attribute *attr, const char *buf, size_t count) { int pkey; int ret; if (sscanf(buf, "%i", &pkey) != 1) return -EINVAL; if (pkey < 0 || pkey > 0xffff) return -EINVAL; ret = ipoib_vlan_delete(to_net_dev(dev), pkey); return ret ? ret : count; } static DEVICE_ATTR_WO(delete_child); int ipoib_add_pkey_attr(struct net_device *dev) { return device_create_file(&dev->dev, &dev_attr_pkey); } /* * We erroneously exposed the iface's port number in the dev_id * sysfs field long after dev_port was introduced for that purpose[1], * and we need to stop everyone from relying on that. * Let's overload the shower routine for the dev_id file here * to gently bring the issue up. * * [1] https://www.spinics.net/lists/netdev/msg272123.html */ static ssize_t dev_id_show(struct device *dev, struct device_attribute *attr, char *buf) { struct net_device *ndev = to_net_dev(dev); /* * ndev->dev_port will be equal to 0 in old kernel prior to commit * 9b8b2a323008 ("IB/ipoib: Use dev_port to expose network interface * port numbers") Zero was chosen as special case for user space * applications to fallback and query dev_id to check if it has * different value or not. * * Don't print warning in such scenario. * * https://github.com/systemd/systemd/blob/master/src/udev/udev-builtin-net_id.c#L358 */ if (ndev->dev_port && ndev->dev_id == ndev->dev_port) netdev_info_once(ndev, "\"%s\" wants to know my dev_id. Should it look at dev_port instead? See Documentation/ABI/testing/sysfs-class-net for more info.\n", current->comm); return sysfs_emit(buf, "%#x\n", ndev->dev_id); } static DEVICE_ATTR_RO(dev_id); static int ipoib_intercept_dev_id_attr(struct net_device *dev) { device_remove_file(&dev->dev, &dev_attr_dev_id); return device_create_file(&dev->dev, &dev_attr_dev_id); } static struct net_device *ipoib_add_port(const char *format, struct ib_device *hca, u32 port) { struct rtnl_link_ops *ops = ipoib_get_link_ops(); struct rdma_netdev_alloc_params params; struct ipoib_dev_priv *priv; struct net_device *ndev; int result; ndev = ipoib_intf_alloc(hca, port, format); if (IS_ERR(ndev)) { pr_warn("%s, %d: ipoib_intf_alloc failed %ld\n", hca->name, port, PTR_ERR(ndev)); return ndev; } priv = ipoib_priv(ndev); INIT_IB_EVENT_HANDLER(&priv->event_handler, priv->ca, ipoib_event); ib_register_event_handler(&priv->event_handler); /* call event handler to ensure pkey in sync */ queue_work(ipoib_workqueue, &priv->flush_heavy); ndev->rtnl_link_ops = ipoib_get_link_ops(); result = register_netdev(ndev); if (result) { pr_warn("%s: couldn't register ipoib port %d; error %d\n", hca->name, port, result); ipoib_parent_unregister_pre(ndev); ipoib_intf_free(ndev); free_netdev(ndev); return ERR_PTR(result); } if (hca->ops.rdma_netdev_get_params) { int rc = hca->ops.rdma_netdev_get_params(hca, port, RDMA_NETDEV_IPOIB, ¶ms); if (!rc && ops->priv_size < params.sizeof_priv) ops->priv_size = params.sizeof_priv; } /* * We cannot set priv_destructor before register_netdev because we * need priv to be always valid during the error flow to execute * ipoib_parent_unregister_pre(). Instead handle it manually and only * enter priv_destructor mode once we are completely registered. */ ndev->priv_destructor = ipoib_intf_free; if (ipoib_intercept_dev_id_attr(ndev)) goto sysfs_failed; if (ipoib_cm_add_mode_attr(ndev)) goto sysfs_failed; if (ipoib_add_pkey_attr(ndev)) goto sysfs_failed; if (ipoib_add_umcast_attr(ndev)) goto sysfs_failed; if (device_create_file(&ndev->dev, &dev_attr_create_child)) goto sysfs_failed; if (device_create_file(&ndev->dev, &dev_attr_delete_child)) goto sysfs_failed; return ndev; sysfs_failed: ipoib_parent_unregister_pre(ndev); unregister_netdev(ndev); return ERR_PTR(-ENOMEM); } static int ipoib_add_one(struct ib_device *device) { struct list_head *dev_list; struct net_device *dev; struct ipoib_dev_priv *priv; unsigned int p; int count = 0; dev_list = kmalloc(sizeof(*dev_list), GFP_KERNEL); if (!dev_list) return -ENOMEM; INIT_LIST_HEAD(dev_list); rdma_for_each_port (device, p) { if (!rdma_protocol_ib(device, p)) continue; dev = ipoib_add_port("ib%d", device, p); if (!IS_ERR(dev)) { priv = ipoib_priv(dev); list_add_tail(&priv->list, dev_list); count++; } } if (!count) { kfree(dev_list); return -EOPNOTSUPP; } ib_set_client_data(device, &ipoib_client, dev_list); return 0; } static void ipoib_remove_one(struct ib_device *device, void *client_data) { struct ipoib_dev_priv *priv, *tmp, *cpriv, *tcpriv; struct list_head *dev_list = client_data; list_for_each_entry_safe(priv, tmp, dev_list, list) { LIST_HEAD(head); ipoib_parent_unregister_pre(priv->dev); rtnl_lock(); list_for_each_entry_safe(cpriv, tcpriv, &priv->child_intfs, list) unregister_netdevice_queue(cpriv->dev, &head); unregister_netdevice_queue(priv->dev, &head); unregister_netdevice_many(&head); rtnl_unlock(); } kfree(dev_list); } #ifdef CONFIG_INFINIBAND_IPOIB_DEBUG static struct notifier_block ipoib_netdev_notifier = { .notifier_call = ipoib_netdev_event, }; #endif static int __init ipoib_init_module(void) { int ret; ipoib_recvq_size = roundup_pow_of_two(ipoib_recvq_size); ipoib_recvq_size = min(ipoib_recvq_size, IPOIB_MAX_QUEUE_SIZE); ipoib_recvq_size = max(ipoib_recvq_size, IPOIB_MIN_QUEUE_SIZE); ipoib_sendq_size = roundup_pow_of_two(ipoib_sendq_size); ipoib_sendq_size = min(ipoib_sendq_size, IPOIB_MAX_QUEUE_SIZE); ipoib_sendq_size = max3(ipoib_sendq_size, 2 * MAX_SEND_CQE, IPOIB_MIN_QUEUE_SIZE); #ifdef CONFIG_INFINIBAND_IPOIB_CM ipoib_max_conn_qp = min(ipoib_max_conn_qp, IPOIB_CM_MAX_CONN_QP); ipoib_max_conn_qp = max(ipoib_max_conn_qp, 0); #endif /* * When copying small received packets, we only copy from the * linear data part of the SKB, so we rely on this condition. */ BUILD_BUG_ON(IPOIB_CM_COPYBREAK > IPOIB_CM_HEAD_SIZE); ipoib_register_debugfs(); /* * We create a global workqueue here that is used for all flush * operations. However, if you attempt to flush a workqueue * from a task on that same workqueue, it deadlocks the system. * We want to be able to flush the tasks associated with a * specific net device, so we also create a workqueue for each * netdevice. We queue up the tasks for that device only on * its private workqueue, and we only queue up flush events * on our global flush workqueue. This avoids the deadlocks. */ ipoib_workqueue = alloc_ordered_workqueue("ipoib_flush", 0); if (!ipoib_workqueue) { ret = -ENOMEM; goto err_fs; } ib_sa_register_client(&ipoib_sa_client); ret = ib_register_client(&ipoib_client); if (ret) goto err_sa; ret = ipoib_netlink_init(); if (ret) goto err_client; #ifdef CONFIG_INFINIBAND_IPOIB_DEBUG register_netdevice_notifier(&ipoib_netdev_notifier); #endif return 0; err_client: ib_unregister_client(&ipoib_client); err_sa: ib_sa_unregister_client(&ipoib_sa_client); destroy_workqueue(ipoib_workqueue); err_fs: ipoib_unregister_debugfs(); return ret; } static void __exit ipoib_cleanup_module(void) { #ifdef CONFIG_INFINIBAND_IPOIB_DEBUG unregister_netdevice_notifier(&ipoib_netdev_notifier); #endif ipoib_netlink_fini(); ib_unregister_client(&ipoib_client); ib_sa_unregister_client(&ipoib_sa_client); ipoib_unregister_debugfs(); destroy_workqueue(ipoib_workqueue); } module_init(ipoib_init_module); module_exit(ipoib_cleanup_module); |
| 1043 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 | /* SPDX-License-Identifier: GPL-2.0-only */ /* * Copyright (C) 2012 ARM Ltd. */ #ifndef __ASM_FP_H #define __ASM_FP_H #include <asm/errno.h> #include <asm/ptrace.h> #include <asm/processor.h> #include <asm/sigcontext.h> #include <asm/sysreg.h> #ifndef __ASSEMBLY__ #include <linux/bitmap.h> #include <linux/build_bug.h> #include <linux/bug.h> #include <linux/cache.h> #include <linux/init.h> #include <linux/stddef.h> #include <linux/types.h> /* Masks for extracting the FPSR and FPCR from the FPSCR */ #define VFP_FPSCR_STAT_MASK 0xf800009f #define VFP_FPSCR_CTRL_MASK 0x07f79f00 /* * The VFP state has 32x64-bit registers and a single 32-bit * control/status register. */ #define VFP_STATE_SIZE ((32 * 8) + 4) static inline unsigned long cpacr_save_enable_kernel_sve(void) { unsigned long old = read_sysreg(cpacr_el1); unsigned long set = CPACR_EL1_FPEN_EL1EN | CPACR_EL1_ZEN_EL1EN; write_sysreg(old | set, cpacr_el1); isb(); return old; } static inline unsigned long cpacr_save_enable_kernel_sme(void) { unsigned long old = read_sysreg(cpacr_el1); unsigned long set = CPACR_EL1_FPEN_EL1EN | CPACR_EL1_SMEN_EL1EN; write_sysreg(old | set, cpacr_el1); isb(); return old; } static inline void cpacr_restore(unsigned long cpacr) { write_sysreg(cpacr, cpacr_el1); isb(); } /* * When we defined the maximum SVE vector length we defined the ABI so * that the maximum vector length included all the reserved for future * expansion bits in ZCR rather than those just currently defined by * the architecture. Using this length to allocate worst size buffers * results in excessively large allocations, and this effect is even * more pronounced for SME due to ZA. Define more suitable VLs for * these situations. */ #define ARCH_SVE_VQ_MAX ((ZCR_ELx_LEN_MASK >> ZCR_ELx_LEN_SHIFT) + 1) #define SME_VQ_MAX ((SMCR_ELx_LEN_MASK >> SMCR_ELx_LEN_SHIFT) + 1) struct task_struct; extern void fpsimd_save_state(struct user_fpsimd_state *state); extern void fpsimd_load_state(struct user_fpsimd_state *state); extern void fpsimd_thread_switch(struct task_struct *next); extern void fpsimd_flush_thread(void); extern void fpsimd_signal_preserve_current_state(void); extern void fpsimd_preserve_current_state(void); extern void fpsimd_restore_current_state(void); extern void fpsimd_update_current_state(struct user_fpsimd_state const *state); extern void fpsimd_kvm_prepare(void); struct cpu_fp_state { struct user_fpsimd_state *st; void *sve_state; void *sme_state; u64 *svcr; u64 *fpmr; unsigned int sve_vl; unsigned int sme_vl; enum fp_type *fp_type; enum fp_type to_save; }; extern void fpsimd_bind_state_to_cpu(struct cpu_fp_state *fp_state); extern void fpsimd_flush_task_state(struct task_struct *target); extern void fpsimd_save_and_flush_cpu_state(void); static inline bool thread_sm_enabled(struct thread_struct *thread) { return system_supports_sme() && (thread->svcr & SVCR_SM_MASK); } static inline bool thread_za_enabled(struct thread_struct *thread) { return system_supports_sme() && (thread->svcr & SVCR_ZA_MASK); } /* Maximum VL that SVE/SME VL-agnostic software can transparently support */ #define VL_ARCH_MAX 0x100 /* Offset of FFR in the SVE register dump */ static inline size_t sve_ffr_offset(int vl) { return SVE_SIG_FFR_OFFSET(sve_vq_from_vl(vl)) - SVE_SIG_REGS_OFFSET; } static inline void *sve_pffr(struct thread_struct *thread) { unsigned int vl; if (system_supports_sme() && thread_sm_enabled(thread)) vl = thread_get_sme_vl(thread); else vl = thread_get_sve_vl(thread); return (char *)thread->sve_state + sve_ffr_offset(vl); } static inline void *thread_zt_state(struct thread_struct *thread) { /* The ZT register state is stored immediately after the ZA state */ unsigned int sme_vq = sve_vq_from_vl(thread_get_sme_vl(thread)); return thread->sme_state + ZA_SIG_REGS_SIZE(sme_vq); } extern void sve_save_state(void *state, u32 *pfpsr, int save_ffr); extern void sve_load_state(void const *state, u32 const *pfpsr, int restore_ffr); extern void sve_flush_live(bool flush_ffr, unsigned long vq_minus_1); extern unsigned int sve_get_vl(void); extern void sve_set_vq(unsigned long vq_minus_1); extern void sme_set_vq(unsigned long vq_minus_1); extern void sme_save_state(void *state, int zt); extern void sme_load_state(void const *state, int zt); struct arm64_cpu_capabilities; extern void cpu_enable_fpsimd(const struct arm64_cpu_capabilities *__unused); extern void cpu_enable_sve(const struct arm64_cpu_capabilities *__unused); extern void cpu_enable_sme(const struct arm64_cpu_capabilities *__unused); extern void cpu_enable_sme2(const struct arm64_cpu_capabilities *__unused); extern void cpu_enable_fa64(const struct arm64_cpu_capabilities *__unused); extern void cpu_enable_fpmr(const struct arm64_cpu_capabilities *__unused); /* * Helpers to translate bit indices in sve_vq_map to VQ values (and * vice versa). This allows find_next_bit() to be used to find the * _maximum_ VQ not exceeding a certain value. */ static inline unsigned int __vq_to_bit(unsigned int vq) { return SVE_VQ_MAX - vq; } static inline unsigned int __bit_to_vq(unsigned int bit) { return SVE_VQ_MAX - bit; } struct vl_info { enum vec_type type; const char *name; /* For display purposes */ /* Minimum supported vector length across all CPUs */ int min_vl; /* Maximum supported vector length across all CPUs */ int max_vl; int max_virtualisable_vl; /* * Set of available vector lengths, * where length vq encoded as bit __vq_to_bit(vq): */ DECLARE_BITMAP(vq_map, SVE_VQ_MAX); /* Set of vector lengths present on at least one cpu: */ DECLARE_BITMAP(vq_partial_map, SVE_VQ_MAX); }; #ifdef CONFIG_ARM64_SVE extern void sve_alloc(struct task_struct *task, bool flush); extern void fpsimd_release_task(struct task_struct *task); extern void fpsimd_sync_to_sve(struct task_struct *task); extern void fpsimd_force_sync_to_sve(struct task_struct *task); extern void sve_sync_to_fpsimd(struct task_struct *task); extern void sve_sync_from_fpsimd_zeropad(struct task_struct *task); extern int vec_set_vector_length(struct task_struct *task, enum vec_type type, unsigned long vl, unsigned long flags); extern int sve_set_current_vl(unsigned long arg); extern int sve_get_current_vl(void); static inline void sve_user_disable(void) { sysreg_clear_set(cpacr_el1, CPACR_EL1_ZEN_EL0EN, 0); } static inline void sve_user_enable(void) { sysreg_clear_set(cpacr_el1, 0, CPACR_EL1_ZEN_EL0EN); } #define sve_cond_update_zcr_vq(val, reg) \ do { \ u64 __zcr = read_sysreg_s((reg)); \ u64 __new = __zcr & ~ZCR_ELx_LEN_MASK; \ __new |= (val) & ZCR_ELx_LEN_MASK; \ if (__zcr != __new) \ write_sysreg_s(__new, (reg)); \ } while (0) /* * Probing and setup functions. * Calls to these functions must be serialised with one another. */ enum vec_type; extern void __init vec_init_vq_map(enum vec_type type); extern void vec_update_vq_map(enum vec_type type); extern int vec_verify_vq_map(enum vec_type type); extern void __init sve_setup(void); extern __ro_after_init struct vl_info vl_info[ARM64_VEC_MAX]; static inline void write_vl(enum vec_type type, u64 val) { u64 tmp; switch (type) { #ifdef CONFIG_ARM64_SVE case ARM64_VEC_SVE: tmp = read_sysreg_s(SYS_ZCR_EL1) & ~ZCR_ELx_LEN_MASK; write_sysreg_s(tmp | val, SYS_ZCR_EL1); break; #endif #ifdef CONFIG_ARM64_SME case ARM64_VEC_SME: tmp = read_sysreg_s(SYS_SMCR_EL1) & ~SMCR_ELx_LEN_MASK; write_sysreg_s(tmp | val, SYS_SMCR_EL1); break; #endif default: WARN_ON_ONCE(1); break; } } static inline int vec_max_vl(enum vec_type type) { return vl_info[type].max_vl; } static inline int vec_max_virtualisable_vl(enum vec_type type) { return vl_info[type].max_virtualisable_vl; } static inline int sve_max_vl(void) { return vec_max_vl(ARM64_VEC_SVE); } static inline int sve_max_virtualisable_vl(void) { return vec_max_virtualisable_vl(ARM64_VEC_SVE); } /* Ensure vq >= SVE_VQ_MIN && vq <= SVE_VQ_MAX before calling this function */ static inline bool vq_available(enum vec_type type, unsigned int vq) { return test_bit(__vq_to_bit(vq), vl_info[type].vq_map); } static inline bool sve_vq_available(unsigned int vq) { return vq_available(ARM64_VEC_SVE, vq); } size_t sve_state_size(struct task_struct const *task); #else /* ! CONFIG_ARM64_SVE */ static inline void sve_alloc(struct task_struct *task, bool flush) { } static inline void fpsimd_release_task(struct task_struct *task) { } static inline void sve_sync_to_fpsimd(struct task_struct *task) { } static inline void sve_sync_from_fpsimd_zeropad(struct task_struct *task) { } static inline int sve_max_virtualisable_vl(void) { return 0; } static inline int sve_set_current_vl(unsigned long arg) { return -EINVAL; } static inline int sve_get_current_vl(void) { return -EINVAL; } static inline int sve_max_vl(void) { return -EINVAL; } static inline bool sve_vq_available(unsigned int vq) { return false; } static inline void sve_user_disable(void) { BUILD_BUG(); } static inline void sve_user_enable(void) { BUILD_BUG(); } #define sve_cond_update_zcr_vq(val, reg) do { } while (0) static inline void vec_init_vq_map(enum vec_type t) { } static inline void vec_update_vq_map(enum vec_type t) { } static inline int vec_verify_vq_map(enum vec_type t) { return 0; } static inline void sve_setup(void) { } static inline size_t sve_state_size(struct task_struct const *task) { return 0; } #endif /* ! CONFIG_ARM64_SVE */ #ifdef CONFIG_ARM64_SME static inline void sme_user_disable(void) { sysreg_clear_set(cpacr_el1, CPACR_EL1_SMEN_EL0EN, 0); } static inline void sme_user_enable(void) { sysreg_clear_set(cpacr_el1, 0, CPACR_EL1_SMEN_EL0EN); } static inline void sme_smstart_sm(void) { asm volatile(__msr_s(SYS_SVCR_SMSTART_SM_EL0, "xzr")); } static inline void sme_smstop_sm(void) { asm volatile(__msr_s(SYS_SVCR_SMSTOP_SM_EL0, "xzr")); } static inline void sme_smstop(void) { asm volatile(__msr_s(SYS_SVCR_SMSTOP_SMZA_EL0, "xzr")); } extern void __init sme_setup(void); static inline int sme_max_vl(void) { return vec_max_vl(ARM64_VEC_SME); } static inline int sme_max_virtualisable_vl(void) { return vec_max_virtualisable_vl(ARM64_VEC_SME); } extern void sme_alloc(struct task_struct *task, bool flush); extern unsigned int sme_get_vl(void); extern int sme_set_current_vl(unsigned long arg); extern int sme_get_current_vl(void); extern void sme_suspend_exit(void); /* * Return how many bytes of memory are required to store the full SME * specific state for task, given task's currently configured vector * length. */ static inline size_t sme_state_size(struct task_struct const *task) { unsigned int vl = task_get_sme_vl(task); size_t size; size = ZA_SIG_REGS_SIZE(sve_vq_from_vl(vl)); if (system_supports_sme2()) size += ZT_SIG_REG_SIZE; return size; } #else static inline void sme_user_disable(void) { BUILD_BUG(); } static inline void sme_user_enable(void) { BUILD_BUG(); } static inline void sme_smstart_sm(void) { } static inline void sme_smstop_sm(void) { } static inline void sme_smstop(void) { } static inline void sme_alloc(struct task_struct *task, bool flush) { } static inline void sme_setup(void) { } static inline unsigned int sme_get_vl(void) { return 0; } static inline int sme_max_vl(void) { return 0; } static inline int sme_max_virtualisable_vl(void) { return 0; } static inline int sme_set_current_vl(unsigned long arg) { return -EINVAL; } static inline int sme_get_current_vl(void) { return -EINVAL; } static inline void sme_suspend_exit(void) { } static inline size_t sme_state_size(struct task_struct const *task) { return 0; } #endif /* ! CONFIG_ARM64_SME */ /* For use by EFI runtime services calls only */ extern void __efi_fpsimd_begin(void); extern void __efi_fpsimd_end(void); #endif #endif |
| 14 1 13 14 15 15 5 5 5 5 5 5 5 5 5 5 5 5 5 5 5 5 5 5 5 5 5 5 5 5 5 5 5 5 5 5 5 5 5 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 | // SPDX-License-Identifier: GPL-2.0 /* * linux/fs/attr.c * * Copyright (C) 1991, 1992 Linus Torvalds * changes by Thomas Schoebel-Theuer */ #include <linux/export.h> #include <linux/time.h> #include <linux/mm.h> #include <linux/string.h> #include <linux/sched/signal.h> #include <linux/capability.h> #include <linux/fsnotify.h> #include <linux/fcntl.h> #include <linux/filelock.h> #include <linux/security.h> /** * setattr_should_drop_sgid - determine whether the setgid bit needs to be * removed * @idmap: idmap of the mount @inode was found from * @inode: inode to check * * This function determines whether the setgid bit needs to be removed. * We retain backwards compatibility and require setgid bit to be removed * unconditionally if S_IXGRP is set. Otherwise we have the exact same * requirements as setattr_prepare() and setattr_copy(). * * Return: ATTR_KILL_SGID if setgid bit needs to be removed, 0 otherwise. */ int setattr_should_drop_sgid(struct mnt_idmap *idmap, const struct inode *inode) { umode_t mode = inode->i_mode; if (!(mode & S_ISGID)) return 0; if (mode & S_IXGRP) return ATTR_KILL_SGID; if (!in_group_or_capable(idmap, inode, i_gid_into_vfsgid(idmap, inode))) return ATTR_KILL_SGID; return 0; } EXPORT_SYMBOL(setattr_should_drop_sgid); /** * setattr_should_drop_suidgid - determine whether the set{g,u}id bit needs to * be dropped * @idmap: idmap of the mount @inode was found from * @inode: inode to check * * This function determines whether the set{g,u}id bits need to be removed. * If the setuid bit needs to be removed ATTR_KILL_SUID is returned. If the * setgid bit needs to be removed ATTR_KILL_SGID is returned. If both * set{g,u}id bits need to be removed the corresponding mask of both flags is * returned. * * Return: A mask of ATTR_KILL_S{G,U}ID indicating which - if any - setid bits * to remove, 0 otherwise. */ int setattr_should_drop_suidgid(struct mnt_idmap *idmap, struct inode *inode) { umode_t mode = inode->i_mode; int kill = 0; /* suid always must be killed */ if (unlikely(mode & S_ISUID)) kill = ATTR_KILL_SUID; kill |= setattr_should_drop_sgid(idmap, inode); if (unlikely(kill && !capable(CAP_FSETID) && S_ISREG(mode))) return kill; return 0; } EXPORT_SYMBOL(setattr_should_drop_suidgid); /** * chown_ok - verify permissions to chown inode * @idmap: idmap of the mount @inode was found from * @inode: inode to check permissions on * @ia_vfsuid: uid to chown @inode to * * If the inode has been found through an idmapped mount the idmap of * the vfsmount must be passed through @idmap. This function will then * take care to map the inode according to @idmap before checking * permissions. On non-idmapped mounts or if permission checking is to be * performed on the raw inode simply pass @nop_mnt_idmap. */ static bool chown_ok(struct mnt_idmap *idmap, const struct inode *inode, vfsuid_t ia_vfsuid) { vfsuid_t vfsuid = i_uid_into_vfsuid(idmap, inode); if (vfsuid_eq_kuid(vfsuid, current_fsuid()) && vfsuid_eq(ia_vfsuid, vfsuid)) return true; if (capable_wrt_inode_uidgid(idmap, inode, CAP_CHOWN)) return true; if (!vfsuid_valid(vfsuid) && ns_capable(inode->i_sb->s_user_ns, CAP_CHOWN)) return true; return false; } /** * chgrp_ok - verify permissions to chgrp inode * @idmap: idmap of the mount @inode was found from * @inode: inode to check permissions on * @ia_vfsgid: gid to chown @inode to * * If the inode has been found through an idmapped mount the idmap of * the vfsmount must be passed through @idmap. This function will then * take care to map the inode according to @idmap before checking * permissions. On non-idmapped mounts or if permission checking is to be * performed on the raw inode simply pass @nop_mnt_idmap. */ static bool chgrp_ok(struct mnt_idmap *idmap, const struct inode *inode, vfsgid_t ia_vfsgid) { vfsgid_t vfsgid = i_gid_into_vfsgid(idmap, inode); vfsuid_t vfsuid = i_uid_into_vfsuid(idmap, inode); if (vfsuid_eq_kuid(vfsuid, current_fsuid())) { if (vfsgid_eq(ia_vfsgid, vfsgid)) return true; if (vfsgid_in_group_p(ia_vfsgid)) return true; } if (capable_wrt_inode_uidgid(idmap, inode, CAP_CHOWN)) return true; if (!vfsgid_valid(vfsgid) && ns_capable(inode->i_sb->s_user_ns, CAP_CHOWN)) return true; return false; } /** * setattr_prepare - check if attribute changes to a dentry are allowed * @idmap: idmap of the mount the inode was found from * @dentry: dentry to check * @attr: attributes to change * * Check if we are allowed to change the attributes contained in @attr * in the given dentry. This includes the normal unix access permission * checks, as well as checks for rlimits and others. The function also clears * SGID bit from mode if user is not allowed to set it. Also file capabilities * and IMA extended attributes are cleared if ATTR_KILL_PRIV is set. * * If the inode has been found through an idmapped mount the idmap of * the vfsmount must be passed through @idmap. This function will then * take care to map the inode according to @idmap before checking * permissions. On non-idmapped mounts or if permission checking is to be * performed on the raw inode simply pass @nop_mnt_idmap. * * Should be called as the first thing in ->setattr implementations, * possibly after taking additional locks. */ int setattr_prepare(struct mnt_idmap *idmap, struct dentry *dentry, struct iattr *attr) { struct inode *inode = d_inode(dentry); unsigned int ia_valid = attr->ia_valid; /* * First check size constraints. These can't be overriden using * ATTR_FORCE. */ if (ia_valid & ATTR_SIZE) { int error = inode_newsize_ok(inode, attr->ia_size); if (error) return error; } /* If force is set do it anyway. */ if (ia_valid & ATTR_FORCE) goto kill_priv; /* Make sure a caller can chown. */ if ((ia_valid & ATTR_UID) && !chown_ok(idmap, inode, attr->ia_vfsuid)) return -EPERM; /* Make sure caller can chgrp. */ if ((ia_valid & ATTR_GID) && !chgrp_ok(idmap, inode, attr->ia_vfsgid)) return -EPERM; /* Make sure a caller can chmod. */ if (ia_valid & ATTR_MODE) { vfsgid_t vfsgid; if (!inode_owner_or_capable(idmap, inode)) return -EPERM; if (ia_valid & ATTR_GID) vfsgid = attr->ia_vfsgid; else vfsgid = i_gid_into_vfsgid(idmap, inode); /* Also check the setgid bit! */ if (!in_group_or_capable(idmap, inode, vfsgid)) attr->ia_mode &= ~S_ISGID; } /* Check for setting the inode time. */ if (ia_valid & (ATTR_MTIME_SET | ATTR_ATIME_SET | ATTR_TIMES_SET)) { if (!inode_owner_or_capable(idmap, inode)) return -EPERM; } kill_priv: /* User has permission for the change */ if (ia_valid & ATTR_KILL_PRIV) { int error; error = security_inode_killpriv(idmap, dentry); if (error) return error; } return 0; } EXPORT_SYMBOL(setattr_prepare); /** * inode_newsize_ok - may this inode be truncated to a given size * @inode: the inode to be truncated * @offset: the new size to assign to the inode * * inode_newsize_ok must be called with i_mutex held. * * inode_newsize_ok will check filesystem limits and ulimits to check that the * new inode size is within limits. inode_newsize_ok will also send SIGXFSZ * when necessary. Caller must not proceed with inode size change if failure is * returned. @inode must be a file (not directory), with appropriate * permissions to allow truncate (inode_newsize_ok does NOT check these * conditions). * * Return: 0 on success, -ve errno on failure */ int inode_newsize_ok(const struct inode *inode, loff_t offset) { if (offset < 0) return -EINVAL; if (inode->i_size < offset) { unsigned long limit; limit = rlimit(RLIMIT_FSIZE); if (limit != RLIM_INFINITY && offset > limit) goto out_sig; if (offset > inode->i_sb->s_maxbytes) goto out_big; } else { /* * truncation of in-use swapfiles is disallowed - it would * cause subsequent swapout to scribble on the now-freed * blocks. */ if (IS_SWAPFILE(inode)) return -ETXTBSY; } return 0; out_sig: send_sig(SIGXFSZ, current, 0); out_big: return -EFBIG; } EXPORT_SYMBOL(inode_newsize_ok); /** * setattr_copy_mgtime - update timestamps for mgtime inodes * @inode: inode timestamps to be updated * @attr: attrs for the update * * With multigrain timestamps, take more care to prevent races when * updating the ctime. Always update the ctime to the very latest using * the standard mechanism, and use that to populate the atime and mtime * appropriately (unless those are being set to specific values). */ static void setattr_copy_mgtime(struct inode *inode, const struct iattr *attr) { unsigned int ia_valid = attr->ia_valid; struct timespec64 now; if (ia_valid & ATTR_CTIME) { /* * In the case of an update for a write delegation, we must respect * the value in ia_ctime and not use the current time. */ if (ia_valid & ATTR_DELEG) now = inode_set_ctime_deleg(inode, attr->ia_ctime); else now = inode_set_ctime_current(inode); } else { /* If ATTR_CTIME isn't set, then ATTR_MTIME shouldn't be either. */ WARN_ON_ONCE(ia_valid & ATTR_MTIME); now = current_time(inode); } if (ia_valid & ATTR_ATIME_SET) inode_set_atime_to_ts(inode, attr->ia_atime); else if (ia_valid & ATTR_ATIME) inode_set_atime_to_ts(inode, now); if (ia_valid & ATTR_MTIME_SET) inode_set_mtime_to_ts(inode, attr->ia_mtime); else if (ia_valid & ATTR_MTIME) inode_set_mtime_to_ts(inode, now); } /** * setattr_copy - copy simple metadata updates into the generic inode * @idmap: idmap of the mount the inode was found from * @inode: the inode to be updated * @attr: the new attributes * * setattr_copy must be called with i_mutex held. * * setattr_copy updates the inode's metadata with that specified * in attr on idmapped mounts. Necessary permission checks to determine * whether or not the S_ISGID property needs to be removed are performed with * the correct idmapped mount permission helpers. * Noticeably missing is inode size update, which is more complex * as it requires pagecache updates. * * If the inode has been found through an idmapped mount the idmap of * the vfsmount must be passed through @idmap. This function will then * take care to map the inode according to @idmap before checking * permissions. On non-idmapped mounts or if permission checking is to be * performed on the raw inode simply pass @nop_mnt_idmap. * * The inode is not marked as dirty after this operation. The rationale is * that for "simple" filesystems, the struct inode is the inode storage. * The caller is free to mark the inode dirty afterwards if needed. */ void setattr_copy(struct mnt_idmap *idmap, struct inode *inode, const struct iattr *attr) { unsigned int ia_valid = attr->ia_valid; i_uid_update(idmap, attr, inode); i_gid_update(idmap, attr, inode); if (ia_valid & ATTR_MODE) { umode_t mode = attr->ia_mode; if (!in_group_or_capable(idmap, inode, i_gid_into_vfsgid(idmap, inode))) mode &= ~S_ISGID; inode->i_mode = mode; } if (is_mgtime(inode)) return setattr_copy_mgtime(inode, attr); if (ia_valid & ATTR_ATIME) inode_set_atime_to_ts(inode, attr->ia_atime); if (ia_valid & ATTR_MTIME) inode_set_mtime_to_ts(inode, attr->ia_mtime); if (ia_valid & ATTR_CTIME) { if (ia_valid & ATTR_DELEG) inode_set_ctime_deleg(inode, attr->ia_ctime); else inode_set_ctime_to_ts(inode, attr->ia_ctime); } } EXPORT_SYMBOL(setattr_copy); int may_setattr(struct mnt_idmap *idmap, struct inode *inode, unsigned int ia_valid) { int error; if (ia_valid & (ATTR_MODE | ATTR_UID | ATTR_GID | ATTR_TIMES_SET)) { if (IS_IMMUTABLE(inode) || IS_APPEND(inode)) return -EPERM; } /* * If utimes(2) and friends are called with times == NULL (or both * times are UTIME_NOW), then we need to check for write permission */ if (ia_valid & ATTR_TOUCH) { if (IS_IMMUTABLE(inode)) return -EPERM; if (!inode_owner_or_capable(idmap, inode)) { error = inode_permission(idmap, inode, MAY_WRITE); if (error) return error; } } return 0; } EXPORT_SYMBOL(may_setattr); /** * notify_change - modify attributes of a filesystem object * @idmap: idmap of the mount the inode was found from * @dentry: object affected * @attr: new attributes * @delegated_inode: returns inode, if the inode is delegated * * The caller must hold the i_mutex on the affected object. * * If notify_change discovers a delegation in need of breaking, * it will return -EWOULDBLOCK and return a reference to the inode in * delegated_inode. The caller should then break the delegation and * retry. Because breaking a delegation may take a long time, the * caller should drop the i_mutex before doing so. * * Alternatively, a caller may pass NULL for delegated_inode. This may * be appropriate for callers that expect the underlying filesystem not * to be NFS exported. Also, passing NULL is fine for callers holding * the file open for write, as there can be no conflicting delegation in * that case. * * If the inode has been found through an idmapped mount the idmap of * the vfsmount must be passed through @idmap. This function will then * take care to map the inode according to @idmap before checking * permissions. On non-idmapped mounts or if permission checking is to be * performed on the raw inode simply pass @nop_mnt_idmap. */ int notify_change(struct mnt_idmap *idmap, struct dentry *dentry, struct iattr *attr, struct inode **delegated_inode) { struct inode *inode = dentry->d_inode; umode_t mode = inode->i_mode; int error; struct timespec64 now; unsigned int ia_valid = attr->ia_valid; WARN_ON_ONCE(!inode_is_locked(inode)); error = may_setattr(idmap, inode, ia_valid); if (error) return error; if ((ia_valid & ATTR_MODE)) { /* * Don't allow changing the mode of symlinks: * * (1) The vfs doesn't take the mode of symlinks into account * during permission checking. * (2) This has never worked correctly. Most major filesystems * did return EOPNOTSUPP due to interactions with POSIX ACLs * but did still updated the mode of the symlink. * This inconsistency led system call wrapper providers such * as libc to block changing the mode of symlinks with * EOPNOTSUPP already. * (3) To even do this in the first place one would have to use * specific file descriptors and quite some effort. */ if (S_ISLNK(inode->i_mode)) return -EOPNOTSUPP; /* Flag setting protected by i_mutex */ if (is_sxid(attr->ia_mode)) inode->i_flags &= ~S_NOSEC; } now = current_time(inode); attr->ia_ctime = now; if (!(ia_valid & ATTR_ATIME_SET)) attr->ia_atime = now; else attr->ia_atime = timestamp_truncate(attr->ia_atime, inode); if (!(ia_valid & ATTR_MTIME_SET)) attr->ia_mtime = now; else attr->ia_mtime = timestamp_truncate(attr->ia_mtime, inode); if (ia_valid & ATTR_KILL_PRIV) { error = security_inode_need_killpriv(dentry); if (error < 0) return error; if (error == 0) ia_valid = attr->ia_valid &= ~ATTR_KILL_PRIV; } /* * We now pass ATTR_KILL_S*ID to the lower level setattr function so * that the function has the ability to reinterpret a mode change * that's due to these bits. This adds an implicit restriction that * no function will ever call notify_change with both ATTR_MODE and * ATTR_KILL_S*ID set. */ if ((ia_valid & (ATTR_KILL_SUID|ATTR_KILL_SGID)) && (ia_valid & ATTR_MODE)) BUG(); if (ia_valid & ATTR_KILL_SUID) { if (mode & S_ISUID) { ia_valid = attr->ia_valid |= ATTR_MODE; attr->ia_mode = (inode->i_mode & ~S_ISUID); } } if (ia_valid & ATTR_KILL_SGID) { if (mode & S_ISGID) { if (!(ia_valid & ATTR_MODE)) { ia_valid = attr->ia_valid |= ATTR_MODE; attr->ia_mode = inode->i_mode; } attr->ia_mode &= ~S_ISGID; } } if (!(attr->ia_valid & ~(ATTR_KILL_SUID | ATTR_KILL_SGID))) return 0; /* * Verify that uid/gid changes are valid in the target * namespace of the superblock. */ if (ia_valid & ATTR_UID && !vfsuid_has_fsmapping(idmap, inode->i_sb->s_user_ns, attr->ia_vfsuid)) return -EOVERFLOW; if (ia_valid & ATTR_GID && !vfsgid_has_fsmapping(idmap, inode->i_sb->s_user_ns, attr->ia_vfsgid)) return -EOVERFLOW; /* Don't allow modifications of files with invalid uids or * gids unless those uids & gids are being made valid. */ if (!(ia_valid & ATTR_UID) && !vfsuid_valid(i_uid_into_vfsuid(idmap, inode))) return -EOVERFLOW; if (!(ia_valid & ATTR_GID) && !vfsgid_valid(i_gid_into_vfsgid(idmap, inode))) return -EOVERFLOW; error = security_inode_setattr(idmap, dentry, attr); if (error) return error; /* * If ATTR_DELEG is set, then these attributes are being set on * behalf of the holder of a write delegation. We want to avoid * breaking the delegation in this case. */ if (!(ia_valid & ATTR_DELEG)) { error = try_break_deleg(inode, delegated_inode); if (error) return error; } if (inode->i_op->setattr) error = inode->i_op->setattr(idmap, dentry, attr); else error = simple_setattr(idmap, dentry, attr); if (!error) { fsnotify_change(dentry, ia_valid); security_inode_post_setattr(idmap, dentry, ia_valid); } return error; } EXPORT_SYMBOL(notify_change); |
| 78 572 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 | /* SPDX-License-Identifier: GPL-2.0 */ /* * Copyright (c) 2021, Google LLC. * Pasha Tatashin <pasha.tatashin@soleen.com> */ #ifndef __LINUX_PAGE_TABLE_CHECK_H #define __LINUX_PAGE_TABLE_CHECK_H #ifdef CONFIG_PAGE_TABLE_CHECK #include <linux/jump_label.h> extern struct static_key_true page_table_check_disabled; extern struct page_ext_operations page_table_check_ops; void __page_table_check_zero(struct page *page, unsigned int order); void __page_table_check_pte_clear(struct mm_struct *mm, pte_t pte); void __page_table_check_pmd_clear(struct mm_struct *mm, pmd_t pmd); void __page_table_check_pud_clear(struct mm_struct *mm, pud_t pud); void __page_table_check_ptes_set(struct mm_struct *mm, pte_t *ptep, pte_t pte, unsigned int nr); void __page_table_check_pmd_set(struct mm_struct *mm, pmd_t *pmdp, pmd_t pmd); void __page_table_check_pud_set(struct mm_struct *mm, pud_t *pudp, pud_t pud); void __page_table_check_pte_clear_range(struct mm_struct *mm, unsigned long addr, pmd_t pmd); static inline void page_table_check_alloc(struct page *page, unsigned int order) { if (static_branch_likely(&page_table_check_disabled)) return; __page_table_check_zero(page, order); } static inline void page_table_check_free(struct page *page, unsigned int order) { if (static_branch_likely(&page_table_check_disabled)) return; __page_table_check_zero(page, order); } static inline void page_table_check_pte_clear(struct mm_struct *mm, pte_t pte) { if (static_branch_likely(&page_table_check_disabled)) return; __page_table_check_pte_clear(mm, pte); } static inline void page_table_check_pmd_clear(struct mm_struct *mm, pmd_t pmd) { if (static_branch_likely(&page_table_check_disabled)) return; __page_table_check_pmd_clear(mm, pmd); } static inline void page_table_check_pud_clear(struct mm_struct *mm, pud_t pud) { if (static_branch_likely(&page_table_check_disabled)) return; __page_table_check_pud_clear(mm, pud); } static inline void page_table_check_ptes_set(struct mm_struct *mm, pte_t *ptep, pte_t pte, unsigned int nr) { if (static_branch_likely(&page_table_check_disabled)) return; __page_table_check_ptes_set(mm, ptep, pte, nr); } static inline void page_table_check_pmd_set(struct mm_struct *mm, pmd_t *pmdp, pmd_t pmd) { if (static_branch_likely(&page_table_check_disabled)) return; __page_table_check_pmd_set(mm, pmdp, pmd); } static inline void page_table_check_pud_set(struct mm_struct *mm, pud_t *pudp, pud_t pud) { if (static_branch_likely(&page_table_check_disabled)) return; __page_table_check_pud_set(mm, pudp, pud); } static inline void page_table_check_pte_clear_range(struct mm_struct *mm, unsigned long addr, pmd_t pmd) { if (static_branch_likely(&page_table_check_disabled)) return; __page_table_check_pte_clear_range(mm, addr, pmd); } #else static inline void page_table_check_alloc(struct page *page, unsigned int order) { } static inline void page_table_check_free(struct page *page, unsigned int order) { } static inline void page_table_check_pte_clear(struct mm_struct *mm, pte_t pte) { } static inline void page_table_check_pmd_clear(struct mm_struct *mm, pmd_t pmd) { } static inline void page_table_check_pud_clear(struct mm_struct *mm, pud_t pud) { } static inline void page_table_check_ptes_set(struct mm_struct *mm, pte_t *ptep, pte_t pte, unsigned int nr) { } static inline void page_table_check_pmd_set(struct mm_struct *mm, pmd_t *pmdp, pmd_t pmd) { } static inline void page_table_check_pud_set(struct mm_struct *mm, pud_t *pudp, pud_t pud) { } static inline void page_table_check_pte_clear_range(struct mm_struct *mm, unsigned long addr, pmd_t pmd) { } #endif /* CONFIG_PAGE_TABLE_CHECK */ #endif /* __LINUX_PAGE_TABLE_CHECK_H */ |
| 616 616 616 163 163 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 | /* SPDX-License-Identifier: GPL-2.0-or-later */ /* Credentials management - see Documentation/security/credentials.rst * * Copyright (C) 2008 Red Hat, Inc. All Rights Reserved. * Written by David Howells (dhowells@redhat.com) */ #ifndef _LINUX_CRED_H #define _LINUX_CRED_H #include <linux/capability.h> #include <linux/init.h> #include <linux/key.h> #include <linux/atomic.h> #include <linux/refcount.h> #include <linux/uidgid.h> #include <linux/sched.h> #include <linux/sched/user.h> struct cred; struct inode; /* * COW Supplementary groups list */ struct group_info { refcount_t usage; int ngroups; kgid_t gid[]; } __randomize_layout; /** * get_group_info - Get a reference to a group info structure * @group_info: The group info to reference * * This gets a reference to a set of supplementary groups. * * If the caller is accessing a task's credentials, they must hold the RCU read * lock when reading. */ static inline struct group_info *get_group_info(struct group_info *gi) { refcount_inc(&gi->usage); return gi; } /** * put_group_info - Release a reference to a group info structure * @group_info: The group info to release */ #define put_group_info(group_info) \ do { \ if (refcount_dec_and_test(&(group_info)->usage)) \ groups_free(group_info); \ } while (0) #ifdef CONFIG_MULTIUSER extern struct group_info *groups_alloc(int); extern void groups_free(struct group_info *); extern int in_group_p(kgid_t); extern int in_egroup_p(kgid_t); extern int groups_search(const struct group_info *, kgid_t); extern int set_current_groups(struct group_info *); extern void set_groups(struct cred *, struct group_info *); extern bool may_setgroups(void); extern void groups_sort(struct group_info *); #else static inline void groups_free(struct group_info *group_info) { } static inline int in_group_p(kgid_t grp) { return 1; } static inline int in_egroup_p(kgid_t grp) { return 1; } static inline int groups_search(const struct group_info *group_info, kgid_t grp) { return 1; } #endif /* * The security context of a task * * The parts of the context break down into two categories: * * (1) The objective context of a task. These parts are used when some other * task is attempting to affect this one. * * (2) The subjective context. These details are used when the task is acting * upon another object, be that a file, a task, a key or whatever. * * Note that some members of this structure belong to both categories - the * LSM security pointer for instance. * * A task has two security pointers. task->real_cred points to the objective * context that defines that task's actual details. The objective part of this * context is used whenever that task is acted upon. * * task->cred points to the subjective context that defines the details of how * that task is going to act upon another object. This may be overridden * temporarily to point to another security context, but normally points to the * same context as task->real_cred. */ struct cred { atomic_long_t usage; kuid_t uid; /* real UID of the task */ kgid_t gid; /* real GID of the task */ kuid_t suid; /* saved UID of the task */ kgid_t sgid; /* saved GID of the task */ kuid_t euid; /* effective UID of the task */ kgid_t egid; /* effective GID of the task */ kuid_t fsuid; /* UID for VFS ops */ kgid_t fsgid; /* GID for VFS ops */ unsigned securebits; /* SUID-less security management */ kernel_cap_t cap_inheritable; /* caps our children can inherit */ kernel_cap_t cap_permitted; /* caps we're permitted */ kernel_cap_t cap_effective; /* caps we can actually use */ kernel_cap_t cap_bset; /* capability bounding set */ kernel_cap_t cap_ambient; /* Ambient capability set */ #ifdef CONFIG_KEYS unsigned char jit_keyring; /* default keyring to attach requested * keys to */ struct key *session_keyring; /* keyring inherited over fork */ struct key *process_keyring; /* keyring private to this process */ struct key *thread_keyring; /* keyring private to this thread */ struct key *request_key_auth; /* assumed request_key authority */ #endif #ifdef CONFIG_SECURITY void *security; /* LSM security */ #endif struct user_struct *user; /* real user ID subscription */ struct user_namespace *user_ns; /* user_ns the caps and keyrings are relative to. */ struct ucounts *ucounts; struct group_info *group_info; /* supplementary groups for euid/fsgid */ /* RCU deletion */ union { int non_rcu; /* Can we skip RCU deletion? */ struct rcu_head rcu; /* RCU deletion hook */ }; } __randomize_layout; extern void __put_cred(struct cred *); extern void exit_creds(struct task_struct *); extern int copy_creds(struct task_struct *, unsigned long); extern const struct cred *get_task_cred(struct task_struct *); extern struct cred *cred_alloc_blank(void); extern struct cred *prepare_creds(void); extern struct cred *prepare_exec_creds(void); extern int commit_creds(struct cred *); extern void abort_creds(struct cred *); extern const struct cred *override_creds(const struct cred *); extern void revert_creds(const struct cred *); extern struct cred *prepare_kernel_cred(struct task_struct *); extern int set_security_override(struct cred *, u32); extern int set_security_override_from_ctx(struct cred *, const char *); extern int set_create_files_as(struct cred *, struct inode *); extern int cred_fscmp(const struct cred *, const struct cred *); extern void __init cred_init(void); extern int set_cred_ucounts(struct cred *); static inline bool cap_ambient_invariant_ok(const struct cred *cred) { return cap_issubset(cred->cap_ambient, cap_intersect(cred->cap_permitted, cred->cap_inheritable)); } /* * Override creds without bumping reference count. Caller must ensure * reference remains valid or has taken reference. Almost always not the * interface you want. Use override_creds()/revert_creds() instead. */ static inline const struct cred *override_creds_light(const struct cred *override_cred) { const struct cred *old = current->cred; rcu_assign_pointer(current->cred, override_cred); return old; } static inline void revert_creds_light(const struct cred *revert_cred) { rcu_assign_pointer(current->cred, revert_cred); } /** * get_new_cred_many - Get references on a new set of credentials * @cred: The new credentials to reference * @nr: Number of references to acquire * * Get references on the specified set of new credentials. The caller must * release all acquired references. */ static inline struct cred *get_new_cred_many(struct cred *cred, int nr) { atomic_long_add(nr, &cred->usage); return cred; } /** * get_new_cred - Get a reference on a new set of credentials * @cred: The new credentials to reference * * Get a reference on the specified set of new credentials. The caller must * release the reference. */ static inline struct cred *get_new_cred(struct cred *cred) { return get_new_cred_many(cred, 1); } /** * get_cred_many - Get references on a set of credentials * @cred: The credentials to reference * @nr: Number of references to acquire * * Get references on the specified set of credentials. The caller must release * all acquired reference. If %NULL is passed, it is returned with no action. * * This is used to deal with a committed set of credentials. Although the * pointer is const, this will temporarily discard the const and increment the * usage count. The purpose of this is to attempt to catch at compile time the * accidental alteration of a set of credentials that should be considered * immutable. */ static inline const struct cred *get_cred_many(const struct cred *cred, int nr) { struct cred *nonconst_cred = (struct cred *) cred; if (!cred) return cred; nonconst_cred->non_rcu = 0; return get_new_cred_many(nonconst_cred, nr); } /* * get_cred - Get a reference on a set of credentials * @cred: The credentials to reference * * Get a reference on the specified set of credentials. The caller must * release the reference. If %NULL is passed, it is returned with no action. * * This is used to deal with a committed set of credentials. */ static inline const struct cred *get_cred(const struct cred *cred) { return get_cred_many(cred, 1); } static inline const struct cred *get_cred_rcu(const struct cred *cred) { struct cred *nonconst_cred = (struct cred *) cred; if (!cred) return NULL; if (!atomic_long_inc_not_zero(&nonconst_cred->usage)) return NULL; nonconst_cred->non_rcu = 0; return cred; } /** * put_cred - Release a reference to a set of credentials * @cred: The credentials to release * @nr: Number of references to release * * Release a reference to a set of credentials, deleting them when the last ref * is released. If %NULL is passed, nothing is done. * * This takes a const pointer to a set of credentials because the credentials * on task_struct are attached by const pointers to prevent accidental * alteration of otherwise immutable credential sets. */ static inline void put_cred_many(const struct cred *_cred, int nr) { struct cred *cred = (struct cred *) _cred; if (cred) { if (atomic_long_sub_and_test(nr, &cred->usage)) __put_cred(cred); } } /* * put_cred - Release a reference to a set of credentials * @cred: The credentials to release * * Release a reference to a set of credentials, deleting them when the last ref * is released. If %NULL is passed, nothing is done. */ static inline void put_cred(const struct cred *cred) { put_cred_many(cred, 1); } /** * current_cred - Access the current task's subjective credentials * * Access the subjective credentials of the current task. RCU-safe, * since nobody else can modify it. */ #define current_cred() \ rcu_dereference_protected(current->cred, 1) /** * current_real_cred - Access the current task's objective credentials * * Access the objective credentials of the current task. RCU-safe, * since nobody else can modify it. */ #define current_real_cred() \ rcu_dereference_protected(current->real_cred, 1) /** * __task_cred - Access a task's objective credentials * @task: The task to query * * Access the objective credentials of a task. The caller must hold the RCU * readlock. * * The result of this function should not be passed directly to get_cred(); * rather get_task_cred() should be used instead. */ #define __task_cred(task) \ rcu_dereference((task)->real_cred) /** * get_current_cred - Get the current task's subjective credentials * * Get the subjective credentials of the current task, pinning them so that * they can't go away. Accessing the current task's credentials directly is * not permitted. */ #define get_current_cred() \ (get_cred(current_cred())) /** * get_current_user - Get the current task's user_struct * * Get the user record of the current task, pinning it so that it can't go * away. */ #define get_current_user() \ ({ \ struct user_struct *__u; \ const struct cred *__cred; \ __cred = current_cred(); \ __u = get_uid(__cred->user); \ __u; \ }) /** * get_current_groups - Get the current task's supplementary group list * * Get the supplementary group list of the current task, pinning it so that it * can't go away. */ #define get_current_groups() \ ({ \ struct group_info *__groups; \ const struct cred *__cred; \ __cred = current_cred(); \ __groups = get_group_info(__cred->group_info); \ __groups; \ }) #define task_cred_xxx(task, xxx) \ ({ \ __typeof__(((struct cred *)NULL)->xxx) ___val; \ rcu_read_lock(); \ ___val = __task_cred((task))->xxx; \ rcu_read_unlock(); \ ___val; \ }) #define task_uid(task) (task_cred_xxx((task), uid)) #define task_euid(task) (task_cred_xxx((task), euid)) #define task_ucounts(task) (task_cred_xxx((task), ucounts)) #define current_cred_xxx(xxx) \ ({ \ current_cred()->xxx; \ }) #define current_uid() (current_cred_xxx(uid)) #define current_gid() (current_cred_xxx(gid)) #define current_euid() (current_cred_xxx(euid)) #define current_egid() (current_cred_xxx(egid)) #define current_suid() (current_cred_xxx(suid)) #define current_sgid() (current_cred_xxx(sgid)) #define current_fsuid() (current_cred_xxx(fsuid)) #define current_fsgid() (current_cred_xxx(fsgid)) #define current_cap() (current_cred_xxx(cap_effective)) #define current_user() (current_cred_xxx(user)) #define current_ucounts() (current_cred_xxx(ucounts)) extern struct user_namespace init_user_ns; #ifdef CONFIG_USER_NS #define current_user_ns() (current_cred_xxx(user_ns)) #else static inline struct user_namespace *current_user_ns(void) { return &init_user_ns; } #endif #define current_uid_gid(_uid, _gid) \ do { \ const struct cred *__cred; \ __cred = current_cred(); \ *(_uid) = __cred->uid; \ *(_gid) = __cred->gid; \ } while(0) #define current_euid_egid(_euid, _egid) \ do { \ const struct cred *__cred; \ __cred = current_cred(); \ *(_euid) = __cred->euid; \ *(_egid) = __cred->egid; \ } while(0) #define current_fsuid_fsgid(_fsuid, _fsgid) \ do { \ const struct cred *__cred; \ __cred = current_cred(); \ *(_fsuid) = __cred->fsuid; \ *(_fsgid) = __cred->fsgid; \ } while(0) #endif /* _LINUX_CRED_H */ |
| 298 292 7 20 11 12 17 298 10 253 13 5 296 15 15 107 154 32 72 304 298 1 10 120 196 196 297 10 304 298 10 304 17 304 119 195 196 298 10 304 8 8 3 5 8 8 8 304 313 33 296 314 75 253 8 356 336 88 355 50 49 50 50 308 307 308 304 6 262 284 298 10 303 304 304 304 262 285 261 285 14 205 14 204 6 2 2 372 373 373 372 373 373 17 17 17 17 17 17 8 314 313 313 313 304 6 8 303 17 16 17 17 3 8 8 8 6 17 17 356 296 356 33 295 296 365 311 108 30 354 355 355 356 356 356 295 108 3 358 150 265 265 356 147 285 356 356 352 18 132 335 4 17 354 356 356 355 356 356 356 356 3 112 112 4 107 113 113 1 112 350 65 65 65 65 351 338 64 11 349 326 65 72 48 31 47 234 17 83 60 31 96 8 96 18 80 91 71 286 229 70 71 218 218 218 218 218 218 218 218 218 218 7 218 218 218 218 218 218 218 218 218 218 218 218 218 218 218 218 218 218 218 195 3 47 297 2 295 33 313 16 24 314 195 50 158 157 195 47 95 274 273 137 164 124 47 286 314 315 314 313 303 285 286 48 2 50 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 1522 1523 1524 1525 1526 1527 1528 1529 1530 1531 1532 1533 1534 1535 1536 1537 1538 1539 1540 1541 1542 1543 1544 1545 1546 1547 1548 1549 1550 1551 1552 1553 1554 1555 1556 1557 1558 1559 1560 1561 1562 1563 1564 1565 1566 1567 1568 1569 1570 1571 1572 1573 1574 1575 1576 1577 1578 1579 1580 1581 1582 1583 1584 1585 1586 1587 1588 1589 1590 1591 1592 1593 1594 1595 1596 1597 1598 1599 1600 1601 1602 1603 1604 1605 1606 1607 1608 1609 1610 1611 1612 1613 1614 1615 1616 1617 1618 1619 1620 1621 1622 1623 1624 1625 1626 1627 1628 1629 1630 1631 1632 1633 1634 1635 1636 1637 1638 1639 1640 1641 1642 1643 1644 1645 1646 1647 1648 1649 1650 1651 1652 1653 1654 1655 1656 1657 1658 1659 1660 1661 1662 1663 1664 1665 1666 1667 1668 1669 1670 1671 1672 1673 1674 1675 1676 1677 1678 1679 1680 1681 1682 1683 1684 1685 1686 1687 1688 1689 1690 1691 1692 1693 1694 1695 1696 1697 1698 1699 1700 1701 1702 1703 1704 1705 1706 1707 1708 1709 1710 1711 1712 1713 1714 1715 1716 1717 1718 1719 1720 1721 1722 1723 1724 1725 1726 1727 1728 1729 1730 1731 1732 1733 1734 1735 1736 1737 1738 1739 1740 1741 1742 1743 1744 1745 1746 1747 1748 1749 1750 1751 1752 1753 1754 1755 1756 1757 1758 1759 1760 1761 1762 1763 1764 1765 1766 1767 1768 1769 1770 1771 1772 1773 1774 1775 1776 1777 1778 1779 1780 1781 1782 1783 1784 1785 1786 1787 1788 1789 1790 1791 1792 1793 1794 1795 1796 1797 1798 1799 1800 1801 1802 1803 1804 1805 1806 1807 1808 1809 1810 1811 1812 1813 1814 1815 1816 1817 1818 1819 1820 1821 1822 1823 1824 1825 1826 1827 1828 1829 1830 1831 1832 1833 1834 1835 1836 1837 1838 1839 1840 1841 1842 1843 1844 1845 1846 1847 1848 1849 1850 1851 1852 1853 1854 1855 1856 1857 1858 1859 1860 1861 1862 1863 1864 1865 1866 1867 1868 1869 1870 1871 1872 1873 1874 1875 1876 1877 1878 1879 1880 1881 1882 1883 1884 1885 1886 1887 1888 1889 1890 1891 1892 1893 1894 1895 1896 1897 1898 1899 1900 1901 1902 1903 1904 1905 1906 1907 1908 1909 1910 1911 1912 1913 1914 1915 1916 1917 1918 1919 1920 1921 1922 1923 1924 1925 1926 1927 1928 1929 1930 1931 1932 1933 1934 1935 1936 1937 1938 1939 1940 1941 1942 1943 1944 1945 1946 1947 1948 1949 1950 1951 1952 1953 1954 1955 1956 1957 1958 1959 1960 1961 1962 1963 1964 1965 1966 1967 1968 1969 1970 1971 1972 1973 1974 1975 1976 1977 1978 1979 1980 1981 1982 1983 1984 1985 1986 1987 1988 1989 1990 1991 1992 1993 1994 1995 1996 1997 1998 1999 2000 2001 2002 2003 2004 2005 2006 2007 2008 2009 2010 2011 2012 2013 2014 2015 2016 2017 2018 2019 2020 2021 2022 2023 2024 2025 2026 2027 2028 2029 2030 2031 2032 2033 2034 2035 2036 2037 2038 2039 2040 2041 2042 2043 2044 2045 2046 2047 2048 2049 2050 2051 2052 2053 2054 2055 2056 2057 2058 2059 2060 2061 2062 2063 2064 2065 2066 2067 2068 2069 2070 2071 2072 2073 2074 2075 2076 2077 2078 2079 2080 2081 2082 2083 2084 2085 2086 2087 2088 2089 2090 2091 2092 2093 2094 2095 2096 2097 2098 2099 2100 2101 2102 2103 2104 2105 2106 2107 2108 2109 2110 2111 2112 2113 2114 2115 2116 2117 2118 2119 2120 2121 2122 2123 2124 2125 2126 2127 2128 2129 2130 2131 2132 2133 2134 2135 2136 2137 2138 2139 2140 2141 2142 2143 2144 2145 2146 2147 2148 2149 2150 2151 2152 2153 2154 2155 2156 2157 2158 2159 2160 2161 2162 2163 2164 2165 2166 2167 2168 2169 2170 2171 2172 2173 2174 2175 2176 2177 2178 2179 2180 2181 2182 2183 2184 2185 2186 2187 2188 2189 2190 2191 2192 2193 2194 2195 2196 2197 2198 2199 2200 2201 2202 2203 2204 2205 2206 2207 2208 2209 2210 2211 2212 2213 2214 2215 2216 2217 2218 2219 2220 2221 2222 2223 2224 2225 2226 2227 2228 2229 2230 2231 2232 2233 2234 2235 2236 2237 2238 2239 2240 2241 2242 2243 2244 2245 2246 2247 2248 2249 2250 2251 2252 2253 2254 2255 2256 2257 2258 2259 2260 2261 2262 2263 2264 2265 2266 2267 2268 2269 2270 2271 2272 2273 2274 2275 2276 2277 2278 2279 2280 2281 2282 2283 2284 2285 2286 2287 2288 2289 2290 2291 2292 2293 2294 2295 2296 2297 2298 2299 2300 2301 2302 2303 2304 2305 2306 2307 2308 2309 2310 2311 2312 2313 2314 2315 2316 2317 2318 2319 2320 2321 2322 2323 2324 2325 2326 2327 2328 2329 2330 2331 2332 2333 2334 2335 2336 2337 2338 2339 2340 2341 2342 2343 2344 2345 2346 2347 2348 2349 2350 2351 2352 2353 2354 2355 2356 2357 2358 2359 2360 2361 2362 2363 2364 2365 2366 2367 2368 2369 2370 2371 2372 2373 2374 2375 2376 2377 2378 2379 2380 2381 2382 2383 2384 2385 2386 2387 2388 2389 2390 2391 2392 2393 2394 2395 2396 2397 2398 2399 2400 2401 2402 2403 2404 2405 2406 2407 2408 2409 2410 2411 2412 2413 2414 2415 2416 2417 2418 2419 2420 2421 2422 2423 2424 2425 2426 2427 2428 2429 2430 2431 2432 2433 2434 2435 2436 2437 2438 2439 2440 2441 2442 2443 2444 2445 2446 2447 2448 2449 2450 2451 2452 2453 2454 2455 2456 2457 2458 2459 2460 2461 2462 2463 2464 2465 2466 2467 2468 2469 2470 2471 2472 2473 2474 2475 2476 2477 2478 2479 2480 | // SPDX-License-Identifier: GPL-2.0-or-later /* * VMA-specific functions. */ #include "vma_internal.h" #include "vma.h" struct mmap_state { struct mm_struct *mm; struct vma_iterator *vmi; unsigned long addr; unsigned long end; pgoff_t pgoff; unsigned long pglen; unsigned long flags; struct file *file; unsigned long charged; bool retry_merge; struct vm_area_struct *prev; struct vm_area_struct *next; /* Unmapping state. */ struct vma_munmap_struct vms; struct ma_state mas_detach; struct maple_tree mt_detach; }; #define MMAP_STATE(name, mm_, vmi_, addr_, len_, pgoff_, flags_, file_) \ struct mmap_state name = { \ .mm = mm_, \ .vmi = vmi_, \ .addr = addr_, \ .end = (addr_) + (len_), \ .pgoff = pgoff_, \ .pglen = PHYS_PFN(len_), \ .flags = flags_, \ .file = file_, \ } #define VMG_MMAP_STATE(name, map_, vma_) \ struct vma_merge_struct name = { \ .mm = (map_)->mm, \ .vmi = (map_)->vmi, \ .start = (map_)->addr, \ .end = (map_)->end, \ .flags = (map_)->flags, \ .pgoff = (map_)->pgoff, \ .file = (map_)->file, \ .prev = (map_)->prev, \ .vma = vma_, \ .next = (vma_) ? NULL : (map_)->next, \ .state = VMA_MERGE_START, \ .merge_flags = VMG_FLAG_DEFAULT, \ } static inline bool is_mergeable_vma(struct vma_merge_struct *vmg, bool merge_next) { struct vm_area_struct *vma = merge_next ? vmg->next : vmg->prev; if (!mpol_equal(vmg->policy, vma_policy(vma))) return false; /* * VM_SOFTDIRTY should not prevent from VMA merging, if we * match the flags but dirty bit -- the caller should mark * merged VMA as dirty. If dirty bit won't be excluded from * comparison, we increase pressure on the memory system forcing * the kernel to generate new VMAs when old one could be * extended instead. */ if ((vma->vm_flags ^ vmg->flags) & ~VM_SOFTDIRTY) return false; if (vma->vm_file != vmg->file) return false; if (!is_mergeable_vm_userfaultfd_ctx(vma, vmg->uffd_ctx)) return false; if (!anon_vma_name_eq(anon_vma_name(vma), vmg->anon_name)) return false; return true; } static inline bool is_mergeable_anon_vma(struct anon_vma *anon_vma1, struct anon_vma *anon_vma2, struct vm_area_struct *vma) { /* * The list_is_singular() test is to avoid merging VMA cloned from * parents. This can improve scalability caused by anon_vma lock. */ if ((!anon_vma1 || !anon_vma2) && (!vma || list_is_singular(&vma->anon_vma_chain))) return true; return anon_vma1 == anon_vma2; } /* Are the anon_vma's belonging to each VMA compatible with one another? */ static inline bool are_anon_vmas_compatible(struct vm_area_struct *vma1, struct vm_area_struct *vma2) { return is_mergeable_anon_vma(vma1->anon_vma, vma2->anon_vma, NULL); } /* * init_multi_vma_prep() - Initializer for struct vma_prepare * @vp: The vma_prepare struct * @vma: The vma that will be altered once locked * @next: The next vma if it is to be adjusted * @remove: The first vma to be removed * @remove2: The second vma to be removed */ static void init_multi_vma_prep(struct vma_prepare *vp, struct vm_area_struct *vma, struct vm_area_struct *next, struct vm_area_struct *remove, struct vm_area_struct *remove2) { memset(vp, 0, sizeof(struct vma_prepare)); vp->vma = vma; vp->anon_vma = vma->anon_vma; vp->remove = remove; vp->remove2 = remove2; vp->adj_next = next; if (!vp->anon_vma && next) vp->anon_vma = next->anon_vma; vp->file = vma->vm_file; if (vp->file) vp->mapping = vma->vm_file->f_mapping; } /* * Return true if we can merge this (vm_flags,anon_vma,file,vm_pgoff) * in front of (at a lower virtual address and file offset than) the vma. * * We cannot merge two vmas if they have differently assigned (non-NULL) * anon_vmas, nor if same anon_vma is assigned but offsets incompatible. * * We don't check here for the merged mmap wrapping around the end of pagecache * indices (16TB on ia32) because do_mmap() does not permit mmap's which * wrap, nor mmaps which cover the final page at index -1UL. * * We assume the vma may be removed as part of the merge. */ static bool can_vma_merge_before(struct vma_merge_struct *vmg) { pgoff_t pglen = PHYS_PFN(vmg->end - vmg->start); if (is_mergeable_vma(vmg, /* merge_next = */ true) && is_mergeable_anon_vma(vmg->anon_vma, vmg->next->anon_vma, vmg->next)) { if (vmg->next->vm_pgoff == vmg->pgoff + pglen) return true; } return false; } /* * Return true if we can merge this (vm_flags,anon_vma,file,vm_pgoff) * beyond (at a higher virtual address and file offset than) the vma. * * We cannot merge two vmas if they have differently assigned (non-NULL) * anon_vmas, nor if same anon_vma is assigned but offsets incompatible. * * We assume that vma is not removed as part of the merge. */ static bool can_vma_merge_after(struct vma_merge_struct *vmg) { if (is_mergeable_vma(vmg, /* merge_next = */ false) && is_mergeable_anon_vma(vmg->anon_vma, vmg->prev->anon_vma, vmg->prev)) { if (vmg->prev->vm_pgoff + vma_pages(vmg->prev) == vmg->pgoff) return true; } return false; } static void __vma_link_file(struct vm_area_struct *vma, struct address_space *mapping) { if (vma_is_shared_maywrite(vma)) mapping_allow_writable(mapping); flush_dcache_mmap_lock(mapping); vma_interval_tree_insert(vma, &mapping->i_mmap); flush_dcache_mmap_unlock(mapping); } /* * Requires inode->i_mapping->i_mmap_rwsem */ static void __remove_shared_vm_struct(struct vm_area_struct *vma, struct address_space *mapping) { if (vma_is_shared_maywrite(vma)) mapping_unmap_writable(mapping); flush_dcache_mmap_lock(mapping); vma_interval_tree_remove(vma, &mapping->i_mmap); flush_dcache_mmap_unlock(mapping); } /* * vma_prepare() - Helper function for handling locking VMAs prior to altering * @vp: The initialized vma_prepare struct */ static void vma_prepare(struct vma_prepare *vp) { if (vp->file) { uprobe_munmap(vp->vma, vp->vma->vm_start, vp->vma->vm_end); if (vp->adj_next) uprobe_munmap(vp->adj_next, vp->adj_next->vm_start, vp->adj_next->vm_end); i_mmap_lock_write(vp->mapping); if (vp->insert && vp->insert->vm_file) { /* * Put into interval tree now, so instantiated pages * are visible to arm/parisc __flush_dcache_page * throughout; but we cannot insert into address * space until vma start or end is updated. */ __vma_link_file(vp->insert, vp->insert->vm_file->f_mapping); } } if (vp->anon_vma) { anon_vma_lock_write(vp->anon_vma); anon_vma_interval_tree_pre_update_vma(vp->vma); if (vp->adj_next) anon_vma_interval_tree_pre_update_vma(vp->adj_next); } if (vp->file) { flush_dcache_mmap_lock(vp->mapping); vma_interval_tree_remove(vp->vma, &vp->mapping->i_mmap); if (vp->adj_next) vma_interval_tree_remove(vp->adj_next, &vp->mapping->i_mmap); } } /* * vma_complete- Helper function for handling the unlocking after altering VMAs, * or for inserting a VMA. * * @vp: The vma_prepare struct * @vmi: The vma iterator * @mm: The mm_struct */ static void vma_complete(struct vma_prepare *vp, struct vma_iterator *vmi, struct mm_struct *mm) { if (vp->file) { if (vp->adj_next) vma_interval_tree_insert(vp->adj_next, &vp->mapping->i_mmap); vma_interval_tree_insert(vp->vma, &vp->mapping->i_mmap); flush_dcache_mmap_unlock(vp->mapping); } if (vp->remove && vp->file) { __remove_shared_vm_struct(vp->remove, vp->mapping); if (vp->remove2) __remove_shared_vm_struct(vp->remove2, vp->mapping); } else if (vp->insert) { /* * split_vma has split insert from vma, and needs * us to insert it before dropping the locks * (it may either follow vma or precede it). */ vma_iter_store(vmi, vp->insert); mm->map_count++; } if (vp->anon_vma) { anon_vma_interval_tree_post_update_vma(vp->vma); if (vp->adj_next) anon_vma_interval_tree_post_update_vma(vp->adj_next); anon_vma_unlock_write(vp->anon_vma); } if (vp->file) { i_mmap_unlock_write(vp->mapping); uprobe_mmap(vp->vma); if (vp->adj_next) uprobe_mmap(vp->adj_next); } if (vp->remove) { again: vma_mark_detached(vp->remove, true); if (vp->file) { uprobe_munmap(vp->remove, vp->remove->vm_start, vp->remove->vm_end); fput(vp->file); } if (vp->remove->anon_vma) anon_vma_merge(vp->vma, vp->remove); mm->map_count--; mpol_put(vma_policy(vp->remove)); if (!vp->remove2) WARN_ON_ONCE(vp->vma->vm_end < vp->remove->vm_end); vm_area_free(vp->remove); /* * In mprotect's case 6 (see comments on vma_merge), * we are removing both mid and next vmas */ if (vp->remove2) { vp->remove = vp->remove2; vp->remove2 = NULL; goto again; } } if (vp->insert && vp->file) uprobe_mmap(vp->insert); } /* * init_vma_prep() - Initializer wrapper for vma_prepare struct * @vp: The vma_prepare struct * @vma: The vma that will be altered once locked */ static void init_vma_prep(struct vma_prepare *vp, struct vm_area_struct *vma) { init_multi_vma_prep(vp, vma, NULL, NULL, NULL); } /* * Can the proposed VMA be merged with the left (previous) VMA taking into * account the start position of the proposed range. */ static bool can_vma_merge_left(struct vma_merge_struct *vmg) { return vmg->prev && vmg->prev->vm_end == vmg->start && can_vma_merge_after(vmg); } /* * Can the proposed VMA be merged with the right (next) VMA taking into * account the end position of the proposed range. * * In addition, if we can merge with the left VMA, ensure that left and right * anon_vma's are also compatible. */ static bool can_vma_merge_right(struct vma_merge_struct *vmg, bool can_merge_left) { if (!vmg->next || vmg->end != vmg->next->vm_start || !can_vma_merge_before(vmg)) return false; if (!can_merge_left) return true; /* * If we can merge with prev (left) and next (right), indicating that * each VMA's anon_vma is compatible with the proposed anon_vma, this * does not mean prev and next are compatible with EACH OTHER. * * We therefore check this in addition to mergeability to either side. */ return are_anon_vmas_compatible(vmg->prev, vmg->next); } /* * Close a vm structure and free it. */ void remove_vma(struct vm_area_struct *vma, bool unreachable) { might_sleep(); vma_close(vma); if (vma->vm_file) fput(vma->vm_file); mpol_put(vma_policy(vma)); if (unreachable) __vm_area_free(vma); else vm_area_free(vma); } /* * Get rid of page table information in the indicated region. * * Called with the mm semaphore held. */ void unmap_region(struct ma_state *mas, struct vm_area_struct *vma, struct vm_area_struct *prev, struct vm_area_struct *next) { struct mm_struct *mm = vma->vm_mm; struct mmu_gather tlb; lru_add_drain(); tlb_gather_mmu(&tlb, mm); update_hiwater_rss(mm); unmap_vmas(&tlb, mas, vma, vma->vm_start, vma->vm_end, vma->vm_end, /* mm_wr_locked = */ true); mas_set(mas, vma->vm_end); free_pgtables(&tlb, mas, vma, prev ? prev->vm_end : FIRST_USER_ADDRESS, next ? next->vm_start : USER_PGTABLES_CEILING, /* mm_wr_locked = */ true); tlb_finish_mmu(&tlb); } /* * __split_vma() bypasses sysctl_max_map_count checking. We use this where it * has already been checked or doesn't make sense to fail. * VMA Iterator will point to the original VMA. */ static int __split_vma(struct vma_iterator *vmi, struct vm_area_struct *vma, unsigned long addr, int new_below) { struct vma_prepare vp; struct vm_area_struct *new; int err; WARN_ON(vma->vm_start >= addr); WARN_ON(vma->vm_end <= addr); if (vma->vm_ops && vma->vm_ops->may_split) { err = vma->vm_ops->may_split(vma, addr); if (err) return err; } new = vm_area_dup(vma); if (!new) return -ENOMEM; if (new_below) { new->vm_end = addr; } else { new->vm_start = addr; new->vm_pgoff += ((addr - vma->vm_start) >> PAGE_SHIFT); } err = -ENOMEM; vma_iter_config(vmi, new->vm_start, new->vm_end); if (vma_iter_prealloc(vmi, new)) goto out_free_vma; err = vma_dup_policy(vma, new); if (err) goto out_free_vmi; err = anon_vma_clone(new, vma); if (err) goto out_free_mpol; if (new->vm_file) get_file(new->vm_file); if (new->vm_ops && new->vm_ops->open) new->vm_ops->open(new); vma_start_write(vma); vma_start_write(new); init_vma_prep(&vp, vma); vp.insert = new; vma_prepare(&vp); vma_adjust_trans_huge(vma, vma->vm_start, addr, 0); if (new_below) { vma->vm_start = addr; vma->vm_pgoff += (addr - new->vm_start) >> PAGE_SHIFT; } else { vma->vm_end = addr; } /* vma_complete stores the new vma */ vma_complete(&vp, vmi, vma->vm_mm); validate_mm(vma->vm_mm); /* Success. */ if (new_below) vma_next(vmi); else vma_prev(vmi); return 0; out_free_mpol: mpol_put(vma_policy(new)); out_free_vmi: vma_iter_free(vmi); out_free_vma: vm_area_free(new); return err; } /* * Split a vma into two pieces at address 'addr', a new vma is allocated * either for the first part or the tail. */ static int split_vma(struct vma_iterator *vmi, struct vm_area_struct *vma, unsigned long addr, int new_below) { if (vma->vm_mm->map_count >= sysctl_max_map_count) return -ENOMEM; return __split_vma(vmi, vma, addr, new_below); } /* * vma has some anon_vma assigned, and is already inserted on that * anon_vma's interval trees. * * Before updating the vma's vm_start / vm_end / vm_pgoff fields, the * vma must be removed from the anon_vma's interval trees using * anon_vma_interval_tree_pre_update_vma(). * * After the update, the vma will be reinserted using * anon_vma_interval_tree_post_update_vma(). * * The entire update must be protected by exclusive mmap_lock and by * the root anon_vma's mutex. */ void anon_vma_interval_tree_pre_update_vma(struct vm_area_struct *vma) { struct anon_vma_chain *avc; list_for_each_entry(avc, &vma->anon_vma_chain, same_vma) anon_vma_interval_tree_remove(avc, &avc->anon_vma->rb_root); } void anon_vma_interval_tree_post_update_vma(struct vm_area_struct *vma) { struct anon_vma_chain *avc; list_for_each_entry(avc, &vma->anon_vma_chain, same_vma) anon_vma_interval_tree_insert(avc, &avc->anon_vma->rb_root); } /* * dup_anon_vma() - Helper function to duplicate anon_vma * @dst: The destination VMA * @src: The source VMA * @dup: Pointer to the destination VMA when successful. * * Returns: 0 on success. */ static int dup_anon_vma(struct vm_area_struct *dst, struct vm_area_struct *src, struct vm_area_struct **dup) { /* * Easily overlooked: when mprotect shifts the boundary, make sure the * expanding vma has anon_vma set if the shrinking vma had, to cover any * anon pages imported. */ if (src->anon_vma && !dst->anon_vma) { int ret; vma_assert_write_locked(dst); dst->anon_vma = src->anon_vma; ret = anon_vma_clone(dst, src); if (ret) return ret; *dup = dst; } return 0; } #ifdef CONFIG_DEBUG_VM_MAPLE_TREE void validate_mm(struct mm_struct *mm) { int bug = 0; int i = 0; struct vm_area_struct *vma; VMA_ITERATOR(vmi, mm, 0); mt_validate(&mm->mm_mt); for_each_vma(vmi, vma) { #ifdef CONFIG_DEBUG_VM_RB struct anon_vma *anon_vma = vma->anon_vma; struct anon_vma_chain *avc; #endif unsigned long vmi_start, vmi_end; bool warn = 0; vmi_start = vma_iter_addr(&vmi); vmi_end = vma_iter_end(&vmi); if (VM_WARN_ON_ONCE_MM(vma->vm_end != vmi_end, mm)) warn = 1; if (VM_WARN_ON_ONCE_MM(vma->vm_start != vmi_start, mm)) warn = 1; if (warn) { pr_emerg("issue in %s\n", current->comm); dump_stack(); dump_vma(vma); pr_emerg("tree range: %px start %lx end %lx\n", vma, vmi_start, vmi_end - 1); vma_iter_dump_tree(&vmi); } #ifdef CONFIG_DEBUG_VM_RB if (anon_vma) { anon_vma_lock_read(anon_vma); list_for_each_entry(avc, &vma->anon_vma_chain, same_vma) anon_vma_interval_tree_verify(avc); anon_vma_unlock_read(anon_vma); } #endif /* Check for a infinite loop */ if (++i > mm->map_count + 10) { i = -1; break; } } if (i != mm->map_count) { pr_emerg("map_count %d vma iterator %d\n", mm->map_count, i); bug = 1; } VM_BUG_ON_MM(bug, mm); } #endif /* CONFIG_DEBUG_VM_MAPLE_TREE */ /* Actually perform the VMA merge operation. */ static int commit_merge(struct vma_merge_struct *vmg, struct vm_area_struct *adjust, struct vm_area_struct *remove, struct vm_area_struct *remove2, long adj_start, bool expanded) { struct vma_prepare vp; init_multi_vma_prep(&vp, vmg->vma, adjust, remove, remove2); VM_WARN_ON(vp.anon_vma && adjust && adjust->anon_vma && vp.anon_vma != adjust->anon_vma); if (expanded) { /* Note: vma iterator must be pointing to 'start'. */ vma_iter_config(vmg->vmi, vmg->start, vmg->end); } else { vma_iter_config(vmg->vmi, adjust->vm_start + adj_start, adjust->vm_end); } if (vma_iter_prealloc(vmg->vmi, vmg->vma)) return -ENOMEM; vma_prepare(&vp); vma_adjust_trans_huge(vmg->vma, vmg->start, vmg->end, adj_start); vma_set_range(vmg->vma, vmg->start, vmg->end, vmg->pgoff); if (expanded) vma_iter_store(vmg->vmi, vmg->vma); if (adj_start) { adjust->vm_start += adj_start; adjust->vm_pgoff += PHYS_PFN(adj_start); if (adj_start < 0) { WARN_ON(expanded); vma_iter_store(vmg->vmi, adjust); } } vma_complete(&vp, vmg->vmi, vmg->vma->vm_mm); return 0; } /* We can only remove VMAs when merging if they do not have a close hook. */ static bool can_merge_remove_vma(struct vm_area_struct *vma) { return !vma->vm_ops || !vma->vm_ops->close; } /* * vma_merge_existing_range - Attempt to merge VMAs based on a VMA having its * attributes modified. * * @vmg: Describes the modifications being made to a VMA and associated * metadata. * * When the attributes of a range within a VMA change, then it might be possible * for immediately adjacent VMAs to be merged into that VMA due to having * identical properties. * * This function checks for the existence of any such mergeable VMAs and updates * the maple tree describing the @vmg->vma->vm_mm address space to account for * this, as well as any VMAs shrunk/expanded/deleted as a result of this merge. * * As part of this operation, if a merge occurs, the @vmg object will have its * vma, start, end, and pgoff fields modified to execute the merge. Subsequent * calls to this function should reset these fields. * * Returns: The merged VMA if merge succeeds, or NULL otherwise. * * ASSUMPTIONS: * - The caller must assign the VMA to be modifed to @vmg->vma. * - The caller must have set @vmg->prev to the previous VMA, if there is one. * - The caller must not set @vmg->next, as we determine this. * - The caller must hold a WRITE lock on the mm_struct->mmap_lock. * - vmi must be positioned within [@vmg->vma->vm_start, @vmg->vma->vm_end). */ static struct vm_area_struct *vma_merge_existing_range(struct vma_merge_struct *vmg) { struct vm_area_struct *vma = vmg->vma; struct vm_area_struct *prev = vmg->prev; struct vm_area_struct *next, *res; struct vm_area_struct *anon_dup = NULL; struct vm_area_struct *adjust = NULL; unsigned long start = vmg->start; unsigned long end = vmg->end; bool left_side = vma && start == vma->vm_start; bool right_side = vma && end == vma->vm_end; int err = 0; long adj_start = 0; bool merge_will_delete_vma, merge_will_delete_next; bool merge_left, merge_right, merge_both; bool expanded; mmap_assert_write_locked(vmg->mm); VM_WARN_ON(!vma); /* We are modifying a VMA, so caller must specify. */ VM_WARN_ON(vmg->next); /* We set this. */ VM_WARN_ON(prev && start <= prev->vm_start); VM_WARN_ON(start >= end); /* * If vma == prev, then we are offset into a VMA. Otherwise, if we are * not, we must span a portion of the VMA. */ VM_WARN_ON(vma && ((vma != prev && vmg->start != vma->vm_start) || vmg->end > vma->vm_end)); /* The vmi must be positioned within vmg->vma. */ VM_WARN_ON(vma && !(vma_iter_addr(vmg->vmi) >= vma->vm_start && vma_iter_addr(vmg->vmi) < vma->vm_end)); vmg->state = VMA_MERGE_NOMERGE; /* * If a special mapping or if the range being modified is neither at the * furthermost left or right side of the VMA, then we have no chance of * merging and should abort. */ if (vmg->flags & VM_SPECIAL || (!left_side && !right_side)) return NULL; if (left_side) merge_left = can_vma_merge_left(vmg); else merge_left = false; if (right_side) { next = vmg->next = vma_iter_next_range(vmg->vmi); vma_iter_prev_range(vmg->vmi); merge_right = can_vma_merge_right(vmg, merge_left); } else { merge_right = false; next = NULL; } if (merge_left) /* If merging prev, position iterator there. */ vma_prev(vmg->vmi); else if (!merge_right) /* If we have nothing to merge, abort. */ return NULL; merge_both = merge_left && merge_right; /* If we span the entire VMA, a merge implies it will be deleted. */ merge_will_delete_vma = left_side && right_side; /* * If we need to remove vma in its entirety but are unable to do so, * we have no sensible recourse but to abort the merge. */ if (merge_will_delete_vma && !can_merge_remove_vma(vma)) return NULL; /* * If we merge both VMAs, then next is also deleted. This implies * merge_will_delete_vma also. */ merge_will_delete_next = merge_both; /* * If we cannot delete next, then we can reduce the operation to merging * prev and vma (thereby deleting vma). */ if (merge_will_delete_next && !can_merge_remove_vma(next)) { merge_will_delete_next = false; merge_right = false; merge_both = false; } /* No matter what happens, we will be adjusting vma. */ vma_start_write(vma); if (merge_left) vma_start_write(prev); if (merge_right) vma_start_write(next); if (merge_both) { /* * |<----->| * |-------*********-------| * prev vma next * extend delete delete */ vmg->vma = prev; vmg->start = prev->vm_start; vmg->end = next->vm_end; vmg->pgoff = prev->vm_pgoff; /* * We already ensured anon_vma compatibility above, so now it's * simply a case of, if prev has no anon_vma object, which of * next or vma contains the anon_vma we must duplicate. */ err = dup_anon_vma(prev, next->anon_vma ? next : vma, &anon_dup); } else if (merge_left) { /* * |<----->| OR * |<--------->| * |-------************* * prev vma * extend shrink/delete */ vmg->vma = prev; vmg->start = prev->vm_start; vmg->pgoff = prev->vm_pgoff; if (!merge_will_delete_vma) { adjust = vma; adj_start = vmg->end - vma->vm_start; } err = dup_anon_vma(prev, vma, &anon_dup); } else { /* merge_right */ /* * |<----->| OR * |<--------->| * *************-------| * vma next * shrink/delete extend */ pgoff_t pglen = PHYS_PFN(vmg->end - vmg->start); VM_WARN_ON(!merge_right); /* If we are offset into a VMA, then prev must be vma. */ VM_WARN_ON(vmg->start > vma->vm_start && prev && vma != prev); if (merge_will_delete_vma) { vmg->vma = next; vmg->end = next->vm_end; vmg->pgoff = next->vm_pgoff - pglen; } else { /* * We shrink vma and expand next. * * IMPORTANT: This is the ONLY case where the final * merged VMA is NOT vmg->vma, but rather vmg->next. */ vmg->start = vma->vm_start; vmg->end = start; vmg->pgoff = vma->vm_pgoff; adjust = next; adj_start = -(vma->vm_end - start); } err = dup_anon_vma(next, vma, &anon_dup); } if (err) goto abort; /* * In nearly all cases, we expand vmg->vma. There is one exception - * merge_right where we partially span the VMA. In this case we shrink * the end of vmg->vma and adjust the start of vmg->next accordingly. */ expanded = !merge_right || merge_will_delete_vma; if (commit_merge(vmg, adjust, merge_will_delete_vma ? vma : NULL, merge_will_delete_next ? next : NULL, adj_start, expanded)) { if (anon_dup) unlink_anon_vmas(anon_dup); vmg->state = VMA_MERGE_ERROR_NOMEM; return NULL; } res = merge_left ? prev : next; khugepaged_enter_vma(res, vmg->flags); vmg->state = VMA_MERGE_SUCCESS; return res; abort: vma_iter_set(vmg->vmi, start); vma_iter_load(vmg->vmi); vmg->state = VMA_MERGE_ERROR_NOMEM; return NULL; } /* * vma_merge_new_range - Attempt to merge a new VMA into address space * * @vmg: Describes the VMA we are adding, in the range @vmg->start to @vmg->end * (exclusive), which we try to merge with any adjacent VMAs if possible. * * We are about to add a VMA to the address space starting at @vmg->start and * ending at @vmg->end. There are three different possible scenarios: * * 1. There is a VMA with identical properties immediately adjacent to the * proposed new VMA [@vmg->start, @vmg->end) either before or after it - * EXPAND that VMA: * * Proposed: |-----| or |-----| * Existing: |----| |----| * * 2. There are VMAs with identical properties immediately adjacent to the * proposed new VMA [@vmg->start, @vmg->end) both before AND after it - * EXPAND the former and REMOVE the latter: * * Proposed: |-----| * Existing: |----| |----| * * 3. There are no VMAs immediately adjacent to the proposed new VMA or those * VMAs do not have identical attributes - NO MERGE POSSIBLE. * * In instances where we can merge, this function returns the expanded VMA which * will have its range adjusted accordingly and the underlying maple tree also * adjusted. * * Returns: In instances where no merge was possible, NULL. Otherwise, a pointer * to the VMA we expanded. * * This function adjusts @vmg to provide @vmg->next if not already specified, * and adjusts [@vmg->start, @vmg->end) to span the expanded range. * * ASSUMPTIONS: * - The caller must hold a WRITE lock on the mm_struct->mmap_lock. * - The caller must have determined that [@vmg->start, @vmg->end) is empty, other than VMAs that will be unmapped should the operation succeed. * - The caller must have specified the previous vma in @vmg->prev. * - The caller must have specified the next vma in @vmg->next. * - The caller must have positioned the vmi at or before the gap. */ struct vm_area_struct *vma_merge_new_range(struct vma_merge_struct *vmg) { struct vm_area_struct *prev = vmg->prev; struct vm_area_struct *next = vmg->next; unsigned long end = vmg->end; bool can_merge_left, can_merge_right; bool just_expand = vmg->merge_flags & VMG_FLAG_JUST_EXPAND; mmap_assert_write_locked(vmg->mm); VM_WARN_ON(vmg->vma); /* vmi must point at or before the gap. */ VM_WARN_ON(vma_iter_addr(vmg->vmi) > end); vmg->state = VMA_MERGE_NOMERGE; /* Special VMAs are unmergeable, also if no prev/next. */ if ((vmg->flags & VM_SPECIAL) || (!prev && !next)) return NULL; can_merge_left = can_vma_merge_left(vmg); can_merge_right = !just_expand && can_vma_merge_right(vmg, can_merge_left); /* If we can merge with the next VMA, adjust vmg accordingly. */ if (can_merge_right) { vmg->end = next->vm_end; vmg->vma = next; } /* If we can merge with the previous VMA, adjust vmg accordingly. */ if (can_merge_left) { vmg->start = prev->vm_start; vmg->vma = prev; vmg->pgoff = prev->vm_pgoff; /* * If this merge would result in removal of the next VMA but we * are not permitted to do so, reduce the operation to merging * prev and vma. */ if (can_merge_right && !can_merge_remove_vma(next)) vmg->end = end; /* In expand-only case we are already positioned at prev. */ if (!just_expand) { /* Equivalent to going to the previous range. */ vma_prev(vmg->vmi); } } /* * Now try to expand adjacent VMA(s). This takes care of removing the * following VMA if we have VMAs on both sides. */ if (vmg->vma && !vma_expand(vmg)) { khugepaged_enter_vma(vmg->vma, vmg->flags); vmg->state = VMA_MERGE_SUCCESS; return vmg->vma; } return NULL; } /* * vma_expand - Expand an existing VMA * * @vmg: Describes a VMA expansion operation. * * Expand @vma to vmg->start and vmg->end. Can expand off the start and end. * Will expand over vmg->next if it's different from vmg->vma and vmg->end == * vmg->next->vm_end. Checking if the vmg->vma can expand and merge with * vmg->next needs to be handled by the caller. * * Returns: 0 on success. * * ASSUMPTIONS: * - The caller must hold a WRITE lock on vmg->vma->mm->mmap_lock. * - The caller must have set @vmg->vma and @vmg->next. */ int vma_expand(struct vma_merge_struct *vmg) { struct vm_area_struct *anon_dup = NULL; bool remove_next = false; struct vm_area_struct *vma = vmg->vma; struct vm_area_struct *next = vmg->next; mmap_assert_write_locked(vmg->mm); vma_start_write(vma); if (next && (vma != next) && (vmg->end == next->vm_end)) { int ret; remove_next = true; /* This should already have been checked by this point. */ VM_WARN_ON(!can_merge_remove_vma(next)); vma_start_write(next); ret = dup_anon_vma(vma, next, &anon_dup); if (ret) return ret; } /* Not merging but overwriting any part of next is not handled. */ VM_WARN_ON(next && !remove_next && next != vma && vmg->end > next->vm_start); /* Only handles expanding */ VM_WARN_ON(vma->vm_start < vmg->start || vma->vm_end > vmg->end); if (commit_merge(vmg, NULL, remove_next ? next : NULL, NULL, 0, true)) goto nomem; return 0; nomem: vmg->state = VMA_MERGE_ERROR_NOMEM; if (anon_dup) unlink_anon_vmas(anon_dup); return -ENOMEM; } /* * vma_shrink() - Reduce an existing VMAs memory area * @vmi: The vma iterator * @vma: The VMA to modify * @start: The new start * @end: The new end * * Returns: 0 on success, -ENOMEM otherwise */ int vma_shrink(struct vma_iterator *vmi, struct vm_area_struct *vma, unsigned long start, unsigned long end, pgoff_t pgoff) { struct vma_prepare vp; WARN_ON((vma->vm_start != start) && (vma->vm_end != end)); if (vma->vm_start < start) vma_iter_config(vmi, vma->vm_start, start); else vma_iter_config(vmi, end, vma->vm_end); if (vma_iter_prealloc(vmi, NULL)) return -ENOMEM; vma_start_write(vma); init_vma_prep(&vp, vma); vma_prepare(&vp); vma_adjust_trans_huge(vma, start, end, 0); vma_iter_clear(vmi); vma_set_range(vma, start, end, pgoff); vma_complete(&vp, vmi, vma->vm_mm); validate_mm(vma->vm_mm); return 0; } static inline void vms_clear_ptes(struct vma_munmap_struct *vms, struct ma_state *mas_detach, bool mm_wr_locked) { struct mmu_gather tlb; if (!vms->clear_ptes) /* Nothing to do */ return; /* * We can free page tables without write-locking mmap_lock because VMAs * were isolated before we downgraded mmap_lock. */ mas_set(mas_detach, 1); lru_add_drain(); tlb_gather_mmu(&tlb, vms->vma->vm_mm); update_hiwater_rss(vms->vma->vm_mm); unmap_vmas(&tlb, mas_detach, vms->vma, vms->start, vms->end, vms->vma_count, mm_wr_locked); mas_set(mas_detach, 1); /* start and end may be different if there is no prev or next vma. */ free_pgtables(&tlb, mas_detach, vms->vma, vms->unmap_start, vms->unmap_end, mm_wr_locked); tlb_finish_mmu(&tlb); vms->clear_ptes = false; } static void vms_clean_up_area(struct vma_munmap_struct *vms, struct ma_state *mas_detach) { struct vm_area_struct *vma; if (!vms->nr_pages) return; vms_clear_ptes(vms, mas_detach, true); mas_set(mas_detach, 0); mas_for_each(mas_detach, vma, ULONG_MAX) vma_close(vma); } /* * vms_complete_munmap_vmas() - Finish the munmap() operation * @vms: The vma munmap struct * @mas_detach: The maple state of the detached vmas * * This updates the mm_struct, unmaps the region, frees the resources * used for the munmap() and may downgrade the lock - if requested. Everything * needed to be done once the vma maple tree is updated. */ static void vms_complete_munmap_vmas(struct vma_munmap_struct *vms, struct ma_state *mas_detach) { struct vm_area_struct *vma; struct mm_struct *mm; mm = current->mm; mm->map_count -= vms->vma_count; mm->locked_vm -= vms->locked_vm; if (vms->unlock) mmap_write_downgrade(mm); if (!vms->nr_pages) return; vms_clear_ptes(vms, mas_detach, !vms->unlock); /* Update high watermark before we lower total_vm */ update_hiwater_vm(mm); /* Stat accounting */ WRITE_ONCE(mm->total_vm, READ_ONCE(mm->total_vm) - vms->nr_pages); /* Paranoid bookkeeping */ VM_WARN_ON(vms->exec_vm > mm->exec_vm); VM_WARN_ON(vms->stack_vm > mm->stack_vm); VM_WARN_ON(vms->data_vm > mm->data_vm); mm->exec_vm -= vms->exec_vm; mm->stack_vm -= vms->stack_vm; mm->data_vm -= vms->data_vm; /* Remove and clean up vmas */ mas_set(mas_detach, 0); mas_for_each(mas_detach, vma, ULONG_MAX) remove_vma(vma, /* unreachable = */ false); vm_unacct_memory(vms->nr_accounted); validate_mm(mm); if (vms->unlock) mmap_read_unlock(mm); __mt_destroy(mas_detach->tree); } /* * reattach_vmas() - Undo any munmap work and free resources * @mas_detach: The maple state with the detached maple tree * * Reattach any detached vmas and free up the maple tree used to track the vmas. */ static void reattach_vmas(struct ma_state *mas_detach) { struct vm_area_struct *vma; mas_set(mas_detach, 0); mas_for_each(mas_detach, vma, ULONG_MAX) vma_mark_detached(vma, false); __mt_destroy(mas_detach->tree); } /* * vms_gather_munmap_vmas() - Put all VMAs within a range into a maple tree * for removal at a later date. Handles splitting first and last if necessary * and marking the vmas as isolated. * * @vms: The vma munmap struct * @mas_detach: The maple state tracking the detached tree * * Return: 0 on success, error otherwise */ static int vms_gather_munmap_vmas(struct vma_munmap_struct *vms, struct ma_state *mas_detach) { struct vm_area_struct *next = NULL; int error; /* * If we need to split any vma, do it now to save pain later. * Does it split the first one? */ if (vms->start > vms->vma->vm_start) { /* * Make sure that map_count on return from munmap() will * not exceed its limit; but let map_count go just above * its limit temporarily, to help free resources as expected. */ if (vms->end < vms->vma->vm_end && vms->vma->vm_mm->map_count >= sysctl_max_map_count) { error = -ENOMEM; goto map_count_exceeded; } /* Don't bother splitting the VMA if we can't unmap it anyway */ if (!can_modify_vma(vms->vma)) { error = -EPERM; goto start_split_failed; } error = __split_vma(vms->vmi, vms->vma, vms->start, 1); if (error) goto start_split_failed; } vms->prev = vma_prev(vms->vmi); if (vms->prev) vms->unmap_start = vms->prev->vm_end; /* * Detach a range of VMAs from the mm. Using next as a temp variable as * it is always overwritten. */ for_each_vma_range(*(vms->vmi), next, vms->end) { long nrpages; if (!can_modify_vma(next)) { error = -EPERM; goto modify_vma_failed; } /* Does it split the end? */ if (next->vm_end > vms->end) { error = __split_vma(vms->vmi, next, vms->end, 0); if (error) goto end_split_failed; } vma_start_write(next); mas_set(mas_detach, vms->vma_count++); error = mas_store_gfp(mas_detach, next, GFP_KERNEL); if (error) goto munmap_gather_failed; vma_mark_detached(next, true); nrpages = vma_pages(next); vms->nr_pages += nrpages; if (next->vm_flags & VM_LOCKED) vms->locked_vm += nrpages; if (next->vm_flags & VM_ACCOUNT) vms->nr_accounted += nrpages; if (is_exec_mapping(next->vm_flags)) vms->exec_vm += nrpages; else if (is_stack_mapping(next->vm_flags)) vms->stack_vm += nrpages; else if (is_data_mapping(next->vm_flags)) vms->data_vm += nrpages; if (vms->uf) { /* * If userfaultfd_unmap_prep returns an error the vmas * will remain split, but userland will get a * highly unexpected error anyway. This is no * different than the case where the first of the two * __split_vma fails, but we don't undo the first * split, despite we could. This is unlikely enough * failure that it's not worth optimizing it for. */ error = userfaultfd_unmap_prep(next, vms->start, vms->end, vms->uf); if (error) goto userfaultfd_error; } #ifdef CONFIG_DEBUG_VM_MAPLE_TREE BUG_ON(next->vm_start < vms->start); BUG_ON(next->vm_start > vms->end); #endif } vms->next = vma_next(vms->vmi); if (vms->next) vms->unmap_end = vms->next->vm_start; #if defined(CONFIG_DEBUG_VM_MAPLE_TREE) /* Make sure no VMAs are about to be lost. */ { MA_STATE(test, mas_detach->tree, 0, 0); struct vm_area_struct *vma_mas, *vma_test; int test_count = 0; vma_iter_set(vms->vmi, vms->start); rcu_read_lock(); vma_test = mas_find(&test, vms->vma_count - 1); for_each_vma_range(*(vms->vmi), vma_mas, vms->end) { BUG_ON(vma_mas != vma_test); test_count++; vma_test = mas_next(&test, vms->vma_count - 1); } rcu_read_unlock(); BUG_ON(vms->vma_count != test_count); } #endif while (vma_iter_addr(vms->vmi) > vms->start) vma_iter_prev_range(vms->vmi); vms->clear_ptes = true; return 0; userfaultfd_error: munmap_gather_failed: end_split_failed: modify_vma_failed: reattach_vmas(mas_detach); start_split_failed: map_count_exceeded: return error; } /* * init_vma_munmap() - Initializer wrapper for vma_munmap_struct * @vms: The vma munmap struct * @vmi: The vma iterator * @vma: The first vm_area_struct to munmap * @start: The aligned start address to munmap * @end: The aligned end address to munmap * @uf: The userfaultfd list_head * @unlock: Unlock after the operation. Only unlocked on success */ static void init_vma_munmap(struct vma_munmap_struct *vms, struct vma_iterator *vmi, struct vm_area_struct *vma, unsigned long start, unsigned long end, struct list_head *uf, bool unlock) { vms->vmi = vmi; vms->vma = vma; if (vma) { vms->start = start; vms->end = end; } else { vms->start = vms->end = 0; } vms->unlock = unlock; vms->uf = uf; vms->vma_count = 0; vms->nr_pages = vms->locked_vm = vms->nr_accounted = 0; vms->exec_vm = vms->stack_vm = vms->data_vm = 0; vms->unmap_start = FIRST_USER_ADDRESS; vms->unmap_end = USER_PGTABLES_CEILING; vms->clear_ptes = false; } /* * do_vmi_align_munmap() - munmap the aligned region from @start to @end. * @vmi: The vma iterator * @vma: The starting vm_area_struct * @mm: The mm_struct * @start: The aligned start address to munmap. * @end: The aligned end address to munmap. * @uf: The userfaultfd list_head * @unlock: Set to true to drop the mmap_lock. unlocking only happens on * success. * * Return: 0 on success and drops the lock if so directed, error and leaves the * lock held otherwise. */ int do_vmi_align_munmap(struct vma_iterator *vmi, struct vm_area_struct *vma, struct mm_struct *mm, unsigned long start, unsigned long end, struct list_head *uf, bool unlock) { struct maple_tree mt_detach; MA_STATE(mas_detach, &mt_detach, 0, 0); mt_init_flags(&mt_detach, vmi->mas.tree->ma_flags & MT_FLAGS_LOCK_MASK); mt_on_stack(mt_detach); struct vma_munmap_struct vms; int error; init_vma_munmap(&vms, vmi, vma, start, end, uf, unlock); error = vms_gather_munmap_vmas(&vms, &mas_detach); if (error) goto gather_failed; error = vma_iter_clear_gfp(vmi, start, end, GFP_KERNEL); if (error) goto clear_tree_failed; /* Point of no return */ vms_complete_munmap_vmas(&vms, &mas_detach); return 0; clear_tree_failed: reattach_vmas(&mas_detach); gather_failed: validate_mm(mm); return error; } /* * do_vmi_munmap() - munmap a given range. * @vmi: The vma iterator * @mm: The mm_struct * @start: The start address to munmap * @len: The length of the range to munmap * @uf: The userfaultfd list_head * @unlock: set to true if the user wants to drop the mmap_lock on success * * This function takes a @mas that is either pointing to the previous VMA or set * to MA_START and sets it up to remove the mapping(s). The @len will be * aligned. * * Return: 0 on success and drops the lock if so directed, error and leaves the * lock held otherwise. */ int do_vmi_munmap(struct vma_iterator *vmi, struct mm_struct *mm, unsigned long start, size_t len, struct list_head *uf, bool unlock) { unsigned long end; struct vm_area_struct *vma; if ((offset_in_page(start)) || start > TASK_SIZE || len > TASK_SIZE-start) return -EINVAL; end = start + PAGE_ALIGN(len); if (end == start) return -EINVAL; /* Find the first overlapping VMA */ vma = vma_find(vmi, end); if (!vma) { if (unlock) mmap_write_unlock(mm); return 0; } return do_vmi_align_munmap(vmi, vma, mm, start, end, uf, unlock); } /* * We are about to modify one or multiple of a VMA's flags, policy, userfaultfd * context and anonymous VMA name within the range [start, end). * * As a result, we might be able to merge the newly modified VMA range with an * adjacent VMA with identical properties. * * If no merge is possible and the range does not span the entirety of the VMA, * we then need to split the VMA to accommodate the change. * * The function returns either the merged VMA, the original VMA if a split was * required instead, or an error if the split failed. */ static struct vm_area_struct *vma_modify(struct vma_merge_struct *vmg) { struct vm_area_struct *vma = vmg->vma; struct vm_area_struct *merged; /* First, try to merge. */ merged = vma_merge_existing_range(vmg); if (merged) return merged; /* Split any preceding portion of the VMA. */ if (vma->vm_start < vmg->start) { int err = split_vma(vmg->vmi, vma, vmg->start, 1); if (err) return ERR_PTR(err); } /* Split any trailing portion of the VMA. */ if (vma->vm_end > vmg->end) { int err = split_vma(vmg->vmi, vma, vmg->end, 0); if (err) return ERR_PTR(err); } return vma; } struct vm_area_struct *vma_modify_flags( struct vma_iterator *vmi, struct vm_area_struct *prev, struct vm_area_struct *vma, unsigned long start, unsigned long end, unsigned long new_flags) { VMG_VMA_STATE(vmg, vmi, prev, vma, start, end); vmg.flags = new_flags; return vma_modify(&vmg); } struct vm_area_struct *vma_modify_flags_name(struct vma_iterator *vmi, struct vm_area_struct *prev, struct vm_area_struct *vma, unsigned long start, unsigned long end, unsigned long new_flags, struct anon_vma_name *new_name) { VMG_VMA_STATE(vmg, vmi, prev, vma, start, end); vmg.flags = new_flags; vmg.anon_name = new_name; return vma_modify(&vmg); } struct vm_area_struct *vma_modify_policy(struct vma_iterator *vmi, struct vm_area_struct *prev, struct vm_area_struct *vma, unsigned long start, unsigned long end, struct mempolicy *new_pol) { VMG_VMA_STATE(vmg, vmi, prev, vma, start, end); vmg.policy = new_pol; return vma_modify(&vmg); } struct vm_area_struct *vma_modify_flags_uffd(struct vma_iterator *vmi, struct vm_area_struct *prev, struct vm_area_struct *vma, unsigned long start, unsigned long end, unsigned long new_flags, struct vm_userfaultfd_ctx new_ctx) { VMG_VMA_STATE(vmg, vmi, prev, vma, start, end); vmg.flags = new_flags; vmg.uffd_ctx = new_ctx; return vma_modify(&vmg); } /* * Expand vma by delta bytes, potentially merging with an immediately adjacent * VMA with identical properties. */ struct vm_area_struct *vma_merge_extend(struct vma_iterator *vmi, struct vm_area_struct *vma, unsigned long delta) { VMG_VMA_STATE(vmg, vmi, vma, vma, vma->vm_end, vma->vm_end + delta); vmg.next = vma_iter_next_rewind(vmi, NULL); vmg.vma = NULL; /* We use the VMA to populate VMG fields only. */ return vma_merge_new_range(&vmg); } void unlink_file_vma_batch_init(struct unlink_vma_file_batch *vb) { vb->count = 0; } static void unlink_file_vma_batch_process(struct unlink_vma_file_batch *vb) { struct address_space *mapping; int i; mapping = vb->vmas[0]->vm_file->f_mapping; i_mmap_lock_write(mapping); for (i = 0; i < vb->count; i++) { VM_WARN_ON_ONCE(vb->vmas[i]->vm_file->f_mapping != mapping); __remove_shared_vm_struct(vb->vmas[i], mapping); } i_mmap_unlock_write(mapping); unlink_file_vma_batch_init(vb); } void unlink_file_vma_batch_add(struct unlink_vma_file_batch *vb, struct vm_area_struct *vma) { if (vma->vm_file == NULL) return; if ((vb->count > 0 && vb->vmas[0]->vm_file != vma->vm_file) || vb->count == ARRAY_SIZE(vb->vmas)) unlink_file_vma_batch_process(vb); vb->vmas[vb->count] = vma; vb->count++; } void unlink_file_vma_batch_final(struct unlink_vma_file_batch *vb) { if (vb->count > 0) unlink_file_vma_batch_process(vb); } /* * Unlink a file-based vm structure from its interval tree, to hide * vma from rmap and vmtruncate before freeing its page tables. */ void unlink_file_vma(struct vm_area_struct *vma) { struct file *file = vma->vm_file; if (file) { struct address_space *mapping = file->f_mapping; i_mmap_lock_write(mapping); __remove_shared_vm_struct(vma, mapping); i_mmap_unlock_write(mapping); } } void vma_link_file(struct vm_area_struct *vma) { struct file *file = vma->vm_file; struct address_space *mapping; if (file) { mapping = file->f_mapping; i_mmap_lock_write(mapping); __vma_link_file(vma, mapping); i_mmap_unlock_write(mapping); } } int vma_link(struct mm_struct *mm, struct vm_area_struct *vma) { VMA_ITERATOR(vmi, mm, 0); vma_iter_config(&vmi, vma->vm_start, vma->vm_end); if (vma_iter_prealloc(&vmi, vma)) return -ENOMEM; vma_start_write(vma); vma_iter_store(&vmi, vma); vma_link_file(vma); mm->map_count++; validate_mm(mm); return 0; } /* * Copy the vma structure to a new location in the same mm, * prior to moving page table entries, to effect an mremap move. */ struct vm_area_struct *copy_vma(struct vm_area_struct **vmap, unsigned long addr, unsigned long len, pgoff_t pgoff, bool *need_rmap_locks) { struct vm_area_struct *vma = *vmap; unsigned long vma_start = vma->vm_start; struct mm_struct *mm = vma->vm_mm; struct vm_area_struct *new_vma; bool faulted_in_anon_vma = true; VMA_ITERATOR(vmi, mm, addr); VMG_VMA_STATE(vmg, &vmi, NULL, vma, addr, addr + len); /* * If anonymous vma has not yet been faulted, update new pgoff * to match new location, to increase its chance of merging. */ if (unlikely(vma_is_anonymous(vma) && !vma->anon_vma)) { pgoff = addr >> PAGE_SHIFT; faulted_in_anon_vma = false; } new_vma = find_vma_prev(mm, addr, &vmg.prev); if (new_vma && new_vma->vm_start < addr + len) return NULL; /* should never get here */ vmg.vma = NULL; /* New VMA range. */ vmg.pgoff = pgoff; vmg.next = vma_iter_next_rewind(&vmi, NULL); new_vma = vma_merge_new_range(&vmg); if (new_vma) { /* * Source vma may have been merged into new_vma */ if (unlikely(vma_start >= new_vma->vm_start && vma_start < new_vma->vm_end)) { /* * The only way we can get a vma_merge with * self during an mremap is if the vma hasn't * been faulted in yet and we were allowed to * reset the dst vma->vm_pgoff to the * destination address of the mremap to allow * the merge to happen. mremap must change the * vm_pgoff linearity between src and dst vmas * (in turn preventing a vma_merge) to be * safe. It is only safe to keep the vm_pgoff * linear if there are no pages mapped yet. */ VM_BUG_ON_VMA(faulted_in_anon_vma, new_vma); *vmap = vma = new_vma; } *need_rmap_locks = (new_vma->vm_pgoff <= vma->vm_pgoff); } else { new_vma = vm_area_dup(vma); if (!new_vma) goto out; vma_set_range(new_vma, addr, addr + len, pgoff); if (vma_dup_policy(vma, new_vma)) goto out_free_vma; if (anon_vma_clone(new_vma, vma)) goto out_free_mempol; if (new_vma->vm_file) get_file(new_vma->vm_file); if (new_vma->vm_ops && new_vma->vm_ops->open) new_vma->vm_ops->open(new_vma); if (vma_link(mm, new_vma)) goto out_vma_link; *need_rmap_locks = false; } return new_vma; out_vma_link: vma_close(new_vma); if (new_vma->vm_file) fput(new_vma->vm_file); unlink_anon_vmas(new_vma); out_free_mempol: mpol_put(vma_policy(new_vma)); out_free_vma: vm_area_free(new_vma); out: return NULL; } /* * Rough compatibility check to quickly see if it's even worth looking * at sharing an anon_vma. * * They need to have the same vm_file, and the flags can only differ * in things that mprotect may change. * * NOTE! The fact that we share an anon_vma doesn't _have_ to mean that * we can merge the two vma's. For example, we refuse to merge a vma if * there is a vm_ops->close() function, because that indicates that the * driver is doing some kind of reference counting. But that doesn't * really matter for the anon_vma sharing case. */ static int anon_vma_compatible(struct vm_area_struct *a, struct vm_area_struct *b) { return a->vm_end == b->vm_start && mpol_equal(vma_policy(a), vma_policy(b)) && a->vm_file == b->vm_file && !((a->vm_flags ^ b->vm_flags) & ~(VM_ACCESS_FLAGS | VM_SOFTDIRTY)) && b->vm_pgoff == a->vm_pgoff + ((b->vm_start - a->vm_start) >> PAGE_SHIFT); } /* * Do some basic sanity checking to see if we can re-use the anon_vma * from 'old'. The 'a'/'b' vma's are in VM order - one of them will be * the same as 'old', the other will be the new one that is trying * to share the anon_vma. * * NOTE! This runs with mmap_lock held for reading, so it is possible that * the anon_vma of 'old' is concurrently in the process of being set up * by another page fault trying to merge _that_. But that's ok: if it * is being set up, that automatically means that it will be a singleton * acceptable for merging, so we can do all of this optimistically. But * we do that READ_ONCE() to make sure that we never re-load the pointer. * * IOW: that the "list_is_singular()" test on the anon_vma_chain only * matters for the 'stable anon_vma' case (ie the thing we want to avoid * is to return an anon_vma that is "complex" due to having gone through * a fork). * * We also make sure that the two vma's are compatible (adjacent, * and with the same memory policies). That's all stable, even with just * a read lock on the mmap_lock. */ static struct anon_vma *reusable_anon_vma(struct vm_area_struct *old, struct vm_area_struct *a, struct vm_area_struct *b) { if (anon_vma_compatible(a, b)) { struct anon_vma *anon_vma = READ_ONCE(old->anon_vma); if (anon_vma && list_is_singular(&old->anon_vma_chain)) return anon_vma; } return NULL; } /* * find_mergeable_anon_vma is used by anon_vma_prepare, to check * neighbouring vmas for a suitable anon_vma, before it goes off * to allocate a new anon_vma. It checks because a repetitive * sequence of mprotects and faults may otherwise lead to distinct * anon_vmas being allocated, preventing vma merge in subsequent * mprotect. */ struct anon_vma *find_mergeable_anon_vma(struct vm_area_struct *vma) { struct anon_vma *anon_vma = NULL; struct vm_area_struct *prev, *next; VMA_ITERATOR(vmi, vma->vm_mm, vma->vm_end); /* Try next first. */ next = vma_iter_load(&vmi); if (next) { anon_vma = reusable_anon_vma(next, vma, next); if (anon_vma) return anon_vma; } prev = vma_prev(&vmi); VM_BUG_ON_VMA(prev != vma, vma); prev = vma_prev(&vmi); /* Try prev next. */ if (prev) anon_vma = reusable_anon_vma(prev, prev, vma); /* * We might reach here with anon_vma == NULL if we can't find * any reusable anon_vma. * There's no absolute need to look only at touching neighbours: * we could search further afield for "compatible" anon_vmas. * But it would probably just be a waste of time searching, * or lead to too many vmas hanging off the same anon_vma. * We're trying to allow mprotect remerging later on, * not trying to minimize memory used for anon_vmas. */ return anon_vma; } static bool vm_ops_needs_writenotify(const struct vm_operations_struct *vm_ops) { return vm_ops && (vm_ops->page_mkwrite || vm_ops->pfn_mkwrite); } static bool vma_is_shared_writable(struct vm_area_struct *vma) { return (vma->vm_flags & (VM_WRITE | VM_SHARED)) == (VM_WRITE | VM_SHARED); } static bool vma_fs_can_writeback(struct vm_area_struct *vma) { /* No managed pages to writeback. */ if (vma->vm_flags & VM_PFNMAP) return false; return vma->vm_file && vma->vm_file->f_mapping && mapping_can_writeback(vma->vm_file->f_mapping); } /* * Does this VMA require the underlying folios to have their dirty state * tracked? */ bool vma_needs_dirty_tracking(struct vm_area_struct *vma) { /* Only shared, writable VMAs require dirty tracking. */ if (!vma_is_shared_writable(vma)) return false; /* Does the filesystem need to be notified? */ if (vm_ops_needs_writenotify(vma->vm_ops)) return true; /* * Even if the filesystem doesn't indicate a need for writenotify, if it * can writeback, dirty tracking is still required. */ return vma_fs_can_writeback(vma); } /* * Some shared mappings will want the pages marked read-only * to track write events. If so, we'll downgrade vm_page_prot * to the private version (using protection_map[] without the * VM_SHARED bit). */ bool vma_wants_writenotify(struct vm_area_struct *vma, pgprot_t vm_page_prot) { /* If it was private or non-writable, the write bit is already clear */ if (!vma_is_shared_writable(vma)) return false; /* The backer wishes to know when pages are first written to? */ if (vm_ops_needs_writenotify(vma->vm_ops)) return true; /* The open routine did something to the protections that pgprot_modify * won't preserve? */ if (pgprot_val(vm_page_prot) != pgprot_val(vm_pgprot_modify(vm_page_prot, vma->vm_flags))) return false; /* * Do we need to track softdirty? hugetlb does not support softdirty * tracking yet. */ if (vma_soft_dirty_enabled(vma) && !is_vm_hugetlb_page(vma)) return true; /* Do we need write faults for uffd-wp tracking? */ if (userfaultfd_wp(vma)) return true; /* Can the mapping track the dirty pages? */ return vma_fs_can_writeback(vma); } static DEFINE_MUTEX(mm_all_locks_mutex); static void vm_lock_anon_vma(struct mm_struct *mm, struct anon_vma *anon_vma) { if (!test_bit(0, (unsigned long *) &anon_vma->root->rb_root.rb_root.rb_node)) { /* * The LSB of head.next can't change from under us * because we hold the mm_all_locks_mutex. */ down_write_nest_lock(&anon_vma->root->rwsem, &mm->mmap_lock); /* * We can safely modify head.next after taking the * anon_vma->root->rwsem. If some other vma in this mm shares * the same anon_vma we won't take it again. * * No need of atomic instructions here, head.next * can't change from under us thanks to the * anon_vma->root->rwsem. */ if (__test_and_set_bit(0, (unsigned long *) &anon_vma->root->rb_root.rb_root.rb_node)) BUG(); } } static void vm_lock_mapping(struct mm_struct *mm, struct address_space *mapping) { if (!test_bit(AS_MM_ALL_LOCKS, &mapping->flags)) { /* * AS_MM_ALL_LOCKS can't change from under us because * we hold the mm_all_locks_mutex. * * Operations on ->flags have to be atomic because * even if AS_MM_ALL_LOCKS is stable thanks to the * mm_all_locks_mutex, there may be other cpus * changing other bitflags in parallel to us. */ if (test_and_set_bit(AS_MM_ALL_LOCKS, &mapping->flags)) BUG(); down_write_nest_lock(&mapping->i_mmap_rwsem, &mm->mmap_lock); } } /* * This operation locks against the VM for all pte/vma/mm related * operations that could ever happen on a certain mm. This includes * vmtruncate, try_to_unmap, and all page faults. * * The caller must take the mmap_lock in write mode before calling * mm_take_all_locks(). The caller isn't allowed to release the * mmap_lock until mm_drop_all_locks() returns. * * mmap_lock in write mode is required in order to block all operations * that could modify pagetables and free pages without need of * altering the vma layout. It's also needed in write mode to avoid new * anon_vmas to be associated with existing vmas. * * A single task can't take more than one mm_take_all_locks() in a row * or it would deadlock. * * The LSB in anon_vma->rb_root.rb_node and the AS_MM_ALL_LOCKS bitflag in * mapping->flags avoid to take the same lock twice, if more than one * vma in this mm is backed by the same anon_vma or address_space. * * We take locks in following order, accordingly to comment at beginning * of mm/rmap.c: * - all hugetlbfs_i_mmap_rwsem_key locks (aka mapping->i_mmap_rwsem for * hugetlb mapping); * - all vmas marked locked * - all i_mmap_rwsem locks; * - all anon_vma->rwseml * * We can take all locks within these types randomly because the VM code * doesn't nest them and we protected from parallel mm_take_all_locks() by * mm_all_locks_mutex. * * mm_take_all_locks() and mm_drop_all_locks are expensive operations * that may have to take thousand of locks. * * mm_take_all_locks() can fail if it's interrupted by signals. */ int mm_take_all_locks(struct mm_struct *mm) { struct vm_area_struct *vma; struct anon_vma_chain *avc; VMA_ITERATOR(vmi, mm, 0); mmap_assert_write_locked(mm); mutex_lock(&mm_all_locks_mutex); /* * vma_start_write() does not have a complement in mm_drop_all_locks() * because vma_start_write() is always asymmetrical; it marks a VMA as * being written to until mmap_write_unlock() or mmap_write_downgrade() * is reached. */ for_each_vma(vmi, vma) { if (signal_pending(current)) goto out_unlock; vma_start_write(vma); } vma_iter_init(&vmi, mm, 0); for_each_vma(vmi, vma) { if (signal_pending(current)) goto out_unlock; if (vma->vm_file && vma->vm_file->f_mapping && is_vm_hugetlb_page(vma)) vm_lock_mapping(mm, vma->vm_file->f_mapping); } vma_iter_init(&vmi, mm, 0); for_each_vma(vmi, vma) { if (signal_pending(current)) goto out_unlock; if (vma->vm_file && vma->vm_file->f_mapping && !is_vm_hugetlb_page(vma)) vm_lock_mapping(mm, vma->vm_file->f_mapping); } vma_iter_init(&vmi, mm, 0); for_each_vma(vmi, vma) { if (signal_pending(current)) goto out_unlock; if (vma->anon_vma) list_for_each_entry(avc, &vma->anon_vma_chain, same_vma) vm_lock_anon_vma(mm, avc->anon_vma); } return 0; out_unlock: mm_drop_all_locks(mm); return -EINTR; } static void vm_unlock_anon_vma(struct anon_vma *anon_vma) { if (test_bit(0, (unsigned long *) &anon_vma->root->rb_root.rb_root.rb_node)) { /* * The LSB of head.next can't change to 0 from under * us because we hold the mm_all_locks_mutex. * * We must however clear the bitflag before unlocking * the vma so the users using the anon_vma->rb_root will * never see our bitflag. * * No need of atomic instructions here, head.next * can't change from under us until we release the * anon_vma->root->rwsem. */ if (!__test_and_clear_bit(0, (unsigned long *) &anon_vma->root->rb_root.rb_root.rb_node)) BUG(); anon_vma_unlock_write(anon_vma); } } static void vm_unlock_mapping(struct address_space *mapping) { if (test_bit(AS_MM_ALL_LOCKS, &mapping->flags)) { /* * AS_MM_ALL_LOCKS can't change to 0 from under us * because we hold the mm_all_locks_mutex. */ i_mmap_unlock_write(mapping); if (!test_and_clear_bit(AS_MM_ALL_LOCKS, &mapping->flags)) BUG(); } } /* * The mmap_lock cannot be released by the caller until * mm_drop_all_locks() returns. */ void mm_drop_all_locks(struct mm_struct *mm) { struct vm_area_struct *vma; struct anon_vma_chain *avc; VMA_ITERATOR(vmi, mm, 0); mmap_assert_write_locked(mm); BUG_ON(!mutex_is_locked(&mm_all_locks_mutex)); for_each_vma(vmi, vma) { if (vma->anon_vma) list_for_each_entry(avc, &vma->anon_vma_chain, same_vma) vm_unlock_anon_vma(avc->anon_vma); if (vma->vm_file && vma->vm_file->f_mapping) vm_unlock_mapping(vma->vm_file->f_mapping); } mutex_unlock(&mm_all_locks_mutex); } /* * We account for memory if it's a private writeable mapping, * not hugepages and VM_NORESERVE wasn't set. */ static bool accountable_mapping(struct file *file, vm_flags_t vm_flags) { /* * hugetlb has its own accounting separate from the core VM * VM_HUGETLB may not be set yet so we cannot check for that flag. */ if (file && is_file_hugepages(file)) return false; return (vm_flags & (VM_NORESERVE | VM_SHARED | VM_WRITE)) == VM_WRITE; } /* * vms_abort_munmap_vmas() - Undo as much as possible from an aborted munmap() * operation. * @vms: The vma unmap structure * @mas_detach: The maple state with the detached maple tree * * Reattach any detached vmas, free up the maple tree used to track the vmas. * If that's not possible because the ptes are cleared (and vm_ops->closed() may * have been called), then a NULL is written over the vmas and the vmas are * removed (munmap() completed). */ static void vms_abort_munmap_vmas(struct vma_munmap_struct *vms, struct ma_state *mas_detach) { struct ma_state *mas = &vms->vmi->mas; if (!vms->nr_pages) return; if (vms->clear_ptes) return reattach_vmas(mas_detach); /* * Aborting cannot just call the vm_ops open() because they are often * not symmetrical and state data has been lost. Resort to the old * failure method of leaving a gap where the MAP_FIXED mapping failed. */ mas_set_range(mas, vms->start, vms->end - 1); mas_store_gfp(mas, NULL, GFP_KERNEL|__GFP_NOFAIL); /* Clean up the insertion of the unfortunate gap */ vms_complete_munmap_vmas(vms, mas_detach); } /* * __mmap_prepare() - Prepare to gather any overlapping VMAs that need to be * unmapped once the map operation is completed, check limits, account mapping * and clean up any pre-existing VMAs. * * @map: Mapping state. * @uf: Userfaultfd context list. * * Returns: 0 on success, error code otherwise. */ static int __mmap_prepare(struct mmap_state *map, struct list_head *uf) { int error; struct vma_iterator *vmi = map->vmi; struct vma_munmap_struct *vms = &map->vms; /* Find the first overlapping VMA and initialise unmap state. */ vms->vma = vma_find(vmi, map->end); init_vma_munmap(vms, vmi, vms->vma, map->addr, map->end, uf, /* unlock = */ false); /* OK, we have overlapping VMAs - prepare to unmap them. */ if (vms->vma) { mt_init_flags(&map->mt_detach, vmi->mas.tree->ma_flags & MT_FLAGS_LOCK_MASK); mt_on_stack(map->mt_detach); mas_init(&map->mas_detach, &map->mt_detach, /* addr = */ 0); /* Prepare to unmap any existing mapping in the area */ error = vms_gather_munmap_vmas(vms, &map->mas_detach); if (error) { /* On error VMAs will already have been reattached. */ vms->nr_pages = 0; return error; } map->next = vms->next; map->prev = vms->prev; } else { map->next = vma_iter_next_rewind(vmi, &map->prev); } /* Check against address space limit. */ if (!may_expand_vm(map->mm, map->flags, map->pglen - vms->nr_pages)) return -ENOMEM; /* Private writable mapping: check memory availability. */ if (accountable_mapping(map->file, map->flags)) { map->charged = map->pglen; map->charged -= vms->nr_accounted; if (map->charged) { error = security_vm_enough_memory_mm(map->mm, map->charged); if (error) return error; } vms->nr_accounted = 0; map->flags |= VM_ACCOUNT; } /* * Clear PTEs while the vma is still in the tree so that rmap * cannot race with the freeing later in the truncate scenario. * This is also needed for mmap_file(), which is why vm_ops * close function is called. */ vms_clean_up_area(vms, &map->mas_detach); return 0; } static int __mmap_new_file_vma(struct mmap_state *map, struct vm_area_struct *vma) { struct vma_iterator *vmi = map->vmi; int error; vma->vm_file = get_file(map->file); error = mmap_file(vma->vm_file, vma); if (error) { fput(vma->vm_file); vma->vm_file = NULL; vma_iter_set(vmi, vma->vm_end); /* Undo any partial mapping done by a device driver. */ unmap_region(&vmi->mas, vma, map->prev, map->next); return error; } /* Drivers cannot alter the address of the VMA. */ WARN_ON_ONCE(map->addr != vma->vm_start); /* * Drivers should not permit writability when previously it was * disallowed. */ VM_WARN_ON_ONCE(map->flags != vma->vm_flags && !(map->flags & VM_MAYWRITE) && (vma->vm_flags & VM_MAYWRITE)); /* If the flags change (and are mergeable), let's retry later. */ map->retry_merge = vma->vm_flags != map->flags && !(vma->vm_flags & VM_SPECIAL); map->flags = vma->vm_flags; return 0; } /* * __mmap_new_vma() - Allocate a new VMA for the region, as merging was not * possible. * * @map: Mapping state. * @vmap: Output pointer for the new VMA. * * Returns: Zero on success, or an error. */ static int __mmap_new_vma(struct mmap_state *map, struct vm_area_struct **vmap) { struct vma_iterator *vmi = map->vmi; int error = 0; struct vm_area_struct *vma; /* * Determine the object being mapped and call the appropriate * specific mapper. the address has already been validated, but * not unmapped, but the maps are removed from the list. */ vma = vm_area_alloc(map->mm); if (!vma) return -ENOMEM; vma_iter_config(vmi, map->addr, map->end); vma_set_range(vma, map->addr, map->end, map->pgoff); vm_flags_init(vma, map->flags); vma->vm_page_prot = vm_get_page_prot(map->flags); if (vma_iter_prealloc(vmi, vma)) { error = -ENOMEM; goto free_vma; } if (map->file) error = __mmap_new_file_vma(map, vma); else if (map->flags & VM_SHARED) error = shmem_zero_setup(vma); else vma_set_anonymous(vma); if (error) goto free_iter_vma; #ifdef CONFIG_SPARC64 /* TODO: Fix SPARC ADI! */ WARN_ON_ONCE(!arch_validate_flags(map->flags)); #endif /* Lock the VMA since it is modified after insertion into VMA tree */ vma_start_write(vma); vma_iter_store(vmi, vma); map->mm->map_count++; vma_link_file(vma); /* * vma_merge_new_range() calls khugepaged_enter_vma() too, the below * call covers the non-merge case. */ khugepaged_enter_vma(vma, map->flags); ksm_add_vma(vma); *vmap = vma; return 0; free_iter_vma: vma_iter_free(vmi); free_vma: vm_area_free(vma); return error; } /* * __mmap_complete() - Unmap any VMAs we overlap, account memory mapping * statistics, handle locking and finalise the VMA. * * @map: Mapping state. * @vma: Merged or newly allocated VMA for the mmap()'d region. */ static void __mmap_complete(struct mmap_state *map, struct vm_area_struct *vma) { struct mm_struct *mm = map->mm; unsigned long vm_flags = vma->vm_flags; perf_event_mmap(vma); /* Unmap any existing mapping in the area. */ vms_complete_munmap_vmas(&map->vms, &map->mas_detach); vm_stat_account(mm, vma->vm_flags, map->pglen); if (vm_flags & VM_LOCKED) { if ((vm_flags & VM_SPECIAL) || vma_is_dax(vma) || is_vm_hugetlb_page(vma) || vma == get_gate_vma(mm)) vm_flags_clear(vma, VM_LOCKED_MASK); else mm->locked_vm += map->pglen; } if (vma->vm_file) uprobe_mmap(vma); /* * New (or expanded) vma always get soft dirty status. * Otherwise user-space soft-dirty page tracker won't * be able to distinguish situation when vma area unmapped, * then new mapped in-place (which must be aimed as * a completely new data area). */ vm_flags_set(vma, VM_SOFTDIRTY); vma_set_page_prot(vma); } unsigned long __mmap_region(struct file *file, unsigned long addr, unsigned long len, vm_flags_t vm_flags, unsigned long pgoff, struct list_head *uf) { struct mm_struct *mm = current->mm; struct vm_area_struct *vma = NULL; int error; VMA_ITERATOR(vmi, mm, addr); MMAP_STATE(map, mm, &vmi, addr, len, pgoff, vm_flags, file); error = __mmap_prepare(&map, uf); if (error) goto abort_munmap; /* Attempt to merge with adjacent VMAs... */ if (map.prev || map.next) { VMG_MMAP_STATE(vmg, &map, /* vma = */ NULL); vma = vma_merge_new_range(&vmg); } /* ...but if we can't, allocate a new VMA. */ if (!vma) { error = __mmap_new_vma(&map, &vma); if (error) goto unacct_error; } /* If flags changed, we might be able to merge, so try again. */ if (map.retry_merge) { VMG_MMAP_STATE(vmg, &map, vma); vma_iter_config(map.vmi, map.addr, map.end); vma_merge_existing_range(&vmg); } __mmap_complete(&map, vma); return addr; /* Accounting was done by __mmap_prepare(). */ unacct_error: if (map.charged) vm_unacct_memory(map.charged); abort_munmap: vms_abort_munmap_vmas(&map.vms, &map.mas_detach); return error; } |
| 36 36 756 36 755 753 754 752 753 36 36 36 36 36 36 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 | // SPDX-License-Identifier: GPL-2.0-or-later /* * printk_safe.c - Safe printk for printk-deadlock-prone contexts */ #include <linux/preempt.h> #include <linux/kdb.h> #include <linux/smp.h> #include <linux/cpumask.h> #include <linux/printk.h> #include <linux/kprobes.h> #include "internal.h" /* Context where printk messages are never suppressed */ static atomic_t force_con; void printk_force_console_enter(void) { atomic_inc(&force_con); } void printk_force_console_exit(void) { atomic_dec(&force_con); } bool is_printk_force_console(void) { return atomic_read(&force_con); } static DEFINE_PER_CPU(int, printk_context); /* Can be preempted by NMI. */ void __printk_safe_enter(void) { this_cpu_inc(printk_context); } /* Can be preempted by NMI. */ void __printk_safe_exit(void) { this_cpu_dec(printk_context); } void __printk_deferred_enter(void) { cant_migrate(); __printk_safe_enter(); } void __printk_deferred_exit(void) { cant_migrate(); __printk_safe_exit(); } bool is_printk_legacy_deferred(void) { /* * The per-CPU variable @printk_context can be read safely in any * context. CPU migration is always disabled when set. */ return (force_legacy_kthread() || this_cpu_read(printk_context) || in_nmi()); } asmlinkage int vprintk(const char *fmt, va_list args) { #ifdef CONFIG_KGDB_KDB /* Allow to pass printk() to kdb but avoid a recursion. */ if (unlikely(kdb_trap_printk && kdb_printf_cpu < 0)) return vkdb_printf(KDB_MSGSRC_PRINTK, fmt, args); #endif /* * Use the main logbuf even in NMI. But avoid calling console * drivers that might have their own locks. */ if (is_printk_legacy_deferred()) return vprintk_deferred(fmt, args); /* No obstacles. */ return vprintk_default(fmt, args); } EXPORT_SYMBOL(vprintk); |
| 655 7 651 292 85 622 4 623 622 651 302 625 150 109 109 45 44 97 78 78 4 144 18 60 2 7 7 7 11 11 1 1 7 144 20 18 49 62 16 16 16 16 4 16 16 152 145 144 145 82 143 38 152 67 68 60 80 45 97 89 11 169 44 171 171 106 96 151 44 171 170 89 11 11 11 97 7 7 7 59 7 55 11 55 33 7 59 33 405 91 32 406 194 194 7 7 1 7 8 8 8 81 82 5 11 11 1 10 543 544 544 45 49 4 4 4 45 45 45 45 45 45 45 167 167 168 167 99 101 95 96 93 92 17 17 95 91 17 20 20 20 20 20 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 1522 1523 1524 1525 1526 1527 1528 1529 1530 1531 1532 1533 1534 1535 1536 1537 1538 1539 1540 1541 1542 1543 1544 1545 1546 1547 1548 1549 1550 1551 1552 1553 1554 1555 1556 1557 1558 1559 1560 1561 1562 1563 1564 1565 1566 1567 1568 1569 1570 1571 1572 1573 1574 1575 1576 1577 1578 1579 1580 1581 1582 1583 1584 1585 1586 1587 1588 1589 1590 1591 1592 1593 1594 1595 1596 1597 1598 1599 1600 1601 1602 1603 1604 1605 1606 1607 1608 1609 1610 1611 1612 1613 1614 1615 1616 1617 1618 1619 1620 1621 1622 1623 1624 1625 1626 1627 1628 1629 1630 1631 1632 1633 1634 1635 1636 1637 1638 1639 1640 1641 1642 1643 1644 1645 1646 1647 1648 1649 1650 1651 1652 1653 1654 1655 1656 1657 1658 1659 1660 1661 1662 1663 1664 1665 1666 1667 1668 1669 1670 1671 1672 1673 1674 1675 1676 1677 1678 1679 1680 1681 1682 1683 1684 1685 1686 1687 1688 1689 1690 1691 1692 1693 1694 1695 1696 1697 1698 1699 1700 1701 1702 1703 1704 1705 1706 1707 1708 1709 1710 1711 1712 1713 1714 1715 1716 1717 1718 1719 1720 1721 1722 1723 1724 1725 1726 1727 1728 1729 1730 1731 1732 1733 1734 1735 1736 1737 1738 1739 1740 1741 1742 1743 1744 1745 1746 1747 1748 1749 1750 1751 1752 1753 1754 1755 1756 1757 1758 1759 1760 1761 1762 1763 1764 1765 1766 1767 1768 1769 1770 1771 1772 1773 1774 1775 1776 1777 1778 1779 1780 1781 1782 1783 1784 1785 1786 1787 1788 1789 1790 1791 1792 1793 1794 1795 1796 1797 1798 1799 1800 1801 1802 1803 1804 1805 1806 1807 1808 1809 1810 1811 1812 1813 1814 1815 1816 1817 1818 1819 1820 1821 1822 1823 1824 1825 1826 1827 1828 1829 1830 1831 1832 1833 1834 1835 1836 1837 1838 1839 1840 1841 1842 1843 1844 1845 1846 1847 1848 1849 1850 1851 1852 1853 1854 1855 1856 1857 1858 1859 1860 1861 1862 1863 1864 1865 1866 1867 1868 1869 1870 1871 1872 1873 1874 1875 1876 1877 1878 1879 1880 1881 1882 1883 1884 1885 1886 1887 1888 1889 1890 1891 1892 1893 1894 1895 1896 1897 1898 1899 1900 1901 1902 1903 1904 1905 1906 1907 1908 1909 1910 1911 1912 1913 1914 1915 1916 1917 1918 1919 1920 1921 1922 1923 1924 1925 1926 1927 1928 1929 1930 1931 1932 1933 1934 1935 1936 1937 1938 1939 1940 1941 1942 1943 1944 1945 1946 1947 1948 1949 1950 1951 1952 1953 1954 1955 1956 1957 1958 1959 1960 1961 1962 1963 1964 1965 1966 1967 1968 1969 1970 1971 1972 1973 1974 1975 1976 1977 1978 1979 1980 1981 1982 1983 1984 1985 1986 1987 1988 1989 1990 1991 1992 1993 1994 1995 1996 1997 1998 1999 2000 2001 2002 2003 2004 2005 2006 2007 2008 2009 2010 2011 2012 2013 2014 2015 2016 2017 2018 2019 2020 2021 2022 2023 2024 2025 2026 2027 2028 2029 2030 2031 2032 2033 2034 2035 2036 2037 2038 2039 2040 2041 2042 2043 2044 2045 2046 2047 2048 2049 2050 2051 2052 2053 2054 2055 2056 2057 2058 2059 2060 2061 2062 2063 2064 2065 2066 2067 2068 2069 2070 2071 2072 2073 2074 2075 2076 2077 2078 2079 2080 2081 2082 2083 2084 2085 2086 2087 2088 2089 2090 2091 2092 2093 2094 2095 2096 2097 2098 2099 2100 2101 2102 2103 2104 2105 2106 2107 2108 2109 2110 2111 2112 2113 2114 2115 2116 2117 2118 2119 2120 2121 2122 2123 2124 2125 2126 2127 2128 2129 2130 2131 2132 2133 2134 2135 2136 2137 2138 2139 2140 2141 2142 2143 2144 2145 2146 2147 2148 2149 2150 2151 2152 2153 2154 2155 2156 2157 2158 2159 2160 2161 2162 2163 2164 2165 2166 2167 2168 2169 2170 2171 2172 2173 2174 2175 2176 2177 2178 2179 2180 2181 2182 2183 2184 2185 2186 2187 2188 2189 2190 2191 2192 2193 2194 2195 2196 2197 2198 2199 2200 2201 2202 2203 2204 2205 2206 2207 2208 2209 2210 2211 2212 2213 2214 2215 2216 2217 2218 2219 2220 2221 2222 2223 2224 2225 2226 2227 2228 2229 2230 2231 2232 2233 2234 2235 2236 2237 2238 2239 2240 2241 2242 2243 2244 2245 2246 2247 2248 2249 2250 2251 2252 2253 2254 2255 2256 2257 2258 2259 2260 2261 2262 2263 2264 2265 2266 2267 2268 2269 2270 2271 2272 2273 2274 2275 2276 2277 2278 2279 2280 2281 2282 2283 2284 2285 2286 2287 2288 2289 2290 2291 2292 2293 2294 2295 2296 2297 2298 2299 2300 2301 2302 2303 2304 2305 2306 2307 2308 2309 2310 2311 2312 2313 2314 2315 2316 2317 2318 2319 2320 2321 2322 2323 2324 2325 2326 2327 2328 2329 2330 2331 2332 2333 2334 2335 2336 2337 2338 | // SPDX-License-Identifier: GPL-2.0+ /* * XArray implementation * Copyright (c) 2017-2018 Microsoft Corporation * Copyright (c) 2018-2020 Oracle * Author: Matthew Wilcox <willy@infradead.org> */ #include <linux/bitmap.h> #include <linux/export.h> #include <linux/list.h> #include <linux/slab.h> #include <linux/xarray.h> #include "radix-tree.h" /* * Coding conventions in this file: * * @xa is used to refer to the entire xarray. * @xas is the 'xarray operation state'. It may be either a pointer to * an xa_state, or an xa_state stored on the stack. This is an unfortunate * ambiguity. * @index is the index of the entry being operated on * @mark is an xa_mark_t; a small number indicating one of the mark bits. * @node refers to an xa_node; usually the primary one being operated on by * this function. * @offset is the index into the slots array inside an xa_node. * @parent refers to the @xa_node closer to the head than @node. * @entry refers to something stored in a slot in the xarray */ static inline unsigned int xa_lock_type(const struct xarray *xa) { return (__force unsigned int)xa->xa_flags & 3; } static inline void xas_lock_type(struct xa_state *xas, unsigned int lock_type) { if (lock_type == XA_LOCK_IRQ) xas_lock_irq(xas); else if (lock_type == XA_LOCK_BH) xas_lock_bh(xas); else xas_lock(xas); } static inline void xas_unlock_type(struct xa_state *xas, unsigned int lock_type) { if (lock_type == XA_LOCK_IRQ) xas_unlock_irq(xas); else if (lock_type == XA_LOCK_BH) xas_unlock_bh(xas); else xas_unlock(xas); } static inline bool xa_track_free(const struct xarray *xa) { return xa->xa_flags & XA_FLAGS_TRACK_FREE; } static inline bool xa_zero_busy(const struct xarray *xa) { return xa->xa_flags & XA_FLAGS_ZERO_BUSY; } static inline void xa_mark_set(struct xarray *xa, xa_mark_t mark) { if (!(xa->xa_flags & XA_FLAGS_MARK(mark))) xa->xa_flags |= XA_FLAGS_MARK(mark); } static inline void xa_mark_clear(struct xarray *xa, xa_mark_t mark) { if (xa->xa_flags & XA_FLAGS_MARK(mark)) xa->xa_flags &= ~(XA_FLAGS_MARK(mark)); } static inline unsigned long *node_marks(struct xa_node *node, xa_mark_t mark) { return node->marks[(__force unsigned)mark]; } static inline bool node_get_mark(struct xa_node *node, unsigned int offset, xa_mark_t mark) { return test_bit(offset, node_marks(node, mark)); } /* returns true if the bit was set */ static inline bool node_set_mark(struct xa_node *node, unsigned int offset, xa_mark_t mark) { return __test_and_set_bit(offset, node_marks(node, mark)); } /* returns true if the bit was set */ static inline bool node_clear_mark(struct xa_node *node, unsigned int offset, xa_mark_t mark) { return __test_and_clear_bit(offset, node_marks(node, mark)); } static inline bool node_any_mark(struct xa_node *node, xa_mark_t mark) { return !bitmap_empty(node_marks(node, mark), XA_CHUNK_SIZE); } static inline void node_mark_all(struct xa_node *node, xa_mark_t mark) { bitmap_fill(node_marks(node, mark), XA_CHUNK_SIZE); } #define mark_inc(mark) do { \ mark = (__force xa_mark_t)((__force unsigned)(mark) + 1); \ } while (0) /* * xas_squash_marks() - Merge all marks to the first entry * @xas: Array operation state. * * Set a mark on the first entry if any entry has it set. Clear marks on * all sibling entries. */ static void xas_squash_marks(const struct xa_state *xas) { unsigned int mark = 0; unsigned int limit = xas->xa_offset + xas->xa_sibs + 1; if (!xas->xa_sibs) return; do { unsigned long *marks = xas->xa_node->marks[mark]; if (find_next_bit(marks, limit, xas->xa_offset + 1) == limit) continue; __set_bit(xas->xa_offset, marks); bitmap_clear(marks, xas->xa_offset + 1, xas->xa_sibs); } while (mark++ != (__force unsigned)XA_MARK_MAX); } /* extracts the offset within this node from the index */ static unsigned int get_offset(unsigned long index, struct xa_node *node) { return (index >> node->shift) & XA_CHUNK_MASK; } static void xas_set_offset(struct xa_state *xas) { xas->xa_offset = get_offset(xas->xa_index, xas->xa_node); } /* move the index either forwards (find) or backwards (sibling slot) */ static void xas_move_index(struct xa_state *xas, unsigned long offset) { unsigned int shift = xas->xa_node->shift; xas->xa_index &= ~XA_CHUNK_MASK << shift; xas->xa_index += offset << shift; } static void xas_next_offset(struct xa_state *xas) { xas->xa_offset++; xas_move_index(xas, xas->xa_offset); } static void *set_bounds(struct xa_state *xas) { xas->xa_node = XAS_BOUNDS; return NULL; } /* * Starts a walk. If the @xas is already valid, we assume that it's on * the right path and just return where we've got to. If we're in an * error state, return NULL. If the index is outside the current scope * of the xarray, return NULL without changing @xas->xa_node. Otherwise * set @xas->xa_node to NULL and return the current head of the array. */ static void *xas_start(struct xa_state *xas) { void *entry; if (xas_valid(xas)) return xas_reload(xas); if (xas_error(xas)) return NULL; entry = xa_head(xas->xa); if (!xa_is_node(entry)) { if (xas->xa_index) return set_bounds(xas); } else { if ((xas->xa_index >> xa_to_node(entry)->shift) > XA_CHUNK_MASK) return set_bounds(xas); } xas->xa_node = NULL; return entry; } static __always_inline void *xas_descend(struct xa_state *xas, struct xa_node *node) { unsigned int offset = get_offset(xas->xa_index, node); void *entry = xa_entry(xas->xa, node, offset); xas->xa_node = node; while (xa_is_sibling(entry)) { offset = xa_to_sibling(entry); entry = xa_entry(xas->xa, node, offset); if (node->shift && xa_is_node(entry)) entry = XA_RETRY_ENTRY; } xas->xa_offset = offset; return entry; } /** * xas_load() - Load an entry from the XArray (advanced). * @xas: XArray operation state. * * Usually walks the @xas to the appropriate state to load the entry * stored at xa_index. However, it will do nothing and return %NULL if * @xas is in an error state. xas_load() will never expand the tree. * * If the xa_state is set up to operate on a multi-index entry, xas_load() * may return %NULL or an internal entry, even if there are entries * present within the range specified by @xas. * * Context: Any context. The caller should hold the xa_lock or the RCU lock. * Return: Usually an entry in the XArray, but see description for exceptions. */ void *xas_load(struct xa_state *xas) { void *entry = xas_start(xas); while (xa_is_node(entry)) { struct xa_node *node = xa_to_node(entry); if (xas->xa_shift > node->shift) break; entry = xas_descend(xas, node); if (node->shift == 0) break; } return entry; } EXPORT_SYMBOL_GPL(xas_load); #define XA_RCU_FREE ((struct xarray *)1) static void xa_node_free(struct xa_node *node) { XA_NODE_BUG_ON(node, !list_empty(&node->private_list)); node->array = XA_RCU_FREE; call_rcu(&node->rcu_head, radix_tree_node_rcu_free); } /* * xas_destroy() - Free any resources allocated during the XArray operation. * @xas: XArray operation state. * * Most users will not need to call this function; it is called for you * by xas_nomem(). */ void xas_destroy(struct xa_state *xas) { struct xa_node *next, *node = xas->xa_alloc; while (node) { XA_NODE_BUG_ON(node, !list_empty(&node->private_list)); next = rcu_dereference_raw(node->parent); radix_tree_node_rcu_free(&node->rcu_head); xas->xa_alloc = node = next; } } /** * xas_nomem() - Allocate memory if needed. * @xas: XArray operation state. * @gfp: Memory allocation flags. * * If we need to add new nodes to the XArray, we try to allocate memory * with GFP_NOWAIT while holding the lock, which will usually succeed. * If it fails, @xas is flagged as needing memory to continue. The caller * should drop the lock and call xas_nomem(). If xas_nomem() succeeds, * the caller should retry the operation. * * Forward progress is guaranteed as one node is allocated here and * stored in the xa_state where it will be found by xas_alloc(). More * nodes will likely be found in the slab allocator, but we do not tie * them up here. * * Return: true if memory was needed, and was successfully allocated. */ bool xas_nomem(struct xa_state *xas, gfp_t gfp) { if (xas->xa_node != XA_ERROR(-ENOMEM)) { xas_destroy(xas); return false; } if (xas->xa->xa_flags & XA_FLAGS_ACCOUNT) gfp |= __GFP_ACCOUNT; xas->xa_alloc = kmem_cache_alloc_lru(radix_tree_node_cachep, xas->xa_lru, gfp); if (!xas->xa_alloc) return false; xas->xa_alloc->parent = NULL; XA_NODE_BUG_ON(xas->xa_alloc, !list_empty(&xas->xa_alloc->private_list)); xas->xa_node = XAS_RESTART; return true; } EXPORT_SYMBOL_GPL(xas_nomem); /* * __xas_nomem() - Drop locks and allocate memory if needed. * @xas: XArray operation state. * @gfp: Memory allocation flags. * * Internal variant of xas_nomem(). * * Return: true if memory was needed, and was successfully allocated. */ static bool __xas_nomem(struct xa_state *xas, gfp_t gfp) __must_hold(xas->xa->xa_lock) { unsigned int lock_type = xa_lock_type(xas->xa); if (xas->xa_node != XA_ERROR(-ENOMEM)) { xas_destroy(xas); return false; } if (xas->xa->xa_flags & XA_FLAGS_ACCOUNT) gfp |= __GFP_ACCOUNT; if (gfpflags_allow_blocking(gfp)) { xas_unlock_type(xas, lock_type); xas->xa_alloc = kmem_cache_alloc_lru(radix_tree_node_cachep, xas->xa_lru, gfp); xas_lock_type(xas, lock_type); } else { xas->xa_alloc = kmem_cache_alloc_lru(radix_tree_node_cachep, xas->xa_lru, gfp); } if (!xas->xa_alloc) return false; xas->xa_alloc->parent = NULL; XA_NODE_BUG_ON(xas->xa_alloc, !list_empty(&xas->xa_alloc->private_list)); xas->xa_node = XAS_RESTART; return true; } static void xas_update(struct xa_state *xas, struct xa_node *node) { if (xas->xa_update) xas->xa_update(node); else XA_NODE_BUG_ON(node, !list_empty(&node->private_list)); } static void *xas_alloc(struct xa_state *xas, unsigned int shift) { struct xa_node *parent = xas->xa_node; struct xa_node *node = xas->xa_alloc; if (xas_invalid(xas)) return NULL; if (node) { xas->xa_alloc = NULL; } else { gfp_t gfp = GFP_NOWAIT | __GFP_NOWARN; if (xas->xa->xa_flags & XA_FLAGS_ACCOUNT) gfp |= __GFP_ACCOUNT; node = kmem_cache_alloc_lru(radix_tree_node_cachep, xas->xa_lru, gfp); if (!node) { xas_set_err(xas, -ENOMEM); return NULL; } } if (parent) { node->offset = xas->xa_offset; parent->count++; XA_NODE_BUG_ON(node, parent->count > XA_CHUNK_SIZE); xas_update(xas, parent); } XA_NODE_BUG_ON(node, shift > BITS_PER_LONG); XA_NODE_BUG_ON(node, !list_empty(&node->private_list)); node->shift = shift; node->count = 0; node->nr_values = 0; RCU_INIT_POINTER(node->parent, xas->xa_node); node->array = xas->xa; return node; } #ifdef CONFIG_XARRAY_MULTI /* Returns the number of indices covered by a given xa_state */ static unsigned long xas_size(const struct xa_state *xas) { return (xas->xa_sibs + 1UL) << xas->xa_shift; } #endif /* * Use this to calculate the maximum index that will need to be created * in order to add the entry described by @xas. Because we cannot store a * multi-index entry at index 0, the calculation is a little more complex * than you might expect. */ static unsigned long xas_max(struct xa_state *xas) { unsigned long max = xas->xa_index; #ifdef CONFIG_XARRAY_MULTI if (xas->xa_shift || xas->xa_sibs) { unsigned long mask = xas_size(xas) - 1; max |= mask; if (mask == max) max++; } #endif return max; } /* The maximum index that can be contained in the array without expanding it */ static unsigned long max_index(void *entry) { if (!xa_is_node(entry)) return 0; return (XA_CHUNK_SIZE << xa_to_node(entry)->shift) - 1; } static void xas_shrink(struct xa_state *xas) { struct xarray *xa = xas->xa; struct xa_node *node = xas->xa_node; for (;;) { void *entry; XA_NODE_BUG_ON(node, node->count > XA_CHUNK_SIZE); if (node->count != 1) break; entry = xa_entry_locked(xa, node, 0); if (!entry) break; if (!xa_is_node(entry) && node->shift) break; if (xa_is_zero(entry) && xa_zero_busy(xa)) entry = NULL; xas->xa_node = XAS_BOUNDS; RCU_INIT_POINTER(xa->xa_head, entry); if (xa_track_free(xa) && !node_get_mark(node, 0, XA_FREE_MARK)) xa_mark_clear(xa, XA_FREE_MARK); node->count = 0; node->nr_values = 0; if (!xa_is_node(entry)) RCU_INIT_POINTER(node->slots[0], XA_RETRY_ENTRY); xas_update(xas, node); xa_node_free(node); if (!xa_is_node(entry)) break; node = xa_to_node(entry); node->parent = NULL; } } /* * xas_delete_node() - Attempt to delete an xa_node * @xas: Array operation state. * * Attempts to delete the @xas->xa_node. This will fail if xa->node has * a non-zero reference count. */ static void xas_delete_node(struct xa_state *xas) { struct xa_node *node = xas->xa_node; for (;;) { struct xa_node *parent; XA_NODE_BUG_ON(node, node->count > XA_CHUNK_SIZE); if (node->count) break; parent = xa_parent_locked(xas->xa, node); xas->xa_node = parent; xas->xa_offset = node->offset; xa_node_free(node); if (!parent) { xas->xa->xa_head = NULL; xas->xa_node = XAS_BOUNDS; return; } parent->slots[xas->xa_offset] = NULL; parent->count--; XA_NODE_BUG_ON(parent, parent->count > XA_CHUNK_SIZE); node = parent; xas_update(xas, node); } if (!node->parent) xas_shrink(xas); } /** * xas_free_nodes() - Free this node and all nodes that it references * @xas: Array operation state. * @top: Node to free * * This node has been removed from the tree. We must now free it and all * of its subnodes. There may be RCU walkers with references into the tree, * so we must replace all entries with retry markers. */ static void xas_free_nodes(struct xa_state *xas, struct xa_node *top) { unsigned int offset = 0; struct xa_node *node = top; for (;;) { void *entry = xa_entry_locked(xas->xa, node, offset); if (node->shift && xa_is_node(entry)) { node = xa_to_node(entry); offset = 0; continue; } if (entry) RCU_INIT_POINTER(node->slots[offset], XA_RETRY_ENTRY); offset++; while (offset == XA_CHUNK_SIZE) { struct xa_node *parent; parent = xa_parent_locked(xas->xa, node); offset = node->offset + 1; node->count = 0; node->nr_values = 0; xas_update(xas, node); xa_node_free(node); if (node == top) return; node = parent; } } } /* * xas_expand adds nodes to the head of the tree until it has reached * sufficient height to be able to contain @xas->xa_index */ static int xas_expand(struct xa_state *xas, void *head) { struct xarray *xa = xas->xa; struct xa_node *node = NULL; unsigned int shift = 0; unsigned long max = xas_max(xas); if (!head) { if (max == 0) return 0; while ((max >> shift) >= XA_CHUNK_SIZE) shift += XA_CHUNK_SHIFT; return shift + XA_CHUNK_SHIFT; } else if (xa_is_node(head)) { node = xa_to_node(head); shift = node->shift + XA_CHUNK_SHIFT; } xas->xa_node = NULL; while (max > max_index(head)) { xa_mark_t mark = 0; XA_NODE_BUG_ON(node, shift > BITS_PER_LONG); node = xas_alloc(xas, shift); if (!node) return -ENOMEM; node->count = 1; if (xa_is_value(head)) node->nr_values = 1; RCU_INIT_POINTER(node->slots[0], head); /* Propagate the aggregated mark info to the new child */ for (;;) { if (xa_track_free(xa) && mark == XA_FREE_MARK) { node_mark_all(node, XA_FREE_MARK); if (!xa_marked(xa, XA_FREE_MARK)) { node_clear_mark(node, 0, XA_FREE_MARK); xa_mark_set(xa, XA_FREE_MARK); } } else if (xa_marked(xa, mark)) { node_set_mark(node, 0, mark); } if (mark == XA_MARK_MAX) break; mark_inc(mark); } /* * Now that the new node is fully initialised, we can add * it to the tree */ if (xa_is_node(head)) { xa_to_node(head)->offset = 0; rcu_assign_pointer(xa_to_node(head)->parent, node); } head = xa_mk_node(node); rcu_assign_pointer(xa->xa_head, head); xas_update(xas, node); shift += XA_CHUNK_SHIFT; } xas->xa_node = node; return shift; } /* * xas_create() - Create a slot to store an entry in. * @xas: XArray operation state. * @allow_root: %true if we can store the entry in the root directly * * Most users will not need to call this function directly, as it is called * by xas_store(). It is useful for doing conditional store operations * (see the xa_cmpxchg() implementation for an example). * * Return: If the slot already existed, returns the contents of this slot. * If the slot was newly created, returns %NULL. If it failed to create the * slot, returns %NULL and indicates the error in @xas. */ static void *xas_create(struct xa_state *xas, bool allow_root) { struct xarray *xa = xas->xa; void *entry; void __rcu **slot; struct xa_node *node = xas->xa_node; int shift; unsigned int order = xas->xa_shift; if (xas_top(node)) { entry = xa_head_locked(xa); xas->xa_node = NULL; if (!entry && xa_zero_busy(xa)) entry = XA_ZERO_ENTRY; shift = xas_expand(xas, entry); if (shift < 0) return NULL; if (!shift && !allow_root) shift = XA_CHUNK_SHIFT; entry = xa_head_locked(xa); slot = &xa->xa_head; } else if (xas_error(xas)) { return NULL; } else if (node) { unsigned int offset = xas->xa_offset; shift = node->shift; entry = xa_entry_locked(xa, node, offset); slot = &node->slots[offset]; } else { shift = 0; entry = xa_head_locked(xa); slot = &xa->xa_head; } while (shift > order) { shift -= XA_CHUNK_SHIFT; if (!entry) { node = xas_alloc(xas, shift); if (!node) break; if (xa_track_free(xa)) node_mark_all(node, XA_FREE_MARK); rcu_assign_pointer(*slot, xa_mk_node(node)); } else if (xa_is_node(entry)) { node = xa_to_node(entry); } else { break; } entry = xas_descend(xas, node); slot = &node->slots[xas->xa_offset]; } return entry; } /** * xas_create_range() - Ensure that stores to this range will succeed * @xas: XArray operation state. * * Creates all of the slots in the range covered by @xas. Sets @xas to * create single-index entries and positions it at the beginning of the * range. This is for the benefit of users which have not yet been * converted to use multi-index entries. */ void xas_create_range(struct xa_state *xas) { unsigned long index = xas->xa_index; unsigned char shift = xas->xa_shift; unsigned char sibs = xas->xa_sibs; xas->xa_index |= ((sibs + 1UL) << shift) - 1; if (xas_is_node(xas) && xas->xa_node->shift == xas->xa_shift) xas->xa_offset |= sibs; xas->xa_shift = 0; xas->xa_sibs = 0; for (;;) { xas_create(xas, true); if (xas_error(xas)) goto restore; if (xas->xa_index <= (index | XA_CHUNK_MASK)) goto success; xas->xa_index -= XA_CHUNK_SIZE; for (;;) { struct xa_node *node = xas->xa_node; if (node->shift >= shift) break; xas->xa_node = xa_parent_locked(xas->xa, node); xas->xa_offset = node->offset - 1; if (node->offset != 0) break; } } restore: xas->xa_shift = shift; xas->xa_sibs = sibs; xas->xa_index = index; return; success: xas->xa_index = index; if (xas->xa_node) xas_set_offset(xas); } EXPORT_SYMBOL_GPL(xas_create_range); static void update_node(struct xa_state *xas, struct xa_node *node, int count, int values) { if (!node || (!count && !values)) return; node->count += count; node->nr_values += values; XA_NODE_BUG_ON(node, node->count > XA_CHUNK_SIZE); XA_NODE_BUG_ON(node, node->nr_values > XA_CHUNK_SIZE); xas_update(xas, node); if (count < 0) xas_delete_node(xas); } /** * xas_store() - Store this entry in the XArray. * @xas: XArray operation state. * @entry: New entry. * * If @xas is operating on a multi-index entry, the entry returned by this * function is essentially meaningless (it may be an internal entry or it * may be %NULL, even if there are non-NULL entries at some of the indices * covered by the range). This is not a problem for any current users, * and can be changed if needed. * * Return: The old entry at this index. */ void *xas_store(struct xa_state *xas, void *entry) { struct xa_node *node; void __rcu **slot = &xas->xa->xa_head; unsigned int offset, max; int count = 0; int values = 0; void *first, *next; bool value = xa_is_value(entry); if (entry) { bool allow_root = !xa_is_node(entry) && !xa_is_zero(entry); first = xas_create(xas, allow_root); } else { first = xas_load(xas); } if (xas_invalid(xas)) return first; node = xas->xa_node; if (node && (xas->xa_shift < node->shift)) xas->xa_sibs = 0; if ((first == entry) && !xas->xa_sibs) return first; next = first; offset = xas->xa_offset; max = xas->xa_offset + xas->xa_sibs; if (node) { slot = &node->slots[offset]; if (xas->xa_sibs) xas_squash_marks(xas); } if (!entry) xas_init_marks(xas); for (;;) { /* * Must clear the marks before setting the entry to NULL, * otherwise xas_for_each_marked may find a NULL entry and * stop early. rcu_assign_pointer contains a release barrier * so the mark clearing will appear to happen before the * entry is set to NULL. */ rcu_assign_pointer(*slot, entry); if (xa_is_node(next) && (!node || node->shift)) xas_free_nodes(xas, xa_to_node(next)); if (!node) break; count += !next - !entry; values += !xa_is_value(first) - !value; if (entry) { if (offset == max) break; if (!xa_is_sibling(entry)) entry = xa_mk_sibling(xas->xa_offset); } else { if (offset == XA_CHUNK_MASK) break; } next = xa_entry_locked(xas->xa, node, ++offset); if (!xa_is_sibling(next)) { if (!entry && (offset > max)) break; first = next; } slot++; } update_node(xas, node, count, values); return first; } EXPORT_SYMBOL_GPL(xas_store); /** * xas_get_mark() - Returns the state of this mark. * @xas: XArray operation state. * @mark: Mark number. * * Return: true if the mark is set, false if the mark is clear or @xas * is in an error state. */ bool xas_get_mark(const struct xa_state *xas, xa_mark_t mark) { if (xas_invalid(xas)) return false; if (!xas->xa_node) return xa_marked(xas->xa, mark); return node_get_mark(xas->xa_node, xas->xa_offset, mark); } EXPORT_SYMBOL_GPL(xas_get_mark); /** * xas_set_mark() - Sets the mark on this entry and its parents. * @xas: XArray operation state. * @mark: Mark number. * * Sets the specified mark on this entry, and walks up the tree setting it * on all the ancestor entries. Does nothing if @xas has not been walked to * an entry, or is in an error state. */ void xas_set_mark(const struct xa_state *xas, xa_mark_t mark) { struct xa_node *node = xas->xa_node; unsigned int offset = xas->xa_offset; if (xas_invalid(xas)) return; while (node) { if (node_set_mark(node, offset, mark)) return; offset = node->offset; node = xa_parent_locked(xas->xa, node); } if (!xa_marked(xas->xa, mark)) xa_mark_set(xas->xa, mark); } EXPORT_SYMBOL_GPL(xas_set_mark); /** * xas_clear_mark() - Clears the mark on this entry and its parents. * @xas: XArray operation state. * @mark: Mark number. * * Clears the specified mark on this entry, and walks back to the head * attempting to clear it on all the ancestor entries. Does nothing if * @xas has not been walked to an entry, or is in an error state. */ void xas_clear_mark(const struct xa_state *xas, xa_mark_t mark) { struct xa_node *node = xas->xa_node; unsigned int offset = xas->xa_offset; if (xas_invalid(xas)) return; while (node) { if (!node_clear_mark(node, offset, mark)) return; if (node_any_mark(node, mark)) return; offset = node->offset; node = xa_parent_locked(xas->xa, node); } if (xa_marked(xas->xa, mark)) xa_mark_clear(xas->xa, mark); } EXPORT_SYMBOL_GPL(xas_clear_mark); /** * xas_init_marks() - Initialise all marks for the entry * @xas: Array operations state. * * Initialise all marks for the entry specified by @xas. If we're tracking * free entries with a mark, we need to set it on all entries. All other * marks are cleared. * * This implementation is not as efficient as it could be; we may walk * up the tree multiple times. */ void xas_init_marks(const struct xa_state *xas) { xa_mark_t mark = 0; for (;;) { if (xa_track_free(xas->xa) && mark == XA_FREE_MARK) xas_set_mark(xas, mark); else xas_clear_mark(xas, mark); if (mark == XA_MARK_MAX) break; mark_inc(mark); } } EXPORT_SYMBOL_GPL(xas_init_marks); #ifdef CONFIG_XARRAY_MULTI static unsigned int node_get_marks(struct xa_node *node, unsigned int offset) { unsigned int marks = 0; xa_mark_t mark = XA_MARK_0; for (;;) { if (node_get_mark(node, offset, mark)) marks |= 1 << (__force unsigned int)mark; if (mark == XA_MARK_MAX) break; mark_inc(mark); } return marks; } static inline void node_mark_slots(struct xa_node *node, unsigned int sibs, xa_mark_t mark) { int i; if (sibs == 0) node_mark_all(node, mark); else { for (i = 0; i < XA_CHUNK_SIZE; i += sibs + 1) node_set_mark(node, i, mark); } } static void node_set_marks(struct xa_node *node, unsigned int offset, struct xa_node *child, unsigned int sibs, unsigned int marks) { xa_mark_t mark = XA_MARK_0; for (;;) { if (marks & (1 << (__force unsigned int)mark)) { node_set_mark(node, offset, mark); if (child) node_mark_slots(child, sibs, mark); } if (mark == XA_MARK_MAX) break; mark_inc(mark); } } /** * xas_split_alloc() - Allocate memory for splitting an entry. * @xas: XArray operation state. * @entry: New entry which will be stored in the array. * @order: Current entry order. * @gfp: Memory allocation flags. * * This function should be called before calling xas_split(). * If necessary, it will allocate new nodes (and fill them with @entry) * to prepare for the upcoming split of an entry of @order size into * entries of the order stored in the @xas. * * Context: May sleep if @gfp flags permit. */ void xas_split_alloc(struct xa_state *xas, void *entry, unsigned int order, gfp_t gfp) { unsigned int sibs = (1 << (order % XA_CHUNK_SHIFT)) - 1; unsigned int mask = xas->xa_sibs; /* XXX: no support for splitting really large entries yet */ if (WARN_ON(xas->xa_shift + 2 * XA_CHUNK_SHIFT < order)) goto nomem; if (xas->xa_shift + XA_CHUNK_SHIFT > order) return; do { unsigned int i; void *sibling = NULL; struct xa_node *node; node = kmem_cache_alloc_lru(radix_tree_node_cachep, xas->xa_lru, gfp); if (!node) goto nomem; node->array = xas->xa; for (i = 0; i < XA_CHUNK_SIZE; i++) { if ((i & mask) == 0) { RCU_INIT_POINTER(node->slots[i], entry); sibling = xa_mk_sibling(i); } else { RCU_INIT_POINTER(node->slots[i], sibling); } } RCU_INIT_POINTER(node->parent, xas->xa_alloc); xas->xa_alloc = node; } while (sibs-- > 0); return; nomem: xas_destroy(xas); xas_set_err(xas, -ENOMEM); } EXPORT_SYMBOL_GPL(xas_split_alloc); /** * xas_split() - Split a multi-index entry into smaller entries. * @xas: XArray operation state. * @entry: New entry to store in the array. * @order: Current entry order. * * The size of the new entries is set in @xas. The value in @entry is * copied to all the replacement entries. * * Context: Any context. The caller should hold the xa_lock. */ void xas_split(struct xa_state *xas, void *entry, unsigned int order) { unsigned int sibs = (1 << (order % XA_CHUNK_SHIFT)) - 1; unsigned int offset, marks; struct xa_node *node; void *curr = xas_load(xas); int values = 0; node = xas->xa_node; if (xas_top(node)) return; marks = node_get_marks(node, xas->xa_offset); offset = xas->xa_offset + sibs; do { if (xas->xa_shift < node->shift) { struct xa_node *child = xas->xa_alloc; xas->xa_alloc = rcu_dereference_raw(child->parent); child->shift = node->shift - XA_CHUNK_SHIFT; child->offset = offset; child->count = XA_CHUNK_SIZE; child->nr_values = xa_is_value(entry) ? XA_CHUNK_SIZE : 0; RCU_INIT_POINTER(child->parent, node); node_set_marks(node, offset, child, xas->xa_sibs, marks); rcu_assign_pointer(node->slots[offset], xa_mk_node(child)); if (xa_is_value(curr)) values--; xas_update(xas, child); } else { unsigned int canon = offset - xas->xa_sibs; node_set_marks(node, canon, NULL, 0, marks); rcu_assign_pointer(node->slots[canon], entry); while (offset > canon) rcu_assign_pointer(node->slots[offset--], xa_mk_sibling(canon)); values += (xa_is_value(entry) - xa_is_value(curr)) * (xas->xa_sibs + 1); } } while (offset-- > xas->xa_offset); node->nr_values += values; xas_update(xas, node); } EXPORT_SYMBOL_GPL(xas_split); #endif /** * xas_pause() - Pause a walk to drop a lock. * @xas: XArray operation state. * * Some users need to pause a walk and drop the lock they're holding in * order to yield to a higher priority thread or carry out an operation * on an entry. Those users should call this function before they drop * the lock. It resets the @xas to be suitable for the next iteration * of the loop after the user has reacquired the lock. If most entries * found during a walk require you to call xas_pause(), the xa_for_each() * iterator may be more appropriate. * * Note that xas_pause() only works for forward iteration. If a user needs * to pause a reverse iteration, we will need a xas_pause_rev(). */ void xas_pause(struct xa_state *xas) { struct xa_node *node = xas->xa_node; if (xas_invalid(xas)) return; xas->xa_node = XAS_RESTART; if (node) { unsigned long offset = xas->xa_offset; while (++offset < XA_CHUNK_SIZE) { if (!xa_is_sibling(xa_entry(xas->xa, node, offset))) break; } xas->xa_index += (offset - xas->xa_offset) << node->shift; if (xas->xa_index == 0) xas->xa_node = XAS_BOUNDS; } else { xas->xa_index++; } } EXPORT_SYMBOL_GPL(xas_pause); /* * __xas_prev() - Find the previous entry in the XArray. * @xas: XArray operation state. * * Helper function for xas_prev() which handles all the complex cases * out of line. */ void *__xas_prev(struct xa_state *xas) { void *entry; if (!xas_frozen(xas->xa_node)) xas->xa_index--; if (!xas->xa_node) return set_bounds(xas); if (xas_not_node(xas->xa_node)) return xas_load(xas); if (xas->xa_offset != get_offset(xas->xa_index, xas->xa_node)) xas->xa_offset--; while (xas->xa_offset == 255) { xas->xa_offset = xas->xa_node->offset - 1; xas->xa_node = xa_parent(xas->xa, xas->xa_node); if (!xas->xa_node) return set_bounds(xas); } for (;;) { entry = xa_entry(xas->xa, xas->xa_node, xas->xa_offset); if (!xa_is_node(entry)) return entry; xas->xa_node = xa_to_node(entry); xas_set_offset(xas); } } EXPORT_SYMBOL_GPL(__xas_prev); /* * __xas_next() - Find the next entry in the XArray. * @xas: XArray operation state. * * Helper function for xas_next() which handles all the complex cases * out of line. */ void *__xas_next(struct xa_state *xas) { void *entry; if (!xas_frozen(xas->xa_node)) xas->xa_index++; if (!xas->xa_node) return set_bounds(xas); if (xas_not_node(xas->xa_node)) return xas_load(xas); if (xas->xa_offset != get_offset(xas->xa_index, xas->xa_node)) xas->xa_offset++; while (xas->xa_offset == XA_CHUNK_SIZE) { xas->xa_offset = xas->xa_node->offset + 1; xas->xa_node = xa_parent(xas->xa, xas->xa_node); if (!xas->xa_node) return set_bounds(xas); } for (;;) { entry = xa_entry(xas->xa, xas->xa_node, xas->xa_offset); if (!xa_is_node(entry)) return entry; xas->xa_node = xa_to_node(entry); xas_set_offset(xas); } } EXPORT_SYMBOL_GPL(__xas_next); /** * xas_find() - Find the next present entry in the XArray. * @xas: XArray operation state. * @max: Highest index to return. * * If the @xas has not yet been walked to an entry, return the entry * which has an index >= xas.xa_index. If it has been walked, the entry * currently being pointed at has been processed, and so we move to the * next entry. * * If no entry is found and the array is smaller than @max, the iterator * is set to the smallest index not yet in the array. This allows @xas * to be immediately passed to xas_store(). * * Return: The entry, if found, otherwise %NULL. */ void *xas_find(struct xa_state *xas, unsigned long max) { void *entry; if (xas_error(xas) || xas->xa_node == XAS_BOUNDS) return NULL; if (xas->xa_index > max) return set_bounds(xas); if (!xas->xa_node) { xas->xa_index = 1; return set_bounds(xas); } else if (xas->xa_node == XAS_RESTART) { entry = xas_load(xas); if (entry || xas_not_node(xas->xa_node)) return entry; } else if (!xas->xa_node->shift && xas->xa_offset != (xas->xa_index & XA_CHUNK_MASK)) { xas->xa_offset = ((xas->xa_index - 1) & XA_CHUNK_MASK) + 1; } xas_next_offset(xas); while (xas->xa_node && (xas->xa_index <= max)) { if (unlikely(xas->xa_offset == XA_CHUNK_SIZE)) { xas->xa_offset = xas->xa_node->offset + 1; xas->xa_node = xa_parent(xas->xa, xas->xa_node); continue; } entry = xa_entry(xas->xa, xas->xa_node, xas->xa_offset); if (xa_is_node(entry)) { xas->xa_node = xa_to_node(entry); xas->xa_offset = 0; continue; } if (entry && !xa_is_sibling(entry)) return entry; xas_next_offset(xas); } if (!xas->xa_node) xas->xa_node = XAS_BOUNDS; return NULL; } EXPORT_SYMBOL_GPL(xas_find); /** * xas_find_marked() - Find the next marked entry in the XArray. * @xas: XArray operation state. * @max: Highest index to return. * @mark: Mark number to search for. * * If the @xas has not yet been walked to an entry, return the marked entry * which has an index >= xas.xa_index. If it has been walked, the entry * currently being pointed at has been processed, and so we return the * first marked entry with an index > xas.xa_index. * * If no marked entry is found and the array is smaller than @max, @xas is * set to the bounds state and xas->xa_index is set to the smallest index * not yet in the array. This allows @xas to be immediately passed to * xas_store(). * * If no entry is found before @max is reached, @xas is set to the restart * state. * * Return: The entry, if found, otherwise %NULL. */ void *xas_find_marked(struct xa_state *xas, unsigned long max, xa_mark_t mark) { bool advance = true; unsigned int offset; void *entry; if (xas_error(xas)) return NULL; if (xas->xa_index > max) goto max; if (!xas->xa_node) { xas->xa_index = 1; goto out; } else if (xas_top(xas->xa_node)) { advance = false; entry = xa_head(xas->xa); xas->xa_node = NULL; if (xas->xa_index > max_index(entry)) goto out; if (!xa_is_node(entry)) { if (xa_marked(xas->xa, mark)) return entry; xas->xa_index = 1; goto out; } xas->xa_node = xa_to_node(entry); xas->xa_offset = xas->xa_index >> xas->xa_node->shift; } while (xas->xa_index <= max) { if (unlikely(xas->xa_offset == XA_CHUNK_SIZE)) { xas->xa_offset = xas->xa_node->offset + 1; xas->xa_node = xa_parent(xas->xa, xas->xa_node); if (!xas->xa_node) break; advance = false; continue; } if (!advance) { entry = xa_entry(xas->xa, xas->xa_node, xas->xa_offset); if (xa_is_sibling(entry)) { xas->xa_offset = xa_to_sibling(entry); xas_move_index(xas, xas->xa_offset); } } offset = xas_find_chunk(xas, advance, mark); if (offset > xas->xa_offset) { advance = false; xas_move_index(xas, offset); /* Mind the wrap */ if ((xas->xa_index - 1) >= max) goto max; xas->xa_offset = offset; if (offset == XA_CHUNK_SIZE) continue; } entry = xa_entry(xas->xa, xas->xa_node, xas->xa_offset); if (!entry && !(xa_track_free(xas->xa) && mark == XA_FREE_MARK)) continue; if (!xa_is_node(entry)) return entry; xas->xa_node = xa_to_node(entry); xas_set_offset(xas); } out: if (xas->xa_index > max) goto max; return set_bounds(xas); max: xas->xa_node = XAS_RESTART; return NULL; } EXPORT_SYMBOL_GPL(xas_find_marked); /** * xas_find_conflict() - Find the next present entry in a range. * @xas: XArray operation state. * * The @xas describes both a range and a position within that range. * * Context: Any context. Expects xa_lock to be held. * Return: The next entry in the range covered by @xas or %NULL. */ void *xas_find_conflict(struct xa_state *xas) { void *curr; if (xas_error(xas)) return NULL; if (!xas->xa_node) return NULL; if (xas_top(xas->xa_node)) { curr = xas_start(xas); if (!curr) return NULL; while (xa_is_node(curr)) { struct xa_node *node = xa_to_node(curr); curr = xas_descend(xas, node); } if (curr) return curr; } if (xas->xa_node->shift > xas->xa_shift) return NULL; for (;;) { if (xas->xa_node->shift == xas->xa_shift) { if ((xas->xa_offset & xas->xa_sibs) == xas->xa_sibs) break; } else if (xas->xa_offset == XA_CHUNK_MASK) { xas->xa_offset = xas->xa_node->offset; xas->xa_node = xa_parent_locked(xas->xa, xas->xa_node); if (!xas->xa_node) break; continue; } curr = xa_entry_locked(xas->xa, xas->xa_node, ++xas->xa_offset); if (xa_is_sibling(curr)) continue; while (xa_is_node(curr)) { xas->xa_node = xa_to_node(curr); xas->xa_offset = 0; curr = xa_entry_locked(xas->xa, xas->xa_node, 0); } if (curr) return curr; } xas->xa_offset -= xas->xa_sibs; return NULL; } EXPORT_SYMBOL_GPL(xas_find_conflict); /** * xa_load() - Load an entry from an XArray. * @xa: XArray. * @index: index into array. * * Context: Any context. Takes and releases the RCU lock. * Return: The entry at @index in @xa. */ void *xa_load(struct xarray *xa, unsigned long index) { XA_STATE(xas, xa, index); void *entry; rcu_read_lock(); do { entry = xas_load(&xas); if (xa_is_zero(entry)) entry = NULL; } while (xas_retry(&xas, entry)); rcu_read_unlock(); return entry; } EXPORT_SYMBOL(xa_load); static void *xas_result(struct xa_state *xas, void *curr) { if (xa_is_zero(curr)) return NULL; if (xas_error(xas)) curr = xas->xa_node; return curr; } /** * __xa_erase() - Erase this entry from the XArray while locked. * @xa: XArray. * @index: Index into array. * * After this function returns, loading from @index will return %NULL. * If the index is part of a multi-index entry, all indices will be erased * and none of the entries will be part of a multi-index entry. * * Context: Any context. Expects xa_lock to be held on entry. * Return: The entry which used to be at this index. */ void *__xa_erase(struct xarray *xa, unsigned long index) { XA_STATE(xas, xa, index); return xas_result(&xas, xas_store(&xas, NULL)); } EXPORT_SYMBOL(__xa_erase); /** * xa_erase() - Erase this entry from the XArray. * @xa: XArray. * @index: Index of entry. * * After this function returns, loading from @index will return %NULL. * If the index is part of a multi-index entry, all indices will be erased * and none of the entries will be part of a multi-index entry. * * Context: Any context. Takes and releases the xa_lock. * Return: The entry which used to be at this index. */ void *xa_erase(struct xarray *xa, unsigned long index) { void *entry; xa_lock(xa); entry = __xa_erase(xa, index); xa_unlock(xa); return entry; } EXPORT_SYMBOL(xa_erase); /** * __xa_store() - Store this entry in the XArray. * @xa: XArray. * @index: Index into array. * @entry: New entry. * @gfp: Memory allocation flags. * * You must already be holding the xa_lock when calling this function. * It will drop the lock if needed to allocate memory, and then reacquire * it afterwards. * * Context: Any context. Expects xa_lock to be held on entry. May * release and reacquire xa_lock if @gfp flags permit. * Return: The old entry at this index or xa_err() if an error happened. */ void *__xa_store(struct xarray *xa, unsigned long index, void *entry, gfp_t gfp) { XA_STATE(xas, xa, index); void *curr; if (WARN_ON_ONCE(xa_is_advanced(entry))) return XA_ERROR(-EINVAL); if (xa_track_free(xa) && !entry) entry = XA_ZERO_ENTRY; do { curr = xas_store(&xas, entry); if (xa_track_free(xa)) xas_clear_mark(&xas, XA_FREE_MARK); } while (__xas_nomem(&xas, gfp)); return xas_result(&xas, curr); } EXPORT_SYMBOL(__xa_store); /** * xa_store() - Store this entry in the XArray. * @xa: XArray. * @index: Index into array. * @entry: New entry. * @gfp: Memory allocation flags. * * After this function returns, loads from this index will return @entry. * Storing into an existing multi-index entry updates the entry of every index. * The marks associated with @index are unaffected unless @entry is %NULL. * * Context: Any context. Takes and releases the xa_lock. * May sleep if the @gfp flags permit. * Return: The old entry at this index on success, xa_err(-EINVAL) if @entry * cannot be stored in an XArray, or xa_err(-ENOMEM) if memory allocation * failed. */ void *xa_store(struct xarray *xa, unsigned long index, void *entry, gfp_t gfp) { void *curr; xa_lock(xa); curr = __xa_store(xa, index, entry, gfp); xa_unlock(xa); return curr; } EXPORT_SYMBOL(xa_store); /** * __xa_cmpxchg() - Store this entry in the XArray. * @xa: XArray. * @index: Index into array. * @old: Old value to test against. * @entry: New entry. * @gfp: Memory allocation flags. * * You must already be holding the xa_lock when calling this function. * It will drop the lock if needed to allocate memory, and then reacquire * it afterwards. * * Context: Any context. Expects xa_lock to be held on entry. May * release and reacquire xa_lock if @gfp flags permit. * Return: The old entry at this index or xa_err() if an error happened. */ void *__xa_cmpxchg(struct xarray *xa, unsigned long index, void *old, void *entry, gfp_t gfp) { XA_STATE(xas, xa, index); void *curr; if (WARN_ON_ONCE(xa_is_advanced(entry))) return XA_ERROR(-EINVAL); do { curr = xas_load(&xas); if (curr == old) { xas_store(&xas, entry); if (xa_track_free(xa) && entry && !curr) xas_clear_mark(&xas, XA_FREE_MARK); } } while (__xas_nomem(&xas, gfp)); return xas_result(&xas, curr); } EXPORT_SYMBOL(__xa_cmpxchg); /** * __xa_insert() - Store this entry in the XArray if no entry is present. * @xa: XArray. * @index: Index into array. * @entry: New entry. * @gfp: Memory allocation flags. * * Inserting a NULL entry will store a reserved entry (like xa_reserve()) * if no entry is present. Inserting will fail if a reserved entry is * present, even though loading from this index will return NULL. * * Context: Any context. Expects xa_lock to be held on entry. May * release and reacquire xa_lock if @gfp flags permit. * Return: 0 if the store succeeded. -EBUSY if another entry was present. * -ENOMEM if memory could not be allocated. */ int __xa_insert(struct xarray *xa, unsigned long index, void *entry, gfp_t gfp) { XA_STATE(xas, xa, index); void *curr; if (WARN_ON_ONCE(xa_is_advanced(entry))) return -EINVAL; if (!entry) entry = XA_ZERO_ENTRY; do { curr = xas_load(&xas); if (!curr) { xas_store(&xas, entry); if (xa_track_free(xa)) xas_clear_mark(&xas, XA_FREE_MARK); } else { xas_set_err(&xas, -EBUSY); } } while (__xas_nomem(&xas, gfp)); return xas_error(&xas); } EXPORT_SYMBOL(__xa_insert); #ifdef CONFIG_XARRAY_MULTI static void xas_set_range(struct xa_state *xas, unsigned long first, unsigned long last) { unsigned int shift = 0; unsigned long sibs = last - first; unsigned int offset = XA_CHUNK_MASK; xas_set(xas, first); while ((first & XA_CHUNK_MASK) == 0) { if (sibs < XA_CHUNK_MASK) break; if ((sibs == XA_CHUNK_MASK) && (offset < XA_CHUNK_MASK)) break; shift += XA_CHUNK_SHIFT; if (offset == XA_CHUNK_MASK) offset = sibs & XA_CHUNK_MASK; sibs >>= XA_CHUNK_SHIFT; first >>= XA_CHUNK_SHIFT; } offset = first & XA_CHUNK_MASK; if (offset + sibs > XA_CHUNK_MASK) sibs = XA_CHUNK_MASK - offset; if ((((first + sibs + 1) << shift) - 1) > last) sibs -= 1; xas->xa_shift = shift; xas->xa_sibs = sibs; } /** * xa_store_range() - Store this entry at a range of indices in the XArray. * @xa: XArray. * @first: First index to affect. * @last: Last index to affect. * @entry: New entry. * @gfp: Memory allocation flags. * * After this function returns, loads from any index between @first and @last, * inclusive will return @entry. * Storing into an existing multi-index entry updates the entry of every index. * The marks associated with @index are unaffected unless @entry is %NULL. * * Context: Process context. Takes and releases the xa_lock. May sleep * if the @gfp flags permit. * Return: %NULL on success, xa_err(-EINVAL) if @entry cannot be stored in * an XArray, or xa_err(-ENOMEM) if memory allocation failed. */ void *xa_store_range(struct xarray *xa, unsigned long first, unsigned long last, void *entry, gfp_t gfp) { XA_STATE(xas, xa, 0); if (WARN_ON_ONCE(xa_is_internal(entry))) return XA_ERROR(-EINVAL); if (last < first) return XA_ERROR(-EINVAL); do { xas_lock(&xas); if (entry) { unsigned int order = BITS_PER_LONG; if (last + 1) order = __ffs(last + 1); xas_set_order(&xas, last, order); xas_create(&xas, true); if (xas_error(&xas)) goto unlock; } do { xas_set_range(&xas, first, last); xas_store(&xas, entry); if (xas_error(&xas)) goto unlock; first += xas_size(&xas); } while (first <= last); unlock: xas_unlock(&xas); } while (xas_nomem(&xas, gfp)); return xas_result(&xas, NULL); } EXPORT_SYMBOL(xa_store_range); /** * xas_get_order() - Get the order of an entry. * @xas: XArray operation state. * * Called after xas_load, the xas should not be in an error state. * * Return: A number between 0 and 63 indicating the order of the entry. */ int xas_get_order(struct xa_state *xas) { int order = 0; if (!xas->xa_node) return 0; for (;;) { unsigned int slot = xas->xa_offset + (1 << order); if (slot >= XA_CHUNK_SIZE) break; if (!xa_is_sibling(xa_entry(xas->xa, xas->xa_node, slot))) break; order++; } order += xas->xa_node->shift; return order; } EXPORT_SYMBOL_GPL(xas_get_order); /** * xa_get_order() - Get the order of an entry. * @xa: XArray. * @index: Index of the entry. * * Return: A number between 0 and 63 indicating the order of the entry. */ int xa_get_order(struct xarray *xa, unsigned long index) { XA_STATE(xas, xa, index); int order = 0; void *entry; rcu_read_lock(); entry = xas_load(&xas); if (entry) order = xas_get_order(&xas); rcu_read_unlock(); return order; } EXPORT_SYMBOL(xa_get_order); #endif /* CONFIG_XARRAY_MULTI */ /** * __xa_alloc() - Find somewhere to store this entry in the XArray. * @xa: XArray. * @id: Pointer to ID. * @limit: Range for allocated ID. * @entry: New entry. * @gfp: Memory allocation flags. * * Finds an empty entry in @xa between @limit.min and @limit.max, * stores the index into the @id pointer, then stores the entry at * that index. A concurrent lookup will not see an uninitialised @id. * * Must only be operated on an xarray initialized with flag XA_FLAGS_ALLOC set * in xa_init_flags(). * * Context: Any context. Expects xa_lock to be held on entry. May * release and reacquire xa_lock if @gfp flags permit. * Return: 0 on success, -ENOMEM if memory could not be allocated or * -EBUSY if there are no free entries in @limit. */ int __xa_alloc(struct xarray *xa, u32 *id, void *entry, struct xa_limit limit, gfp_t gfp) { XA_STATE(xas, xa, 0); if (WARN_ON_ONCE(xa_is_advanced(entry))) return -EINVAL; if (WARN_ON_ONCE(!xa_track_free(xa))) return -EINVAL; if (!entry) entry = XA_ZERO_ENTRY; do { xas.xa_index = limit.min; xas_find_marked(&xas, limit.max, XA_FREE_MARK); if (xas.xa_node == XAS_RESTART) xas_set_err(&xas, -EBUSY); else *id = xas.xa_index; xas_store(&xas, entry); xas_clear_mark(&xas, XA_FREE_MARK); } while (__xas_nomem(&xas, gfp)); return xas_error(&xas); } EXPORT_SYMBOL(__xa_alloc); /** * __xa_alloc_cyclic() - Find somewhere to store this entry in the XArray. * @xa: XArray. * @id: Pointer to ID. * @entry: New entry. * @limit: Range of allocated ID. * @next: Pointer to next ID to allocate. * @gfp: Memory allocation flags. * * Finds an empty entry in @xa between @limit.min and @limit.max, * stores the index into the @id pointer, then stores the entry at * that index. A concurrent lookup will not see an uninitialised @id. * The search for an empty entry will start at @next and will wrap * around if necessary. * * Must only be operated on an xarray initialized with flag XA_FLAGS_ALLOC set * in xa_init_flags(). * * Context: Any context. Expects xa_lock to be held on entry. May * release and reacquire xa_lock if @gfp flags permit. * Return: 0 if the allocation succeeded without wrapping. 1 if the * allocation succeeded after wrapping, -ENOMEM if memory could not be * allocated or -EBUSY if there are no free entries in @limit. */ int __xa_alloc_cyclic(struct xarray *xa, u32 *id, void *entry, struct xa_limit limit, u32 *next, gfp_t gfp) { u32 min = limit.min; int ret; limit.min = max(min, *next); ret = __xa_alloc(xa, id, entry, limit, gfp); if ((xa->xa_flags & XA_FLAGS_ALLOC_WRAPPED) && ret == 0) { xa->xa_flags &= ~XA_FLAGS_ALLOC_WRAPPED; ret = 1; } if (ret < 0 && limit.min > min) { limit.min = min; ret = __xa_alloc(xa, id, entry, limit, gfp); if (ret == 0) ret = 1; } if (ret >= 0) { *next = *id + 1; if (*next == 0) xa->xa_flags |= XA_FLAGS_ALLOC_WRAPPED; } return ret; } EXPORT_SYMBOL(__xa_alloc_cyclic); /** * __xa_set_mark() - Set this mark on this entry while locked. * @xa: XArray. * @index: Index of entry. * @mark: Mark number. * * Attempting to set a mark on a %NULL entry does not succeed. * * Context: Any context. Expects xa_lock to be held on entry. */ void __xa_set_mark(struct xarray *xa, unsigned long index, xa_mark_t mark) { XA_STATE(xas, xa, index); void *entry = xas_load(&xas); if (entry) xas_set_mark(&xas, mark); } EXPORT_SYMBOL(__xa_set_mark); /** * __xa_clear_mark() - Clear this mark on this entry while locked. * @xa: XArray. * @index: Index of entry. * @mark: Mark number. * * Context: Any context. Expects xa_lock to be held on entry. */ void __xa_clear_mark(struct xarray *xa, unsigned long index, xa_mark_t mark) { XA_STATE(xas, xa, index); void *entry = xas_load(&xas); if (entry) xas_clear_mark(&xas, mark); } EXPORT_SYMBOL(__xa_clear_mark); /** * xa_get_mark() - Inquire whether this mark is set on this entry. * @xa: XArray. * @index: Index of entry. * @mark: Mark number. * * This function uses the RCU read lock, so the result may be out of date * by the time it returns. If you need the result to be stable, use a lock. * * Context: Any context. Takes and releases the RCU lock. * Return: True if the entry at @index has this mark set, false if it doesn't. */ bool xa_get_mark(struct xarray *xa, unsigned long index, xa_mark_t mark) { XA_STATE(xas, xa, index); void *entry; rcu_read_lock(); entry = xas_start(&xas); while (xas_get_mark(&xas, mark)) { if (!xa_is_node(entry)) goto found; entry = xas_descend(&xas, xa_to_node(entry)); } rcu_read_unlock(); return false; found: rcu_read_unlock(); return true; } EXPORT_SYMBOL(xa_get_mark); /** * xa_set_mark() - Set this mark on this entry. * @xa: XArray. * @index: Index of entry. * @mark: Mark number. * * Attempting to set a mark on a %NULL entry does not succeed. * * Context: Process context. Takes and releases the xa_lock. */ void xa_set_mark(struct xarray *xa, unsigned long index, xa_mark_t mark) { xa_lock(xa); __xa_set_mark(xa, index, mark); xa_unlock(xa); } EXPORT_SYMBOL(xa_set_mark); /** * xa_clear_mark() - Clear this mark on this entry. * @xa: XArray. * @index: Index of entry. * @mark: Mark number. * * Clearing a mark always succeeds. * * Context: Process context. Takes and releases the xa_lock. */ void xa_clear_mark(struct xarray *xa, unsigned long index, xa_mark_t mark) { xa_lock(xa); __xa_clear_mark(xa, index, mark); xa_unlock(xa); } EXPORT_SYMBOL(xa_clear_mark); /** * xa_find() - Search the XArray for an entry. * @xa: XArray. * @indexp: Pointer to an index. * @max: Maximum index to search to. * @filter: Selection criterion. * * Finds the entry in @xa which matches the @filter, and has the lowest * index that is at least @indexp and no more than @max. * If an entry is found, @indexp is updated to be the index of the entry. * This function is protected by the RCU read lock, so it may not find * entries which are being simultaneously added. It will not return an * %XA_RETRY_ENTRY; if you need to see retry entries, use xas_find(). * * Context: Any context. Takes and releases the RCU lock. * Return: The entry, if found, otherwise %NULL. */ void *xa_find(struct xarray *xa, unsigned long *indexp, unsigned long max, xa_mark_t filter) { XA_STATE(xas, xa, *indexp); void *entry; rcu_read_lock(); do { if ((__force unsigned int)filter < XA_MAX_MARKS) entry = xas_find_marked(&xas, max, filter); else entry = xas_find(&xas, max); } while (xas_retry(&xas, entry)); rcu_read_unlock(); if (entry) *indexp = xas.xa_index; return entry; } EXPORT_SYMBOL(xa_find); static bool xas_sibling(struct xa_state *xas) { struct xa_node *node = xas->xa_node; unsigned long mask; if (!IS_ENABLED(CONFIG_XARRAY_MULTI) || !node) return false; mask = (XA_CHUNK_SIZE << node->shift) - 1; return (xas->xa_index & mask) > ((unsigned long)xas->xa_offset << node->shift); } /** * xa_find_after() - Search the XArray for a present entry. * @xa: XArray. * @indexp: Pointer to an index. * @max: Maximum index to search to. * @filter: Selection criterion. * * Finds the entry in @xa which matches the @filter and has the lowest * index that is above @indexp and no more than @max. * If an entry is found, @indexp is updated to be the index of the entry. * This function is protected by the RCU read lock, so it may miss entries * which are being simultaneously added. It will not return an * %XA_RETRY_ENTRY; if you need to see retry entries, use xas_find(). * * Context: Any context. Takes and releases the RCU lock. * Return: The pointer, if found, otherwise %NULL. */ void *xa_find_after(struct xarray *xa, unsigned long *indexp, unsigned long max, xa_mark_t filter) { XA_STATE(xas, xa, *indexp + 1); void *entry; if (xas.xa_index == 0) return NULL; rcu_read_lock(); for (;;) { if ((__force unsigned int)filter < XA_MAX_MARKS) entry = xas_find_marked(&xas, max, filter); else entry = xas_find(&xas, max); if (xas_invalid(&xas)) break; if (xas_sibling(&xas)) continue; if (!xas_retry(&xas, entry)) break; } rcu_read_unlock(); if (entry) *indexp = xas.xa_index; return entry; } EXPORT_SYMBOL(xa_find_after); static unsigned int xas_extract_present(struct xa_state *xas, void **dst, unsigned long max, unsigned int n) { void *entry; unsigned int i = 0; rcu_read_lock(); xas_for_each(xas, entry, max) { if (xas_retry(xas, entry)) continue; dst[i++] = entry; if (i == n) break; } rcu_read_unlock(); return i; } static unsigned int xas_extract_marked(struct xa_state *xas, void **dst, unsigned long max, unsigned int n, xa_mark_t mark) { void *entry; unsigned int i = 0; rcu_read_lock(); xas_for_each_marked(xas, entry, max, mark) { if (xas_retry(xas, entry)) continue; dst[i++] = entry; if (i == n) break; } rcu_read_unlock(); return i; } /** * xa_extract() - Copy selected entries from the XArray into a normal array. * @xa: The source XArray to copy from. * @dst: The buffer to copy entries into. * @start: The first index in the XArray eligible to be selected. * @max: The last index in the XArray eligible to be selected. * @n: The maximum number of entries to copy. * @filter: Selection criterion. * * Copies up to @n entries that match @filter from the XArray. The * copied entries will have indices between @start and @max, inclusive. * * The @filter may be an XArray mark value, in which case entries which are * marked with that mark will be copied. It may also be %XA_PRESENT, in * which case all entries which are not %NULL will be copied. * * The entries returned may not represent a snapshot of the XArray at a * moment in time. For example, if another thread stores to index 5, then * index 10, calling xa_extract() may return the old contents of index 5 * and the new contents of index 10. Indices not modified while this * function is running will not be skipped. * * If you need stronger guarantees, holding the xa_lock across calls to this * function will prevent concurrent modification. * * Context: Any context. Takes and releases the RCU lock. * Return: The number of entries copied. */ unsigned int xa_extract(struct xarray *xa, void **dst, unsigned long start, unsigned long max, unsigned int n, xa_mark_t filter) { XA_STATE(xas, xa, start); if (!n) return 0; if ((__force unsigned int)filter < XA_MAX_MARKS) return xas_extract_marked(&xas, dst, max, n, filter); return xas_extract_present(&xas, dst, max, n); } EXPORT_SYMBOL(xa_extract); /** * xa_delete_node() - Private interface for workingset code. * @node: Node to be removed from the tree. * @update: Function to call to update ancestor nodes. * * Context: xa_lock must be held on entry and will not be released. */ void xa_delete_node(struct xa_node *node, xa_update_node_t update) { struct xa_state xas = { .xa = node->array, .xa_index = (unsigned long)node->offset << (node->shift + XA_CHUNK_SHIFT), .xa_shift = node->shift + XA_CHUNK_SHIFT, .xa_offset = node->offset, .xa_node = xa_parent_locked(node->array, node), .xa_update = update, }; xas_store(&xas, NULL); } EXPORT_SYMBOL_GPL(xa_delete_node); /* For the benefit of the test suite */ /** * xa_destroy() - Free all internal data structures. * @xa: XArray. * * After calling this function, the XArray is empty and has freed all memory * allocated for its internal data structures. You are responsible for * freeing the objects referenced by the XArray. * * Context: Any context. Takes and releases the xa_lock, interrupt-safe. */ void xa_destroy(struct xarray *xa) { XA_STATE(xas, xa, 0); unsigned long flags; void *entry; xas.xa_node = NULL; xas_lock_irqsave(&xas, flags); entry = xa_head_locked(xa); RCU_INIT_POINTER(xa->xa_head, NULL); xas_init_marks(&xas); if (xa_zero_busy(xa)) xa_mark_clear(xa, XA_FREE_MARK); /* lockdep checks we're still holding the lock in xas_free_nodes() */ if (xa_is_node(entry)) xas_free_nodes(&xas, xa_to_node(entry)); xas_unlock_irqrestore(&xas, flags); } EXPORT_SYMBOL(xa_destroy); #ifdef XA_DEBUG void xa_dump_node(const struct xa_node *node) { unsigned i, j; if (!node) return; if ((unsigned long)node & 3) { pr_cont("node %px\n", node); return; } pr_cont("node %px %s %d parent %px shift %d count %d values %d " "array %px list %px %px marks", node, node->parent ? "offset" : "max", node->offset, node->parent, node->shift, node->count, node->nr_values, node->array, node->private_list.prev, node->private_list.next); for (i = 0; i < XA_MAX_MARKS; i++) for (j = 0; j < XA_MARK_LONGS; j++) pr_cont(" %lx", node->marks[i][j]); pr_cont("\n"); } void xa_dump_index(unsigned long index, unsigned int shift) { if (!shift) pr_info("%lu: ", index); else if (shift >= BITS_PER_LONG) pr_info("0-%lu: ", ~0UL); else pr_info("%lu-%lu: ", index, index | ((1UL << shift) - 1)); } void xa_dump_entry(const void *entry, unsigned long index, unsigned long shift) { if (!entry) return; xa_dump_index(index, shift); if (xa_is_node(entry)) { if (shift == 0) { pr_cont("%px\n", entry); } else { unsigned long i; struct xa_node *node = xa_to_node(entry); xa_dump_node(node); for (i = 0; i < XA_CHUNK_SIZE; i++) xa_dump_entry(node->slots[i], index + (i << node->shift), node->shift); } } else if (xa_is_value(entry)) pr_cont("value %ld (0x%lx) [%px]\n", xa_to_value(entry), xa_to_value(entry), entry); else if (!xa_is_internal(entry)) pr_cont("%px\n", entry); else if (xa_is_retry(entry)) pr_cont("retry (%ld)\n", xa_to_internal(entry)); else if (xa_is_sibling(entry)) pr_cont("sibling (slot %ld)\n", xa_to_sibling(entry)); else if (xa_is_zero(entry)) pr_cont("zero (%ld)\n", xa_to_internal(entry)); else pr_cont("UNKNOWN ENTRY (%px)\n", entry); } void xa_dump(const struct xarray *xa) { void *entry = xa->xa_head; unsigned int shift = 0; pr_info("xarray: %px head %px flags %x marks %d %d %d\n", xa, entry, xa->xa_flags, xa_marked(xa, XA_MARK_0), xa_marked(xa, XA_MARK_1), xa_marked(xa, XA_MARK_2)); if (xa_is_node(entry)) shift = xa_to_node(entry)->shift + XA_CHUNK_SHIFT; xa_dump_entry(entry, 0, shift); } #endif |
| 3 3 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 | // SPDX-License-Identifier: GPL-2.0-only #include <linux/kernel.h> #include <linux/module.h> #include <linux/init.h> #include <linux/netlink.h> #include <linux/netfilter.h> #include <linux/workqueue.h> #include <linux/spinlock.h> #include <linux/netfilter/nf_conntrack_common.h> #include <linux/netfilter/nf_tables.h> #include <net/ip.h> #include <net/inet_dscp.h> #include <net/netfilter/nf_tables.h> #include <net/netfilter/nf_tables_core.h> #include <net/netfilter/nf_conntrack_core.h> #include <net/netfilter/nf_conntrack_extend.h> #include <net/netfilter/nf_flow_table.h> struct nft_flow_offload { struct nft_flowtable *flowtable; }; static enum flow_offload_xmit_type nft_xmit_type(struct dst_entry *dst) { if (dst_xfrm(dst)) return FLOW_OFFLOAD_XMIT_XFRM; return FLOW_OFFLOAD_XMIT_NEIGH; } static void nft_default_forward_path(struct nf_flow_route *route, struct dst_entry *dst_cache, enum ip_conntrack_dir dir) { route->tuple[!dir].in.ifindex = dst_cache->dev->ifindex; route->tuple[dir].dst = dst_cache; route->tuple[dir].xmit_type = nft_xmit_type(dst_cache); } static bool nft_is_valid_ether_device(const struct net_device *dev) { if (!dev || (dev->flags & IFF_LOOPBACK) || dev->type != ARPHRD_ETHER || dev->addr_len != ETH_ALEN || !is_valid_ether_addr(dev->dev_addr)) return false; return true; } static int nft_dev_fill_forward_path(const struct nf_flow_route *route, const struct dst_entry *dst_cache, const struct nf_conn *ct, enum ip_conntrack_dir dir, u8 *ha, struct net_device_path_stack *stack) { const void *daddr = &ct->tuplehash[!dir].tuple.src.u3; struct net_device *dev = dst_cache->dev; struct neighbour *n; u8 nud_state; if (!nft_is_valid_ether_device(dev)) goto out; n = dst_neigh_lookup(dst_cache, daddr); if (!n) return -1; read_lock_bh(&n->lock); nud_state = n->nud_state; ether_addr_copy(ha, n->ha); read_unlock_bh(&n->lock); neigh_release(n); if (!(nud_state & NUD_VALID)) return -1; out: return dev_fill_forward_path(dev, ha, stack); } struct nft_forward_info { const struct net_device *indev; const struct net_device *outdev; const struct net_device *hw_outdev; struct id { __u16 id; __be16 proto; } encap[NF_FLOW_TABLE_ENCAP_MAX]; u8 num_encaps; u8 ingress_vlans; u8 h_source[ETH_ALEN]; u8 h_dest[ETH_ALEN]; enum flow_offload_xmit_type xmit_type; }; static void nft_dev_path_info(const struct net_device_path_stack *stack, struct nft_forward_info *info, unsigned char *ha, struct nf_flowtable *flowtable) { const struct net_device_path *path; int i; memcpy(info->h_dest, ha, ETH_ALEN); for (i = 0; i < stack->num_paths; i++) { path = &stack->path[i]; switch (path->type) { case DEV_PATH_ETHERNET: case DEV_PATH_DSA: case DEV_PATH_VLAN: case DEV_PATH_PPPOE: info->indev = path->dev; if (is_zero_ether_addr(info->h_source)) memcpy(info->h_source, path->dev->dev_addr, ETH_ALEN); if (path->type == DEV_PATH_ETHERNET) break; if (path->type == DEV_PATH_DSA) { i = stack->num_paths; break; } /* DEV_PATH_VLAN and DEV_PATH_PPPOE */ if (info->num_encaps >= NF_FLOW_TABLE_ENCAP_MAX) { info->indev = NULL; break; } if (!info->outdev) info->outdev = path->dev; info->encap[info->num_encaps].id = path->encap.id; info->encap[info->num_encaps].proto = path->encap.proto; info->num_encaps++; if (path->type == DEV_PATH_PPPOE) memcpy(info->h_dest, path->encap.h_dest, ETH_ALEN); break; case DEV_PATH_BRIDGE: if (is_zero_ether_addr(info->h_source)) memcpy(info->h_source, path->dev->dev_addr, ETH_ALEN); switch (path->bridge.vlan_mode) { case DEV_PATH_BR_VLAN_UNTAG_HW: info->ingress_vlans |= BIT(info->num_encaps - 1); break; case DEV_PATH_BR_VLAN_TAG: info->encap[info->num_encaps].id = path->bridge.vlan_id; info->encap[info->num_encaps].proto = path->bridge.vlan_proto; info->num_encaps++; break; case DEV_PATH_BR_VLAN_UNTAG: info->num_encaps--; break; case DEV_PATH_BR_VLAN_KEEP: break; } info->xmit_type = FLOW_OFFLOAD_XMIT_DIRECT; break; default: info->indev = NULL; break; } } if (!info->outdev) info->outdev = info->indev; info->hw_outdev = info->indev; if (nf_flowtable_hw_offload(flowtable) && nft_is_valid_ether_device(info->indev)) info->xmit_type = FLOW_OFFLOAD_XMIT_DIRECT; } static bool nft_flowtable_find_dev(const struct net_device *dev, struct nft_flowtable *ft) { struct nft_hook *hook; bool found = false; list_for_each_entry_rcu(hook, &ft->hook_list, list) { if (hook->ops.dev != dev) continue; found = true; break; } return found; } static void nft_dev_forward_path(struct nf_flow_route *route, const struct nf_conn *ct, enum ip_conntrack_dir dir, struct nft_flowtable *ft) { const struct dst_entry *dst = route->tuple[dir].dst; struct net_device_path_stack stack; struct nft_forward_info info = {}; unsigned char ha[ETH_ALEN]; int i; if (nft_dev_fill_forward_path(route, dst, ct, dir, ha, &stack) >= 0) nft_dev_path_info(&stack, &info, ha, &ft->data); if (!info.indev || !nft_flowtable_find_dev(info.indev, ft)) return; route->tuple[!dir].in.ifindex = info.indev->ifindex; for (i = 0; i < info.num_encaps; i++) { route->tuple[!dir].in.encap[i].id = info.encap[i].id; route->tuple[!dir].in.encap[i].proto = info.encap[i].proto; } route->tuple[!dir].in.num_encaps = info.num_encaps; route->tuple[!dir].in.ingress_vlans = info.ingress_vlans; if (info.xmit_type == FLOW_OFFLOAD_XMIT_DIRECT) { memcpy(route->tuple[dir].out.h_source, info.h_source, ETH_ALEN); memcpy(route->tuple[dir].out.h_dest, info.h_dest, ETH_ALEN); route->tuple[dir].out.ifindex = info.outdev->ifindex; route->tuple[dir].out.hw_ifindex = info.hw_outdev->ifindex; route->tuple[dir].xmit_type = info.xmit_type; } } static int nft_flow_route(const struct nft_pktinfo *pkt, const struct nf_conn *ct, struct nf_flow_route *route, enum ip_conntrack_dir dir, struct nft_flowtable *ft) { struct dst_entry *this_dst = skb_dst(pkt->skb); struct dst_entry *other_dst = NULL; struct flowi fl; memset(&fl, 0, sizeof(fl)); switch (nft_pf(pkt)) { case NFPROTO_IPV4: fl.u.ip4.daddr = ct->tuplehash[dir].tuple.src.u3.ip; fl.u.ip4.saddr = ct->tuplehash[!dir].tuple.src.u3.ip; fl.u.ip4.flowi4_oif = nft_in(pkt)->ifindex; fl.u.ip4.flowi4_iif = this_dst->dev->ifindex; fl.u.ip4.flowi4_tos = inet_dscp_to_dsfield(ip4h_dscp(ip_hdr(pkt->skb))); fl.u.ip4.flowi4_mark = pkt->skb->mark; fl.u.ip4.flowi4_flags = FLOWI_FLAG_ANYSRC; break; case NFPROTO_IPV6: fl.u.ip6.daddr = ct->tuplehash[dir].tuple.src.u3.in6; fl.u.ip6.saddr = ct->tuplehash[!dir].tuple.src.u3.in6; fl.u.ip6.flowi6_oif = nft_in(pkt)->ifindex; fl.u.ip6.flowi6_iif = this_dst->dev->ifindex; fl.u.ip6.flowlabel = ip6_flowinfo(ipv6_hdr(pkt->skb)); fl.u.ip6.flowi6_mark = pkt->skb->mark; fl.u.ip6.flowi6_flags = FLOWI_FLAG_ANYSRC; break; } if (!dst_hold_safe(this_dst)) return -ENOENT; nf_route(nft_net(pkt), &other_dst, &fl, false, nft_pf(pkt)); if (!other_dst) { dst_release(this_dst); return -ENOENT; } nft_default_forward_path(route, this_dst, dir); nft_default_forward_path(route, other_dst, !dir); if (route->tuple[dir].xmit_type == FLOW_OFFLOAD_XMIT_NEIGH && route->tuple[!dir].xmit_type == FLOW_OFFLOAD_XMIT_NEIGH) { nft_dev_forward_path(route, ct, dir, ft); nft_dev_forward_path(route, ct, !dir, ft); } return 0; } static bool nft_flow_offload_skip(struct sk_buff *skb, int family) { if (skb_sec_path(skb)) return true; if (family == NFPROTO_IPV4) { const struct ip_options *opt; opt = &(IPCB(skb)->opt); if (unlikely(opt->optlen)) return true; } return false; } static void nft_flow_offload_eval(const struct nft_expr *expr, struct nft_regs *regs, const struct nft_pktinfo *pkt) { struct nft_flow_offload *priv = nft_expr_priv(expr); struct nf_flowtable *flowtable = &priv->flowtable->data; struct tcphdr _tcph, *tcph = NULL; struct nf_flow_route route = {}; enum ip_conntrack_info ctinfo; struct flow_offload *flow; enum ip_conntrack_dir dir; struct nf_conn *ct; int ret; if (nft_flow_offload_skip(pkt->skb, nft_pf(pkt))) goto out; ct = nf_ct_get(pkt->skb, &ctinfo); if (!ct) goto out; switch (ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple.dst.protonum) { case IPPROTO_TCP: tcph = skb_header_pointer(pkt->skb, nft_thoff(pkt), sizeof(_tcph), &_tcph); if (unlikely(!tcph || tcph->fin || tcph->rst || !nf_conntrack_tcp_established(ct))) goto out; break; case IPPROTO_UDP: break; #ifdef CONFIG_NF_CT_PROTO_GRE case IPPROTO_GRE: { struct nf_conntrack_tuple *tuple; if (ct->status & IPS_NAT_MASK) goto out; tuple = &ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple; /* No support for GRE v1 */ if (tuple->src.u.gre.key || tuple->dst.u.gre.key) goto out; break; } #endif default: goto out; } if (nf_ct_ext_exist(ct, NF_CT_EXT_HELPER) || ct->status & (IPS_SEQ_ADJUST | IPS_NAT_CLASH)) goto out; if (!nf_ct_is_confirmed(ct)) goto out; if (test_and_set_bit(IPS_OFFLOAD_BIT, &ct->status)) goto out; dir = CTINFO2DIR(ctinfo); if (nft_flow_route(pkt, ct, &route, dir, priv->flowtable) < 0) goto err_flow_route; flow = flow_offload_alloc(ct); if (!flow) goto err_flow_alloc; flow_offload_route_init(flow, &route); if (tcph) { ct->proto.tcp.seen[0].flags |= IP_CT_TCP_FLAG_BE_LIBERAL; ct->proto.tcp.seen[1].flags |= IP_CT_TCP_FLAG_BE_LIBERAL; } __set_bit(NF_FLOW_HW_BIDIRECTIONAL, &flow->flags); ret = flow_offload_add(flowtable, flow); if (ret < 0) goto err_flow_add; return; err_flow_add: flow_offload_free(flow); err_flow_alloc: dst_release(route.tuple[dir].dst); dst_release(route.tuple[!dir].dst); err_flow_route: clear_bit(IPS_OFFLOAD_BIT, &ct->status); out: regs->verdict.code = NFT_BREAK; } static int nft_flow_offload_validate(const struct nft_ctx *ctx, const struct nft_expr *expr) { unsigned int hook_mask = (1 << NF_INET_FORWARD); if (ctx->family != NFPROTO_IPV4 && ctx->family != NFPROTO_IPV6 && ctx->family != NFPROTO_INET) return -EOPNOTSUPP; return nft_chain_validate_hooks(ctx->chain, hook_mask); } static const struct nla_policy nft_flow_offload_policy[NFTA_FLOW_MAX + 1] = { [NFTA_FLOW_TABLE_NAME] = { .type = NLA_STRING, .len = NFT_NAME_MAXLEN - 1 }, }; static int nft_flow_offload_init(const struct nft_ctx *ctx, const struct nft_expr *expr, const struct nlattr * const tb[]) { struct nft_flow_offload *priv = nft_expr_priv(expr); u8 genmask = nft_genmask_next(ctx->net); struct nft_flowtable *flowtable; if (!tb[NFTA_FLOW_TABLE_NAME]) return -EINVAL; flowtable = nft_flowtable_lookup(ctx->net, ctx->table, tb[NFTA_FLOW_TABLE_NAME], genmask); if (IS_ERR(flowtable)) return PTR_ERR(flowtable); if (!nft_use_inc(&flowtable->use)) return -EMFILE; priv->flowtable = flowtable; return nf_ct_netns_get(ctx->net, ctx->family); } static void nft_flow_offload_deactivate(const struct nft_ctx *ctx, const struct nft_expr *expr, enum nft_trans_phase phase) { struct nft_flow_offload *priv = nft_expr_priv(expr); nf_tables_deactivate_flowtable(ctx, priv->flowtable, phase); } static void nft_flow_offload_activate(const struct nft_ctx *ctx, const struct nft_expr *expr) { struct nft_flow_offload *priv = nft_expr_priv(expr); nft_use_inc_restore(&priv->flowtable->use); } static void nft_flow_offload_destroy(const struct nft_ctx *ctx, const struct nft_expr *expr) { nf_ct_netns_put(ctx->net, ctx->family); } static int nft_flow_offload_dump(struct sk_buff *skb, const struct nft_expr *expr, bool reset) { struct nft_flow_offload *priv = nft_expr_priv(expr); if (nla_put_string(skb, NFTA_FLOW_TABLE_NAME, priv->flowtable->name)) goto nla_put_failure; return 0; nla_put_failure: return -1; } static struct nft_expr_type nft_flow_offload_type; static const struct nft_expr_ops nft_flow_offload_ops = { .type = &nft_flow_offload_type, .size = NFT_EXPR_SIZE(sizeof(struct nft_flow_offload)), .eval = nft_flow_offload_eval, .init = nft_flow_offload_init, .activate = nft_flow_offload_activate, .deactivate = nft_flow_offload_deactivate, .destroy = nft_flow_offload_destroy, .validate = nft_flow_offload_validate, .dump = nft_flow_offload_dump, .reduce = NFT_REDUCE_READONLY, }; static struct nft_expr_type nft_flow_offload_type __read_mostly = { .name = "flow_offload", .ops = &nft_flow_offload_ops, .policy = nft_flow_offload_policy, .maxattr = NFTA_FLOW_MAX, .owner = THIS_MODULE, }; static int flow_offload_netdev_event(struct notifier_block *this, unsigned long event, void *ptr) { struct net_device *dev = netdev_notifier_info_to_dev(ptr); if (event != NETDEV_DOWN) return NOTIFY_DONE; nf_flow_table_cleanup(dev); return NOTIFY_DONE; } static struct notifier_block flow_offload_netdev_notifier = { .notifier_call = flow_offload_netdev_event, }; static int __init nft_flow_offload_module_init(void) { int err; err = register_netdevice_notifier(&flow_offload_netdev_notifier); if (err) goto err; err = nft_register_expr(&nft_flow_offload_type); if (err < 0) goto register_expr; return 0; register_expr: unregister_netdevice_notifier(&flow_offload_netdev_notifier); err: return err; } static void __exit nft_flow_offload_module_exit(void) { nft_unregister_expr(&nft_flow_offload_type); unregister_netdevice_notifier(&flow_offload_netdev_notifier); } module_init(nft_flow_offload_module_init); module_exit(nft_flow_offload_module_exit); MODULE_LICENSE("GPL"); MODULE_AUTHOR("Pablo Neira Ayuso <pablo@netfilter.org>"); MODULE_ALIAS_NFT_EXPR("flow_offload"); MODULE_DESCRIPTION("nftables hardware flow offload module"); |
| 266 279 57 281 281 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _LINUX_LIST_BL_H #define _LINUX_LIST_BL_H #include <linux/list.h> #include <linux/bit_spinlock.h> /* * Special version of lists, where head of the list has a lock in the lowest * bit. This is useful for scalable hash tables without increasing memory * footprint overhead. * * For modification operations, the 0 bit of hlist_bl_head->first * pointer must be set. * * With some small modifications, this can easily be adapted to store several * arbitrary bits (not just a single lock bit), if the need arises to store * some fast and compact auxiliary data. */ #if defined(CONFIG_SMP) || defined(CONFIG_DEBUG_SPINLOCK) #define LIST_BL_LOCKMASK 1UL #else #define LIST_BL_LOCKMASK 0UL #endif #ifdef CONFIG_DEBUG_LIST #define LIST_BL_BUG_ON(x) BUG_ON(x) #else #define LIST_BL_BUG_ON(x) #endif struct hlist_bl_head { struct hlist_bl_node *first; }; struct hlist_bl_node { struct hlist_bl_node *next, **pprev; }; #define INIT_HLIST_BL_HEAD(ptr) \ ((ptr)->first = NULL) static inline void INIT_HLIST_BL_NODE(struct hlist_bl_node *h) { h->next = NULL; h->pprev = NULL; } #define hlist_bl_entry(ptr, type, member) container_of(ptr,type,member) static inline bool hlist_bl_unhashed(const struct hlist_bl_node *h) { return !h->pprev; } static inline struct hlist_bl_node *hlist_bl_first(struct hlist_bl_head *h) { return (struct hlist_bl_node *) ((unsigned long)h->first & ~LIST_BL_LOCKMASK); } static inline void hlist_bl_set_first(struct hlist_bl_head *h, struct hlist_bl_node *n) { LIST_BL_BUG_ON((unsigned long)n & LIST_BL_LOCKMASK); LIST_BL_BUG_ON(((unsigned long)h->first & LIST_BL_LOCKMASK) != LIST_BL_LOCKMASK); h->first = (struct hlist_bl_node *)((unsigned long)n | LIST_BL_LOCKMASK); } static inline bool hlist_bl_empty(const struct hlist_bl_head *h) { return !((unsigned long)READ_ONCE(h->first) & ~LIST_BL_LOCKMASK); } static inline void hlist_bl_add_head(struct hlist_bl_node *n, struct hlist_bl_head *h) { struct hlist_bl_node *first = hlist_bl_first(h); n->next = first; if (first) first->pprev = &n->next; n->pprev = &h->first; hlist_bl_set_first(h, n); } static inline void hlist_bl_add_before(struct hlist_bl_node *n, struct hlist_bl_node *next) { struct hlist_bl_node **pprev = next->pprev; n->pprev = pprev; n->next = next; next->pprev = &n->next; /* pprev may be `first`, so be careful not to lose the lock bit */ WRITE_ONCE(*pprev, (struct hlist_bl_node *) ((uintptr_t)n | ((uintptr_t)*pprev & LIST_BL_LOCKMASK))); } static inline void hlist_bl_add_behind(struct hlist_bl_node *n, struct hlist_bl_node *prev) { n->next = prev->next; n->pprev = &prev->next; prev->next = n; if (n->next) n->next->pprev = &n->next; } static inline void __hlist_bl_del(struct hlist_bl_node *n) { struct hlist_bl_node *next = n->next; struct hlist_bl_node **pprev = n->pprev; LIST_BL_BUG_ON((unsigned long)n & LIST_BL_LOCKMASK); /* pprev may be `first`, so be careful not to lose the lock bit */ WRITE_ONCE(*pprev, (struct hlist_bl_node *) ((unsigned long)next | ((unsigned long)*pprev & LIST_BL_LOCKMASK))); if (next) next->pprev = pprev; } static inline void hlist_bl_del(struct hlist_bl_node *n) { __hlist_bl_del(n); n->next = LIST_POISON1; n->pprev = LIST_POISON2; } static inline void hlist_bl_del_init(struct hlist_bl_node *n) { if (!hlist_bl_unhashed(n)) { __hlist_bl_del(n); INIT_HLIST_BL_NODE(n); } } static inline void hlist_bl_lock(struct hlist_bl_head *b) { bit_spin_lock(0, (unsigned long *)b); } static inline void hlist_bl_unlock(struct hlist_bl_head *b) { __bit_spin_unlock(0, (unsigned long *)b); } static inline bool hlist_bl_is_locked(struct hlist_bl_head *b) { return bit_spin_is_locked(0, (unsigned long *)b); } /** * hlist_bl_for_each_entry - iterate over list of given type * @tpos: the type * to use as a loop cursor. * @pos: the &struct hlist_node to use as a loop cursor. * @head: the head for your list. * @member: the name of the hlist_node within the struct. * */ #define hlist_bl_for_each_entry(tpos, pos, head, member) \ for (pos = hlist_bl_first(head); \ pos && \ ({ tpos = hlist_bl_entry(pos, typeof(*tpos), member); 1;}); \ pos = pos->next) /** * hlist_bl_for_each_entry_safe - iterate over list of given type safe against removal of list entry * @tpos: the type * to use as a loop cursor. * @pos: the &struct hlist_node to use as a loop cursor. * @n: another &struct hlist_node to use as temporary storage * @head: the head for your list. * @member: the name of the hlist_node within the struct. */ #define hlist_bl_for_each_entry_safe(tpos, pos, n, head, member) \ for (pos = hlist_bl_first(head); \ pos && ({ n = pos->next; 1; }) && \ ({ tpos = hlist_bl_entry(pos, typeof(*tpos), member); 1;}); \ pos = n) #endif |
| 3 3 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 1522 1523 1524 1525 1526 1527 1528 1529 1530 1531 1532 1533 1534 1535 1536 1537 1538 1539 1540 1541 1542 1543 1544 1545 1546 1547 1548 1549 1550 1551 1552 1553 1554 1555 1556 1557 1558 1559 1560 1561 1562 1563 1564 1565 1566 1567 1568 1569 1570 1571 1572 1573 1574 1575 1576 1577 1578 1579 1580 1581 1582 1583 1584 1585 1586 1587 1588 1589 1590 1591 1592 1593 1594 1595 1596 1597 1598 1599 1600 1601 1602 1603 1604 1605 1606 1607 1608 1609 1610 1611 1612 1613 1614 1615 1616 1617 1618 1619 1620 1621 1622 1623 1624 1625 1626 1627 1628 1629 1630 1631 1632 1633 1634 1635 1636 1637 1638 1639 1640 1641 1642 1643 1644 1645 1646 1647 1648 1649 1650 1651 1652 1653 1654 1655 1656 1657 1658 1659 1660 1661 1662 1663 1664 1665 1666 1667 1668 1669 1670 1671 1672 1673 1674 1675 1676 1677 1678 1679 1680 1681 1682 1683 1684 1685 1686 1687 1688 1689 1690 1691 1692 1693 1694 1695 1696 1697 1698 1699 1700 1701 1702 1703 1704 1705 1706 1707 1708 1709 1710 1711 1712 1713 1714 1715 1716 1717 1718 1719 1720 1721 1722 1723 1724 1725 1726 1727 1728 1729 1730 1731 1732 1733 1734 1735 1736 1737 1738 1739 1740 1741 1742 1743 1744 1745 1746 1747 1748 1749 1750 1751 1752 1753 1754 1755 1756 1757 1758 1759 1760 1761 1762 1763 1764 1765 1766 1767 1768 1769 1770 1771 1772 1773 1774 1775 1776 1777 1778 1779 1780 1781 1782 1783 1784 1785 1786 1787 1788 1789 1790 1791 1792 1793 1794 1795 1796 1797 1798 1799 1800 1801 1802 1803 1804 1805 1806 1807 1808 1809 1810 1811 1812 1813 1814 1815 1816 1817 1818 1819 1820 1821 1822 1823 1824 1825 1826 1827 1828 1829 1830 1831 1832 1833 1834 1835 1836 1837 1838 | // SPDX-License-Identifier: (GPL-2.0 OR BSD-3-Clause) /* * bcm.c - Broadcast Manager to filter/send (cyclic) CAN content * * Copyright (c) 2002-2017 Volkswagen Group Electronic Research * All rights reserved. * * Redistribution and use in source and binary forms, with or without * modification, are permitted provided that the following conditions * are met: * 1. Redistributions of source code must retain the above copyright * notice, this list of conditions and the following disclaimer. * 2. Redistributions in binary form must reproduce the above copyright * notice, this list of conditions and the following disclaimer in the * documentation and/or other materials provided with the distribution. * 3. Neither the name of Volkswagen nor the names of its contributors * may be used to endorse or promote products derived from this software * without specific prior written permission. * * Alternatively, provided that this notice is retained in full, this * software may be distributed under the terms of the GNU General * Public License ("GPL") version 2, in which case the provisions of the * GPL apply INSTEAD OF those given above. * * The provided data structures and external interfaces from this code * are not restricted to be used by modules with a GPL compatible license. * * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS * "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT * LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR * A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT * OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, * SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT * LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, * DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY * THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT * (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE * OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH * DAMAGE. * */ #include <linux/module.h> #include <linux/init.h> #include <linux/interrupt.h> #include <linux/hrtimer.h> #include <linux/list.h> #include <linux/proc_fs.h> #include <linux/seq_file.h> #include <linux/uio.h> #include <linux/net.h> #include <linux/netdevice.h> #include <linux/socket.h> #include <linux/if_arp.h> #include <linux/skbuff.h> #include <linux/can.h> #include <linux/can/core.h> #include <linux/can/skb.h> #include <linux/can/bcm.h> #include <linux/slab.h> #include <net/sock.h> #include <net/net_namespace.h> /* * To send multiple CAN frame content within TX_SETUP or to filter * CAN messages with multiplex index within RX_SETUP, the number of * different filters is limited to 256 due to the one byte index value. */ #define MAX_NFRAMES 256 /* limit timers to 400 days for sending/timeouts */ #define BCM_TIMER_SEC_MAX (400 * 24 * 60 * 60) /* use of last_frames[index].flags */ #define RX_LOCAL 0x10 /* frame was created on the local host */ #define RX_OWN 0x20 /* frame was sent via the socket it was received on */ #define RX_RECV 0x40 /* received data for this element */ #define RX_THR 0x80 /* element not been sent due to throttle feature */ #define BCM_CAN_FLAGS_MASK 0x0F /* to clean private flags after usage */ /* get best masking value for can_rx_register() for a given single can_id */ #define REGMASK(id) ((id & CAN_EFF_FLAG) ? \ (CAN_EFF_MASK | CAN_EFF_FLAG | CAN_RTR_FLAG) : \ (CAN_SFF_MASK | CAN_EFF_FLAG | CAN_RTR_FLAG)) MODULE_DESCRIPTION("PF_CAN broadcast manager protocol"); MODULE_LICENSE("Dual BSD/GPL"); MODULE_AUTHOR("Oliver Hartkopp <oliver.hartkopp@volkswagen.de>"); MODULE_ALIAS("can-proto-2"); #define BCM_MIN_NAMELEN CAN_REQUIRED_SIZE(struct sockaddr_can, can_ifindex) /* * easy access to the first 64 bit of can(fd)_frame payload. cp->data is * 64 bit aligned so the offset has to be multiples of 8 which is ensured * by the only callers in bcm_rx_cmp_to_index() bcm_rx_handler(). */ static inline u64 get_u64(const struct canfd_frame *cp, int offset) { return *(u64 *)(cp->data + offset); } struct bcm_op { struct list_head list; struct rcu_head rcu; int ifindex; canid_t can_id; u32 flags; unsigned long frames_abs, frames_filtered; struct bcm_timeval ival1, ival2; struct hrtimer timer, thrtimer; ktime_t rx_stamp, kt_ival1, kt_ival2, kt_lastmsg; int rx_ifindex; int cfsiz; u32 count; u32 nframes; u32 currframe; /* void pointers to arrays of struct can[fd]_frame */ void *frames; void *last_frames; struct canfd_frame sframe; struct canfd_frame last_sframe; struct sock *sk; struct net_device *rx_reg_dev; }; struct bcm_sock { struct sock sk; int bound; int ifindex; struct list_head notifier; struct list_head rx_ops; struct list_head tx_ops; unsigned long dropped_usr_msgs; struct proc_dir_entry *bcm_proc_read; char procname [32]; /* inode number in decimal with \0 */ }; static LIST_HEAD(bcm_notifier_list); static DEFINE_SPINLOCK(bcm_notifier_lock); static struct bcm_sock *bcm_busy_notifier; /* Return pointer to store the extra msg flags for bcm_recvmsg(). * We use the space of one unsigned int beyond the 'struct sockaddr_can' * in skb->cb. */ static inline unsigned int *bcm_flags(struct sk_buff *skb) { /* return pointer after struct sockaddr_can */ return (unsigned int *)(&((struct sockaddr_can *)skb->cb)[1]); } static inline struct bcm_sock *bcm_sk(const struct sock *sk) { return (struct bcm_sock *)sk; } static inline ktime_t bcm_timeval_to_ktime(struct bcm_timeval tv) { return ktime_set(tv.tv_sec, tv.tv_usec * NSEC_PER_USEC); } /* check limitations for timeval provided by user */ static bool bcm_is_invalid_tv(struct bcm_msg_head *msg_head) { if ((msg_head->ival1.tv_sec < 0) || (msg_head->ival1.tv_sec > BCM_TIMER_SEC_MAX) || (msg_head->ival1.tv_usec < 0) || (msg_head->ival1.tv_usec >= USEC_PER_SEC) || (msg_head->ival2.tv_sec < 0) || (msg_head->ival2.tv_sec > BCM_TIMER_SEC_MAX) || (msg_head->ival2.tv_usec < 0) || (msg_head->ival2.tv_usec >= USEC_PER_SEC)) return true; return false; } #define CFSIZ(flags) ((flags & CAN_FD_FRAME) ? CANFD_MTU : CAN_MTU) #define OPSIZ sizeof(struct bcm_op) #define MHSIZ sizeof(struct bcm_msg_head) /* * procfs functions */ #if IS_ENABLED(CONFIG_PROC_FS) static char *bcm_proc_getifname(struct net *net, char *result, int ifindex) { struct net_device *dev; if (!ifindex) return "any"; rcu_read_lock(); dev = dev_get_by_index_rcu(net, ifindex); if (dev) strcpy(result, dev->name); else strcpy(result, "???"); rcu_read_unlock(); return result; } static int bcm_proc_show(struct seq_file *m, void *v) { char ifname[IFNAMSIZ]; struct net *net = m->private; struct sock *sk = (struct sock *)pde_data(m->file->f_inode); struct bcm_sock *bo = bcm_sk(sk); struct bcm_op *op; seq_printf(m, ">>> socket %pK", sk->sk_socket); seq_printf(m, " / sk %pK", sk); seq_printf(m, " / bo %pK", bo); seq_printf(m, " / dropped %lu", bo->dropped_usr_msgs); seq_printf(m, " / bound %s", bcm_proc_getifname(net, ifname, bo->ifindex)); seq_printf(m, " <<<\n"); list_for_each_entry(op, &bo->rx_ops, list) { unsigned long reduction; /* print only active entries & prevent division by zero */ if (!op->frames_abs) continue; seq_printf(m, "rx_op: %03X %-5s ", op->can_id, bcm_proc_getifname(net, ifname, op->ifindex)); if (op->flags & CAN_FD_FRAME) seq_printf(m, "(%u)", op->nframes); else seq_printf(m, "[%u]", op->nframes); seq_printf(m, "%c ", (op->flags & RX_CHECK_DLC) ? 'd' : ' '); if (op->kt_ival1) seq_printf(m, "timeo=%lld ", (long long)ktime_to_us(op->kt_ival1)); if (op->kt_ival2) seq_printf(m, "thr=%lld ", (long long)ktime_to_us(op->kt_ival2)); seq_printf(m, "# recv %ld (%ld) => reduction: ", op->frames_filtered, op->frames_abs); reduction = 100 - (op->frames_filtered * 100) / op->frames_abs; seq_printf(m, "%s%ld%%\n", (reduction == 100) ? "near " : "", reduction); } list_for_each_entry(op, &bo->tx_ops, list) { seq_printf(m, "tx_op: %03X %s ", op->can_id, bcm_proc_getifname(net, ifname, op->ifindex)); if (op->flags & CAN_FD_FRAME) seq_printf(m, "(%u) ", op->nframes); else seq_printf(m, "[%u] ", op->nframes); if (op->kt_ival1) seq_printf(m, "t1=%lld ", (long long)ktime_to_us(op->kt_ival1)); if (op->kt_ival2) seq_printf(m, "t2=%lld ", (long long)ktime_to_us(op->kt_ival2)); seq_printf(m, "# sent %ld\n", op->frames_abs); } seq_putc(m, '\n'); return 0; } #endif /* CONFIG_PROC_FS */ /* * bcm_can_tx - send the (next) CAN frame to the appropriate CAN interface * of the given bcm tx op */ static void bcm_can_tx(struct bcm_op *op) { struct sk_buff *skb; struct net_device *dev; struct canfd_frame *cf = op->frames + op->cfsiz * op->currframe; int err; /* no target device? => exit */ if (!op->ifindex) return; dev = dev_get_by_index(sock_net(op->sk), op->ifindex); if (!dev) { /* RFC: should this bcm_op remove itself here? */ return; } skb = alloc_skb(op->cfsiz + sizeof(struct can_skb_priv), gfp_any()); if (!skb) goto out; can_skb_reserve(skb); can_skb_prv(skb)->ifindex = dev->ifindex; can_skb_prv(skb)->skbcnt = 0; skb_put_data(skb, cf, op->cfsiz); /* send with loopback */ skb->dev = dev; can_skb_set_owner(skb, op->sk); err = can_send(skb, 1); if (!err) op->frames_abs++; op->currframe++; /* reached last frame? */ if (op->currframe >= op->nframes) op->currframe = 0; out: dev_put(dev); } /* * bcm_send_to_user - send a BCM message to the userspace * (consisting of bcm_msg_head + x CAN frames) */ static void bcm_send_to_user(struct bcm_op *op, struct bcm_msg_head *head, struct canfd_frame *frames, int has_timestamp) { struct sk_buff *skb; struct canfd_frame *firstframe; struct sockaddr_can *addr; struct sock *sk = op->sk; unsigned int datalen = head->nframes * op->cfsiz; int err; unsigned int *pflags; skb = alloc_skb(sizeof(*head) + datalen, gfp_any()); if (!skb) return; skb_put_data(skb, head, sizeof(*head)); /* ensure space for sockaddr_can and msg flags */ sock_skb_cb_check_size(sizeof(struct sockaddr_can) + sizeof(unsigned int)); /* initialize msg flags */ pflags = bcm_flags(skb); *pflags = 0; if (head->nframes) { /* CAN frames starting here */ firstframe = (struct canfd_frame *)skb_tail_pointer(skb); skb_put_data(skb, frames, datalen); /* * the BCM uses the flags-element of the canfd_frame * structure for internal purposes. This is only * relevant for updates that are generated by the * BCM, where nframes is 1 */ if (head->nframes == 1) { if (firstframe->flags & RX_LOCAL) *pflags |= MSG_DONTROUTE; if (firstframe->flags & RX_OWN) *pflags |= MSG_CONFIRM; firstframe->flags &= BCM_CAN_FLAGS_MASK; } } if (has_timestamp) { /* restore rx timestamp */ skb->tstamp = op->rx_stamp; } /* * Put the datagram to the queue so that bcm_recvmsg() can * get it from there. We need to pass the interface index to * bcm_recvmsg(). We pass a whole struct sockaddr_can in skb->cb * containing the interface index. */ addr = (struct sockaddr_can *)skb->cb; memset(addr, 0, sizeof(*addr)); addr->can_family = AF_CAN; addr->can_ifindex = op->rx_ifindex; err = sock_queue_rcv_skb(sk, skb); if (err < 0) { struct bcm_sock *bo = bcm_sk(sk); kfree_skb(skb); /* don't care about overflows in this statistic */ bo->dropped_usr_msgs++; } } static bool bcm_tx_set_expiry(struct bcm_op *op, struct hrtimer *hrt) { ktime_t ival; if (op->kt_ival1 && op->count) ival = op->kt_ival1; else if (op->kt_ival2) ival = op->kt_ival2; else return false; hrtimer_set_expires(hrt, ktime_add(ktime_get(), ival)); return true; } static void bcm_tx_start_timer(struct bcm_op *op) { if (bcm_tx_set_expiry(op, &op->timer)) hrtimer_start_expires(&op->timer, HRTIMER_MODE_ABS_SOFT); } /* bcm_tx_timeout_handler - performs cyclic CAN frame transmissions */ static enum hrtimer_restart bcm_tx_timeout_handler(struct hrtimer *hrtimer) { struct bcm_op *op = container_of(hrtimer, struct bcm_op, timer); struct bcm_msg_head msg_head; if (op->kt_ival1 && (op->count > 0)) { op->count--; if (!op->count && (op->flags & TX_COUNTEVT)) { /* create notification to user */ memset(&msg_head, 0, sizeof(msg_head)); msg_head.opcode = TX_EXPIRED; msg_head.flags = op->flags; msg_head.count = op->count; msg_head.ival1 = op->ival1; msg_head.ival2 = op->ival2; msg_head.can_id = op->can_id; msg_head.nframes = 0; bcm_send_to_user(op, &msg_head, NULL, 0); } bcm_can_tx(op); } else if (op->kt_ival2) { bcm_can_tx(op); } return bcm_tx_set_expiry(op, &op->timer) ? HRTIMER_RESTART : HRTIMER_NORESTART; } /* * bcm_rx_changed - create a RX_CHANGED notification due to changed content */ static void bcm_rx_changed(struct bcm_op *op, struct canfd_frame *data) { struct bcm_msg_head head; /* update statistics */ op->frames_filtered++; /* prevent statistics overflow */ if (op->frames_filtered > ULONG_MAX/100) op->frames_filtered = op->frames_abs = 0; /* this element is not throttled anymore */ data->flags &= ~RX_THR; memset(&head, 0, sizeof(head)); head.opcode = RX_CHANGED; head.flags = op->flags; head.count = op->count; head.ival1 = op->ival1; head.ival2 = op->ival2; head.can_id = op->can_id; head.nframes = 1; bcm_send_to_user(op, &head, data, 1); } /* * bcm_rx_update_and_send - process a detected relevant receive content change * 1. update the last received data * 2. send a notification to the user (if possible) */ static void bcm_rx_update_and_send(struct bcm_op *op, struct canfd_frame *lastdata, const struct canfd_frame *rxdata, unsigned char traffic_flags) { memcpy(lastdata, rxdata, op->cfsiz); /* mark as used and throttled by default */ lastdata->flags |= (RX_RECV|RX_THR); /* add own/local/remote traffic flags */ lastdata->flags |= traffic_flags; /* throttling mode inactive ? */ if (!op->kt_ival2) { /* send RX_CHANGED to the user immediately */ bcm_rx_changed(op, lastdata); return; } /* with active throttling timer we are just done here */ if (hrtimer_active(&op->thrtimer)) return; /* first reception with enabled throttling mode */ if (!op->kt_lastmsg) goto rx_changed_settime; /* got a second frame inside a potential throttle period? */ if (ktime_us_delta(ktime_get(), op->kt_lastmsg) < ktime_to_us(op->kt_ival2)) { /* do not send the saved data - only start throttle timer */ hrtimer_start(&op->thrtimer, ktime_add(op->kt_lastmsg, op->kt_ival2), HRTIMER_MODE_ABS_SOFT); return; } /* the gap was that big, that throttling was not needed here */ rx_changed_settime: bcm_rx_changed(op, lastdata); op->kt_lastmsg = ktime_get(); } /* * bcm_rx_cmp_to_index - (bit)compares the currently received data to formerly * received data stored in op->last_frames[] */ static void bcm_rx_cmp_to_index(struct bcm_op *op, unsigned int index, const struct canfd_frame *rxdata, unsigned char traffic_flags) { struct canfd_frame *cf = op->frames + op->cfsiz * index; struct canfd_frame *lcf = op->last_frames + op->cfsiz * index; int i; /* * no one uses the MSBs of flags for comparison, * so we use it here to detect the first time of reception */ if (!(lcf->flags & RX_RECV)) { /* received data for the first time => send update to user */ bcm_rx_update_and_send(op, lcf, rxdata, traffic_flags); return; } /* do a real check in CAN frame data section */ for (i = 0; i < rxdata->len; i += 8) { if ((get_u64(cf, i) & get_u64(rxdata, i)) != (get_u64(cf, i) & get_u64(lcf, i))) { bcm_rx_update_and_send(op, lcf, rxdata, traffic_flags); return; } } if (op->flags & RX_CHECK_DLC) { /* do a real check in CAN frame length */ if (rxdata->len != lcf->len) { bcm_rx_update_and_send(op, lcf, rxdata, traffic_flags); return; } } } /* * bcm_rx_starttimer - enable timeout monitoring for CAN frame reception */ static void bcm_rx_starttimer(struct bcm_op *op) { if (op->flags & RX_NO_AUTOTIMER) return; if (op->kt_ival1) hrtimer_start(&op->timer, op->kt_ival1, HRTIMER_MODE_REL_SOFT); } /* bcm_rx_timeout_handler - when the (cyclic) CAN frame reception timed out */ static enum hrtimer_restart bcm_rx_timeout_handler(struct hrtimer *hrtimer) { struct bcm_op *op = container_of(hrtimer, struct bcm_op, timer); struct bcm_msg_head msg_head; /* if user wants to be informed, when cyclic CAN-Messages come back */ if ((op->flags & RX_ANNOUNCE_RESUME) && op->last_frames) { /* clear received CAN frames to indicate 'nothing received' */ memset(op->last_frames, 0, op->nframes * op->cfsiz); } /* create notification to user */ memset(&msg_head, 0, sizeof(msg_head)); msg_head.opcode = RX_TIMEOUT; msg_head.flags = op->flags; msg_head.count = op->count; msg_head.ival1 = op->ival1; msg_head.ival2 = op->ival2; msg_head.can_id = op->can_id; msg_head.nframes = 0; bcm_send_to_user(op, &msg_head, NULL, 0); return HRTIMER_NORESTART; } /* * bcm_rx_do_flush - helper for bcm_rx_thr_flush */ static inline int bcm_rx_do_flush(struct bcm_op *op, unsigned int index) { struct canfd_frame *lcf = op->last_frames + op->cfsiz * index; if ((op->last_frames) && (lcf->flags & RX_THR)) { bcm_rx_changed(op, lcf); return 1; } return 0; } /* * bcm_rx_thr_flush - Check for throttled data and send it to the userspace */ static int bcm_rx_thr_flush(struct bcm_op *op) { int updated = 0; if (op->nframes > 1) { unsigned int i; /* for MUX filter we start at index 1 */ for (i = 1; i < op->nframes; i++) updated += bcm_rx_do_flush(op, i); } else { /* for RX_FILTER_ID and simple filter */ updated += bcm_rx_do_flush(op, 0); } return updated; } /* * bcm_rx_thr_handler - the time for blocked content updates is over now: * Check for throttled data and send it to the userspace */ static enum hrtimer_restart bcm_rx_thr_handler(struct hrtimer *hrtimer) { struct bcm_op *op = container_of(hrtimer, struct bcm_op, thrtimer); if (bcm_rx_thr_flush(op)) { hrtimer_forward_now(hrtimer, op->kt_ival2); return HRTIMER_RESTART; } else { /* rearm throttle handling */ op->kt_lastmsg = 0; return HRTIMER_NORESTART; } } /* * bcm_rx_handler - handle a CAN frame reception */ static void bcm_rx_handler(struct sk_buff *skb, void *data) { struct bcm_op *op = (struct bcm_op *)data; const struct canfd_frame *rxframe = (struct canfd_frame *)skb->data; unsigned int i; unsigned char traffic_flags; if (op->can_id != rxframe->can_id) return; /* make sure to handle the correct frame type (CAN / CAN FD) */ if (op->flags & CAN_FD_FRAME) { if (!can_is_canfd_skb(skb)) return; } else { if (!can_is_can_skb(skb)) return; } /* disable timeout */ hrtimer_cancel(&op->timer); /* save rx timestamp */ op->rx_stamp = skb->tstamp; /* save originator for recvfrom() */ op->rx_ifindex = skb->dev->ifindex; /* update statistics */ op->frames_abs++; if (op->flags & RX_RTR_FRAME) { /* send reply for RTR-request (placed in op->frames[0]) */ bcm_can_tx(op); return; } /* compute flags to distinguish between own/local/remote CAN traffic */ traffic_flags = 0; if (skb->sk) { traffic_flags |= RX_LOCAL; if (skb->sk == op->sk) traffic_flags |= RX_OWN; } if (op->flags & RX_FILTER_ID) { /* the easiest case */ bcm_rx_update_and_send(op, op->last_frames, rxframe, traffic_flags); goto rx_starttimer; } if (op->nframes == 1) { /* simple compare with index 0 */ bcm_rx_cmp_to_index(op, 0, rxframe, traffic_flags); goto rx_starttimer; } if (op->nframes > 1) { /* * multiplex compare * * find the first multiplex mask that fits. * Remark: The MUX-mask is stored in index 0 - but only the * first 64 bits of the frame data[] are relevant (CAN FD) */ for (i = 1; i < op->nframes; i++) { if ((get_u64(op->frames, 0) & get_u64(rxframe, 0)) == (get_u64(op->frames, 0) & get_u64(op->frames + op->cfsiz * i, 0))) { bcm_rx_cmp_to_index(op, i, rxframe, traffic_flags); break; } } } rx_starttimer: bcm_rx_starttimer(op); } /* * helpers for bcm_op handling: find & delete bcm [rx|tx] op elements */ static struct bcm_op *bcm_find_op(struct list_head *ops, struct bcm_msg_head *mh, int ifindex) { struct bcm_op *op; list_for_each_entry(op, ops, list) { if ((op->can_id == mh->can_id) && (op->ifindex == ifindex) && (op->flags & CAN_FD_FRAME) == (mh->flags & CAN_FD_FRAME)) return op; } return NULL; } static void bcm_free_op_rcu(struct rcu_head *rcu_head) { struct bcm_op *op = container_of(rcu_head, struct bcm_op, rcu); if ((op->frames) && (op->frames != &op->sframe)) kfree(op->frames); if ((op->last_frames) && (op->last_frames != &op->last_sframe)) kfree(op->last_frames); kfree(op); } static void bcm_remove_op(struct bcm_op *op) { hrtimer_cancel(&op->timer); hrtimer_cancel(&op->thrtimer); call_rcu(&op->rcu, bcm_free_op_rcu); } static void bcm_rx_unreg(struct net_device *dev, struct bcm_op *op) { if (op->rx_reg_dev == dev) { can_rx_unregister(dev_net(dev), dev, op->can_id, REGMASK(op->can_id), bcm_rx_handler, op); /* mark as removed subscription */ op->rx_reg_dev = NULL; } else printk(KERN_ERR "can-bcm: bcm_rx_unreg: registered device " "mismatch %p %p\n", op->rx_reg_dev, dev); } /* * bcm_delete_rx_op - find and remove a rx op (returns number of removed ops) */ static int bcm_delete_rx_op(struct list_head *ops, struct bcm_msg_head *mh, int ifindex) { struct bcm_op *op, *n; list_for_each_entry_safe(op, n, ops, list) { if ((op->can_id == mh->can_id) && (op->ifindex == ifindex) && (op->flags & CAN_FD_FRAME) == (mh->flags & CAN_FD_FRAME)) { /* disable automatic timer on frame reception */ op->flags |= RX_NO_AUTOTIMER; /* * Don't care if we're bound or not (due to netdev * problems) can_rx_unregister() is always a save * thing to do here. */ if (op->ifindex) { /* * Only remove subscriptions that had not * been removed due to NETDEV_UNREGISTER * in bcm_notifier() */ if (op->rx_reg_dev) { struct net_device *dev; dev = dev_get_by_index(sock_net(op->sk), op->ifindex); if (dev) { bcm_rx_unreg(dev, op); dev_put(dev); } } } else can_rx_unregister(sock_net(op->sk), NULL, op->can_id, REGMASK(op->can_id), bcm_rx_handler, op); list_del(&op->list); bcm_remove_op(op); return 1; /* done */ } } return 0; /* not found */ } /* * bcm_delete_tx_op - find and remove a tx op (returns number of removed ops) */ static int bcm_delete_tx_op(struct list_head *ops, struct bcm_msg_head *mh, int ifindex) { struct bcm_op *op, *n; list_for_each_entry_safe(op, n, ops, list) { if ((op->can_id == mh->can_id) && (op->ifindex == ifindex) && (op->flags & CAN_FD_FRAME) == (mh->flags & CAN_FD_FRAME)) { list_del(&op->list); bcm_remove_op(op); return 1; /* done */ } } return 0; /* not found */ } /* * bcm_read_op - read out a bcm_op and send it to the user (for bcm_sendmsg) */ static int bcm_read_op(struct list_head *ops, struct bcm_msg_head *msg_head, int ifindex) { struct bcm_op *op = bcm_find_op(ops, msg_head, ifindex); if (!op) return -EINVAL; /* put current values into msg_head */ msg_head->flags = op->flags; msg_head->count = op->count; msg_head->ival1 = op->ival1; msg_head->ival2 = op->ival2; msg_head->nframes = op->nframes; bcm_send_to_user(op, msg_head, op->frames, 0); return MHSIZ; } /* * bcm_tx_setup - create or update a bcm tx op (for bcm_sendmsg) */ static int bcm_tx_setup(struct bcm_msg_head *msg_head, struct msghdr *msg, int ifindex, struct sock *sk) { struct bcm_sock *bo = bcm_sk(sk); struct bcm_op *op; struct canfd_frame *cf; unsigned int i; int err; /* we need a real device to send frames */ if (!ifindex) return -ENODEV; /* check nframes boundaries - we need at least one CAN frame */ if (msg_head->nframes < 1 || msg_head->nframes > MAX_NFRAMES) return -EINVAL; /* check timeval limitations */ if ((msg_head->flags & SETTIMER) && bcm_is_invalid_tv(msg_head)) return -EINVAL; /* check the given can_id */ op = bcm_find_op(&bo->tx_ops, msg_head, ifindex); if (op) { /* update existing BCM operation */ /* * Do we need more space for the CAN frames than currently * allocated? -> This is a _really_ unusual use-case and * therefore (complexity / locking) it is not supported. */ if (msg_head->nframes > op->nframes) return -E2BIG; /* update CAN frames content */ for (i = 0; i < msg_head->nframes; i++) { cf = op->frames + op->cfsiz * i; err = memcpy_from_msg((u8 *)cf, msg, op->cfsiz); if (op->flags & CAN_FD_FRAME) { if (cf->len > 64) err = -EINVAL; } else { if (cf->len > 8) err = -EINVAL; } if (err < 0) return err; if (msg_head->flags & TX_CP_CAN_ID) { /* copy can_id into frame */ cf->can_id = msg_head->can_id; } } op->flags = msg_head->flags; } else { /* insert new BCM operation for the given can_id */ op = kzalloc(OPSIZ, GFP_KERNEL); if (!op) return -ENOMEM; op->can_id = msg_head->can_id; op->cfsiz = CFSIZ(msg_head->flags); op->flags = msg_head->flags; /* create array for CAN frames and copy the data */ if (msg_head->nframes > 1) { op->frames = kmalloc_array(msg_head->nframes, op->cfsiz, GFP_KERNEL); if (!op->frames) { kfree(op); return -ENOMEM; } } else op->frames = &op->sframe; for (i = 0; i < msg_head->nframes; i++) { cf = op->frames + op->cfsiz * i; err = memcpy_from_msg((u8 *)cf, msg, op->cfsiz); if (err < 0) goto free_op; if (op->flags & CAN_FD_FRAME) { if (cf->len > 64) err = -EINVAL; } else { if (cf->len > 8) err = -EINVAL; } if (err < 0) goto free_op; if (msg_head->flags & TX_CP_CAN_ID) { /* copy can_id into frame */ cf->can_id = msg_head->can_id; } } /* tx_ops never compare with previous received messages */ op->last_frames = NULL; /* bcm_can_tx / bcm_tx_timeout_handler needs this */ op->sk = sk; op->ifindex = ifindex; /* initialize uninitialized (kzalloc) structure */ hrtimer_init(&op->timer, CLOCK_MONOTONIC, HRTIMER_MODE_REL_SOFT); op->timer.function = bcm_tx_timeout_handler; /* currently unused in tx_ops */ hrtimer_init(&op->thrtimer, CLOCK_MONOTONIC, HRTIMER_MODE_REL_SOFT); /* add this bcm_op to the list of the tx_ops */ list_add(&op->list, &bo->tx_ops); } /* if ((op = bcm_find_op(&bo->tx_ops, msg_head->can_id, ifindex))) */ if (op->nframes != msg_head->nframes) { op->nframes = msg_head->nframes; /* start multiple frame transmission with index 0 */ op->currframe = 0; } /* check flags */ if (op->flags & TX_RESET_MULTI_IDX) { /* start multiple frame transmission with index 0 */ op->currframe = 0; } if (op->flags & SETTIMER) { /* set timer values */ op->count = msg_head->count; op->ival1 = msg_head->ival1; op->ival2 = msg_head->ival2; op->kt_ival1 = bcm_timeval_to_ktime(msg_head->ival1); op->kt_ival2 = bcm_timeval_to_ktime(msg_head->ival2); /* disable an active timer due to zero values? */ if (!op->kt_ival1 && !op->kt_ival2) hrtimer_cancel(&op->timer); } if (op->flags & STARTTIMER) { hrtimer_cancel(&op->timer); /* spec: send CAN frame when starting timer */ op->flags |= TX_ANNOUNCE; } if (op->flags & TX_ANNOUNCE) { bcm_can_tx(op); if (op->count) op->count--; } if (op->flags & STARTTIMER) bcm_tx_start_timer(op); return msg_head->nframes * op->cfsiz + MHSIZ; free_op: if (op->frames != &op->sframe) kfree(op->frames); kfree(op); return err; } /* * bcm_rx_setup - create or update a bcm rx op (for bcm_sendmsg) */ static int bcm_rx_setup(struct bcm_msg_head *msg_head, struct msghdr *msg, int ifindex, struct sock *sk) { struct bcm_sock *bo = bcm_sk(sk); struct bcm_op *op; int do_rx_register; int err = 0; if ((msg_head->flags & RX_FILTER_ID) || (!(msg_head->nframes))) { /* be robust against wrong usage ... */ msg_head->flags |= RX_FILTER_ID; /* ignore trailing garbage */ msg_head->nframes = 0; } /* the first element contains the mux-mask => MAX_NFRAMES + 1 */ if (msg_head->nframes > MAX_NFRAMES + 1) return -EINVAL; if ((msg_head->flags & RX_RTR_FRAME) && ((msg_head->nframes != 1) || (!(msg_head->can_id & CAN_RTR_FLAG)))) return -EINVAL; /* check timeval limitations */ if ((msg_head->flags & SETTIMER) && bcm_is_invalid_tv(msg_head)) return -EINVAL; /* check the given can_id */ op = bcm_find_op(&bo->rx_ops, msg_head, ifindex); if (op) { /* update existing BCM operation */ /* * Do we need more space for the CAN frames than currently * allocated? -> This is a _really_ unusual use-case and * therefore (complexity / locking) it is not supported. */ if (msg_head->nframes > op->nframes) return -E2BIG; if (msg_head->nframes) { /* update CAN frames content */ err = memcpy_from_msg(op->frames, msg, msg_head->nframes * op->cfsiz); if (err < 0) return err; /* clear last_frames to indicate 'nothing received' */ memset(op->last_frames, 0, msg_head->nframes * op->cfsiz); } op->nframes = msg_head->nframes; op->flags = msg_head->flags; /* Only an update -> do not call can_rx_register() */ do_rx_register = 0; } else { /* insert new BCM operation for the given can_id */ op = kzalloc(OPSIZ, GFP_KERNEL); if (!op) return -ENOMEM; op->can_id = msg_head->can_id; op->nframes = msg_head->nframes; op->cfsiz = CFSIZ(msg_head->flags); op->flags = msg_head->flags; if (msg_head->nframes > 1) { /* create array for CAN frames and copy the data */ op->frames = kmalloc_array(msg_head->nframes, op->cfsiz, GFP_KERNEL); if (!op->frames) { kfree(op); return -ENOMEM; } /* create and init array for received CAN frames */ op->last_frames = kcalloc(msg_head->nframes, op->cfsiz, GFP_KERNEL); if (!op->last_frames) { kfree(op->frames); kfree(op); return -ENOMEM; } } else { op->frames = &op->sframe; op->last_frames = &op->last_sframe; } if (msg_head->nframes) { err = memcpy_from_msg(op->frames, msg, msg_head->nframes * op->cfsiz); if (err < 0) { if (op->frames != &op->sframe) kfree(op->frames); if (op->last_frames != &op->last_sframe) kfree(op->last_frames); kfree(op); return err; } } /* bcm_can_tx / bcm_tx_timeout_handler needs this */ op->sk = sk; op->ifindex = ifindex; /* ifindex for timeout events w/o previous frame reception */ op->rx_ifindex = ifindex; /* initialize uninitialized (kzalloc) structure */ hrtimer_init(&op->timer, CLOCK_MONOTONIC, HRTIMER_MODE_REL_SOFT); op->timer.function = bcm_rx_timeout_handler; hrtimer_init(&op->thrtimer, CLOCK_MONOTONIC, HRTIMER_MODE_REL_SOFT); op->thrtimer.function = bcm_rx_thr_handler; /* add this bcm_op to the list of the rx_ops */ list_add(&op->list, &bo->rx_ops); /* call can_rx_register() */ do_rx_register = 1; } /* if ((op = bcm_find_op(&bo->rx_ops, msg_head->can_id, ifindex))) */ /* check flags */ if (op->flags & RX_RTR_FRAME) { struct canfd_frame *frame0 = op->frames; /* no timers in RTR-mode */ hrtimer_cancel(&op->thrtimer); hrtimer_cancel(&op->timer); /* * funny feature in RX(!)_SETUP only for RTR-mode: * copy can_id into frame BUT without RTR-flag to * prevent a full-load-loopback-test ... ;-] */ if ((op->flags & TX_CP_CAN_ID) || (frame0->can_id == op->can_id)) frame0->can_id = op->can_id & ~CAN_RTR_FLAG; } else { if (op->flags & SETTIMER) { /* set timer value */ op->ival1 = msg_head->ival1; op->ival2 = msg_head->ival2; op->kt_ival1 = bcm_timeval_to_ktime(msg_head->ival1); op->kt_ival2 = bcm_timeval_to_ktime(msg_head->ival2); /* disable an active timer due to zero value? */ if (!op->kt_ival1) hrtimer_cancel(&op->timer); /* * In any case cancel the throttle timer, flush * potentially blocked msgs and reset throttle handling */ op->kt_lastmsg = 0; hrtimer_cancel(&op->thrtimer); bcm_rx_thr_flush(op); } if ((op->flags & STARTTIMER) && op->kt_ival1) hrtimer_start(&op->timer, op->kt_ival1, HRTIMER_MODE_REL_SOFT); } /* now we can register for can_ids, if we added a new bcm_op */ if (do_rx_register) { if (ifindex) { struct net_device *dev; dev = dev_get_by_index(sock_net(sk), ifindex); if (dev) { err = can_rx_register(sock_net(sk), dev, op->can_id, REGMASK(op->can_id), bcm_rx_handler, op, "bcm", sk); op->rx_reg_dev = dev; dev_put(dev); } } else err = can_rx_register(sock_net(sk), NULL, op->can_id, REGMASK(op->can_id), bcm_rx_handler, op, "bcm", sk); if (err) { /* this bcm rx op is broken -> remove it */ list_del(&op->list); bcm_remove_op(op); return err; } } return msg_head->nframes * op->cfsiz + MHSIZ; } /* * bcm_tx_send - send a single CAN frame to the CAN interface (for bcm_sendmsg) */ static int bcm_tx_send(struct msghdr *msg, int ifindex, struct sock *sk, int cfsiz) { struct sk_buff *skb; struct net_device *dev; int err; /* we need a real device to send frames */ if (!ifindex) return -ENODEV; skb = alloc_skb(cfsiz + sizeof(struct can_skb_priv), GFP_KERNEL); if (!skb) return -ENOMEM; can_skb_reserve(skb); err = memcpy_from_msg(skb_put(skb, cfsiz), msg, cfsiz); if (err < 0) { kfree_skb(skb); return err; } dev = dev_get_by_index(sock_net(sk), ifindex); if (!dev) { kfree_skb(skb); return -ENODEV; } can_skb_prv(skb)->ifindex = dev->ifindex; can_skb_prv(skb)->skbcnt = 0; skb->dev = dev; can_skb_set_owner(skb, sk); err = can_send(skb, 1); /* send with loopback */ dev_put(dev); if (err) return err; return cfsiz + MHSIZ; } /* * bcm_sendmsg - process BCM commands (opcodes) from the userspace */ static int bcm_sendmsg(struct socket *sock, struct msghdr *msg, size_t size) { struct sock *sk = sock->sk; struct bcm_sock *bo = bcm_sk(sk); int ifindex = bo->ifindex; /* default ifindex for this bcm_op */ struct bcm_msg_head msg_head; int cfsiz; int ret; /* read bytes or error codes as return value */ if (!bo->bound) return -ENOTCONN; /* check for valid message length from userspace */ if (size < MHSIZ) return -EINVAL; /* read message head information */ ret = memcpy_from_msg((u8 *)&msg_head, msg, MHSIZ); if (ret < 0) return ret; cfsiz = CFSIZ(msg_head.flags); if ((size - MHSIZ) % cfsiz) return -EINVAL; /* check for alternative ifindex for this bcm_op */ if (!ifindex && msg->msg_name) { /* no bound device as default => check msg_name */ DECLARE_SOCKADDR(struct sockaddr_can *, addr, msg->msg_name); if (msg->msg_namelen < BCM_MIN_NAMELEN) return -EINVAL; if (addr->can_family != AF_CAN) return -EINVAL; /* ifindex from sendto() */ ifindex = addr->can_ifindex; if (ifindex) { struct net_device *dev; dev = dev_get_by_index(sock_net(sk), ifindex); if (!dev) return -ENODEV; if (dev->type != ARPHRD_CAN) { dev_put(dev); return -ENODEV; } dev_put(dev); } } lock_sock(sk); switch (msg_head.opcode) { case TX_SETUP: ret = bcm_tx_setup(&msg_head, msg, ifindex, sk); break; case RX_SETUP: ret = bcm_rx_setup(&msg_head, msg, ifindex, sk); break; case TX_DELETE: if (bcm_delete_tx_op(&bo->tx_ops, &msg_head, ifindex)) ret = MHSIZ; else ret = -EINVAL; break; case RX_DELETE: if (bcm_delete_rx_op(&bo->rx_ops, &msg_head, ifindex)) ret = MHSIZ; else ret = -EINVAL; break; case TX_READ: /* reuse msg_head for the reply to TX_READ */ msg_head.opcode = TX_STATUS; ret = bcm_read_op(&bo->tx_ops, &msg_head, ifindex); break; case RX_READ: /* reuse msg_head for the reply to RX_READ */ msg_head.opcode = RX_STATUS; ret = bcm_read_op(&bo->rx_ops, &msg_head, ifindex); break; case TX_SEND: /* we need exactly one CAN frame behind the msg head */ if ((msg_head.nframes != 1) || (size != cfsiz + MHSIZ)) ret = -EINVAL; else ret = bcm_tx_send(msg, ifindex, sk, cfsiz); break; default: ret = -EINVAL; break; } release_sock(sk); return ret; } /* * notification handler for netdevice status changes */ static void bcm_notify(struct bcm_sock *bo, unsigned long msg, struct net_device *dev) { struct sock *sk = &bo->sk; struct bcm_op *op; int notify_enodev = 0; if (!net_eq(dev_net(dev), sock_net(sk))) return; switch (msg) { case NETDEV_UNREGISTER: lock_sock(sk); /* remove device specific receive entries */ list_for_each_entry(op, &bo->rx_ops, list) if (op->rx_reg_dev == dev) bcm_rx_unreg(dev, op); /* remove device reference, if this is our bound device */ if (bo->bound && bo->ifindex == dev->ifindex) { #if IS_ENABLED(CONFIG_PROC_FS) if (sock_net(sk)->can.bcmproc_dir && bo->bcm_proc_read) { remove_proc_entry(bo->procname, sock_net(sk)->can.bcmproc_dir); bo->bcm_proc_read = NULL; } #endif bo->bound = 0; bo->ifindex = 0; notify_enodev = 1; } release_sock(sk); if (notify_enodev) { sk->sk_err = ENODEV; if (!sock_flag(sk, SOCK_DEAD)) sk_error_report(sk); } break; case NETDEV_DOWN: if (bo->bound && bo->ifindex == dev->ifindex) { sk->sk_err = ENETDOWN; if (!sock_flag(sk, SOCK_DEAD)) sk_error_report(sk); } } } static int bcm_notifier(struct notifier_block *nb, unsigned long msg, void *ptr) { struct net_device *dev = netdev_notifier_info_to_dev(ptr); if (dev->type != ARPHRD_CAN) return NOTIFY_DONE; if (msg != NETDEV_UNREGISTER && msg != NETDEV_DOWN) return NOTIFY_DONE; if (unlikely(bcm_busy_notifier)) /* Check for reentrant bug. */ return NOTIFY_DONE; spin_lock(&bcm_notifier_lock); list_for_each_entry(bcm_busy_notifier, &bcm_notifier_list, notifier) { spin_unlock(&bcm_notifier_lock); bcm_notify(bcm_busy_notifier, msg, dev); spin_lock(&bcm_notifier_lock); } bcm_busy_notifier = NULL; spin_unlock(&bcm_notifier_lock); return NOTIFY_DONE; } /* * initial settings for all BCM sockets to be set at socket creation time */ static int bcm_init(struct sock *sk) { struct bcm_sock *bo = bcm_sk(sk); bo->bound = 0; bo->ifindex = 0; bo->dropped_usr_msgs = 0; bo->bcm_proc_read = NULL; INIT_LIST_HEAD(&bo->tx_ops); INIT_LIST_HEAD(&bo->rx_ops); /* set notifier */ spin_lock(&bcm_notifier_lock); list_add_tail(&bo->notifier, &bcm_notifier_list); spin_unlock(&bcm_notifier_lock); return 0; } /* * standard socket functions */ static int bcm_release(struct socket *sock) { struct sock *sk = sock->sk; struct net *net; struct bcm_sock *bo; struct bcm_op *op, *next; if (!sk) return 0; net = sock_net(sk); bo = bcm_sk(sk); /* remove bcm_ops, timer, rx_unregister(), etc. */ spin_lock(&bcm_notifier_lock); while (bcm_busy_notifier == bo) { spin_unlock(&bcm_notifier_lock); schedule_timeout_uninterruptible(1); spin_lock(&bcm_notifier_lock); } list_del(&bo->notifier); spin_unlock(&bcm_notifier_lock); lock_sock(sk); #if IS_ENABLED(CONFIG_PROC_FS) /* remove procfs entry */ if (net->can.bcmproc_dir && bo->bcm_proc_read) remove_proc_entry(bo->procname, net->can.bcmproc_dir); #endif /* CONFIG_PROC_FS */ list_for_each_entry_safe(op, next, &bo->tx_ops, list) bcm_remove_op(op); list_for_each_entry_safe(op, next, &bo->rx_ops, list) { /* * Don't care if we're bound or not (due to netdev problems) * can_rx_unregister() is always a save thing to do here. */ if (op->ifindex) { /* * Only remove subscriptions that had not * been removed due to NETDEV_UNREGISTER * in bcm_notifier() */ if (op->rx_reg_dev) { struct net_device *dev; dev = dev_get_by_index(net, op->ifindex); if (dev) { bcm_rx_unreg(dev, op); dev_put(dev); } } } else can_rx_unregister(net, NULL, op->can_id, REGMASK(op->can_id), bcm_rx_handler, op); } synchronize_rcu(); list_for_each_entry_safe(op, next, &bo->rx_ops, list) bcm_remove_op(op); /* remove device reference */ if (bo->bound) { bo->bound = 0; bo->ifindex = 0; } sock_orphan(sk); sock->sk = NULL; release_sock(sk); sock_put(sk); return 0; } static int bcm_connect(struct socket *sock, struct sockaddr *uaddr, int len, int flags) { struct sockaddr_can *addr = (struct sockaddr_can *)uaddr; struct sock *sk = sock->sk; struct bcm_sock *bo = bcm_sk(sk); struct net *net = sock_net(sk); int ret = 0; if (len < BCM_MIN_NAMELEN) return -EINVAL; lock_sock(sk); if (bo->bound) { ret = -EISCONN; goto fail; } /* bind a device to this socket */ if (addr->can_ifindex) { struct net_device *dev; dev = dev_get_by_index(net, addr->can_ifindex); if (!dev) { ret = -ENODEV; goto fail; } if (dev->type != ARPHRD_CAN) { dev_put(dev); ret = -ENODEV; goto fail; } bo->ifindex = dev->ifindex; dev_put(dev); } else { /* no interface reference for ifindex = 0 ('any' CAN device) */ bo->ifindex = 0; } #if IS_ENABLED(CONFIG_PROC_FS) if (net->can.bcmproc_dir) { /* unique socket address as filename */ sprintf(bo->procname, "%lu", sock_i_ino(sk)); bo->bcm_proc_read = proc_create_net_single(bo->procname, 0644, net->can.bcmproc_dir, bcm_proc_show, sk); if (!bo->bcm_proc_read) { ret = -ENOMEM; goto fail; } } #endif /* CONFIG_PROC_FS */ bo->bound = 1; fail: release_sock(sk); return ret; } static int bcm_recvmsg(struct socket *sock, struct msghdr *msg, size_t size, int flags) { struct sock *sk = sock->sk; struct sk_buff *skb; int error = 0; int err; skb = skb_recv_datagram(sk, flags, &error); if (!skb) return error; if (skb->len < size) size = skb->len; err = memcpy_to_msg(msg, skb->data, size); if (err < 0) { skb_free_datagram(sk, skb); return err; } sock_recv_cmsgs(msg, sk, skb); if (msg->msg_name) { __sockaddr_check_size(BCM_MIN_NAMELEN); msg->msg_namelen = BCM_MIN_NAMELEN; memcpy(msg->msg_name, skb->cb, msg->msg_namelen); } /* assign the flags that have been recorded in bcm_send_to_user() */ msg->msg_flags |= *(bcm_flags(skb)); skb_free_datagram(sk, skb); return size; } static int bcm_sock_no_ioctlcmd(struct socket *sock, unsigned int cmd, unsigned long arg) { /* no ioctls for socket layer -> hand it down to NIC layer */ return -ENOIOCTLCMD; } static const struct proto_ops bcm_ops = { .family = PF_CAN, .release = bcm_release, .bind = sock_no_bind, .connect = bcm_connect, .socketpair = sock_no_socketpair, .accept = sock_no_accept, .getname = sock_no_getname, .poll = datagram_poll, .ioctl = bcm_sock_no_ioctlcmd, .gettstamp = sock_gettstamp, .listen = sock_no_listen, .shutdown = sock_no_shutdown, .sendmsg = bcm_sendmsg, .recvmsg = bcm_recvmsg, .mmap = sock_no_mmap, }; static struct proto bcm_proto __read_mostly = { .name = "CAN_BCM", .owner = THIS_MODULE, .obj_size = sizeof(struct bcm_sock), .init = bcm_init, }; static const struct can_proto bcm_can_proto = { .type = SOCK_DGRAM, .protocol = CAN_BCM, .ops = &bcm_ops, .prot = &bcm_proto, }; static int canbcm_pernet_init(struct net *net) { #if IS_ENABLED(CONFIG_PROC_FS) /* create /proc/net/can-bcm directory */ net->can.bcmproc_dir = proc_net_mkdir(net, "can-bcm", net->proc_net); #endif /* CONFIG_PROC_FS */ return 0; } static void canbcm_pernet_exit(struct net *net) { #if IS_ENABLED(CONFIG_PROC_FS) /* remove /proc/net/can-bcm directory */ if (net->can.bcmproc_dir) remove_proc_entry("can-bcm", net->proc_net); #endif /* CONFIG_PROC_FS */ } static struct pernet_operations canbcm_pernet_ops __read_mostly = { .init = canbcm_pernet_init, .exit = canbcm_pernet_exit, }; static struct notifier_block canbcm_notifier = { .notifier_call = bcm_notifier }; static int __init bcm_module_init(void) { int err; pr_info("can: broadcast manager protocol\n"); err = register_pernet_subsys(&canbcm_pernet_ops); if (err) return err; err = register_netdevice_notifier(&canbcm_notifier); if (err) goto register_notifier_failed; err = can_proto_register(&bcm_can_proto); if (err < 0) { printk(KERN_ERR "can: registration of bcm protocol failed\n"); goto register_proto_failed; } return 0; register_proto_failed: unregister_netdevice_notifier(&canbcm_notifier); register_notifier_failed: unregister_pernet_subsys(&canbcm_pernet_ops); return err; } static void __exit bcm_module_exit(void) { can_proto_unregister(&bcm_can_proto); unregister_netdevice_notifier(&canbcm_notifier); unregister_pernet_subsys(&canbcm_pernet_ops); } module_init(bcm_module_init); module_exit(bcm_module_exit); |
| 53 53 53 53 54 54 3 53 54 54 54 54 54 53 3 53 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 | // SPDX-License-Identifier: GPL-2.0-only #include <linux/stat.h> #include <linux/sysctl.h> #include <linux/slab.h> #include <linux/cred.h> #include <linux/hash.h> #include <linux/kmemleak.h> #include <linux/user_namespace.h> struct ucounts init_ucounts = { .ns = &init_user_ns, .uid = GLOBAL_ROOT_UID, .count = ATOMIC_INIT(1), }; #define UCOUNTS_HASHTABLE_BITS 10 static struct hlist_head ucounts_hashtable[(1 << UCOUNTS_HASHTABLE_BITS)]; static DEFINE_SPINLOCK(ucounts_lock); #define ucounts_hashfn(ns, uid) \ hash_long((unsigned long)__kuid_val(uid) + (unsigned long)(ns), \ UCOUNTS_HASHTABLE_BITS) #define ucounts_hashentry(ns, uid) \ (ucounts_hashtable + ucounts_hashfn(ns, uid)) #ifdef CONFIG_SYSCTL static struct ctl_table_set * set_lookup(struct ctl_table_root *root) { return ¤t_user_ns()->set; } static int set_is_seen(struct ctl_table_set *set) { return ¤t_user_ns()->set == set; } static int set_permissions(struct ctl_table_header *head, const struct ctl_table *table) { struct user_namespace *user_ns = container_of(head->set, struct user_namespace, set); int mode; /* Allow users with CAP_SYS_RESOURCE unrestrained access */ if (ns_capable(user_ns, CAP_SYS_RESOURCE)) mode = (table->mode & S_IRWXU) >> 6; else /* Allow all others at most read-only access */ mode = table->mode & S_IROTH; return (mode << 6) | (mode << 3) | mode; } static struct ctl_table_root set_root = { .lookup = set_lookup, .permissions = set_permissions, }; static long ue_zero = 0; static long ue_int_max = INT_MAX; #define UCOUNT_ENTRY(name) \ { \ .procname = name, \ .maxlen = sizeof(long), \ .mode = 0644, \ .proc_handler = proc_doulongvec_minmax, \ .extra1 = &ue_zero, \ .extra2 = &ue_int_max, \ } static const struct ctl_table user_table[] = { UCOUNT_ENTRY("max_user_namespaces"), UCOUNT_ENTRY("max_pid_namespaces"), UCOUNT_ENTRY("max_uts_namespaces"), UCOUNT_ENTRY("max_ipc_namespaces"), UCOUNT_ENTRY("max_net_namespaces"), UCOUNT_ENTRY("max_mnt_namespaces"), UCOUNT_ENTRY("max_cgroup_namespaces"), UCOUNT_ENTRY("max_time_namespaces"), #ifdef CONFIG_INOTIFY_USER UCOUNT_ENTRY("max_inotify_instances"), UCOUNT_ENTRY("max_inotify_watches"), #endif #ifdef CONFIG_FANOTIFY UCOUNT_ENTRY("max_fanotify_groups"), UCOUNT_ENTRY("max_fanotify_marks"), #endif }; #endif /* CONFIG_SYSCTL */ bool setup_userns_sysctls(struct user_namespace *ns) { #ifdef CONFIG_SYSCTL struct ctl_table *tbl; BUILD_BUG_ON(ARRAY_SIZE(user_table) != UCOUNT_COUNTS); setup_sysctl_set(&ns->set, &set_root, set_is_seen); tbl = kmemdup(user_table, sizeof(user_table), GFP_KERNEL); if (tbl) { int i; for (i = 0; i < UCOUNT_COUNTS; i++) { tbl[i].data = &ns->ucount_max[i]; } ns->sysctls = __register_sysctl_table(&ns->set, "user", tbl, ARRAY_SIZE(user_table)); } if (!ns->sysctls) { kfree(tbl); retire_sysctl_set(&ns->set); return false; } #endif return true; } void retire_userns_sysctls(struct user_namespace *ns) { #ifdef CONFIG_SYSCTL const struct ctl_table *tbl; tbl = ns->sysctls->ctl_table_arg; unregister_sysctl_table(ns->sysctls); retire_sysctl_set(&ns->set); kfree(tbl); #endif } static struct ucounts *find_ucounts(struct user_namespace *ns, kuid_t uid, struct hlist_head *hashent) { struct ucounts *ucounts; hlist_for_each_entry(ucounts, hashent, node) { if (uid_eq(ucounts->uid, uid) && (ucounts->ns == ns)) return ucounts; } return NULL; } static void hlist_add_ucounts(struct ucounts *ucounts) { struct hlist_head *hashent = ucounts_hashentry(ucounts->ns, ucounts->uid); spin_lock_irq(&ucounts_lock); hlist_add_head(&ucounts->node, hashent); spin_unlock_irq(&ucounts_lock); } static inline bool get_ucounts_or_wrap(struct ucounts *ucounts) { /* Returns true on a successful get, false if the count wraps. */ return !atomic_add_negative(1, &ucounts->count); } struct ucounts *get_ucounts(struct ucounts *ucounts) { if (!get_ucounts_or_wrap(ucounts)) { put_ucounts(ucounts); ucounts = NULL; } return ucounts; } struct ucounts *alloc_ucounts(struct user_namespace *ns, kuid_t uid) { struct hlist_head *hashent = ucounts_hashentry(ns, uid); struct ucounts *ucounts, *new; bool wrapped; spin_lock_irq(&ucounts_lock); ucounts = find_ucounts(ns, uid, hashent); if (!ucounts) { spin_unlock_irq(&ucounts_lock); new = kzalloc(sizeof(*new), GFP_KERNEL); if (!new) return NULL; new->ns = ns; new->uid = uid; atomic_set(&new->count, 1); spin_lock_irq(&ucounts_lock); ucounts = find_ucounts(ns, uid, hashent); if (ucounts) { kfree(new); } else { hlist_add_head(&new->node, hashent); get_user_ns(new->ns); spin_unlock_irq(&ucounts_lock); return new; } } wrapped = !get_ucounts_or_wrap(ucounts); spin_unlock_irq(&ucounts_lock); if (wrapped) { put_ucounts(ucounts); return NULL; } return ucounts; } void put_ucounts(struct ucounts *ucounts) { unsigned long flags; if (atomic_dec_and_lock_irqsave(&ucounts->count, &ucounts_lock, flags)) { hlist_del_init(&ucounts->node); spin_unlock_irqrestore(&ucounts_lock, flags); put_user_ns(ucounts->ns); kfree(ucounts); } } static inline bool atomic_long_inc_below(atomic_long_t *v, int u) { long c, old; c = atomic_long_read(v); for (;;) { if (unlikely(c >= u)) return false; old = atomic_long_cmpxchg(v, c, c+1); if (likely(old == c)) return true; c = old; } } struct ucounts *inc_ucount(struct user_namespace *ns, kuid_t uid, enum ucount_type type) { struct ucounts *ucounts, *iter, *bad; struct user_namespace *tns; ucounts = alloc_ucounts(ns, uid); for (iter = ucounts; iter; iter = tns->ucounts) { long max; tns = iter->ns; max = READ_ONCE(tns->ucount_max[type]); if (!atomic_long_inc_below(&iter->ucount[type], max)) goto fail; } return ucounts; fail: bad = iter; for (iter = ucounts; iter != bad; iter = iter->ns->ucounts) atomic_long_dec(&iter->ucount[type]); put_ucounts(ucounts); return NULL; } void dec_ucount(struct ucounts *ucounts, enum ucount_type type) { struct ucounts *iter; for (iter = ucounts; iter; iter = iter->ns->ucounts) { long dec = atomic_long_dec_if_positive(&iter->ucount[type]); WARN_ON_ONCE(dec < 0); } put_ucounts(ucounts); } long inc_rlimit_ucounts(struct ucounts *ucounts, enum rlimit_type type, long v) { struct ucounts *iter; long max = LONG_MAX; long ret = 0; for (iter = ucounts; iter; iter = iter->ns->ucounts) { long new = atomic_long_add_return(v, &iter->rlimit[type]); if (new < 0 || new > max) ret = LONG_MAX; else if (iter == ucounts) ret = new; max = get_userns_rlimit_max(iter->ns, type); } return ret; } bool dec_rlimit_ucounts(struct ucounts *ucounts, enum rlimit_type type, long v) { struct ucounts *iter; long new = -1; /* Silence compiler warning */ for (iter = ucounts; iter; iter = iter->ns->ucounts) { long dec = atomic_long_sub_return(v, &iter->rlimit[type]); WARN_ON_ONCE(dec < 0); if (iter == ucounts) new = dec; } return (new == 0); } static void do_dec_rlimit_put_ucounts(struct ucounts *ucounts, struct ucounts *last, enum rlimit_type type) { struct ucounts *iter, *next; for (iter = ucounts; iter != last; iter = next) { long dec = atomic_long_sub_return(1, &iter->rlimit[type]); WARN_ON_ONCE(dec < 0); next = iter->ns->ucounts; if (dec == 0) put_ucounts(iter); } } void dec_rlimit_put_ucounts(struct ucounts *ucounts, enum rlimit_type type) { do_dec_rlimit_put_ucounts(ucounts, NULL, type); } long inc_rlimit_get_ucounts(struct ucounts *ucounts, enum rlimit_type type, bool override_rlimit) { /* Caller must hold a reference to ucounts */ struct ucounts *iter; long max = LONG_MAX; long dec, ret = 0; for (iter = ucounts; iter; iter = iter->ns->ucounts) { long new = atomic_long_add_return(1, &iter->rlimit[type]); if (new < 0 || new > max) goto dec_unwind; if (iter == ucounts) ret = new; if (!override_rlimit) max = get_userns_rlimit_max(iter->ns, type); /* * Grab an extra ucount reference for the caller when * the rlimit count was previously 0. */ if (new != 1) continue; if (!get_ucounts(iter)) goto dec_unwind; } return ret; dec_unwind: dec = atomic_long_sub_return(1, &iter->rlimit[type]); WARN_ON_ONCE(dec < 0); do_dec_rlimit_put_ucounts(ucounts, iter, type); return 0; } bool is_rlimit_overlimit(struct ucounts *ucounts, enum rlimit_type type, unsigned long rlimit) { struct ucounts *iter; long max = rlimit; if (rlimit > LONG_MAX) max = LONG_MAX; for (iter = ucounts; iter; iter = iter->ns->ucounts) { long val = get_rlimit_value(iter, type); if (val < 0 || val > max) return true; max = get_userns_rlimit_max(iter->ns, type); } return false; } static __init int user_namespace_sysctl_init(void) { #ifdef CONFIG_SYSCTL static struct ctl_table_header *user_header; static struct ctl_table empty[1]; /* * It is necessary to register the user directory in the * default set so that registrations in the child sets work * properly. */ user_header = register_sysctl_sz("user", empty, 0); kmemleak_ignore(user_header); BUG_ON(!user_header); BUG_ON(!setup_userns_sysctls(&init_user_ns)); #endif hlist_add_ucounts(&init_ucounts); inc_rlimit_ucounts(&init_ucounts, UCOUNT_RLIMIT_NPROC, 1); return 0; } subsys_initcall(user_namespace_sysctl_init); |
| 29 281 281 1 1 361 361 362 362 265 220 221 218 221 217 218 4 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _LINUX_PAGE_REF_H #define _LINUX_PAGE_REF_H #include <linux/atomic.h> #include <linux/mm_types.h> #include <linux/page-flags.h> #include <linux/tracepoint-defs.h> DECLARE_TRACEPOINT(page_ref_set); DECLARE_TRACEPOINT(page_ref_mod); DECLARE_TRACEPOINT(page_ref_mod_and_test); DECLARE_TRACEPOINT(page_ref_mod_and_return); DECLARE_TRACEPOINT(page_ref_mod_unless); DECLARE_TRACEPOINT(page_ref_freeze); DECLARE_TRACEPOINT(page_ref_unfreeze); #ifdef CONFIG_DEBUG_PAGE_REF /* * Ideally we would want to use the trace_<tracepoint>_enabled() helper * functions. But due to include header file issues, that is not * feasible. Instead we have to open code the static key functions. * * See trace_##name##_enabled(void) in include/linux/tracepoint.h */ #define page_ref_tracepoint_active(t) tracepoint_enabled(t) extern void __page_ref_set(struct page *page, int v); extern void __page_ref_mod(struct page *page, int v); extern void __page_ref_mod_and_test(struct page *page, int v, int ret); extern void __page_ref_mod_and_return(struct page *page, int v, int ret); extern void __page_ref_mod_unless(struct page *page, int v, int u); extern void __page_ref_freeze(struct page *page, int v, int ret); extern void __page_ref_unfreeze(struct page *page, int v); #else #define page_ref_tracepoint_active(t) false static inline void __page_ref_set(struct page *page, int v) { } static inline void __page_ref_mod(struct page *page, int v) { } static inline void __page_ref_mod_and_test(struct page *page, int v, int ret) { } static inline void __page_ref_mod_and_return(struct page *page, int v, int ret) { } static inline void __page_ref_mod_unless(struct page *page, int v, int u) { } static inline void __page_ref_freeze(struct page *page, int v, int ret) { } static inline void __page_ref_unfreeze(struct page *page, int v) { } #endif static inline int page_ref_count(const struct page *page) { return atomic_read(&page->_refcount); } /** * folio_ref_count - The reference count on this folio. * @folio: The folio. * * The refcount is usually incremented by calls to folio_get() and * decremented by calls to folio_put(). Some typical users of the * folio refcount: * * - Each reference from a page table * - The page cache * - Filesystem private data * - The LRU list * - Pipes * - Direct IO which references this page in the process address space * * Return: The number of references to this folio. */ static inline int folio_ref_count(const struct folio *folio) { return page_ref_count(&folio->page); } static inline int page_count(const struct page *page) { return folio_ref_count(page_folio(page)); } static inline void set_page_count(struct page *page, int v) { atomic_set(&page->_refcount, v); if (page_ref_tracepoint_active(page_ref_set)) __page_ref_set(page, v); } static inline void folio_set_count(struct folio *folio, int v) { set_page_count(&folio->page, v); } /* * Setup the page count before being freed into the page allocator for * the first time (boot or memory hotplug) */ static inline void init_page_count(struct page *page) { set_page_count(page, 1); } static inline void page_ref_add(struct page *page, int nr) { atomic_add(nr, &page->_refcount); if (page_ref_tracepoint_active(page_ref_mod)) __page_ref_mod(page, nr); } static inline void folio_ref_add(struct folio *folio, int nr) { page_ref_add(&folio->page, nr); } static inline void page_ref_sub(struct page *page, int nr) { atomic_sub(nr, &page->_refcount); if (page_ref_tracepoint_active(page_ref_mod)) __page_ref_mod(page, -nr); } static inline void folio_ref_sub(struct folio *folio, int nr) { page_ref_sub(&folio->page, nr); } static inline int folio_ref_sub_return(struct folio *folio, int nr) { int ret = atomic_sub_return(nr, &folio->_refcount); if (page_ref_tracepoint_active(page_ref_mod_and_return)) __page_ref_mod_and_return(&folio->page, -nr, ret); return ret; } static inline void page_ref_inc(struct page *page) { atomic_inc(&page->_refcount); if (page_ref_tracepoint_active(page_ref_mod)) __page_ref_mod(page, 1); } static inline void folio_ref_inc(struct folio *folio) { page_ref_inc(&folio->page); } static inline void page_ref_dec(struct page *page) { atomic_dec(&page->_refcount); if (page_ref_tracepoint_active(page_ref_mod)) __page_ref_mod(page, -1); } static inline void folio_ref_dec(struct folio *folio) { page_ref_dec(&folio->page); } static inline int page_ref_sub_and_test(struct page *page, int nr) { int ret = atomic_sub_and_test(nr, &page->_refcount); if (page_ref_tracepoint_active(page_ref_mod_and_test)) __page_ref_mod_and_test(page, -nr, ret); return ret; } static inline int folio_ref_sub_and_test(struct folio *folio, int nr) { return page_ref_sub_and_test(&folio->page, nr); } static inline int page_ref_inc_return(struct page *page) { int ret = atomic_inc_return(&page->_refcount); if (page_ref_tracepoint_active(page_ref_mod_and_return)) __page_ref_mod_and_return(page, 1, ret); return ret; } static inline int folio_ref_inc_return(struct folio *folio) { return page_ref_inc_return(&folio->page); } static inline int page_ref_dec_and_test(struct page *page) { int ret = atomic_dec_and_test(&page->_refcount); if (page_ref_tracepoint_active(page_ref_mod_and_test)) __page_ref_mod_and_test(page, -1, ret); return ret; } static inline int folio_ref_dec_and_test(struct folio *folio) { return page_ref_dec_and_test(&folio->page); } static inline int page_ref_dec_return(struct page *page) { int ret = atomic_dec_return(&page->_refcount); if (page_ref_tracepoint_active(page_ref_mod_and_return)) __page_ref_mod_and_return(page, -1, ret); return ret; } static inline int folio_ref_dec_return(struct folio *folio) { return page_ref_dec_return(&folio->page); } static inline bool page_ref_add_unless(struct page *page, int nr, int u) { bool ret = false; rcu_read_lock(); /* avoid writing to the vmemmap area being remapped */ if (!page_is_fake_head(page) && page_ref_count(page) != u) ret = atomic_add_unless(&page->_refcount, nr, u); rcu_read_unlock(); if (page_ref_tracepoint_active(page_ref_mod_unless)) __page_ref_mod_unless(page, nr, ret); return ret; } static inline bool folio_ref_add_unless(struct folio *folio, int nr, int u) { return page_ref_add_unless(&folio->page, nr, u); } /** * folio_try_get - Attempt to increase the refcount on a folio. * @folio: The folio. * * If you do not already have a reference to a folio, you can attempt to * get one using this function. It may fail if, for example, the folio * has been freed since you found a pointer to it, or it is frozen for * the purposes of splitting or migration. * * Return: True if the reference count was successfully incremented. */ static inline bool folio_try_get(struct folio *folio) { return folio_ref_add_unless(folio, 1, 0); } static inline bool folio_ref_try_add(struct folio *folio, int count) { return folio_ref_add_unless(folio, count, 0); } static inline int page_ref_freeze(struct page *page, int count) { int ret = likely(atomic_cmpxchg(&page->_refcount, count, 0) == count); if (page_ref_tracepoint_active(page_ref_freeze)) __page_ref_freeze(page, count, ret); return ret; } static inline int folio_ref_freeze(struct folio *folio, int count) { return page_ref_freeze(&folio->page, count); } static inline void page_ref_unfreeze(struct page *page, int count) { VM_BUG_ON_PAGE(page_count(page) != 0, page); VM_BUG_ON(count == 0); atomic_set_release(&page->_refcount, count); if (page_ref_tracepoint_active(page_ref_unfreeze)) __page_ref_unfreeze(page, count); } static inline void folio_ref_unfreeze(struct folio *folio, int count) { page_ref_unfreeze(&folio->page, count); } #endif |
| 874 874 176 874 874 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef __LINUX_CPUMASK_H #define __LINUX_CPUMASK_H /* * Cpumasks provide a bitmap suitable for representing the * set of CPUs in a system, one bit position per CPU number. In general, * only nr_cpu_ids (<= NR_CPUS) bits are valid. */ #include <linux/cleanup.h> #include <linux/kernel.h> #include <linux/bitmap.h> #include <linux/cpumask_types.h> #include <linux/atomic.h> #include <linux/bug.h> #include <linux/gfp_types.h> #include <linux/numa.h> /** * cpumask_pr_args - printf args to output a cpumask * @maskp: cpumask to be printed * * Can be used to provide arguments for '%*pb[l]' when printing a cpumask. */ #define cpumask_pr_args(maskp) nr_cpu_ids, cpumask_bits(maskp) #if (NR_CPUS == 1) || defined(CONFIG_FORCE_NR_CPUS) #define nr_cpu_ids ((unsigned int)NR_CPUS) #else extern unsigned int nr_cpu_ids; #endif static __always_inline void set_nr_cpu_ids(unsigned int nr) { #if (NR_CPUS == 1) || defined(CONFIG_FORCE_NR_CPUS) WARN_ON(nr != nr_cpu_ids); #else nr_cpu_ids = nr; #endif } /* * We have several different "preferred sizes" for the cpumask * operations, depending on operation. * * For example, the bitmap scanning and operating operations have * optimized routines that work for the single-word case, but only when * the size is constant. So if NR_CPUS fits in one single word, we are * better off using that small constant, in order to trigger the * optimized bit finding. That is 'small_cpumask_size'. * * The clearing and copying operations will similarly perform better * with a constant size, but we limit that size arbitrarily to four * words. We call this 'large_cpumask_size'. * * Finally, some operations just want the exact limit, either because * they set bits or just don't have any faster fixed-sized versions. We * call this just 'nr_cpumask_bits'. * * Note that these optional constants are always guaranteed to be at * least as big as 'nr_cpu_ids' itself is, and all our cpumask * allocations are at least that size (see cpumask_size()). The * optimization comes from being able to potentially use a compile-time * constant instead of a run-time generated exact number of CPUs. */ #if NR_CPUS <= BITS_PER_LONG #define small_cpumask_bits ((unsigned int)NR_CPUS) #define large_cpumask_bits ((unsigned int)NR_CPUS) #elif NR_CPUS <= 4*BITS_PER_LONG #define small_cpumask_bits nr_cpu_ids #define large_cpumask_bits ((unsigned int)NR_CPUS) #else #define small_cpumask_bits nr_cpu_ids #define large_cpumask_bits nr_cpu_ids #endif #define nr_cpumask_bits nr_cpu_ids /* * The following particular system cpumasks and operations manage * possible, present, active and online cpus. * * cpu_possible_mask- has bit 'cpu' set iff cpu is populatable * cpu_present_mask - has bit 'cpu' set iff cpu is populated * cpu_enabled_mask - has bit 'cpu' set iff cpu can be brought online * cpu_online_mask - has bit 'cpu' set iff cpu available to scheduler * cpu_active_mask - has bit 'cpu' set iff cpu available to migration * * If !CONFIG_HOTPLUG_CPU, present == possible, and active == online. * * The cpu_possible_mask is fixed at boot time, as the set of CPU IDs * that it is possible might ever be plugged in at anytime during the * life of that system boot. The cpu_present_mask is dynamic(*), * representing which CPUs are currently plugged in. And * cpu_online_mask is the dynamic subset of cpu_present_mask, * indicating those CPUs available for scheduling. * * If HOTPLUG is enabled, then cpu_present_mask varies dynamically, * depending on what ACPI reports as currently plugged in, otherwise * cpu_present_mask is just a copy of cpu_possible_mask. * * (*) Well, cpu_present_mask is dynamic in the hotplug case. If not * hotplug, it's a copy of cpu_possible_mask, hence fixed at boot. * * Subtleties: * 1) UP ARCHes (NR_CPUS == 1, CONFIG_SMP not defined) hardcode * assumption that their single CPU is online. The UP * cpu_{online,possible,present}_masks are placebos. Changing them * will have no useful affect on the following num_*_cpus() * and cpu_*() macros in the UP case. This ugliness is a UP * optimization - don't waste any instructions or memory references * asking if you're online or how many CPUs there are if there is * only one CPU. */ extern struct cpumask __cpu_possible_mask; extern struct cpumask __cpu_online_mask; extern struct cpumask __cpu_enabled_mask; extern struct cpumask __cpu_present_mask; extern struct cpumask __cpu_active_mask; extern struct cpumask __cpu_dying_mask; #define cpu_possible_mask ((const struct cpumask *)&__cpu_possible_mask) #define cpu_online_mask ((const struct cpumask *)&__cpu_online_mask) #define cpu_enabled_mask ((const struct cpumask *)&__cpu_enabled_mask) #define cpu_present_mask ((const struct cpumask *)&__cpu_present_mask) #define cpu_active_mask ((const struct cpumask *)&__cpu_active_mask) #define cpu_dying_mask ((const struct cpumask *)&__cpu_dying_mask) extern atomic_t __num_online_cpus; extern cpumask_t cpus_booted_once_mask; static __always_inline void cpu_max_bits_warn(unsigned int cpu, unsigned int bits) { #ifdef CONFIG_DEBUG_PER_CPU_MAPS WARN_ON_ONCE(cpu >= bits); #endif /* CONFIG_DEBUG_PER_CPU_MAPS */ } /* verify cpu argument to cpumask_* operators */ static __always_inline unsigned int cpumask_check(unsigned int cpu) { cpu_max_bits_warn(cpu, small_cpumask_bits); return cpu; } /** * cpumask_first - get the first cpu in a cpumask * @srcp: the cpumask pointer * * Return: >= nr_cpu_ids if no cpus set. */ static __always_inline unsigned int cpumask_first(const struct cpumask *srcp) { return find_first_bit(cpumask_bits(srcp), small_cpumask_bits); } /** * cpumask_first_zero - get the first unset cpu in a cpumask * @srcp: the cpumask pointer * * Return: >= nr_cpu_ids if all cpus are set. */ static __always_inline unsigned int cpumask_first_zero(const struct cpumask *srcp) { return find_first_zero_bit(cpumask_bits(srcp), small_cpumask_bits); } /** * cpumask_first_and - return the first cpu from *srcp1 & *srcp2 * @srcp1: the first input * @srcp2: the second input * * Return: >= nr_cpu_ids if no cpus set in both. See also cpumask_next_and(). */ static __always_inline unsigned int cpumask_first_and(const struct cpumask *srcp1, const struct cpumask *srcp2) { return find_first_and_bit(cpumask_bits(srcp1), cpumask_bits(srcp2), small_cpumask_bits); } /** * cpumask_first_and_and - return the first cpu from *srcp1 & *srcp2 & *srcp3 * @srcp1: the first input * @srcp2: the second input * @srcp3: the third input * * Return: >= nr_cpu_ids if no cpus set in all. */ static __always_inline unsigned int cpumask_first_and_and(const struct cpumask *srcp1, const struct cpumask *srcp2, const struct cpumask *srcp3) { return find_first_and_and_bit(cpumask_bits(srcp1), cpumask_bits(srcp2), cpumask_bits(srcp3), small_cpumask_bits); } /** * cpumask_last - get the last CPU in a cpumask * @srcp: - the cpumask pointer * * Return: >= nr_cpumask_bits if no CPUs set. */ static __always_inline unsigned int cpumask_last(const struct cpumask *srcp) { return find_last_bit(cpumask_bits(srcp), small_cpumask_bits); } /** * cpumask_next - get the next cpu in a cpumask * @n: the cpu prior to the place to search (i.e. return will be > @n) * @srcp: the cpumask pointer * * Return: >= nr_cpu_ids if no further cpus set. */ static __always_inline unsigned int cpumask_next(int n, const struct cpumask *srcp) { /* -1 is a legal arg here. */ if (n != -1) cpumask_check(n); return find_next_bit(cpumask_bits(srcp), small_cpumask_bits, n + 1); } /** * cpumask_next_zero - get the next unset cpu in a cpumask * @n: the cpu prior to the place to search (i.e. return will be > @n) * @srcp: the cpumask pointer * * Return: >= nr_cpu_ids if no further cpus unset. */ static __always_inline unsigned int cpumask_next_zero(int n, const struct cpumask *srcp) { /* -1 is a legal arg here. */ if (n != -1) cpumask_check(n); return find_next_zero_bit(cpumask_bits(srcp), small_cpumask_bits, n+1); } #if NR_CPUS == 1 /* Uniprocessor: there is only one valid CPU */ static __always_inline unsigned int cpumask_local_spread(unsigned int i, int node) { return 0; } static __always_inline unsigned int cpumask_any_and_distribute(const struct cpumask *src1p, const struct cpumask *src2p) { return cpumask_first_and(src1p, src2p); } static __always_inline unsigned int cpumask_any_distribute(const struct cpumask *srcp) { return cpumask_first(srcp); } #else unsigned int cpumask_local_spread(unsigned int i, int node); unsigned int cpumask_any_and_distribute(const struct cpumask *src1p, const struct cpumask *src2p); unsigned int cpumask_any_distribute(const struct cpumask *srcp); #endif /* NR_CPUS */ /** * cpumask_next_and - get the next cpu in *src1p & *src2p * @n: the cpu prior to the place to search (i.e. return will be > @n) * @src1p: the first cpumask pointer * @src2p: the second cpumask pointer * * Return: >= nr_cpu_ids if no further cpus set in both. */ static __always_inline unsigned int cpumask_next_and(int n, const struct cpumask *src1p, const struct cpumask *src2p) { /* -1 is a legal arg here. */ if (n != -1) cpumask_check(n); return find_next_and_bit(cpumask_bits(src1p), cpumask_bits(src2p), small_cpumask_bits, n + 1); } /** * for_each_cpu - iterate over every cpu in a mask * @cpu: the (optionally unsigned) integer iterator * @mask: the cpumask pointer * * After the loop, cpu is >= nr_cpu_ids. */ #define for_each_cpu(cpu, mask) \ for_each_set_bit(cpu, cpumask_bits(mask), small_cpumask_bits) #if NR_CPUS == 1 static __always_inline unsigned int cpumask_next_wrap(int n, const struct cpumask *mask, int start, bool wrap) { cpumask_check(start); if (n != -1) cpumask_check(n); /* * Return the first available CPU when wrapping, or when starting before cpu0, * since there is only one valid option. */ if (wrap && n >= 0) return nr_cpumask_bits; return cpumask_first(mask); } #else unsigned int __pure cpumask_next_wrap(int n, const struct cpumask *mask, int start, bool wrap); #endif /** * for_each_cpu_wrap - iterate over every cpu in a mask, starting at a specified location * @cpu: the (optionally unsigned) integer iterator * @mask: the cpumask pointer * @start: the start location * * The implementation does not assume any bit in @mask is set (including @start). * * After the loop, cpu is >= nr_cpu_ids. */ #define for_each_cpu_wrap(cpu, mask, start) \ for_each_set_bit_wrap(cpu, cpumask_bits(mask), small_cpumask_bits, start) /** * for_each_cpu_and - iterate over every cpu in both masks * @cpu: the (optionally unsigned) integer iterator * @mask1: the first cpumask pointer * @mask2: the second cpumask pointer * * This saves a temporary CPU mask in many places. It is equivalent to: * struct cpumask tmp; * cpumask_and(&tmp, &mask1, &mask2); * for_each_cpu(cpu, &tmp) * ... * * After the loop, cpu is >= nr_cpu_ids. */ #define for_each_cpu_and(cpu, mask1, mask2) \ for_each_and_bit(cpu, cpumask_bits(mask1), cpumask_bits(mask2), small_cpumask_bits) /** * for_each_cpu_andnot - iterate over every cpu present in one mask, excluding * those present in another. * @cpu: the (optionally unsigned) integer iterator * @mask1: the first cpumask pointer * @mask2: the second cpumask pointer * * This saves a temporary CPU mask in many places. It is equivalent to: * struct cpumask tmp; * cpumask_andnot(&tmp, &mask1, &mask2); * for_each_cpu(cpu, &tmp) * ... * * After the loop, cpu is >= nr_cpu_ids. */ #define for_each_cpu_andnot(cpu, mask1, mask2) \ for_each_andnot_bit(cpu, cpumask_bits(mask1), cpumask_bits(mask2), small_cpumask_bits) /** * for_each_cpu_or - iterate over every cpu present in either mask * @cpu: the (optionally unsigned) integer iterator * @mask1: the first cpumask pointer * @mask2: the second cpumask pointer * * This saves a temporary CPU mask in many places. It is equivalent to: * struct cpumask tmp; * cpumask_or(&tmp, &mask1, &mask2); * for_each_cpu(cpu, &tmp) * ... * * After the loop, cpu is >= nr_cpu_ids. */ #define for_each_cpu_or(cpu, mask1, mask2) \ for_each_or_bit(cpu, cpumask_bits(mask1), cpumask_bits(mask2), small_cpumask_bits) /** * for_each_cpu_from - iterate over CPUs present in @mask, from @cpu to the end of @mask. * @cpu: the (optionally unsigned) integer iterator * @mask: the cpumask pointer * * After the loop, cpu is >= nr_cpu_ids. */ #define for_each_cpu_from(cpu, mask) \ for_each_set_bit_from(cpu, cpumask_bits(mask), small_cpumask_bits) /** * cpumask_any_but - return a "random" in a cpumask, but not this one. * @mask: the cpumask to search * @cpu: the cpu to ignore. * * Often used to find any cpu but smp_processor_id() in a mask. * Return: >= nr_cpu_ids if no cpus set. */ static __always_inline unsigned int cpumask_any_but(const struct cpumask *mask, unsigned int cpu) { unsigned int i; cpumask_check(cpu); for_each_cpu(i, mask) if (i != cpu) break; return i; } /** * cpumask_any_and_but - pick a "random" cpu from *mask1 & *mask2, but not this one. * @mask1: the first input cpumask * @mask2: the second input cpumask * @cpu: the cpu to ignore * * Returns >= nr_cpu_ids if no cpus set. */ static __always_inline unsigned int cpumask_any_and_but(const struct cpumask *mask1, const struct cpumask *mask2, unsigned int cpu) { unsigned int i; cpumask_check(cpu); i = cpumask_first_and(mask1, mask2); if (i != cpu) return i; return cpumask_next_and(cpu, mask1, mask2); } /** * cpumask_nth - get the Nth cpu in a cpumask * @srcp: the cpumask pointer * @cpu: the Nth cpu to find, starting from 0 * * Return: >= nr_cpu_ids if such cpu doesn't exist. */ static __always_inline unsigned int cpumask_nth(unsigned int cpu, const struct cpumask *srcp) { return find_nth_bit(cpumask_bits(srcp), small_cpumask_bits, cpumask_check(cpu)); } /** * cpumask_nth_and - get the Nth cpu in 2 cpumasks * @srcp1: the cpumask pointer * @srcp2: the cpumask pointer * @cpu: the Nth cpu to find, starting from 0 * * Return: >= nr_cpu_ids if such cpu doesn't exist. */ static __always_inline unsigned int cpumask_nth_and(unsigned int cpu, const struct cpumask *srcp1, const struct cpumask *srcp2) { return find_nth_and_bit(cpumask_bits(srcp1), cpumask_bits(srcp2), small_cpumask_bits, cpumask_check(cpu)); } /** * cpumask_nth_andnot - get the Nth cpu set in 1st cpumask, and clear in 2nd. * @srcp1: the cpumask pointer * @srcp2: the cpumask pointer * @cpu: the Nth cpu to find, starting from 0 * * Return: >= nr_cpu_ids if such cpu doesn't exist. */ static __always_inline unsigned int cpumask_nth_andnot(unsigned int cpu, const struct cpumask *srcp1, const struct cpumask *srcp2) { return find_nth_andnot_bit(cpumask_bits(srcp1), cpumask_bits(srcp2), small_cpumask_bits, cpumask_check(cpu)); } /** * cpumask_nth_and_andnot - get the Nth cpu set in 1st and 2nd cpumask, and clear in 3rd. * @srcp1: the cpumask pointer * @srcp2: the cpumask pointer * @srcp3: the cpumask pointer * @cpu: the Nth cpu to find, starting from 0 * * Return: >= nr_cpu_ids if such cpu doesn't exist. */ static __always_inline unsigned int cpumask_nth_and_andnot(unsigned int cpu, const struct cpumask *srcp1, const struct cpumask *srcp2, const struct cpumask *srcp3) { return find_nth_and_andnot_bit(cpumask_bits(srcp1), cpumask_bits(srcp2), cpumask_bits(srcp3), small_cpumask_bits, cpumask_check(cpu)); } #define CPU_BITS_NONE \ { \ [0 ... BITS_TO_LONGS(NR_CPUS)-1] = 0UL \ } #define CPU_BITS_CPU0 \ { \ [0] = 1UL \ } /** * cpumask_set_cpu - set a cpu in a cpumask * @cpu: cpu number (< nr_cpu_ids) * @dstp: the cpumask pointer */ static __always_inline void cpumask_set_cpu(unsigned int cpu, struct cpumask *dstp) { set_bit(cpumask_check(cpu), cpumask_bits(dstp)); } static __always_inline void __cpumask_set_cpu(unsigned int cpu, struct cpumask *dstp) { __set_bit(cpumask_check(cpu), cpumask_bits(dstp)); } /** * cpumask_clear_cpu - clear a cpu in a cpumask * @cpu: cpu number (< nr_cpu_ids) * @dstp: the cpumask pointer */ static __always_inline void cpumask_clear_cpu(int cpu, struct cpumask *dstp) { clear_bit(cpumask_check(cpu), cpumask_bits(dstp)); } static __always_inline void __cpumask_clear_cpu(int cpu, struct cpumask *dstp) { __clear_bit(cpumask_check(cpu), cpumask_bits(dstp)); } /** * cpumask_assign_cpu - assign a cpu in a cpumask * @cpu: cpu number (< nr_cpu_ids) * @dstp: the cpumask pointer * @bool: the value to assign */ static __always_inline void cpumask_assign_cpu(int cpu, struct cpumask *dstp, bool value) { assign_bit(cpumask_check(cpu), cpumask_bits(dstp), value); } static __always_inline void __cpumask_assign_cpu(int cpu, struct cpumask *dstp, bool value) { __assign_bit(cpumask_check(cpu), cpumask_bits(dstp), value); } /** * cpumask_test_cpu - test for a cpu in a cpumask * @cpu: cpu number (< nr_cpu_ids) * @cpumask: the cpumask pointer * * Return: true if @cpu is set in @cpumask, else returns false */ static __always_inline bool cpumask_test_cpu(int cpu, const struct cpumask *cpumask) { return test_bit(cpumask_check(cpu), cpumask_bits((cpumask))); } /** * cpumask_test_and_set_cpu - atomically test and set a cpu in a cpumask * @cpu: cpu number (< nr_cpu_ids) * @cpumask: the cpumask pointer * * test_and_set_bit wrapper for cpumasks. * * Return: true if @cpu is set in old bitmap of @cpumask, else returns false */ static __always_inline bool cpumask_test_and_set_cpu(int cpu, struct cpumask *cpumask) { return test_and_set_bit(cpumask_check(cpu), cpumask_bits(cpumask)); } /** * cpumask_test_and_clear_cpu - atomically test and clear a cpu in a cpumask * @cpu: cpu number (< nr_cpu_ids) * @cpumask: the cpumask pointer * * test_and_clear_bit wrapper for cpumasks. * * Return: true if @cpu is set in old bitmap of @cpumask, else returns false */ static __always_inline bool cpumask_test_and_clear_cpu(int cpu, struct cpumask *cpumask) { return test_and_clear_bit(cpumask_check(cpu), cpumask_bits(cpumask)); } /** * cpumask_setall - set all cpus (< nr_cpu_ids) in a cpumask * @dstp: the cpumask pointer */ static __always_inline void cpumask_setall(struct cpumask *dstp) { if (small_const_nbits(small_cpumask_bits)) { cpumask_bits(dstp)[0] = BITMAP_LAST_WORD_MASK(nr_cpumask_bits); return; } bitmap_fill(cpumask_bits(dstp), nr_cpumask_bits); } /** * cpumask_clear - clear all cpus (< nr_cpu_ids) in a cpumask * @dstp: the cpumask pointer */ static __always_inline void cpumask_clear(struct cpumask *dstp) { bitmap_zero(cpumask_bits(dstp), large_cpumask_bits); } /** * cpumask_and - *dstp = *src1p & *src2p * @dstp: the cpumask result * @src1p: the first input * @src2p: the second input * * Return: false if *@dstp is empty, else returns true */ static __always_inline bool cpumask_and(struct cpumask *dstp, const struct cpumask *src1p, const struct cpumask *src2p) { return bitmap_and(cpumask_bits(dstp), cpumask_bits(src1p), cpumask_bits(src2p), small_cpumask_bits); } /** * cpumask_or - *dstp = *src1p | *src2p * @dstp: the cpumask result * @src1p: the first input * @src2p: the second input */ static __always_inline void cpumask_or(struct cpumask *dstp, const struct cpumask *src1p, const struct cpumask *src2p) { bitmap_or(cpumask_bits(dstp), cpumask_bits(src1p), cpumask_bits(src2p), small_cpumask_bits); } /** * cpumask_xor - *dstp = *src1p ^ *src2p * @dstp: the cpumask result * @src1p: the first input * @src2p: the second input */ static __always_inline void cpumask_xor(struct cpumask *dstp, const struct cpumask *src1p, const struct cpumask *src2p) { bitmap_xor(cpumask_bits(dstp), cpumask_bits(src1p), cpumask_bits(src2p), small_cpumask_bits); } /** * cpumask_andnot - *dstp = *src1p & ~*src2p * @dstp: the cpumask result * @src1p: the first input * @src2p: the second input * * Return: false if *@dstp is empty, else returns true */ static __always_inline bool cpumask_andnot(struct cpumask *dstp, const struct cpumask *src1p, const struct cpumask *src2p) { return bitmap_andnot(cpumask_bits(dstp), cpumask_bits(src1p), cpumask_bits(src2p), small_cpumask_bits); } /** * cpumask_equal - *src1p == *src2p * @src1p: the first input * @src2p: the second input * * Return: true if the cpumasks are equal, false if not */ static __always_inline bool cpumask_equal(const struct cpumask *src1p, const struct cpumask *src2p) { return bitmap_equal(cpumask_bits(src1p), cpumask_bits(src2p), small_cpumask_bits); } /** * cpumask_or_equal - *src1p | *src2p == *src3p * @src1p: the first input * @src2p: the second input * @src3p: the third input * * Return: true if first cpumask ORed with second cpumask == third cpumask, * otherwise false */ static __always_inline bool cpumask_or_equal(const struct cpumask *src1p, const struct cpumask *src2p, const struct cpumask *src3p) { return bitmap_or_equal(cpumask_bits(src1p), cpumask_bits(src2p), cpumask_bits(src3p), small_cpumask_bits); } /** * cpumask_intersects - (*src1p & *src2p) != 0 * @src1p: the first input * @src2p: the second input * * Return: true if first cpumask ANDed with second cpumask is non-empty, * otherwise false */ static __always_inline bool cpumask_intersects(const struct cpumask *src1p, const struct cpumask *src2p) { return bitmap_intersects(cpumask_bits(src1p), cpumask_bits(src2p), small_cpumask_bits); } /** * cpumask_subset - (*src1p & ~*src2p) == 0 * @src1p: the first input * @src2p: the second input * * Return: true if *@src1p is a subset of *@src2p, else returns false */ static __always_inline bool cpumask_subset(const struct cpumask *src1p, const struct cpumask *src2p) { return bitmap_subset(cpumask_bits(src1p), cpumask_bits(src2p), small_cpumask_bits); } /** * cpumask_empty - *srcp == 0 * @srcp: the cpumask to that all cpus < nr_cpu_ids are clear. * * Return: true if srcp is empty (has no bits set), else false */ static __always_inline bool cpumask_empty(const struct cpumask *srcp) { return bitmap_empty(cpumask_bits(srcp), small_cpumask_bits); } /** * cpumask_full - *srcp == 0xFFFFFFFF... * @srcp: the cpumask to that all cpus < nr_cpu_ids are set. * * Return: true if srcp is full (has all bits set), else false */ static __always_inline bool cpumask_full(const struct cpumask *srcp) { return bitmap_full(cpumask_bits(srcp), nr_cpumask_bits); } /** * cpumask_weight - Count of bits in *srcp * @srcp: the cpumask to count bits (< nr_cpu_ids) in. * * Return: count of bits set in *srcp */ static __always_inline unsigned int cpumask_weight(const struct cpumask *srcp) { return bitmap_weight(cpumask_bits(srcp), small_cpumask_bits); } /** * cpumask_weight_and - Count of bits in (*srcp1 & *srcp2) * @srcp1: the cpumask to count bits (< nr_cpu_ids) in. * @srcp2: the cpumask to count bits (< nr_cpu_ids) in. * * Return: count of bits set in both *srcp1 and *srcp2 */ static __always_inline unsigned int cpumask_weight_and(const struct cpumask *srcp1, const struct cpumask *srcp2) { return bitmap_weight_and(cpumask_bits(srcp1), cpumask_bits(srcp2), small_cpumask_bits); } /** * cpumask_weight_andnot - Count of bits in (*srcp1 & ~*srcp2) * @srcp1: the cpumask to count bits (< nr_cpu_ids) in. * @srcp2: the cpumask to count bits (< nr_cpu_ids) in. * * Return: count of bits set in both *srcp1 and *srcp2 */ static __always_inline unsigned int cpumask_weight_andnot(const struct cpumask *srcp1, const struct cpumask *srcp2) { return bitmap_weight_andnot(cpumask_bits(srcp1), cpumask_bits(srcp2), small_cpumask_bits); } /** * cpumask_shift_right - *dstp = *srcp >> n * @dstp: the cpumask result * @srcp: the input to shift * @n: the number of bits to shift by */ static __always_inline void cpumask_shift_right(struct cpumask *dstp, const struct cpumask *srcp, int n) { bitmap_shift_right(cpumask_bits(dstp), cpumask_bits(srcp), n, small_cpumask_bits); } /** * cpumask_shift_left - *dstp = *srcp << n * @dstp: the cpumask result * @srcp: the input to shift * @n: the number of bits to shift by */ static __always_inline void cpumask_shift_left(struct cpumask *dstp, const struct cpumask *srcp, int n) { bitmap_shift_left(cpumask_bits(dstp), cpumask_bits(srcp), n, nr_cpumask_bits); } /** * cpumask_copy - *dstp = *srcp * @dstp: the result * @srcp: the input cpumask */ static __always_inline void cpumask_copy(struct cpumask *dstp, const struct cpumask *srcp) { bitmap_copy(cpumask_bits(dstp), cpumask_bits(srcp), large_cpumask_bits); } /** * cpumask_any - pick a "random" cpu from *srcp * @srcp: the input cpumask * * Return: >= nr_cpu_ids if no cpus set. */ #define cpumask_any(srcp) cpumask_first(srcp) /** * cpumask_any_and - pick a "random" cpu from *mask1 & *mask2 * @mask1: the first input cpumask * @mask2: the second input cpumask * * Return: >= nr_cpu_ids if no cpus set. */ #define cpumask_any_and(mask1, mask2) cpumask_first_and((mask1), (mask2)) /** * cpumask_of - the cpumask containing just a given cpu * @cpu: the cpu (<= nr_cpu_ids) */ #define cpumask_of(cpu) (get_cpu_mask(cpu)) /** * cpumask_parse_user - extract a cpumask from a user string * @buf: the buffer to extract from * @len: the length of the buffer * @dstp: the cpumask to set. * * Return: -errno, or 0 for success. */ static __always_inline int cpumask_parse_user(const char __user *buf, int len, struct cpumask *dstp) { return bitmap_parse_user(buf, len, cpumask_bits(dstp), nr_cpumask_bits); } /** * cpumask_parselist_user - extract a cpumask from a user string * @buf: the buffer to extract from * @len: the length of the buffer * @dstp: the cpumask to set. * * Return: -errno, or 0 for success. */ static __always_inline int cpumask_parselist_user(const char __user *buf, int len, struct cpumask *dstp) { return bitmap_parselist_user(buf, len, cpumask_bits(dstp), nr_cpumask_bits); } /** * cpumask_parse - extract a cpumask from a string * @buf: the buffer to extract from * @dstp: the cpumask to set. * * Return: -errno, or 0 for success. */ static __always_inline int cpumask_parse(const char *buf, struct cpumask *dstp) { return bitmap_parse(buf, UINT_MAX, cpumask_bits(dstp), nr_cpumask_bits); } /** * cpulist_parse - extract a cpumask from a user string of ranges * @buf: the buffer to extract from * @dstp: the cpumask to set. * * Return: -errno, or 0 for success. */ static __always_inline int cpulist_parse(const char *buf, struct cpumask *dstp) { return bitmap_parselist(buf, cpumask_bits(dstp), nr_cpumask_bits); } /** * cpumask_size - calculate size to allocate for a 'struct cpumask' in bytes * * Return: size to allocate for a &struct cpumask in bytes */ static __always_inline unsigned int cpumask_size(void) { return bitmap_size(large_cpumask_bits); } #ifdef CONFIG_CPUMASK_OFFSTACK #define this_cpu_cpumask_var_ptr(x) this_cpu_read(x) #define __cpumask_var_read_mostly __read_mostly bool alloc_cpumask_var_node(cpumask_var_t *mask, gfp_t flags, int node); static __always_inline bool zalloc_cpumask_var_node(cpumask_var_t *mask, gfp_t flags, int node) { return alloc_cpumask_var_node(mask, flags | __GFP_ZERO, node); } /** * alloc_cpumask_var - allocate a struct cpumask * @mask: pointer to cpumask_var_t where the cpumask is returned * @flags: GFP_ flags * * Only defined when CONFIG_CPUMASK_OFFSTACK=y, otherwise is * a nop returning a constant 1 (in <linux/cpumask.h>). * * See alloc_cpumask_var_node. * * Return: %true if allocation succeeded, %false if not */ static __always_inline bool alloc_cpumask_var(cpumask_var_t *mask, gfp_t flags) { return alloc_cpumask_var_node(mask, flags, NUMA_NO_NODE); } static __always_inline bool zalloc_cpumask_var(cpumask_var_t *mask, gfp_t flags) { return alloc_cpumask_var(mask, flags | __GFP_ZERO); } void alloc_bootmem_cpumask_var(cpumask_var_t *mask); void free_cpumask_var(cpumask_var_t mask); void free_bootmem_cpumask_var(cpumask_var_t mask); static __always_inline bool cpumask_available(cpumask_var_t mask) { return mask != NULL; } #else #define this_cpu_cpumask_var_ptr(x) this_cpu_ptr(x) #define __cpumask_var_read_mostly static __always_inline bool alloc_cpumask_var(cpumask_var_t *mask, gfp_t flags) { return true; } static __always_inline bool alloc_cpumask_var_node(cpumask_var_t *mask, gfp_t flags, int node) { return true; } static __always_inline bool zalloc_cpumask_var(cpumask_var_t *mask, gfp_t flags) { cpumask_clear(*mask); return true; } static __always_inline bool zalloc_cpumask_var_node(cpumask_var_t *mask, gfp_t flags, int node) { cpumask_clear(*mask); return true; } static __always_inline void alloc_bootmem_cpumask_var(cpumask_var_t *mask) { } static __always_inline void free_cpumask_var(cpumask_var_t mask) { } static __always_inline void free_bootmem_cpumask_var(cpumask_var_t mask) { } static __always_inline bool cpumask_available(cpumask_var_t mask) { return true; } #endif /* CONFIG_CPUMASK_OFFSTACK */ DEFINE_FREE(free_cpumask_var, struct cpumask *, if (_T) free_cpumask_var(_T)); /* It's common to want to use cpu_all_mask in struct member initializers, * so it has to refer to an address rather than a pointer. */ extern const DECLARE_BITMAP(cpu_all_bits, NR_CPUS); #define cpu_all_mask to_cpumask(cpu_all_bits) /* First bits of cpu_bit_bitmap are in fact unset. */ #define cpu_none_mask to_cpumask(cpu_bit_bitmap[0]) #if NR_CPUS == 1 /* Uniprocessor: the possible/online/present masks are always "1" */ #define for_each_possible_cpu(cpu) for ((cpu) = 0; (cpu) < 1; (cpu)++) #define for_each_online_cpu(cpu) for ((cpu) = 0; (cpu) < 1; (cpu)++) #define for_each_present_cpu(cpu) for ((cpu) = 0; (cpu) < 1; (cpu)++) #else #define for_each_possible_cpu(cpu) for_each_cpu((cpu), cpu_possible_mask) #define for_each_online_cpu(cpu) for_each_cpu((cpu), cpu_online_mask) #define for_each_enabled_cpu(cpu) for_each_cpu((cpu), cpu_enabled_mask) #define for_each_present_cpu(cpu) for_each_cpu((cpu), cpu_present_mask) #endif /* Wrappers for arch boot code to manipulate normally-constant masks */ void init_cpu_present(const struct cpumask *src); void init_cpu_possible(const struct cpumask *src); void init_cpu_online(const struct cpumask *src); #define assign_cpu(cpu, mask, val) \ assign_bit(cpumask_check(cpu), cpumask_bits(mask), (val)) #define set_cpu_possible(cpu, possible) assign_cpu((cpu), &__cpu_possible_mask, (possible)) #define set_cpu_enabled(cpu, enabled) assign_cpu((cpu), &__cpu_enabled_mask, (enabled)) #define set_cpu_present(cpu, present) assign_cpu((cpu), &__cpu_present_mask, (present)) #define set_cpu_active(cpu, active) assign_cpu((cpu), &__cpu_active_mask, (active)) #define set_cpu_dying(cpu, dying) assign_cpu((cpu), &__cpu_dying_mask, (dying)) void set_cpu_online(unsigned int cpu, bool online); /** * to_cpumask - convert a NR_CPUS bitmap to a struct cpumask * * @bitmap: the bitmap * * There are a few places where cpumask_var_t isn't appropriate and * static cpumasks must be used (eg. very early boot), yet we don't * expose the definition of 'struct cpumask'. * * This does the conversion, and can be used as a constant initializer. */ #define to_cpumask(bitmap) \ ((struct cpumask *)(1 ? (bitmap) \ : (void *)sizeof(__check_is_bitmap(bitmap)))) static __always_inline int __check_is_bitmap(const unsigned long *bitmap) { return 1; } /* * Special-case data structure for "single bit set only" constant CPU masks. * * We pre-generate all the 64 (or 32) possible bit positions, with enough * padding to the left and the right, and return the constant pointer * appropriately offset. */ extern const unsigned long cpu_bit_bitmap[BITS_PER_LONG+1][BITS_TO_LONGS(NR_CPUS)]; static __always_inline const struct cpumask *get_cpu_mask(unsigned int cpu) { const unsigned long *p = cpu_bit_bitmap[1 + cpu % BITS_PER_LONG]; p -= cpu / BITS_PER_LONG; return to_cpumask(p); } #if NR_CPUS > 1 /** * num_online_cpus() - Read the number of online CPUs * * Despite the fact that __num_online_cpus is of type atomic_t, this * interface gives only a momentary snapshot and is not protected against * concurrent CPU hotplug operations unless invoked from a cpuhp_lock held * region. * * Return: momentary snapshot of the number of online CPUs */ static __always_inline unsigned int num_online_cpus(void) { return raw_atomic_read(&__num_online_cpus); } #define num_possible_cpus() cpumask_weight(cpu_possible_mask) #define num_enabled_cpus() cpumask_weight(cpu_enabled_mask) #define num_present_cpus() cpumask_weight(cpu_present_mask) #define num_active_cpus() cpumask_weight(cpu_active_mask) static __always_inline bool cpu_online(unsigned int cpu) { return cpumask_test_cpu(cpu, cpu_online_mask); } static __always_inline bool cpu_enabled(unsigned int cpu) { return cpumask_test_cpu(cpu, cpu_enabled_mask); } static __always_inline bool cpu_possible(unsigned int cpu) { return cpumask_test_cpu(cpu, cpu_possible_mask); } static __always_inline bool cpu_present(unsigned int cpu) { return cpumask_test_cpu(cpu, cpu_present_mask); } static __always_inline bool cpu_active(unsigned int cpu) { return cpumask_test_cpu(cpu, cpu_active_mask); } static __always_inline bool cpu_dying(unsigned int cpu) { return cpumask_test_cpu(cpu, cpu_dying_mask); } #else #define num_online_cpus() 1U #define num_possible_cpus() 1U #define num_enabled_cpus() 1U #define num_present_cpus() 1U #define num_active_cpus() 1U static __always_inline bool cpu_online(unsigned int cpu) { return cpu == 0; } static __always_inline bool cpu_possible(unsigned int cpu) { return cpu == 0; } static __always_inline bool cpu_enabled(unsigned int cpu) { return cpu == 0; } static __always_inline bool cpu_present(unsigned int cpu) { return cpu == 0; } static __always_inline bool cpu_active(unsigned int cpu) { return cpu == 0; } static __always_inline bool cpu_dying(unsigned int cpu) { return false; } #endif /* NR_CPUS > 1 */ #define cpu_is_offline(cpu) unlikely(!cpu_online(cpu)) #if NR_CPUS <= BITS_PER_LONG #define CPU_BITS_ALL \ { \ [BITS_TO_LONGS(NR_CPUS)-1] = BITMAP_LAST_WORD_MASK(NR_CPUS) \ } #else /* NR_CPUS > BITS_PER_LONG */ #define CPU_BITS_ALL \ { \ [0 ... BITS_TO_LONGS(NR_CPUS)-2] = ~0UL, \ [BITS_TO_LONGS(NR_CPUS)-1] = BITMAP_LAST_WORD_MASK(NR_CPUS) \ } #endif /* NR_CPUS > BITS_PER_LONG */ /** * cpumap_print_to_pagebuf - copies the cpumask into the buffer either * as comma-separated list of cpus or hex values of cpumask * @list: indicates whether the cpumap must be list * @mask: the cpumask to copy * @buf: the buffer to copy into * * Return: the length of the (null-terminated) @buf string, zero if * nothing is copied. */ static __always_inline ssize_t cpumap_print_to_pagebuf(bool list, char *buf, const struct cpumask *mask) { return bitmap_print_to_pagebuf(list, buf, cpumask_bits(mask), nr_cpu_ids); } /** * cpumap_print_bitmask_to_buf - copies the cpumask into the buffer as * hex values of cpumask * * @buf: the buffer to copy into * @mask: the cpumask to copy * @off: in the string from which we are copying, we copy to @buf * @count: the maximum number of bytes to print * * The function prints the cpumask into the buffer as hex values of * cpumask; Typically used by bin_attribute to export cpumask bitmask * ABI. * * Return: the length of how many bytes have been copied, excluding * terminating '\0'. */ static __always_inline ssize_t cpumap_print_bitmask_to_buf(char *buf, const struct cpumask *mask, loff_t off, size_t count) { return bitmap_print_bitmask_to_buf(buf, cpumask_bits(mask), nr_cpu_ids, off, count) - 1; } /** * cpumap_print_list_to_buf - copies the cpumask into the buffer as * comma-separated list of cpus * @buf: the buffer to copy into * @mask: the cpumask to copy * @off: in the string from which we are copying, we copy to @buf * @count: the maximum number of bytes to print * * Everything is same with the above cpumap_print_bitmask_to_buf() * except the print format. * * Return: the length of how many bytes have been copied, excluding * terminating '\0'. */ static __always_inline ssize_t cpumap_print_list_to_buf(char *buf, const struct cpumask *mask, loff_t off, size_t count) { return bitmap_print_list_to_buf(buf, cpumask_bits(mask), nr_cpu_ids, off, count) - 1; } #if NR_CPUS <= BITS_PER_LONG #define CPU_MASK_ALL \ (cpumask_t) { { \ [BITS_TO_LONGS(NR_CPUS)-1] = BITMAP_LAST_WORD_MASK(NR_CPUS) \ } } #else #define CPU_MASK_ALL \ (cpumask_t) { { \ [0 ... BITS_TO_LONGS(NR_CPUS)-2] = ~0UL, \ [BITS_TO_LONGS(NR_CPUS)-1] = BITMAP_LAST_WORD_MASK(NR_CPUS) \ } } #endif /* NR_CPUS > BITS_PER_LONG */ #define CPU_MASK_NONE \ (cpumask_t) { { \ [0 ... BITS_TO_LONGS(NR_CPUS)-1] = 0UL \ } } #define CPU_MASK_CPU0 \ (cpumask_t) { { \ [0] = 1UL \ } } /* * Provide a valid theoretical max size for cpumap and cpulist sysfs files * to avoid breaking userspace which may allocate a buffer based on the size * reported by e.g. fstat. * * for cpumap NR_CPUS * 9/32 - 1 should be an exact length. * * For cpulist 7 is (ceil(log10(NR_CPUS)) + 1) allowing for NR_CPUS to be up * to 2 orders of magnitude larger than 8192. And then we divide by 2 to * cover a worst-case of every other cpu being on one of two nodes for a * very large NR_CPUS. * * Use PAGE_SIZE as a minimum for smaller configurations while avoiding * unsigned comparison to -1. */ #define CPUMAP_FILE_MAX_BYTES (((NR_CPUS * 9)/32 > PAGE_SIZE) \ ? (NR_CPUS * 9)/32 - 1 : PAGE_SIZE) #define CPULIST_FILE_MAX_BYTES (((NR_CPUS * 7)/2 > PAGE_SIZE) ? (NR_CPUS * 7)/2 : PAGE_SIZE) #endif /* __LINUX_CPUMASK_H */ |
| 3 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 | /* SPDX-License-Identifier: GPL-2.0 */ /* * kernel/workqueue_internal.h * * Workqueue internal header file. Only to be included by workqueue and * core kernel subsystems. */ #ifndef _KERNEL_WORKQUEUE_INTERNAL_H #define _KERNEL_WORKQUEUE_INTERNAL_H #include <linux/workqueue.h> #include <linux/kthread.h> #include <linux/preempt.h> struct worker_pool; /* * The poor guys doing the actual heavy lifting. All on-duty workers are * either serving the manager role, on idle list or on busy hash. For * details on the locking annotation (L, I, X...), refer to workqueue.c. * * Only to be used in workqueue and async. */ struct worker { /* on idle list while idle, on busy hash table while busy */ union { struct list_head entry; /* L: while idle */ struct hlist_node hentry; /* L: while busy */ }; struct work_struct *current_work; /* K: work being processed and its */ work_func_t current_func; /* K: function */ struct pool_workqueue *current_pwq; /* K: pwq */ u64 current_at; /* K: runtime at start or last wakeup */ unsigned int current_color; /* K: color */ int sleeping; /* S: is worker sleeping? */ /* used by the scheduler to determine a worker's last known identity */ work_func_t last_func; /* K: last work's fn */ struct list_head scheduled; /* L: scheduled works */ struct task_struct *task; /* I: worker task */ struct worker_pool *pool; /* A: the associated pool */ /* L: for rescuers */ struct list_head node; /* A: anchored at pool->workers */ /* A: runs through worker->node */ unsigned long last_active; /* K: last active timestamp */ unsigned int flags; /* L: flags */ int id; /* I: worker id */ /* * Opaque string set with work_set_desc(). Printed out with task * dump for debugging - WARN, BUG, panic or sysrq. */ char desc[WORKER_DESC_LEN]; /* used only by rescuers to point to the target workqueue */ struct workqueue_struct *rescue_wq; /* I: the workqueue to rescue */ }; /** * current_wq_worker - return struct worker if %current is a workqueue worker */ static inline struct worker *current_wq_worker(void) { if (in_task() && (current->flags & PF_WQ_WORKER)) return kthread_data(current); return NULL; } /* * Scheduler hooks for concurrency managed workqueue. Only to be used from * sched/ and workqueue.c. */ void wq_worker_running(struct task_struct *task); void wq_worker_sleeping(struct task_struct *task); void wq_worker_tick(struct task_struct *task); work_func_t wq_worker_last_func(struct task_struct *task); #endif /* _KERNEL_WORKQUEUE_INTERNAL_H */ |
| 160 267 268 192 160 161 160 82 96 62 80 81 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 | // SPDX-License-Identifier: GPL-2.0-only /* * Based on arch/arm/mm/flush.c * * Copyright (C) 1995-2002 Russell King * Copyright (C) 2012 ARM Ltd. */ #include <linux/export.h> #include <linux/mm.h> #include <linux/libnvdimm.h> #include <linux/pagemap.h> #include <asm/cacheflush.h> #include <asm/cache.h> #include <asm/tlbflush.h> void sync_icache_aliases(unsigned long start, unsigned long end) { if (icache_is_aliasing()) { dcache_clean_pou(start, end); icache_inval_all_pou(); } else { /* * Don't issue kick_all_cpus_sync() after I-cache invalidation * for user mappings. */ caches_clean_inval_pou(start, end); } } static void flush_ptrace_access(struct vm_area_struct *vma, unsigned long start, unsigned long end) { if (vma->vm_flags & VM_EXEC) sync_icache_aliases(start, end); } /* * Copy user data from/to a page which is mapped into a different processes * address space. Really, we want to allow our "user space" model to handle * this. */ void copy_to_user_page(struct vm_area_struct *vma, struct page *page, unsigned long uaddr, void *dst, const void *src, unsigned long len) { memcpy(dst, src, len); flush_ptrace_access(vma, (unsigned long)dst, (unsigned long)dst + len); } void __sync_icache_dcache(pte_t pte) { struct folio *folio = page_folio(pte_page(pte)); if (!test_bit(PG_dcache_clean, &folio->flags)) { sync_icache_aliases((unsigned long)folio_address(folio), (unsigned long)folio_address(folio) + folio_size(folio)); set_bit(PG_dcache_clean, &folio->flags); } } EXPORT_SYMBOL_GPL(__sync_icache_dcache); /* * This function is called when a page has been modified by the kernel. Mark * it as dirty for later flushing when mapped in user space (if executable, * see __sync_icache_dcache). */ void flush_dcache_folio(struct folio *folio) { if (test_bit(PG_dcache_clean, &folio->flags)) clear_bit(PG_dcache_clean, &folio->flags); } EXPORT_SYMBOL(flush_dcache_folio); void flush_dcache_page(struct page *page) { flush_dcache_folio(page_folio(page)); } EXPORT_SYMBOL(flush_dcache_page); /* * Additional functions defined in assembly. */ EXPORT_SYMBOL(caches_clean_inval_pou); #ifdef CONFIG_ARCH_HAS_PMEM_API void arch_wb_cache_pmem(void *addr, size_t size) { /* Ensure order against any prior non-cacheable writes */ dmb(osh); dcache_clean_pop((unsigned long)addr, (unsigned long)addr + size); } EXPORT_SYMBOL_GPL(arch_wb_cache_pmem); void arch_invalidate_pmem(void *addr, size_t size) { dcache_inval_poc((unsigned long)addr, (unsigned long)addr + size); } EXPORT_SYMBOL_GPL(arch_invalidate_pmem); #endif |
| 162 162 163 306 20 168 433 433 54 433 430 433 433 432 433 433 53 52 54 2 53 16 425 425 425 426 39 39 38 1 9 36 432 1026 1026 1 1036 1034 1039 1034 42 420 1002 958 1013 2 2 53 14 68 68 66 10 3 3 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 | // SPDX-License-Identifier: GPL-2.0 /* * linux/fs/file.c * * Copyright (C) 1998-1999, Stephen Tweedie and Bill Hawes * * Manage the dynamic fd arrays in the process files_struct. */ #include <linux/syscalls.h> #include <linux/export.h> #include <linux/fs.h> #include <linux/kernel.h> #include <linux/mm.h> #include <linux/sched/signal.h> #include <linux/slab.h> #include <linux/file.h> #include <linux/fdtable.h> #include <linux/bitops.h> #include <linux/spinlock.h> #include <linux/rcupdate.h> #include <linux/close_range.h> #include <linux/file_ref.h> #include <net/sock.h> #include "internal.h" /** * __file_ref_put - Slowpath of file_ref_put() * @ref: Pointer to the reference count * @cnt: Current reference count * * Invoked when the reference count is outside of the valid zone. * * Return: * True if this was the last reference with no future references * possible. This signals the caller that it can safely schedule the * object, which is protected by the reference counter, for * deconstruction. * * False if there are still active references or the put() raced * with a concurrent get()/put() pair. Caller is not allowed to * deconstruct the protected object. */ bool __file_ref_put(file_ref_t *ref, unsigned long cnt) { /* Did this drop the last reference? */ if (likely(cnt == FILE_REF_NOREF)) { /* * Carefully try to set the reference count to FILE_REF_DEAD. * * This can fail if a concurrent get() operation has * elevated it again or the corresponding put() even marked * it dead already. Both are valid situations and do not * require a retry. If this fails the caller is not * allowed to deconstruct the object. */ if (!atomic_long_try_cmpxchg_release(&ref->refcnt, &cnt, FILE_REF_DEAD)) return false; /* * The caller can safely schedule the object for * deconstruction. Provide acquire ordering. */ smp_acquire__after_ctrl_dep(); return true; } /* * If the reference count was already in the dead zone, then this * put() operation is imbalanced. Warn, put the reference count back to * DEAD and tell the caller to not deconstruct the object. */ if (WARN_ONCE(cnt >= FILE_REF_RELEASED, "imbalanced put on file reference count")) { atomic_long_set(&ref->refcnt, FILE_REF_DEAD); return false; } /* * This is a put() operation on a saturated refcount. Restore the * mean saturation value and tell the caller to not deconstruct the * object. */ if (cnt > FILE_REF_MAXREF) atomic_long_set(&ref->refcnt, FILE_REF_SATURATED); return false; } EXPORT_SYMBOL_GPL(__file_ref_put); unsigned int sysctl_nr_open __read_mostly = 1024*1024; unsigned int sysctl_nr_open_min = BITS_PER_LONG; /* our min() is unusable in constant expressions ;-/ */ #define __const_min(x, y) ((x) < (y) ? (x) : (y)) unsigned int sysctl_nr_open_max = __const_min(INT_MAX, ~(size_t)0/sizeof(void *)) & -BITS_PER_LONG; static void __free_fdtable(struct fdtable *fdt) { kvfree(fdt->fd); kvfree(fdt->open_fds); kfree(fdt); } static void free_fdtable_rcu(struct rcu_head *rcu) { __free_fdtable(container_of(rcu, struct fdtable, rcu)); } #define BITBIT_NR(nr) BITS_TO_LONGS(BITS_TO_LONGS(nr)) #define BITBIT_SIZE(nr) (BITBIT_NR(nr) * sizeof(long)) #define fdt_words(fdt) ((fdt)->max_fds / BITS_PER_LONG) // words in ->open_fds /* * Copy 'count' fd bits from the old table to the new table and clear the extra * space if any. This does not copy the file pointers. Called with the files * spinlock held for write. */ static inline void copy_fd_bitmaps(struct fdtable *nfdt, struct fdtable *ofdt, unsigned int copy_words) { unsigned int nwords = fdt_words(nfdt); bitmap_copy_and_extend(nfdt->open_fds, ofdt->open_fds, copy_words * BITS_PER_LONG, nwords * BITS_PER_LONG); bitmap_copy_and_extend(nfdt->close_on_exec, ofdt->close_on_exec, copy_words * BITS_PER_LONG, nwords * BITS_PER_LONG); bitmap_copy_and_extend(nfdt->full_fds_bits, ofdt->full_fds_bits, copy_words, nwords); } /* * Copy all file descriptors from the old table to the new, expanded table and * clear the extra space. Called with the files spinlock held for write. */ static void copy_fdtable(struct fdtable *nfdt, struct fdtable *ofdt) { size_t cpy, set; BUG_ON(nfdt->max_fds < ofdt->max_fds); cpy = ofdt->max_fds * sizeof(struct file *); set = (nfdt->max_fds - ofdt->max_fds) * sizeof(struct file *); memcpy(nfdt->fd, ofdt->fd, cpy); memset((char *)nfdt->fd + cpy, 0, set); copy_fd_bitmaps(nfdt, ofdt, fdt_words(ofdt)); } /* * Note how the fdtable bitmap allocations very much have to be a multiple of * BITS_PER_LONG. This is not only because we walk those things in chunks of * 'unsigned long' in some places, but simply because that is how the Linux * kernel bitmaps are defined to work: they are not "bits in an array of bytes", * they are very much "bits in an array of unsigned long". */ static struct fdtable *alloc_fdtable(unsigned int slots_wanted) { struct fdtable *fdt; unsigned int nr; void *data; /* * Figure out how many fds we actually want to support in this fdtable. * Allocation steps are keyed to the size of the fdarray, since it * grows far faster than any of the other dynamic data. We try to fit * the fdarray into comfortable page-tuned chunks: starting at 1024B * and growing in powers of two from there on. Since we called only * with slots_wanted > BITS_PER_LONG (embedded instance in files->fdtab * already gives BITS_PER_LONG slots), the above boils down to * 1. use the smallest power of two large enough to give us that many * slots. * 2. on 32bit skip 64 and 128 - the minimal capacity we want there is * 256 slots (i.e. 1Kb fd array). * 3. on 64bit don't skip anything, 1Kb fd array means 128 slots there * and we are never going to be asked for 64 or less. */ if (IS_ENABLED(CONFIG_32BIT) && slots_wanted < 256) nr = 256; else nr = roundup_pow_of_two(slots_wanted); /* * Note that this can drive nr *below* what we had passed if sysctl_nr_open * had been set lower between the check in expand_files() and here. * * We make sure that nr remains a multiple of BITS_PER_LONG - otherwise * bitmaps handling below becomes unpleasant, to put it mildly... */ if (unlikely(nr > sysctl_nr_open)) { nr = round_down(sysctl_nr_open, BITS_PER_LONG); if (nr < slots_wanted) return ERR_PTR(-EMFILE); } fdt = kmalloc(sizeof(struct fdtable), GFP_KERNEL_ACCOUNT); if (!fdt) goto out; fdt->max_fds = nr; data = kvmalloc_array(nr, sizeof(struct file *), GFP_KERNEL_ACCOUNT); if (!data) goto out_fdt; fdt->fd = data; data = kvmalloc(max_t(size_t, 2 * nr / BITS_PER_BYTE + BITBIT_SIZE(nr), L1_CACHE_BYTES), GFP_KERNEL_ACCOUNT); if (!data) goto out_arr; fdt->open_fds = data; data += nr / BITS_PER_BYTE; fdt->close_on_exec = data; data += nr / BITS_PER_BYTE; fdt->full_fds_bits = data; return fdt; out_arr: kvfree(fdt->fd); out_fdt: kfree(fdt); out: return ERR_PTR(-ENOMEM); } /* * Expand the file descriptor table. * This function will allocate a new fdtable and both fd array and fdset, of * the given size. * Return <0 error code on error; 0 on successful completion. * The files->file_lock should be held on entry, and will be held on exit. */ static int expand_fdtable(struct files_struct *files, unsigned int nr) __releases(files->file_lock) __acquires(files->file_lock) { struct fdtable *new_fdt, *cur_fdt; spin_unlock(&files->file_lock); new_fdt = alloc_fdtable(nr + 1); /* make sure all fd_install() have seen resize_in_progress * or have finished their rcu_read_lock_sched() section. */ if (atomic_read(&files->count) > 1) synchronize_rcu(); spin_lock(&files->file_lock); if (IS_ERR(new_fdt)) return PTR_ERR(new_fdt); cur_fdt = files_fdtable(files); BUG_ON(nr < cur_fdt->max_fds); copy_fdtable(new_fdt, cur_fdt); rcu_assign_pointer(files->fdt, new_fdt); if (cur_fdt != &files->fdtab) call_rcu(&cur_fdt->rcu, free_fdtable_rcu); /* coupled with smp_rmb() in fd_install() */ smp_wmb(); return 0; } /* * Expand files. * This function will expand the file structures, if the requested size exceeds * the current capacity and there is room for expansion. * Return <0 error code on error; 0 on success. * The files->file_lock should be held on entry, and will be held on exit. */ static int expand_files(struct files_struct *files, unsigned int nr) __releases(files->file_lock) __acquires(files->file_lock) { struct fdtable *fdt; int error; repeat: fdt = files_fdtable(files); /* Do we need to expand? */ if (nr < fdt->max_fds) return 0; /* Can we expand? */ if (nr >= sysctl_nr_open) return -EMFILE; if (unlikely(files->resize_in_progress)) { spin_unlock(&files->file_lock); wait_event(files->resize_wait, !files->resize_in_progress); spin_lock(&files->file_lock); goto repeat; } /* All good, so we try */ files->resize_in_progress = true; error = expand_fdtable(files, nr); files->resize_in_progress = false; wake_up_all(&files->resize_wait); return error; } static inline void __set_close_on_exec(unsigned int fd, struct fdtable *fdt, bool set) { if (set) { __set_bit(fd, fdt->close_on_exec); } else { if (test_bit(fd, fdt->close_on_exec)) __clear_bit(fd, fdt->close_on_exec); } } static inline void __set_open_fd(unsigned int fd, struct fdtable *fdt, bool set) { __set_bit(fd, fdt->open_fds); __set_close_on_exec(fd, fdt, set); fd /= BITS_PER_LONG; if (!~fdt->open_fds[fd]) __set_bit(fd, fdt->full_fds_bits); } static inline void __clear_open_fd(unsigned int fd, struct fdtable *fdt) { __clear_bit(fd, fdt->open_fds); fd /= BITS_PER_LONG; if (test_bit(fd, fdt->full_fds_bits)) __clear_bit(fd, fdt->full_fds_bits); } static inline bool fd_is_open(unsigned int fd, const struct fdtable *fdt) { return test_bit(fd, fdt->open_fds); } /* * Note that a sane fdtable size always has to be a multiple of * BITS_PER_LONG, since we have bitmaps that are sized by this. * * punch_hole is optional - when close_range() is asked to unshare * and close, we don't need to copy descriptors in that range, so * a smaller cloned descriptor table might suffice if the last * currently opened descriptor falls into that range. */ static unsigned int sane_fdtable_size(struct fdtable *fdt, struct fd_range *punch_hole) { unsigned int last = find_last_bit(fdt->open_fds, fdt->max_fds); if (last == fdt->max_fds) return NR_OPEN_DEFAULT; if (punch_hole && punch_hole->to >= last && punch_hole->from <= last) { last = find_last_bit(fdt->open_fds, punch_hole->from); if (last == punch_hole->from) return NR_OPEN_DEFAULT; } return ALIGN(last + 1, BITS_PER_LONG); } /* * Allocate a new descriptor table and copy contents from the passed in * instance. Returns a pointer to cloned table on success, ERR_PTR() * on failure. For 'punch_hole' see sane_fdtable_size(). */ struct files_struct *dup_fd(struct files_struct *oldf, struct fd_range *punch_hole) { struct files_struct *newf; struct file **old_fds, **new_fds; unsigned int open_files, i; struct fdtable *old_fdt, *new_fdt; newf = kmem_cache_alloc(files_cachep, GFP_KERNEL); if (!newf) return ERR_PTR(-ENOMEM); atomic_set(&newf->count, 1); spin_lock_init(&newf->file_lock); newf->resize_in_progress = false; init_waitqueue_head(&newf->resize_wait); newf->next_fd = 0; new_fdt = &newf->fdtab; new_fdt->max_fds = NR_OPEN_DEFAULT; new_fdt->close_on_exec = newf->close_on_exec_init; new_fdt->open_fds = newf->open_fds_init; new_fdt->full_fds_bits = newf->full_fds_bits_init; new_fdt->fd = &newf->fd_array[0]; spin_lock(&oldf->file_lock); old_fdt = files_fdtable(oldf); open_files = sane_fdtable_size(old_fdt, punch_hole); /* * Check whether we need to allocate a larger fd array and fd set. */ while (unlikely(open_files > new_fdt->max_fds)) { spin_unlock(&oldf->file_lock); if (new_fdt != &newf->fdtab) __free_fdtable(new_fdt); new_fdt = alloc_fdtable(open_files); if (IS_ERR(new_fdt)) { kmem_cache_free(files_cachep, newf); return ERR_CAST(new_fdt); } /* * Reacquire the oldf lock and a pointer to its fd table * who knows it may have a new bigger fd table. We need * the latest pointer. */ spin_lock(&oldf->file_lock); old_fdt = files_fdtable(oldf); open_files = sane_fdtable_size(old_fdt, punch_hole); } copy_fd_bitmaps(new_fdt, old_fdt, open_files / BITS_PER_LONG); old_fds = old_fdt->fd; new_fds = new_fdt->fd; for (i = open_files; i != 0; i--) { struct file *f = *old_fds++; if (f) { get_file(f); } else { /* * The fd may be claimed in the fd bitmap but not yet * instantiated in the files array if a sibling thread * is partway through open(). So make sure that this * fd is available to the new process. */ __clear_open_fd(open_files - i, new_fdt); } rcu_assign_pointer(*new_fds++, f); } spin_unlock(&oldf->file_lock); /* clear the remainder */ memset(new_fds, 0, (new_fdt->max_fds - open_files) * sizeof(struct file *)); rcu_assign_pointer(newf->fdt, new_fdt); return newf; } static struct fdtable *close_files(struct files_struct * files) { /* * It is safe to dereference the fd table without RCU or * ->file_lock because this is the last reference to the * files structure. */ struct fdtable *fdt = rcu_dereference_raw(files->fdt); unsigned int i, j = 0; for (;;) { unsigned long set; i = j * BITS_PER_LONG; if (i >= fdt->max_fds) break; set = fdt->open_fds[j++]; while (set) { if (set & 1) { struct file *file = fdt->fd[i]; if (file) { filp_close(file, files); cond_resched(); } } i++; set >>= 1; } } return fdt; } void put_files_struct(struct files_struct *files) { if (atomic_dec_and_test(&files->count)) { struct fdtable *fdt = close_files(files); /* free the arrays if they are not embedded */ if (fdt != &files->fdtab) __free_fdtable(fdt); kmem_cache_free(files_cachep, files); } } void exit_files(struct task_struct *tsk) { struct files_struct * files = tsk->files; if (files) { task_lock(tsk); tsk->files = NULL; task_unlock(tsk); put_files_struct(files); } } struct files_struct init_files = { .count = ATOMIC_INIT(1), .fdt = &init_files.fdtab, .fdtab = { .max_fds = NR_OPEN_DEFAULT, .fd = &init_files.fd_array[0], .close_on_exec = init_files.close_on_exec_init, .open_fds = init_files.open_fds_init, .full_fds_bits = init_files.full_fds_bits_init, }, .file_lock = __SPIN_LOCK_UNLOCKED(init_files.file_lock), .resize_wait = __WAIT_QUEUE_HEAD_INITIALIZER(init_files.resize_wait), }; static unsigned int find_next_fd(struct fdtable *fdt, unsigned int start) { unsigned int maxfd = fdt->max_fds; /* always multiple of BITS_PER_LONG */ unsigned int maxbit = maxfd / BITS_PER_LONG; unsigned int bitbit = start / BITS_PER_LONG; unsigned int bit; /* * Try to avoid looking at the second level bitmap */ bit = find_next_zero_bit(&fdt->open_fds[bitbit], BITS_PER_LONG, start & (BITS_PER_LONG - 1)); if (bit < BITS_PER_LONG) return bit + bitbit * BITS_PER_LONG; bitbit = find_next_zero_bit(fdt->full_fds_bits, maxbit, bitbit) * BITS_PER_LONG; if (bitbit >= maxfd) return maxfd; if (bitbit > start) start = bitbit; return find_next_zero_bit(fdt->open_fds, maxfd, start); } /* * allocate a file descriptor, mark it busy. */ static int alloc_fd(unsigned start, unsigned end, unsigned flags) { struct files_struct *files = current->files; unsigned int fd; int error; struct fdtable *fdt; spin_lock(&files->file_lock); repeat: fdt = files_fdtable(files); fd = start; if (fd < files->next_fd) fd = files->next_fd; if (likely(fd < fdt->max_fds)) fd = find_next_fd(fdt, fd); /* * N.B. For clone tasks sharing a files structure, this test * will limit the total number of files that can be opened. */ error = -EMFILE; if (unlikely(fd >= end)) goto out; if (unlikely(fd >= fdt->max_fds)) { error = expand_files(files, fd); if (error < 0) goto out; goto repeat; } if (start <= files->next_fd) files->next_fd = fd + 1; __set_open_fd(fd, fdt, flags & O_CLOEXEC); error = fd; out: spin_unlock(&files->file_lock); return error; } int __get_unused_fd_flags(unsigned flags, unsigned long nofile) { return alloc_fd(0, nofile, flags); } int get_unused_fd_flags(unsigned flags) { return __get_unused_fd_flags(flags, rlimit(RLIMIT_NOFILE)); } EXPORT_SYMBOL(get_unused_fd_flags); static void __put_unused_fd(struct files_struct *files, unsigned int fd) { struct fdtable *fdt = files_fdtable(files); __clear_open_fd(fd, fdt); if (fd < files->next_fd) files->next_fd = fd; } void put_unused_fd(unsigned int fd) { struct files_struct *files = current->files; spin_lock(&files->file_lock); __put_unused_fd(files, fd); spin_unlock(&files->file_lock); } EXPORT_SYMBOL(put_unused_fd); /* * Install a file pointer in the fd array. * * The VFS is full of places where we drop the files lock between * setting the open_fds bitmap and installing the file in the file * array. At any such point, we are vulnerable to a dup2() race * installing a file in the array before us. We need to detect this and * fput() the struct file we are about to overwrite in this case. * * It should never happen - if we allow dup2() do it, _really_ bad things * will follow. * * This consumes the "file" refcount, so callers should treat it * as if they had called fput(file). */ void fd_install(unsigned int fd, struct file *file) { struct files_struct *files = current->files; struct fdtable *fdt; if (WARN_ON_ONCE(unlikely(file->f_mode & FMODE_BACKING))) return; rcu_read_lock_sched(); if (unlikely(files->resize_in_progress)) { rcu_read_unlock_sched(); spin_lock(&files->file_lock); fdt = files_fdtable(files); WARN_ON(fdt->fd[fd] != NULL); rcu_assign_pointer(fdt->fd[fd], file); spin_unlock(&files->file_lock); return; } /* coupled with smp_wmb() in expand_fdtable() */ smp_rmb(); fdt = rcu_dereference_sched(files->fdt); BUG_ON(fdt->fd[fd] != NULL); rcu_assign_pointer(fdt->fd[fd], file); rcu_read_unlock_sched(); } EXPORT_SYMBOL(fd_install); /** * file_close_fd_locked - return file associated with fd * @files: file struct to retrieve file from * @fd: file descriptor to retrieve file for * * Doesn't take a separate reference count. * * Context: files_lock must be held. * * Returns: The file associated with @fd (NULL if @fd is not open) */ struct file *file_close_fd_locked(struct files_struct *files, unsigned fd) { struct fdtable *fdt = files_fdtable(files); struct file *file; lockdep_assert_held(&files->file_lock); if (fd >= fdt->max_fds) return NULL; fd = array_index_nospec(fd, fdt->max_fds); file = fdt->fd[fd]; if (file) { rcu_assign_pointer(fdt->fd[fd], NULL); __put_unused_fd(files, fd); } return file; } int close_fd(unsigned fd) { struct files_struct *files = current->files; struct file *file; spin_lock(&files->file_lock); file = file_close_fd_locked(files, fd); spin_unlock(&files->file_lock); if (!file) return -EBADF; return filp_close(file, files); } EXPORT_SYMBOL(close_fd); /** * last_fd - return last valid index into fd table * @fdt: File descriptor table. * * Context: Either rcu read lock or files_lock must be held. * * Returns: Last valid index into fdtable. */ static inline unsigned last_fd(struct fdtable *fdt) { return fdt->max_fds - 1; } static inline void __range_cloexec(struct files_struct *cur_fds, unsigned int fd, unsigned int max_fd) { struct fdtable *fdt; /* make sure we're using the correct maximum value */ spin_lock(&cur_fds->file_lock); fdt = files_fdtable(cur_fds); max_fd = min(last_fd(fdt), max_fd); if (fd <= max_fd) bitmap_set(fdt->close_on_exec, fd, max_fd - fd + 1); spin_unlock(&cur_fds->file_lock); } static inline void __range_close(struct files_struct *files, unsigned int fd, unsigned int max_fd) { struct file *file; unsigned n; spin_lock(&files->file_lock); n = last_fd(files_fdtable(files)); max_fd = min(max_fd, n); for (; fd <= max_fd; fd++) { file = file_close_fd_locked(files, fd); if (file) { spin_unlock(&files->file_lock); filp_close(file, files); cond_resched(); spin_lock(&files->file_lock); } else if (need_resched()) { spin_unlock(&files->file_lock); cond_resched(); spin_lock(&files->file_lock); } } spin_unlock(&files->file_lock); } /** * sys_close_range() - Close all file descriptors in a given range. * * @fd: starting file descriptor to close * @max_fd: last file descriptor to close * @flags: CLOSE_RANGE flags. * * This closes a range of file descriptors. All file descriptors * from @fd up to and including @max_fd are closed. * Currently, errors to close a given file descriptor are ignored. */ SYSCALL_DEFINE3(close_range, unsigned int, fd, unsigned int, max_fd, unsigned int, flags) { struct task_struct *me = current; struct files_struct *cur_fds = me->files, *fds = NULL; if (flags & ~(CLOSE_RANGE_UNSHARE | CLOSE_RANGE_CLOEXEC)) return -EINVAL; if (fd > max_fd) return -EINVAL; if ((flags & CLOSE_RANGE_UNSHARE) && atomic_read(&cur_fds->count) > 1) { struct fd_range range = {fd, max_fd}, *punch_hole = ⦥ /* * If the caller requested all fds to be made cloexec we always * copy all of the file descriptors since they still want to * use them. */ if (flags & CLOSE_RANGE_CLOEXEC) punch_hole = NULL; fds = dup_fd(cur_fds, punch_hole); if (IS_ERR(fds)) return PTR_ERR(fds); /* * We used to share our file descriptor table, and have now * created a private one, make sure we're using it below. */ swap(cur_fds, fds); } if (flags & CLOSE_RANGE_CLOEXEC) __range_cloexec(cur_fds, fd, max_fd); else __range_close(cur_fds, fd, max_fd); if (fds) { /* * We're done closing the files we were supposed to. Time to install * the new file descriptor table and drop the old one. */ task_lock(me); me->files = cur_fds; task_unlock(me); put_files_struct(fds); } return 0; } /** * file_close_fd - return file associated with fd * @fd: file descriptor to retrieve file for * * Doesn't take a separate reference count. * * Returns: The file associated with @fd (NULL if @fd is not open) */ struct file *file_close_fd(unsigned int fd) { struct files_struct *files = current->files; struct file *file; spin_lock(&files->file_lock); file = file_close_fd_locked(files, fd); spin_unlock(&files->file_lock); return file; } void do_close_on_exec(struct files_struct *files) { unsigned i; struct fdtable *fdt; /* exec unshares first */ spin_lock(&files->file_lock); for (i = 0; ; i++) { unsigned long set; unsigned fd = i * BITS_PER_LONG; fdt = files_fdtable(files); if (fd >= fdt->max_fds) break; set = fdt->close_on_exec[i]; if (!set) continue; fdt->close_on_exec[i] = 0; for ( ; set ; fd++, set >>= 1) { struct file *file; if (!(set & 1)) continue; file = fdt->fd[fd]; if (!file) continue; rcu_assign_pointer(fdt->fd[fd], NULL); __put_unused_fd(files, fd); spin_unlock(&files->file_lock); filp_close(file, files); cond_resched(); spin_lock(&files->file_lock); } } spin_unlock(&files->file_lock); } static struct file *__get_file_rcu(struct file __rcu **f) { struct file __rcu *file; struct file __rcu *file_reloaded; struct file __rcu *file_reloaded_cmp; file = rcu_dereference_raw(*f); if (!file) return NULL; if (unlikely(!file_ref_get(&file->f_ref))) return ERR_PTR(-EAGAIN); file_reloaded = rcu_dereference_raw(*f); /* * Ensure that all accesses have a dependency on the load from * rcu_dereference_raw() above so we get correct ordering * between reuse/allocation and the pointer check below. */ file_reloaded_cmp = file_reloaded; OPTIMIZER_HIDE_VAR(file_reloaded_cmp); /* * file_ref_get() above provided a full memory barrier when we * acquired a reference. * * This is paired with the write barrier from assigning to the * __rcu protected file pointer so that if that pointer still * matches the current file, we know we have successfully * acquired a reference to the right file. * * If the pointers don't match the file has been reallocated by * SLAB_TYPESAFE_BY_RCU. */ if (file == file_reloaded_cmp) return file_reloaded; fput(file); return ERR_PTR(-EAGAIN); } /** * get_file_rcu - try go get a reference to a file under rcu * @f: the file to get a reference on * * This function tries to get a reference on @f carefully verifying that * @f hasn't been reused. * * This function should rarely have to be used and only by users who * understand the implications of SLAB_TYPESAFE_BY_RCU. Try to avoid it. * * Return: Returns @f with the reference count increased or NULL. */ struct file *get_file_rcu(struct file __rcu **f) { for (;;) { struct file __rcu *file; file = __get_file_rcu(f); if (!IS_ERR(file)) return file; } } EXPORT_SYMBOL_GPL(get_file_rcu); /** * get_file_active - try go get a reference to a file * @f: the file to get a reference on * * In contast to get_file_rcu() the pointer itself isn't part of the * reference counting. * * This function should rarely have to be used and only by users who * understand the implications of SLAB_TYPESAFE_BY_RCU. Try to avoid it. * * Return: Returns @f with the reference count increased or NULL. */ struct file *get_file_active(struct file **f) { struct file __rcu *file; rcu_read_lock(); file = __get_file_rcu(f); rcu_read_unlock(); if (IS_ERR(file)) file = NULL; return file; } EXPORT_SYMBOL_GPL(get_file_active); static inline struct file *__fget_files_rcu(struct files_struct *files, unsigned int fd, fmode_t mask) { for (;;) { struct file *file; struct fdtable *fdt = rcu_dereference_raw(files->fdt); struct file __rcu **fdentry; unsigned long nospec_mask; /* Mask is a 0 for invalid fd's, ~0 for valid ones */ nospec_mask = array_index_mask_nospec(fd, fdt->max_fds); /* * fdentry points to the 'fd' offset, or fdt->fd[0]. * Loading from fdt->fd[0] is always safe, because the * array always exists. */ fdentry = fdt->fd + (fd & nospec_mask); /* Do the load, then mask any invalid result */ file = rcu_dereference_raw(*fdentry); file = (void *)(nospec_mask & (unsigned long)file); if (unlikely(!file)) return NULL; /* * Ok, we have a file pointer that was valid at * some point, but it might have become stale since. * * We need to confirm it by incrementing the refcount * and then check the lookup again. * * file_ref_get() gives us a full memory barrier. We * only really need an 'acquire' one to protect the * loads below, but we don't have that. */ if (unlikely(!file_ref_get(&file->f_ref))) continue; /* * Such a race can take two forms: * * (a) the file ref already went down to zero and the * file hasn't been reused yet or the file count * isn't zero but the file has already been reused. * * (b) the file table entry has changed under us. * Note that we don't need to re-check the 'fdt->fd' * pointer having changed, because it always goes * hand-in-hand with 'fdt'. * * If so, we need to put our ref and try again. */ if (unlikely(file != rcu_dereference_raw(*fdentry)) || unlikely(rcu_dereference_raw(files->fdt) != fdt)) { fput(file); continue; } /* * This isn't the file we're looking for or we're not * allowed to get a reference to it. */ if (unlikely(file->f_mode & mask)) { fput(file); return NULL; } /* * Ok, we have a ref to the file, and checked that it * still exists. */ return file; } } static struct file *__fget_files(struct files_struct *files, unsigned int fd, fmode_t mask) { struct file *file; rcu_read_lock(); file = __fget_files_rcu(files, fd, mask); rcu_read_unlock(); return file; } static inline struct file *__fget(unsigned int fd, fmode_t mask) { return __fget_files(current->files, fd, mask); } struct file *fget(unsigned int fd) { return __fget(fd, FMODE_PATH); } EXPORT_SYMBOL(fget); struct file *fget_raw(unsigned int fd) { return __fget(fd, 0); } EXPORT_SYMBOL(fget_raw); struct file *fget_task(struct task_struct *task, unsigned int fd) { struct file *file = NULL; task_lock(task); if (task->files) file = __fget_files(task->files, fd, 0); task_unlock(task); return file; } struct file *fget_task_next(struct task_struct *task, unsigned int *ret_fd) { /* Must be called with rcu_read_lock held */ struct files_struct *files; unsigned int fd = *ret_fd; struct file *file = NULL; task_lock(task); files = task->files; if (files) { rcu_read_lock(); for (; fd < files_fdtable(files)->max_fds; fd++) { file = __fget_files_rcu(files, fd, 0); if (file) break; } rcu_read_unlock(); } task_unlock(task); *ret_fd = fd; return file; } EXPORT_SYMBOL(fget_task_next); /* * Lightweight file lookup - no refcnt increment if fd table isn't shared. * * You can use this instead of fget if you satisfy all of the following * conditions: * 1) You must call fput_light before exiting the syscall and returning control * to userspace (i.e. you cannot remember the returned struct file * after * returning to userspace). * 2) You must not call filp_close on the returned struct file * in between * calls to fget_light and fput_light. * 3) You must not clone the current task in between the calls to fget_light * and fput_light. * * The fput_needed flag returned by fget_light should be passed to the * corresponding fput_light. * * (As an exception to rule 2, you can call filp_close between fget_light and * fput_light provided that you capture a real refcount with get_file before * the call to filp_close, and ensure that this real refcount is fput *after* * the fput_light call.) * * See also the documentation in rust/kernel/file.rs. */ static inline struct fd __fget_light(unsigned int fd, fmode_t mask) { struct files_struct *files = current->files; struct file *file; /* * If another thread is concurrently calling close_fd() followed * by put_files_struct(), we must not observe the old table * entry combined with the new refcount - otherwise we could * return a file that is concurrently being freed. * * atomic_read_acquire() pairs with atomic_dec_and_test() in * put_files_struct(). */ if (likely(atomic_read_acquire(&files->count) == 1)) { file = files_lookup_fd_raw(files, fd); if (!file || unlikely(file->f_mode & mask)) return EMPTY_FD; return BORROWED_FD(file); } else { file = __fget_files(files, fd, mask); if (!file) return EMPTY_FD; return CLONED_FD(file); } } struct fd fdget(unsigned int fd) { return __fget_light(fd, FMODE_PATH); } EXPORT_SYMBOL(fdget); struct fd fdget_raw(unsigned int fd) { return __fget_light(fd, 0); } /* * Try to avoid f_pos locking. We only need it if the * file is marked for FMODE_ATOMIC_POS, and it can be * accessed multiple ways. * * Always do it for directories, because pidfd_getfd() * can make a file accessible even if it otherwise would * not be, and for directories this is a correctness * issue, not a "POSIX requirement". */ static inline bool file_needs_f_pos_lock(struct file *file) { return (file->f_mode & FMODE_ATOMIC_POS) && (file_count(file) > 1 || file->f_op->iterate_shared); } struct fd fdget_pos(unsigned int fd) { struct fd f = fdget(fd); struct file *file = fd_file(f); if (file && file_needs_f_pos_lock(file)) { f.word |= FDPUT_POS_UNLOCK; mutex_lock(&file->f_pos_lock); } return f; } void __f_unlock_pos(struct file *f) { mutex_unlock(&f->f_pos_lock); } /* * We only lock f_pos if we have threads or if the file might be * shared with another process. In both cases we'll have an elevated * file count (done either by fdget() or by fork()). */ void set_close_on_exec(unsigned int fd, int flag) { struct files_struct *files = current->files; spin_lock(&files->file_lock); __set_close_on_exec(fd, files_fdtable(files), flag); spin_unlock(&files->file_lock); } bool get_close_on_exec(unsigned int fd) { bool res; rcu_read_lock(); res = close_on_exec(fd, current->files); rcu_read_unlock(); return res; } static int do_dup2(struct files_struct *files, struct file *file, unsigned fd, unsigned flags) __releases(&files->file_lock) { struct file *tofree; struct fdtable *fdt; /* * We need to detect attempts to do dup2() over allocated but still * not finished descriptor. NB: OpenBSD avoids that at the price of * extra work in their equivalent of fget() - they insert struct * file immediately after grabbing descriptor, mark it larval if * more work (e.g. actual opening) is needed and make sure that * fget() treats larval files as absent. Potentially interesting, * but while extra work in fget() is trivial, locking implications * and amount of surgery on open()-related paths in VFS are not. * FreeBSD fails with -EBADF in the same situation, NetBSD "solution" * deadlocks in rather amusing ways, AFAICS. All of that is out of * scope of POSIX or SUS, since neither considers shared descriptor * tables and this condition does not arise without those. */ fdt = files_fdtable(files); fd = array_index_nospec(fd, fdt->max_fds); tofree = fdt->fd[fd]; if (!tofree && fd_is_open(fd, fdt)) goto Ebusy; get_file(file); rcu_assign_pointer(fdt->fd[fd], file); __set_open_fd(fd, fdt, flags & O_CLOEXEC); spin_unlock(&files->file_lock); if (tofree) filp_close(tofree, files); return fd; Ebusy: spin_unlock(&files->file_lock); return -EBUSY; } int replace_fd(unsigned fd, struct file *file, unsigned flags) { int err; struct files_struct *files = current->files; if (!file) return close_fd(fd); if (fd >= rlimit(RLIMIT_NOFILE)) return -EBADF; spin_lock(&files->file_lock); err = expand_files(files, fd); if (unlikely(err < 0)) goto out_unlock; return do_dup2(files, file, fd, flags); out_unlock: spin_unlock(&files->file_lock); return err; } /** * receive_fd() - Install received file into file descriptor table * @file: struct file that was received from another process * @ufd: __user pointer to write new fd number to * @o_flags: the O_* flags to apply to the new fd entry * * Installs a received file into the file descriptor table, with appropriate * checks and count updates. Optionally writes the fd number to userspace, if * @ufd is non-NULL. * * This helper handles its own reference counting of the incoming * struct file. * * Returns newly install fd or -ve on error. */ int receive_fd(struct file *file, int __user *ufd, unsigned int o_flags) { int new_fd; int error; error = security_file_receive(file); if (error) return error; new_fd = get_unused_fd_flags(o_flags); if (new_fd < 0) return new_fd; if (ufd) { error = put_user(new_fd, ufd); if (error) { put_unused_fd(new_fd); return error; } } fd_install(new_fd, get_file(file)); __receive_sock(file); return new_fd; } EXPORT_SYMBOL_GPL(receive_fd); int receive_fd_replace(int new_fd, struct file *file, unsigned int o_flags) { int error; error = security_file_receive(file); if (error) return error; error = replace_fd(new_fd, file, o_flags); if (error) return error; __receive_sock(file); return new_fd; } static int ksys_dup3(unsigned int oldfd, unsigned int newfd, int flags) { int err = -EBADF; struct file *file; struct files_struct *files = current->files; if ((flags & ~O_CLOEXEC) != 0) return -EINVAL; if (unlikely(oldfd == newfd)) return -EINVAL; if (newfd >= rlimit(RLIMIT_NOFILE)) return -EBADF; spin_lock(&files->file_lock); err = expand_files(files, newfd); file = files_lookup_fd_locked(files, oldfd); if (unlikely(!file)) goto Ebadf; if (unlikely(err < 0)) { if (err == -EMFILE) goto Ebadf; goto out_unlock; } return do_dup2(files, file, newfd, flags); Ebadf: err = -EBADF; out_unlock: spin_unlock(&files->file_lock); return err; } SYSCALL_DEFINE3(dup3, unsigned int, oldfd, unsigned int, newfd, int, flags) { return ksys_dup3(oldfd, newfd, flags); } SYSCALL_DEFINE2(dup2, unsigned int, oldfd, unsigned int, newfd) { if (unlikely(newfd == oldfd)) { /* corner case */ struct files_struct *files = current->files; struct file *f; int retval = oldfd; rcu_read_lock(); f = __fget_files_rcu(files, oldfd, 0); if (!f) retval = -EBADF; rcu_read_unlock(); if (f) fput(f); return retval; } return ksys_dup3(oldfd, newfd, 0); } SYSCALL_DEFINE1(dup, unsigned int, fildes) { int ret = -EBADF; struct file *file = fget_raw(fildes); if (file) { ret = get_unused_fd_flags(0); if (ret >= 0) fd_install(ret, file); else fput(file); } return ret; } int f_dupfd(unsigned int from, struct file *file, unsigned flags) { unsigned long nofile = rlimit(RLIMIT_NOFILE); int err; if (from >= nofile) return -EINVAL; err = alloc_fd(from, nofile, flags); if (err >= 0) { get_file(file); fd_install(err, file); } return err; } int iterate_fd(struct files_struct *files, unsigned n, int (*f)(const void *, struct file *, unsigned), const void *p) { struct fdtable *fdt; int res = 0; if (!files) return 0; spin_lock(&files->file_lock); for (fdt = files_fdtable(files); n < fdt->max_fds; n++) { struct file *file; file = rcu_dereference_check_fdtable(files, fdt->fd[n]); if (!file) continue; res = f(p, file, n); if (res) break; } spin_unlock(&files->file_lock); return res; } EXPORT_SYMBOL(iterate_fd); |
| 7 7 7 7 7 7 7 7 7 7 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 | // SPDX-License-Identifier: GPL-2.0-or-later /* * Fast Userspace Mutexes (which I call "Futexes!"). * (C) Rusty Russell, IBM 2002 * * Generalized futexes, futex requeueing, misc fixes by Ingo Molnar * (C) Copyright 2003 Red Hat Inc, All Rights Reserved * * Removed page pinning, fix privately mapped COW pages and other cleanups * (C) Copyright 2003, 2004 Jamie Lokier * * Robust futex support started by Ingo Molnar * (C) Copyright 2006 Red Hat Inc, All Rights Reserved * Thanks to Thomas Gleixner for suggestions, analysis and fixes. * * PI-futex support started by Ingo Molnar and Thomas Gleixner * Copyright (C) 2006 Red Hat, Inc., Ingo Molnar <mingo@redhat.com> * Copyright (C) 2006 Timesys Corp., Thomas Gleixner <tglx@timesys.com> * * PRIVATE futexes by Eric Dumazet * Copyright (C) 2007 Eric Dumazet <dada1@cosmosbay.com> * * Requeue-PI support by Darren Hart <dvhltc@us.ibm.com> * Copyright (C) IBM Corporation, 2009 * Thanks to Thomas Gleixner for conceptual design and careful reviews. * * Thanks to Ben LaHaise for yelling "hashed waitqueues" loudly * enough at me, Linus for the original (flawed) idea, Matthew * Kirkwood for proof-of-concept implementation. * * "The futexes are also cursed." * "But they come in a choice of three flavours!" */ #include <linux/compat.h> #include <linux/jhash.h> #include <linux/pagemap.h> #include <linux/debugfs.h> #include <linux/plist.h> #include <linux/memblock.h> #include <linux/fault-inject.h> #include <linux/slab.h> #include "futex.h" #include "../locking/rtmutex_common.h" /* * The base of the bucket array and its size are always used together * (after initialization only in futex_hash()), so ensure that they * reside in the same cacheline. */ static struct { struct futex_hash_bucket *queues; unsigned long hashsize; } __futex_data __read_mostly __aligned(2*sizeof(long)); #define futex_queues (__futex_data.queues) #define futex_hashsize (__futex_data.hashsize) /* * Fault injections for futexes. */ #ifdef CONFIG_FAIL_FUTEX static struct { struct fault_attr attr; bool ignore_private; } fail_futex = { .attr = FAULT_ATTR_INITIALIZER, .ignore_private = false, }; static int __init setup_fail_futex(char *str) { return setup_fault_attr(&fail_futex.attr, str); } __setup("fail_futex=", setup_fail_futex); bool should_fail_futex(bool fshared) { if (fail_futex.ignore_private && !fshared) return false; return should_fail(&fail_futex.attr, 1); } #ifdef CONFIG_FAULT_INJECTION_DEBUG_FS static int __init fail_futex_debugfs(void) { umode_t mode = S_IFREG | S_IRUSR | S_IWUSR; struct dentry *dir; dir = fault_create_debugfs_attr("fail_futex", NULL, &fail_futex.attr); if (IS_ERR(dir)) return PTR_ERR(dir); debugfs_create_bool("ignore-private", mode, dir, &fail_futex.ignore_private); return 0; } late_initcall(fail_futex_debugfs); #endif /* CONFIG_FAULT_INJECTION_DEBUG_FS */ #endif /* CONFIG_FAIL_FUTEX */ /** * futex_hash - Return the hash bucket in the global hash * @key: Pointer to the futex key for which the hash is calculated * * We hash on the keys returned from get_futex_key (see below) and return the * corresponding hash bucket in the global hash. */ struct futex_hash_bucket *futex_hash(union futex_key *key) { u32 hash = jhash2((u32 *)key, offsetof(typeof(*key), both.offset) / 4, key->both.offset); return &futex_queues[hash & (futex_hashsize - 1)]; } /** * futex_setup_timer - set up the sleeping hrtimer. * @time: ptr to the given timeout value * @timeout: the hrtimer_sleeper structure to be set up * @flags: futex flags * @range_ns: optional range in ns * * Return: Initialized hrtimer_sleeper structure or NULL if no timeout * value given */ struct hrtimer_sleeper * futex_setup_timer(ktime_t *time, struct hrtimer_sleeper *timeout, int flags, u64 range_ns) { if (!time) return NULL; hrtimer_setup_sleeper_on_stack(timeout, (flags & FLAGS_CLOCKRT) ? CLOCK_REALTIME : CLOCK_MONOTONIC, HRTIMER_MODE_ABS); /* * If range_ns is 0, calling hrtimer_set_expires_range_ns() is * effectively the same as calling hrtimer_set_expires(). */ hrtimer_set_expires_range_ns(&timeout->timer, *time, range_ns); return timeout; } /* * Generate a machine wide unique identifier for this inode. * * This relies on u64 not wrapping in the life-time of the machine; which with * 1ns resolution means almost 585 years. * * This further relies on the fact that a well formed program will not unmap * the file while it has a (shared) futex waiting on it. This mapping will have * a file reference which pins the mount and inode. * * If for some reason an inode gets evicted and read back in again, it will get * a new sequence number and will _NOT_ match, even though it is the exact same * file. * * It is important that futex_match() will never have a false-positive, esp. * for PI futexes that can mess up the state. The above argues that false-negatives * are only possible for malformed programs. */ static u64 get_inode_sequence_number(struct inode *inode) { static atomic64_t i_seq; u64 old; /* Does the inode already have a sequence number? */ old = atomic64_read(&inode->i_sequence); if (likely(old)) return old; for (;;) { u64 new = atomic64_inc_return(&i_seq); if (WARN_ON_ONCE(!new)) continue; old = 0; if (!atomic64_try_cmpxchg_relaxed(&inode->i_sequence, &old, new)) return old; return new; } } /** * get_futex_key() - Get parameters which are the keys for a futex * @uaddr: virtual address of the futex * @flags: FLAGS_* * @key: address where result is stored. * @rw: mapping needs to be read/write (values: FUTEX_READ, * FUTEX_WRITE) * * Return: a negative error code or 0 * * The key words are stored in @key on success. * * For shared mappings (when @fshared), the key is: * * ( inode->i_sequence, page->index, offset_within_page ) * * [ also see get_inode_sequence_number() ] * * For private mappings (or when !@fshared), the key is: * * ( current->mm, address, 0 ) * * This allows (cross process, where applicable) identification of the futex * without keeping the page pinned for the duration of the FUTEX_WAIT. * * lock_page() might sleep, the caller should not hold a spinlock. */ int get_futex_key(u32 __user *uaddr, unsigned int flags, union futex_key *key, enum futex_access rw) { unsigned long address = (unsigned long)uaddr; struct mm_struct *mm = current->mm; struct page *page; struct folio *folio; struct address_space *mapping; int err, ro = 0; bool fshared; fshared = flags & FLAGS_SHARED; /* * The futex address must be "naturally" aligned. */ key->both.offset = address % PAGE_SIZE; if (unlikely((address % sizeof(u32)) != 0)) return -EINVAL; address -= key->both.offset; if (unlikely(!access_ok(uaddr, sizeof(u32)))) return -EFAULT; if (unlikely(should_fail_futex(fshared))) return -EFAULT; /* * PROCESS_PRIVATE futexes are fast. * As the mm cannot disappear under us and the 'key' only needs * virtual address, we dont even have to find the underlying vma. * Note : We do have to check 'uaddr' is a valid user address, * but access_ok() should be faster than find_vma() */ if (!fshared) { /* * On no-MMU, shared futexes are treated as private, therefore * we must not include the current process in the key. Since * there is only one address space, the address is a unique key * on its own. */ if (IS_ENABLED(CONFIG_MMU)) key->private.mm = mm; else key->private.mm = NULL; key->private.address = address; return 0; } again: /* Ignore any VERIFY_READ mapping (futex common case) */ if (unlikely(should_fail_futex(true))) return -EFAULT; err = get_user_pages_fast(address, 1, FOLL_WRITE, &page); /* * If write access is not required (eg. FUTEX_WAIT), try * and get read-only access. */ if (err == -EFAULT && rw == FUTEX_READ) { err = get_user_pages_fast(address, 1, 0, &page); ro = 1; } if (err < 0) return err; else err = 0; /* * The treatment of mapping from this point on is critical. The folio * lock protects many things but in this context the folio lock * stabilizes mapping, prevents inode freeing in the shared * file-backed region case and guards against movement to swap cache. * * Strictly speaking the folio lock is not needed in all cases being * considered here and folio lock forces unnecessarily serialization. * From this point on, mapping will be re-verified if necessary and * folio lock will be acquired only if it is unavoidable * * Mapping checks require the folio so it is looked up now. For * anonymous pages, it does not matter if the folio is split * in the future as the key is based on the address. For * filesystem-backed pages, the precise page is required as the * index of the page determines the key. */ folio = page_folio(page); mapping = READ_ONCE(folio->mapping); /* * If folio->mapping is NULL, then it cannot be an anonymous * page; but it might be the ZERO_PAGE or in the gate area or * in a special mapping (all cases which we are happy to fail); * or it may have been a good file page when get_user_pages_fast * found it, but truncated or holepunched or subjected to * invalidate_complete_page2 before we got the folio lock (also * cases which we are happy to fail). And we hold a reference, * so refcount care in invalidate_inode_page's remove_mapping * prevents drop_caches from setting mapping to NULL beneath us. * * The case we do have to guard against is when memory pressure made * shmem_writepage move it from filecache to swapcache beneath us: * an unlikely race, but we do need to retry for folio->mapping. */ if (unlikely(!mapping)) { int shmem_swizzled; /* * Folio lock is required to identify which special case above * applies. If this is really a shmem page then the folio lock * will prevent unexpected transitions. */ folio_lock(folio); shmem_swizzled = folio_test_swapcache(folio) || folio->mapping; folio_unlock(folio); folio_put(folio); if (shmem_swizzled) goto again; return -EFAULT; } /* * Private mappings are handled in a simple way. * * If the futex key is stored in anonymous memory, then the associated * object is the mm which is implicitly pinned by the calling process. * * NOTE: When userspace waits on a MAP_SHARED mapping, even if * it's a read-only handle, it's expected that futexes attach to * the object not the particular process. */ if (folio_test_anon(folio)) { /* * A RO anonymous page will never change and thus doesn't make * sense for futex operations. */ if (unlikely(should_fail_futex(true)) || ro) { err = -EFAULT; goto out; } key->both.offset |= FUT_OFF_MMSHARED; /* ref taken on mm */ key->private.mm = mm; key->private.address = address; } else { struct inode *inode; /* * The associated futex object in this case is the inode and * the folio->mapping must be traversed. Ordinarily this should * be stabilised under folio lock but it's not strictly * necessary in this case as we just want to pin the inode, not * update i_pages or anything like that. * * The RCU read lock is taken as the inode is finally freed * under RCU. If the mapping still matches expectations then the * mapping->host can be safely accessed as being a valid inode. */ rcu_read_lock(); if (READ_ONCE(folio->mapping) != mapping) { rcu_read_unlock(); folio_put(folio); goto again; } inode = READ_ONCE(mapping->host); if (!inode) { rcu_read_unlock(); folio_put(folio); goto again; } key->both.offset |= FUT_OFF_INODE; /* inode-based key */ key->shared.i_seq = get_inode_sequence_number(inode); key->shared.pgoff = page_pgoff(folio, page); rcu_read_unlock(); } out: folio_put(folio); return err; } /** * fault_in_user_writeable() - Fault in user address and verify RW access * @uaddr: pointer to faulting user space address * * Slow path to fixup the fault we just took in the atomic write * access to @uaddr. * * We have no generic implementation of a non-destructive write to the * user address. We know that we faulted in the atomic pagefault * disabled section so we can as well avoid the #PF overhead by * calling get_user_pages() right away. */ int fault_in_user_writeable(u32 __user *uaddr) { struct mm_struct *mm = current->mm; int ret; mmap_read_lock(mm); ret = fixup_user_fault(mm, (unsigned long)uaddr, FAULT_FLAG_WRITE, NULL); mmap_read_unlock(mm); return ret < 0 ? ret : 0; } /** * futex_top_waiter() - Return the highest priority waiter on a futex * @hb: the hash bucket the futex_q's reside in * @key: the futex key (to distinguish it from other futex futex_q's) * * Must be called with the hb lock held. */ struct futex_q *futex_top_waiter(struct futex_hash_bucket *hb, union futex_key *key) { struct futex_q *this; plist_for_each_entry(this, &hb->chain, list) { if (futex_match(&this->key, key)) return this; } return NULL; } /** * wait_for_owner_exiting - Block until the owner has exited * @ret: owner's current futex lock status * @exiting: Pointer to the exiting task * * Caller must hold a refcount on @exiting. */ void wait_for_owner_exiting(int ret, struct task_struct *exiting) { if (ret != -EBUSY) { WARN_ON_ONCE(exiting); return; } if (WARN_ON_ONCE(ret == -EBUSY && !exiting)) return; mutex_lock(&exiting->futex_exit_mutex); /* * No point in doing state checking here. If the waiter got here * while the task was in exec()->exec_futex_release() then it can * have any FUTEX_STATE_* value when the waiter has acquired the * mutex. OK, if running, EXITING or DEAD if it reached exit() * already. Highly unlikely and not a problem. Just one more round * through the futex maze. */ mutex_unlock(&exiting->futex_exit_mutex); put_task_struct(exiting); } /** * __futex_unqueue() - Remove the futex_q from its futex_hash_bucket * @q: The futex_q to unqueue * * The q->lock_ptr must not be NULL and must be held by the caller. */ void __futex_unqueue(struct futex_q *q) { struct futex_hash_bucket *hb; if (WARN_ON_SMP(!q->lock_ptr) || WARN_ON(plist_node_empty(&q->list))) return; lockdep_assert_held(q->lock_ptr); hb = container_of(q->lock_ptr, struct futex_hash_bucket, lock); plist_del(&q->list, &hb->chain); futex_hb_waiters_dec(hb); } /* The key must be already stored in q->key. */ struct futex_hash_bucket *futex_q_lock(struct futex_q *q) __acquires(&hb->lock) { struct futex_hash_bucket *hb; hb = futex_hash(&q->key); /* * Increment the counter before taking the lock so that * a potential waker won't miss a to-be-slept task that is * waiting for the spinlock. This is safe as all futex_q_lock() * users end up calling futex_queue(). Similarly, for housekeeping, * decrement the counter at futex_q_unlock() when some error has * occurred and we don't end up adding the task to the list. */ futex_hb_waiters_inc(hb); /* implies smp_mb(); (A) */ q->lock_ptr = &hb->lock; spin_lock(&hb->lock); return hb; } void futex_q_unlock(struct futex_hash_bucket *hb) __releases(&hb->lock) { spin_unlock(&hb->lock); futex_hb_waiters_dec(hb); } void __futex_queue(struct futex_q *q, struct futex_hash_bucket *hb) { int prio; /* * The priority used to register this element is * - either the real thread-priority for the real-time threads * (i.e. threads with a priority lower than MAX_RT_PRIO) * - or MAX_RT_PRIO for non-RT threads. * Thus, all RT-threads are woken first in priority order, and * the others are woken last, in FIFO order. */ prio = min(current->normal_prio, MAX_RT_PRIO); plist_node_init(&q->list, prio); plist_add(&q->list, &hb->chain); q->task = current; } /** * futex_unqueue() - Remove the futex_q from its futex_hash_bucket * @q: The futex_q to unqueue * * The q->lock_ptr must not be held by the caller. A call to futex_unqueue() must * be paired with exactly one earlier call to futex_queue(). * * Return: * - 1 - if the futex_q was still queued (and we removed unqueued it); * - 0 - if the futex_q was already removed by the waking thread */ int futex_unqueue(struct futex_q *q) { spinlock_t *lock_ptr; int ret = 0; /* In the common case we don't take the spinlock, which is nice. */ retry: /* * q->lock_ptr can change between this read and the following spin_lock. * Use READ_ONCE to forbid the compiler from reloading q->lock_ptr and * optimizing lock_ptr out of the logic below. */ lock_ptr = READ_ONCE(q->lock_ptr); if (lock_ptr != NULL) { spin_lock(lock_ptr); /* * q->lock_ptr can change between reading it and * spin_lock(), causing us to take the wrong lock. This * corrects the race condition. * * Reasoning goes like this: if we have the wrong lock, * q->lock_ptr must have changed (maybe several times) * between reading it and the spin_lock(). It can * change again after the spin_lock() but only if it was * already changed before the spin_lock(). It cannot, * however, change back to the original value. Therefore * we can detect whether we acquired the correct lock. */ if (unlikely(lock_ptr != q->lock_ptr)) { spin_unlock(lock_ptr); goto retry; } __futex_unqueue(q); BUG_ON(q->pi_state); spin_unlock(lock_ptr); ret = 1; } return ret; } /* * PI futexes can not be requeued and must remove themselves from the hash * bucket. The hash bucket lock (i.e. lock_ptr) is held. */ void futex_unqueue_pi(struct futex_q *q) { /* * If the lock was not acquired (due to timeout or signal) then the * rt_waiter is removed before futex_q is. If this is observed by * an unlocker after dropping the rtmutex wait lock and before * acquiring the hash bucket lock, then the unlocker dequeues the * futex_q from the hash bucket list to guarantee consistent state * vs. userspace. Therefore the dequeue here must be conditional. */ if (!plist_node_empty(&q->list)) __futex_unqueue(q); BUG_ON(!q->pi_state); put_pi_state(q->pi_state); q->pi_state = NULL; } /* Constants for the pending_op argument of handle_futex_death */ #define HANDLE_DEATH_PENDING true #define HANDLE_DEATH_LIST false /* * Process a futex-list entry, check whether it's owned by the * dying task, and do notification if so: */ static int handle_futex_death(u32 __user *uaddr, struct task_struct *curr, bool pi, bool pending_op) { u32 uval, nval, mval; pid_t owner; int err; /* Futex address must be 32bit aligned */ if ((((unsigned long)uaddr) % sizeof(*uaddr)) != 0) return -1; retry: if (get_user(uval, uaddr)) return -1; /* * Special case for regular (non PI) futexes. The unlock path in * user space has two race scenarios: * * 1. The unlock path releases the user space futex value and * before it can execute the futex() syscall to wake up * waiters it is killed. * * 2. A woken up waiter is killed before it can acquire the * futex in user space. * * In the second case, the wake up notification could be generated * by the unlock path in user space after setting the futex value * to zero or by the kernel after setting the OWNER_DIED bit below. * * In both cases the TID validation below prevents a wakeup of * potential waiters which can cause these waiters to block * forever. * * In both cases the following conditions are met: * * 1) task->robust_list->list_op_pending != NULL * @pending_op == true * 2) The owner part of user space futex value == 0 * 3) Regular futex: @pi == false * * If these conditions are met, it is safe to attempt waking up a * potential waiter without touching the user space futex value and * trying to set the OWNER_DIED bit. If the futex value is zero, * the rest of the user space mutex state is consistent, so a woken * waiter will just take over the uncontended futex. Setting the * OWNER_DIED bit would create inconsistent state and malfunction * of the user space owner died handling. Otherwise, the OWNER_DIED * bit is already set, and the woken waiter is expected to deal with * this. */ owner = uval & FUTEX_TID_MASK; if (pending_op && !pi && !owner) { futex_wake(uaddr, FLAGS_SIZE_32 | FLAGS_SHARED, 1, FUTEX_BITSET_MATCH_ANY); return 0; } if (owner != task_pid_vnr(curr)) return 0; /* * Ok, this dying thread is truly holding a futex * of interest. Set the OWNER_DIED bit atomically * via cmpxchg, and if the value had FUTEX_WAITERS * set, wake up a waiter (if any). (We have to do a * futex_wake() even if OWNER_DIED is already set - * to handle the rare but possible case of recursive * thread-death.) The rest of the cleanup is done in * userspace. */ mval = (uval & FUTEX_WAITERS) | FUTEX_OWNER_DIED; /* * We are not holding a lock here, but we want to have * the pagefault_disable/enable() protection because * we want to handle the fault gracefully. If the * access fails we try to fault in the futex with R/W * verification via get_user_pages. get_user() above * does not guarantee R/W access. If that fails we * give up and leave the futex locked. */ if ((err = futex_cmpxchg_value_locked(&nval, uaddr, uval, mval))) { switch (err) { case -EFAULT: if (fault_in_user_writeable(uaddr)) return -1; goto retry; case -EAGAIN: cond_resched(); goto retry; default: WARN_ON_ONCE(1); return err; } } if (nval != uval) goto retry; /* * Wake robust non-PI futexes here. The wakeup of * PI futexes happens in exit_pi_state(): */ if (!pi && (uval & FUTEX_WAITERS)) { futex_wake(uaddr, FLAGS_SIZE_32 | FLAGS_SHARED, 1, FUTEX_BITSET_MATCH_ANY); } return 0; } /* * Fetch a robust-list pointer. Bit 0 signals PI futexes: */ static inline int fetch_robust_entry(struct robust_list __user **entry, struct robust_list __user * __user *head, unsigned int *pi) { unsigned long uentry; if (get_user(uentry, (unsigned long __user *)head)) return -EFAULT; *entry = (void __user *)(uentry & ~1UL); *pi = uentry & 1; return 0; } /* * Walk curr->robust_list (very carefully, it's a userspace list!) * and mark any locks found there dead, and notify any waiters. * * We silently return on any sign of list-walking problem. */ static void exit_robust_list(struct task_struct *curr) { struct robust_list_head __user *head = curr->robust_list; struct robust_list __user *entry, *next_entry, *pending; unsigned int limit = ROBUST_LIST_LIMIT, pi, pip; unsigned int next_pi; unsigned long futex_offset; int rc; /* * Fetch the list head (which was registered earlier, via * sys_set_robust_list()): */ if (fetch_robust_entry(&entry, &head->list.next, &pi)) return; /* * Fetch the relative futex offset: */ if (get_user(futex_offset, &head->futex_offset)) return; /* * Fetch any possibly pending lock-add first, and handle it * if it exists: */ if (fetch_robust_entry(&pending, &head->list_op_pending, &pip)) return; next_entry = NULL; /* avoid warning with gcc */ while (entry != &head->list) { /* * Fetch the next entry in the list before calling * handle_futex_death: */ rc = fetch_robust_entry(&next_entry, &entry->next, &next_pi); /* * A pending lock might already be on the list, so * don't process it twice: */ if (entry != pending) { if (handle_futex_death((void __user *)entry + futex_offset, curr, pi, HANDLE_DEATH_LIST)) return; } if (rc) return; entry = next_entry; pi = next_pi; /* * Avoid excessively long or circular lists: */ if (!--limit) break; cond_resched(); } if (pending) { handle_futex_death((void __user *)pending + futex_offset, curr, pip, HANDLE_DEATH_PENDING); } } #ifdef CONFIG_COMPAT static void __user *futex_uaddr(struct robust_list __user *entry, compat_long_t futex_offset) { compat_uptr_t base = ptr_to_compat(entry); void __user *uaddr = compat_ptr(base + futex_offset); return uaddr; } /* * Fetch a robust-list pointer. Bit 0 signals PI futexes: */ static inline int compat_fetch_robust_entry(compat_uptr_t *uentry, struct robust_list __user **entry, compat_uptr_t __user *head, unsigned int *pi) { if (get_user(*uentry, head)) return -EFAULT; *entry = compat_ptr((*uentry) & ~1); *pi = (unsigned int)(*uentry) & 1; return 0; } /* * Walk curr->robust_list (very carefully, it's a userspace list!) * and mark any locks found there dead, and notify any waiters. * * We silently return on any sign of list-walking problem. */ static void compat_exit_robust_list(struct task_struct *curr) { struct compat_robust_list_head __user *head = curr->compat_robust_list; struct robust_list __user *entry, *next_entry, *pending; unsigned int limit = ROBUST_LIST_LIMIT, pi, pip; unsigned int next_pi; compat_uptr_t uentry, next_uentry, upending; compat_long_t futex_offset; int rc; /* * Fetch the list head (which was registered earlier, via * sys_set_robust_list()): */ if (compat_fetch_robust_entry(&uentry, &entry, &head->list.next, &pi)) return; /* * Fetch the relative futex offset: */ if (get_user(futex_offset, &head->futex_offset)) return; /* * Fetch any possibly pending lock-add first, and handle it * if it exists: */ if (compat_fetch_robust_entry(&upending, &pending, &head->list_op_pending, &pip)) return; next_entry = NULL; /* avoid warning with gcc */ while (entry != (struct robust_list __user *) &head->list) { /* * Fetch the next entry in the list before calling * handle_futex_death: */ rc = compat_fetch_robust_entry(&next_uentry, &next_entry, (compat_uptr_t __user *)&entry->next, &next_pi); /* * A pending lock might already be on the list, so * dont process it twice: */ if (entry != pending) { void __user *uaddr = futex_uaddr(entry, futex_offset); if (handle_futex_death(uaddr, curr, pi, HANDLE_DEATH_LIST)) return; } if (rc) return; uentry = next_uentry; entry = next_entry; pi = next_pi; /* * Avoid excessively long or circular lists: */ if (!--limit) break; cond_resched(); } if (pending) { void __user *uaddr = futex_uaddr(pending, futex_offset); handle_futex_death(uaddr, curr, pip, HANDLE_DEATH_PENDING); } } #endif #ifdef CONFIG_FUTEX_PI /* * This task is holding PI mutexes at exit time => bad. * Kernel cleans up PI-state, but userspace is likely hosed. * (Robust-futex cleanup is separate and might save the day for userspace.) */ static void exit_pi_state_list(struct task_struct *curr) { struct list_head *next, *head = &curr->pi_state_list; struct futex_pi_state *pi_state; struct futex_hash_bucket *hb; union futex_key key = FUTEX_KEY_INIT; /* * We are a ZOMBIE and nobody can enqueue itself on * pi_state_list anymore, but we have to be careful * versus waiters unqueueing themselves: */ raw_spin_lock_irq(&curr->pi_lock); while (!list_empty(head)) { next = head->next; pi_state = list_entry(next, struct futex_pi_state, list); key = pi_state->key; hb = futex_hash(&key); /* * We can race against put_pi_state() removing itself from the * list (a waiter going away). put_pi_state() will first * decrement the reference count and then modify the list, so * its possible to see the list entry but fail this reference * acquire. * * In that case; drop the locks to let put_pi_state() make * progress and retry the loop. */ if (!refcount_inc_not_zero(&pi_state->refcount)) { raw_spin_unlock_irq(&curr->pi_lock); cpu_relax(); raw_spin_lock_irq(&curr->pi_lock); continue; } raw_spin_unlock_irq(&curr->pi_lock); spin_lock(&hb->lock); raw_spin_lock_irq(&pi_state->pi_mutex.wait_lock); raw_spin_lock(&curr->pi_lock); /* * We dropped the pi-lock, so re-check whether this * task still owns the PI-state: */ if (head->next != next) { /* retain curr->pi_lock for the loop invariant */ raw_spin_unlock(&pi_state->pi_mutex.wait_lock); spin_unlock(&hb->lock); put_pi_state(pi_state); continue; } WARN_ON(pi_state->owner != curr); WARN_ON(list_empty(&pi_state->list)); list_del_init(&pi_state->list); pi_state->owner = NULL; raw_spin_unlock(&curr->pi_lock); raw_spin_unlock_irq(&pi_state->pi_mutex.wait_lock); spin_unlock(&hb->lock); rt_mutex_futex_unlock(&pi_state->pi_mutex); put_pi_state(pi_state); raw_spin_lock_irq(&curr->pi_lock); } raw_spin_unlock_irq(&curr->pi_lock); } #else static inline void exit_pi_state_list(struct task_struct *curr) { } #endif static void futex_cleanup(struct task_struct *tsk) { if (unlikely(tsk->robust_list)) { exit_robust_list(tsk); tsk->robust_list = NULL; } #ifdef CONFIG_COMPAT if (unlikely(tsk->compat_robust_list)) { compat_exit_robust_list(tsk); tsk->compat_robust_list = NULL; } #endif if (unlikely(!list_empty(&tsk->pi_state_list))) exit_pi_state_list(tsk); } /** * futex_exit_recursive - Set the tasks futex state to FUTEX_STATE_DEAD * @tsk: task to set the state on * * Set the futex exit state of the task lockless. The futex waiter code * observes that state when a task is exiting and loops until the task has * actually finished the futex cleanup. The worst case for this is that the * waiter runs through the wait loop until the state becomes visible. * * This is called from the recursive fault handling path in make_task_dead(). * * This is best effort. Either the futex exit code has run already or * not. If the OWNER_DIED bit has been set on the futex then the waiter can * take it over. If not, the problem is pushed back to user space. If the * futex exit code did not run yet, then an already queued waiter might * block forever, but there is nothing which can be done about that. */ void futex_exit_recursive(struct task_struct *tsk) { /* If the state is FUTEX_STATE_EXITING then futex_exit_mutex is held */ if (tsk->futex_state == FUTEX_STATE_EXITING) mutex_unlock(&tsk->futex_exit_mutex); tsk->futex_state = FUTEX_STATE_DEAD; } static void futex_cleanup_begin(struct task_struct *tsk) { /* * Prevent various race issues against a concurrent incoming waiter * including live locks by forcing the waiter to block on * tsk->futex_exit_mutex when it observes FUTEX_STATE_EXITING in * attach_to_pi_owner(). */ mutex_lock(&tsk->futex_exit_mutex); /* * Switch the state to FUTEX_STATE_EXITING under tsk->pi_lock. * * This ensures that all subsequent checks of tsk->futex_state in * attach_to_pi_owner() must observe FUTEX_STATE_EXITING with * tsk->pi_lock held. * * It guarantees also that a pi_state which was queued right before * the state change under tsk->pi_lock by a concurrent waiter must * be observed in exit_pi_state_list(). */ raw_spin_lock_irq(&tsk->pi_lock); tsk->futex_state = FUTEX_STATE_EXITING; raw_spin_unlock_irq(&tsk->pi_lock); } static void futex_cleanup_end(struct task_struct *tsk, int state) { /* * Lockless store. The only side effect is that an observer might * take another loop until it becomes visible. */ tsk->futex_state = state; /* * Drop the exit protection. This unblocks waiters which observed * FUTEX_STATE_EXITING to reevaluate the state. */ mutex_unlock(&tsk->futex_exit_mutex); } void futex_exec_release(struct task_struct *tsk) { /* * The state handling is done for consistency, but in the case of * exec() there is no way to prevent further damage as the PID stays * the same. But for the unlikely and arguably buggy case that a * futex is held on exec(), this provides at least as much state * consistency protection which is possible. */ futex_cleanup_begin(tsk); futex_cleanup(tsk); /* * Reset the state to FUTEX_STATE_OK. The task is alive and about * exec a new binary. */ futex_cleanup_end(tsk, FUTEX_STATE_OK); } void futex_exit_release(struct task_struct *tsk) { futex_cleanup_begin(tsk); futex_cleanup(tsk); futex_cleanup_end(tsk, FUTEX_STATE_DEAD); } static int __init futex_init(void) { unsigned int futex_shift; unsigned long i; #ifdef CONFIG_BASE_SMALL futex_hashsize = 16; #else futex_hashsize = roundup_pow_of_two(256 * num_possible_cpus()); #endif futex_queues = alloc_large_system_hash("futex", sizeof(*futex_queues), futex_hashsize, 0, 0, &futex_shift, NULL, futex_hashsize, futex_hashsize); futex_hashsize = 1UL << futex_shift; for (i = 0; i < futex_hashsize; i++) { atomic_set(&futex_queues[i].waiters, 0); plist_head_init(&futex_queues[i].chain); spin_lock_init(&futex_queues[i].lock); } return 0; } core_initcall(futex_init); |
| 162 161 162 162 161 161 162 162 162 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 | // SPDX-License-Identifier: GPL-2.0 /* * device_cgroup.c - device cgroup subsystem * * Copyright 2007 IBM Corp */ #include <linux/bpf-cgroup.h> #include <linux/device_cgroup.h> #include <linux/cgroup.h> #include <linux/ctype.h> #include <linux/list.h> #include <linux/uaccess.h> #include <linux/seq_file.h> #include <linux/slab.h> #include <linux/rcupdate.h> #include <linux/mutex.h> #ifdef CONFIG_CGROUP_DEVICE static DEFINE_MUTEX(devcgroup_mutex); enum devcg_behavior { DEVCG_DEFAULT_NONE, DEVCG_DEFAULT_ALLOW, DEVCG_DEFAULT_DENY, }; /* * exception list locking rules: * hold devcgroup_mutex for update/read. * hold rcu_read_lock() for read. */ struct dev_exception_item { u32 major, minor; short type; short access; struct list_head list; struct rcu_head rcu; }; struct dev_cgroup { struct cgroup_subsys_state css; struct list_head exceptions; enum devcg_behavior behavior; }; static inline struct dev_cgroup *css_to_devcgroup(struct cgroup_subsys_state *s) { return s ? container_of(s, struct dev_cgroup, css) : NULL; } static inline struct dev_cgroup *task_devcgroup(struct task_struct *task) { return css_to_devcgroup(task_css(task, devices_cgrp_id)); } /* * called under devcgroup_mutex */ static int dev_exceptions_copy(struct list_head *dest, struct list_head *orig) { struct dev_exception_item *ex, *tmp, *new; lockdep_assert_held(&devcgroup_mutex); list_for_each_entry(ex, orig, list) { new = kmemdup(ex, sizeof(*ex), GFP_KERNEL); if (!new) goto free_and_exit; list_add_tail(&new->list, dest); } return 0; free_and_exit: list_for_each_entry_safe(ex, tmp, dest, list) { list_del(&ex->list); kfree(ex); } return -ENOMEM; } static void dev_exceptions_move(struct list_head *dest, struct list_head *orig) { struct dev_exception_item *ex, *tmp; lockdep_assert_held(&devcgroup_mutex); list_for_each_entry_safe(ex, tmp, orig, list) { list_move_tail(&ex->list, dest); } } /* * called under devcgroup_mutex */ static int dev_exception_add(struct dev_cgroup *dev_cgroup, struct dev_exception_item *ex) { struct dev_exception_item *excopy, *walk; lockdep_assert_held(&devcgroup_mutex); excopy = kmemdup(ex, sizeof(*ex), GFP_KERNEL); if (!excopy) return -ENOMEM; list_for_each_entry(walk, &dev_cgroup->exceptions, list) { if (walk->type != ex->type) continue; if (walk->major != ex->major) continue; if (walk->minor != ex->minor) continue; walk->access |= ex->access; kfree(excopy); excopy = NULL; } if (excopy != NULL) list_add_tail_rcu(&excopy->list, &dev_cgroup->exceptions); return 0; } /* * called under devcgroup_mutex */ static void dev_exception_rm(struct dev_cgroup *dev_cgroup, struct dev_exception_item *ex) { struct dev_exception_item *walk, *tmp; lockdep_assert_held(&devcgroup_mutex); list_for_each_entry_safe(walk, tmp, &dev_cgroup->exceptions, list) { if (walk->type != ex->type) continue; if (walk->major != ex->major) continue; if (walk->minor != ex->minor) continue; walk->access &= ~ex->access; if (!walk->access) { list_del_rcu(&walk->list); kfree_rcu(walk, rcu); } } } static void __dev_exception_clean(struct dev_cgroup *dev_cgroup) { struct dev_exception_item *ex, *tmp; list_for_each_entry_safe(ex, tmp, &dev_cgroup->exceptions, list) { list_del_rcu(&ex->list); kfree_rcu(ex, rcu); } } /** * dev_exception_clean - frees all entries of the exception list * @dev_cgroup: dev_cgroup with the exception list to be cleaned * * called under devcgroup_mutex */ static void dev_exception_clean(struct dev_cgroup *dev_cgroup) { lockdep_assert_held(&devcgroup_mutex); __dev_exception_clean(dev_cgroup); } static inline bool is_devcg_online(const struct dev_cgroup *devcg) { return (devcg->behavior != DEVCG_DEFAULT_NONE); } /** * devcgroup_online - initializes devcgroup's behavior and exceptions based on * parent's * @css: css getting online * returns 0 in case of success, error code otherwise */ static int devcgroup_online(struct cgroup_subsys_state *css) { struct dev_cgroup *dev_cgroup = css_to_devcgroup(css); struct dev_cgroup *parent_dev_cgroup = css_to_devcgroup(css->parent); int ret = 0; mutex_lock(&devcgroup_mutex); if (parent_dev_cgroup == NULL) dev_cgroup->behavior = DEVCG_DEFAULT_ALLOW; else { ret = dev_exceptions_copy(&dev_cgroup->exceptions, &parent_dev_cgroup->exceptions); if (!ret) dev_cgroup->behavior = parent_dev_cgroup->behavior; } mutex_unlock(&devcgroup_mutex); return ret; } static void devcgroup_offline(struct cgroup_subsys_state *css) { struct dev_cgroup *dev_cgroup = css_to_devcgroup(css); mutex_lock(&devcgroup_mutex); dev_cgroup->behavior = DEVCG_DEFAULT_NONE; mutex_unlock(&devcgroup_mutex); } /* * called from kernel/cgroup/cgroup.c with cgroup_lock() held. */ static struct cgroup_subsys_state * devcgroup_css_alloc(struct cgroup_subsys_state *parent_css) { struct dev_cgroup *dev_cgroup; dev_cgroup = kzalloc(sizeof(*dev_cgroup), GFP_KERNEL); if (!dev_cgroup) return ERR_PTR(-ENOMEM); INIT_LIST_HEAD(&dev_cgroup->exceptions); dev_cgroup->behavior = DEVCG_DEFAULT_NONE; return &dev_cgroup->css; } static void devcgroup_css_free(struct cgroup_subsys_state *css) { struct dev_cgroup *dev_cgroup = css_to_devcgroup(css); __dev_exception_clean(dev_cgroup); kfree(dev_cgroup); } #define DEVCG_ALLOW 1 #define DEVCG_DENY 2 #define DEVCG_LIST 3 #define MAJMINLEN 13 #define ACCLEN 4 static void set_access(char *acc, short access) { int idx = 0; memset(acc, 0, ACCLEN); if (access & DEVCG_ACC_READ) acc[idx++] = 'r'; if (access & DEVCG_ACC_WRITE) acc[idx++] = 'w'; if (access & DEVCG_ACC_MKNOD) acc[idx++] = 'm'; } static char type_to_char(short type) { if (type == DEVCG_DEV_ALL) return 'a'; if (type == DEVCG_DEV_CHAR) return 'c'; if (type == DEVCG_DEV_BLOCK) return 'b'; return 'X'; } static void set_majmin(char *str, unsigned m) { if (m == ~0) strcpy(str, "*"); else sprintf(str, "%u", m); } static int devcgroup_seq_show(struct seq_file *m, void *v) { struct dev_cgroup *devcgroup = css_to_devcgroup(seq_css(m)); struct dev_exception_item *ex; char maj[MAJMINLEN], min[MAJMINLEN], acc[ACCLEN]; rcu_read_lock(); /* * To preserve the compatibility: * - Only show the "all devices" when the default policy is to allow * - List the exceptions in case the default policy is to deny * This way, the file remains as a "whitelist of devices" */ if (devcgroup->behavior == DEVCG_DEFAULT_ALLOW) { set_access(acc, DEVCG_ACC_MASK); set_majmin(maj, ~0); set_majmin(min, ~0); seq_printf(m, "%c %s:%s %s\n", type_to_char(DEVCG_DEV_ALL), maj, min, acc); } else { list_for_each_entry_rcu(ex, &devcgroup->exceptions, list) { set_access(acc, ex->access); set_majmin(maj, ex->major); set_majmin(min, ex->minor); seq_printf(m, "%c %s:%s %s\n", type_to_char(ex->type), maj, min, acc); } } rcu_read_unlock(); return 0; } /** * match_exception - iterates the exception list trying to find a complete match * @exceptions: list of exceptions * @type: device type (DEVCG_DEV_BLOCK or DEVCG_DEV_CHAR) * @major: device file major number, ~0 to match all * @minor: device file minor number, ~0 to match all * @access: permission mask (DEVCG_ACC_READ, DEVCG_ACC_WRITE, DEVCG_ACC_MKNOD) * * It is considered a complete match if an exception is found that will * contain the entire range of provided parameters. * * Return: true in case it matches an exception completely */ static bool match_exception(struct list_head *exceptions, short type, u32 major, u32 minor, short access) { struct dev_exception_item *ex; list_for_each_entry_rcu(ex, exceptions, list) { if ((type & DEVCG_DEV_BLOCK) && !(ex->type & DEVCG_DEV_BLOCK)) continue; if ((type & DEVCG_DEV_CHAR) && !(ex->type & DEVCG_DEV_CHAR)) continue; if (ex->major != ~0 && ex->major != major) continue; if (ex->minor != ~0 && ex->minor != minor) continue; /* provided access cannot have more than the exception rule */ if (access & (~ex->access)) continue; return true; } return false; } /** * match_exception_partial - iterates the exception list trying to find a partial match * @exceptions: list of exceptions * @type: device type (DEVCG_DEV_BLOCK or DEVCG_DEV_CHAR) * @major: device file major number, ~0 to match all * @minor: device file minor number, ~0 to match all * @access: permission mask (DEVCG_ACC_READ, DEVCG_ACC_WRITE, DEVCG_ACC_MKNOD) * * It is considered a partial match if an exception's range is found to * contain *any* of the devices specified by provided parameters. This is * used to make sure no extra access is being granted that is forbidden by * any of the exception list. * * Return: true in case the provided range mat matches an exception completely */ static bool match_exception_partial(struct list_head *exceptions, short type, u32 major, u32 minor, short access) { struct dev_exception_item *ex; list_for_each_entry_rcu(ex, exceptions, list, lockdep_is_held(&devcgroup_mutex)) { if ((type & DEVCG_DEV_BLOCK) && !(ex->type & DEVCG_DEV_BLOCK)) continue; if ((type & DEVCG_DEV_CHAR) && !(ex->type & DEVCG_DEV_CHAR)) continue; /* * We must be sure that both the exception and the provided * range aren't masking all devices */ if (ex->major != ~0 && major != ~0 && ex->major != major) continue; if (ex->minor != ~0 && minor != ~0 && ex->minor != minor) continue; /* * In order to make sure the provided range isn't matching * an exception, all its access bits shouldn't match the * exception's access bits */ if (!(access & ex->access)) continue; return true; } return false; } /** * verify_new_ex - verifies if a new exception is allowed by parent cgroup's permissions * @dev_cgroup: dev cgroup to be tested against * @refex: new exception * @behavior: behavior of the exception's dev_cgroup * * This is used to make sure a child cgroup won't have more privileges * than its parent */ static bool verify_new_ex(struct dev_cgroup *dev_cgroup, struct dev_exception_item *refex, enum devcg_behavior behavior) { bool match = false; RCU_LOCKDEP_WARN(!rcu_read_lock_held() && !lockdep_is_held(&devcgroup_mutex), "device_cgroup:verify_new_ex called without proper synchronization"); if (dev_cgroup->behavior == DEVCG_DEFAULT_ALLOW) { if (behavior == DEVCG_DEFAULT_ALLOW) { /* * new exception in the child doesn't matter, only * adding extra restrictions */ return true; } else { /* * new exception in the child will add more devices * that can be accessed, so it can't match any of * parent's exceptions, even slightly */ match = match_exception_partial(&dev_cgroup->exceptions, refex->type, refex->major, refex->minor, refex->access); if (match) return false; return true; } } else { /* * Only behavior == DEVCG_DEFAULT_DENY allowed here, therefore * the new exception will add access to more devices and must * be contained completely in an parent's exception to be * allowed */ match = match_exception(&dev_cgroup->exceptions, refex->type, refex->major, refex->minor, refex->access); if (match) /* parent has an exception that matches the proposed */ return true; else return false; } return false; } /* * parent_has_perm: * when adding a new allow rule to a device exception list, the rule * must be allowed in the parent device */ static int parent_has_perm(struct dev_cgroup *childcg, struct dev_exception_item *ex) { struct dev_cgroup *parent = css_to_devcgroup(childcg->css.parent); if (!parent) return 1; return verify_new_ex(parent, ex, childcg->behavior); } /** * parent_allows_removal - verify if it's ok to remove an exception * @childcg: child cgroup from where the exception will be removed * @ex: exception being removed * * When removing an exception in cgroups with default ALLOW policy, it must * be checked if removing it will give the child cgroup more access than the * parent. * * Return: true if it's ok to remove exception, false otherwise */ static bool parent_allows_removal(struct dev_cgroup *childcg, struct dev_exception_item *ex) { struct dev_cgroup *parent = css_to_devcgroup(childcg->css.parent); if (!parent) return true; /* It's always allowed to remove access to devices */ if (childcg->behavior == DEVCG_DEFAULT_DENY) return true; /* * Make sure you're not removing part or a whole exception existing in * the parent cgroup */ return !match_exception_partial(&parent->exceptions, ex->type, ex->major, ex->minor, ex->access); } /** * may_allow_all - checks if it's possible to change the behavior to * allow based on parent's rules. * @parent: device cgroup's parent * returns: != 0 in case it's allowed, 0 otherwise */ static inline int may_allow_all(struct dev_cgroup *parent) { if (!parent) return 1; return parent->behavior == DEVCG_DEFAULT_ALLOW; } /** * revalidate_active_exceptions - walks through the active exception list and * revalidates the exceptions based on parent's * behavior and exceptions. The exceptions that * are no longer valid will be removed. * Called with devcgroup_mutex held. * @devcg: cgroup which exceptions will be checked * * This is one of the three key functions for hierarchy implementation. * This function is responsible for re-evaluating all the cgroup's active * exceptions due to a parent's exception change. * Refer to Documentation/admin-guide/cgroup-v1/devices.rst for more details. */ static void revalidate_active_exceptions(struct dev_cgroup *devcg) { struct dev_exception_item *ex; struct list_head *this, *tmp; list_for_each_safe(this, tmp, &devcg->exceptions) { ex = container_of(this, struct dev_exception_item, list); if (!parent_has_perm(devcg, ex)) dev_exception_rm(devcg, ex); } } /** * propagate_exception - propagates a new exception to the children * @devcg_root: device cgroup that added a new exception * @ex: new exception to be propagated * * returns: 0 in case of success, != 0 in case of error */ static int propagate_exception(struct dev_cgroup *devcg_root, struct dev_exception_item *ex) { struct cgroup_subsys_state *pos; int rc = 0; rcu_read_lock(); css_for_each_descendant_pre(pos, &devcg_root->css) { struct dev_cgroup *devcg = css_to_devcgroup(pos); /* * Because devcgroup_mutex is held, no devcg will become * online or offline during the tree walk (see on/offline * methods), and online ones are safe to access outside RCU * read lock without bumping refcnt. */ if (pos == &devcg_root->css || !is_devcg_online(devcg)) continue; rcu_read_unlock(); /* * in case both root's behavior and devcg is allow, a new * restriction means adding to the exception list */ if (devcg_root->behavior == DEVCG_DEFAULT_ALLOW && devcg->behavior == DEVCG_DEFAULT_ALLOW) { rc = dev_exception_add(devcg, ex); if (rc) return rc; } else { /* * in the other possible cases: * root's behavior: allow, devcg's: deny * root's behavior: deny, devcg's: deny * the exception will be removed */ dev_exception_rm(devcg, ex); } revalidate_active_exceptions(devcg); rcu_read_lock(); } rcu_read_unlock(); return rc; } /* * Modify the exception list using allow/deny rules. * CAP_SYS_ADMIN is needed for this. It's at least separate from CAP_MKNOD * so we can give a container CAP_MKNOD to let it create devices but not * modify the exception list. * It seems likely we'll want to add a CAP_CONTAINER capability to allow * us to also grant CAP_SYS_ADMIN to containers without giving away the * device exception list controls, but for now we'll stick with CAP_SYS_ADMIN * * Taking rules away is always allowed (given CAP_SYS_ADMIN). Granting * new access is only allowed if you're in the top-level cgroup, or your * parent cgroup has the access you're asking for. */ static int devcgroup_update_access(struct dev_cgroup *devcgroup, int filetype, char *buffer) { const char *b; char temp[12]; /* 11 + 1 characters needed for a u32 */ int count, rc = 0; struct dev_exception_item ex; struct dev_cgroup *parent = css_to_devcgroup(devcgroup->css.parent); struct dev_cgroup tmp_devcgrp; if (!capable(CAP_SYS_ADMIN)) return -EPERM; memset(&ex, 0, sizeof(ex)); memset(&tmp_devcgrp, 0, sizeof(tmp_devcgrp)); b = buffer; switch (*b) { case 'a': switch (filetype) { case DEVCG_ALLOW: if (css_has_online_children(&devcgroup->css)) return -EINVAL; if (!may_allow_all(parent)) return -EPERM; if (!parent) { devcgroup->behavior = DEVCG_DEFAULT_ALLOW; dev_exception_clean(devcgroup); break; } INIT_LIST_HEAD(&tmp_devcgrp.exceptions); rc = dev_exceptions_copy(&tmp_devcgrp.exceptions, &devcgroup->exceptions); if (rc) return rc; dev_exception_clean(devcgroup); rc = dev_exceptions_copy(&devcgroup->exceptions, &parent->exceptions); if (rc) { dev_exceptions_move(&devcgroup->exceptions, &tmp_devcgrp.exceptions); return rc; } devcgroup->behavior = DEVCG_DEFAULT_ALLOW; dev_exception_clean(&tmp_devcgrp); break; case DEVCG_DENY: if (css_has_online_children(&devcgroup->css)) return -EINVAL; dev_exception_clean(devcgroup); devcgroup->behavior = DEVCG_DEFAULT_DENY; break; default: return -EINVAL; } return 0; case 'b': ex.type = DEVCG_DEV_BLOCK; break; case 'c': ex.type = DEVCG_DEV_CHAR; break; default: return -EINVAL; } b++; if (!isspace(*b)) return -EINVAL; b++; if (*b == '*') { ex.major = ~0; b++; } else if (isdigit(*b)) { memset(temp, 0, sizeof(temp)); for (count = 0; count < sizeof(temp) - 1; count++) { temp[count] = *b; b++; if (!isdigit(*b)) break; } rc = kstrtou32(temp, 10, &ex.major); if (rc) return -EINVAL; } else { return -EINVAL; } if (*b != ':') return -EINVAL; b++; /* read minor */ if (*b == '*') { ex.minor = ~0; b++; } else if (isdigit(*b)) { memset(temp, 0, sizeof(temp)); for (count = 0; count < sizeof(temp) - 1; count++) { temp[count] = *b; b++; if (!isdigit(*b)) break; } rc = kstrtou32(temp, 10, &ex.minor); if (rc) return -EINVAL; } else { return -EINVAL; } if (!isspace(*b)) return -EINVAL; for (b++, count = 0; count < 3; count++, b++) { switch (*b) { case 'r': ex.access |= DEVCG_ACC_READ; break; case 'w': ex.access |= DEVCG_ACC_WRITE; break; case 'm': ex.access |= DEVCG_ACC_MKNOD; break; case '\n': case '\0': count = 3; break; default: return -EINVAL; } } switch (filetype) { case DEVCG_ALLOW: /* * If the default policy is to allow by default, try to remove * an matching exception instead. And be silent about it: we * don't want to break compatibility */ if (devcgroup->behavior == DEVCG_DEFAULT_ALLOW) { /* Check if the parent allows removing it first */ if (!parent_allows_removal(devcgroup, &ex)) return -EPERM; dev_exception_rm(devcgroup, &ex); break; } if (!parent_has_perm(devcgroup, &ex)) return -EPERM; rc = dev_exception_add(devcgroup, &ex); break; case DEVCG_DENY: /* * If the default policy is to deny by default, try to remove * an matching exception instead. And be silent about it: we * don't want to break compatibility */ if (devcgroup->behavior == DEVCG_DEFAULT_DENY) dev_exception_rm(devcgroup, &ex); else rc = dev_exception_add(devcgroup, &ex); if (rc) break; /* we only propagate new restrictions */ rc = propagate_exception(devcgroup, &ex); break; default: rc = -EINVAL; } return rc; } static ssize_t devcgroup_access_write(struct kernfs_open_file *of, char *buf, size_t nbytes, loff_t off) { int retval; mutex_lock(&devcgroup_mutex); retval = devcgroup_update_access(css_to_devcgroup(of_css(of)), of_cft(of)->private, strstrip(buf)); mutex_unlock(&devcgroup_mutex); return retval ?: nbytes; } static struct cftype dev_cgroup_files[] = { { .name = "allow", .write = devcgroup_access_write, .private = DEVCG_ALLOW, }, { .name = "deny", .write = devcgroup_access_write, .private = DEVCG_DENY, }, { .name = "list", .seq_show = devcgroup_seq_show, .private = DEVCG_LIST, }, { } /* terminate */ }; struct cgroup_subsys devices_cgrp_subsys = { .css_alloc = devcgroup_css_alloc, .css_free = devcgroup_css_free, .css_online = devcgroup_online, .css_offline = devcgroup_offline, .legacy_cftypes = dev_cgroup_files, }; /** * devcgroup_legacy_check_permission - checks if an inode operation is permitted * @type: device type * @major: device major number * @minor: device minor number * @access: combination of DEVCG_ACC_WRITE, DEVCG_ACC_READ and DEVCG_ACC_MKNOD * * returns 0 on success, -EPERM case the operation is not permitted */ static int devcgroup_legacy_check_permission(short type, u32 major, u32 minor, short access) { struct dev_cgroup *dev_cgroup; bool rc; rcu_read_lock(); dev_cgroup = task_devcgroup(current); if (dev_cgroup->behavior == DEVCG_DEFAULT_ALLOW) /* Can't match any of the exceptions, even partially */ rc = !match_exception_partial(&dev_cgroup->exceptions, type, major, minor, access); else /* Need to match completely one exception to be allowed */ rc = match_exception(&dev_cgroup->exceptions, type, major, minor, access); rcu_read_unlock(); if (!rc) return -EPERM; return 0; } #endif /* CONFIG_CGROUP_DEVICE */ #if defined(CONFIG_CGROUP_DEVICE) || defined(CONFIG_CGROUP_BPF) int devcgroup_check_permission(short type, u32 major, u32 minor, short access) { int rc = BPF_CGROUP_RUN_PROG_DEVICE_CGROUP(type, major, minor, access); if (rc) return rc; #ifdef CONFIG_CGROUP_DEVICE return devcgroup_legacy_check_permission(type, major, minor, access); #else /* CONFIG_CGROUP_DEVICE */ return 0; #endif /* CONFIG_CGROUP_DEVICE */ } EXPORT_SYMBOL(devcgroup_check_permission); #endif /* defined(CONFIG_CGROUP_DEVICE) || defined(CONFIG_CGROUP_BPF) */ |
| 73 692 75 1046 71 1048 145 73 73 724 359 176 321 538 433 92 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 | /* SPDX-License-Identifier: GPL-2.0-only */ /* * Copyright (C) 2014 Linaro Ltd. <ard.biesheuvel@linaro.org> */ #ifndef __ASM_CPUFEATURE_H #define __ASM_CPUFEATURE_H #include <asm/alternative-macros.h> #include <asm/cpucaps.h> #include <asm/cputype.h> #include <asm/hwcap.h> #include <asm/sysreg.h> #define MAX_CPU_FEATURES 192 #define cpu_feature(x) KERNEL_HWCAP_ ## x #define ARM64_SW_FEATURE_OVERRIDE_NOKASLR 0 #define ARM64_SW_FEATURE_OVERRIDE_HVHE 4 #define ARM64_SW_FEATURE_OVERRIDE_RODATA_OFF 8 #ifndef __ASSEMBLY__ #include <linux/bug.h> #include <linux/jump_label.h> #include <linux/kernel.h> #include <linux/cpumask.h> /* * CPU feature register tracking * * The safe value of a CPUID feature field is dependent on the implications * of the values assigned to it by the architecture. Based on the relationship * between the values, the features are classified into 3 types - LOWER_SAFE, * HIGHER_SAFE and EXACT. * * The lowest value of all the CPUs is chosen for LOWER_SAFE and highest * for HIGHER_SAFE. It is expected that all CPUs have the same value for * a field when EXACT is specified, failing which, the safe value specified * in the table is chosen. */ enum ftr_type { FTR_EXACT, /* Use a predefined safe value */ FTR_LOWER_SAFE, /* Smaller value is safe */ FTR_HIGHER_SAFE, /* Bigger value is safe */ FTR_HIGHER_OR_ZERO_SAFE, /* Bigger value is safe, but 0 is biggest */ }; #define FTR_STRICT true /* SANITY check strict matching required */ #define FTR_NONSTRICT false /* SANITY check ignored */ #define FTR_SIGNED true /* Value should be treated as signed */ #define FTR_UNSIGNED false /* Value should be treated as unsigned */ #define FTR_VISIBLE true /* Feature visible to the user space */ #define FTR_HIDDEN false /* Feature is hidden from the user */ #define FTR_VISIBLE_IF_IS_ENABLED(config) \ (IS_ENABLED(config) ? FTR_VISIBLE : FTR_HIDDEN) struct arm64_ftr_bits { bool sign; /* Value is signed ? */ bool visible; bool strict; /* CPU Sanity check: strict matching required ? */ enum ftr_type type; u8 shift; u8 width; s64 safe_val; /* safe value for FTR_EXACT features */ }; /* * Describe the early feature override to the core override code: * * @val Values that are to be merged into the final * sanitised value of the register. Only the bitfields * set to 1 in @mask are valid * @mask Mask of the features that are overridden by @val * * A @mask field set to full-1 indicates that the corresponding field * in @val is a valid override. * * A @mask field set to full-0 with the corresponding @val field set * to full-0 denotes that this field has no override * * A @mask field set to full-0 with the corresponding @val field set * to full-1 denotes that this field has an invalid override. */ struct arm64_ftr_override { u64 val; u64 mask; }; /* * @arm64_ftr_reg - Feature register * @strict_mask Bits which should match across all CPUs for sanity. * @sys_val Safe value across the CPUs (system view) */ struct arm64_ftr_reg { const char *name; u64 strict_mask; u64 user_mask; u64 sys_val; u64 user_val; struct arm64_ftr_override *override; const struct arm64_ftr_bits *ftr_bits; }; extern struct arm64_ftr_reg arm64_ftr_reg_ctrel0; /* * CPU capabilities: * * We use arm64_cpu_capabilities to represent system features, errata work * arounds (both used internally by kernel and tracked in system_cpucaps) and * ELF HWCAPs (which are exposed to user). * * To support systems with heterogeneous CPUs, we need to make sure that we * detect the capabilities correctly on the system and take appropriate * measures to ensure there are no incompatibilities. * * This comment tries to explain how we treat the capabilities. * Each capability has the following list of attributes : * * 1) Scope of Detection : The system detects a given capability by * performing some checks at runtime. This could be, e.g, checking the * value of a field in CPU ID feature register or checking the cpu * model. The capability provides a call back ( @matches() ) to * perform the check. Scope defines how the checks should be performed. * There are three cases: * * a) SCOPE_LOCAL_CPU: check all the CPUs and "detect" if at least one * matches. This implies, we have to run the check on all the * booting CPUs, until the system decides that state of the * capability is finalised. (See section 2 below) * Or * b) SCOPE_SYSTEM: check all the CPUs and "detect" if all the CPUs * matches. This implies, we run the check only once, when the * system decides to finalise the state of the capability. If the * capability relies on a field in one of the CPU ID feature * registers, we use the sanitised value of the register from the * CPU feature infrastructure to make the decision. * Or * c) SCOPE_BOOT_CPU: Check only on the primary boot CPU to detect the * feature. This category is for features that are "finalised" * (or used) by the kernel very early even before the SMP cpus * are brought up. * * The process of detection is usually denoted by "update" capability * state in the code. * * 2) Finalise the state : The kernel should finalise the state of a * capability at some point during its execution and take necessary * actions if any. Usually, this is done, after all the boot-time * enabled CPUs are brought up by the kernel, so that it can make * better decision based on the available set of CPUs. However, there * are some special cases, where the action is taken during the early * boot by the primary boot CPU. (e.g, running the kernel at EL2 with * Virtualisation Host Extensions). The kernel usually disallows any * changes to the state of a capability once it finalises the capability * and takes any action, as it may be impossible to execute the actions * safely. A CPU brought up after a capability is "finalised" is * referred to as "Late CPU" w.r.t the capability. e.g, all secondary * CPUs are treated "late CPUs" for capabilities determined by the boot * CPU. * * At the moment there are two passes of finalising the capabilities. * a) Boot CPU scope capabilities - Finalised by primary boot CPU via * setup_boot_cpu_capabilities(). * b) Everything except (a) - Run via setup_system_capabilities(). * * 3) Verification: When a CPU is brought online (e.g, by user or by the * kernel), the kernel should make sure that it is safe to use the CPU, * by verifying that the CPU is compliant with the state of the * capabilities finalised already. This happens via : * * secondary_start_kernel()-> check_local_cpu_capabilities() * * As explained in (2) above, capabilities could be finalised at * different points in the execution. Each newly booted CPU is verified * against the capabilities that have been finalised by the time it * boots. * * a) SCOPE_BOOT_CPU : All CPUs are verified against the capability * except for the primary boot CPU. * * b) SCOPE_LOCAL_CPU, SCOPE_SYSTEM: All CPUs hotplugged on by the * user after the kernel boot are verified against the capability. * * If there is a conflict, the kernel takes an action, based on the * severity (e.g, a CPU could be prevented from booting or cause a * kernel panic). The CPU is allowed to "affect" the state of the * capability, if it has not been finalised already. See section 5 * for more details on conflicts. * * 4) Action: As mentioned in (2), the kernel can take an action for each * detected capability, on all CPUs on the system. Appropriate actions * include, turning on an architectural feature, modifying the control * registers (e.g, SCTLR, TCR etc.) or patching the kernel via * alternatives. The kernel patching is batched and performed at later * point. The actions are always initiated only after the capability * is finalised. This is usally denoted by "enabling" the capability. * The actions are initiated as follows : * a) Action is triggered on all online CPUs, after the capability is * finalised, invoked within the stop_machine() context from * enable_cpu_capabilitie(). * * b) Any late CPU, brought up after (1), the action is triggered via: * * check_local_cpu_capabilities() -> verify_local_cpu_capabilities() * * 5) Conflicts: Based on the state of the capability on a late CPU vs. * the system state, we could have the following combinations : * * x-----------------------------x * | Type | System | Late CPU | * |-----------------------------| * | a | y | n | * |-----------------------------| * | b | n | y | * x-----------------------------x * * Two separate flag bits are defined to indicate whether each kind of * conflict can be allowed: * ARM64_CPUCAP_OPTIONAL_FOR_LATE_CPU - Case(a) is allowed * ARM64_CPUCAP_PERMITTED_FOR_LATE_CPU - Case(b) is allowed * * Case (a) is not permitted for a capability that the system requires * all CPUs to have in order for the capability to be enabled. This is * typical for capabilities that represent enhanced functionality. * * Case (b) is not permitted for a capability that must be enabled * during boot if any CPU in the system requires it in order to run * safely. This is typical for erratum work arounds that cannot be * enabled after the corresponding capability is finalised. * * In some non-typical cases either both (a) and (b), or neither, * should be permitted. This can be described by including neither * or both flags in the capability's type field. * * In case of a conflict, the CPU is prevented from booting. If the * ARM64_CPUCAP_PANIC_ON_CONFLICT flag is specified for the capability, * then a kernel panic is triggered. */ /* * Decide how the capability is detected. * On any local CPU vs System wide vs the primary boot CPU */ #define ARM64_CPUCAP_SCOPE_LOCAL_CPU ((u16)BIT(0)) #define ARM64_CPUCAP_SCOPE_SYSTEM ((u16)BIT(1)) /* * The capabilitiy is detected on the Boot CPU and is used by kernel * during early boot. i.e, the capability should be "detected" and * "enabled" as early as possibly on all booting CPUs. */ #define ARM64_CPUCAP_SCOPE_BOOT_CPU ((u16)BIT(2)) #define ARM64_CPUCAP_SCOPE_MASK \ (ARM64_CPUCAP_SCOPE_SYSTEM | \ ARM64_CPUCAP_SCOPE_LOCAL_CPU | \ ARM64_CPUCAP_SCOPE_BOOT_CPU) #define SCOPE_SYSTEM ARM64_CPUCAP_SCOPE_SYSTEM #define SCOPE_LOCAL_CPU ARM64_CPUCAP_SCOPE_LOCAL_CPU #define SCOPE_BOOT_CPU ARM64_CPUCAP_SCOPE_BOOT_CPU #define SCOPE_ALL ARM64_CPUCAP_SCOPE_MASK /* * Is it permitted for a late CPU to have this capability when system * hasn't already enabled it ? */ #define ARM64_CPUCAP_PERMITTED_FOR_LATE_CPU ((u16)BIT(4)) /* Is it safe for a late CPU to miss this capability when system has it */ #define ARM64_CPUCAP_OPTIONAL_FOR_LATE_CPU ((u16)BIT(5)) /* Panic when a conflict is detected */ #define ARM64_CPUCAP_PANIC_ON_CONFLICT ((u16)BIT(6)) /* * CPU errata workarounds that need to be enabled at boot time if one or * more CPUs in the system requires it. When one of these capabilities * has been enabled, it is safe to allow any CPU to boot that doesn't * require the workaround. However, it is not safe if a "late" CPU * requires a workaround and the system hasn't enabled it already. */ #define ARM64_CPUCAP_LOCAL_CPU_ERRATUM \ (ARM64_CPUCAP_SCOPE_LOCAL_CPU | ARM64_CPUCAP_OPTIONAL_FOR_LATE_CPU) /* * CPU feature detected at boot time based on system-wide value of a * feature. It is safe for a late CPU to have this feature even though * the system hasn't enabled it, although the feature will not be used * by Linux in this case. If the system has enabled this feature already, * then every late CPU must have it. */ #define ARM64_CPUCAP_SYSTEM_FEATURE \ (ARM64_CPUCAP_SCOPE_SYSTEM | ARM64_CPUCAP_PERMITTED_FOR_LATE_CPU) /* * CPU feature detected at boot time based on feature of one or more CPUs. * All possible conflicts for a late CPU are ignored. * NOTE: this means that a late CPU with the feature will *not* cause the * capability to be advertised by cpus_have_*cap()! */ #define ARM64_CPUCAP_WEAK_LOCAL_CPU_FEATURE \ (ARM64_CPUCAP_SCOPE_LOCAL_CPU | \ ARM64_CPUCAP_OPTIONAL_FOR_LATE_CPU | \ ARM64_CPUCAP_PERMITTED_FOR_LATE_CPU) /* * CPU feature detected at boot time, on one or more CPUs. A late CPU * is not allowed to have the capability when the system doesn't have it. * It is Ok for a late CPU to miss the feature. */ #define ARM64_CPUCAP_BOOT_RESTRICTED_CPU_LOCAL_FEATURE \ (ARM64_CPUCAP_SCOPE_LOCAL_CPU | \ ARM64_CPUCAP_OPTIONAL_FOR_LATE_CPU) /* * CPU feature used early in the boot based on the boot CPU. All secondary * CPUs must match the state of the capability as detected by the boot CPU. In * case of a conflict, a kernel panic is triggered. */ #define ARM64_CPUCAP_STRICT_BOOT_CPU_FEATURE \ (ARM64_CPUCAP_SCOPE_BOOT_CPU | ARM64_CPUCAP_PANIC_ON_CONFLICT) /* * CPU feature used early in the boot based on the boot CPU. It is safe for a * late CPU to have this feature even though the boot CPU hasn't enabled it, * although the feature will not be used by Linux in this case. If the boot CPU * has enabled this feature already, then every late CPU must have it. */ #define ARM64_CPUCAP_BOOT_CPU_FEATURE \ (ARM64_CPUCAP_SCOPE_BOOT_CPU | ARM64_CPUCAP_PERMITTED_FOR_LATE_CPU) struct arm64_cpu_capabilities { const char *desc; u16 capability; u16 type; bool (*matches)(const struct arm64_cpu_capabilities *caps, int scope); /* * Take the appropriate actions to configure this capability * for this CPU. If the capability is detected by the kernel * this will be called on all the CPUs in the system, * including the hotplugged CPUs, regardless of whether the * capability is available on that specific CPU. This is * useful for some capabilities (e.g, working around CPU * errata), where all the CPUs must take some action (e.g, * changing system control/configuration). Thus, if an action * is required only if the CPU has the capability, then the * routine must check it before taking any action. */ void (*cpu_enable)(const struct arm64_cpu_capabilities *cap); union { struct { /* To be used for erratum handling only */ struct midr_range midr_range; const struct arm64_midr_revidr { u32 midr_rv; /* revision/variant */ u32 revidr_mask; } * const fixed_revs; }; const struct midr_range *midr_range_list; struct { /* Feature register checking */ u32 sys_reg; u8 field_pos; u8 field_width; u8 min_field_value; u8 max_field_value; u8 hwcap_type; bool sign; unsigned long hwcap; }; }; /* * An optional list of "matches/cpu_enable" pair for the same * "capability" of the same "type" as described by the parent. * Only matches(), cpu_enable() and fields relevant to these * methods are significant in the list. The cpu_enable is * invoked only if the corresponding entry "matches()". * However, if a cpu_enable() method is associated * with multiple matches(), care should be taken that either * the match criteria are mutually exclusive, or that the * method is robust against being called multiple times. */ const struct arm64_cpu_capabilities *match_list; const struct cpumask *cpus; }; static inline int cpucap_default_scope(const struct arm64_cpu_capabilities *cap) { return cap->type & ARM64_CPUCAP_SCOPE_MASK; } /* * Generic helper for handling capabilities with multiple (match,enable) pairs * of call backs, sharing the same capability bit. * Iterate over each entry to see if at least one matches. */ static inline bool cpucap_multi_entry_cap_matches(const struct arm64_cpu_capabilities *entry, int scope) { const struct arm64_cpu_capabilities *caps; for (caps = entry->match_list; caps->matches; caps++) if (caps->matches(caps, scope)) return true; return false; } static __always_inline bool is_vhe_hyp_code(void) { /* Only defined for code run in VHE hyp context */ return __is_defined(__KVM_VHE_HYPERVISOR__); } static __always_inline bool is_nvhe_hyp_code(void) { /* Only defined for code run in NVHE hyp context */ return __is_defined(__KVM_NVHE_HYPERVISOR__); } static __always_inline bool is_hyp_code(void) { return is_vhe_hyp_code() || is_nvhe_hyp_code(); } extern DECLARE_BITMAP(system_cpucaps, ARM64_NCAPS); extern DECLARE_BITMAP(boot_cpucaps, ARM64_NCAPS); #define for_each_available_cap(cap) \ for_each_set_bit(cap, system_cpucaps, ARM64_NCAPS) bool this_cpu_has_cap(unsigned int cap); void cpu_set_feature(unsigned int num); bool cpu_have_feature(unsigned int num); unsigned long cpu_get_elf_hwcap(void); unsigned long cpu_get_elf_hwcap2(void); unsigned long cpu_get_elf_hwcap3(void); #define cpu_set_named_feature(name) cpu_set_feature(cpu_feature(name)) #define cpu_have_named_feature(name) cpu_have_feature(cpu_feature(name)) static __always_inline bool boot_capabilities_finalized(void) { return alternative_has_cap_likely(ARM64_ALWAYS_BOOT); } static __always_inline bool system_capabilities_finalized(void) { return alternative_has_cap_likely(ARM64_ALWAYS_SYSTEM); } /* * Test for a capability with a runtime check. * * Before the capability is detected, this returns false. */ static __always_inline bool cpus_have_cap(unsigned int num) { if (__builtin_constant_p(num) && !cpucap_is_possible(num)) return false; if (num >= ARM64_NCAPS) return false; return arch_test_bit(num, system_cpucaps); } /* * Test for a capability without a runtime check. * * Before boot capabilities are finalized, this will BUG(). * After boot capabilities are finalized, this is patched to avoid a runtime * check. * * @num must be a compile-time constant. */ static __always_inline bool cpus_have_final_boot_cap(int num) { if (boot_capabilities_finalized()) return alternative_has_cap_unlikely(num); else BUG(); } /* * Test for a capability without a runtime check. * * Before system capabilities are finalized, this will BUG(). * After system capabilities are finalized, this is patched to avoid a runtime * check. * * @num must be a compile-time constant. */ static __always_inline bool cpus_have_final_cap(int num) { if (system_capabilities_finalized()) return alternative_has_cap_unlikely(num); else BUG(); } static inline int __attribute_const__ cpuid_feature_extract_signed_field_width(u64 features, int field, int width) { return (s64)(features << (64 - width - field)) >> (64 - width); } static inline int __attribute_const__ cpuid_feature_extract_signed_field(u64 features, int field) { return cpuid_feature_extract_signed_field_width(features, field, 4); } static __always_inline unsigned int __attribute_const__ cpuid_feature_extract_unsigned_field_width(u64 features, int field, int width) { return (u64)(features << (64 - width - field)) >> (64 - width); } static __always_inline unsigned int __attribute_const__ cpuid_feature_extract_unsigned_field(u64 features, int field) { return cpuid_feature_extract_unsigned_field_width(features, field, 4); } /* * Fields that identify the version of the Performance Monitors Extension do * not follow the standard ID scheme. See ARM DDI 0487E.a page D13-2825, * "Alternative ID scheme used for the Performance Monitors Extension version". */ static inline u64 __attribute_const__ cpuid_feature_cap_perfmon_field(u64 features, int field, u64 cap) { u64 val = cpuid_feature_extract_unsigned_field(features, field); u64 mask = GENMASK_ULL(field + 3, field); /* Treat IMPLEMENTATION DEFINED functionality as unimplemented */ if (val == ID_AA64DFR0_EL1_PMUVer_IMP_DEF) val = 0; if (val > cap) { features &= ~mask; features |= (cap << field) & mask; } return features; } static inline u64 arm64_ftr_mask(const struct arm64_ftr_bits *ftrp) { return (u64)GENMASK(ftrp->shift + ftrp->width - 1, ftrp->shift); } static inline u64 arm64_ftr_reg_user_value(const struct arm64_ftr_reg *reg) { return (reg->user_val | (reg->sys_val & reg->user_mask)); } static inline int __attribute_const__ cpuid_feature_extract_field_width(u64 features, int field, int width, bool sign) { if (WARN_ON_ONCE(!width)) width = 4; return (sign) ? cpuid_feature_extract_signed_field_width(features, field, width) : cpuid_feature_extract_unsigned_field_width(features, field, width); } static inline int __attribute_const__ cpuid_feature_extract_field(u64 features, int field, bool sign) { return cpuid_feature_extract_field_width(features, field, 4, sign); } static inline s64 arm64_ftr_value(const struct arm64_ftr_bits *ftrp, u64 val) { return (s64)cpuid_feature_extract_field_width(val, ftrp->shift, ftrp->width, ftrp->sign); } static inline bool id_aa64mmfr0_mixed_endian_el0(u64 mmfr0) { return cpuid_feature_extract_unsigned_field(mmfr0, ID_AA64MMFR0_EL1_BIGEND_SHIFT) == 0x1 || cpuid_feature_extract_unsigned_field(mmfr0, ID_AA64MMFR0_EL1_BIGENDEL0_SHIFT) == 0x1; } static inline bool id_aa64pfr0_32bit_el1(u64 pfr0) { u32 val = cpuid_feature_extract_unsigned_field(pfr0, ID_AA64PFR0_EL1_EL1_SHIFT); return val == ID_AA64PFR0_EL1_EL1_AARCH32; } static inline bool id_aa64pfr0_32bit_el0(u64 pfr0) { u32 val = cpuid_feature_extract_unsigned_field(pfr0, ID_AA64PFR0_EL1_EL0_SHIFT); return val == ID_AA64PFR0_EL1_EL0_AARCH32; } static inline bool id_aa64pfr0_sve(u64 pfr0) { u32 val = cpuid_feature_extract_unsigned_field(pfr0, ID_AA64PFR0_EL1_SVE_SHIFT); return val > 0; } static inline bool id_aa64pfr1_sme(u64 pfr1) { u32 val = cpuid_feature_extract_unsigned_field(pfr1, ID_AA64PFR1_EL1_SME_SHIFT); return val > 0; } static inline bool id_aa64pfr0_mpam(u64 pfr0) { u32 val = cpuid_feature_extract_unsigned_field(pfr0, ID_AA64PFR0_EL1_MPAM_SHIFT); return val > 0; } static inline bool id_aa64pfr1_mte(u64 pfr1) { u32 val = cpuid_feature_extract_unsigned_field(pfr1, ID_AA64PFR1_EL1_MTE_SHIFT); return val >= ID_AA64PFR1_EL1_MTE_MTE2; } void __init setup_boot_cpu_features(void); void __init setup_system_features(void); void __init setup_user_features(void); void check_local_cpu_capabilities(void); u64 read_sanitised_ftr_reg(u32 id); u64 __read_sysreg_by_encoding(u32 sys_id); static inline bool cpu_supports_mixed_endian_el0(void) { return id_aa64mmfr0_mixed_endian_el0(read_cpuid(ID_AA64MMFR0_EL1)); } static inline bool supports_csv2p3(int scope) { u64 pfr0; u8 csv2_val; if (scope == SCOPE_LOCAL_CPU) pfr0 = read_sysreg_s(SYS_ID_AA64PFR0_EL1); else pfr0 = read_sanitised_ftr_reg(SYS_ID_AA64PFR0_EL1); csv2_val = cpuid_feature_extract_unsigned_field(pfr0, ID_AA64PFR0_EL1_CSV2_SHIFT); return csv2_val == 3; } static inline bool supports_clearbhb(int scope) { u64 isar2; if (scope == SCOPE_LOCAL_CPU) isar2 = read_sysreg_s(SYS_ID_AA64ISAR2_EL1); else isar2 = read_sanitised_ftr_reg(SYS_ID_AA64ISAR2_EL1); return cpuid_feature_extract_unsigned_field(isar2, ID_AA64ISAR2_EL1_CLRBHB_SHIFT); } const struct cpumask *system_32bit_el0_cpumask(void); DECLARE_STATIC_KEY_FALSE(arm64_mismatched_32bit_el0); static inline bool system_supports_32bit_el0(void) { u64 pfr0 = read_sanitised_ftr_reg(SYS_ID_AA64PFR0_EL1); return static_branch_unlikely(&arm64_mismatched_32bit_el0) || id_aa64pfr0_32bit_el0(pfr0); } static inline bool system_supports_4kb_granule(void) { u64 mmfr0; u32 val; mmfr0 = read_sanitised_ftr_reg(SYS_ID_AA64MMFR0_EL1); val = cpuid_feature_extract_unsigned_field(mmfr0, ID_AA64MMFR0_EL1_TGRAN4_SHIFT); return (val >= ID_AA64MMFR0_EL1_TGRAN4_SUPPORTED_MIN) && (val <= ID_AA64MMFR0_EL1_TGRAN4_SUPPORTED_MAX); } static inline bool system_supports_64kb_granule(void) { u64 mmfr0; u32 val; mmfr0 = read_sanitised_ftr_reg(SYS_ID_AA64MMFR0_EL1); val = cpuid_feature_extract_unsigned_field(mmfr0, ID_AA64MMFR0_EL1_TGRAN64_SHIFT); return (val >= ID_AA64MMFR0_EL1_TGRAN64_SUPPORTED_MIN) && (val <= ID_AA64MMFR0_EL1_TGRAN64_SUPPORTED_MAX); } static inline bool system_supports_16kb_granule(void) { u64 mmfr0; u32 val; mmfr0 = read_sanitised_ftr_reg(SYS_ID_AA64MMFR0_EL1); val = cpuid_feature_extract_unsigned_field(mmfr0, ID_AA64MMFR0_EL1_TGRAN16_SHIFT); return (val >= ID_AA64MMFR0_EL1_TGRAN16_SUPPORTED_MIN) && (val <= ID_AA64MMFR0_EL1_TGRAN16_SUPPORTED_MAX); } static inline bool system_supports_mixed_endian_el0(void) { return id_aa64mmfr0_mixed_endian_el0(read_sanitised_ftr_reg(SYS_ID_AA64MMFR0_EL1)); } static inline bool system_supports_mixed_endian(void) { u64 mmfr0; u32 val; mmfr0 = read_sanitised_ftr_reg(SYS_ID_AA64MMFR0_EL1); val = cpuid_feature_extract_unsigned_field(mmfr0, ID_AA64MMFR0_EL1_BIGEND_SHIFT); return val == 0x1; } static __always_inline bool system_supports_fpsimd(void) { return alternative_has_cap_likely(ARM64_HAS_FPSIMD); } static inline bool system_uses_hw_pan(void) { return alternative_has_cap_unlikely(ARM64_HAS_PAN); } static inline bool system_uses_ttbr0_pan(void) { return IS_ENABLED(CONFIG_ARM64_SW_TTBR0_PAN) && !system_uses_hw_pan(); } static __always_inline bool system_supports_sve(void) { return alternative_has_cap_unlikely(ARM64_SVE); } static __always_inline bool system_supports_sme(void) { return alternative_has_cap_unlikely(ARM64_SME); } static __always_inline bool system_supports_sme2(void) { return alternative_has_cap_unlikely(ARM64_SME2); } static __always_inline bool system_supports_fa64(void) { return alternative_has_cap_unlikely(ARM64_SME_FA64); } static __always_inline bool system_supports_tpidr2(void) { return system_supports_sme(); } static __always_inline bool system_supports_fpmr(void) { return alternative_has_cap_unlikely(ARM64_HAS_FPMR); } static __always_inline bool system_supports_cnp(void) { return alternative_has_cap_unlikely(ARM64_HAS_CNP); } static inline bool system_supports_address_auth(void) { return cpus_have_final_boot_cap(ARM64_HAS_ADDRESS_AUTH); } static inline bool system_supports_generic_auth(void) { return alternative_has_cap_unlikely(ARM64_HAS_GENERIC_AUTH); } static inline bool system_has_full_ptr_auth(void) { return system_supports_address_auth() && system_supports_generic_auth(); } static __always_inline bool system_uses_irq_prio_masking(void) { return alternative_has_cap_unlikely(ARM64_HAS_GIC_PRIO_MASKING); } static inline bool system_supports_mte(void) { return alternative_has_cap_unlikely(ARM64_MTE); } static inline bool system_has_prio_mask_debugging(void) { return IS_ENABLED(CONFIG_ARM64_DEBUG_PRIORITY_MASKING) && system_uses_irq_prio_masking(); } static inline bool system_supports_bti(void) { return cpus_have_final_cap(ARM64_BTI); } static inline bool system_supports_bti_kernel(void) { return IS_ENABLED(CONFIG_ARM64_BTI_KERNEL) && cpus_have_final_boot_cap(ARM64_BTI); } static inline bool system_supports_tlb_range(void) { return alternative_has_cap_unlikely(ARM64_HAS_TLB_RANGE); } static inline bool system_supports_lpa2(void) { return cpus_have_final_cap(ARM64_HAS_LPA2); } static inline bool system_supports_poe(void) { return alternative_has_cap_unlikely(ARM64_HAS_S1POE); } static inline bool system_supports_gcs(void) { return alternative_has_cap_unlikely(ARM64_HAS_GCS); } static inline bool system_supports_haft(void) { return cpus_have_final_cap(ARM64_HAFT); } static __always_inline bool system_supports_mpam(void) { return alternative_has_cap_unlikely(ARM64_MPAM); } static __always_inline bool system_supports_mpam_hcr(void) { return alternative_has_cap_unlikely(ARM64_MPAM_HCR); } int do_emulate_mrs(struct pt_regs *regs, u32 sys_reg, u32 rt); bool try_emulate_mrs(struct pt_regs *regs, u32 isn); static inline u32 id_aa64mmfr0_parange_to_phys_shift(int parange) { switch (parange) { case ID_AA64MMFR0_EL1_PARANGE_32: return 32; case ID_AA64MMFR0_EL1_PARANGE_36: return 36; case ID_AA64MMFR0_EL1_PARANGE_40: return 40; case ID_AA64MMFR0_EL1_PARANGE_42: return 42; case ID_AA64MMFR0_EL1_PARANGE_44: return 44; case ID_AA64MMFR0_EL1_PARANGE_48: return 48; case ID_AA64MMFR0_EL1_PARANGE_52: return 52; /* * A future PE could use a value unknown to the kernel. * However, by the "D10.1.4 Principles of the ID scheme * for fields in ID registers", ARM DDI 0487C.a, any new * value is guaranteed to be higher than what we know already. * As a safe limit, we return the limit supported by the kernel. */ default: return CONFIG_ARM64_PA_BITS; } } /* Check whether hardware update of the Access flag is supported */ static inline bool cpu_has_hw_af(void) { u64 mmfr1; if (!IS_ENABLED(CONFIG_ARM64_HW_AFDBM)) return false; /* * Use cached version to avoid emulated msr operation on KVM * guests. */ mmfr1 = read_sanitised_ftr_reg(SYS_ID_AA64MMFR1_EL1); return cpuid_feature_extract_unsigned_field(mmfr1, ID_AA64MMFR1_EL1_HAFDBS_SHIFT); } static inline bool cpu_has_pan(void) { u64 mmfr1 = read_cpuid(ID_AA64MMFR1_EL1); return cpuid_feature_extract_unsigned_field(mmfr1, ID_AA64MMFR1_EL1_PAN_SHIFT); } #ifdef CONFIG_ARM64_AMU_EXTN /* Check whether the cpu supports the Activity Monitors Unit (AMU) */ extern bool cpu_has_amu_feat(int cpu); #else static inline bool cpu_has_amu_feat(int cpu) { return false; } #endif /* Get a cpu that supports the Activity Monitors Unit (AMU) */ extern int get_cpu_with_amu_feat(void); static inline unsigned int get_vmid_bits(u64 mmfr1) { int vmid_bits; vmid_bits = cpuid_feature_extract_unsigned_field(mmfr1, ID_AA64MMFR1_EL1_VMIDBits_SHIFT); if (vmid_bits == ID_AA64MMFR1_EL1_VMIDBits_16) return 16; /* * Return the default here even if any reserved * value is fetched from the system register. */ return 8; } s64 arm64_ftr_safe_value(const struct arm64_ftr_bits *ftrp, s64 new, s64 cur); struct arm64_ftr_reg *get_arm64_ftr_reg(u32 sys_id); extern struct arm64_ftr_override id_aa64mmfr0_override; extern struct arm64_ftr_override id_aa64mmfr1_override; extern struct arm64_ftr_override id_aa64mmfr2_override; extern struct arm64_ftr_override id_aa64pfr0_override; extern struct arm64_ftr_override id_aa64pfr1_override; extern struct arm64_ftr_override id_aa64zfr0_override; extern struct arm64_ftr_override id_aa64smfr0_override; extern struct arm64_ftr_override id_aa64isar1_override; extern struct arm64_ftr_override id_aa64isar2_override; extern struct arm64_ftr_override arm64_sw_feature_override; static inline u64 arm64_apply_feature_override(u64 val, int feat, int width, const struct arm64_ftr_override *override) { u64 oval = override->val; /* * When it encounters an invalid override (e.g., an override that * cannot be honoured due to a missing CPU feature), the early idreg * override code will set the mask to 0x0 and the value to non-zero for * the field in question. In order to determine whether the override is * valid or not for the field we are interested in, we first need to * disregard bits belonging to other fields. */ oval &= GENMASK_ULL(feat + width - 1, feat); /* * The override is valid if all value bits are accounted for in the * mask. If so, replace the masked bits with the override value. */ if (oval == (oval & override->mask)) { val &= ~override->mask; val |= oval; } /* Extract the field from the updated value */ return cpuid_feature_extract_unsigned_field(val, feat); } static inline bool arm64_test_sw_feature_override(int feat) { /* * Software features are pseudo CPU features that have no underlying * CPUID system register value to apply the override to. */ return arm64_apply_feature_override(0, feat, 4, &arm64_sw_feature_override); } static inline bool kaslr_disabled_cmdline(void) { return arm64_test_sw_feature_override(ARM64_SW_FEATURE_OVERRIDE_NOKASLR); } u32 get_kvm_ipa_limit(void); void dump_cpu_features(void); static inline bool cpu_has_bti(void) { if (!IS_ENABLED(CONFIG_ARM64_BTI)) return false; return arm64_apply_feature_override(read_cpuid(ID_AA64PFR1_EL1), ID_AA64PFR1_EL1_BT_SHIFT, 4, &id_aa64pfr1_override); } static inline bool cpu_has_pac(void) { u64 isar1, isar2; if (!IS_ENABLED(CONFIG_ARM64_PTR_AUTH)) return false; isar1 = read_cpuid(ID_AA64ISAR1_EL1); isar2 = read_cpuid(ID_AA64ISAR2_EL1); if (arm64_apply_feature_override(isar1, ID_AA64ISAR1_EL1_APA_SHIFT, 4, &id_aa64isar1_override)) return true; if (arm64_apply_feature_override(isar1, ID_AA64ISAR1_EL1_API_SHIFT, 4, &id_aa64isar1_override)) return true; return arm64_apply_feature_override(isar2, ID_AA64ISAR2_EL1_APA3_SHIFT, 4, &id_aa64isar2_override); } static inline bool cpu_has_lva(void) { u64 mmfr2; mmfr2 = read_sysreg_s(SYS_ID_AA64MMFR2_EL1); mmfr2 &= ~id_aa64mmfr2_override.mask; mmfr2 |= id_aa64mmfr2_override.val; return cpuid_feature_extract_unsigned_field(mmfr2, ID_AA64MMFR2_EL1_VARange_SHIFT); } static inline bool cpu_has_lpa2(void) { #ifdef CONFIG_ARM64_LPA2 u64 mmfr0; int feat; mmfr0 = read_sysreg(id_aa64mmfr0_el1); mmfr0 &= ~id_aa64mmfr0_override.mask; mmfr0 |= id_aa64mmfr0_override.val; feat = cpuid_feature_extract_signed_field(mmfr0, ID_AA64MMFR0_EL1_TGRAN_SHIFT); return feat >= ID_AA64MMFR0_EL1_TGRAN_LPA2; #else return false; #endif } #endif /* __ASSEMBLY__ */ #endif |
| 413 417 417 939 935 417 416 328 417 861 857 861 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 | // SPDX-License-Identifier: GPL-2.0-only #include "cgroup-internal.h" #include <linux/sched/cputime.h> #include <linux/bpf.h> #include <linux/btf.h> #include <linux/btf_ids.h> #include <trace/events/cgroup.h> static DEFINE_SPINLOCK(cgroup_rstat_lock); static DEFINE_PER_CPU(raw_spinlock_t, cgroup_rstat_cpu_lock); static void cgroup_base_stat_flush(struct cgroup *cgrp, int cpu); static struct cgroup_rstat_cpu *cgroup_rstat_cpu(struct cgroup *cgrp, int cpu) { return per_cpu_ptr(cgrp->rstat_cpu, cpu); } /* * Helper functions for rstat per CPU lock (cgroup_rstat_cpu_lock). * * This makes it easier to diagnose locking issues and contention in * production environments. The parameter @fast_path determine the * tracepoints being added, allowing us to diagnose "flush" related * operations without handling high-frequency fast-path "update" events. */ static __always_inline unsigned long _cgroup_rstat_cpu_lock(raw_spinlock_t *cpu_lock, int cpu, struct cgroup *cgrp, const bool fast_path) { unsigned long flags; bool contended; /* * The _irqsave() is needed because cgroup_rstat_lock is * spinlock_t which is a sleeping lock on PREEMPT_RT. Acquiring * this lock with the _irq() suffix only disables interrupts on * a non-PREEMPT_RT kernel. The raw_spinlock_t below disables * interrupts on both configurations. The _irqsave() ensures * that interrupts are always disabled and later restored. */ contended = !raw_spin_trylock_irqsave(cpu_lock, flags); if (contended) { if (fast_path) trace_cgroup_rstat_cpu_lock_contended_fastpath(cgrp, cpu, contended); else trace_cgroup_rstat_cpu_lock_contended(cgrp, cpu, contended); raw_spin_lock_irqsave(cpu_lock, flags); } if (fast_path) trace_cgroup_rstat_cpu_locked_fastpath(cgrp, cpu, contended); else trace_cgroup_rstat_cpu_locked(cgrp, cpu, contended); return flags; } static __always_inline void _cgroup_rstat_cpu_unlock(raw_spinlock_t *cpu_lock, int cpu, struct cgroup *cgrp, unsigned long flags, const bool fast_path) { if (fast_path) trace_cgroup_rstat_cpu_unlock_fastpath(cgrp, cpu, false); else trace_cgroup_rstat_cpu_unlock(cgrp, cpu, false); raw_spin_unlock_irqrestore(cpu_lock, flags); } /** * cgroup_rstat_updated - keep track of updated rstat_cpu * @cgrp: target cgroup * @cpu: cpu on which rstat_cpu was updated * * @cgrp's rstat_cpu on @cpu was updated. Put it on the parent's matching * rstat_cpu->updated_children list. See the comment on top of * cgroup_rstat_cpu definition for details. */ __bpf_kfunc void cgroup_rstat_updated(struct cgroup *cgrp, int cpu) { raw_spinlock_t *cpu_lock = per_cpu_ptr(&cgroup_rstat_cpu_lock, cpu); unsigned long flags; /* * Speculative already-on-list test. This may race leading to * temporary inaccuracies, which is fine. * * Because @parent's updated_children is terminated with @parent * instead of NULL, we can tell whether @cgrp is on the list by * testing the next pointer for NULL. */ if (data_race(cgroup_rstat_cpu(cgrp, cpu)->updated_next)) return; flags = _cgroup_rstat_cpu_lock(cpu_lock, cpu, cgrp, true); /* put @cgrp and all ancestors on the corresponding updated lists */ while (true) { struct cgroup_rstat_cpu *rstatc = cgroup_rstat_cpu(cgrp, cpu); struct cgroup *parent = cgroup_parent(cgrp); struct cgroup_rstat_cpu *prstatc; /* * Both additions and removals are bottom-up. If a cgroup * is already in the tree, all ancestors are. */ if (rstatc->updated_next) break; /* Root has no parent to link it to, but mark it busy */ if (!parent) { rstatc->updated_next = cgrp; break; } prstatc = cgroup_rstat_cpu(parent, cpu); rstatc->updated_next = prstatc->updated_children; prstatc->updated_children = cgrp; cgrp = parent; } _cgroup_rstat_cpu_unlock(cpu_lock, cpu, cgrp, flags, true); } /** * cgroup_rstat_push_children - push children cgroups into the given list * @head: current head of the list (= subtree root) * @child: first child of the root * @cpu: target cpu * Return: A new singly linked list of cgroups to be flush * * Iteratively traverse down the cgroup_rstat_cpu updated tree level by * level and push all the parents first before their next level children * into a singly linked list built from the tail backward like "pushing" * cgroups into a stack. The root is pushed by the caller. */ static struct cgroup *cgroup_rstat_push_children(struct cgroup *head, struct cgroup *child, int cpu) { struct cgroup *chead = child; /* Head of child cgroup level */ struct cgroup *ghead = NULL; /* Head of grandchild cgroup level */ struct cgroup *parent, *grandchild; struct cgroup_rstat_cpu *crstatc; child->rstat_flush_next = NULL; next_level: while (chead) { child = chead; chead = child->rstat_flush_next; parent = cgroup_parent(child); /* updated_next is parent cgroup terminated */ while (child != parent) { child->rstat_flush_next = head; head = child; crstatc = cgroup_rstat_cpu(child, cpu); grandchild = crstatc->updated_children; if (grandchild != child) { /* Push the grand child to the next level */ crstatc->updated_children = child; grandchild->rstat_flush_next = ghead; ghead = grandchild; } child = crstatc->updated_next; crstatc->updated_next = NULL; } } if (ghead) { chead = ghead; ghead = NULL; goto next_level; } return head; } /** * cgroup_rstat_updated_list - return a list of updated cgroups to be flushed * @root: root of the cgroup subtree to traverse * @cpu: target cpu * Return: A singly linked list of cgroups to be flushed * * Walks the updated rstat_cpu tree on @cpu from @root. During traversal, * each returned cgroup is unlinked from the updated tree. * * The only ordering guarantee is that, for a parent and a child pair * covered by a given traversal, the child is before its parent in * the list. * * Note that updated_children is self terminated and points to a list of * child cgroups if not empty. Whereas updated_next is like a sibling link * within the children list and terminated by the parent cgroup. An exception * here is the cgroup root whose updated_next can be self terminated. */ static struct cgroup *cgroup_rstat_updated_list(struct cgroup *root, int cpu) { raw_spinlock_t *cpu_lock = per_cpu_ptr(&cgroup_rstat_cpu_lock, cpu); struct cgroup_rstat_cpu *rstatc = cgroup_rstat_cpu(root, cpu); struct cgroup *head = NULL, *parent, *child; unsigned long flags; flags = _cgroup_rstat_cpu_lock(cpu_lock, cpu, root, false); /* Return NULL if this subtree is not on-list */ if (!rstatc->updated_next) goto unlock_ret; /* * Unlink @root from its parent. As the updated_children list is * singly linked, we have to walk it to find the removal point. */ parent = cgroup_parent(root); if (parent) { struct cgroup_rstat_cpu *prstatc; struct cgroup **nextp; prstatc = cgroup_rstat_cpu(parent, cpu); nextp = &prstatc->updated_children; while (*nextp != root) { struct cgroup_rstat_cpu *nrstatc; nrstatc = cgroup_rstat_cpu(*nextp, cpu); WARN_ON_ONCE(*nextp == parent); nextp = &nrstatc->updated_next; } *nextp = rstatc->updated_next; } rstatc->updated_next = NULL; /* Push @root to the list first before pushing the children */ head = root; root->rstat_flush_next = NULL; child = rstatc->updated_children; rstatc->updated_children = root; if (child != root) head = cgroup_rstat_push_children(head, child, cpu); unlock_ret: _cgroup_rstat_cpu_unlock(cpu_lock, cpu, root, flags, false); return head; } /* * A hook for bpf stat collectors to attach to and flush their stats. * Together with providing bpf kfuncs for cgroup_rstat_updated() and * cgroup_rstat_flush(), this enables a complete workflow where bpf progs that * collect cgroup stats can integrate with rstat for efficient flushing. * * A static noinline declaration here could cause the compiler to optimize away * the function. A global noinline declaration will keep the definition, but may * optimize away the callsite. Therefore, __weak is needed to ensure that the * call is still emitted, by telling the compiler that we don't know what the * function might eventually be. */ __bpf_hook_start(); __weak noinline void bpf_rstat_flush(struct cgroup *cgrp, struct cgroup *parent, int cpu) { } __bpf_hook_end(); /* * Helper functions for locking cgroup_rstat_lock. * * This makes it easier to diagnose locking issues and contention in * production environments. The parameter @cpu_in_loop indicate lock * was released and re-taken when collection data from the CPUs. The * value -1 is used when obtaining the main lock else this is the CPU * number processed last. */ static inline void __cgroup_rstat_lock(struct cgroup *cgrp, int cpu_in_loop) __acquires(&cgroup_rstat_lock) { bool contended; contended = !spin_trylock_irq(&cgroup_rstat_lock); if (contended) { trace_cgroup_rstat_lock_contended(cgrp, cpu_in_loop, contended); spin_lock_irq(&cgroup_rstat_lock); } trace_cgroup_rstat_locked(cgrp, cpu_in_loop, contended); } static inline void __cgroup_rstat_unlock(struct cgroup *cgrp, int cpu_in_loop) __releases(&cgroup_rstat_lock) { trace_cgroup_rstat_unlock(cgrp, cpu_in_loop, false); spin_unlock_irq(&cgroup_rstat_lock); } /* see cgroup_rstat_flush() */ static void cgroup_rstat_flush_locked(struct cgroup *cgrp) __releases(&cgroup_rstat_lock) __acquires(&cgroup_rstat_lock) { int cpu; lockdep_assert_held(&cgroup_rstat_lock); for_each_possible_cpu(cpu) { struct cgroup *pos = cgroup_rstat_updated_list(cgrp, cpu); for (; pos; pos = pos->rstat_flush_next) { struct cgroup_subsys_state *css; cgroup_base_stat_flush(pos, cpu); bpf_rstat_flush(pos, cgroup_parent(pos), cpu); rcu_read_lock(); list_for_each_entry_rcu(css, &pos->rstat_css_list, rstat_css_node) css->ss->css_rstat_flush(css, cpu); rcu_read_unlock(); } /* play nice and yield if necessary */ if (need_resched() || spin_needbreak(&cgroup_rstat_lock)) { __cgroup_rstat_unlock(cgrp, cpu); if (!cond_resched()) cpu_relax(); __cgroup_rstat_lock(cgrp, cpu); } } } /** * cgroup_rstat_flush - flush stats in @cgrp's subtree * @cgrp: target cgroup * * Collect all per-cpu stats in @cgrp's subtree into the global counters * and propagate them upwards. After this function returns, all cgroups in * the subtree have up-to-date ->stat. * * This also gets all cgroups in the subtree including @cgrp off the * ->updated_children lists. * * This function may block. */ __bpf_kfunc void cgroup_rstat_flush(struct cgroup *cgrp) { might_sleep(); __cgroup_rstat_lock(cgrp, -1); cgroup_rstat_flush_locked(cgrp); __cgroup_rstat_unlock(cgrp, -1); } /** * cgroup_rstat_flush_hold - flush stats in @cgrp's subtree and hold * @cgrp: target cgroup * * Flush stats in @cgrp's subtree and prevent further flushes. Must be * paired with cgroup_rstat_flush_release(). * * This function may block. */ void cgroup_rstat_flush_hold(struct cgroup *cgrp) __acquires(&cgroup_rstat_lock) { might_sleep(); __cgroup_rstat_lock(cgrp, -1); cgroup_rstat_flush_locked(cgrp); } /** * cgroup_rstat_flush_release - release cgroup_rstat_flush_hold() * @cgrp: cgroup used by tracepoint */ void cgroup_rstat_flush_release(struct cgroup *cgrp) __releases(&cgroup_rstat_lock) { __cgroup_rstat_unlock(cgrp, -1); } int cgroup_rstat_init(struct cgroup *cgrp) { int cpu; /* the root cgrp has rstat_cpu preallocated */ if (!cgrp->rstat_cpu) { cgrp->rstat_cpu = alloc_percpu(struct cgroup_rstat_cpu); if (!cgrp->rstat_cpu) return -ENOMEM; } /* ->updated_children list is self terminated */ for_each_possible_cpu(cpu) { struct cgroup_rstat_cpu *rstatc = cgroup_rstat_cpu(cgrp, cpu); rstatc->updated_children = cgrp; u64_stats_init(&rstatc->bsync); } return 0; } void cgroup_rstat_exit(struct cgroup *cgrp) { int cpu; cgroup_rstat_flush(cgrp); /* sanity check */ for_each_possible_cpu(cpu) { struct cgroup_rstat_cpu *rstatc = cgroup_rstat_cpu(cgrp, cpu); if (WARN_ON_ONCE(rstatc->updated_children != cgrp) || WARN_ON_ONCE(rstatc->updated_next)) return; } free_percpu(cgrp->rstat_cpu); cgrp->rstat_cpu = NULL; } void __init cgroup_rstat_boot(void) { int cpu; for_each_possible_cpu(cpu) raw_spin_lock_init(per_cpu_ptr(&cgroup_rstat_cpu_lock, cpu)); } /* * Functions for cgroup basic resource statistics implemented on top of * rstat. */ static void cgroup_base_stat_add(struct cgroup_base_stat *dst_bstat, struct cgroup_base_stat *src_bstat) { dst_bstat->cputime.utime += src_bstat->cputime.utime; dst_bstat->cputime.stime += src_bstat->cputime.stime; dst_bstat->cputime.sum_exec_runtime += src_bstat->cputime.sum_exec_runtime; #ifdef CONFIG_SCHED_CORE dst_bstat->forceidle_sum += src_bstat->forceidle_sum; #endif dst_bstat->ntime += src_bstat->ntime; } static void cgroup_base_stat_sub(struct cgroup_base_stat *dst_bstat, struct cgroup_base_stat *src_bstat) { dst_bstat->cputime.utime -= src_bstat->cputime.utime; dst_bstat->cputime.stime -= src_bstat->cputime.stime; dst_bstat->cputime.sum_exec_runtime -= src_bstat->cputime.sum_exec_runtime; #ifdef CONFIG_SCHED_CORE dst_bstat->forceidle_sum -= src_bstat->forceidle_sum; #endif dst_bstat->ntime -= src_bstat->ntime; } static void cgroup_base_stat_flush(struct cgroup *cgrp, int cpu) { struct cgroup_rstat_cpu *rstatc = cgroup_rstat_cpu(cgrp, cpu); struct cgroup *parent = cgroup_parent(cgrp); struct cgroup_rstat_cpu *prstatc; struct cgroup_base_stat delta; unsigned seq; /* Root-level stats are sourced from system-wide CPU stats */ if (!parent) return; /* fetch the current per-cpu values */ do { seq = __u64_stats_fetch_begin(&rstatc->bsync); delta = rstatc->bstat; } while (__u64_stats_fetch_retry(&rstatc->bsync, seq)); /* propagate per-cpu delta to cgroup and per-cpu global statistics */ cgroup_base_stat_sub(&delta, &rstatc->last_bstat); cgroup_base_stat_add(&cgrp->bstat, &delta); cgroup_base_stat_add(&rstatc->last_bstat, &delta); cgroup_base_stat_add(&rstatc->subtree_bstat, &delta); /* propagate cgroup and per-cpu global delta to parent (unless that's root) */ if (cgroup_parent(parent)) { delta = cgrp->bstat; cgroup_base_stat_sub(&delta, &cgrp->last_bstat); cgroup_base_stat_add(&parent->bstat, &delta); cgroup_base_stat_add(&cgrp->last_bstat, &delta); delta = rstatc->subtree_bstat; prstatc = cgroup_rstat_cpu(parent, cpu); cgroup_base_stat_sub(&delta, &rstatc->last_subtree_bstat); cgroup_base_stat_add(&prstatc->subtree_bstat, &delta); cgroup_base_stat_add(&rstatc->last_subtree_bstat, &delta); } } static struct cgroup_rstat_cpu * cgroup_base_stat_cputime_account_begin(struct cgroup *cgrp, unsigned long *flags) { struct cgroup_rstat_cpu *rstatc; rstatc = get_cpu_ptr(cgrp->rstat_cpu); *flags = u64_stats_update_begin_irqsave(&rstatc->bsync); return rstatc; } static void cgroup_base_stat_cputime_account_end(struct cgroup *cgrp, struct cgroup_rstat_cpu *rstatc, unsigned long flags) { u64_stats_update_end_irqrestore(&rstatc->bsync, flags); cgroup_rstat_updated(cgrp, smp_processor_id()); put_cpu_ptr(rstatc); } void __cgroup_account_cputime(struct cgroup *cgrp, u64 delta_exec) { struct cgroup_rstat_cpu *rstatc; unsigned long flags; rstatc = cgroup_base_stat_cputime_account_begin(cgrp, &flags); rstatc->bstat.cputime.sum_exec_runtime += delta_exec; cgroup_base_stat_cputime_account_end(cgrp, rstatc, flags); } void __cgroup_account_cputime_field(struct cgroup *cgrp, enum cpu_usage_stat index, u64 delta_exec) { struct cgroup_rstat_cpu *rstatc; unsigned long flags; rstatc = cgroup_base_stat_cputime_account_begin(cgrp, &flags); switch (index) { case CPUTIME_NICE: rstatc->bstat.ntime += delta_exec; fallthrough; case CPUTIME_USER: rstatc->bstat.cputime.utime += delta_exec; break; case CPUTIME_SYSTEM: case CPUTIME_IRQ: case CPUTIME_SOFTIRQ: rstatc->bstat.cputime.stime += delta_exec; break; #ifdef CONFIG_SCHED_CORE case CPUTIME_FORCEIDLE: rstatc->bstat.forceidle_sum += delta_exec; break; #endif default: break; } cgroup_base_stat_cputime_account_end(cgrp, rstatc, flags); } /* * compute the cputime for the root cgroup by getting the per cpu data * at a global level, then categorizing the fields in a manner consistent * with how it is done by __cgroup_account_cputime_field for each bit of * cpu time attributed to a cgroup. */ static void root_cgroup_cputime(struct cgroup_base_stat *bstat) { struct task_cputime *cputime = &bstat->cputime; int i; memset(bstat, 0, sizeof(*bstat)); for_each_possible_cpu(i) { struct kernel_cpustat kcpustat; u64 *cpustat = kcpustat.cpustat; u64 user = 0; u64 sys = 0; kcpustat_cpu_fetch(&kcpustat, i); user += cpustat[CPUTIME_USER]; user += cpustat[CPUTIME_NICE]; cputime->utime += user; sys += cpustat[CPUTIME_SYSTEM]; sys += cpustat[CPUTIME_IRQ]; sys += cpustat[CPUTIME_SOFTIRQ]; cputime->stime += sys; cputime->sum_exec_runtime += user; cputime->sum_exec_runtime += sys; cputime->sum_exec_runtime += cpustat[CPUTIME_STEAL]; #ifdef CONFIG_SCHED_CORE bstat->forceidle_sum += cpustat[CPUTIME_FORCEIDLE]; #endif bstat->ntime += cpustat[CPUTIME_NICE]; } } static void cgroup_force_idle_show(struct seq_file *seq, struct cgroup_base_stat *bstat) { #ifdef CONFIG_SCHED_CORE u64 forceidle_time = bstat->forceidle_sum; do_div(forceidle_time, NSEC_PER_USEC); seq_printf(seq, "core_sched.force_idle_usec %llu\n", forceidle_time); #endif } void cgroup_base_stat_cputime_show(struct seq_file *seq) { struct cgroup *cgrp = seq_css(seq)->cgroup; u64 usage, utime, stime, ntime; if (cgroup_parent(cgrp)) { cgroup_rstat_flush_hold(cgrp); usage = cgrp->bstat.cputime.sum_exec_runtime; cputime_adjust(&cgrp->bstat.cputime, &cgrp->prev_cputime, &utime, &stime); ntime = cgrp->bstat.ntime; cgroup_rstat_flush_release(cgrp); } else { /* cgrp->bstat of root is not actually used, reuse it */ root_cgroup_cputime(&cgrp->bstat); usage = cgrp->bstat.cputime.sum_exec_runtime; utime = cgrp->bstat.cputime.utime; stime = cgrp->bstat.cputime.stime; ntime = cgrp->bstat.ntime; } do_div(usage, NSEC_PER_USEC); do_div(utime, NSEC_PER_USEC); do_div(stime, NSEC_PER_USEC); do_div(ntime, NSEC_PER_USEC); seq_printf(seq, "usage_usec %llu\n" "user_usec %llu\n" "system_usec %llu\n" "nice_usec %llu\n", usage, utime, stime, ntime); cgroup_force_idle_show(seq, &cgrp->bstat); } /* Add bpf kfuncs for cgroup_rstat_updated() and cgroup_rstat_flush() */ BTF_KFUNCS_START(bpf_rstat_kfunc_ids) BTF_ID_FLAGS(func, cgroup_rstat_updated) BTF_ID_FLAGS(func, cgroup_rstat_flush, KF_SLEEPABLE) BTF_KFUNCS_END(bpf_rstat_kfunc_ids) static const struct btf_kfunc_id_set bpf_rstat_kfunc_set = { .owner = THIS_MODULE, .set = &bpf_rstat_kfunc_ids, }; static int __init bpf_rstat_kfunc_init(void) { return register_btf_kfunc_id_set(BPF_PROG_TYPE_TRACING, &bpf_rstat_kfunc_set); } late_initcall(bpf_rstat_kfunc_init); |
| 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _LINUX_TIMEKEEPING_H #define _LINUX_TIMEKEEPING_H #include <linux/errno.h> #include <linux/clocksource_ids.h> #include <linux/ktime.h> /* Included from linux/ktime.h */ void timekeeping_init(void); extern int timekeeping_suspended; /* Architecture timer tick functions: */ extern void legacy_timer_tick(unsigned long ticks); /* * Get and set timeofday */ extern int do_settimeofday64(const struct timespec64 *ts); extern int do_sys_settimeofday64(const struct timespec64 *tv, const struct timezone *tz); /* * ktime_get() family - read the current time in a multitude of ways. * * The default time reference is CLOCK_MONOTONIC, starting at * boot time but not counting the time spent in suspend. * For other references, use the functions with "real", "clocktai", * "boottime" and "raw" suffixes. * * To get the time in a different format, use the ones with * "ns", "ts64" and "seconds" suffix. * * See Documentation/core-api/timekeeping.rst for more details. */ /* * timespec64 based interfaces */ extern void ktime_get_raw_ts64(struct timespec64 *ts); extern void ktime_get_ts64(struct timespec64 *ts); extern void ktime_get_real_ts64(struct timespec64 *tv); extern void ktime_get_coarse_ts64(struct timespec64 *ts); extern void ktime_get_coarse_real_ts64(struct timespec64 *ts); /* Multigrain timestamp interfaces */ extern void ktime_get_coarse_real_ts64_mg(struct timespec64 *ts); extern void ktime_get_real_ts64_mg(struct timespec64 *ts); extern unsigned long timekeeping_get_mg_floor_swaps(void); void getboottime64(struct timespec64 *ts); /* * time64_t base interfaces */ extern time64_t ktime_get_seconds(void); extern time64_t __ktime_get_real_seconds(void); extern time64_t ktime_get_real_seconds(void); /* * ktime_t based interfaces */ enum tk_offsets { TK_OFFS_REAL, TK_OFFS_BOOT, TK_OFFS_TAI, TK_OFFS_MAX, }; extern ktime_t ktime_get(void); extern ktime_t ktime_get_with_offset(enum tk_offsets offs); extern ktime_t ktime_get_coarse_with_offset(enum tk_offsets offs); extern ktime_t ktime_mono_to_any(ktime_t tmono, enum tk_offsets offs); extern ktime_t ktime_get_raw(void); extern u32 ktime_get_resolution_ns(void); /** * ktime_get_real - get the real (wall-) time in ktime_t format * * Returns: real (wall) time in ktime_t format */ static inline ktime_t ktime_get_real(void) { return ktime_get_with_offset(TK_OFFS_REAL); } static inline ktime_t ktime_get_coarse_real(void) { return ktime_get_coarse_with_offset(TK_OFFS_REAL); } /** * ktime_get_boottime - Get monotonic time since boot in ktime_t format * * This is similar to CLOCK_MONTONIC/ktime_get, but also includes the * time spent in suspend. * * Returns: monotonic time since boot in ktime_t format */ static inline ktime_t ktime_get_boottime(void) { return ktime_get_with_offset(TK_OFFS_BOOT); } static inline ktime_t ktime_get_coarse_boottime(void) { return ktime_get_coarse_with_offset(TK_OFFS_BOOT); } /** * ktime_get_clocktai - Get the TAI time of day in ktime_t format * * Returns: the TAI time of day in ktime_t format */ static inline ktime_t ktime_get_clocktai(void) { return ktime_get_with_offset(TK_OFFS_TAI); } static inline ktime_t ktime_get_coarse_clocktai(void) { return ktime_get_coarse_with_offset(TK_OFFS_TAI); } static inline ktime_t ktime_get_coarse(void) { struct timespec64 ts; ktime_get_coarse_ts64(&ts); return timespec64_to_ktime(ts); } static inline u64 ktime_get_coarse_ns(void) { return ktime_to_ns(ktime_get_coarse()); } static inline u64 ktime_get_coarse_real_ns(void) { return ktime_to_ns(ktime_get_coarse_real()); } static inline u64 ktime_get_coarse_boottime_ns(void) { return ktime_to_ns(ktime_get_coarse_boottime()); } static inline u64 ktime_get_coarse_clocktai_ns(void) { return ktime_to_ns(ktime_get_coarse_clocktai()); } /** * ktime_mono_to_real - Convert monotonic time to clock realtime * @mono: monotonic time to convert * * Returns: time converted to realtime clock */ static inline ktime_t ktime_mono_to_real(ktime_t mono) { return ktime_mono_to_any(mono, TK_OFFS_REAL); } /** * ktime_get_ns - Get the current time in nanoseconds * * Returns: current time converted to nanoseconds */ static inline u64 ktime_get_ns(void) { return ktime_to_ns(ktime_get()); } /** * ktime_get_real_ns - Get the current real/wall time in nanoseconds * * Returns: current real time converted to nanoseconds */ static inline u64 ktime_get_real_ns(void) { return ktime_to_ns(ktime_get_real()); } /** * ktime_get_boottime_ns - Get the monotonic time since boot in nanoseconds * * Returns: current boottime converted to nanoseconds */ static inline u64 ktime_get_boottime_ns(void) { return ktime_to_ns(ktime_get_boottime()); } /** * ktime_get_clocktai_ns - Get the current TAI time of day in nanoseconds * * Returns: current TAI time converted to nanoseconds */ static inline u64 ktime_get_clocktai_ns(void) { return ktime_to_ns(ktime_get_clocktai()); } /** * ktime_get_raw_ns - Get the raw monotonic time in nanoseconds * * Returns: current raw monotonic time converted to nanoseconds */ static inline u64 ktime_get_raw_ns(void) { return ktime_to_ns(ktime_get_raw()); } extern u64 ktime_get_mono_fast_ns(void); extern u64 ktime_get_raw_fast_ns(void); extern u64 ktime_get_boot_fast_ns(void); extern u64 ktime_get_tai_fast_ns(void); extern u64 ktime_get_real_fast_ns(void); /* * timespec64/time64_t interfaces utilizing the ktime based ones * for API completeness, these could be implemented more efficiently * if needed. */ static inline void ktime_get_boottime_ts64(struct timespec64 *ts) { *ts = ktime_to_timespec64(ktime_get_boottime()); } static inline void ktime_get_coarse_boottime_ts64(struct timespec64 *ts) { *ts = ktime_to_timespec64(ktime_get_coarse_boottime()); } static inline time64_t ktime_get_boottime_seconds(void) { return ktime_divns(ktime_get_coarse_boottime(), NSEC_PER_SEC); } static inline void ktime_get_clocktai_ts64(struct timespec64 *ts) { *ts = ktime_to_timespec64(ktime_get_clocktai()); } static inline void ktime_get_coarse_clocktai_ts64(struct timespec64 *ts) { *ts = ktime_to_timespec64(ktime_get_coarse_clocktai()); } static inline time64_t ktime_get_clocktai_seconds(void) { return ktime_divns(ktime_get_coarse_clocktai(), NSEC_PER_SEC); } /* * RTC specific */ extern bool timekeeping_rtc_skipsuspend(void); extern bool timekeeping_rtc_skipresume(void); extern void timekeeping_inject_sleeptime64(const struct timespec64 *delta); /** * struct ktime_timestamps - Simultaneous mono/boot/real timestamps * @mono: Monotonic timestamp * @boot: Boottime timestamp * @real: Realtime timestamp */ struct ktime_timestamps { u64 mono; u64 boot; u64 real; }; /** * struct system_time_snapshot - simultaneous raw/real time capture with * counter value * @cycles: Clocksource counter value to produce the system times * @real: Realtime system time * @boot: Boot time * @raw: Monotonic raw system time * @cs_id: Clocksource ID * @clock_was_set_seq: The sequence number of clock-was-set events * @cs_was_changed_seq: The sequence number of clocksource change events */ struct system_time_snapshot { u64 cycles; ktime_t real; ktime_t boot; ktime_t raw; enum clocksource_ids cs_id; unsigned int clock_was_set_seq; u8 cs_was_changed_seq; }; /** * struct system_device_crosststamp - system/device cross-timestamp * (synchronized capture) * @device: Device time * @sys_realtime: Realtime simultaneous with device time * @sys_monoraw: Monotonic raw simultaneous with device time */ struct system_device_crosststamp { ktime_t device; ktime_t sys_realtime; ktime_t sys_monoraw; }; /** * struct system_counterval_t - system counter value with the ID of the * corresponding clocksource * @cycles: System counter value * @cs_id: Clocksource ID corresponding to system counter value. Used by * timekeeping code to verify comparability of two cycle values. * The default ID, CSID_GENERIC, does not identify a specific * clocksource. * @use_nsecs: @cycles is in nanoseconds. */ struct system_counterval_t { u64 cycles; enum clocksource_ids cs_id; bool use_nsecs; }; extern bool ktime_real_to_base_clock(ktime_t treal, enum clocksource_ids base_id, u64 *cycles); extern bool timekeeping_clocksource_has_base(enum clocksource_ids id); /* * Get cross timestamp between system clock and device clock */ extern int get_device_system_crosststamp( int (*get_time_fn)(ktime_t *device_time, struct system_counterval_t *system_counterval, void *ctx), void *ctx, struct system_time_snapshot *history, struct system_device_crosststamp *xtstamp); /* * Simultaneously snapshot realtime and monotonic raw clocks */ extern void ktime_get_snapshot(struct system_time_snapshot *systime_snapshot); /* NMI safe mono/boot/realtime timestamps */ extern void ktime_get_fast_timestamps(struct ktime_timestamps *snap); /* * Persistent clock related interfaces */ extern int persistent_clock_is_local; extern void read_persistent_clock64(struct timespec64 *ts); void read_persistent_wall_and_boot_offset(struct timespec64 *wall_clock, struct timespec64 *boot_offset); #ifdef CONFIG_GENERIC_CMOS_UPDATE extern int update_persistent_clock64(struct timespec64 now); #endif #endif |
| 415 436 437 293 153 69 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _LINUX_VMSTAT_H #define _LINUX_VMSTAT_H #include <linux/types.h> #include <linux/percpu.h> #include <linux/mmzone.h> #include <linux/vm_event_item.h> #include <linux/atomic.h> #include <linux/static_key.h> #include <linux/mmdebug.h> extern int sysctl_stat_interval; #ifdef CONFIG_NUMA #define ENABLE_NUMA_STAT 1 #define DISABLE_NUMA_STAT 0 extern int sysctl_vm_numa_stat; DECLARE_STATIC_KEY_TRUE(vm_numa_stat_key); int sysctl_vm_numa_stat_handler(const struct ctl_table *table, int write, void *buffer, size_t *length, loff_t *ppos); #endif struct reclaim_stat { unsigned nr_dirty; unsigned nr_unqueued_dirty; unsigned nr_congested; unsigned nr_writeback; unsigned nr_immediate; unsigned nr_pageout; unsigned nr_activate[ANON_AND_FILE]; unsigned nr_ref_keep; unsigned nr_unmap_fail; unsigned nr_lazyfree_fail; unsigned nr_demoted; }; /* Stat data for system wide items */ enum vm_stat_item { NR_DIRTY_THRESHOLD, NR_DIRTY_BG_THRESHOLD, NR_MEMMAP_PAGES, /* page metadata allocated through buddy allocator */ NR_MEMMAP_BOOT_PAGES, /* page metadata allocated through boot allocator */ NR_VM_STAT_ITEMS, }; #ifdef CONFIG_VM_EVENT_COUNTERS /* * Light weight per cpu counter implementation. * * Counters should only be incremented and no critical kernel component * should rely on the counter values. * * Counters are handled completely inline. On many platforms the code * generated will simply be the increment of a global address. */ struct vm_event_state { unsigned long event[NR_VM_EVENT_ITEMS]; }; DECLARE_PER_CPU(struct vm_event_state, vm_event_states); /* * vm counters are allowed to be racy. Use raw_cpu_ops to avoid the * local_irq_disable overhead. */ static inline void __count_vm_event(enum vm_event_item item) { raw_cpu_inc(vm_event_states.event[item]); } static inline void count_vm_event(enum vm_event_item item) { this_cpu_inc(vm_event_states.event[item]); } static inline void __count_vm_events(enum vm_event_item item, long delta) { raw_cpu_add(vm_event_states.event[item], delta); } static inline void count_vm_events(enum vm_event_item item, long delta) { this_cpu_add(vm_event_states.event[item], delta); } extern void all_vm_events(unsigned long *); extern void vm_events_fold_cpu(int cpu); #else /* Disable counters */ static inline void count_vm_event(enum vm_event_item item) { } static inline void count_vm_events(enum vm_event_item item, long delta) { } static inline void __count_vm_event(enum vm_event_item item) { } static inline void __count_vm_events(enum vm_event_item item, long delta) { } static inline void all_vm_events(unsigned long *ret) { } static inline void vm_events_fold_cpu(int cpu) { } #endif /* CONFIG_VM_EVENT_COUNTERS */ #ifdef CONFIG_NUMA_BALANCING #define count_vm_numa_event(x) count_vm_event(x) #define count_vm_numa_events(x, y) count_vm_events(x, y) #else #define count_vm_numa_event(x) do {} while (0) #define count_vm_numa_events(x, y) do { (void)(y); } while (0) #endif /* CONFIG_NUMA_BALANCING */ #ifdef CONFIG_DEBUG_TLBFLUSH #define count_vm_tlb_event(x) count_vm_event(x) #define count_vm_tlb_events(x, y) count_vm_events(x, y) #else #define count_vm_tlb_event(x) do {} while (0) #define count_vm_tlb_events(x, y) do { (void)(y); } while (0) #endif #ifdef CONFIG_PER_VMA_LOCK_STATS #define count_vm_vma_lock_event(x) count_vm_event(x) #else #define count_vm_vma_lock_event(x) do {} while (0) #endif #define __count_zid_vm_events(item, zid, delta) \ __count_vm_events(item##_NORMAL - ZONE_NORMAL + zid, delta) /* * Zone and node-based page accounting with per cpu differentials. */ extern atomic_long_t vm_zone_stat[NR_VM_ZONE_STAT_ITEMS]; extern atomic_long_t vm_node_stat[NR_VM_NODE_STAT_ITEMS]; extern atomic_long_t vm_numa_event[NR_VM_NUMA_EVENT_ITEMS]; #ifdef CONFIG_NUMA static inline void zone_numa_event_add(long x, struct zone *zone, enum numa_stat_item item) { atomic_long_add(x, &zone->vm_numa_event[item]); atomic_long_add(x, &vm_numa_event[item]); } static inline unsigned long zone_numa_event_state(struct zone *zone, enum numa_stat_item item) { return atomic_long_read(&zone->vm_numa_event[item]); } static inline unsigned long global_numa_event_state(enum numa_stat_item item) { return atomic_long_read(&vm_numa_event[item]); } #endif /* CONFIG_NUMA */ static inline void zone_page_state_add(long x, struct zone *zone, enum zone_stat_item item) { atomic_long_add(x, &zone->vm_stat[item]); atomic_long_add(x, &vm_zone_stat[item]); } static inline void node_page_state_add(long x, struct pglist_data *pgdat, enum node_stat_item item) { atomic_long_add(x, &pgdat->vm_stat[item]); atomic_long_add(x, &vm_node_stat[item]); } static inline unsigned long global_zone_page_state(enum zone_stat_item item) { long x = atomic_long_read(&vm_zone_stat[item]); #ifdef CONFIG_SMP if (x < 0) x = 0; #endif return x; } static inline unsigned long global_node_page_state_pages(enum node_stat_item item) { long x = atomic_long_read(&vm_node_stat[item]); #ifdef CONFIG_SMP if (x < 0) x = 0; #endif return x; } static inline unsigned long global_node_page_state(enum node_stat_item item) { VM_WARN_ON_ONCE(vmstat_item_in_bytes(item)); return global_node_page_state_pages(item); } static inline unsigned long zone_page_state(struct zone *zone, enum zone_stat_item item) { long x = atomic_long_read(&zone->vm_stat[item]); #ifdef CONFIG_SMP if (x < 0) x = 0; #endif return x; } /* * More accurate version that also considers the currently pending * deltas. For that we need to loop over all cpus to find the current * deltas. There is no synchronization so the result cannot be * exactly accurate either. */ static inline unsigned long zone_page_state_snapshot(struct zone *zone, enum zone_stat_item item) { long x = atomic_long_read(&zone->vm_stat[item]); #ifdef CONFIG_SMP int cpu; for_each_online_cpu(cpu) x += per_cpu_ptr(zone->per_cpu_zonestats, cpu)->vm_stat_diff[item]; if (x < 0) x = 0; #endif return x; } #ifdef CONFIG_NUMA /* See __count_vm_event comment on why raw_cpu_inc is used. */ static inline void __count_numa_event(struct zone *zone, enum numa_stat_item item) { struct per_cpu_zonestat __percpu *pzstats = zone->per_cpu_zonestats; raw_cpu_inc(pzstats->vm_numa_event[item]); } static inline void __count_numa_events(struct zone *zone, enum numa_stat_item item, long delta) { struct per_cpu_zonestat __percpu *pzstats = zone->per_cpu_zonestats; raw_cpu_add(pzstats->vm_numa_event[item], delta); } extern unsigned long sum_zone_node_page_state(int node, enum zone_stat_item item); extern unsigned long sum_zone_numa_event_state(int node, enum numa_stat_item item); extern unsigned long node_page_state(struct pglist_data *pgdat, enum node_stat_item item); extern unsigned long node_page_state_pages(struct pglist_data *pgdat, enum node_stat_item item); extern void fold_vm_numa_events(void); #else #define sum_zone_node_page_state(node, item) global_zone_page_state(item) #define node_page_state(node, item) global_node_page_state(item) #define node_page_state_pages(node, item) global_node_page_state_pages(item) static inline void fold_vm_numa_events(void) { } #endif /* CONFIG_NUMA */ #ifdef CONFIG_SMP void __mod_zone_page_state(struct zone *, enum zone_stat_item item, long); void __inc_zone_page_state(struct page *, enum zone_stat_item); void __dec_zone_page_state(struct page *, enum zone_stat_item); void __mod_node_page_state(struct pglist_data *, enum node_stat_item item, long); void __inc_node_page_state(struct page *, enum node_stat_item); void __dec_node_page_state(struct page *, enum node_stat_item); void mod_zone_page_state(struct zone *, enum zone_stat_item, long); void inc_zone_page_state(struct page *, enum zone_stat_item); void dec_zone_page_state(struct page *, enum zone_stat_item); void mod_node_page_state(struct pglist_data *, enum node_stat_item, long); void inc_node_page_state(struct page *, enum node_stat_item); void dec_node_page_state(struct page *, enum node_stat_item); extern void inc_node_state(struct pglist_data *, enum node_stat_item); extern void __inc_zone_state(struct zone *, enum zone_stat_item); extern void __inc_node_state(struct pglist_data *, enum node_stat_item); extern void dec_zone_state(struct zone *, enum zone_stat_item); extern void __dec_zone_state(struct zone *, enum zone_stat_item); extern void __dec_node_state(struct pglist_data *, enum node_stat_item); void quiet_vmstat(void); void cpu_vm_stats_fold(int cpu); void refresh_zone_stat_thresholds(void); struct ctl_table; int vmstat_refresh(const struct ctl_table *, int write, void *buffer, size_t *lenp, loff_t *ppos); void drain_zonestat(struct zone *zone, struct per_cpu_zonestat *); int calculate_pressure_threshold(struct zone *zone); int calculate_normal_threshold(struct zone *zone); void set_pgdat_percpu_threshold(pg_data_t *pgdat, int (*calculate_pressure)(struct zone *)); #else /* CONFIG_SMP */ /* * We do not maintain differentials in a single processor configuration. * The functions directly modify the zone and global counters. */ static inline void __mod_zone_page_state(struct zone *zone, enum zone_stat_item item, long delta) { zone_page_state_add(delta, zone, item); } static inline void __mod_node_page_state(struct pglist_data *pgdat, enum node_stat_item item, int delta) { if (vmstat_item_in_bytes(item)) { /* * Only cgroups use subpage accounting right now; at * the global level, these items still change in * multiples of whole pages. Store them as pages * internally to keep the per-cpu counters compact. */ VM_WARN_ON_ONCE(delta & (PAGE_SIZE - 1)); delta >>= PAGE_SHIFT; } node_page_state_add(delta, pgdat, item); } static inline void __inc_zone_state(struct zone *zone, enum zone_stat_item item) { atomic_long_inc(&zone->vm_stat[item]); atomic_long_inc(&vm_zone_stat[item]); } static inline void __inc_node_state(struct pglist_data *pgdat, enum node_stat_item item) { atomic_long_inc(&pgdat->vm_stat[item]); atomic_long_inc(&vm_node_stat[item]); } static inline void __dec_zone_state(struct zone *zone, enum zone_stat_item item) { atomic_long_dec(&zone->vm_stat[item]); atomic_long_dec(&vm_zone_stat[item]); } static inline void __dec_node_state(struct pglist_data *pgdat, enum node_stat_item item) { atomic_long_dec(&pgdat->vm_stat[item]); atomic_long_dec(&vm_node_stat[item]); } static inline void __inc_zone_page_state(struct page *page, enum zone_stat_item item) { __inc_zone_state(page_zone(page), item); } static inline void __inc_node_page_state(struct page *page, enum node_stat_item item) { __inc_node_state(page_pgdat(page), item); } static inline void __dec_zone_page_state(struct page *page, enum zone_stat_item item) { __dec_zone_state(page_zone(page), item); } static inline void __dec_node_page_state(struct page *page, enum node_stat_item item) { __dec_node_state(page_pgdat(page), item); } /* * We only use atomic operations to update counters. So there is no need to * disable interrupts. */ #define inc_zone_page_state __inc_zone_page_state #define dec_zone_page_state __dec_zone_page_state #define mod_zone_page_state __mod_zone_page_state #define inc_node_page_state __inc_node_page_state #define dec_node_page_state __dec_node_page_state #define mod_node_page_state __mod_node_page_state #define inc_zone_state __inc_zone_state #define inc_node_state __inc_node_state #define dec_zone_state __dec_zone_state #define set_pgdat_percpu_threshold(pgdat, callback) { } static inline void refresh_zone_stat_thresholds(void) { } static inline void cpu_vm_stats_fold(int cpu) { } static inline void quiet_vmstat(void) { } static inline void drain_zonestat(struct zone *zone, struct per_cpu_zonestat *pzstats) { } #endif /* CONFIG_SMP */ static inline void __zone_stat_mod_folio(struct folio *folio, enum zone_stat_item item, long nr) { __mod_zone_page_state(folio_zone(folio), item, nr); } static inline void __zone_stat_add_folio(struct folio *folio, enum zone_stat_item item) { __mod_zone_page_state(folio_zone(folio), item, folio_nr_pages(folio)); } static inline void __zone_stat_sub_folio(struct folio *folio, enum zone_stat_item item) { __mod_zone_page_state(folio_zone(folio), item, -folio_nr_pages(folio)); } static inline void zone_stat_mod_folio(struct folio *folio, enum zone_stat_item item, long nr) { mod_zone_page_state(folio_zone(folio), item, nr); } static inline void zone_stat_add_folio(struct folio *folio, enum zone_stat_item item) { mod_zone_page_state(folio_zone(folio), item, folio_nr_pages(folio)); } static inline void zone_stat_sub_folio(struct folio *folio, enum zone_stat_item item) { mod_zone_page_state(folio_zone(folio), item, -folio_nr_pages(folio)); } static inline void __node_stat_mod_folio(struct folio *folio, enum node_stat_item item, long nr) { __mod_node_page_state(folio_pgdat(folio), item, nr); } static inline void __node_stat_add_folio(struct folio *folio, enum node_stat_item item) { __mod_node_page_state(folio_pgdat(folio), item, folio_nr_pages(folio)); } static inline void __node_stat_sub_folio(struct folio *folio, enum node_stat_item item) { __mod_node_page_state(folio_pgdat(folio), item, -folio_nr_pages(folio)); } static inline void node_stat_mod_folio(struct folio *folio, enum node_stat_item item, long nr) { mod_node_page_state(folio_pgdat(folio), item, nr); } static inline void node_stat_add_folio(struct folio *folio, enum node_stat_item item) { mod_node_page_state(folio_pgdat(folio), item, folio_nr_pages(folio)); } static inline void node_stat_sub_folio(struct folio *folio, enum node_stat_item item) { mod_node_page_state(folio_pgdat(folio), item, -folio_nr_pages(folio)); } extern const char * const vmstat_text[]; static inline const char *zone_stat_name(enum zone_stat_item item) { return vmstat_text[item]; } #ifdef CONFIG_NUMA static inline const char *numa_stat_name(enum numa_stat_item item) { return vmstat_text[NR_VM_ZONE_STAT_ITEMS + item]; } #endif /* CONFIG_NUMA */ static inline const char *node_stat_name(enum node_stat_item item) { return vmstat_text[NR_VM_ZONE_STAT_ITEMS + NR_VM_NUMA_EVENT_ITEMS + item]; } static inline const char *lru_list_name(enum lru_list lru) { return node_stat_name(NR_LRU_BASE + lru) + 3; // skip "nr_" } #if defined(CONFIG_VM_EVENT_COUNTERS) || defined(CONFIG_MEMCG) static inline const char *vm_event_name(enum vm_event_item item) { return vmstat_text[NR_VM_ZONE_STAT_ITEMS + NR_VM_NUMA_EVENT_ITEMS + NR_VM_NODE_STAT_ITEMS + NR_VM_STAT_ITEMS + item]; } #endif /* CONFIG_VM_EVENT_COUNTERS || CONFIG_MEMCG */ #ifdef CONFIG_MEMCG void __mod_lruvec_state(struct lruvec *lruvec, enum node_stat_item idx, int val); static inline void mod_lruvec_state(struct lruvec *lruvec, enum node_stat_item idx, int val) { unsigned long flags; local_irq_save(flags); __mod_lruvec_state(lruvec, idx, val); local_irq_restore(flags); } void __lruvec_stat_mod_folio(struct folio *folio, enum node_stat_item idx, int val); static inline void lruvec_stat_mod_folio(struct folio *folio, enum node_stat_item idx, int val) { unsigned long flags; local_irq_save(flags); __lruvec_stat_mod_folio(folio, idx, val); local_irq_restore(flags); } static inline void mod_lruvec_page_state(struct page *page, enum node_stat_item idx, int val) { lruvec_stat_mod_folio(page_folio(page), idx, val); } #else static inline void __mod_lruvec_state(struct lruvec *lruvec, enum node_stat_item idx, int val) { __mod_node_page_state(lruvec_pgdat(lruvec), idx, val); } static inline void mod_lruvec_state(struct lruvec *lruvec, enum node_stat_item idx, int val) { mod_node_page_state(lruvec_pgdat(lruvec), idx, val); } static inline void __lruvec_stat_mod_folio(struct folio *folio, enum node_stat_item idx, int val) { __mod_node_page_state(folio_pgdat(folio), idx, val); } static inline void lruvec_stat_mod_folio(struct folio *folio, enum node_stat_item idx, int val) { mod_node_page_state(folio_pgdat(folio), idx, val); } static inline void mod_lruvec_page_state(struct page *page, enum node_stat_item idx, int val) { mod_node_page_state(page_pgdat(page), idx, val); } #endif /* CONFIG_MEMCG */ static inline void __lruvec_stat_add_folio(struct folio *folio, enum node_stat_item idx) { __lruvec_stat_mod_folio(folio, idx, folio_nr_pages(folio)); } static inline void __lruvec_stat_sub_folio(struct folio *folio, enum node_stat_item idx) { __lruvec_stat_mod_folio(folio, idx, -folio_nr_pages(folio)); } static inline void lruvec_stat_add_folio(struct folio *folio, enum node_stat_item idx) { lruvec_stat_mod_folio(folio, idx, folio_nr_pages(folio)); } static inline void lruvec_stat_sub_folio(struct folio *folio, enum node_stat_item idx) { lruvec_stat_mod_folio(folio, idx, -folio_nr_pages(folio)); } void memmap_boot_pages_add(long delta); void memmap_pages_add(long delta); #endif /* _LINUX_VMSTAT_H */ |
| 8 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _LINUX_POLL_H #define _LINUX_POLL_H #include <linux/compiler.h> #include <linux/ktime.h> #include <linux/wait.h> #include <linux/string.h> #include <linux/fs.h> #include <linux/uaccess.h> #include <uapi/linux/poll.h> #include <uapi/linux/eventpoll.h> /* ~832 bytes of stack space used max in sys_select/sys_poll before allocating additional memory. */ #define MAX_STACK_ALLOC 832 #define FRONTEND_STACK_ALLOC 256 #define SELECT_STACK_ALLOC FRONTEND_STACK_ALLOC #define POLL_STACK_ALLOC FRONTEND_STACK_ALLOC #define WQUEUES_STACK_ALLOC (MAX_STACK_ALLOC - FRONTEND_STACK_ALLOC) #define N_INLINE_POLL_ENTRIES (WQUEUES_STACK_ALLOC / sizeof(struct poll_table_entry)) #define DEFAULT_POLLMASK (EPOLLIN | EPOLLOUT | EPOLLRDNORM | EPOLLWRNORM) struct poll_table_struct; /* * structures and helpers for f_op->poll implementations */ typedef void (*poll_queue_proc)(struct file *, wait_queue_head_t *, struct poll_table_struct *); /* * Do not touch the structure directly, use the access functions * poll_does_not_wait() and poll_requested_events() instead. */ typedef struct poll_table_struct { poll_queue_proc _qproc; __poll_t _key; } poll_table; static inline void poll_wait(struct file * filp, wait_queue_head_t * wait_address, poll_table *p) { if (p && p->_qproc && wait_address) p->_qproc(filp, wait_address, p); } /* * Return true if it is guaranteed that poll will not wait. This is the case * if the poll() of another file descriptor in the set got an event, so there * is no need for waiting. */ static inline bool poll_does_not_wait(const poll_table *p) { return p == NULL || p->_qproc == NULL; } /* * Return the set of events that the application wants to poll for. * This is useful for drivers that need to know whether a DMA transfer has * to be started implicitly on poll(). You typically only want to do that * if the application is actually polling for POLLIN and/or POLLOUT. */ static inline __poll_t poll_requested_events(const poll_table *p) { return p ? p->_key : ~(__poll_t)0; } static inline void init_poll_funcptr(poll_table *pt, poll_queue_proc qproc) { pt->_qproc = qproc; pt->_key = ~(__poll_t)0; /* all events enabled */ } static inline bool file_can_poll(struct file *file) { return file->f_op->poll; } static inline __poll_t vfs_poll(struct file *file, struct poll_table_struct *pt) { if (unlikely(!file->f_op->poll)) return DEFAULT_POLLMASK; return file->f_op->poll(file, pt); } struct poll_table_entry { struct file *filp; __poll_t key; wait_queue_entry_t wait; wait_queue_head_t *wait_address; }; /* * Structures and helpers for select/poll syscall */ struct poll_wqueues { poll_table pt; struct poll_table_page *table; struct task_struct *polling_task; int triggered; int error; int inline_index; struct poll_table_entry inline_entries[N_INLINE_POLL_ENTRIES]; }; extern void poll_initwait(struct poll_wqueues *pwq); extern void poll_freewait(struct poll_wqueues *pwq); extern u64 select_estimate_accuracy(struct timespec64 *tv); #define MAX_INT64_SECONDS (((s64)(~((u64)0)>>1)/HZ)-1) extern int core_sys_select(int n, fd_set __user *inp, fd_set __user *outp, fd_set __user *exp, struct timespec64 *end_time); extern int poll_select_set_timeout(struct timespec64 *to, time64_t sec, long nsec); #define __MAP(v, from, to) \ (from < to ? (v & from) * (to/from) : (v & from) / (from/to)) static inline __u16 mangle_poll(__poll_t val) { __u16 v = (__force __u16)val; #define M(X) __MAP(v, (__force __u16)EPOLL##X, POLL##X) return M(IN) | M(OUT) | M(PRI) | M(ERR) | M(NVAL) | M(RDNORM) | M(RDBAND) | M(WRNORM) | M(WRBAND) | M(HUP) | M(RDHUP) | M(MSG); #undef M } static inline __poll_t demangle_poll(u16 val) { #define M(X) (__force __poll_t)__MAP(val, POLL##X, (__force __u16)EPOLL##X) return M(IN) | M(OUT) | M(PRI) | M(ERR) | M(NVAL) | M(RDNORM) | M(RDBAND) | M(WRNORM) | M(WRBAND) | M(HUP) | M(RDHUP) | M(MSG); #undef M } #undef __MAP #endif /* _LINUX_POLL_H */ |
| 2 8 7 351 72 351 72 126 61 93 93 8 53 61 27 20 12 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _LINUX_HUGETLB_H #define _LINUX_HUGETLB_H #include <linux/mm.h> #include <linux/mm_types.h> #include <linux/mmdebug.h> #include <linux/fs.h> #include <linux/hugetlb_inline.h> #include <linux/cgroup.h> #include <linux/page_ref.h> #include <linux/list.h> #include <linux/kref.h> #include <linux/pgtable.h> #include <linux/gfp.h> #include <linux/userfaultfd_k.h> struct ctl_table; struct user_struct; struct mmu_gather; struct node; void free_huge_folio(struct folio *folio); #ifdef CONFIG_HUGETLB_PAGE #include <linux/pagemap.h> #include <linux/shm.h> #include <asm/tlbflush.h> /* * For HugeTLB page, there are more metadata to save in the struct page. But * the head struct page cannot meet our needs, so we have to abuse other tail * struct page to store the metadata. */ #define __NR_USED_SUBPAGE 3 struct hugepage_subpool { spinlock_t lock; long count; long max_hpages; /* Maximum huge pages or -1 if no maximum. */ long used_hpages; /* Used count against maximum, includes */ /* both allocated and reserved pages. */ struct hstate *hstate; long min_hpages; /* Minimum huge pages or -1 if no minimum. */ long rsv_hpages; /* Pages reserved against global pool to */ /* satisfy minimum size. */ }; struct resv_map { struct kref refs; spinlock_t lock; struct list_head regions; long adds_in_progress; struct list_head region_cache; long region_cache_count; struct rw_semaphore rw_sema; #ifdef CONFIG_CGROUP_HUGETLB /* * On private mappings, the counter to uncharge reservations is stored * here. If these fields are 0, then either the mapping is shared, or * cgroup accounting is disabled for this resv_map. */ struct page_counter *reservation_counter; unsigned long pages_per_hpage; struct cgroup_subsys_state *css; #endif }; /* * Region tracking -- allows tracking of reservations and instantiated pages * across the pages in a mapping. * * The region data structures are embedded into a resv_map and protected * by a resv_map's lock. The set of regions within the resv_map represent * reservations for huge pages, or huge pages that have already been * instantiated within the map. The from and to elements are huge page * indices into the associated mapping. from indicates the starting index * of the region. to represents the first index past the end of the region. * * For example, a file region structure with from == 0 and to == 4 represents * four huge pages in a mapping. It is important to note that the to element * represents the first element past the end of the region. This is used in * arithmetic as 4(to) - 0(from) = 4 huge pages in the region. * * Interval notation of the form [from, to) will be used to indicate that * the endpoint from is inclusive and to is exclusive. */ struct file_region { struct list_head link; long from; long to; #ifdef CONFIG_CGROUP_HUGETLB /* * On shared mappings, each reserved region appears as a struct * file_region in resv_map. These fields hold the info needed to * uncharge each reservation. */ struct page_counter *reservation_counter; struct cgroup_subsys_state *css; #endif }; struct hugetlb_vma_lock { struct kref refs; struct rw_semaphore rw_sema; struct vm_area_struct *vma; }; extern struct resv_map *resv_map_alloc(void); void resv_map_release(struct kref *ref); extern spinlock_t hugetlb_lock; extern int hugetlb_max_hstate __read_mostly; #define for_each_hstate(h) \ for ((h) = hstates; (h) < &hstates[hugetlb_max_hstate]; (h)++) struct hugepage_subpool *hugepage_new_subpool(struct hstate *h, long max_hpages, long min_hpages); void hugepage_put_subpool(struct hugepage_subpool *spool); void hugetlb_dup_vma_private(struct vm_area_struct *vma); void clear_vma_resv_huge_pages(struct vm_area_struct *vma); int move_hugetlb_page_tables(struct vm_area_struct *vma, struct vm_area_struct *new_vma, unsigned long old_addr, unsigned long new_addr, unsigned long len); int copy_hugetlb_page_range(struct mm_struct *, struct mm_struct *, struct vm_area_struct *, struct vm_area_struct *); void unmap_hugepage_range(struct vm_area_struct *, unsigned long, unsigned long, struct page *, zap_flags_t); void __unmap_hugepage_range(struct mmu_gather *tlb, struct vm_area_struct *vma, unsigned long start, unsigned long end, struct page *ref_page, zap_flags_t zap_flags); void hugetlb_report_meminfo(struct seq_file *); int hugetlb_report_node_meminfo(char *buf, int len, int nid); void hugetlb_show_meminfo_node(int nid); unsigned long hugetlb_total_pages(void); vm_fault_t hugetlb_fault(struct mm_struct *mm, struct vm_area_struct *vma, unsigned long address, unsigned int flags); #ifdef CONFIG_USERFAULTFD int hugetlb_mfill_atomic_pte(pte_t *dst_pte, struct vm_area_struct *dst_vma, unsigned long dst_addr, unsigned long src_addr, uffd_flags_t flags, struct folio **foliop); #endif /* CONFIG_USERFAULTFD */ bool hugetlb_reserve_pages(struct inode *inode, long from, long to, struct vm_area_struct *vma, vm_flags_t vm_flags); long hugetlb_unreserve_pages(struct inode *inode, long start, long end, long freed); bool isolate_hugetlb(struct folio *folio, struct list_head *list); int get_hwpoison_hugetlb_folio(struct folio *folio, bool *hugetlb, bool unpoison); int get_huge_page_for_hwpoison(unsigned long pfn, int flags, bool *migratable_cleared); void folio_putback_active_hugetlb(struct folio *folio); void move_hugetlb_state(struct folio *old_folio, struct folio *new_folio, int reason); void hugetlb_fix_reserve_counts(struct inode *inode); extern struct mutex *hugetlb_fault_mutex_table; u32 hugetlb_fault_mutex_hash(struct address_space *mapping, pgoff_t idx); pte_t *huge_pmd_share(struct mm_struct *mm, struct vm_area_struct *vma, unsigned long addr, pud_t *pud); bool hugetlbfs_pagecache_present(struct hstate *h, struct vm_area_struct *vma, unsigned long address); struct address_space *hugetlb_folio_mapping_lock_write(struct folio *folio); extern int sysctl_hugetlb_shm_group; extern struct list_head huge_boot_pages[MAX_NUMNODES]; /* arch callbacks */ #ifndef CONFIG_HIGHPTE /* * pte_offset_huge() and pte_alloc_huge() are helpers for those architectures * which may go down to the lowest PTE level in their huge_pte_offset() and * huge_pte_alloc(): to avoid reliance on pte_offset_map() without pte_unmap(). */ static inline pte_t *pte_offset_huge(pmd_t *pmd, unsigned long address) { return pte_offset_kernel(pmd, address); } static inline pte_t *pte_alloc_huge(struct mm_struct *mm, pmd_t *pmd, unsigned long address) { return pte_alloc(mm, pmd) ? NULL : pte_offset_huge(pmd, address); } #endif pte_t *huge_pte_alloc(struct mm_struct *mm, struct vm_area_struct *vma, unsigned long addr, unsigned long sz); /* * huge_pte_offset(): Walk the hugetlb pgtable until the last level PTE. * Returns the pte_t* if found, or NULL if the address is not mapped. * * IMPORTANT: we should normally not directly call this function, instead * this is only a common interface to implement arch-specific * walker. Please use hugetlb_walk() instead, because that will attempt to * verify the locking for you. * * Since this function will walk all the pgtable pages (including not only * high-level pgtable page, but also PUD entry that can be unshared * concurrently for VM_SHARED), the caller of this function should be * responsible of its thread safety. One can follow this rule: * * (1) For private mappings: pmd unsharing is not possible, so holding the * mmap_lock for either read or write is sufficient. Most callers * already hold the mmap_lock, so normally, no special action is * required. * * (2) For shared mappings: pmd unsharing is possible (so the PUD-ranged * pgtable page can go away from under us! It can be done by a pmd * unshare with a follow up munmap() on the other process), then we * need either: * * (2.1) hugetlb vma lock read or write held, to make sure pmd unshare * won't happen upon the range (it also makes sure the pte_t we * read is the right and stable one), or, * * (2.2) hugetlb mapping i_mmap_rwsem lock held read or write, to make * sure even if unshare happened the racy unmap() will wait until * i_mmap_rwsem is released. * * Option (2.1) is the safest, which guarantees pte stability from pmd * sharing pov, until the vma lock released. Option (2.2) doesn't protect * a concurrent pmd unshare, but it makes sure the pgtable page is safe to * access. */ pte_t *huge_pte_offset(struct mm_struct *mm, unsigned long addr, unsigned long sz); unsigned long hugetlb_mask_last_page(struct hstate *h); int huge_pmd_unshare(struct mm_struct *mm, struct vm_area_struct *vma, unsigned long addr, pte_t *ptep); void adjust_range_if_pmd_sharing_possible(struct vm_area_struct *vma, unsigned long *start, unsigned long *end); extern void __hugetlb_zap_begin(struct vm_area_struct *vma, unsigned long *begin, unsigned long *end); extern void __hugetlb_zap_end(struct vm_area_struct *vma, struct zap_details *details); static inline void hugetlb_zap_begin(struct vm_area_struct *vma, unsigned long *start, unsigned long *end) { if (is_vm_hugetlb_page(vma)) __hugetlb_zap_begin(vma, start, end); } static inline void hugetlb_zap_end(struct vm_area_struct *vma, struct zap_details *details) { if (is_vm_hugetlb_page(vma)) __hugetlb_zap_end(vma, details); } void hugetlb_vma_lock_read(struct vm_area_struct *vma); void hugetlb_vma_unlock_read(struct vm_area_struct *vma); void hugetlb_vma_lock_write(struct vm_area_struct *vma); void hugetlb_vma_unlock_write(struct vm_area_struct *vma); int hugetlb_vma_trylock_write(struct vm_area_struct *vma); void hugetlb_vma_assert_locked(struct vm_area_struct *vma); void hugetlb_vma_lock_release(struct kref *kref); long hugetlb_change_protection(struct vm_area_struct *vma, unsigned long address, unsigned long end, pgprot_t newprot, unsigned long cp_flags); bool is_hugetlb_entry_migration(pte_t pte); bool is_hugetlb_entry_hwpoisoned(pte_t pte); void hugetlb_unshare_all_pmds(struct vm_area_struct *vma); #else /* !CONFIG_HUGETLB_PAGE */ static inline void hugetlb_dup_vma_private(struct vm_area_struct *vma) { } static inline void clear_vma_resv_huge_pages(struct vm_area_struct *vma) { } static inline unsigned long hugetlb_total_pages(void) { return 0; } static inline struct address_space *hugetlb_folio_mapping_lock_write( struct folio *folio) { return NULL; } static inline int huge_pmd_unshare(struct mm_struct *mm, struct vm_area_struct *vma, unsigned long addr, pte_t *ptep) { return 0; } static inline void adjust_range_if_pmd_sharing_possible( struct vm_area_struct *vma, unsigned long *start, unsigned long *end) { } static inline void hugetlb_zap_begin( struct vm_area_struct *vma, unsigned long *start, unsigned long *end) { } static inline void hugetlb_zap_end( struct vm_area_struct *vma, struct zap_details *details) { } static inline int copy_hugetlb_page_range(struct mm_struct *dst, struct mm_struct *src, struct vm_area_struct *dst_vma, struct vm_area_struct *src_vma) { BUG(); return 0; } static inline int move_hugetlb_page_tables(struct vm_area_struct *vma, struct vm_area_struct *new_vma, unsigned long old_addr, unsigned long new_addr, unsigned long len) { BUG(); return 0; } static inline void hugetlb_report_meminfo(struct seq_file *m) { } static inline int hugetlb_report_node_meminfo(char *buf, int len, int nid) { return 0; } static inline void hugetlb_show_meminfo_node(int nid) { } static inline int prepare_hugepage_range(struct file *file, unsigned long addr, unsigned long len) { return -EINVAL; } static inline void hugetlb_vma_lock_read(struct vm_area_struct *vma) { } static inline void hugetlb_vma_unlock_read(struct vm_area_struct *vma) { } static inline void hugetlb_vma_lock_write(struct vm_area_struct *vma) { } static inline void hugetlb_vma_unlock_write(struct vm_area_struct *vma) { } static inline int hugetlb_vma_trylock_write(struct vm_area_struct *vma) { return 1; } static inline void hugetlb_vma_assert_locked(struct vm_area_struct *vma) { } static inline int is_hugepage_only_range(struct mm_struct *mm, unsigned long addr, unsigned long len) { return 0; } static inline void hugetlb_free_pgd_range(struct mmu_gather *tlb, unsigned long addr, unsigned long end, unsigned long floor, unsigned long ceiling) { BUG(); } #ifdef CONFIG_USERFAULTFD static inline int hugetlb_mfill_atomic_pte(pte_t *dst_pte, struct vm_area_struct *dst_vma, unsigned long dst_addr, unsigned long src_addr, uffd_flags_t flags, struct folio **foliop) { BUG(); return 0; } #endif /* CONFIG_USERFAULTFD */ static inline pte_t *huge_pte_offset(struct mm_struct *mm, unsigned long addr, unsigned long sz) { return NULL; } static inline bool isolate_hugetlb(struct folio *folio, struct list_head *list) { return false; } static inline int get_hwpoison_hugetlb_folio(struct folio *folio, bool *hugetlb, bool unpoison) { return 0; } static inline int get_huge_page_for_hwpoison(unsigned long pfn, int flags, bool *migratable_cleared) { return 0; } static inline void folio_putback_active_hugetlb(struct folio *folio) { } static inline void move_hugetlb_state(struct folio *old_folio, struct folio *new_folio, int reason) { } static inline long hugetlb_change_protection( struct vm_area_struct *vma, unsigned long address, unsigned long end, pgprot_t newprot, unsigned long cp_flags) { return 0; } static inline void __unmap_hugepage_range(struct mmu_gather *tlb, struct vm_area_struct *vma, unsigned long start, unsigned long end, struct page *ref_page, zap_flags_t zap_flags) { BUG(); } static inline vm_fault_t hugetlb_fault(struct mm_struct *mm, struct vm_area_struct *vma, unsigned long address, unsigned int flags) { BUG(); return 0; } static inline void hugetlb_unshare_all_pmds(struct vm_area_struct *vma) { } #endif /* !CONFIG_HUGETLB_PAGE */ #ifndef pgd_write static inline int pgd_write(pgd_t pgd) { BUG(); return 0; } #endif #define HUGETLB_ANON_FILE "anon_hugepage" enum { /* * The file will be used as an shm file so shmfs accounting rules * apply */ HUGETLB_SHMFS_INODE = 1, /* * The file is being created on the internal vfs mount and shmfs * accounting rules do not apply */ HUGETLB_ANONHUGE_INODE = 2, }; #ifdef CONFIG_HUGETLBFS struct hugetlbfs_sb_info { long max_inodes; /* inodes allowed */ long free_inodes; /* inodes free */ spinlock_t stat_lock; struct hstate *hstate; struct hugepage_subpool *spool; kuid_t uid; kgid_t gid; umode_t mode; }; static inline struct hugetlbfs_sb_info *HUGETLBFS_SB(struct super_block *sb) { return sb->s_fs_info; } struct hugetlbfs_inode_info { struct inode vfs_inode; unsigned int seals; }; static inline struct hugetlbfs_inode_info *HUGETLBFS_I(struct inode *inode) { return container_of(inode, struct hugetlbfs_inode_info, vfs_inode); } extern const struct vm_operations_struct hugetlb_vm_ops; struct file *hugetlb_file_setup(const char *name, size_t size, vm_flags_t acct, int creat_flags, int page_size_log); static inline bool is_file_hugepages(const struct file *file) { return file->f_op->fop_flags & FOP_HUGE_PAGES; } static inline struct hstate *hstate_inode(struct inode *i) { return HUGETLBFS_SB(i->i_sb)->hstate; } #else /* !CONFIG_HUGETLBFS */ #define is_file_hugepages(file) false static inline struct file * hugetlb_file_setup(const char *name, size_t size, vm_flags_t acctflag, int creat_flags, int page_size_log) { return ERR_PTR(-ENOSYS); } static inline struct hstate *hstate_inode(struct inode *i) { return NULL; } #endif /* !CONFIG_HUGETLBFS */ unsigned long hugetlb_get_unmapped_area(struct file *file, unsigned long addr, unsigned long len, unsigned long pgoff, unsigned long flags); /* * huegtlb page specific state flags. These flags are located in page.private * of the hugetlb head page. Functions created via the below macros should be * used to manipulate these flags. * * HPG_restore_reserve - Set when a hugetlb page consumes a reservation at * allocation time. Cleared when page is fully instantiated. Free * routine checks flag to restore a reservation on error paths. * Synchronization: Examined or modified by code that knows it has * the only reference to page. i.e. After allocation but before use * or when the page is being freed. * HPG_migratable - Set after a newly allocated page is added to the page * cache and/or page tables. Indicates the page is a candidate for * migration. * Synchronization: Initially set after new page allocation with no * locking. When examined and modified during migration processing * (isolate, migrate, putback) the hugetlb_lock is held. * HPG_temporary - Set on a page that is temporarily allocated from the buddy * allocator. Typically used for migration target pages when no pages * are available in the pool. The hugetlb free page path will * immediately free pages with this flag set to the buddy allocator. * Synchronization: Can be set after huge page allocation from buddy when * code knows it has only reference. All other examinations and * modifications require hugetlb_lock. * HPG_freed - Set when page is on the free lists. * Synchronization: hugetlb_lock held for examination and modification. * HPG_vmemmap_optimized - Set when the vmemmap pages of the page are freed. * HPG_raw_hwp_unreliable - Set when the hugetlb page has a hwpoison sub-page * that is not tracked by raw_hwp_page list. */ enum hugetlb_page_flags { HPG_restore_reserve = 0, HPG_migratable, HPG_temporary, HPG_freed, HPG_vmemmap_optimized, HPG_raw_hwp_unreliable, __NR_HPAGEFLAGS, }; /* * Macros to create test, set and clear function definitions for * hugetlb specific page flags. */ #ifdef CONFIG_HUGETLB_PAGE #define TESTHPAGEFLAG(uname, flname) \ static __always_inline \ bool folio_test_hugetlb_##flname(struct folio *folio) \ { void *private = &folio->private; \ return test_bit(HPG_##flname, private); \ } #define SETHPAGEFLAG(uname, flname) \ static __always_inline \ void folio_set_hugetlb_##flname(struct folio *folio) \ { void *private = &folio->private; \ set_bit(HPG_##flname, private); \ } #define CLEARHPAGEFLAG(uname, flname) \ static __always_inline \ void folio_clear_hugetlb_##flname(struct folio *folio) \ { void *private = &folio->private; \ clear_bit(HPG_##flname, private); \ } #else #define TESTHPAGEFLAG(uname, flname) \ static inline bool \ folio_test_hugetlb_##flname(struct folio *folio) \ { return 0; } #define SETHPAGEFLAG(uname, flname) \ static inline void \ folio_set_hugetlb_##flname(struct folio *folio) \ { } #define CLEARHPAGEFLAG(uname, flname) \ static inline void \ folio_clear_hugetlb_##flname(struct folio *folio) \ { } #endif #define HPAGEFLAG(uname, flname) \ TESTHPAGEFLAG(uname, flname) \ SETHPAGEFLAG(uname, flname) \ CLEARHPAGEFLAG(uname, flname) \ /* * Create functions associated with hugetlb page flags */ HPAGEFLAG(RestoreReserve, restore_reserve) HPAGEFLAG(Migratable, migratable) HPAGEFLAG(Temporary, temporary) HPAGEFLAG(Freed, freed) HPAGEFLAG(VmemmapOptimized, vmemmap_optimized) HPAGEFLAG(RawHwpUnreliable, raw_hwp_unreliable) #ifdef CONFIG_HUGETLB_PAGE #define HSTATE_NAME_LEN 32 /* Defines one hugetlb page size */ struct hstate { struct mutex resize_lock; struct lock_class_key resize_key; int next_nid_to_alloc; int next_nid_to_free; unsigned int order; unsigned int demote_order; unsigned long mask; unsigned long max_huge_pages; unsigned long nr_huge_pages; unsigned long free_huge_pages; unsigned long resv_huge_pages; unsigned long surplus_huge_pages; unsigned long nr_overcommit_huge_pages; struct list_head hugepage_activelist; struct list_head hugepage_freelists[MAX_NUMNODES]; unsigned int max_huge_pages_node[MAX_NUMNODES]; unsigned int nr_huge_pages_node[MAX_NUMNODES]; unsigned int free_huge_pages_node[MAX_NUMNODES]; unsigned int surplus_huge_pages_node[MAX_NUMNODES]; char name[HSTATE_NAME_LEN]; }; struct huge_bootmem_page { struct list_head list; struct hstate *hstate; }; int isolate_or_dissolve_huge_page(struct page *page, struct list_head *list); struct folio *alloc_hugetlb_folio(struct vm_area_struct *vma, unsigned long addr, int avoid_reserve); struct folio *alloc_hugetlb_folio_nodemask(struct hstate *h, int preferred_nid, nodemask_t *nmask, gfp_t gfp_mask, bool allow_alloc_fallback); struct folio *alloc_hugetlb_folio_reserve(struct hstate *h, int preferred_nid, nodemask_t *nmask, gfp_t gfp_mask); int hugetlb_add_to_page_cache(struct folio *folio, struct address_space *mapping, pgoff_t idx); void restore_reserve_on_error(struct hstate *h, struct vm_area_struct *vma, unsigned long address, struct folio *folio); /* arch callback */ int __init __alloc_bootmem_huge_page(struct hstate *h, int nid); int __init alloc_bootmem_huge_page(struct hstate *h, int nid); bool __init hugetlb_node_alloc_supported(void); void __init hugetlb_add_hstate(unsigned order); bool __init arch_hugetlb_valid_size(unsigned long size); struct hstate *size_to_hstate(unsigned long size); #ifndef HUGE_MAX_HSTATE #define HUGE_MAX_HSTATE 1 #endif extern struct hstate hstates[HUGE_MAX_HSTATE]; extern unsigned int default_hstate_idx; #define default_hstate (hstates[default_hstate_idx]) static inline struct hugepage_subpool *hugetlb_folio_subpool(struct folio *folio) { return folio->_hugetlb_subpool; } static inline void hugetlb_set_folio_subpool(struct folio *folio, struct hugepage_subpool *subpool) { folio->_hugetlb_subpool = subpool; } static inline struct hstate *hstate_file(struct file *f) { return hstate_inode(file_inode(f)); } static inline struct hstate *hstate_sizelog(int page_size_log) { if (!page_size_log) return &default_hstate; if (page_size_log < BITS_PER_LONG) return size_to_hstate(1UL << page_size_log); return NULL; } static inline struct hstate *hstate_vma(struct vm_area_struct *vma) { return hstate_file(vma->vm_file); } static inline unsigned long huge_page_size(const struct hstate *h) { return (unsigned long)PAGE_SIZE << h->order; } extern unsigned long vma_kernel_pagesize(struct vm_area_struct *vma); extern unsigned long vma_mmu_pagesize(struct vm_area_struct *vma); static inline unsigned long huge_page_mask(struct hstate *h) { return h->mask; } static inline unsigned int huge_page_order(struct hstate *h) { return h->order; } static inline unsigned huge_page_shift(struct hstate *h) { return h->order + PAGE_SHIFT; } static inline bool hstate_is_gigantic(struct hstate *h) { return huge_page_order(h) > MAX_PAGE_ORDER; } static inline unsigned int pages_per_huge_page(const struct hstate *h) { return 1 << h->order; } static inline unsigned int blocks_per_huge_page(struct hstate *h) { return huge_page_size(h) / 512; } static inline struct folio *filemap_lock_hugetlb_folio(struct hstate *h, struct address_space *mapping, pgoff_t idx) { return filemap_lock_folio(mapping, idx << huge_page_order(h)); } #include <asm/hugetlb.h> #ifndef is_hugepage_only_range static inline int is_hugepage_only_range(struct mm_struct *mm, unsigned long addr, unsigned long len) { return 0; } #define is_hugepage_only_range is_hugepage_only_range #endif #ifndef arch_clear_hugetlb_flags static inline void arch_clear_hugetlb_flags(struct folio *folio) { } #define arch_clear_hugetlb_flags arch_clear_hugetlb_flags #endif #ifndef arch_make_huge_pte static inline pte_t arch_make_huge_pte(pte_t entry, unsigned int shift, vm_flags_t flags) { return pte_mkhuge(entry); } #endif static inline struct hstate *folio_hstate(struct folio *folio) { VM_BUG_ON_FOLIO(!folio_test_hugetlb(folio), folio); return size_to_hstate(folio_size(folio)); } static inline unsigned hstate_index_to_shift(unsigned index) { return hstates[index].order + PAGE_SHIFT; } static inline int hstate_index(struct hstate *h) { return h - hstates; } int dissolve_free_hugetlb_folio(struct folio *folio); int dissolve_free_hugetlb_folios(unsigned long start_pfn, unsigned long end_pfn); #ifdef CONFIG_MEMORY_FAILURE extern void folio_clear_hugetlb_hwpoison(struct folio *folio); #else static inline void folio_clear_hugetlb_hwpoison(struct folio *folio) { } #endif #ifdef CONFIG_ARCH_ENABLE_HUGEPAGE_MIGRATION #ifndef arch_hugetlb_migration_supported static inline bool arch_hugetlb_migration_supported(struct hstate *h) { if ((huge_page_shift(h) == PMD_SHIFT) || (huge_page_shift(h) == PUD_SHIFT) || (huge_page_shift(h) == PGDIR_SHIFT)) return true; else return false; } #endif #else static inline bool arch_hugetlb_migration_supported(struct hstate *h) { return false; } #endif static inline bool hugepage_migration_supported(struct hstate *h) { return arch_hugetlb_migration_supported(h); } /* * Movability check is different as compared to migration check. * It determines whether or not a huge page should be placed on * movable zone or not. Movability of any huge page should be * required only if huge page size is supported for migration. * There won't be any reason for the huge page to be movable if * it is not migratable to start with. Also the size of the huge * page should be large enough to be placed under a movable zone * and still feasible enough to be migratable. Just the presence * in movable zone does not make the migration feasible. * * So even though large huge page sizes like the gigantic ones * are migratable they should not be movable because its not * feasible to migrate them from movable zone. */ static inline bool hugepage_movable_supported(struct hstate *h) { if (!hugepage_migration_supported(h)) return false; if (hstate_is_gigantic(h)) return false; return true; } /* Movability of hugepages depends on migration support. */ static inline gfp_t htlb_alloc_mask(struct hstate *h) { gfp_t gfp = __GFP_COMP | __GFP_NOWARN; gfp |= hugepage_movable_supported(h) ? GFP_HIGHUSER_MOVABLE : GFP_HIGHUSER; return gfp; } static inline gfp_t htlb_modify_alloc_mask(struct hstate *h, gfp_t gfp_mask) { gfp_t modified_mask = htlb_alloc_mask(h); /* Some callers might want to enforce node */ modified_mask |= (gfp_mask & __GFP_THISNODE); modified_mask |= (gfp_mask & __GFP_NOWARN); return modified_mask; } static inline bool htlb_allow_alloc_fallback(int reason) { bool allowed_fallback = false; /* * Note: the memory offline, memory failure and migration syscalls will * be allowed to fallback to other nodes due to lack of a better chioce, * that might break the per-node hugetlb pool. While other cases will * set the __GFP_THISNODE to avoid breaking the per-node hugetlb pool. */ switch (reason) { case MR_MEMORY_HOTPLUG: case MR_MEMORY_FAILURE: case MR_SYSCALL: case MR_MEMPOLICY_MBIND: allowed_fallback = true; break; default: break; } return allowed_fallback; } static inline spinlock_t *huge_pte_lockptr(struct hstate *h, struct mm_struct *mm, pte_t *pte) { const unsigned long size = huge_page_size(h); VM_WARN_ON(size == PAGE_SIZE); /* * hugetlb must use the exact same PT locks as core-mm page table * walkers would. When modifying a PTE table, hugetlb must take the * PTE PT lock, when modifying a PMD table, hugetlb must take the PMD * PT lock etc. * * The expectation is that any hugetlb folio smaller than a PMD is * always mapped into a single PTE table and that any hugetlb folio * smaller than a PUD (but at least as big as a PMD) is always mapped * into a single PMD table. * * If that does not hold for an architecture, then that architecture * must disable split PT locks such that all *_lockptr() functions * will give us the same result: the per-MM PT lock. * * Note that with e.g., CONFIG_PGTABLE_LEVELS=2 where * PGDIR_SIZE==P4D_SIZE==PUD_SIZE==PMD_SIZE, we'd use pud_lockptr() * and core-mm would use pmd_lockptr(). However, in such configurations * split PMD locks are disabled -- they don't make sense on a single * PGDIR page table -- and the end result is the same. */ if (size >= PUD_SIZE) return pud_lockptr(mm, (pud_t *) pte); else if (size >= PMD_SIZE || IS_ENABLED(CONFIG_HIGHPTE)) return pmd_lockptr(mm, (pmd_t *) pte); /* pte_alloc_huge() only applies with !CONFIG_HIGHPTE */ return ptep_lockptr(mm, pte); } #ifndef hugepages_supported /* * Some platform decide whether they support huge pages at boot * time. Some of them, such as powerpc, set HPAGE_SHIFT to 0 * when there is no such support */ #define hugepages_supported() (HPAGE_SHIFT != 0) #endif void hugetlb_report_usage(struct seq_file *m, struct mm_struct *mm); static inline void hugetlb_count_init(struct mm_struct *mm) { atomic_long_set(&mm->hugetlb_usage, 0); } static inline void hugetlb_count_add(long l, struct mm_struct *mm) { atomic_long_add(l, &mm->hugetlb_usage); } static inline void hugetlb_count_sub(long l, struct mm_struct *mm) { atomic_long_sub(l, &mm->hugetlb_usage); } #ifndef huge_ptep_modify_prot_start #define huge_ptep_modify_prot_start huge_ptep_modify_prot_start static inline pte_t huge_ptep_modify_prot_start(struct vm_area_struct *vma, unsigned long addr, pte_t *ptep) { return huge_ptep_get_and_clear(vma->vm_mm, addr, ptep); } #endif #ifndef huge_ptep_modify_prot_commit #define huge_ptep_modify_prot_commit huge_ptep_modify_prot_commit static inline void huge_ptep_modify_prot_commit(struct vm_area_struct *vma, unsigned long addr, pte_t *ptep, pte_t old_pte, pte_t pte) { unsigned long psize = huge_page_size(hstate_vma(vma)); set_huge_pte_at(vma->vm_mm, addr, ptep, pte, psize); } #endif #ifdef CONFIG_NUMA void hugetlb_register_node(struct node *node); void hugetlb_unregister_node(struct node *node); #endif /* * Check if a given raw @page in a hugepage is HWPOISON. */ bool is_raw_hwpoison_page_in_hugepage(struct page *page); static inline unsigned long huge_page_mask_align(struct file *file) { return PAGE_MASK & ~huge_page_mask(hstate_file(file)); } #else /* CONFIG_HUGETLB_PAGE */ struct hstate {}; static inline unsigned long huge_page_mask_align(struct file *file) { return 0; } static inline struct hugepage_subpool *hugetlb_folio_subpool(struct folio *folio) { return NULL; } static inline struct folio *filemap_lock_hugetlb_folio(struct hstate *h, struct address_space *mapping, pgoff_t idx) { return NULL; } static inline int isolate_or_dissolve_huge_page(struct page *page, struct list_head *list) { return -ENOMEM; } static inline struct folio *alloc_hugetlb_folio(struct vm_area_struct *vma, unsigned long addr, int avoid_reserve) { return NULL; } static inline struct folio * alloc_hugetlb_folio_reserve(struct hstate *h, int preferred_nid, nodemask_t *nmask, gfp_t gfp_mask) { return NULL; } static inline struct folio * alloc_hugetlb_folio_nodemask(struct hstate *h, int preferred_nid, nodemask_t *nmask, gfp_t gfp_mask, bool allow_alloc_fallback) { return NULL; } static inline int __alloc_bootmem_huge_page(struct hstate *h) { return 0; } static inline struct hstate *hstate_file(struct file *f) { return NULL; } static inline struct hstate *hstate_sizelog(int page_size_log) { return NULL; } static inline struct hstate *hstate_vma(struct vm_area_struct *vma) { return NULL; } static inline struct hstate *folio_hstate(struct folio *folio) { return NULL; } static inline struct hstate *size_to_hstate(unsigned long size) { return NULL; } static inline unsigned long huge_page_size(struct hstate *h) { return PAGE_SIZE; } static inline unsigned long huge_page_mask(struct hstate *h) { return PAGE_MASK; } static inline unsigned long vma_kernel_pagesize(struct vm_area_struct *vma) { return PAGE_SIZE; } static inline unsigned long vma_mmu_pagesize(struct vm_area_struct *vma) { return PAGE_SIZE; } static inline unsigned int huge_page_order(struct hstate *h) { return 0; } static inline unsigned int huge_page_shift(struct hstate *h) { return PAGE_SHIFT; } static inline bool hstate_is_gigantic(struct hstate *h) { return false; } static inline unsigned int pages_per_huge_page(struct hstate *h) { return 1; } static inline unsigned hstate_index_to_shift(unsigned index) { return 0; } static inline int hstate_index(struct hstate *h) { return 0; } static inline int dissolve_free_hugetlb_folio(struct folio *folio) { return 0; } static inline int dissolve_free_hugetlb_folios(unsigned long start_pfn, unsigned long end_pfn) { return 0; } static inline bool hugepage_migration_supported(struct hstate *h) { return false; } static inline bool hugepage_movable_supported(struct hstate *h) { return false; } static inline gfp_t htlb_alloc_mask(struct hstate *h) { return 0; } static inline gfp_t htlb_modify_alloc_mask(struct hstate *h, gfp_t gfp_mask) { return 0; } static inline bool htlb_allow_alloc_fallback(int reason) { return false; } static inline spinlock_t *huge_pte_lockptr(struct hstate *h, struct mm_struct *mm, pte_t *pte) { return &mm->page_table_lock; } static inline void hugetlb_count_init(struct mm_struct *mm) { } static inline void hugetlb_report_usage(struct seq_file *f, struct mm_struct *m) { } static inline void hugetlb_count_sub(long l, struct mm_struct *mm) { } static inline pte_t huge_ptep_clear_flush(struct vm_area_struct *vma, unsigned long addr, pte_t *ptep) { #ifdef CONFIG_MMU return ptep_get(ptep); #else return *ptep; #endif } static inline void set_huge_pte_at(struct mm_struct *mm, unsigned long addr, pte_t *ptep, pte_t pte, unsigned long sz) { } static inline void hugetlb_register_node(struct node *node) { } static inline void hugetlb_unregister_node(struct node *node) { } static inline bool hugetlbfs_pagecache_present( struct hstate *h, struct vm_area_struct *vma, unsigned long address) { return false; } #endif /* CONFIG_HUGETLB_PAGE */ static inline spinlock_t *huge_pte_lock(struct hstate *h, struct mm_struct *mm, pte_t *pte) { spinlock_t *ptl; ptl = huge_pte_lockptr(h, mm, pte); spin_lock(ptl); return ptl; } #if defined(CONFIG_HUGETLB_PAGE) && defined(CONFIG_CMA) extern void __init hugetlb_cma_reserve(int order); #else static inline __init void hugetlb_cma_reserve(int order) { } #endif #ifdef CONFIG_HUGETLB_PMD_PAGE_TABLE_SHARING static inline bool hugetlb_pmd_shared(pte_t *pte) { return page_count(virt_to_page(pte)) > 1; } #else static inline bool hugetlb_pmd_shared(pte_t *pte) { return false; } #endif bool want_pmd_share(struct vm_area_struct *vma, unsigned long addr); #ifndef __HAVE_ARCH_FLUSH_HUGETLB_TLB_RANGE /* * ARCHes with special requirements for evicting HUGETLB backing TLB entries can * implement this. */ #define flush_hugetlb_tlb_range(vma, addr, end) flush_tlb_range(vma, addr, end) #endif static inline bool __vma_shareable_lock(struct vm_area_struct *vma) { return (vma->vm_flags & VM_MAYSHARE) && vma->vm_private_data; } bool __vma_private_lock(struct vm_area_struct *vma); /* * Safe version of huge_pte_offset() to check the locks. See comments * above huge_pte_offset(). */ static inline pte_t * hugetlb_walk(struct vm_area_struct *vma, unsigned long addr, unsigned long sz) { #if defined(CONFIG_HUGETLB_PMD_PAGE_TABLE_SHARING) && defined(CONFIG_LOCKDEP) struct hugetlb_vma_lock *vma_lock = vma->vm_private_data; /* * If pmd sharing possible, locking needed to safely walk the * hugetlb pgtables. More information can be found at the comment * above huge_pte_offset() in the same file. * * NOTE: lockdep_is_held() is only defined with CONFIG_LOCKDEP. */ if (__vma_shareable_lock(vma)) WARN_ON_ONCE(!lockdep_is_held(&vma_lock->rw_sema) && !lockdep_is_held( &vma->vm_file->f_mapping->i_mmap_rwsem)); #endif return huge_pte_offset(vma->vm_mm, addr, sz); } #endif /* _LINUX_HUGETLB_H */ |
| 74 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef __LINUX_NODEMASK_H #define __LINUX_NODEMASK_H /* * Nodemasks provide a bitmap suitable for representing the * set of Node's in a system, one bit position per Node number. * * See detailed comments in the file linux/bitmap.h describing the * data type on which these nodemasks are based. * * For details of nodemask_parse_user(), see bitmap_parse_user() in * lib/bitmap.c. For details of nodelist_parse(), see bitmap_parselist(), * also in bitmap.c. For details of node_remap(), see bitmap_bitremap in * lib/bitmap.c. For details of nodes_remap(), see bitmap_remap in * lib/bitmap.c. For details of nodes_onto(), see bitmap_onto in * lib/bitmap.c. For details of nodes_fold(), see bitmap_fold in * lib/bitmap.c. * * The available nodemask operations are: * * void node_set(node, mask) turn on bit 'node' in mask * void node_clear(node, mask) turn off bit 'node' in mask * void nodes_setall(mask) set all bits * void nodes_clear(mask) clear all bits * int node_isset(node, mask) true iff bit 'node' set in mask * int node_test_and_set(node, mask) test and set bit 'node' in mask * * void nodes_and(dst, src1, src2) dst = src1 & src2 [intersection] * void nodes_or(dst, src1, src2) dst = src1 | src2 [union] * void nodes_xor(dst, src1, src2) dst = src1 ^ src2 * void nodes_andnot(dst, src1, src2) dst = src1 & ~src2 * void nodes_complement(dst, src) dst = ~src * * int nodes_equal(mask1, mask2) Does mask1 == mask2? * int nodes_intersects(mask1, mask2) Do mask1 and mask2 intersect? * int nodes_subset(mask1, mask2) Is mask1 a subset of mask2? * int nodes_empty(mask) Is mask empty (no bits sets)? * int nodes_full(mask) Is mask full (all bits sets)? * int nodes_weight(mask) Hamming weight - number of set bits * * void nodes_shift_right(dst, src, n) Shift right * void nodes_shift_left(dst, src, n) Shift left * * unsigned int first_node(mask) Number lowest set bit, or MAX_NUMNODES * unsigend int next_node(node, mask) Next node past 'node', or MAX_NUMNODES * unsigned int next_node_in(node, mask) Next node past 'node', or wrap to first, * or MAX_NUMNODES * unsigned int first_unset_node(mask) First node not set in mask, or * MAX_NUMNODES * * nodemask_t nodemask_of_node(node) Return nodemask with bit 'node' set * NODE_MASK_ALL Initializer - all bits set * NODE_MASK_NONE Initializer - no bits set * unsigned long *nodes_addr(mask) Array of unsigned long's in mask * * int nodemask_parse_user(ubuf, ulen, mask) Parse ascii string as nodemask * int nodelist_parse(buf, map) Parse ascii string as nodelist * int node_remap(oldbit, old, new) newbit = map(old, new)(oldbit) * void nodes_remap(dst, src, old, new) *dst = map(old, new)(src) * void nodes_onto(dst, orig, relmap) *dst = orig relative to relmap * void nodes_fold(dst, orig, sz) dst bits = orig bits mod sz * * for_each_node_mask(node, mask) for-loop node over mask * * int num_online_nodes() Number of online Nodes * int num_possible_nodes() Number of all possible Nodes * * int node_random(mask) Random node with set bit in mask * * int node_online(node) Is some node online? * int node_possible(node) Is some node possible? * * node_set_online(node) set bit 'node' in node_online_map * node_set_offline(node) clear bit 'node' in node_online_map * * for_each_node(node) for-loop node over node_possible_map * for_each_online_node(node) for-loop node over node_online_map * * Subtlety: * 1) The 'type-checked' form of node_isset() causes gcc (3.3.2, anyway) * to generate slightly worse code. So use a simple one-line #define * for node_isset(), instead of wrapping an inline inside a macro, the * way we do the other calls. * * NODEMASK_SCRATCH * When doing above logical AND, OR, XOR, Remap operations the callers tend to * need temporary nodemask_t's on the stack. But if NODES_SHIFT is large, * nodemask_t's consume too much stack space. NODEMASK_SCRATCH is a helper * for such situations. See below and CPUMASK_ALLOC also. */ #include <linux/threads.h> #include <linux/bitmap.h> #include <linux/minmax.h> #include <linux/nodemask_types.h> #include <linux/numa.h> #include <linux/random.h> extern nodemask_t _unused_nodemask_arg_; /** * nodemask_pr_args - printf args to output a nodemask * @maskp: nodemask to be printed * * Can be used to provide arguments for '%*pb[l]' when printing a nodemask. */ #define nodemask_pr_args(maskp) __nodemask_pr_numnodes(maskp), \ __nodemask_pr_bits(maskp) static __always_inline unsigned int __nodemask_pr_numnodes(const nodemask_t *m) { return m ? MAX_NUMNODES : 0; } static __always_inline const unsigned long *__nodemask_pr_bits(const nodemask_t *m) { return m ? m->bits : NULL; } /* * The inline keyword gives the compiler room to decide to inline, or * not inline a function as it sees best. However, as these functions * are called in both __init and non-__init functions, if they are not * inlined we will end up with a section mismatch error (of the type of * freeable items not being freed). So we must use __always_inline here * to fix the problem. If other functions in the future also end up in * this situation they will also need to be annotated as __always_inline */ #define node_set(node, dst) __node_set((node), &(dst)) static __always_inline void __node_set(int node, volatile nodemask_t *dstp) { set_bit(node, dstp->bits); } #define node_clear(node, dst) __node_clear((node), &(dst)) static __always_inline void __node_clear(int node, volatile nodemask_t *dstp) { clear_bit(node, dstp->bits); } #define nodes_setall(dst) __nodes_setall(&(dst), MAX_NUMNODES) static __always_inline void __nodes_setall(nodemask_t *dstp, unsigned int nbits) { bitmap_fill(dstp->bits, nbits); } #define nodes_clear(dst) __nodes_clear(&(dst), MAX_NUMNODES) static __always_inline void __nodes_clear(nodemask_t *dstp, unsigned int nbits) { bitmap_zero(dstp->bits, nbits); } /* No static inline type checking - see Subtlety (1) above. */ #define node_isset(node, nodemask) test_bit((node), (nodemask).bits) #define node_test_and_set(node, nodemask) \ __node_test_and_set((node), &(nodemask)) static __always_inline bool __node_test_and_set(int node, nodemask_t *addr) { return test_and_set_bit(node, addr->bits); } #define nodes_and(dst, src1, src2) \ __nodes_and(&(dst), &(src1), &(src2), MAX_NUMNODES) static __always_inline void __nodes_and(nodemask_t *dstp, const nodemask_t *src1p, const nodemask_t *src2p, unsigned int nbits) { bitmap_and(dstp->bits, src1p->bits, src2p->bits, nbits); } #define nodes_or(dst, src1, src2) \ __nodes_or(&(dst), &(src1), &(src2), MAX_NUMNODES) static __always_inline void __nodes_or(nodemask_t *dstp, const nodemask_t *src1p, const nodemask_t *src2p, unsigned int nbits) { bitmap_or(dstp->bits, src1p->bits, src2p->bits, nbits); } #define nodes_xor(dst, src1, src2) \ __nodes_xor(&(dst), &(src1), &(src2), MAX_NUMNODES) static __always_inline void __nodes_xor(nodemask_t *dstp, const nodemask_t *src1p, const nodemask_t *src2p, unsigned int nbits) { bitmap_xor(dstp->bits, src1p->bits, src2p->bits, nbits); } #define nodes_andnot(dst, src1, src2) \ __nodes_andnot(&(dst), &(src1), &(src2), MAX_NUMNODES) static __always_inline void __nodes_andnot(nodemask_t *dstp, const nodemask_t *src1p, const nodemask_t *src2p, unsigned int nbits) { bitmap_andnot(dstp->bits, src1p->bits, src2p->bits, nbits); } #define nodes_complement(dst, src) \ __nodes_complement(&(dst), &(src), MAX_NUMNODES) static __always_inline void __nodes_complement(nodemask_t *dstp, const nodemask_t *srcp, unsigned int nbits) { bitmap_complement(dstp->bits, srcp->bits, nbits); } #define nodes_equal(src1, src2) \ __nodes_equal(&(src1), &(src2), MAX_NUMNODES) static __always_inline bool __nodes_equal(const nodemask_t *src1p, const nodemask_t *src2p, unsigned int nbits) { return bitmap_equal(src1p->bits, src2p->bits, nbits); } #define nodes_intersects(src1, src2) \ __nodes_intersects(&(src1), &(src2), MAX_NUMNODES) static __always_inline bool __nodes_intersects(const nodemask_t *src1p, const nodemask_t *src2p, unsigned int nbits) { return bitmap_intersects(src1p->bits, src2p->bits, nbits); } #define nodes_subset(src1, src2) \ __nodes_subset(&(src1), &(src2), MAX_NUMNODES) static __always_inline bool __nodes_subset(const nodemask_t *src1p, const nodemask_t *src2p, unsigned int nbits) { return bitmap_subset(src1p->bits, src2p->bits, nbits); } #define nodes_empty(src) __nodes_empty(&(src), MAX_NUMNODES) static __always_inline bool __nodes_empty(const nodemask_t *srcp, unsigned int nbits) { return bitmap_empty(srcp->bits, nbits); } #define nodes_full(nodemask) __nodes_full(&(nodemask), MAX_NUMNODES) static __always_inline bool __nodes_full(const nodemask_t *srcp, unsigned int nbits) { return bitmap_full(srcp->bits, nbits); } #define nodes_weight(nodemask) __nodes_weight(&(nodemask), MAX_NUMNODES) static __always_inline int __nodes_weight(const nodemask_t *srcp, unsigned int nbits) { return bitmap_weight(srcp->bits, nbits); } #define nodes_shift_right(dst, src, n) \ __nodes_shift_right(&(dst), &(src), (n), MAX_NUMNODES) static __always_inline void __nodes_shift_right(nodemask_t *dstp, const nodemask_t *srcp, int n, int nbits) { bitmap_shift_right(dstp->bits, srcp->bits, n, nbits); } #define nodes_shift_left(dst, src, n) \ __nodes_shift_left(&(dst), &(src), (n), MAX_NUMNODES) static __always_inline void __nodes_shift_left(nodemask_t *dstp, const nodemask_t *srcp, int n, int nbits) { bitmap_shift_left(dstp->bits, srcp->bits, n, nbits); } /* FIXME: better would be to fix all architectures to never return > MAX_NUMNODES, then the silly min_ts could be dropped. */ #define first_node(src) __first_node(&(src)) static __always_inline unsigned int __first_node(const nodemask_t *srcp) { return min_t(unsigned int, MAX_NUMNODES, find_first_bit(srcp->bits, MAX_NUMNODES)); } #define next_node(n, src) __next_node((n), &(src)) static __always_inline unsigned int __next_node(int n, const nodemask_t *srcp) { return min_t(unsigned int, MAX_NUMNODES, find_next_bit(srcp->bits, MAX_NUMNODES, n+1)); } /* * Find the next present node in src, starting after node n, wrapping around to * the first node in src if needed. Returns MAX_NUMNODES if src is empty. */ #define next_node_in(n, src) __next_node_in((n), &(src)) static __always_inline unsigned int __next_node_in(int node, const nodemask_t *srcp) { unsigned int ret = __next_node(node, srcp); if (ret == MAX_NUMNODES) ret = __first_node(srcp); return ret; } static __always_inline void init_nodemask_of_node(nodemask_t *mask, int node) { nodes_clear(*mask); node_set(node, *mask); } #define nodemask_of_node(node) \ ({ \ typeof(_unused_nodemask_arg_) m; \ if (sizeof(m) == sizeof(unsigned long)) { \ m.bits[0] = 1UL << (node); \ } else { \ init_nodemask_of_node(&m, (node)); \ } \ m; \ }) #define first_unset_node(mask) __first_unset_node(&(mask)) static __always_inline unsigned int __first_unset_node(const nodemask_t *maskp) { return min_t(unsigned int, MAX_NUMNODES, find_first_zero_bit(maskp->bits, MAX_NUMNODES)); } #define NODE_MASK_LAST_WORD BITMAP_LAST_WORD_MASK(MAX_NUMNODES) #if MAX_NUMNODES <= BITS_PER_LONG #define NODE_MASK_ALL \ ((nodemask_t) { { \ [BITS_TO_LONGS(MAX_NUMNODES)-1] = NODE_MASK_LAST_WORD \ } }) #else #define NODE_MASK_ALL \ ((nodemask_t) { { \ [0 ... BITS_TO_LONGS(MAX_NUMNODES)-2] = ~0UL, \ [BITS_TO_LONGS(MAX_NUMNODES)-1] = NODE_MASK_LAST_WORD \ } }) #endif #define NODE_MASK_NONE \ ((nodemask_t) { { \ [0 ... BITS_TO_LONGS(MAX_NUMNODES)-1] = 0UL \ } }) #define nodes_addr(src) ((src).bits) #define nodemask_parse_user(ubuf, ulen, dst) \ __nodemask_parse_user((ubuf), (ulen), &(dst), MAX_NUMNODES) static __always_inline int __nodemask_parse_user(const char __user *buf, int len, nodemask_t *dstp, int nbits) { return bitmap_parse_user(buf, len, dstp->bits, nbits); } #define nodelist_parse(buf, dst) __nodelist_parse((buf), &(dst), MAX_NUMNODES) static __always_inline int __nodelist_parse(const char *buf, nodemask_t *dstp, int nbits) { return bitmap_parselist(buf, dstp->bits, nbits); } #define node_remap(oldbit, old, new) \ __node_remap((oldbit), &(old), &(new), MAX_NUMNODES) static __always_inline int __node_remap(int oldbit, const nodemask_t *oldp, const nodemask_t *newp, int nbits) { return bitmap_bitremap(oldbit, oldp->bits, newp->bits, nbits); } #define nodes_remap(dst, src, old, new) \ __nodes_remap(&(dst), &(src), &(old), &(new), MAX_NUMNODES) static __always_inline void __nodes_remap(nodemask_t *dstp, const nodemask_t *srcp, const nodemask_t *oldp, const nodemask_t *newp, int nbits) { bitmap_remap(dstp->bits, srcp->bits, oldp->bits, newp->bits, nbits); } #define nodes_onto(dst, orig, relmap) \ __nodes_onto(&(dst), &(orig), &(relmap), MAX_NUMNODES) static __always_inline void __nodes_onto(nodemask_t *dstp, const nodemask_t *origp, const nodemask_t *relmapp, int nbits) { bitmap_onto(dstp->bits, origp->bits, relmapp->bits, nbits); } #define nodes_fold(dst, orig, sz) \ __nodes_fold(&(dst), &(orig), sz, MAX_NUMNODES) static __always_inline void __nodes_fold(nodemask_t *dstp, const nodemask_t *origp, int sz, int nbits) { bitmap_fold(dstp->bits, origp->bits, sz, nbits); } #if MAX_NUMNODES > 1 #define for_each_node_mask(node, mask) \ for ((node) = first_node(mask); \ (node) < MAX_NUMNODES; \ (node) = next_node((node), (mask))) #else /* MAX_NUMNODES == 1 */ #define for_each_node_mask(node, mask) \ for ((node) = 0; (node) < 1 && !nodes_empty(mask); (node)++) #endif /* MAX_NUMNODES */ /* * Bitmasks that are kept for all the nodes. */ enum node_states { N_POSSIBLE, /* The node could become online at some point */ N_ONLINE, /* The node is online */ N_NORMAL_MEMORY, /* The node has regular memory */ #ifdef CONFIG_HIGHMEM N_HIGH_MEMORY, /* The node has regular or high memory */ #else N_HIGH_MEMORY = N_NORMAL_MEMORY, #endif N_MEMORY, /* The node has memory(regular, high, movable) */ N_CPU, /* The node has one or more cpus */ N_GENERIC_INITIATOR, /* The node has one or more Generic Initiators */ NR_NODE_STATES }; /* * The following particular system nodemasks and operations * on them manage all possible and online nodes. */ extern nodemask_t node_states[NR_NODE_STATES]; #if MAX_NUMNODES > 1 static __always_inline int node_state(int node, enum node_states state) { return node_isset(node, node_states[state]); } static __always_inline void node_set_state(int node, enum node_states state) { __node_set(node, &node_states[state]); } static __always_inline void node_clear_state(int node, enum node_states state) { __node_clear(node, &node_states[state]); } static __always_inline int num_node_state(enum node_states state) { return nodes_weight(node_states[state]); } #define for_each_node_state(__node, __state) \ for_each_node_mask((__node), node_states[__state]) #define first_online_node first_node(node_states[N_ONLINE]) #define first_memory_node first_node(node_states[N_MEMORY]) static __always_inline unsigned int next_online_node(int nid) { return next_node(nid, node_states[N_ONLINE]); } static __always_inline unsigned int next_memory_node(int nid) { return next_node(nid, node_states[N_MEMORY]); } extern unsigned int nr_node_ids; extern unsigned int nr_online_nodes; static __always_inline void node_set_online(int nid) { node_set_state(nid, N_ONLINE); nr_online_nodes = num_node_state(N_ONLINE); } static __always_inline void node_set_offline(int nid) { node_clear_state(nid, N_ONLINE); nr_online_nodes = num_node_state(N_ONLINE); } #else static __always_inline int node_state(int node, enum node_states state) { return node == 0; } static __always_inline void node_set_state(int node, enum node_states state) { } static __always_inline void node_clear_state(int node, enum node_states state) { } static __always_inline int num_node_state(enum node_states state) { return 1; } #define for_each_node_state(node, __state) \ for ( (node) = 0; (node) == 0; (node) = 1) #define first_online_node 0 #define first_memory_node 0 #define next_online_node(nid) (MAX_NUMNODES) #define next_memory_node(nid) (MAX_NUMNODES) #define nr_node_ids 1U #define nr_online_nodes 1U #define node_set_online(node) node_set_state((node), N_ONLINE) #define node_set_offline(node) node_clear_state((node), N_ONLINE) #endif static __always_inline int node_random(const nodemask_t *maskp) { #if defined(CONFIG_NUMA) && (MAX_NUMNODES > 1) int w, bit; w = nodes_weight(*maskp); switch (w) { case 0: bit = NUMA_NO_NODE; break; case 1: bit = first_node(*maskp); break; default: bit = find_nth_bit(maskp->bits, MAX_NUMNODES, get_random_u32_below(w)); break; } return bit; #else return 0; #endif } #define node_online_map node_states[N_ONLINE] #define node_possible_map node_states[N_POSSIBLE] #define num_online_nodes() num_node_state(N_ONLINE) #define num_possible_nodes() num_node_state(N_POSSIBLE) #define node_online(node) node_state((node), N_ONLINE) #define node_possible(node) node_state((node), N_POSSIBLE) #define for_each_node(node) for_each_node_state(node, N_POSSIBLE) #define for_each_online_node(node) for_each_node_state(node, N_ONLINE) /* * For nodemask scratch area. * NODEMASK_ALLOC(type, name) allocates an object with a specified type and * name. */ #if NODES_SHIFT > 8 /* nodemask_t > 32 bytes */ #define NODEMASK_ALLOC(type, name, gfp_flags) \ type *name = kmalloc(sizeof(*name), gfp_flags) #define NODEMASK_FREE(m) kfree(m) #else #define NODEMASK_ALLOC(type, name, gfp_flags) type _##name, *name = &_##name #define NODEMASK_FREE(m) do {} while (0) #endif /* Example structure for using NODEMASK_ALLOC, used in mempolicy. */ struct nodemask_scratch { nodemask_t mask1; nodemask_t mask2; }; #define NODEMASK_SCRATCH(x) \ NODEMASK_ALLOC(struct nodemask_scratch, x, \ GFP_KERNEL | __GFP_NORETRY) #define NODEMASK_SCRATCH_FREE(x) NODEMASK_FREE(x) #endif /* __LINUX_NODEMASK_H */ |
| 314 313 313 314 22 15 15 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 | /* SPDX-License-Identifier: GPL-2.0-or-later */ /* Red Black Trees (C) 1999 Andrea Arcangeli <andrea@suse.de> linux/include/linux/rbtree.h To use rbtrees you'll have to implement your own insert and search cores. This will avoid us to use callbacks and to drop drammatically performances. I know it's not the cleaner way, but in C (not in C++) to get performances and genericity... See Documentation/core-api/rbtree.rst for documentation and samples. */ #ifndef _LINUX_RBTREE_H #define _LINUX_RBTREE_H #include <linux/container_of.h> #include <linux/rbtree_types.h> #include <linux/stddef.h> #include <linux/rcupdate.h> #define rb_parent(r) ((struct rb_node *)((r)->__rb_parent_color & ~3)) #define rb_entry(ptr, type, member) container_of(ptr, type, member) #define RB_EMPTY_ROOT(root) (READ_ONCE((root)->rb_node) == NULL) /* 'empty' nodes are nodes that are known not to be inserted in an rbtree */ #define RB_EMPTY_NODE(node) \ ((node)->__rb_parent_color == (unsigned long)(node)) #define RB_CLEAR_NODE(node) \ ((node)->__rb_parent_color = (unsigned long)(node)) extern void rb_insert_color(struct rb_node *, struct rb_root *); extern void rb_erase(struct rb_node *, struct rb_root *); /* Find logical next and previous nodes in a tree */ extern struct rb_node *rb_next(const struct rb_node *); extern struct rb_node *rb_prev(const struct rb_node *); extern struct rb_node *rb_first(const struct rb_root *); extern struct rb_node *rb_last(const struct rb_root *); /* Postorder iteration - always visit the parent after its children */ extern struct rb_node *rb_first_postorder(const struct rb_root *); extern struct rb_node *rb_next_postorder(const struct rb_node *); /* Fast replacement of a single node without remove/rebalance/add/rebalance */ extern void rb_replace_node(struct rb_node *victim, struct rb_node *new, struct rb_root *root); extern void rb_replace_node_rcu(struct rb_node *victim, struct rb_node *new, struct rb_root *root); static inline void rb_link_node(struct rb_node *node, struct rb_node *parent, struct rb_node **rb_link) { node->__rb_parent_color = (unsigned long)parent; node->rb_left = node->rb_right = NULL; *rb_link = node; } static inline void rb_link_node_rcu(struct rb_node *node, struct rb_node *parent, struct rb_node **rb_link) { node->__rb_parent_color = (unsigned long)parent; node->rb_left = node->rb_right = NULL; rcu_assign_pointer(*rb_link, node); } #define rb_entry_safe(ptr, type, member) \ ({ typeof(ptr) ____ptr = (ptr); \ ____ptr ? rb_entry(____ptr, type, member) : NULL; \ }) /** * rbtree_postorder_for_each_entry_safe - iterate in post-order over rb_root of * given type allowing the backing memory of @pos to be invalidated * * @pos: the 'type *' to use as a loop cursor. * @n: another 'type *' to use as temporary storage * @root: 'rb_root *' of the rbtree. * @field: the name of the rb_node field within 'type'. * * rbtree_postorder_for_each_entry_safe() provides a similar guarantee as * list_for_each_entry_safe() and allows the iteration to continue independent * of changes to @pos by the body of the loop. * * Note, however, that it cannot handle other modifications that re-order the * rbtree it is iterating over. This includes calling rb_erase() on @pos, as * rb_erase() may rebalance the tree, causing us to miss some nodes. */ #define rbtree_postorder_for_each_entry_safe(pos, n, root, field) \ for (pos = rb_entry_safe(rb_first_postorder(root), typeof(*pos), field); \ pos && ({ n = rb_entry_safe(rb_next_postorder(&pos->field), \ typeof(*pos), field); 1; }); \ pos = n) /* Same as rb_first(), but O(1) */ #define rb_first_cached(root) (root)->rb_leftmost static inline void rb_insert_color_cached(struct rb_node *node, struct rb_root_cached *root, bool leftmost) { if (leftmost) root->rb_leftmost = node; rb_insert_color(node, &root->rb_root); } static inline struct rb_node * rb_erase_cached(struct rb_node *node, struct rb_root_cached *root) { struct rb_node *leftmost = NULL; if (root->rb_leftmost == node) leftmost = root->rb_leftmost = rb_next(node); rb_erase(node, &root->rb_root); return leftmost; } static inline void rb_replace_node_cached(struct rb_node *victim, struct rb_node *new, struct rb_root_cached *root) { if (root->rb_leftmost == victim) root->rb_leftmost = new; rb_replace_node(victim, new, &root->rb_root); } /* * The below helper functions use 2 operators with 3 different * calling conventions. The operators are related like: * * comp(a->key,b) < 0 := less(a,b) * comp(a->key,b) > 0 := less(b,a) * comp(a->key,b) == 0 := !less(a,b) && !less(b,a) * * If these operators define a partial order on the elements we make no * guarantee on which of the elements matching the key is found. See * rb_find(). * * The reason for this is to allow the find() interface without requiring an * on-stack dummy object, which might not be feasible due to object size. */ /** * rb_add_cached() - insert @node into the leftmost cached tree @tree * @node: node to insert * @tree: leftmost cached tree to insert @node into * @less: operator defining the (partial) node order * * Returns @node when it is the new leftmost, or NULL. */ static __always_inline struct rb_node * rb_add_cached(struct rb_node *node, struct rb_root_cached *tree, bool (*less)(struct rb_node *, const struct rb_node *)) { struct rb_node **link = &tree->rb_root.rb_node; struct rb_node *parent = NULL; bool leftmost = true; while (*link) { parent = *link; if (less(node, parent)) { link = &parent->rb_left; } else { link = &parent->rb_right; leftmost = false; } } rb_link_node(node, parent, link); rb_insert_color_cached(node, tree, leftmost); return leftmost ? node : NULL; } /** * rb_add() - insert @node into @tree * @node: node to insert * @tree: tree to insert @node into * @less: operator defining the (partial) node order */ static __always_inline void rb_add(struct rb_node *node, struct rb_root *tree, bool (*less)(struct rb_node *, const struct rb_node *)) { struct rb_node **link = &tree->rb_node; struct rb_node *parent = NULL; while (*link) { parent = *link; if (less(node, parent)) link = &parent->rb_left; else link = &parent->rb_right; } rb_link_node(node, parent, link); rb_insert_color(node, tree); } /** * rb_find_add() - find equivalent @node in @tree, or add @node * @node: node to look-for / insert * @tree: tree to search / modify * @cmp: operator defining the node order * * Returns the rb_node matching @node, or NULL when no match is found and @node * is inserted. */ static __always_inline struct rb_node * rb_find_add(struct rb_node *node, struct rb_root *tree, int (*cmp)(struct rb_node *, const struct rb_node *)) { struct rb_node **link = &tree->rb_node; struct rb_node *parent = NULL; int c; while (*link) { parent = *link; c = cmp(node, parent); if (c < 0) link = &parent->rb_left; else if (c > 0) link = &parent->rb_right; else return parent; } rb_link_node(node, parent, link); rb_insert_color(node, tree); return NULL; } /** * rb_find_add_rcu() - find equivalent @node in @tree, or add @node * @node: node to look-for / insert * @tree: tree to search / modify * @cmp: operator defining the node order * * Adds a Store-Release for link_node. * * Returns the rb_node matching @node, or NULL when no match is found and @node * is inserted. */ static __always_inline struct rb_node * rb_find_add_rcu(struct rb_node *node, struct rb_root *tree, int (*cmp)(struct rb_node *, const struct rb_node *)) { struct rb_node **link = &tree->rb_node; struct rb_node *parent = NULL; int c; while (*link) { parent = *link; c = cmp(node, parent); if (c < 0) link = &parent->rb_left; else if (c > 0) link = &parent->rb_right; else return parent; } rb_link_node_rcu(node, parent, link); rb_insert_color(node, tree); return NULL; } /** * rb_find() - find @key in tree @tree * @key: key to match * @tree: tree to search * @cmp: operator defining the node order * * Returns the rb_node matching @key or NULL. */ static __always_inline struct rb_node * rb_find(const void *key, const struct rb_root *tree, int (*cmp)(const void *key, const struct rb_node *)) { struct rb_node *node = tree->rb_node; while (node) { int c = cmp(key, node); if (c < 0) node = node->rb_left; else if (c > 0) node = node->rb_right; else return node; } return NULL; } /** * rb_find_rcu() - find @key in tree @tree * @key: key to match * @tree: tree to search * @cmp: operator defining the node order * * Notably, tree descent vs concurrent tree rotations is unsound and can result * in false-negatives. * * Returns the rb_node matching @key or NULL. */ static __always_inline struct rb_node * rb_find_rcu(const void *key, const struct rb_root *tree, int (*cmp)(const void *key, const struct rb_node *)) { struct rb_node *node = tree->rb_node; while (node) { int c = cmp(key, node); if (c < 0) node = rcu_dereference_raw(node->rb_left); else if (c > 0) node = rcu_dereference_raw(node->rb_right); else return node; } return NULL; } /** * rb_find_first() - find the first @key in @tree * @key: key to match * @tree: tree to search * @cmp: operator defining node order * * Returns the leftmost node matching @key, or NULL. */ static __always_inline struct rb_node * rb_find_first(const void *key, const struct rb_root *tree, int (*cmp)(const void *key, const struct rb_node *)) { struct rb_node *node = tree->rb_node; struct rb_node *match = NULL; while (node) { int c = cmp(key, node); if (c <= 0) { if (!c) match = node; node = node->rb_left; } else if (c > 0) { node = node->rb_right; } } return match; } /** * rb_next_match() - find the next @key in @tree * @key: key to match * @tree: tree to search * @cmp: operator defining node order * * Returns the next node matching @key, or NULL. */ static __always_inline struct rb_node * rb_next_match(const void *key, struct rb_node *node, int (*cmp)(const void *key, const struct rb_node *)) { node = rb_next(node); if (node && cmp(key, node)) node = NULL; return node; } /** * rb_for_each() - iterates a subtree matching @key * @node: iterator * @key: key to match * @tree: tree to search * @cmp: operator defining node order */ #define rb_for_each(node, key, tree, cmp) \ for ((node) = rb_find_first((key), (tree), (cmp)); \ (node); (node) = rb_next_match((key), (node), (cmp))) #endif /* _LINUX_RBTREE_H */ |
| 363 160 212 159 212 158 212 42 65 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _LINUX_MMU_NOTIFIER_H #define _LINUX_MMU_NOTIFIER_H #include <linux/list.h> #include <linux/spinlock.h> #include <linux/mm_types.h> #include <linux/mmap_lock.h> #include <linux/srcu.h> #include <linux/interval_tree.h> struct mmu_notifier_subscriptions; struct mmu_notifier; struct mmu_notifier_range; struct mmu_interval_notifier; /** * enum mmu_notifier_event - reason for the mmu notifier callback * @MMU_NOTIFY_UNMAP: either munmap() that unmap the range or a mremap() that * move the range * * @MMU_NOTIFY_CLEAR: clear page table entry (many reasons for this like * madvise() or replacing a page by another one, ...). * * @MMU_NOTIFY_PROTECTION_VMA: update is due to protection change for the range * ie using the vma access permission (vm_page_prot) to update the whole range * is enough no need to inspect changes to the CPU page table (mprotect() * syscall) * * @MMU_NOTIFY_PROTECTION_PAGE: update is due to change in read/write flag for * pages in the range so to mirror those changes the user must inspect the CPU * page table (from the end callback). * * @MMU_NOTIFY_SOFT_DIRTY: soft dirty accounting (still same page and same * access flags). User should soft dirty the page in the end callback to make * sure that anyone relying on soft dirtiness catch pages that might be written * through non CPU mappings. * * @MMU_NOTIFY_RELEASE: used during mmu_interval_notifier invalidate to signal * that the mm refcount is zero and the range is no longer accessible. * * @MMU_NOTIFY_MIGRATE: used during migrate_vma_collect() invalidate to signal * a device driver to possibly ignore the invalidation if the * owner field matches the driver's device private pgmap owner. * * @MMU_NOTIFY_EXCLUSIVE: to signal a device driver that the device will no * longer have exclusive access to the page. When sent during creation of an * exclusive range the owner will be initialised to the value provided by the * caller of make_device_exclusive_range(), otherwise the owner will be NULL. */ enum mmu_notifier_event { MMU_NOTIFY_UNMAP = 0, MMU_NOTIFY_CLEAR, MMU_NOTIFY_PROTECTION_VMA, MMU_NOTIFY_PROTECTION_PAGE, MMU_NOTIFY_SOFT_DIRTY, MMU_NOTIFY_RELEASE, MMU_NOTIFY_MIGRATE, MMU_NOTIFY_EXCLUSIVE, }; #define MMU_NOTIFIER_RANGE_BLOCKABLE (1 << 0) struct mmu_notifier_ops { /* * Called either by mmu_notifier_unregister or when the mm is * being destroyed by exit_mmap, always before all pages are * freed. This can run concurrently with other mmu notifier * methods (the ones invoked outside the mm context) and it * should tear down all secondary mmu mappings and freeze the * secondary mmu. If this method isn't implemented you've to * be sure that nothing could possibly write to the pages * through the secondary mmu by the time the last thread with * tsk->mm == mm exits. * * As side note: the pages freed after ->release returns could * be immediately reallocated by the gart at an alias physical * address with a different cache model, so if ->release isn't * implemented because all _software_ driven memory accesses * through the secondary mmu are terminated by the time the * last thread of this mm quits, you've also to be sure that * speculative _hardware_ operations can't allocate dirty * cachelines in the cpu that could not be snooped and made * coherent with the other read and write operations happening * through the gart alias address, so leading to memory * corruption. */ void (*release)(struct mmu_notifier *subscription, struct mm_struct *mm); /* * clear_flush_young is called after the VM is * test-and-clearing the young/accessed bitflag in the * pte. This way the VM will provide proper aging to the * accesses to the page through the secondary MMUs and not * only to the ones through the Linux pte. * Start-end is necessary in case the secondary MMU is mapping the page * at a smaller granularity than the primary MMU. */ int (*clear_flush_young)(struct mmu_notifier *subscription, struct mm_struct *mm, unsigned long start, unsigned long end); /* * clear_young is a lightweight version of clear_flush_young. Like the * latter, it is supposed to test-and-clear the young/accessed bitflag * in the secondary pte, but it may omit flushing the secondary tlb. */ int (*clear_young)(struct mmu_notifier *subscription, struct mm_struct *mm, unsigned long start, unsigned long end); /* * test_young is called to check the young/accessed bitflag in * the secondary pte. This is used to know if the page is * frequently used without actually clearing the flag or tearing * down the secondary mapping on the page. */ int (*test_young)(struct mmu_notifier *subscription, struct mm_struct *mm, unsigned long address); /* * invalidate_range_start() and invalidate_range_end() must be * paired and are called only when the mmap_lock and/or the * locks protecting the reverse maps are held. If the subsystem * can't guarantee that no additional references are taken to * the pages in the range, it has to implement the * invalidate_range() notifier to remove any references taken * after invalidate_range_start(). * * Invalidation of multiple concurrent ranges may be * optionally permitted by the driver. Either way the * establishment of sptes is forbidden in the range passed to * invalidate_range_begin/end for the whole duration of the * invalidate_range_begin/end critical section. * * invalidate_range_start() is called when all pages in the * range are still mapped and have at least a refcount of one. * * invalidate_range_end() is called when all pages in the * range have been unmapped and the pages have been freed by * the VM. * * The VM will remove the page table entries and potentially * the page between invalidate_range_start() and * invalidate_range_end(). If the page must not be freed * because of pending I/O or other circumstances then the * invalidate_range_start() callback (or the initial mapping * by the driver) must make sure that the refcount is kept * elevated. * * If the driver increases the refcount when the pages are * initially mapped into an address space then either * invalidate_range_start() or invalidate_range_end() may * decrease the refcount. If the refcount is decreased on * invalidate_range_start() then the VM can free pages as page * table entries are removed. If the refcount is only * dropped on invalidate_range_end() then the driver itself * will drop the last refcount but it must take care to flush * any secondary tlb before doing the final free on the * page. Pages will no longer be referenced by the linux * address space but may still be referenced by sptes until * the last refcount is dropped. * * If blockable argument is set to false then the callback cannot * sleep and has to return with -EAGAIN if sleeping would be required. * 0 should be returned otherwise. Please note that notifiers that can * fail invalidate_range_start are not allowed to implement * invalidate_range_end, as there is no mechanism for informing the * notifier that its start failed. */ int (*invalidate_range_start)(struct mmu_notifier *subscription, const struct mmu_notifier_range *range); void (*invalidate_range_end)(struct mmu_notifier *subscription, const struct mmu_notifier_range *range); /* * arch_invalidate_secondary_tlbs() is used to manage a non-CPU TLB * which shares page-tables with the CPU. The * invalidate_range_start()/end() callbacks should not be implemented as * invalidate_secondary_tlbs() already catches the points in time when * an external TLB needs to be flushed. * * This requires arch_invalidate_secondary_tlbs() to be called while * holding the ptl spin-lock and therefore this callback is not allowed * to sleep. * * This is called by architecture code whenever invalidating a TLB * entry. It is assumed that any secondary TLB has the same rules for * when invalidations are required. If this is not the case architecture * code will need to call this explicitly when required for secondary * TLB invalidation. */ void (*arch_invalidate_secondary_tlbs)( struct mmu_notifier *subscription, struct mm_struct *mm, unsigned long start, unsigned long end); /* * These callbacks are used with the get/put interface to manage the * lifetime of the mmu_notifier memory. alloc_notifier() returns a new * notifier for use with the mm. * * free_notifier() is only called after the mmu_notifier has been * fully put, calls to any ops callback are prevented and no ops * callbacks are currently running. It is called from a SRCU callback * and cannot sleep. */ struct mmu_notifier *(*alloc_notifier)(struct mm_struct *mm); void (*free_notifier)(struct mmu_notifier *subscription); }; /* * The notifier chains are protected by mmap_lock and/or the reverse map * semaphores. Notifier chains are only changed when all reverse maps and * the mmap_lock locks are taken. * * Therefore notifier chains can only be traversed when either * * 1. mmap_lock is held. * 2. One of the reverse map locks is held (i_mmap_rwsem or anon_vma->rwsem). * 3. No other concurrent thread can access the list (release) */ struct mmu_notifier { struct hlist_node hlist; const struct mmu_notifier_ops *ops; struct mm_struct *mm; struct rcu_head rcu; unsigned int users; }; /** * struct mmu_interval_notifier_ops * @invalidate: Upon return the caller must stop using any SPTEs within this * range. This function can sleep. Return false only if sleeping * was required but mmu_notifier_range_blockable(range) is false. */ struct mmu_interval_notifier_ops { bool (*invalidate)(struct mmu_interval_notifier *interval_sub, const struct mmu_notifier_range *range, unsigned long cur_seq); }; struct mmu_interval_notifier { struct interval_tree_node interval_tree; const struct mmu_interval_notifier_ops *ops; struct mm_struct *mm; struct hlist_node deferred_item; unsigned long invalidate_seq; }; #ifdef CONFIG_MMU_NOTIFIER #ifdef CONFIG_LOCKDEP extern struct lockdep_map __mmu_notifier_invalidate_range_start_map; #endif struct mmu_notifier_range { struct mm_struct *mm; unsigned long start; unsigned long end; unsigned flags; enum mmu_notifier_event event; void *owner; }; static inline int mm_has_notifiers(struct mm_struct *mm) { return unlikely(mm->notifier_subscriptions); } struct mmu_notifier *mmu_notifier_get_locked(const struct mmu_notifier_ops *ops, struct mm_struct *mm); static inline struct mmu_notifier * mmu_notifier_get(const struct mmu_notifier_ops *ops, struct mm_struct *mm) { struct mmu_notifier *ret; mmap_write_lock(mm); ret = mmu_notifier_get_locked(ops, mm); mmap_write_unlock(mm); return ret; } void mmu_notifier_put(struct mmu_notifier *subscription); void mmu_notifier_synchronize(void); extern int mmu_notifier_register(struct mmu_notifier *subscription, struct mm_struct *mm); extern int __mmu_notifier_register(struct mmu_notifier *subscription, struct mm_struct *mm); extern void mmu_notifier_unregister(struct mmu_notifier *subscription, struct mm_struct *mm); unsigned long mmu_interval_read_begin(struct mmu_interval_notifier *interval_sub); int mmu_interval_notifier_insert(struct mmu_interval_notifier *interval_sub, struct mm_struct *mm, unsigned long start, unsigned long length, const struct mmu_interval_notifier_ops *ops); int mmu_interval_notifier_insert_locked( struct mmu_interval_notifier *interval_sub, struct mm_struct *mm, unsigned long start, unsigned long length, const struct mmu_interval_notifier_ops *ops); void mmu_interval_notifier_remove(struct mmu_interval_notifier *interval_sub); /** * mmu_interval_set_seq - Save the invalidation sequence * @interval_sub - The subscription passed to invalidate * @cur_seq - The cur_seq passed to the invalidate() callback * * This must be called unconditionally from the invalidate callback of a * struct mmu_interval_notifier_ops under the same lock that is used to call * mmu_interval_read_retry(). It updates the sequence number for later use by * mmu_interval_read_retry(). The provided cur_seq will always be odd. * * If the caller does not call mmu_interval_read_begin() or * mmu_interval_read_retry() then this call is not required. */ static inline void mmu_interval_set_seq(struct mmu_interval_notifier *interval_sub, unsigned long cur_seq) { WRITE_ONCE(interval_sub->invalidate_seq, cur_seq); } /** * mmu_interval_read_retry - End a read side critical section against a VA range * interval_sub: The subscription * seq: The return of the paired mmu_interval_read_begin() * * This MUST be called under a user provided lock that is also held * unconditionally by op->invalidate() when it calls mmu_interval_set_seq(). * * Each call should be paired with a single mmu_interval_read_begin() and * should be used to conclude the read side. * * Returns true if an invalidation collided with this critical section, and * the caller should retry. */ static inline bool mmu_interval_read_retry(struct mmu_interval_notifier *interval_sub, unsigned long seq) { return interval_sub->invalidate_seq != seq; } /** * mmu_interval_check_retry - Test if a collision has occurred * interval_sub: The subscription * seq: The return of the matching mmu_interval_read_begin() * * This can be used in the critical section between mmu_interval_read_begin() * and mmu_interval_read_retry(). A return of true indicates an invalidation * has collided with this critical region and a future * mmu_interval_read_retry() will return true. * * False is not reliable and only suggests a collision may not have * occurred. It can be called many times and does not have to hold the user * provided lock. * * This call can be used as part of loops and other expensive operations to * expedite a retry. */ static inline bool mmu_interval_check_retry(struct mmu_interval_notifier *interval_sub, unsigned long seq) { /* Pairs with the WRITE_ONCE in mmu_interval_set_seq() */ return READ_ONCE(interval_sub->invalidate_seq) != seq; } extern void __mmu_notifier_subscriptions_destroy(struct mm_struct *mm); extern void __mmu_notifier_release(struct mm_struct *mm); extern int __mmu_notifier_clear_flush_young(struct mm_struct *mm, unsigned long start, unsigned long end); extern int __mmu_notifier_clear_young(struct mm_struct *mm, unsigned long start, unsigned long end); extern int __mmu_notifier_test_young(struct mm_struct *mm, unsigned long address); extern int __mmu_notifier_invalidate_range_start(struct mmu_notifier_range *r); extern void __mmu_notifier_invalidate_range_end(struct mmu_notifier_range *r); extern void __mmu_notifier_arch_invalidate_secondary_tlbs(struct mm_struct *mm, unsigned long start, unsigned long end); extern bool mmu_notifier_range_update_to_read_only(const struct mmu_notifier_range *range); static inline bool mmu_notifier_range_blockable(const struct mmu_notifier_range *range) { return (range->flags & MMU_NOTIFIER_RANGE_BLOCKABLE); } static inline void mmu_notifier_release(struct mm_struct *mm) { if (mm_has_notifiers(mm)) __mmu_notifier_release(mm); } static inline int mmu_notifier_clear_flush_young(struct mm_struct *mm, unsigned long start, unsigned long end) { if (mm_has_notifiers(mm)) return __mmu_notifier_clear_flush_young(mm, start, end); return 0; } static inline int mmu_notifier_clear_young(struct mm_struct *mm, unsigned long start, unsigned long end) { if (mm_has_notifiers(mm)) return __mmu_notifier_clear_young(mm, start, end); return 0; } static inline int mmu_notifier_test_young(struct mm_struct *mm, unsigned long address) { if (mm_has_notifiers(mm)) return __mmu_notifier_test_young(mm, address); return 0; } static inline void mmu_notifier_invalidate_range_start(struct mmu_notifier_range *range) { might_sleep(); lock_map_acquire(&__mmu_notifier_invalidate_range_start_map); if (mm_has_notifiers(range->mm)) { range->flags |= MMU_NOTIFIER_RANGE_BLOCKABLE; __mmu_notifier_invalidate_range_start(range); } lock_map_release(&__mmu_notifier_invalidate_range_start_map); } /* * This version of mmu_notifier_invalidate_range_start() avoids blocking, but it * can return an error if a notifier can't proceed without blocking, in which * case you're not allowed to modify PTEs in the specified range. * * This is mainly intended for OOM handling. */ static inline int __must_check mmu_notifier_invalidate_range_start_nonblock(struct mmu_notifier_range *range) { int ret = 0; lock_map_acquire(&__mmu_notifier_invalidate_range_start_map); if (mm_has_notifiers(range->mm)) { range->flags &= ~MMU_NOTIFIER_RANGE_BLOCKABLE; ret = __mmu_notifier_invalidate_range_start(range); } lock_map_release(&__mmu_notifier_invalidate_range_start_map); return ret; } static inline void mmu_notifier_invalidate_range_end(struct mmu_notifier_range *range) { if (mmu_notifier_range_blockable(range)) might_sleep(); if (mm_has_notifiers(range->mm)) __mmu_notifier_invalidate_range_end(range); } static inline void mmu_notifier_arch_invalidate_secondary_tlbs(struct mm_struct *mm, unsigned long start, unsigned long end) { if (mm_has_notifiers(mm)) __mmu_notifier_arch_invalidate_secondary_tlbs(mm, start, end); } static inline void mmu_notifier_subscriptions_init(struct mm_struct *mm) { mm->notifier_subscriptions = NULL; } static inline void mmu_notifier_subscriptions_destroy(struct mm_struct *mm) { if (mm_has_notifiers(mm)) __mmu_notifier_subscriptions_destroy(mm); } static inline void mmu_notifier_range_init(struct mmu_notifier_range *range, enum mmu_notifier_event event, unsigned flags, struct mm_struct *mm, unsigned long start, unsigned long end) { range->event = event; range->mm = mm; range->start = start; range->end = end; range->flags = flags; } static inline void mmu_notifier_range_init_owner( struct mmu_notifier_range *range, enum mmu_notifier_event event, unsigned int flags, struct mm_struct *mm, unsigned long start, unsigned long end, void *owner) { mmu_notifier_range_init(range, event, flags, mm, start, end); range->owner = owner; } #define ptep_clear_flush_young_notify(__vma, __address, __ptep) \ ({ \ int __young; \ struct vm_area_struct *___vma = __vma; \ unsigned long ___address = __address; \ __young = ptep_clear_flush_young(___vma, ___address, __ptep); \ __young |= mmu_notifier_clear_flush_young(___vma->vm_mm, \ ___address, \ ___address + \ PAGE_SIZE); \ __young; \ }) #define pmdp_clear_flush_young_notify(__vma, __address, __pmdp) \ ({ \ int __young; \ struct vm_area_struct *___vma = __vma; \ unsigned long ___address = __address; \ __young = pmdp_clear_flush_young(___vma, ___address, __pmdp); \ __young |= mmu_notifier_clear_flush_young(___vma->vm_mm, \ ___address, \ ___address + \ PMD_SIZE); \ __young; \ }) #define ptep_clear_young_notify(__vma, __address, __ptep) \ ({ \ int __young; \ struct vm_area_struct *___vma = __vma; \ unsigned long ___address = __address; \ __young = ptep_test_and_clear_young(___vma, ___address, __ptep);\ __young |= mmu_notifier_clear_young(___vma->vm_mm, ___address, \ ___address + PAGE_SIZE); \ __young; \ }) #define pmdp_clear_young_notify(__vma, __address, __pmdp) \ ({ \ int __young; \ struct vm_area_struct *___vma = __vma; \ unsigned long ___address = __address; \ __young = pmdp_test_and_clear_young(___vma, ___address, __pmdp);\ __young |= mmu_notifier_clear_young(___vma->vm_mm, ___address, \ ___address + PMD_SIZE); \ __young; \ }) #else /* CONFIG_MMU_NOTIFIER */ struct mmu_notifier_range { unsigned long start; unsigned long end; }; static inline void _mmu_notifier_range_init(struct mmu_notifier_range *range, unsigned long start, unsigned long end) { range->start = start; range->end = end; } #define mmu_notifier_range_init(range,event,flags,mm,start,end) \ _mmu_notifier_range_init(range, start, end) #define mmu_notifier_range_init_owner(range, event, flags, mm, start, \ end, owner) \ _mmu_notifier_range_init(range, start, end) static inline bool mmu_notifier_range_blockable(const struct mmu_notifier_range *range) { return true; } static inline int mm_has_notifiers(struct mm_struct *mm) { return 0; } static inline void mmu_notifier_release(struct mm_struct *mm) { } static inline int mmu_notifier_clear_flush_young(struct mm_struct *mm, unsigned long start, unsigned long end) { return 0; } static inline int mmu_notifier_clear_young(struct mm_struct *mm, unsigned long start, unsigned long end) { return 0; } static inline int mmu_notifier_test_young(struct mm_struct *mm, unsigned long address) { return 0; } static inline void mmu_notifier_invalidate_range_start(struct mmu_notifier_range *range) { } static inline int mmu_notifier_invalidate_range_start_nonblock(struct mmu_notifier_range *range) { return 0; } static inline void mmu_notifier_invalidate_range_end(struct mmu_notifier_range *range) { } static inline void mmu_notifier_arch_invalidate_secondary_tlbs(struct mm_struct *mm, unsigned long start, unsigned long end) { } static inline void mmu_notifier_subscriptions_init(struct mm_struct *mm) { } static inline void mmu_notifier_subscriptions_destroy(struct mm_struct *mm) { } #define mmu_notifier_range_update_to_read_only(r) false #define ptep_clear_flush_young_notify ptep_clear_flush_young #define pmdp_clear_flush_young_notify pmdp_clear_flush_young #define ptep_clear_young_notify ptep_test_and_clear_young #define pmdp_clear_young_notify pmdp_test_and_clear_young #define ptep_clear_flush_notify ptep_clear_flush #define pmdp_huge_clear_flush_notify pmdp_huge_clear_flush #define pudp_huge_clear_flush_notify pudp_huge_clear_flush static inline void mmu_notifier_synchronize(void) { } #endif /* CONFIG_MMU_NOTIFIER */ #endif /* _LINUX_MMU_NOTIFIER_H */ |
| 6 4 86 86 86 1 1 2 2 1 1 1 1 1 1 1 13 13 11 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 | // SPDX-License-Identifier: GPL-2.0-only /* * KVM dirty ring implementation * * Copyright 2019 Red Hat, Inc. */ #include <linux/kvm_host.h> #include <linux/kvm.h> #include <linux/vmalloc.h> #include <linux/kvm_dirty_ring.h> #include <trace/events/kvm.h> #include "kvm_mm.h" int __weak kvm_cpu_dirty_log_size(void) { return 0; } u32 kvm_dirty_ring_get_rsvd_entries(void) { return KVM_DIRTY_RING_RSVD_ENTRIES + kvm_cpu_dirty_log_size(); } bool kvm_use_dirty_bitmap(struct kvm *kvm) { lockdep_assert_held(&kvm->slots_lock); return !kvm->dirty_ring_size || kvm->dirty_ring_with_bitmap; } #ifndef CONFIG_NEED_KVM_DIRTY_RING_WITH_BITMAP bool kvm_arch_allow_write_without_running_vcpu(struct kvm *kvm) { return false; } #endif static u32 kvm_dirty_ring_used(struct kvm_dirty_ring *ring) { return READ_ONCE(ring->dirty_index) - READ_ONCE(ring->reset_index); } static bool kvm_dirty_ring_soft_full(struct kvm_dirty_ring *ring) { return kvm_dirty_ring_used(ring) >= ring->soft_limit; } static bool kvm_dirty_ring_full(struct kvm_dirty_ring *ring) { return kvm_dirty_ring_used(ring) >= ring->size; } static void kvm_reset_dirty_gfn(struct kvm *kvm, u32 slot, u64 offset, u64 mask) { struct kvm_memory_slot *memslot; int as_id, id; if (!mask) return; as_id = slot >> 16; id = (u16)slot; if (as_id >= kvm_arch_nr_memslot_as_ids(kvm) || id >= KVM_USER_MEM_SLOTS) return; memslot = id_to_memslot(__kvm_memslots(kvm, as_id), id); if (!memslot || (offset + __fls(mask)) >= memslot->npages) return; KVM_MMU_LOCK(kvm); kvm_arch_mmu_enable_log_dirty_pt_masked(kvm, memslot, offset, mask); KVM_MMU_UNLOCK(kvm); } int kvm_dirty_ring_alloc(struct kvm_dirty_ring *ring, int index, u32 size) { ring->dirty_gfns = vzalloc(size); if (!ring->dirty_gfns) return -ENOMEM; ring->size = size / sizeof(struct kvm_dirty_gfn); ring->soft_limit = ring->size - kvm_dirty_ring_get_rsvd_entries(); ring->dirty_index = 0; ring->reset_index = 0; ring->index = index; return 0; } static inline void kvm_dirty_gfn_set_invalid(struct kvm_dirty_gfn *gfn) { smp_store_release(&gfn->flags, 0); } static inline void kvm_dirty_gfn_set_dirtied(struct kvm_dirty_gfn *gfn) { gfn->flags = KVM_DIRTY_GFN_F_DIRTY; } static inline bool kvm_dirty_gfn_harvested(struct kvm_dirty_gfn *gfn) { return smp_load_acquire(&gfn->flags) & KVM_DIRTY_GFN_F_RESET; } int kvm_dirty_ring_reset(struct kvm *kvm, struct kvm_dirty_ring *ring) { u32 cur_slot, next_slot; u64 cur_offset, next_offset; unsigned long mask; int count = 0; struct kvm_dirty_gfn *entry; bool first_round = true; /* This is only needed to make compilers happy */ cur_slot = cur_offset = mask = 0; while (true) { entry = &ring->dirty_gfns[ring->reset_index & (ring->size - 1)]; if (!kvm_dirty_gfn_harvested(entry)) break; next_slot = READ_ONCE(entry->slot); next_offset = READ_ONCE(entry->offset); /* Update the flags to reflect that this GFN is reset */ kvm_dirty_gfn_set_invalid(entry); ring->reset_index++; count++; /* * Try to coalesce the reset operations when the guest is * scanning pages in the same slot. */ if (!first_round && next_slot == cur_slot) { s64 delta = next_offset - cur_offset; if (delta >= 0 && delta < BITS_PER_LONG) { mask |= 1ull << delta; continue; } /* Backwards visit, careful about overflows! */ if (delta > -BITS_PER_LONG && delta < 0 && (mask << -delta >> -delta) == mask) { cur_offset = next_offset; mask = (mask << -delta) | 1; continue; } } kvm_reset_dirty_gfn(kvm, cur_slot, cur_offset, mask); cur_slot = next_slot; cur_offset = next_offset; mask = 1; first_round = false; } kvm_reset_dirty_gfn(kvm, cur_slot, cur_offset, mask); /* * The request KVM_REQ_DIRTY_RING_SOFT_FULL will be cleared * by the VCPU thread next time when it enters the guest. */ trace_kvm_dirty_ring_reset(ring); return count; } void kvm_dirty_ring_push(struct kvm_vcpu *vcpu, u32 slot, u64 offset) { struct kvm_dirty_ring *ring = &vcpu->dirty_ring; struct kvm_dirty_gfn *entry; /* It should never get full */ WARN_ON_ONCE(kvm_dirty_ring_full(ring)); entry = &ring->dirty_gfns[ring->dirty_index & (ring->size - 1)]; entry->slot = slot; entry->offset = offset; /* * Make sure the data is filled in before we publish this to * the userspace program. There's no paired kernel-side reader. */ smp_wmb(); kvm_dirty_gfn_set_dirtied(entry); ring->dirty_index++; trace_kvm_dirty_ring_push(ring, slot, offset); if (kvm_dirty_ring_soft_full(ring)) kvm_make_request(KVM_REQ_DIRTY_RING_SOFT_FULL, vcpu); } bool kvm_dirty_ring_check_request(struct kvm_vcpu *vcpu) { /* * The VCPU isn't runnable when the dirty ring becomes soft full. * The KVM_REQ_DIRTY_RING_SOFT_FULL event is always set to prevent * the VCPU from running until the dirty pages are harvested and * the dirty ring is reset by userspace. */ if (kvm_check_request(KVM_REQ_DIRTY_RING_SOFT_FULL, vcpu) && kvm_dirty_ring_soft_full(&vcpu->dirty_ring)) { kvm_make_request(KVM_REQ_DIRTY_RING_SOFT_FULL, vcpu); vcpu->run->exit_reason = KVM_EXIT_DIRTY_RING_FULL; trace_kvm_dirty_ring_exit(vcpu); return true; } return false; } struct page *kvm_dirty_ring_get_page(struct kvm_dirty_ring *ring, u32 offset) { return vmalloc_to_page((void *)ring->dirty_gfns + offset * PAGE_SIZE); } void kvm_dirty_ring_free(struct kvm_dirty_ring *ring) { vfree(ring->dirty_gfns); ring->dirty_gfns = NULL; } |
| 3 3 36 36 36 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 | // SPDX-License-Identifier: GPL-2.0-or-later /* * linux/drivers/net/netconsole.c * * Copyright (C) 2001 Ingo Molnar <mingo@redhat.com> * * This file contains the implementation of an IRQ-safe, crash-safe * kernel console implementation that outputs kernel messages to the * network. * * Modification history: * * 2001-09-17 started by Ingo Molnar. * 2003-08-11 2.6 port by Matt Mackall * simplified options * generic card hooks * works non-modular * 2003-09-07 rewritten with netpoll api */ /**************************************************************** * ****************************************************************/ #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt #include <linux/mm.h> #include <linux/init.h> #include <linux/module.h> #include <linux/slab.h> #include <linux/console.h> #include <linux/moduleparam.h> #include <linux/kernel.h> #include <linux/string.h> #include <linux/netpoll.h> #include <linux/inet.h> #include <linux/configfs.h> #include <linux/etherdevice.h> #include <linux/utsname.h> #include <linux/rtnetlink.h> MODULE_AUTHOR("Matt Mackall <mpm@selenic.com>"); MODULE_DESCRIPTION("Console driver for network interfaces"); MODULE_LICENSE("GPL"); #define MAX_PARAM_LENGTH 256 #define MAX_USERDATA_ENTRY_LENGTH 256 #define MAX_USERDATA_VALUE_LENGTH 200 /* The number 3 comes from userdata entry format characters (' ', '=', '\n') */ #define MAX_USERDATA_NAME_LENGTH (MAX_USERDATA_ENTRY_LENGTH - \ MAX_USERDATA_VALUE_LENGTH - 3) #define MAX_USERDATA_ITEMS 16 #define MAX_PRINT_CHUNK 1000 static char config[MAX_PARAM_LENGTH]; module_param_string(netconsole, config, MAX_PARAM_LENGTH, 0); MODULE_PARM_DESC(netconsole, " netconsole=[src-port]@[src-ip]/[dev],[tgt-port]@<tgt-ip>/[tgt-macaddr]"); static bool oops_only; module_param(oops_only, bool, 0600); MODULE_PARM_DESC(oops_only, "Only log oops messages"); #define NETCONSOLE_PARAM_TARGET_PREFIX "cmdline" #ifndef MODULE static int __init option_setup(char *opt) { strscpy(config, opt, MAX_PARAM_LENGTH); return 1; } __setup("netconsole=", option_setup); #endif /* MODULE */ /* Linked list of all configured targets */ static LIST_HEAD(target_list); /* target_cleanup_list is used to track targets that need to be cleaned outside * of target_list_lock. It should be cleaned in the same function it is * populated. */ static LIST_HEAD(target_cleanup_list); /* This needs to be a spinlock because write_msg() cannot sleep */ static DEFINE_SPINLOCK(target_list_lock); /* This needs to be a mutex because netpoll_cleanup might sleep */ static DEFINE_MUTEX(target_cleanup_list_lock); /* * Console driver for extended netconsoles. Registered on the first use to * avoid unnecessarily enabling ext message formatting. */ static struct console netconsole_ext; /** * struct netconsole_target - Represents a configured netconsole target. * @list: Links this target into the target_list. * @group: Links us into the configfs subsystem hierarchy. * @userdata_group: Links to the userdata configfs hierarchy * @userdata_complete: Cached, formatted string of append * @userdata_length: String length of userdata_complete * @enabled: On / off knob to enable / disable target. * Visible from userspace (read-write). * We maintain a strict 1:1 correspondence between this and * whether the corresponding netpoll is active or inactive. * Also, other parameters of a target may be modified at * runtime only when it is disabled (enabled == 0). * @extended: Denotes whether console is extended or not. * @release: Denotes whether kernel release version should be prepended * to the message. Depends on extended console. * @np: The netpoll structure for this target. * Contains the other userspace visible parameters: * dev_name (read-write) * local_port (read-write) * remote_port (read-write) * local_ip (read-write) * remote_ip (read-write) * local_mac (read-only) * remote_mac (read-write) */ struct netconsole_target { struct list_head list; #ifdef CONFIG_NETCONSOLE_DYNAMIC struct config_group group; struct config_group userdata_group; char userdata_complete[MAX_USERDATA_ENTRY_LENGTH * MAX_USERDATA_ITEMS]; size_t userdata_length; #endif bool enabled; bool extended; bool release; struct netpoll np; }; #ifdef CONFIG_NETCONSOLE_DYNAMIC static struct configfs_subsystem netconsole_subsys; static DEFINE_MUTEX(dynamic_netconsole_mutex); static int __init dynamic_netconsole_init(void) { config_group_init(&netconsole_subsys.su_group); mutex_init(&netconsole_subsys.su_mutex); return configfs_register_subsystem(&netconsole_subsys); } static void __exit dynamic_netconsole_exit(void) { configfs_unregister_subsystem(&netconsole_subsys); } /* * Targets that were created by parsing the boot/module option string * do not exist in the configfs hierarchy (and have NULL names) and will * never go away, so make these a no-op for them. */ static void netconsole_target_get(struct netconsole_target *nt) { if (config_item_name(&nt->group.cg_item)) config_group_get(&nt->group); } static void netconsole_target_put(struct netconsole_target *nt) { if (config_item_name(&nt->group.cg_item)) config_group_put(&nt->group); } #else /* !CONFIG_NETCONSOLE_DYNAMIC */ static int __init dynamic_netconsole_init(void) { return 0; } static void __exit dynamic_netconsole_exit(void) { } /* * No danger of targets going away from under us when dynamic * reconfigurability is off. */ static void netconsole_target_get(struct netconsole_target *nt) { } static void netconsole_target_put(struct netconsole_target *nt) { } static void populate_configfs_item(struct netconsole_target *nt, int cmdline_count) { } #endif /* CONFIG_NETCONSOLE_DYNAMIC */ /* Allocate and initialize with defaults. * Note that these targets get their config_item fields zeroed-out. */ static struct netconsole_target *alloc_and_init(void) { struct netconsole_target *nt; nt = kzalloc(sizeof(*nt), GFP_KERNEL); if (!nt) return nt; if (IS_ENABLED(CONFIG_NETCONSOLE_EXTENDED_LOG)) nt->extended = true; if (IS_ENABLED(CONFIG_NETCONSOLE_PREPEND_RELEASE)) nt->release = true; nt->np.name = "netconsole"; strscpy(nt->np.dev_name, "eth0", IFNAMSIZ); nt->np.local_port = 6665; nt->np.remote_port = 6666; eth_broadcast_addr(nt->np.remote_mac); return nt; } /* Clean up every target in the cleanup_list and move the clean targets back to * the main target_list. */ static void netconsole_process_cleanups_core(void) { struct netconsole_target *nt, *tmp; unsigned long flags; /* The cleanup needs RTNL locked */ ASSERT_RTNL(); mutex_lock(&target_cleanup_list_lock); list_for_each_entry_safe(nt, tmp, &target_cleanup_list, list) { /* all entries in the cleanup_list needs to be disabled */ WARN_ON_ONCE(nt->enabled); do_netpoll_cleanup(&nt->np); /* moved the cleaned target to target_list. Need to hold both * locks */ spin_lock_irqsave(&target_list_lock, flags); list_move(&nt->list, &target_list); spin_unlock_irqrestore(&target_list_lock, flags); } WARN_ON_ONCE(!list_empty(&target_cleanup_list)); mutex_unlock(&target_cleanup_list_lock); } #ifdef CONFIG_NETCONSOLE_DYNAMIC /* * Our subsystem hierarchy is: * * /sys/kernel/config/netconsole/ * | * <target>/ * | enabled * | release * | dev_name * | local_port * | remote_port * | local_ip * | remote_ip * | local_mac * | remote_mac * | userdata/ * | <key>/ * | value * | ... * | * <target>/... */ static struct netconsole_target *to_target(struct config_item *item) { struct config_group *cfg_group; cfg_group = to_config_group(item); if (!cfg_group) return NULL; return container_of(to_config_group(item), struct netconsole_target, group); } /* Do the list cleanup with the rtnl lock hold. rtnl lock is necessary because * netdev might be cleaned-up by calling __netpoll_cleanup(), */ static void netconsole_process_cleanups(void) { /* rtnl lock is called here, because it has precedence over * target_cleanup_list_lock mutex and target_cleanup_list */ rtnl_lock(); netconsole_process_cleanups_core(); rtnl_unlock(); } /* Get rid of possible trailing newline, returning the new length */ static void trim_newline(char *s, size_t maxlen) { size_t len; len = strnlen(s, maxlen); if (s[len - 1] == '\n') s[len - 1] = '\0'; } /* * Attribute operations for netconsole_target. */ static ssize_t enabled_show(struct config_item *item, char *buf) { return sysfs_emit(buf, "%d\n", to_target(item)->enabled); } static ssize_t extended_show(struct config_item *item, char *buf) { return sysfs_emit(buf, "%d\n", to_target(item)->extended); } static ssize_t release_show(struct config_item *item, char *buf) { return sysfs_emit(buf, "%d\n", to_target(item)->release); } static ssize_t dev_name_show(struct config_item *item, char *buf) { return sysfs_emit(buf, "%s\n", to_target(item)->np.dev_name); } static ssize_t local_port_show(struct config_item *item, char *buf) { return sysfs_emit(buf, "%d\n", to_target(item)->np.local_port); } static ssize_t remote_port_show(struct config_item *item, char *buf) { return sysfs_emit(buf, "%d\n", to_target(item)->np.remote_port); } static ssize_t local_ip_show(struct config_item *item, char *bu |