| 8232 8220 8240 8230 8223 8229 8216 8284 8283 | 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 | // SPDX-License-Identifier: GPL-2.0-only /* * AppArmor security module * * This file contains AppArmor network mediation * * Copyright (C) 1998-2008 Novell/SUSE * Copyright 2009-2017 Canonical Ltd. */ #include "include/apparmor.h" #include "include/audit.h" #include "include/cred.h" #include "include/label.h" #include "include/net.h" #include "include/policy.h" #include "include/secid.h" #include "net_names.h" struct aa_sfs_entry aa_sfs_entry_network[] = { AA_SFS_FILE_STRING("af_mask", AA_SFS_AF_MASK), { } }; static const char * const net_mask_names[] = { "unknown", "send", "receive", "unknown", "create", "shutdown", "connect", "unknown", "setattr", "getattr", "setcred", "getcred", "chmod", "chown", "chgrp", "lock", "mmap", "mprot", "unknown", "unknown", "accept", "bind", "listen", "unknown", "setopt", "getopt", "unknown", "unknown", "unknown", "unknown", "unknown", "unknown", }; /* audit callback for net specific fields */ void audit_net_cb(struct audit_buffer *ab, void *va) { struct common_audit_data *sa = va; struct apparmor_audit_data *ad = aad(sa); if (address_family_names[sa->u.net->family]) audit_log_format(ab, " family=\"%s\"", address_family_names[sa->u.net->family]); else audit_log_format(ab, " family=\"unknown(%d)\"", sa->u.net->family); if (sock_type_names[ad->net.type]) audit_log_format(ab, " sock_type=\"%s\"", sock_type_names[ad->net.type]); else audit_log_format(ab, " sock_type=\"unknown(%d)\"", ad->net.type); audit_log_format(ab, " protocol=%d", ad->net.protocol); if (ad->request & NET_PERMS_MASK) { audit_log_format(ab, " requested_mask="); aa_audit_perm_mask(ab, ad->request, NULL, 0, net_mask_names, NET_PERMS_MASK); if (ad->denied & NET_PERMS_MASK) { audit_log_format(ab, " denied_mask="); aa_audit_perm_mask(ab, ad->denied, NULL, 0, net_mask_names, NET_PERMS_MASK); } } if (ad->peer) { audit_log_format(ab, " peer="); aa_label_xaudit(ab, labels_ns(ad->subj_label), ad->peer, FLAGS_NONE, GFP_ATOMIC); } } /* Generic af perm */ int aa_profile_af_perm(struct aa_profile *profile, struct apparmor_audit_data *ad, u32 request, u16 family, int type) { struct aa_ruleset *rules = list_first_entry(&profile->rules, typeof(*rules), list); struct aa_perms perms = { }; aa_state_t state; __be16 buffer[2]; AA_BUG(family >= AF_MAX); AA_BUG(type < 0 || type >= SOCK_MAX); if (profile_unconfined(profile)) return 0; state = RULE_MEDIATES(rules, AA_CLASS_NET); if (!state) return 0; buffer[0] = cpu_to_be16(family); buffer[1] = cpu_to_be16((u16) type); state = aa_dfa_match_len(rules->policy->dfa, state, (char *) &buffer, 4); perms = *aa_lookup_perms(rules->policy, state); aa_apply_modes_to_perms(profile, &perms); return aa_check_perms(profile, &perms, request, ad, audit_net_cb); } int aa_af_perm(const struct cred *subj_cred, struct aa_label *label, const char *op, u32 request, u16 family, int type, int protocol) { struct aa_profile *profile; DEFINE_AUDIT_NET(ad, op, NULL, family, type, protocol); return fn_for_each_confined(label, profile, aa_profile_af_perm(profile, &ad, request, family, type)); } static int aa_label_sk_perm(const struct cred *subj_cred, struct aa_label *label, const char *op, u32 request, struct sock *sk) { struct aa_sk_ctx *ctx = aa_sock(sk); int error = 0; AA_BUG(!label); AA_BUG(!sk); if (ctx->label != kernel_t && !unconfined(label)) { struct aa_profile *profile; DEFINE_AUDIT_SK(ad, op, sk); ad.subj_cred = subj_cred; error = fn_for_each_confined(label, profile, aa_profile_af_sk_perm(profile, &ad, request, sk)); } return error; } int aa_sk_perm(const char *op, u32 request, struct sock *sk) { struct aa_label *label; int error; AA_BUG(!sk); AA_BUG(in_interrupt()); /* TODO: switch to begin_current_label ???? */ label = begin_current_label_crit_section(); error = aa_label_sk_perm(current_cred(), label, op, request, sk); end_current_label_crit_section(label); return error; } int aa_sock_file_perm(const struct cred *subj_cred, struct aa_label *label, const char *op, u32 request, struct socket *sock) { AA_BUG(!label); AA_BUG(!sock); AA_BUG(!sock->sk); return aa_label_sk_perm(subj_cred, label, op, request, sock->sk); } #ifdef CONFIG_NETWORK_SECMARK static int apparmor_secmark_init(struct aa_secmark *secmark) { struct aa_label *label; if (secmark->label[0] == '*') { secmark->secid = AA_SECID_WILDCARD; return 0; } label = aa_label_strn_parse(&root_ns->unconfined->label, secmark->label, strlen(secmark->label), GFP_ATOMIC, false, false); if (IS_ERR(label)) return PTR_ERR(label); secmark->secid = label->secid; return 0; } static int aa_secmark_perm(struct aa_profile *profile, u32 request, u32 secid, struct apparmor_audit_data *ad) { int i, ret; struct aa_perms perms = { }; struct aa_ruleset *rules = list_first_entry(&profile->rules, typeof(*rules), list); if (rules->secmark_count == 0) return 0; for (i = 0; i < rules->secmark_count; i++) { if (!rules->secmark[i].secid) { ret = apparmor_secmark_init(&rules->secmark[i]); if (ret) return ret; } if (rules->secmark[i].secid == secid || rules->secmark[i].secid == AA_SECID_WILDCARD) { if (rules->secmark[i].deny) perms.deny = ALL_PERMS_MASK; else perms.allow = ALL_PERMS_MASK; if (rules->secmark[i].audit) perms.audit = ALL_PERMS_MASK; } } aa_apply_modes_to_perms(profile, &perms); return aa_check_perms(profile, &perms, request, ad, audit_net_cb); } int apparmor_secmark_check(struct aa_label *label, char *op, u32 request, u32 secid, const struct sock *sk) { struct aa_profile *profile; DEFINE_AUDIT_SK(ad, op, sk); return fn_for_each_confined(label, profile, aa_secmark_perm(profile, request, secid, &ad)); } #endif |
| 1903 1900 | 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 | // SPDX-License-Identifier: GPL-2.0-or-later /* * Derived from arch/ppc/mm/extable.c and arch/i386/mm/extable.c. * * Copyright (C) 2004 Paul Mackerras, IBM Corp. */ #include <linux/bsearch.h> #include <linux/module.h> #include <linux/init.h> #include <linux/sort.h> #include <linux/uaccess.h> #include <linux/extable.h> #ifndef ARCH_HAS_RELATIVE_EXTABLE #define ex_to_insn(x) ((x)->insn) #else static inline unsigned long ex_to_insn(const struct exception_table_entry *x) { return (unsigned long)&x->insn + x->insn; } #endif #ifndef ARCH_HAS_RELATIVE_EXTABLE #define swap_ex NULL #else static void swap_ex(void *a, void *b, int size) { struct exception_table_entry *x = a, *y = b, tmp; int delta = b - a; tmp = *x; x->insn = y->insn + delta; y->insn = tmp.insn - delta; #ifdef swap_ex_entry_fixup swap_ex_entry_fixup(x, y, tmp, delta); #else x->fixup = y->fixup + delta; y->fixup = tmp.fixup - delta; #endif } #endif /* ARCH_HAS_RELATIVE_EXTABLE */ /* * The exception table needs to be sorted so that the binary * search that we use to find entries in it works properly. * This is used both for the kernel exception table and for * the exception tables of modules that get loaded. */ static int cmp_ex_sort(const void *a, const void *b) { const struct exception_table_entry *x = a, *y = b; /* avoid overflow */ if (ex_to_insn(x) > ex_to_insn(y)) return 1; if (ex_to_insn(x) < ex_to_insn(y)) return -1; return 0; } void sort_extable(struct exception_table_entry *start, struct exception_table_entry *finish) { sort(start, finish - start, sizeof(struct exception_table_entry), cmp_ex_sort, swap_ex); } #ifdef CONFIG_MODULES /* * If the exception table is sorted, any referring to the module init * will be at the beginning or the end. */ void trim_init_extable(struct module *m) { /*trim the beginning*/ while (m->num_exentries && within_module_init(ex_to_insn(&m->extable[0]), m)) { m->extable++; m->num_exentries--; } /*trim the end*/ while (m->num_exentries && within_module_init(ex_to_insn(&m->extable[m->num_exentries - 1]), m)) m->num_exentries--; } #endif /* CONFIG_MODULES */ static int cmp_ex_search(const void *key, const void *elt) { const struct exception_table_entry *_elt = elt; unsigned long _key = *(unsigned long *)key; /* avoid overflow */ if (_key > ex_to_insn(_elt)) return 1; if (_key < ex_to_insn(_elt)) return -1; return 0; } /* * Search one exception table for an entry corresponding to the * given instruction address, and return the address of the entry, * or NULL if none is found. * We use a binary search, and thus we assume that the table is * already sorted. */ const struct exception_table_entry * search_extable(const struct exception_table_entry *base, const size_t num, unsigned long value) { return bsearch(&value, base, num, sizeof(struct exception_table_entry), cmp_ex_search); } |
| 1 337 | 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 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef __LINUX_NETLINK_H #define __LINUX_NETLINK_H #include <linux/capability.h> #include <linux/skbuff.h> #include <linux/export.h> #include <net/scm.h> #include <uapi/linux/netlink.h> struct net; void do_trace_netlink_extack(const char *msg); static inline struct nlmsghdr *nlmsg_hdr(const struct sk_buff *skb) { return (struct nlmsghdr *)skb->data; } enum netlink_skb_flags { NETLINK_SKB_DST = 0x8, /* Dst set in sendto or sendmsg */ }; struct netlink_skb_parms { struct scm_creds creds; /* Skb credentials */ __u32 portid; __u32 dst_group; __u32 flags; struct sock *sk; bool nsid_is_set; int nsid; }; #define NETLINK_CB(skb) (*(struct netlink_skb_parms*)&((skb)->cb)) #define NETLINK_CREDS(skb) (&NETLINK_CB((skb)).creds) #define NETLINK_CTX_SIZE 48 void netlink_table_grab(void); void netlink_table_ungrab(void); #define NL_CFG_F_NONROOT_RECV (1 << 0) #define NL_CFG_F_NONROOT_SEND (1 << 1) /* optional Netlink kernel configuration parameters */ struct netlink_kernel_cfg { unsigned int groups; unsigned int flags; void (*input)(struct sk_buff *skb); int (*bind)(struct net *net, int group); void (*unbind)(struct net *net, int group); void (*release) (struct sock *sk, unsigned long *groups); }; struct sock *__netlink_kernel_create(struct net *net, int unit, struct module *module, struct netlink_kernel_cfg *cfg); static inline struct sock * netlink_kernel_create(struct net *net, int unit, struct netlink_kernel_cfg *cfg) { return __netlink_kernel_create(net, unit, THIS_MODULE, cfg); } /* this can be increased when necessary - don't expose to userland */ #define NETLINK_MAX_COOKIE_LEN 20 #define NETLINK_MAX_FMTMSG_LEN 80 /** * struct netlink_ext_ack - netlink extended ACK report struct * @_msg: message string to report - don't access directly, use * %NL_SET_ERR_MSG * @bad_attr: attribute with error * @policy: policy for a bad attribute * @miss_type: attribute type which was missing * @miss_nest: nest missing an attribute (%NULL if missing top level attr) * @cookie: cookie data to return to userspace (for success) * @cookie_len: actual cookie data length * @_msg_buf: output buffer for formatted message strings - don't access * directly, use %NL_SET_ERR_MSG_FMT */ struct netlink_ext_ack { const char *_msg; const struct nlattr *bad_attr; const struct nla_policy *policy; const struct nlattr *miss_nest; u16 miss_type; u8 cookie[NETLINK_MAX_COOKIE_LEN]; u8 cookie_len; char _msg_buf[NETLINK_MAX_FMTMSG_LEN]; }; /* Always use this macro, this allows later putting the * message into a separate section or such for things * like translation or listing all possible messages. * If string formatting is needed use NL_SET_ERR_MSG_FMT. */ #define NL_SET_ERR_MSG(extack, msg) do { \ static const char __msg[] = msg; \ struct netlink_ext_ack *__extack = (extack); \ \ do_trace_netlink_extack(__msg); \ \ if (__extack) \ __extack->_msg = __msg; \ } while (0) /* We splice fmt with %s at each end even in the snprintf so that both calls * can use the same string constant, avoiding its duplication in .ro */ #define NL_SET_ERR_MSG_FMT(extack, fmt, args...) do { \ struct netlink_ext_ack *__extack = (extack); \ \ if (!__extack) \ break; \ if (snprintf(__extack->_msg_buf, NETLINK_MAX_FMTMSG_LEN, \ "%s" fmt "%s", "", ##args, "") >= \ NETLINK_MAX_FMTMSG_LEN) \ net_warn_ratelimited("%s" fmt "%s", "truncated extack: ", \ ##args, "\n"); \ \ do_trace_netlink_extack(__extack->_msg_buf); \ \ __extack->_msg = __extack->_msg_buf; \ } while (0) #define NL_SET_ERR_MSG_MOD(extack, msg) \ NL_SET_ERR_MSG((extack), KBUILD_MODNAME ": " msg) #define NL_SET_ERR_MSG_FMT_MOD(extack, fmt, args...) \ NL_SET_ERR_MSG_FMT((extack), KBUILD_MODNAME ": " fmt, ##args) #define NL_SET_ERR_MSG_WEAK(extack, msg) do { \ if ((extack) && !(extack)->_msg) \ NL_SET_ERR_MSG((extack), msg); \ } while (0) #define NL_SET_ERR_MSG_WEAK_MOD(extack, msg) do { \ if ((extack) && !(extack)->_msg) \ NL_SET_ERR_MSG_MOD((extack), msg); \ } while (0) #define NL_SET_BAD_ATTR_POLICY(extack, attr, pol) do { \ if ((extack)) { \ (extack)->bad_attr = (attr); \ (extack)->policy = (pol); \ } \ } while (0) #define NL_SET_BAD_ATTR(extack, attr) NL_SET_BAD_ATTR_POLICY(extack, attr, NULL) #define NL_SET_ERR_MSG_ATTR_POL(extack, attr, pol, msg) do { \ static const char __msg[] = msg; \ struct netlink_ext_ack *__extack = (extack); \ \ do_trace_netlink_extack(__msg); \ \ if (__extack) { \ __extack->_msg = __msg; \ __extack->bad_attr = (attr); \ __extack->policy = (pol); \ } \ } while (0) #define NL_SET_ERR_MSG_ATTR_POL_FMT(extack, attr, pol, fmt, args...) do { \ struct netlink_ext_ack *__extack = (extack); \ \ if (!__extack) \ break; \ \ if (snprintf(__extack->_msg_buf, NETLINK_MAX_FMTMSG_LEN, \ "%s" fmt "%s", "", ##args, "") >= \ NETLINK_MAX_FMTMSG_LEN) \ net_warn_ratelimited("%s" fmt "%s", "truncated extack: ", \ ##args, "\n"); \ \ do_trace_netlink_extack(__extack->_msg_buf); \ \ __extack->_msg = __extack->_msg_buf; \ __extack->bad_attr = (attr); \ __extack->policy = (pol); \ } while (0) #define NL_SET_ERR_MSG_ATTR(extack, attr, msg) \ NL_SET_ERR_MSG_ATTR_POL(extack, attr, NULL, msg) #define NL_SET_ERR_MSG_ATTR_FMT(extack, attr, msg, args...) \ NL_SET_ERR_MSG_ATTR_POL_FMT(extack, attr, NULL, msg, ##args) #define NL_SET_ERR_ATTR_MISS(extack, nest, type) do { \ struct netlink_ext_ack *__extack = (extack); \ \ if (__extack) { \ __extack->miss_nest = (nest); \ __extack->miss_type = (type); \ } \ } while (0) #define NL_REQ_ATTR_CHECK(extack, nest, tb, type) ({ \ struct nlattr **__tb = (tb); \ u32 __attr = (type); \ int __retval; \ \ __retval = !__tb[__attr]; \ if (__retval) \ NL_SET_ERR_ATTR_MISS((extack), (nest), __attr); \ __retval; \ }) static inline void nl_set_extack_cookie_u64(struct netlink_ext_ack *extack, u64 cookie) { if (!extack) return; memcpy(extack->cookie, &cookie, sizeof(cookie)); extack->cookie_len = sizeof(cookie); } void netlink_kernel_release(struct sock *sk); int __netlink_change_ngroups(struct sock *sk, unsigned int groups); int netlink_change_ngroups(struct sock *sk, unsigned int groups); void __netlink_clear_multicast_users(struct sock *sk, unsigned int group); void netlink_ack(struct sk_buff *in_skb, struct nlmsghdr *nlh, int err, const struct netlink_ext_ack *extack); int netlink_has_listeners(struct sock *sk, unsigned int group); bool netlink_strict_get_check(struct sk_buff *skb); int netlink_unicast(struct sock *ssk, struct sk_buff *skb, __u32 portid, int nonblock); int netlink_broadcast(struct sock *ssk, struct sk_buff *skb, __u32 portid, __u32 group, gfp_t allocation); typedef int (*netlink_filter_fn)(struct sock *dsk, struct sk_buff *skb, void *data); int netlink_broadcast_filtered(struct sock *ssk, struct sk_buff *skb, __u32 portid, __u32 group, gfp_t allocation, netlink_filter_fn filter, void *filter_data); int netlink_set_err(struct sock *ssk, __u32 portid, __u32 group, int code); int netlink_register_notifier(struct notifier_block *nb); int netlink_unregister_notifier(struct notifier_block *nb); /* finegrained unicast helpers: */ struct sock *netlink_getsockbyfd(int fd); int netlink_attachskb(struct sock *sk, struct sk_buff *skb, long *timeo, struct sock *ssk); void netlink_detachskb(struct sock *sk, struct sk_buff *skb); int netlink_sendskb(struct sock *sk, struct sk_buff *skb); static inline struct sk_buff * netlink_skb_clone(struct sk_buff *skb, gfp_t gfp_mask) { struct sk_buff *nskb; nskb = skb_clone(skb, gfp_mask); if (!nskb) return NULL; /* This is a large skb, set destructor callback to release head */ if (is_vmalloc_addr(skb->head)) nskb->destructor = skb->destructor; return nskb; } /* * skb should fit one page. This choice is good for headerless malloc. * But we should limit to 8K so that userspace does not have to * use enormous buffer sizes on recvmsg() calls just to avoid * MSG_TRUNC when PAGE_SIZE is very large. */ #if PAGE_SIZE < 8192UL #define NLMSG_GOODSIZE SKB_WITH_OVERHEAD(PAGE_SIZE) #else #define NLMSG_GOODSIZE SKB_WITH_OVERHEAD(8192UL) #endif #define NLMSG_DEFAULT_SIZE (NLMSG_GOODSIZE - NLMSG_HDRLEN) struct netlink_callback { struct sk_buff *skb; const struct nlmsghdr *nlh; int (*dump)(struct sk_buff * skb, struct netlink_callback *cb); int (*done)(struct netlink_callback *cb); void *data; /* the module that dump function belong to */ struct module *module; struct netlink_ext_ack *extack; u16 family; u16 answer_flags; u32 min_dump_alloc; unsigned int prev_seq, seq; int flags; bool strict_check; union { u8 ctx[NETLINK_CTX_SIZE]; /* args is deprecated. Cast a struct over ctx instead * for proper type safety. */ long args[6]; }; }; #define NL_ASSERT_CTX_FITS(type_name) \ BUILD_BUG_ON(sizeof(type_name) > \ sizeof_field(struct netlink_callback, ctx)) struct netlink_notify { struct net *net; u32 portid; int protocol; }; struct nlmsghdr * __nlmsg_put(struct sk_buff *skb, u32 portid, u32 seq, int type, int len, int flags); struct netlink_dump_control { int (*start)(struct netlink_callback *); int (*dump)(struct sk_buff *skb, struct netlink_callback *); int (*done)(struct netlink_callback *); struct netlink_ext_ack *extack; void *data; struct module *module; u32 min_dump_alloc; int flags; }; int __netlink_dump_start(struct sock *ssk, struct sk_buff *skb, const struct nlmsghdr *nlh, struct netlink_dump_control *control); static inline int netlink_dump_start(struct sock *ssk, struct sk_buff *skb, const struct nlmsghdr *nlh, struct netlink_dump_control *control) { if (!control->module) control->module = THIS_MODULE; return __netlink_dump_start(ssk, skb, nlh, control); } struct netlink_tap { struct net_device *dev; struct module *module; struct list_head list; }; int netlink_add_tap(struct netlink_tap *nt); int netlink_remove_tap(struct netlink_tap *nt); bool __netlink_ns_capable(const struct netlink_skb_parms *nsp, struct user_namespace *ns, int cap); bool netlink_ns_capable(const struct sk_buff *skb, struct user_namespace *ns, int cap); bool netlink_capable(const struct sk_buff *skb, int cap); bool netlink_net_capable(const struct sk_buff *skb, int cap); struct sk_buff *netlink_alloc_large_skb(unsigned int size, int broadcast); #endif /* __LINUX_NETLINK_H */ |
| 160 160 160 159 558 559 436 435 436 436 436 436 566 565 436 566 159 160 158 159 562 562 440 440 440 440 57 564 563 565 440 564 159 156 4 590 147 147 603 432 153 153 431 15 418 58 | 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 | // SPDX-License-Identifier: GPL-2.0-or-later /* * net-sysfs.c - network device class and attributes * * Copyright (c) 2003 Stephen Hemminger <shemminger@osdl.org> */ #include <linux/capability.h> #include <linux/kernel.h> #include <linux/netdevice.h> #include <linux/if_arp.h> #include <linux/slab.h> #include <linux/sched/signal.h> #include <linux/sched/isolation.h> #include <linux/nsproxy.h> #include <net/sock.h> #include <net/net_namespace.h> #include <linux/rtnetlink.h> #include <linux/vmalloc.h> #include <linux/export.h> #include <linux/jiffies.h> #include <linux/pm_runtime.h> #include <linux/of.h> #include <linux/of_net.h> #include <linux/cpu.h> #include <net/netdev_rx_queue.h> #include <net/rps.h> #include "dev.h" #include "net-sysfs.h" #ifdef CONFIG_SYSFS static const char fmt_hex[] = "%#x\n"; static const char fmt_dec[] = "%d\n"; static const char fmt_uint[] = "%u\n"; static const char fmt_ulong[] = "%lu\n"; static const char fmt_u64[] = "%llu\n"; /* Caller holds RTNL, netdev->lock or RCU */ static inline int dev_isalive(const struct net_device *dev) { return READ_ONCE(dev->reg_state) <= NETREG_REGISTERED; } /* use same locking rules as GIF* ioctl's */ static ssize_t netdev_show(const struct device *dev, struct device_attribute *attr, char *buf, ssize_t (*format)(const struct net_device *, char *)) { struct net_device *ndev = to_net_dev(dev); ssize_t ret = -EINVAL; rcu_read_lock(); if (dev_isalive(ndev)) ret = (*format)(ndev, buf); rcu_read_unlock(); return ret; } /* generate a show function for simple field */ #define NETDEVICE_SHOW(field, format_string) \ static ssize_t format_##field(const struct net_device *dev, char *buf) \ { \ return sysfs_emit(buf, format_string, READ_ONCE(dev->field)); \ } \ static ssize_t field##_show(struct device *dev, \ struct device_attribute *attr, char *buf) \ { \ return netdev_show(dev, attr, buf, format_##field); \ } \ #define NETDEVICE_SHOW_RO(field, format_string) \ NETDEVICE_SHOW(field, format_string); \ static DEVICE_ATTR_RO(field) #define NETDEVICE_SHOW_RW(field, format_string) \ NETDEVICE_SHOW(field, format_string); \ static DEVICE_ATTR_RW(field) /* use same locking and permission rules as SIF* ioctl's */ static ssize_t netdev_store(struct device *dev, struct device_attribute *attr, const char *buf, size_t len, int (*set)(struct net_device *, unsigned long)) { struct net_device *netdev = to_net_dev(dev); struct net *net = dev_net(netdev); unsigned long new; int ret; if (!ns_capable(net->user_ns, CAP_NET_ADMIN)) return -EPERM; ret = kstrtoul(buf, 0, &new); if (ret) goto err; if (!rtnl_trylock()) return restart_syscall(); if (dev_isalive(netdev)) { ret = (*set)(netdev, new); if (ret == 0) ret = len; } rtnl_unlock(); err: return ret; } /* Same as netdev_store() but takes netdev_lock() instead of rtnl_lock() */ static ssize_t netdev_lock_store(struct device *dev, struct device_attribute *attr, const char *buf, size_t len, int (*set)(struct net_device *, unsigned long)) { struct net_device *netdev = to_net_dev(dev); struct net *net = dev_net(netdev); unsigned long new; int ret; if (!ns_capable(net->user_ns, CAP_NET_ADMIN)) return -EPERM; ret = kstrtoul(buf, 0, &new); if (ret) return ret; netdev_lock(netdev); if (dev_isalive(netdev)) { ret = (*set)(netdev, new); if (ret == 0) ret = len; } netdev_unlock(netdev); return ret; } NETDEVICE_SHOW_RO(dev_id, fmt_hex); NETDEVICE_SHOW_RO(dev_port, fmt_dec); NETDEVICE_SHOW_RO(addr_assign_type, fmt_dec); NETDEVICE_SHOW_RO(addr_len, fmt_dec); NETDEVICE_SHOW_RO(ifindex, fmt_dec); NETDEVICE_SHOW_RO(type, fmt_dec); NETDEVICE_SHOW_RO(link_mode, fmt_dec); static ssize_t iflink_show(struct device *dev, struct device_attribute *attr, char *buf) { struct net_device *ndev = to_net_dev(dev); return sysfs_emit(buf, fmt_dec, dev_get_iflink(ndev)); } static DEVICE_ATTR_RO(iflink); static ssize_t format_name_assign_type(const struct net_device *dev, char *buf) { return sysfs_emit(buf, fmt_dec, READ_ONCE(dev->name_assign_type)); } static ssize_t name_assign_type_show(struct device *dev, struct device_attribute *attr, char *buf) { struct net_device *ndev = to_net_dev(dev); ssize_t ret = -EINVAL; if (READ_ONCE(ndev->name_assign_type) != NET_NAME_UNKNOWN) ret = netdev_show(dev, attr, buf, format_name_assign_type); return ret; } static DEVICE_ATTR_RO(name_assign_type); /* use same locking rules as GIFHWADDR ioctl's (dev_get_mac_address()) */ static ssize_t address_show(struct device *dev, struct device_attribute *attr, char *buf) { struct net_device *ndev = to_net_dev(dev); ssize_t ret = -EINVAL; down_read(&dev_addr_sem); rcu_read_lock(); if (dev_isalive(ndev)) ret = sysfs_format_mac(buf, ndev->dev_addr, ndev->addr_len); rcu_read_unlock(); up_read(&dev_addr_sem); return ret; } static DEVICE_ATTR_RO(address); static ssize_t broadcast_show(struct device *dev, struct device_attribute *attr, char *buf) { struct net_device *ndev = to_net_dev(dev); int ret = -EINVAL; rcu_read_lock(); if (dev_isalive(ndev)) ret = sysfs_format_mac(buf, ndev->broadcast, ndev->addr_len); rcu_read_unlock(); return ret; } static DEVICE_ATTR_RO(broadcast); static int change_carrier(struct net_device *dev, unsigned long new_carrier) { if (!netif_running(dev)) return -EINVAL; return dev_change_carrier(dev, (bool)new_carrier); } static ssize_t carrier_store(struct device *dev, struct device_attribute *attr, const char *buf, size_t len) { struct net_device *netdev = to_net_dev(dev); /* The check is also done in change_carrier; this helps returning early * without hitting the trylock/restart in netdev_store. */ if (!netdev->netdev_ops->ndo_change_carrier) return -EOPNOTSUPP; return netdev_store(dev, attr, buf, len, change_carrier); } static ssize_t carrier_show(struct device *dev, struct device_attribute *attr, char *buf) { struct net_device *netdev = to_net_dev(dev); int ret = -EINVAL; if (!rtnl_trylock()) return restart_syscall(); if (netif_running(netdev)) { /* Synchronize carrier state with link watch, * see also rtnl_getlink(). */ linkwatch_sync_dev(netdev); ret = sysfs_emit(buf, fmt_dec, !!netif_carrier_ok(netdev)); } rtnl_unlock(); return ret; } static DEVICE_ATTR_RW(carrier); static ssize_t speed_show(struct device *dev, struct device_attribute *attr, char *buf) { struct net_device *netdev = to_net_dev(dev); int ret = -EINVAL; /* The check is also done in __ethtool_get_link_ksettings; this helps * returning early without hitting the trylock/restart below. */ if (!netdev->ethtool_ops->get_link_ksettings) return ret; if (!rtnl_trylock()) return restart_syscall(); if (netif_running(netdev)) { struct ethtool_link_ksettings cmd; if (!__ethtool_get_link_ksettings(netdev, &cmd)) ret = sysfs_emit(buf, fmt_dec, cmd.base.speed); } rtnl_unlock(); return ret; } static DEVICE_ATTR_RO(speed); static ssize_t duplex_show(struct device *dev, struct device_attribute *attr, char *buf) { struct net_device *netdev = to_net_dev(dev); int ret = -EINVAL; /* The check is also done in __ethtool_get_link_ksettings; this helps * returning early without hitting the trylock/restart below. */ if (!netdev->ethtool_ops->get_link_ksettings) return ret; if (!rtnl_trylock()) return restart_syscall(); if (netif_running(netdev)) { struct ethtool_link_ksettings cmd; if (!__ethtool_get_link_ksettings(netdev, &cmd)) { const char *duplex; switch (cmd.base.duplex) { case DUPLEX_HALF: duplex = "half"; break; case DUPLEX_FULL: duplex = "full"; break; default: duplex = "unknown"; break; } ret = sysfs_emit(buf, "%s\n", duplex); } } rtnl_unlock(); return ret; } static DEVICE_ATTR_RO(duplex); static ssize_t testing_show(struct device *dev, struct device_attribute *attr, char *buf) { struct net_device *netdev = to_net_dev(dev); if (netif_running(netdev)) return sysfs_emit(buf, fmt_dec, !!netif_testing(netdev)); return -EINVAL; } static DEVICE_ATTR_RO(testing); static ssize_t dormant_show(struct device *dev, struct device_attribute *attr, char *buf) { struct net_device *netdev = to_net_dev(dev); if (netif_running(netdev)) return sysfs_emit(buf, fmt_dec, !!netif_dormant(netdev)); return -EINVAL; } static DEVICE_ATTR_RO(dormant); static const char *const operstates[] = { "unknown", "notpresent", /* currently unused */ "down", "lowerlayerdown", "testing", "dormant", "up" }; static ssize_t operstate_show(struct device *dev, struct device_attribute *attr, char *buf) { const struct net_device *netdev = to_net_dev(dev); unsigned char operstate; operstate = READ_ONCE(netdev->operstate); if (!netif_running(netdev)) operstate = IF_OPER_DOWN; if (operstate >= ARRAY_SIZE(operstates)) return -EINVAL; /* should not happen */ return sysfs_emit(buf, "%s\n", operstates[operstate]); } static DEVICE_ATTR_RO(operstate); static ssize_t carrier_changes_show(struct device *dev, struct device_attribute *attr, char *buf) { struct net_device *netdev = to_net_dev(dev); return sysfs_emit(buf, fmt_dec, atomic_read(&netdev->carrier_up_count) + atomic_read(&netdev->carrier_down_count)); } static DEVICE_ATTR_RO(carrier_changes); static ssize_t carrier_up_count_show(struct device *dev, struct device_attribute *attr, char *buf) { struct net_device *netdev = to_net_dev(dev); return sysfs_emit(buf, fmt_dec, atomic_read(&netdev->carrier_up_count)); } static DEVICE_ATTR_RO(carrier_up_count); static ssize_t carrier_down_count_show(struct device *dev, struct device_attribute *attr, char *buf) { struct net_device *netdev = to_net_dev(dev); return sysfs_emit(buf, fmt_dec, atomic_read(&netdev->carrier_down_count)); } static DEVICE_ATTR_RO(carrier_down_count); /* read-write attributes */ static int change_mtu(struct net_device *dev, unsigned long new_mtu) { return dev_set_mtu(dev, (int)new_mtu); } static ssize_t mtu_store(struct device *dev, struct device_attribute *attr, const char *buf, size_t len) { return netdev_store(dev, attr, buf, len, change_mtu); } NETDEVICE_SHOW_RW(mtu, fmt_dec); static int change_flags(struct net_device *dev, unsigned long new_flags) { return dev_change_flags(dev, (unsigned int)new_flags, NULL); } static ssize_t flags_store(struct device *dev, struct device_attribute *attr, const char *buf, size_t len) { return netdev_store(dev, attr, buf, len, change_flags); } NETDEVICE_SHOW_RW(flags, fmt_hex); static ssize_t tx_queue_len_store(struct device *dev, struct device_attribute *attr, const char *buf, size_t len) { if (!capable(CAP_NET_ADMIN)) return -EPERM; return netdev_store(dev, attr, buf, len, dev_change_tx_queue_len); } NETDEVICE_SHOW_RW(tx_queue_len, fmt_dec); static int change_gro_flush_timeout(struct net_device *dev, unsigned long val) { netdev_set_gro_flush_timeout(dev, val); return 0; } static ssize_t gro_flush_timeout_store(struct device *dev, struct device_attribute *attr, const char *buf, size_t len) { if (!capable(CAP_NET_ADMIN)) return -EPERM; return netdev_lock_store(dev, attr, buf, len, change_gro_flush_timeout); } NETDEVICE_SHOW_RW(gro_flush_timeout, fmt_ulong); static int change_napi_defer_hard_irqs(struct net_device *dev, unsigned long val) { if (val > S32_MAX) return -ERANGE; netdev_set_defer_hard_irqs(dev, (u32)val); return 0; } static ssize_t napi_defer_hard_irqs_store(struct device *dev, struct device_attribute *attr, const char *buf, size_t len) { if (!capable(CAP_NET_ADMIN)) return -EPERM; return netdev_lock_store(dev, attr, buf, len, change_napi_defer_hard_irqs); } NETDEVICE_SHOW_RW(napi_defer_hard_irqs, fmt_uint); static ssize_t ifalias_store(struct device *dev, struct device_attribute *attr, const char *buf, size_t len) { struct net_device *netdev = to_net_dev(dev); struct net *net = dev_net(netdev); size_t count = len; ssize_t ret = 0; if (!ns_capable(net->user_ns, CAP_NET_ADMIN)) return -EPERM; /* ignore trailing newline */ if (len > 0 && buf[len - 1] == '\n') --count; if (!rtnl_trylock()) return restart_syscall(); if (dev_isalive(netdev)) { ret = dev_set_alias(netdev, buf, count); if (ret < 0) goto err; ret = len; netdev_state_change(netdev); } err: rtnl_unlock(); return ret; } static ssize_t ifalias_show(struct device *dev, struct device_attribute *attr, char *buf) { const struct net_device *netdev = to_net_dev(dev); char tmp[IFALIASZ]; ssize_t ret = 0; ret = dev_get_alias(netdev, tmp, sizeof(tmp)); if (ret > 0) ret = sysfs_emit(buf, "%s\n", tmp); return ret; } static DEVICE_ATTR_RW(ifalias); static int change_group(struct net_device *dev, unsigned long new_group) { dev_set_group(dev, (int)new_group); return 0; } static ssize_t group_store(struct device *dev, struct device_attribute *attr, const char *buf, size_t len) { return netdev_store(dev, attr, buf, len, change_group); } NETDEVICE_SHOW(group, fmt_dec); static DEVICE_ATTR(netdev_group, 0644, group_show, group_store); static int change_proto_down(struct net_device *dev, unsigned long proto_down) { return dev_change_proto_down(dev, (bool)proto_down); } static ssize_t proto_down_store(struct device *dev, struct device_attribute *attr, const char *buf, size_t len) { return netdev_store(dev, attr, buf, len, change_proto_down); } NETDEVICE_SHOW_RW(proto_down, fmt_dec); static ssize_t phys_port_id_show(struct device *dev, struct device_attribute *attr, char *buf) { struct net_device *netdev = to_net_dev(dev); ssize_t ret = -EINVAL; /* The check is also done in dev_get_phys_port_id; this helps returning * early without hitting the trylock/restart below. */ if (!netdev->netdev_ops->ndo_get_phys_port_id) return -EOPNOTSUPP; if (!rtnl_trylock()) return restart_syscall(); if (dev_isalive(netdev)) { struct netdev_phys_item_id ppid; ret = dev_get_phys_port_id(netdev, &ppid); if (!ret) ret = sysfs_emit(buf, "%*phN\n", ppid.id_len, ppid.id); } rtnl_unlock(); return ret; } static DEVICE_ATTR_RO(phys_port_id); static ssize_t phys_port_name_show(struct device *dev, struct device_attribute *attr, char *buf) { struct net_device *netdev = to_net_dev(dev); ssize_t ret = -EINVAL; /* The checks are also done in dev_get_phys_port_name; this helps * returning early without hitting the trylock/restart below. */ if (!netdev->netdev_ops->ndo_get_phys_port_name && !netdev->devlink_port) return -EOPNOTSUPP; if (!rtnl_trylock()) return restart_syscall(); if (dev_isalive(netdev)) { char name[IFNAMSIZ]; ret = dev_get_phys_port_name(netdev, name, sizeof(name)); if (!ret) ret = sysfs_emit(buf, "%s\n", name); } rtnl_unlock(); return ret; } static DEVICE_ATTR_RO(phys_port_name); static ssize_t phys_switch_id_show(struct device *dev, struct device_attribute *attr, char *buf) { struct net_device *netdev = to_net_dev(dev); ssize_t ret = -EINVAL; /* The checks are also done in dev_get_phys_port_name; this helps * returning early without hitting the trylock/restart below. This works * because recurse is false when calling dev_get_port_parent_id. */ if (!netdev->netdev_ops->ndo_get_port_parent_id && !netdev->devlink_port) return -EOPNOTSUPP; if (!rtnl_trylock()) return restart_syscall(); if (dev_isalive(netdev)) { struct netdev_phys_item_id ppid = { }; ret = dev_get_port_parent_id(netdev, &ppid, false); if (!ret) ret = sysfs_emit(buf, "%*phN\n", ppid.id_len, ppid.id); } rtnl_unlock(); return ret; } static DEVICE_ATTR_RO(phys_switch_id); static ssize_t threaded_show(struct device *dev, struct device_attribute *attr, char *buf) { struct net_device *netdev = to_net_dev(dev); ssize_t ret = -EINVAL; rcu_read_lock(); if (dev_isalive(netdev)) ret = sysfs_emit(buf, fmt_dec, READ_ONCE(netdev->threaded)); rcu_read_unlock(); return ret; } static int modify_napi_threaded(struct net_device *dev, unsigned long val) { int ret; if (list_empty(&dev->napi_list)) return -EOPNOTSUPP; if (val != 0 && val != 1) return -EOPNOTSUPP; ret = dev_set_threaded(dev, val); return ret; } static ssize_t threaded_store(struct device *dev, struct device_attribute *attr, const char *buf, size_t len) { return netdev_lock_store(dev, attr, buf, len, modify_napi_threaded); } static DEVICE_ATTR_RW(threaded); static struct attribute *net_class_attrs[] __ro_after_init = { &dev_attr_netdev_group.attr, &dev_attr_type.attr, &dev_attr_dev_id.attr, &dev_attr_dev_port.attr, &dev_attr_iflink.attr, &dev_attr_ifindex.attr, &dev_attr_name_assign_type.attr, &dev_attr_addr_assign_type.attr, &dev_attr_addr_len.attr, &dev_attr_link_mode.attr, &dev_attr_address.attr, &dev_attr_broadcast.attr, &dev_attr_speed.attr, &dev_attr_duplex.attr, &dev_attr_dormant.attr, &dev_attr_testing.attr, &dev_attr_operstate.attr, &dev_attr_carrier_changes.attr, &dev_attr_ifalias.attr, &dev_attr_carrier.attr, &dev_attr_mtu.attr, &dev_attr_flags.attr, &dev_attr_tx_queue_len.attr, &dev_attr_gro_flush_timeout.attr, &dev_attr_napi_defer_hard_irqs.attr, &dev_attr_phys_port_id.attr, &dev_attr_phys_port_name.attr, &dev_attr_phys_switch_id.attr, &dev_attr_proto_down.attr, &dev_attr_carrier_up_count.attr, &dev_attr_carrier_down_count.attr, &dev_attr_threaded.attr, NULL, }; ATTRIBUTE_GROUPS(net_class); /* Show a given an attribute in the statistics group */ static ssize_t netstat_show(const struct device *d, struct device_attribute *attr, char *buf, unsigned long offset) { struct net_device *dev = to_net_dev(d); ssize_t ret = -EINVAL; WARN_ON(offset > sizeof(struct rtnl_link_stats64) || offset % sizeof(u64) != 0); rcu_read_lock(); if (dev_isalive(dev)) { struct rtnl_link_stats64 temp; const struct rtnl_link_stats64 *stats = dev_get_stats(dev, &temp); ret = sysfs_emit(buf, fmt_u64, *(u64 *)(((u8 *)stats) + offset)); } rcu_read_unlock(); return ret; } /* generate a read-only statistics attribute */ #define NETSTAT_ENTRY(name) \ static ssize_t name##_show(struct device *d, \ struct device_attribute *attr, char *buf) \ { \ return netstat_show(d, attr, buf, \ offsetof(struct rtnl_link_stats64, name)); \ } \ static DEVICE_ATTR_RO(name) NETSTAT_ENTRY(rx_packets); NETSTAT_ENTRY(tx_packets); NETSTAT_ENTRY(rx_bytes); NETSTAT_ENTRY(tx_bytes); NETSTAT_ENTRY(rx_errors); NETSTAT_ENTRY(tx_errors); NETSTAT_ENTRY(rx_dropped); NETSTAT_ENTRY(tx_dropped); NETSTAT_ENTRY(multicast); NETSTAT_ENTRY(collisions); NETSTAT_ENTRY(rx_length_errors); NETSTAT_ENTRY(rx_over_errors); NETSTAT_ENTRY(rx_crc_errors); NETSTAT_ENTRY(rx_frame_errors); NETSTAT_ENTRY(rx_fifo_errors); NETSTAT_ENTRY(rx_missed_errors); NETSTAT_ENTRY(tx_aborted_errors); NETSTAT_ENTRY(tx_carrier_errors); NETSTAT_ENTRY(tx_fifo_errors); NETSTAT_ENTRY(tx_heartbeat_errors); NETSTAT_ENTRY(tx_window_errors); NETSTAT_ENTRY(rx_compressed); NETSTAT_ENTRY(tx_compressed); NETSTAT_ENTRY(rx_nohandler); static struct attribute *netstat_attrs[] __ro_after_init = { &dev_attr_rx_packets.attr, &dev_attr_tx_packets.attr, &dev_attr_rx_bytes.attr, &dev_attr_tx_bytes.attr, &dev_attr_rx_errors.attr, &dev_attr_tx_errors.attr, &dev_attr_rx_dropped.attr, &dev_attr_tx_dropped.attr, &dev_attr_multicast.attr, &dev_attr_collisions.attr, &dev_attr_rx_length_errors.attr, &dev_attr_rx_over_errors.attr, &dev_attr_rx_crc_errors.attr, &dev_attr_rx_frame_errors.attr, &dev_attr_rx_fifo_errors.attr, &dev_attr_rx_missed_errors.attr, &dev_attr_tx_aborted_errors.attr, &dev_attr_tx_carrier_errors.attr, &dev_attr_tx_fifo_errors.attr, &dev_attr_tx_heartbeat_errors.attr, &dev_attr_tx_window_errors.attr, &dev_attr_rx_compressed.attr, &dev_attr_tx_compressed.attr, &dev_attr_rx_nohandler.attr, NULL }; static const struct attribute_group netstat_group = { .name = "statistics", .attrs = netstat_attrs, }; static struct attribute *wireless_attrs[] = { NULL }; static const struct attribute_group wireless_group = { .name = "wireless", .attrs = wireless_attrs, }; static bool wireless_group_needed(struct net_device *ndev) { #if IS_ENABLED(CONFIG_CFG80211) if (ndev->ieee80211_ptr) return true; #endif #if IS_ENABLED(CONFIG_WIRELESS_EXT) if (ndev->wireless_handlers) return true; #endif return false; } #else /* CONFIG_SYSFS */ #define net_class_groups NULL #endif /* CONFIG_SYSFS */ #ifdef CONFIG_SYSFS #define to_rx_queue_attr(_attr) \ container_of(_attr, struct rx_queue_attribute, attr) #define to_rx_queue(obj) container_of(obj, struct netdev_rx_queue, kobj) static ssize_t rx_queue_attr_show(struct kobject *kobj, struct attribute *attr, char *buf) { const struct rx_queue_attribute *attribute = to_rx_queue_attr(attr); struct netdev_rx_queue *queue = to_rx_queue(kobj); if (!attribute->show) return -EIO; return attribute->show(queue, buf); } static ssize_t rx_queue_attr_store(struct kobject *kobj, struct attribute *attr, const char *buf, size_t count) { const struct rx_queue_attribute *attribute = to_rx_queue_attr(attr); struct netdev_rx_queue *queue = to_rx_queue(kobj); if (!attribute->store) return -EIO; return attribute->store(queue, buf, count); } static const struct sysfs_ops rx_queue_sysfs_ops = { .show = rx_queue_attr_show, .store = rx_queue_attr_store, }; #ifdef CONFIG_RPS static ssize_t show_rps_map(struct netdev_rx_queue *queue, char *buf) { struct rps_map *map; cpumask_var_t mask; int i, len; if (!zalloc_cpumask_var(&mask, GFP_KERNEL)) return -ENOMEM; rcu_read_lock(); map = rcu_dereference(queue->rps_map); if (map) for (i = 0; i < map->len; i++) cpumask_set_cpu(map->cpus[i], mask); len = sysfs_emit(buf, "%*pb\n", cpumask_pr_args(mask)); rcu_read_unlock(); free_cpumask_var(mask); return len < PAGE_SIZE ? len : -EINVAL; } static int netdev_rx_queue_set_rps_mask(struct netdev_rx_queue *queue, cpumask_var_t mask) { static DEFINE_MUTEX(rps_map_mutex); struct rps_map *old_map, *map; int cpu, i; map = kzalloc(max_t(unsigned int, RPS_MAP_SIZE(cpumask_weight(mask)), L1_CACHE_BYTES), GFP_KERNEL); if (!map) return -ENOMEM; i = 0; for_each_cpu_and(cpu, mask, cpu_online_mask) map->cpus[i++] = cpu; if (i) { map->len = i; } else { kfree(map); map = NULL; } mutex_lock(&rps_map_mutex); old_map = rcu_dereference_protected(queue->rps_map, mutex_is_locked(&rps_map_mutex)); rcu_assign_pointer(queue->rps_map, map); if (map) static_branch_inc(&rps_needed); if (old_map) static_branch_dec(&rps_needed); mutex_unlock(&rps_map_mutex); if (old_map) kfree_rcu(old_map, rcu); return 0; } int rps_cpumask_housekeeping(struct cpumask *mask) { if (!cpumask_empty(mask)) { cpumask_and(mask, mask, housekeeping_cpumask(HK_TYPE_DOMAIN)); cpumask_and(mask, mask, housekeeping_cpumask(HK_TYPE_WQ)); if (cpumask_empty(mask)) return -EINVAL; } return 0; } static ssize_t store_rps_map(struct netdev_rx_queue *queue, const char *buf, size_t len) { cpumask_var_t mask; int err; if (!capable(CAP_NET_ADMIN)) return -EPERM; if (!alloc_cpumask_var(&mask, GFP_KERNEL)) return -ENOMEM; err = bitmap_parse(buf, len, cpumask_bits(mask), nr_cpumask_bits); if (err) goto out; err = rps_cpumask_housekeeping(mask); if (err) goto out; err = netdev_rx_queue_set_rps_mask(queue, mask); out: free_cpumask_var(mask); return err ? : len; } static ssize_t show_rps_dev_flow_table_cnt(struct netdev_rx_queue *queue, char *buf) { struct rps_dev_flow_table *flow_table; unsigned long val = 0; rcu_read_lock(); flow_table = rcu_dereference(queue->rps_flow_table); if (flow_table) val = (unsigned long)flow_table->mask + 1; rcu_read_unlock(); return sysfs_emit(buf, "%lu\n", val); } static void rps_dev_flow_table_release(struct rcu_head *rcu) { struct rps_dev_flow_table *table = container_of(rcu, struct rps_dev_flow_table, rcu); vfree(table); } static ssize_t store_rps_dev_flow_table_cnt(struct netdev_rx_queue *queue, const char *buf, size_t len) { unsigned long mask, count; struct rps_dev_flow_table *table, *old_table; static DEFINE_SPINLOCK(rps_dev_flow_lock); int rc; if (!capable(CAP_NET_ADMIN)) return -EPERM; rc = kstrtoul(buf, 0, &count); if (rc < 0) return rc; if (count) { mask = count - 1; /* mask = roundup_pow_of_two(count) - 1; * without overflows... */ while ((mask | (mask >> 1)) != mask) mask |= (mask >> 1); /* On 64 bit arches, must check mask fits in table->mask (u32), * and on 32bit arches, must check * RPS_DEV_FLOW_TABLE_SIZE(mask + 1) doesn't overflow. */ #if BITS_PER_LONG > 32 if (mask > (unsigned long)(u32)mask) return -EINVAL; #else if (mask > (ULONG_MAX - RPS_DEV_FLOW_TABLE_SIZE(1)) / sizeof(struct rps_dev_flow)) { /* Enforce a limit to prevent overflow */ return -EINVAL; } #endif table = vmalloc(RPS_DEV_FLOW_TABLE_SIZE(mask + 1)); if (!table) return -ENOMEM; table->mask = mask; for (count = 0; count <= mask; count++) table->flows[count].cpu = RPS_NO_CPU; } else { table = NULL; } spin_lock(&rps_dev_flow_lock); old_table = rcu_dereference_protected(queue->rps_flow_table, lockdep_is_held(&rps_dev_flow_lock)); rcu_assign_pointer(queue->rps_flow_table, table); spin_unlock(&rps_dev_flow_lock); if (old_table) call_rcu(&old_table->rcu, rps_dev_flow_table_release); return len; } static struct rx_queue_attribute rps_cpus_attribute __ro_after_init = __ATTR(rps_cpus, 0644, show_rps_map, store_rps_map); static struct rx_queue_attribute rps_dev_flow_table_cnt_attribute __ro_after_init = __ATTR(rps_flow_cnt, 0644, show_rps_dev_flow_table_cnt, store_rps_dev_flow_table_cnt); #endif /* CONFIG_RPS */ static struct attribute *rx_queue_default_attrs[] __ro_after_init = { #ifdef CONFIG_RPS &rps_cpus_attribute.attr, &rps_dev_flow_table_cnt_attribute.attr, #endif NULL }; ATTRIBUTE_GROUPS(rx_queue_default); static void rx_queue_release(struct kobject *kobj) { struct netdev_rx_queue *queue = to_rx_queue(kobj); #ifdef CONFIG_RPS struct rps_map *map; struct rps_dev_flow_table *flow_table; map = rcu_dereference_protected(queue->rps_map, 1); if (map) { RCU_INIT_POINTER(queue->rps_map, NULL); kfree_rcu(map, rcu); } flow_table = rcu_dereference_protected(queue->rps_flow_table, 1); if (flow_table) { RCU_INIT_POINTER(queue->rps_flow_table, NULL); call_rcu(&flow_table->rcu, rps_dev_flow_table_release); } #endif memset(kobj, 0, sizeof(*kobj)); netdev_put(queue->dev, &queue->dev_tracker); } static const void *rx_queue_namespace(const struct kobject *kobj) { struct netdev_rx_queue *queue = to_rx_queue(kobj); struct device *dev = &queue->dev->dev; const void *ns = NULL; if (dev->class && dev->class->namespace) ns = dev->class->namespace(dev); return ns; } static void rx_queue_get_ownership(const struct kobject *kobj, kuid_t *uid, kgid_t *gid) { const struct net *net = rx_queue_namespace(kobj); net_ns_get_ownership(net, uid, gid); } static const struct kobj_type rx_queue_ktype = { .sysfs_ops = &rx_queue_sysfs_ops, .release = rx_queue_release, .default_groups = rx_queue_default_groups, .namespace = rx_queue_namespace, .get_ownership = rx_queue_get_ownership, }; static int rx_queue_default_mask(struct net_device *dev, struct netdev_rx_queue *queue) { #if IS_ENABLED(CONFIG_RPS) && IS_ENABLED(CONFIG_SYSCTL) struct cpumask *rps_default_mask = READ_ONCE(dev_net(dev)->core.rps_default_mask); if (rps_default_mask && !cpumask_empty(rps_default_mask)) return netdev_rx_queue_set_rps_mask(queue, rps_default_mask); #endif return 0; } static int rx_queue_add_kobject(struct net_device *dev, int index) { struct netdev_rx_queue *queue = dev->_rx + index; struct kobject *kobj = &queue->kobj; int error = 0; /* Kobject_put later will trigger rx_queue_release call which * decreases dev refcount: Take that reference here */ netdev_hold(queue->dev, &queue->dev_tracker, GFP_KERNEL); kobj->kset = dev->queues_kset; error = kobject_init_and_add(kobj, &rx_queue_ktype, NULL, "rx-%u", index); if (error) goto err; if (dev->sysfs_rx_queue_group) { error = sysfs_create_group(kobj, dev->sysfs_rx_queue_group); if (error) goto err; } error = rx_queue_default_mask(dev, queue); if (error) goto err; kobject_uevent(kobj, KOBJ_ADD); return error; err: kobject_put(kobj); return error; } static int rx_queue_change_owner(struct net_device *dev, int index, kuid_t kuid, kgid_t kgid) { struct netdev_rx_queue *queue = dev->_rx + index; struct kobject *kobj = &queue->kobj; int error; error = sysfs_change_owner(kobj, kuid, kgid); if (error) return error; if (dev->sysfs_rx_queue_group) error = sysfs_group_change_owner( kobj, dev->sysfs_rx_queue_group, kuid, kgid); return error; } #endif /* CONFIG_SYSFS */ int net_rx_queue_update_kobjects(struct net_device *dev, int old_num, int new_num) { #ifdef CONFIG_SYSFS int i; int error = 0; #ifndef CONFIG_RPS if (!dev->sysfs_rx_queue_group) return 0; #endif for (i = old_num; i < new_num; i++) { error = rx_queue_add_kobject(dev, i); if (error) { new_num = old_num; break; } } while (--i >= new_num) { struct kobject *kobj = &dev->_rx[i].kobj; if (!refcount_read(&dev_net(dev)->ns.count)) kobj->uevent_suppress = 1; if (dev->sysfs_rx_queue_group) sysfs_remove_group(kobj, dev->sysfs_rx_queue_group); kobject_put(kobj); } return error; #else return 0; #endif } static int net_rx_queue_change_owner(struct net_device *dev, int num, kuid_t kuid, kgid_t kgid) { #ifdef CONFIG_SYSFS int error = 0; int i; #ifndef CONFIG_RPS if (!dev->sysfs_rx_queue_group) return 0; #endif for (i = 0; i < num; i++) { error = rx_queue_change_owner(dev, i, kuid, kgid); if (error) break; } return error; #else return 0; #endif } #ifdef CONFIG_SYSFS /* * netdev_queue sysfs structures and functions. */ struct netdev_queue_attribute { struct attribute attr; ssize_t (*show)(struct netdev_queue *queue, char *buf); ssize_t (*store)(struct netdev_queue *queue, const char *buf, size_t len); }; #define to_netdev_queue_attr(_attr) \ container_of(_attr, struct netdev_queue_attribute, attr) #define to_netdev_queue(obj) container_of(obj, struct netdev_queue, kobj) static ssize_t netdev_queue_attr_show(struct kobject *kobj, struct attribute *attr, char *buf) { const struct netdev_queue_attribute *attribute = to_netdev_queue_attr(attr); struct netdev_queue *queue = to_netdev_queue(kobj); if (!attribute->show) return -EIO; return attribute->show(queue, buf); } static ssize_t netdev_queue_attr_store(struct kobject *kobj, struct attribute *attr, const char *buf, size_t count) { const struct netdev_queue_attribute *attribute = to_netdev_queue_attr(attr); struct netdev_queue *queue = to_netdev_queue(kobj); if (!attribute->store) return -EIO; return attribute->store(queue, buf, count); } static const struct sysfs_ops netdev_queue_sysfs_ops = { .show = netdev_queue_attr_show, .store = netdev_queue_attr_store, }; static ssize_t tx_timeout_show(struct netdev_queue *queue, char *buf) { unsigned long trans_timeout = atomic_long_read(&queue->trans_timeout); return sysfs_emit(buf, fmt_ulong, trans_timeout); } static unsigned int get_netdev_queue_index(struct netdev_queue *queue) { struct net_device *dev = queue->dev; unsigned int i; i = queue - dev->_tx; BUG_ON(i >= dev->num_tx_queues); return i; } static ssize_t traffic_class_show(struct netdev_queue *queue, char *buf) { struct net_device *dev = queue->dev; int num_tc, tc; int index; if (!netif_is_multiqueue(dev)) return -ENOENT; if (!rtnl_trylock()) return restart_syscall(); index = get_netdev_queue_index(queue); /* If queue belongs to subordinate dev use its TC mapping */ dev = netdev_get_tx_queue(dev, index)->sb_dev ? : dev; num_tc = dev->num_tc; tc = netdev_txq_to_tc(dev, index); rtnl_unlock(); if (tc < 0) return -EINVAL; /* We can report the traffic class one of two ways: * Subordinate device traffic classes are reported with the traffic * class first, and then the subordinate class so for example TC0 on * subordinate device 2 will be reported as "0-2". If the queue * belongs to the root device it will be reported with just the * traffic class, so just "0" for TC 0 for example. */ return num_tc < 0 ? sysfs_emit(buf, "%d%d\n", tc, num_tc) : sysfs_emit(buf, "%d\n", tc); } #ifdef CONFIG_XPS static ssize_t tx_maxrate_show(struct netdev_queue *queue, char *buf) { return sysfs_emit(buf, "%lu\n", queue->tx_maxrate); } static ssize_t tx_maxrate_store(struct netdev_queue *queue, const char *buf, size_t len) { struct net_device *dev = queue->dev; int err, index = get_netdev_queue_index(queue); u32 rate = 0; if (!capable(CAP_NET_ADMIN)) return -EPERM; /* The check is also done later; this helps returning early without * hitting the trylock/restart below. */ if (!dev->netdev_ops->ndo_set_tx_maxrate) return -EOPNOTSUPP; err = kstrtou32(buf, 10, &rate); if (err < 0) return err; if (!rtnl_trylock()) return restart_syscall(); err = -EOPNOTSUPP; if (dev->netdev_ops->ndo_set_tx_maxrate) err = dev->netdev_ops->ndo_set_tx_maxrate(dev, index, rate); rtnl_unlock(); if (!err) { queue->tx_maxrate = rate; return len; } return err; } static struct netdev_queue_attribute queue_tx_maxrate __ro_after_init = __ATTR_RW(tx_maxrate); #endif static struct netdev_queue_attribute queue_trans_timeout __ro_after_init = __ATTR_RO(tx_timeout); static struct netdev_queue_attribute queue_traffic_class __ro_after_init = __ATTR_RO(traffic_class); #ifdef CONFIG_BQL /* * Byte queue limits sysfs structures and functions. */ static ssize_t bql_show(char *buf, unsigned int value) { return sysfs_emit(buf, "%u\n", value); } static ssize_t bql_set(const char *buf, const size_t count, unsigned int *pvalue) { unsigned int value; int err; if (!strcmp(buf, "max") || !strcmp(buf, "max\n")) { value = DQL_MAX_LIMIT; } else { err = kstrtouint(buf, 10, &value); if (err < 0) return err; if (value > DQL_MAX_LIMIT) return -EINVAL; } *pvalue = value; return count; } static ssize_t bql_show_hold_time(struct netdev_queue *queue, char *buf) { struct dql *dql = &queue->dql; return sysfs_emit(buf, "%u\n", jiffies_to_msecs(dql->slack_hold_time)); } static ssize_t bql_set_hold_time(struct netdev_queue *queue, const char *buf, size_t len) { struct dql *dql = &queue->dql; unsigned int value; int err; err = kstrtouint(buf, 10, &value); if (err < 0) return err; dql->slack_hold_time = msecs_to_jiffies(value); return len; } static struct netdev_queue_attribute bql_hold_time_attribute __ro_after_init = __ATTR(hold_time, 0644, bql_show_hold_time, bql_set_hold_time); static ssize_t bql_show_stall_thrs(struct netdev_queue *queue, char *buf) { struct dql *dql = &queue->dql; return sysfs_emit(buf, "%u\n", jiffies_to_msecs(dql->stall_thrs)); } static ssize_t bql_set_stall_thrs(struct netdev_queue *queue, const char *buf, size_t len) { struct dql *dql = &queue->dql; unsigned int value; int err; err = kstrtouint(buf, 10, &value); if (err < 0) return err; value = msecs_to_jiffies(value); if (value && (value < 4 || value > 4 / 2 * BITS_PER_LONG)) return -ERANGE; if (!dql->stall_thrs && value) dql->last_reap = jiffies; /* Force last_reap to be live */ smp_wmb(); dql->stall_thrs = value; return len; } static struct netdev_queue_attribute bql_stall_thrs_attribute __ro_after_init = __ATTR(stall_thrs, 0644, bql_show_stall_thrs, bql_set_stall_thrs); static ssize_t bql_show_stall_max(struct netdev_queue *queue, char *buf) { return sysfs_emit(buf, "%u\n", READ_ONCE(queue->dql.stall_max)); } static ssize_t bql_set_stall_max(struct netdev_queue *queue, const char *buf, size_t len) { WRITE_ONCE(queue->dql.stall_max, 0); return len; } static struct netdev_queue_attribute bql_stall_max_attribute __ro_after_init = __ATTR(stall_max, 0644, bql_show_stall_max, bql_set_stall_max); static ssize_t bql_show_stall_cnt(struct netdev_queue *queue, char *buf) { struct dql *dql = &queue->dql; return sysfs_emit(buf, "%lu\n", dql->stall_cnt); } static struct netdev_queue_attribute bql_stall_cnt_attribute __ro_after_init = __ATTR(stall_cnt, 0444, bql_show_stall_cnt, NULL); static ssize_t bql_show_inflight(struct netdev_queue *queue, char *buf) { struct dql *dql = &queue->dql; return sysfs_emit(buf, "%u\n", dql->num_queued - dql->num_completed); } static struct netdev_queue_attribute bql_inflight_attribute __ro_after_init = __ATTR(inflight, 0444, bql_show_inflight, NULL); #define BQL_ATTR(NAME, FIELD) \ static ssize_t bql_show_ ## NAME(struct netdev_queue *queue, \ char *buf) \ { \ return bql_show(buf, queue->dql.FIELD); \ } \ \ static ssize_t bql_set_ ## NAME(struct netdev_queue *queue, \ const char *buf, size_t len) \ { \ return bql_set(buf, len, &queue->dql.FIELD); \ } \ \ static struct netdev_queue_attribute bql_ ## NAME ## _attribute __ro_after_init \ = __ATTR(NAME, 0644, \ bql_show_ ## NAME, bql_set_ ## NAME) BQL_ATTR(limit, limit); BQL_ATTR(limit_max, max_limit); BQL_ATTR(limit_min, min_limit); static struct attribute *dql_attrs[] __ro_after_init = { &bql_limit_attribute.attr, &bql_limit_max_attribute.attr, &bql_limit_min_attribute.attr, &bql_hold_time_attribute.attr, &bql_inflight_attribute.attr, &bql_stall_thrs_attribute.attr, &bql_stall_cnt_attribute.attr, &bql_stall_max_attribute.attr, NULL }; static const struct attribute_group dql_group = { .name = "byte_queue_limits", .attrs = dql_attrs, }; #else /* Fake declaration, all the code using it should be dead */ static const struct attribute_group dql_group = {}; #endif /* CONFIG_BQL */ #ifdef CONFIG_XPS static ssize_t xps_queue_show(struct net_device *dev, unsigned int index, int tc, char *buf, enum xps_map_type type) { struct xps_dev_maps *dev_maps; unsigned long *mask; unsigned int nr_ids; int j, len; rcu_read_lock(); dev_maps = rcu_dereference(dev->xps_maps[type]); /* Default to nr_cpu_ids/dev->num_rx_queues and do not just return 0 * when dev_maps hasn't been allocated yet, to be backward compatible. */ nr_ids = dev_maps ? dev_maps->nr_ids : (type == XPS_CPUS ? nr_cpu_ids : dev->num_rx_queues); mask = bitmap_zalloc(nr_ids, GFP_NOWAIT); if (!mask) { rcu_read_unlock(); return -ENOMEM; } if (!dev_maps || tc >= dev_maps->num_tc) goto out_no_maps; for (j = 0; j < nr_ids; j++) { int i, tci = j * dev_maps->num_tc + tc; struct xps_map *map; map = rcu_dereference(dev_maps->attr_map[tci]); if (!map) continue; for (i = map->len; i--;) { if (map->queues[i] == index) { __set_bit(j, mask); break; } } } out_no_maps: rcu_read_unlock(); len = bitmap_print_to_pagebuf(false, buf, mask, nr_ids); bitmap_free(mask); return len < PAGE_SIZE ? len : -EINVAL; } static ssize_t xps_cpus_show(struct netdev_queue *queue, char *buf) { struct net_device *dev = queue->dev; unsigned int index; int len, tc; if (!netif_is_multiqueue(dev)) return -ENOENT; index = get_netdev_queue_index(queue); if (!rtnl_trylock()) return restart_syscall(); /* If queue belongs to subordinate dev use its map */ dev = netdev_get_tx_queue(dev, index)->sb_dev ? : dev; tc = netdev_txq_to_tc(dev, index); if (tc < 0) { rtnl_unlock(); return -EINVAL; } /* Make sure the subordinate device can't be freed */ get_device(&dev->dev); rtnl_unlock(); len = xps_queue_show(dev, index, tc, buf, XPS_CPUS); put_device(&dev->dev); return len; } static ssize_t xps_cpus_store(struct netdev_queue *queue, const char *buf, size_t len) { struct net_device *dev = queue->dev; unsigned int index; cpumask_var_t mask; int err; if (!netif_is_multiqueue(dev)) return -ENOENT; if (!capable(CAP_NET_ADMIN)) return -EPERM; if (!alloc_cpumask_var(&mask, GFP_KERNEL)) return -ENOMEM; index = get_netdev_queue_index(queue); err = bitmap_parse(buf, len, cpumask_bits(mask), nr_cpumask_bits); if (err) { free_cpumask_var(mask); return err; } if (!rtnl_trylock()) { free_cpumask_var(mask); return restart_syscall(); } err = netif_set_xps_queue(dev, mask, index); rtnl_unlock(); free_cpumask_var(mask); return err ? : len; } static struct netdev_queue_attribute xps_cpus_attribute __ro_after_init = __ATTR_RW(xps_cpus); static ssize_t xps_rxqs_show(struct netdev_queue *queue, char *buf) { struct net_device *dev = queue->dev; unsigned int index; int tc; index = get_netdev_queue_index(queue); if (!rtnl_trylock()) return restart_syscall(); tc = netdev_txq_to_tc(dev, index); rtnl_unlock(); if (tc < 0) return -EINVAL; return xps_queue_show(dev, index, tc, buf, XPS_RXQS); } static ssize_t xps_rxqs_store(struct netdev_queue *queue, const char *buf, size_t len) { struct net_device *dev = queue->dev; struct net *net = dev_net(dev); unsigned long *mask; unsigned int index; int err; if (!ns_capable(net->user_ns, CAP_NET_ADMIN)) return -EPERM; mask = bitmap_zalloc(dev->num_rx_queues, GFP_KERNEL); if (!mask) return -ENOMEM; index = get_netdev_queue_index(queue); err = bitmap_parse(buf, len, mask, dev->num_rx_queues); if (err) { bitmap_free(mask); return err; } if (!rtnl_trylock()) { bitmap_free(mask); return restart_syscall(); } cpus_read_lock(); err = __netif_set_xps_queue(dev, mask, index, XPS_RXQS); cpus_read_unlock(); rtnl_unlock(); bitmap_free(mask); return err ? : len; } static struct netdev_queue_attribute xps_rxqs_attribute __ro_after_init = __ATTR_RW(xps_rxqs); #endif /* CONFIG_XPS */ static struct attribute *netdev_queue_default_attrs[] __ro_after_init = { &queue_trans_timeout.attr, &queue_traffic_class.attr, #ifdef CONFIG_XPS &xps_cpus_attribute.attr, &xps_rxqs_attribute.attr, &queue_tx_maxrate.attr, #endif NULL }; ATTRIBUTE_GROUPS(netdev_queue_default); static void netdev_queue_release(struct kobject *kobj) { struct netdev_queue *queue = to_netdev_queue(kobj); memset(kobj, 0, sizeof(*kobj)); netdev_put(queue->dev, &queue->dev_tracker); } static const void *netdev_queue_namespace(const struct kobject *kobj) { struct netdev_queue *queue = to_netdev_queue(kobj); struct device *dev = &queue->dev->dev; const void *ns = NULL; if (dev->class && dev->class->namespace) ns = dev->class->namespace(dev); return ns; } static void netdev_queue_get_ownership(const struct kobject *kobj, kuid_t *uid, kgid_t *gid) { const struct net *net = netdev_queue_namespace(kobj); net_ns_get_ownership(net, uid, gid); } static const struct kobj_type netdev_queue_ktype = { .sysfs_ops = &netdev_queue_sysfs_ops, .release = netdev_queue_release, .default_groups = netdev_queue_default_groups, .namespace = netdev_queue_namespace, .get_ownership = netdev_queue_get_ownership, }; static bool netdev_uses_bql(const struct net_device *dev) { if (dev->lltx || (dev->priv_flags & IFF_NO_QUEUE)) return false; return IS_ENABLED(CONFIG_BQL); } static int netdev_queue_add_kobject(struct net_device *dev, int index) { struct netdev_queue *queue = dev->_tx + index; struct kobject *kobj = &queue->kobj; int error = 0; /* Kobject_put later will trigger netdev_queue_release call * which decreases dev refcount: Take that reference here */ netdev_hold(queue->dev, &queue->dev_tracker, GFP_KERNEL); kobj->kset = dev->queues_kset; error = kobject_init_and_add(kobj, &netdev_queue_ktype, NULL, "tx-%u", index); if (error) goto err; if (netdev_uses_bql(dev)) { error = sysfs_create_group(kobj, &dql_group); if (error) goto err; } kobject_uevent(kobj, KOBJ_ADD); return 0; err: kobject_put(kobj); return error; } static int tx_queue_change_owner(struct net_device *ndev, int index, kuid_t kuid, kgid_t kgid) { struct netdev_queue *queue = ndev->_tx + index; struct kobject *kobj = &queue->kobj; int error; error = sysfs_change_owner(kobj, kuid, kgid); if (error) return error; if (netdev_uses_bql(ndev)) error = sysfs_group_change_owner(kobj, &dql_group, kuid, kgid); return error; } #endif /* CONFIG_SYSFS */ int netdev_queue_update_kobjects(struct net_device *dev, int old_num, int new_num) { #ifdef CONFIG_SYSFS int i; int error = 0; /* Tx queue kobjects are allowed to be updated when a device is being * unregistered, but solely to remove queues from qdiscs. Any path * adding queues should be fixed. */ WARN(dev->reg_state == NETREG_UNREGISTERING && new_num > old_num, "New queues can't be registered after device unregistration."); for (i = old_num; i < new_num; i++) { error = netdev_queue_add_kobject(dev, i); if (error) { new_num = old_num; break; } } while (--i >= new_num) { struct netdev_queue *queue = dev->_tx + i; if (!refcount_read(&dev_net(dev)->ns.count)) queue->kobj.uevent_suppress = 1; if (netdev_uses_bql(dev)) sysfs_remove_group(&queue->kobj, &dql_group); kobject_put(&queue->kobj); } return error; #else return 0; #endif /* CONFIG_SYSFS */ } static int net_tx_queue_change_owner(struct net_device *dev, int num, kuid_t kuid, kgid_t kgid) { #ifdef CONFIG_SYSFS int error = 0; int i; for (i = 0; i < num; i++) { error = tx_queue_change_owner(dev, i, kuid, kgid); if (error) break; } return error; #else return 0; #endif /* CONFIG_SYSFS */ } static int register_queue_kobjects(struct net_device *dev) { int error = 0, txq = 0, rxq = 0, real_rx = 0, real_tx = 0; #ifdef CONFIG_SYSFS dev->queues_kset = kset_create_and_add("queues", NULL, &dev->dev.kobj); if (!dev->queues_kset) return -ENOMEM; real_rx = dev->real_num_rx_queues; #endif real_tx = dev->real_num_tx_queues; error = net_rx_queue_update_kobjects(dev, 0, real_rx); if (error) goto error; rxq = real_rx; error = netdev_queue_update_kobjects(dev, 0, real_tx); if (error) goto error; txq = real_tx; return 0; error: netdev_queue_update_kobjects(dev, txq, 0); net_rx_queue_update_kobjects(dev, rxq, 0); #ifdef CONFIG_SYSFS kset_unregister(dev->queues_kset); #endif return error; } static int queue_change_owner(struct net_device *ndev, kuid_t kuid, kgid_t kgid) { int error = 0, real_rx = 0, real_tx = 0; #ifdef CONFIG_SYSFS if (ndev->queues_kset) { error = sysfs_change_owner(&ndev->queues_kset->kobj, kuid, kgid); if (error) return error; } real_rx = ndev->real_num_rx_queues; #endif real_tx = ndev->real_num_tx_queues; error = net_rx_queue_change_owner(ndev, real_rx, kuid, kgid); if (error) return error; error = net_tx_queue_change_owner(ndev, real_tx, kuid, kgid); if (error) return error; return 0; } static void remove_queue_kobjects(struct net_device *dev) { int real_rx = 0, real_tx = 0; #ifdef CONFIG_SYSFS real_rx = dev->real_num_rx_queues; #endif real_tx = dev->real_num_tx_queues; net_rx_queue_update_kobjects(dev, real_rx, 0); netdev_queue_update_kobjects(dev, real_tx, 0); dev->real_num_rx_queues = 0; dev->real_num_tx_queues = 0; #ifdef CONFIG_SYSFS kset_unregister(dev->queues_kset); #endif } static bool net_current_may_mount(void) { struct net *net = current->nsproxy->net_ns; return ns_capable(net->user_ns, CAP_SYS_ADMIN); } static void *net_grab_current_ns(void) { struct net *ns = current->nsproxy->net_ns; #ifdef CONFIG_NET_NS if (ns) refcount_inc(&ns->passive); #endif return ns; } static const void *net_initial_ns(void) { return &init_net; } static const void *net_netlink_ns(struct sock *sk) { return sock_net(sk); } const struct kobj_ns_type_operations net_ns_type_operations = { .type = KOBJ_NS_TYPE_NET, .current_may_mount = net_current_may_mount, .grab_current_ns = net_grab_current_ns, .netlink_ns = net_netlink_ns, .initial_ns = net_initial_ns, .drop_ns = net_drop_ns, }; EXPORT_SYMBOL_GPL(net_ns_type_operations); static int netdev_uevent(const struct device *d, struct kobj_uevent_env *env) { const struct net_device *dev = to_net_dev(d); int retval; /* pass interface to uevent. */ retval = add_uevent_var(env, "INTERFACE=%s", dev->name); if (retval) goto exit; /* pass ifindex to uevent. * ifindex is useful as it won't change (interface name may change) * and is what RtNetlink uses natively. */ retval = add_uevent_var(env, "IFINDEX=%d", dev->ifindex); exit: return retval; } /* * netdev_release -- destroy and free a dead device. * Called when last reference to device kobject is gone. */ static void netdev_release(struct device *d) { struct net_device *dev = to_net_dev(d); BUG_ON(dev->reg_state != NETREG_RELEASED); /* no need to wait for rcu grace period: * device is dead and about to be freed. */ kfree(rcu_access_pointer(dev->ifalias)); kvfree(dev); } static const void *net_namespace(const struct device *d) { const struct net_device *dev = to_net_dev(d); return dev_net(dev); } static void net_get_ownership(const struct device *d, kuid_t *uid, kgid_t *gid) { const struct net_device *dev = to_net_dev(d); const struct net *net = dev_net(dev); net_ns_get_ownership(net, uid, gid); } static const struct class net_class = { .name = "net", .dev_release = netdev_release, .dev_groups = net_class_groups, .dev_uevent = netdev_uevent, .ns_type = &net_ns_type_operations, .namespace = net_namespace, .get_ownership = net_get_ownership, }; #ifdef CONFIG_OF static int of_dev_node_match(struct device *dev, const void *data) { for (; dev; dev = dev->parent) { if (dev->of_node == data) return 1; } return 0; } /* * of_find_net_device_by_node - lookup the net device for the device node * @np: OF device node * * Looks up the net_device structure corresponding with the device node. * If successful, returns a pointer to the net_device with the embedded * struct device refcount incremented by one, or NULL on failure. The * refcount must be dropped when done with the net_device. */ struct net_device *of_find_net_device_by_node(struct device_node *np) { struct device *dev; dev = class_find_device(&net_class, NULL, np, of_dev_node_match); if (!dev) return NULL; return to_net_dev(dev); } EXPORT_SYMBOL(of_find_net_device_by_node); #endif /* Delete sysfs entries but hold kobject reference until after all * netdev references are gone. */ void netdev_unregister_kobject(struct net_device *ndev) { struct device *dev = &ndev->dev; if (!refcount_read(&dev_net(ndev)->ns.count)) dev_set_uevent_suppress(dev, 1); kobject_get(&dev->kobj); remove_queue_kobjects(ndev); pm_runtime_set_memalloc_noio(dev, false); device_del(dev); } /* Create sysfs entries for network device. */ int netdev_register_kobject(struct net_device *ndev) { struct device *dev = &ndev->dev; const struct attribute_group **groups = ndev->sysfs_groups; int error = 0; device_initialize(dev); dev->class = &net_class; dev->platform_data = ndev; dev->groups = groups; dev_set_name(dev, "%s", ndev->name); #ifdef CONFIG_SYSFS /* Allow for a device specific group */ if (*groups) groups++; *groups++ = &netstat_group; if (wireless_group_needed(ndev)) *groups++ = &wireless_group; #endif /* CONFIG_SYSFS */ error = device_add(dev); if (error) return error; error = register_queue_kobjects(ndev); if (error) { device_del(dev); return error; } pm_runtime_set_memalloc_noio(dev, true); return error; } /* Change owner for sysfs entries when moving network devices across network * namespaces owned by different user namespaces. */ int netdev_change_owner(struct net_device *ndev, const struct net *net_old, const struct net *net_new) { kuid_t old_uid = GLOBAL_ROOT_UID, new_uid = GLOBAL_ROOT_UID; kgid_t old_gid = GLOBAL_ROOT_GID, new_gid = GLOBAL_ROOT_GID; struct device *dev = &ndev->dev; int error; net_ns_get_ownership(net_old, &old_uid, &old_gid); net_ns_get_ownership(net_new, &new_uid, &new_gid); /* The network namespace was changed but the owning user namespace is * identical so there's no need to change the owner of sysfs entries. */ if (uid_eq(old_uid, new_uid) && gid_eq(old_gid, new_gid)) return 0; error = device_change_owner(dev, new_uid, new_gid); if (error) return error; error = queue_change_owner(ndev, new_uid, new_gid); if (error) return error; return 0; } int netdev_class_create_file_ns(const struct class_attribute *class_attr, const void *ns) { return class_create_file_ns(&net_class, class_attr, ns); } EXPORT_SYMBOL(netdev_class_create_file_ns); void netdev_class_remove_file_ns(const struct class_attribute *class_attr, const void *ns) { class_remove_file_ns(&net_class, class_attr, ns); } EXPORT_SYMBOL(netdev_class_remove_file_ns); int __init netdev_kobject_init(void) { kobj_ns_type_register(&net_ns_type_operations); return class_register(&net_class); } |
| 10 8 9 1 1 1 1 10 10 1 1 2 2 2 2 2 2 15 15 3 15 15 15 14 1 7 7 7 7 12 12 8 1 1 1 1 3 3 1 5 5 4 12 12 12 8 4 4 122 123 124 3 113 2 2 4 4 6 6 | 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 | /* BlueZ - Bluetooth protocol stack for Linux Copyright (C) 2000-2001 Qualcomm Incorporated Copyright (C) 2011 ProFUSION Embedded Systems Written 2000,2001 by Maxim Krasnyansky <maxk@qualcomm.com> This program is free software; you can redistribute it and/or modify it under the terms of the GNU General Public License version 2 as published by the Free Software Foundation; 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 OF THIRD PARTY RIGHTS. IN NO EVENT SHALL THE COPYRIGHT HOLDER(S) AND AUTHOR(S) BE LIABLE FOR ANY CLAIM, OR ANY SPECIAL INDIRECT OR CONSEQUENTIAL DAMAGES, OR ANY DAMAGES WHATSOEVER RESULTING FROM LOSS OF USE, DATA OR PROFITS, WHETHER IN AN ACTION OF CONTRACT, NEGLIGENCE OR OTHER TORTIOUS ACTION, ARISING OUT OF OR IN CONNECTION WITH THE USE OR PERFORMANCE OF THIS SOFTWARE. ALL LIABILITY, INCLUDING LIABILITY FOR INFRINGEMENT OF ANY PATENTS, COPYRIGHTS, TRADEMARKS OR OTHER RIGHTS, RELATING TO USE OF THIS SOFTWARE IS DISCLAIMED. */ /* Bluetooth HCI core. */ #include <linux/export.h> #include <linux/rfkill.h> #include <linux/debugfs.h> #include <linux/crypto.h> #include <linux/kcov.h> #include <linux/property.h> #include <linux/suspend.h> #include <linux/wait.h> #include <linux/unaligned.h> #include <net/bluetooth/bluetooth.h> #include <net/bluetooth/hci_core.h> #include <net/bluetooth/l2cap.h> #include <net/bluetooth/mgmt.h> #include "hci_debugfs.h" #include "smp.h" #include "leds.h" #include "msft.h" #include "aosp.h" #include "hci_codec.h" static void hci_rx_work(struct work_struct *work); static void hci_cmd_work(struct work_struct *work); static void hci_tx_work(struct work_struct *work); /* HCI device list */ LIST_HEAD(hci_dev_list); DEFINE_RWLOCK(hci_dev_list_lock); /* HCI callback list */ LIST_HEAD(hci_cb_list); /* HCI ID Numbering */ static DEFINE_IDA(hci_index_ida); /* Get HCI device by index. * Device is held on return. */ struct hci_dev *hci_dev_get(int index) { struct hci_dev *hdev = NULL, *d; BT_DBG("%d", index); if (index < 0) return NULL; read_lock(&hci_dev_list_lock); list_for_each_entry(d, &hci_dev_list, list) { if (d->id == index) { hdev = hci_dev_hold(d); break; } } read_unlock(&hci_dev_list_lock); return hdev; } /* ---- Inquiry support ---- */ bool hci_discovery_active(struct hci_dev *hdev) { struct discovery_state *discov = &hdev->discovery; switch (discov->state) { case DISCOVERY_FINDING: case DISCOVERY_RESOLVING: return true; default: return false; } } void hci_discovery_set_state(struct hci_dev *hdev, int state) { int old_state = hdev->discovery.state; if (old_state == state) return; hdev->discovery.state = state; switch (state) { case DISCOVERY_STOPPED: hci_update_passive_scan(hdev); if (old_state != DISCOVERY_STARTING) mgmt_discovering(hdev, 0); break; case DISCOVERY_STARTING: break; case DISCOVERY_FINDING: mgmt_discovering(hdev, 1); break; case DISCOVERY_RESOLVING: break; case DISCOVERY_STOPPING: break; } bt_dev_dbg(hdev, "state %u -> %u", old_state, state); } void hci_inquiry_cache_flush(struct hci_dev *hdev) { struct discovery_state *cache = &hdev->discovery; struct inquiry_entry *p, *n; list_for_each_entry_safe(p, n, &cache->all, all) { list_del(&p->all); kfree(p); } INIT_LIST_HEAD(&cache->unknown); INIT_LIST_HEAD(&cache->resolve); } struct inquiry_entry *hci_inquiry_cache_lookup(struct hci_dev *hdev, bdaddr_t *bdaddr) { struct discovery_state *cache = &hdev->discovery; struct inquiry_entry *e; BT_DBG("cache %p, %pMR", cache, bdaddr); list_for_each_entry(e, &cache->all, all) { if (!bacmp(&e->data.bdaddr, bdaddr)) return e; } return NULL; } struct inquiry_entry *hci_inquiry_cache_lookup_unknown(struct hci_dev *hdev, bdaddr_t *bdaddr) { struct discovery_state *cache = &hdev->discovery; struct inquiry_entry *e; BT_DBG("cache %p, %pMR", cache, bdaddr); list_for_each_entry(e, &cache->unknown, list) { if (!bacmp(&e->data.bdaddr, bdaddr)) return e; } return NULL; } struct inquiry_entry *hci_inquiry_cache_lookup_resolve(struct hci_dev *hdev, bdaddr_t *bdaddr, int state) { struct discovery_state *cache = &hdev->discovery; struct inquiry_entry *e; BT_DBG("cache %p bdaddr %pMR state %d", cache, bdaddr, state); list_for_each_entry(e, &cache->resolve, list) { if (!bacmp(bdaddr, BDADDR_ANY) && e->name_state == state) return e; if (!bacmp(&e->data.bdaddr, bdaddr)) return e; } return NULL; } void hci_inquiry_cache_update_resolve(struct hci_dev *hdev, struct inquiry_entry *ie) { struct discovery_state *cache = &hdev->discovery; struct list_head *pos = &cache->resolve; struct inquiry_entry *p; list_del(&ie->list); list_for_each_entry(p, &cache->resolve, list) { if (p->name_state != NAME_PENDING && abs(p->data.rssi) >= abs(ie->data.rssi)) break; pos = &p->list; } list_add(&ie->list, pos); } u32 hci_inquiry_cache_update(struct hci_dev *hdev, struct inquiry_data *data, bool name_known) { struct discovery_state *cache = &hdev->discovery; struct inquiry_entry *ie; u32 flags = 0; BT_DBG("cache %p, %pMR", cache, &data->bdaddr); hci_remove_remote_oob_data(hdev, &data->bdaddr, BDADDR_BREDR); if (!data->ssp_mode) flags |= MGMT_DEV_FOUND_LEGACY_PAIRING; ie = hci_inquiry_cache_lookup(hdev, &data->bdaddr); if (ie) { if (!ie->data.ssp_mode) flags |= MGMT_DEV_FOUND_LEGACY_PAIRING; if (ie->name_state == NAME_NEEDED && data->rssi != ie->data.rssi) { ie->data.rssi = data->rssi; hci_inquiry_cache_update_resolve(hdev, ie); } goto update; } /* Entry not in the cache. Add new one. */ ie = kzalloc(sizeof(*ie), GFP_KERNEL); if (!ie) { flags |= MGMT_DEV_FOUND_CONFIRM_NAME; goto done; } list_add(&ie->all, &cache->all); if (name_known) { ie->name_state = NAME_KNOWN; } else { ie->name_state = NAME_NOT_KNOWN; list_add(&ie->list, &cache->unknown); } update: if (name_known && ie->name_state != NAME_KNOWN && ie->name_state != NAME_PENDING) { ie->name_state = NAME_KNOWN; list_del(&ie->list); } memcpy(&ie->data, data, sizeof(*data)); ie->timestamp = jiffies; cache->timestamp = jiffies; if (ie->name_state == NAME_NOT_KNOWN) flags |= MGMT_DEV_FOUND_CONFIRM_NAME; done: return flags; } static int inquiry_cache_dump(struct hci_dev *hdev, int num, __u8 *buf) { struct discovery_state *cache = &hdev->discovery; struct inquiry_info *info = (struct inquiry_info *) buf; struct inquiry_entry *e; int copied = 0; list_for_each_entry(e, &cache->all, all) { struct inquiry_data *data = &e->data; if (copied >= num) break; bacpy(&info->bdaddr, &data->bdaddr); info->pscan_rep_mode = data->pscan_rep_mode; info->pscan_period_mode = data->pscan_period_mode; info->pscan_mode = data->pscan_mode; memcpy(info->dev_class, data->dev_class, 3); info->clock_offset = data->clock_offset; info++; copied++; } BT_DBG("cache %p, copied %d", cache, copied); return copied; } int hci_inquiry(void __user *arg) { __u8 __user *ptr = arg; struct hci_inquiry_req ir; struct hci_dev *hdev; int err = 0, do_inquiry = 0, max_rsp; __u8 *buf; if (copy_from_user(&ir, ptr, sizeof(ir))) return -EFAULT; hdev = hci_dev_get(ir.dev_id); if (!hdev) return -ENODEV; if (hci_dev_test_flag(hdev, HCI_USER_CHANNEL)) { err = -EBUSY; goto done; } if (hci_dev_test_flag(hdev, HCI_UNCONFIGURED)) { err = -EOPNOTSUPP; goto done; } if (!hci_dev_test_flag(hdev, HCI_BREDR_ENABLED)) { err = -EOPNOTSUPP; goto done; } /* Restrict maximum inquiry length to 60 seconds */ if (ir.length > 60) { err = -EINVAL; goto done; } hci_dev_lock(hdev); if (inquiry_cache_age(hdev) > INQUIRY_CACHE_AGE_MAX || inquiry_cache_empty(hdev) || ir.flags & IREQ_CACHE_FLUSH) { hci_inquiry_cache_flush(hdev); do_inquiry = 1; } hci_dev_unlock(hdev); if (do_inquiry) { hci_req_sync_lock(hdev); err = hci_inquiry_sync(hdev, ir.length, ir.num_rsp); hci_req_sync_unlock(hdev); if (err < 0) goto done; /* Wait until Inquiry procedure finishes (HCI_INQUIRY flag is * cleared). If it is interrupted by a signal, return -EINTR. */ if (wait_on_bit(&hdev->flags, HCI_INQUIRY, TASK_INTERRUPTIBLE)) { err = -EINTR; goto done; } } /* for unlimited number of responses we will use buffer with * 255 entries */ max_rsp = (ir.num_rsp == 0) ? 255 : ir.num_rsp; /* cache_dump can't sleep. Therefore we allocate temp buffer and then * copy it to the user space. */ buf = kmalloc_array(max_rsp, sizeof(struct inquiry_info), GFP_KERNEL); if (!buf) { err = -ENOMEM; goto done; } hci_dev_lock(hdev); ir.num_rsp = inquiry_cache_dump(hdev, max_rsp, buf); hci_dev_unlock(hdev); BT_DBG("num_rsp %d", ir.num_rsp); if (!copy_to_user(ptr, &ir, sizeof(ir))) { ptr += sizeof(ir); if (copy_to_user(ptr, buf, sizeof(struct inquiry_info) * ir.num_rsp)) err = -EFAULT; } else err = -EFAULT; kfree(buf); done: hci_dev_put(hdev); return err; } static int hci_dev_do_open(struct hci_dev *hdev) { int ret = 0; BT_DBG("%s %p", hdev->name, hdev); hci_req_sync_lock(hdev); ret = hci_dev_open_sync(hdev); hci_req_sync_unlock(hdev); return ret; } /* ---- HCI ioctl helpers ---- */ int hci_dev_open(__u16 dev) { struct hci_dev *hdev; int err; hdev = hci_dev_get(dev); if (!hdev) return -ENODEV; /* Devices that are marked as unconfigured can only be powered * up as user channel. Trying to bring them up as normal devices * will result into a failure. Only user channel operation is * possible. * * When this function is called for a user channel, the flag * HCI_USER_CHANNEL will be set first before attempting to * open the device. */ if (hci_dev_test_flag(hdev, HCI_UNCONFIGURED) && !hci_dev_test_flag(hdev, HCI_USER_CHANNEL)) { err = -EOPNOTSUPP; goto done; } /* We need to ensure that no other power on/off work is pending * before proceeding to call hci_dev_do_open. This is * particularly important if the setup procedure has not yet * completed. */ if (hci_dev_test_and_clear_flag(hdev, HCI_AUTO_OFF)) cancel_delayed_work(&hdev->power_off); /* After this call it is guaranteed that the setup procedure * has finished. This means that error conditions like RFKILL * or no valid public or static random address apply. */ flush_workqueue(hdev->req_workqueue); /* For controllers not using the management interface and that * are brought up using legacy ioctl, set the HCI_BONDABLE bit * so that pairing works for them. Once the management interface * is in use this bit will be cleared again and userspace has * to explicitly enable it. */ if (!hci_dev_test_flag(hdev, HCI_USER_CHANNEL) && !hci_dev_test_flag(hdev, HCI_MGMT)) hci_dev_set_flag(hdev, HCI_BONDABLE); err = hci_dev_do_open(hdev); done: hci_dev_put(hdev); return err; } int hci_dev_do_close(struct hci_dev *hdev) { int err; BT_DBG("%s %p", hdev->name, hdev); hci_req_sync_lock(hdev); err = hci_dev_close_sync(hdev); hci_req_sync_unlock(hdev); return err; } int hci_dev_close(__u16 dev) { struct hci_dev *hdev; int err; hdev = hci_dev_get(dev); if (!hdev) return -ENODEV; if (hci_dev_test_flag(hdev, HCI_USER_CHANNEL)) { err = -EBUSY; goto done; } cancel_work_sync(&hdev->power_on); if (hci_dev_test_and_clear_flag(hdev, HCI_AUTO_OFF)) cancel_delayed_work(&hdev->power_off); err = hci_dev_do_close(hdev); done: hci_dev_put(hdev); return err; } static int hci_dev_do_reset(struct hci_dev *hdev) { int ret; BT_DBG("%s %p", hdev->name, hdev); hci_req_sync_lock(hdev); /* Drop queues */ skb_queue_purge(&hdev->rx_q); skb_queue_purge(&hdev->cmd_q); /* Cancel these to avoid queueing non-chained pending work */ hci_dev_set_flag(hdev, HCI_CMD_DRAIN_WORKQUEUE); /* Wait for * * if (!hci_dev_test_flag(hdev, HCI_CMD_DRAIN_WORKQUEUE)) * queue_delayed_work(&hdev->{cmd,ncmd}_timer) * * inside RCU section to see the flag or complete scheduling. */ synchronize_rcu(); /* Explicitly cancel works in case scheduled after setting the flag. */ cancel_delayed_work(&hdev->cmd_timer); cancel_delayed_work(&hdev->ncmd_timer); /* Avoid potential lockdep warnings from the *_flush() calls by * ensuring the workqueue is empty up front. */ drain_workqueue(hdev->workqueue); hci_dev_lock(hdev); hci_inquiry_cache_flush(hdev); hci_conn_hash_flush(hdev); hci_dev_unlock(hdev); if (hdev->flush) hdev->flush(hdev); hci_dev_clear_flag(hdev, HCI_CMD_DRAIN_WORKQUEUE); atomic_set(&hdev->cmd_cnt, 1); hdev->acl_cnt = 0; hdev->sco_cnt = 0; hdev->le_cnt = 0; hdev->iso_cnt = 0; ret = hci_reset_sync(hdev); hci_req_sync_unlock(hdev); return ret; } int hci_dev_reset(__u16 dev) { struct hci_dev *hdev; int err; hdev = hci_dev_get(dev); if (!hdev) return -ENODEV; if (!test_bit(HCI_UP, &hdev->flags)) { err = -ENETDOWN; goto done; } if (hci_dev_test_flag(hdev, HCI_USER_CHANNEL)) { err = -EBUSY; goto done; } if (hci_dev_test_flag(hdev, HCI_UNCONFIGURED)) { err = -EOPNOTSUPP; goto done; } err = hci_dev_do_reset(hdev); done: hci_dev_put(hdev); return err; } int hci_dev_reset_stat(__u16 dev) { struct hci_dev *hdev; int ret = 0; hdev = hci_dev_get(dev); if (!hdev) return -ENODEV; if (hci_dev_test_flag(hdev, HCI_USER_CHANNEL)) { ret = -EBUSY; goto done; } if (hci_dev_test_flag(hdev, HCI_UNCONFIGURED)) { ret = -EOPNOTSUPP; goto done; } memset(&hdev->stat, 0, sizeof(struct hci_dev_stats)); done: hci_dev_put(hdev); return ret; } static void hci_update_passive_scan_state(struct hci_dev *hdev, u8 scan) { bool conn_changed, discov_changed; BT_DBG("%s scan 0x%02x", hdev->name, scan); if ((scan & SCAN_PAGE)) conn_changed = !hci_dev_test_and_set_flag(hdev, HCI_CONNECTABLE); else conn_changed = hci_dev_test_and_clear_flag(hdev, HCI_CONNECTABLE); if ((scan & SCAN_INQUIRY)) { discov_changed = !hci_dev_test_and_set_flag(hdev, HCI_DISCOVERABLE); } else { hci_dev_clear_flag(hdev, HCI_LIMITED_DISCOVERABLE); discov_changed = hci_dev_test_and_clear_flag(hdev, HCI_DISCOVERABLE); } if (!hci_dev_test_flag(hdev, HCI_MGMT)) return; if (conn_changed || discov_changed) { /* In case this was disabled through mgmt */ hci_dev_set_flag(hdev, HCI_BREDR_ENABLED); if (hci_dev_test_flag(hdev, HCI_LE_ENABLED)) hci_update_adv_data(hdev, hdev->cur_adv_instance); mgmt_new_settings(hdev); } } int hci_dev_cmd(unsigned int cmd, void __user *arg) { struct hci_dev *hdev; struct hci_dev_req dr; __le16 policy; int err = 0; if (copy_from_user(&dr, arg, sizeof(dr))) return -EFAULT; hdev = hci_dev_get(dr.dev_id); if (!hdev) return -ENODEV; if (hci_dev_test_flag(hdev, HCI_USER_CHANNEL)) { err = -EBUSY; goto done; } if (hci_dev_test_flag(hdev, HCI_UNCONFIGURED)) { err = -EOPNOTSUPP; goto done; } if (!hci_dev_test_flag(hdev, HCI_BREDR_ENABLED)) { err = -EOPNOTSUPP; goto done; } switch (cmd) { case HCISETAUTH: err = hci_cmd_sync_status(hdev, HCI_OP_WRITE_AUTH_ENABLE, 1, &dr.dev_opt, HCI_CMD_TIMEOUT); break; case HCISETENCRYPT: if (!lmp_encrypt_capable(hdev)) { err = -EOPNOTSUPP; break; } if (!test_bit(HCI_AUTH, &hdev->flags)) { /* Auth must be enabled first */ err = hci_cmd_sync_status(hdev, HCI_OP_WRITE_AUTH_ENABLE, 1, &dr.dev_opt, HCI_CMD_TIMEOUT); if (err) break; } err = hci_cmd_sync_status(hdev, HCI_OP_WRITE_ENCRYPT_MODE, 1, &dr.dev_opt, HCI_CMD_TIMEOUT); break; case HCISETSCAN: err = hci_cmd_sync_status(hdev, HCI_OP_WRITE_SCAN_ENABLE, 1, &dr.dev_opt, HCI_CMD_TIMEOUT); /* Ensure that the connectable and discoverable states * get correctly modified as this was a non-mgmt change. */ if (!err) hci_update_passive_scan_state(hdev, dr.dev_opt); break; case HCISETLINKPOL: policy = cpu_to_le16(dr.dev_opt); err = hci_cmd_sync_status(hdev, HCI_OP_WRITE_DEF_LINK_POLICY, 2, &policy, HCI_CMD_TIMEOUT); break; case HCISETLINKMODE: hdev->link_mode = ((__u16) dr.dev_opt) & (HCI_LM_MASTER | HCI_LM_ACCEPT); break; case HCISETPTYPE: if (hdev->pkt_type == (__u16) dr.dev_opt) break; hdev->pkt_type = (__u16) dr.dev_opt; mgmt_phy_configuration_changed(hdev, NULL); break; case HCISETACLMTU: hdev->acl_mtu = *((__u16 *) &dr.dev_opt + 1); hdev->acl_pkts = *((__u16 *) &dr.dev_opt + 0); break; case HCISETSCOMTU: hdev->sco_mtu = *((__u16 *) &dr.dev_opt + 1); hdev->sco_pkts = *((__u16 *) &dr.dev_opt + 0); break; default: err = -EINVAL; break; } done: hci_dev_put(hdev); return err; } int hci_get_dev_list(void __user *arg) { struct hci_dev *hdev; struct hci_dev_list_req *dl; struct hci_dev_req *dr; int n = 0, err; __u16 dev_num; if (get_user(dev_num, (__u16 __user *) arg)) return -EFAULT; if (!dev_num || dev_num > (PAGE_SIZE * 2) / sizeof(*dr)) return -EINVAL; dl = kzalloc(struct_size(dl, dev_req, dev_num), GFP_KERNEL); if (!dl) return -ENOMEM; dl->dev_num = dev_num; dr = dl->dev_req; read_lock(&hci_dev_list_lock); list_for_each_entry(hdev, &hci_dev_list, list) { unsigned long flags = hdev->flags; /* When the auto-off is configured it means the transport * is running, but in that case still indicate that the * device is actually down. */ if (hci_dev_test_flag(hdev, HCI_AUTO_OFF)) flags &= ~BIT(HCI_UP); dr[n].dev_id = hdev->id; dr[n].dev_opt = flags; if (++n >= dev_num) break; } read_unlock(&hci_dev_list_lock); dl->dev_num = n; err = copy_to_user(arg, dl, struct_size(dl, dev_req, n)); kfree(dl); return err ? -EFAULT : 0; } int hci_get_dev_info(void __user *arg) { struct hci_dev *hdev; struct hci_dev_info di; unsigned long flags; int err = 0; if (copy_from_user(&di, arg, sizeof(di))) return -EFAULT; hdev = hci_dev_get(di.dev_id); if (!hdev) return -ENODEV; /* When the auto-off is configured it means the transport * is running, but in that case still indicate that the * device is actually down. */ if (hci_dev_test_flag(hdev, HCI_AUTO_OFF)) flags = hdev->flags & ~BIT(HCI_UP); else flags = hdev->flags; strscpy(di.name, hdev->name, sizeof(di.name)); di.bdaddr = hdev->bdaddr; di.type = (hdev->bus & 0x0f); di.flags = flags; di.pkt_type = hdev->pkt_type; if (lmp_bredr_capable(hdev)) { di.acl_mtu = hdev->acl_mtu; di.acl_pkts = hdev->acl_pkts; di.sco_mtu = hdev->sco_mtu; di.sco_pkts = hdev->sco_pkts; } else { di.acl_mtu = hdev->le_mtu; di.acl_pkts = hdev->le_pkts; di.sco_mtu = 0; di.sco_pkts = 0; } di.link_policy = hdev->link_policy; di.link_mode = hdev->link_mode; memcpy(&di.stat, &hdev->stat, sizeof(di.stat)); memcpy(&di.features, &hdev->features, sizeof(di.features)); if (copy_to_user(arg, &di, sizeof(di))) err = -EFAULT; hci_dev_put(hdev); return err; } /* ---- Interface to HCI drivers ---- */ static int hci_dev_do_poweroff(struct hci_dev *hdev) { int err; BT_DBG("%s %p", hdev->name, hdev); hci_req_sync_lock(hdev); err = hci_set_powered_sync(hdev, false); hci_req_sync_unlock(hdev); return err; } static int hci_rfkill_set_block(void *data, bool blocked) { struct hci_dev *hdev = data; int err; BT_DBG("%p name %s blocked %d", hdev, hdev->name, blocked); if (hci_dev_test_flag(hdev, HCI_USER_CHANNEL)) return -EBUSY; if (blocked == hci_dev_test_flag(hdev, HCI_RFKILLED)) return 0; if (blocked) { hci_dev_set_flag(hdev, HCI_RFKILLED); if (!hci_dev_test_flag(hdev, HCI_SETUP) && !hci_dev_test_flag(hdev, HCI_CONFIG)) { err = hci_dev_do_poweroff(hdev); if (err) { bt_dev_err(hdev, "Error when powering off device on rfkill (%d)", err); /* Make sure the device is still closed even if * anything during power off sequence (eg. * disconnecting devices) failed. */ hci_dev_do_close(hdev); } } } else { hci_dev_clear_flag(hdev, HCI_RFKILLED); } return 0; } static const struct rfkill_ops hci_rfkill_ops = { .set_block = hci_rfkill_set_block, }; static void hci_power_on(struct work_struct *work) { struct hci_dev *hdev = container_of(work, struct hci_dev, power_on); int err; BT_DBG("%s", hdev->name); if (test_bit(HCI_UP, &hdev->flags) && hci_dev_test_flag(hdev, HCI_MGMT) && hci_dev_test_and_clear_flag(hdev, HCI_AUTO_OFF)) { cancel_delayed_work(&hdev->power_off); err = hci_powered_update_sync(hdev); mgmt_power_on(hdev, err); return; } err = hci_dev_do_open(hdev); if (err < 0) { hci_dev_lock(hdev); mgmt_set_powered_failed(hdev, err); hci_dev_unlock(hdev); return; } /* During the HCI setup phase, a few error conditions are * ignored and they need to be checked now. If they are still * valid, it is important to turn the device back off. */ if (hci_dev_test_flag(hdev, HCI_RFKILLED) || hci_dev_test_flag(hdev, HCI_UNCONFIGURED) || (!bacmp(&hdev->bdaddr, BDADDR_ANY) && !bacmp(&hdev->static_addr, BDADDR_ANY))) { hci_dev_clear_flag(hdev, HCI_AUTO_OFF); hci_dev_do_close(hdev); } else if (hci_dev_test_flag(hdev, HCI_AUTO_OFF)) { queue_delayed_work(hdev->req_workqueue, &hdev->power_off, HCI_AUTO_OFF_TIMEOUT); } if (hci_dev_test_and_clear_flag(hdev, HCI_SETUP)) { /* For unconfigured devices, set the HCI_RAW flag * so that userspace can easily identify them. */ if (hci_dev_test_flag(hdev, HCI_UNCONFIGURED)) set_bit(HCI_RAW, &hdev->flags); /* For fully configured devices, this will send * the Index Added event. For unconfigured devices, * it will send Unconfigued Index Added event. * * Devices with HCI_QUIRK_RAW_DEVICE are ignored * and no event will be send. */ mgmt_index_added(hdev); } else if (hci_dev_test_and_clear_flag(hdev, HCI_CONFIG)) { /* When the controller is now configured, then it * is important to clear the HCI_RAW flag. */ if (!hci_dev_test_flag(hdev, HCI_UNCONFIGURED)) clear_bit(HCI_RAW, &hdev->flags); /* Powering on the controller with HCI_CONFIG set only * happens with the transition from unconfigured to * configured. This will send the Index Added event. */ mgmt_index_added(hdev); } } static void hci_power_off(struct work_struct *work) { struct hci_dev *hdev = container_of(work, struct hci_dev, power_off.work); BT_DBG("%s", hdev->name); hci_dev_do_close(hdev); } static void hci_error_reset(struct work_struct *work) { struct hci_dev *hdev = container_of(work, struct hci_dev, error_reset); hci_dev_hold(hdev); BT_DBG("%s", hdev->name); if (hdev->hw_error) hdev->hw_error(hdev, hdev->hw_error_code); else bt_dev_err(hdev, "hardware error 0x%2.2x", hdev->hw_error_code); if (!hci_dev_do_close(hdev)) hci_dev_do_open(hdev); hci_dev_put(hdev); } void hci_uuids_clear(struct hci_dev *hdev) { struct bt_uuid *uuid, *tmp; list_for_each_entry_safe(uuid, tmp, &hdev->uuids, list) { list_del(&uuid->list); kfree(uuid); } } void hci_link_keys_clear(struct hci_dev *hdev) { struct link_key *key, *tmp; list_for_each_entry_safe(key, tmp, &hdev->link_keys, list) { list_del_rcu(&key->list); kfree_rcu(key, rcu); } } void hci_smp_ltks_clear(struct hci_dev *hdev) { struct smp_ltk *k, *tmp; list_for_each_entry_safe(k, tmp, &hdev->long_term_keys, list) { list_del_rcu(&k->list); kfree_rcu(k, rcu); } } void hci_smp_irks_clear(struct hci_dev *hdev) { struct smp_irk *k, *tmp; list_for_each_entry_safe(k, tmp, &hdev->identity_resolving_keys, list) { list_del_rcu(&k->list); kfree_rcu(k, rcu); } } void hci_blocked_keys_clear(struct hci_dev *hdev) { struct blocked_key *b, *tmp; list_for_each_entry_safe(b, tmp, &hdev->blocked_keys, list) { list_del_rcu(&b->list); kfree_rcu(b, rcu); } } bool hci_is_blocked_key(struct hci_dev *hdev, u8 type, u8 val[16]) { bool blocked = false; struct blocked_key *b; rcu_read_lock(); list_for_each_entry_rcu(b, &hdev->blocked_keys, list) { if (b->type == type && !memcmp(b->val, val, sizeof(b->val))) { blocked = true; break; } } rcu_read_unlock(); return blocked; } struct link_key *hci_find_link_key(struct hci_dev *hdev, bdaddr_t *bdaddr) { struct link_key *k; rcu_read_lock(); list_for_each_entry_rcu(k, &hdev->link_keys, list) { if (bacmp(bdaddr, &k->bdaddr) == 0) { rcu_read_unlock(); if (hci_is_blocked_key(hdev, HCI_BLOCKED_KEY_TYPE_LINKKEY, k->val)) { bt_dev_warn_ratelimited(hdev, "Link key blocked for %pMR", &k->bdaddr); return NULL; } return k; } } rcu_read_unlock(); return NULL; } static bool hci_persistent_key(struct hci_dev *hdev, struct hci_conn *conn, u8 key_type, u8 old_key_type) { /* Legacy key */ if (key_type < 0x03) return true; /* Debug keys are insecure so don't store them persistently */ if (key_type == HCI_LK_DEBUG_COMBINATION) return false; /* Changed combination key and there's no previous one */ if (key_type == HCI_LK_CHANGED_COMBINATION && old_key_type == 0xff) return false; /* Security mode 3 case */ if (!conn) return true; /* BR/EDR key derived using SC from an LE link */ if (conn->type == LE_LINK) return true; /* Neither local nor remote side had no-bonding as requirement */ if (conn->auth_type > 0x01 && conn->remote_auth > 0x01) return true; /* Local side had dedicated bonding as requirement */ if (conn->auth_type == 0x02 || conn->auth_type == 0x03) return true; /* Remote side had dedicated bonding as requirement */ if (conn->remote_auth == 0x02 || conn->remote_auth == 0x03) return true; /* If none of the above criteria match, then don't store the key * persistently */ return false; } static u8 ltk_role(u8 type) { if (type == SMP_LTK) return HCI_ROLE_MASTER; return HCI_ROLE_SLAVE; } struct smp_ltk *hci_find_ltk(struct hci_dev *hdev, bdaddr_t *bdaddr, u8 addr_type, u8 role) { struct smp_ltk *k; rcu_read_lock(); list_for_each_entry_rcu(k, &hdev->long_term_keys, list) { if (addr_type != k->bdaddr_type || bacmp(bdaddr, &k->bdaddr)) continue; if (smp_ltk_is_sc(k) || ltk_role(k->type) == role) { rcu_read_unlock(); if (hci_is_blocked_key(hdev, HCI_BLOCKED_KEY_TYPE_LTK, k->val)) { bt_dev_warn_ratelimited(hdev, "LTK blocked for %pMR", &k->bdaddr); return NULL; } return k; } } rcu_read_unlock(); return NULL; } struct smp_irk *hci_find_irk_by_rpa(struct hci_dev *hdev, bdaddr_t *rpa) { struct smp_irk *irk_to_return = NULL; struct smp_irk *irk; rcu_read_lock(); list_for_each_entry_rcu(irk, &hdev->identity_resolving_keys, list) { if (!bacmp(&irk->rpa, rpa)) { irk_to_return = irk; goto done; } } list_for_each_entry_rcu(irk, &hdev->identity_resolving_keys, list) { if (smp_irk_matches(hdev, irk->val, rpa)) { bacpy(&irk->rpa, rpa); irk_to_return = irk; goto done; } } done: if (irk_to_return && hci_is_blocked_key(hdev, HCI_BLOCKED_KEY_TYPE_IRK, irk_to_return->val)) { bt_dev_warn_ratelimited(hdev, "Identity key blocked for %pMR", &irk_to_return->bdaddr); irk_to_return = NULL; } rcu_read_unlock(); return irk_to_return; } struct smp_irk *hci_find_irk_by_addr(struct hci_dev *hdev, bdaddr_t *bdaddr, u8 addr_type) { struct smp_irk *irk_to_return = NULL; struct smp_irk *irk; /* Identity Address must be public or static random */ if (addr_type == ADDR_LE_DEV_RANDOM && (bdaddr->b[5] & 0xc0) != 0xc0) return NULL; rcu_read_lock(); list_for_each_entry_rcu(irk, &hdev->identity_resolving_keys, list) { if (addr_type == irk->addr_type && bacmp(bdaddr, &irk->bdaddr) == 0) { irk_to_return = irk; goto done; } } done: if (irk_to_return && hci_is_blocked_key(hdev, HCI_BLOCKED_KEY_TYPE_IRK, irk_to_return->val)) { bt_dev_warn_ratelimited(hdev, "Identity key blocked for %pMR", &irk_to_return->bdaddr); irk_to_return = NULL; } rcu_read_unlock(); return irk_to_return; } struct link_key *hci_add_link_key(struct hci_dev *hdev, struct hci_conn *conn, bdaddr_t *bdaddr, u8 *val, u8 type, u8 pin_len, bool *persistent) { struct link_key *key, *old_key; u8 old_key_type; old_key = hci_find_link_key(hdev, bdaddr); if (old_key) { old_key_type = old_key->type; key = old_key; } else { old_key_type = conn ? conn->key_type : 0xff; key = kzalloc(sizeof(*key), GFP_KERNEL); if (!key) return NULL; list_add_rcu(&key->list, &hdev->link_keys); } BT_DBG("%s key for %pMR type %u", hdev->name, bdaddr, type); /* Some buggy controller combinations generate a changed * combination key for legacy pairing even when there's no * previous key */ if (type == HCI_LK_CHANGED_COMBINATION && (!conn || conn->remote_auth == 0xff) && old_key_type == 0xff) { type = HCI_LK_COMBINATION; if (conn) conn->key_type = type; } bacpy(&key->bdaddr, bdaddr); memcpy(key->val, val, HCI_LINK_KEY_SIZE); key->pin_len = pin_len; if (type == HCI_LK_CHANGED_COMBINATION) key->type = old_key_type; else key->type = type; if (persistent) *persistent = hci_persistent_key(hdev, conn, type, old_key_type); return key; } struct smp_ltk *hci_add_ltk(struct hci_dev *hdev, bdaddr_t *bdaddr, u8 addr_type, u8 type, u8 authenticated, u8 tk[16], u8 enc_size, __le16 ediv, __le64 rand) { struct smp_ltk *key, *old_key; u8 role = ltk_role(type); old_key = hci_find_ltk(hdev, bdaddr, addr_type, role); if (old_key) key = old_key; else { key = kzalloc(sizeof(*key), GFP_KERNEL); if (!key) return NULL; list_add_rcu(&key->list, &hdev->long_term_keys); } bacpy(&key->bdaddr, bdaddr); key->bdaddr_type = addr_type; memcpy(key->val, tk, sizeof(key->val)); key->authenticated = authenticated; key->ediv = ediv; key->rand = rand; key->enc_size = enc_size; key->type = type; return key; } struct smp_irk *hci_add_irk(struct hci_dev *hdev, bdaddr_t *bdaddr, u8 addr_type, u8 val[16], bdaddr_t *rpa) { struct smp_irk *irk; irk = hci_find_irk_by_addr(hdev, bdaddr, addr_type); if (!irk) { irk = kzalloc(sizeof(*irk), GFP_KERNEL); if (!irk) return NULL; bacpy(&irk->bdaddr, bdaddr); irk->addr_type = addr_type; list_add_rcu(&irk->list, &hdev->identity_resolving_keys); } memcpy(irk->val, val, 16); bacpy(&irk->rpa, rpa); return irk; } int hci_remove_link_key(struct hci_dev *hdev, bdaddr_t *bdaddr) { struct link_key *key; key = hci_find_link_key(hdev, bdaddr); if (!key) return -ENOENT; BT_DBG("%s removing %pMR", hdev->name, bdaddr); list_del_rcu(&key->list); kfree_rcu(key, rcu); return 0; } int hci_remove_ltk(struct hci_dev *hdev, bdaddr_t *bdaddr, u8 bdaddr_type) { struct smp_ltk *k, *tmp; int removed = 0; list_for_each_entry_safe(k, tmp, &hdev->long_term_keys, list) { if (bacmp(bdaddr, &k->bdaddr) || k->bdaddr_type != bdaddr_type) continue; BT_DBG("%s removing %pMR", hdev->name, bdaddr); list_del_rcu(&k->list); kfree_rcu(k, rcu); removed++; } return removed ? 0 : -ENOENT; } void hci_remove_irk(struct hci_dev *hdev, bdaddr_t *bdaddr, u8 addr_type) { struct smp_irk *k, *tmp; list_for_each_entry_safe(k, tmp, &hdev->identity_resolving_keys, list) { if (bacmp(bdaddr, &k->bdaddr) || k->addr_type != addr_type) continue; BT_DBG("%s removing %pMR", hdev->name, bdaddr); list_del_rcu(&k->list); kfree_rcu(k, rcu); } } bool hci_bdaddr_is_paired(struct hci_dev *hdev, bdaddr_t *bdaddr, u8 type) { struct smp_ltk *k; struct smp_irk *irk; u8 addr_type; if (type == BDADDR_BREDR) { if (hci_find_link_key(hdev, bdaddr)) return true; return false; } /* Convert to HCI addr type which struct smp_ltk uses */ if (type == BDADDR_LE_PUBLIC) addr_type = ADDR_LE_DEV_PUBLIC; else addr_type = ADDR_LE_DEV_RANDOM; irk = hci_get_irk(hdev, bdaddr, addr_type); if (irk) { bdaddr = &irk->bdaddr; addr_type = irk->addr_type; } rcu_read_lock(); list_for_each_entry_rcu(k, &hdev->long_term_keys, list) { if (k->bdaddr_type == addr_type && !bacmp(bdaddr, &k->bdaddr)) { rcu_read_unlock(); return true; } } rcu_read_unlock(); return false; } /* HCI command timer function */ static void hci_cmd_timeout(struct work_struct *work) { struct hci_dev *hdev = container_of(work, struct hci_dev, cmd_timer.work); if (hdev->req_skb) { u16 opcode = hci_skb_opcode(hdev->req_skb); bt_dev_err(hdev, "command 0x%4.4x tx timeout", opcode); hci_cmd_sync_cancel_sync(hdev, ETIMEDOUT); } else { bt_dev_err(hdev, "command tx timeout"); } if (hdev->reset) hdev->reset(hdev); atomic_set(&hdev->cmd_cnt, 1); queue_work(hdev->workqueue, &hdev->cmd_work); } /* HCI ncmd timer function */ static void hci_ncmd_timeout(struct work_struct *work) { struct hci_dev *hdev = container_of(work, struct hci_dev, ncmd_timer.work); bt_dev_err(hdev, "Controller not accepting commands anymore: ncmd = 0"); /* During HCI_INIT phase no events can be injected if the ncmd timer * triggers since the procedure has its own timeout handling. */ if (test_bit(HCI_INIT, &hdev->flags)) return; /* This is an irrecoverable state, inject hardware error event */ hci_reset_dev(hdev); } struct oob_data *hci_find_remote_oob_data(struct hci_dev *hdev, bdaddr_t *bdaddr, u8 bdaddr_type) { struct oob_data *data; list_for_each_entry(data, &hdev->remote_oob_data, list) { if (bacmp(bdaddr, &data->bdaddr) != 0) continue; if (data->bdaddr_type != bdaddr_type) continue; return data; } return NULL; } int hci_remove_remote_oob_data(struct hci_dev *hdev, bdaddr_t *bdaddr, u8 bdaddr_type) { struct oob_data *data; data = hci_find_remote_oob_data(hdev, bdaddr, bdaddr_type); if (!data) return -ENOENT; BT_DBG("%s removing %pMR (%u)", hdev->name, bdaddr, bdaddr_type); list_del(&data->list); kfree(data); return 0; } void hci_remote_oob_data_clear(struct hci_dev *hdev) { struct oob_data *data, *n; list_for_each_entry_safe(data, n, &hdev->remote_oob_data, list) { list_del(&data->list); kfree(data); } } int hci_add_remote_oob_data(struct hci_dev *hdev, bdaddr_t *bdaddr, u8 bdaddr_type, u8 *hash192, u8 *rand192, u8 *hash256, u8 *rand256) { struct oob_data *data; data = hci_find_remote_oob_data(hdev, bdaddr, bdaddr_type); if (!data) { data = kmalloc(sizeof(*data), GFP_KERNEL); if (!data) return -ENOMEM; bacpy(&data->bdaddr, bdaddr); data->bdaddr_type = bdaddr_type; list_add(&data->list, &hdev->remote_oob_data); } if (hash192 && rand192) { memcpy(data->hash192, hash192, sizeof(data->hash192)); memcpy(data->rand192, rand192, sizeof(data->rand192)); if (hash256 && rand256) data->present = 0x03; } else { memset(data->hash192, 0, sizeof(data->hash192)); memset(data->rand192, 0, sizeof(data->rand192)); if (hash256 && rand256) data->present = 0x02; else data->present = 0x00; } if (hash256 && rand256) { memcpy(data->hash256, hash256, sizeof(data->hash256)); memcpy(data->rand256, rand256, sizeof(data->rand256)); } else { memset(data->hash256, 0, sizeof(data->hash256)); memset(data->rand256, 0, sizeof(data->rand256)); if (hash192 && rand192) data->present = 0x01; } BT_DBG("%s for %pMR", hdev->name, bdaddr); return 0; } /* This function requires the caller holds hdev->lock */ struct adv_info *hci_find_adv_instance(struct hci_dev *hdev, u8 instance) { struct adv_info *adv_instance; list_for_each_entry(adv_instance, &hdev->adv_instances, list) { if (adv_instance->instance == instance) return adv_instance; } return NULL; } /* This function requires the caller holds hdev->lock */ struct adv_info *hci_get_next_instance(struct hci_dev *hdev, u8 instance) { struct adv_info *cur_instance; cur_instance = hci_find_adv_instance(hdev, instance); if (!cur_instance) return NULL; if (cur_instance == list_last_entry(&hdev->adv_instances, struct adv_info, list)) return list_first_entry(&hdev->adv_instances, struct adv_info, list); else return list_next_entry(cur_instance, list); } /* This function requires the caller holds hdev->lock */ int hci_remove_adv_instance(struct hci_dev *hdev, u8 instance) { struct adv_info *adv_instance; adv_instance = hci_find_adv_instance(hdev, instance); if (!adv_instance) return -ENOENT; BT_DBG("%s removing %dMR", hdev->name, instance); if (hdev->cur_adv_instance == instance) { if (hdev->adv_instance_timeout) { cancel_delayed_work(&hdev->adv_instance_expire); hdev->adv_instance_timeout = 0; } hdev->cur_adv_instance = 0x00; } cancel_delayed_work_sync(&adv_instance->rpa_expired_cb); list_del(&adv_instance->list); kfree(adv_instance); hdev->adv_instance_cnt--; return 0; } void hci_adv_instances_set_rpa_expired(struct hci_dev *hdev, bool rpa_expired) { struct adv_info *adv_instance, *n; list_for_each_entry_safe(adv_instance, n, &hdev->adv_instances, list) adv_instance->rpa_expired = rpa_expired; } /* This function requires the caller holds hdev->lock */ void hci_adv_instances_clear(struct hci_dev *hdev) { struct adv_info *adv_instance, *n; if (hdev->adv_instance_timeout) { disable_delayed_work(&hdev->adv_instance_expire); hdev->adv_instance_timeout = 0; } list_for_each_entry_safe(adv_instance, n, &hdev->adv_instances, list) { disable_delayed_work_sync(&adv_instance->rpa_expired_cb); list_del(&adv_instance->list); kfree(adv_instance); } hdev->adv_instance_cnt = 0; hdev->cur_adv_instance = 0x00; } static void adv_instance_rpa_expired(struct work_struct *work) { struct adv_info *adv_instance = container_of(work, struct adv_info, rpa_expired_cb.work); BT_DBG(""); adv_instance->rpa_expired = true; } /* This function requires the caller holds hdev->lock */ struct adv_info *hci_add_adv_instance(struct hci_dev *hdev, u8 instance, u32 flags, u16 adv_data_len, u8 *adv_data, u16 scan_rsp_len, u8 *scan_rsp_data, u16 timeout, u16 duration, s8 tx_power, u32 min_interval, u32 max_interval, u8 mesh_handle) { struct adv_info *adv; adv = hci_find_adv_instance(hdev, instance); if (adv) { memset(adv->adv_data, 0, sizeof(adv->adv_data)); memset(adv->scan_rsp_data, 0, sizeof(adv->scan_rsp_data)); memset(adv->per_adv_data, 0, sizeof(adv->per_adv_data)); } else { if (hdev->adv_instance_cnt >= hdev->le_num_of_adv_sets || instance < 1 || instance > hdev->le_num_of_adv_sets + 1) return ERR_PTR(-EOVERFLOW); adv = kzalloc(sizeof(*adv), GFP_KERNEL); if (!adv) return ERR_PTR(-ENOMEM); adv->pending = true; adv->instance = instance; /* If controller support only one set and the instance is set to * 1 then there is no option other than using handle 0x00. */ if (hdev->le_num_of_adv_sets == 1 && instance == 1) adv->handle = 0x00; else adv->handle = instance; list_add(&adv->list, &hdev->adv_instances); hdev->adv_instance_cnt++; } adv->flags = flags; adv->min_interval = min_interval; adv->max_interval = max_interval; adv->tx_power = tx_power; /* Defining a mesh_handle changes the timing units to ms, * rather than seconds, and ties the instance to the requested * mesh_tx queue. */ adv->mesh = mesh_handle; hci_set_adv_instance_data(hdev, instance, adv_data_len, adv_data, scan_rsp_len, scan_rsp_data); adv->timeout = timeout; adv->remaining_time = timeout; if (duration == 0) adv->duration = hdev->def_multi_adv_rotation_duration; else adv->duration = duration; INIT_DELAYED_WORK(&adv->rpa_expired_cb, adv_instance_rpa_expired); BT_DBG("%s for %dMR", hdev->name, instance); return adv; } /* This function requires the caller holds hdev->lock */ struct adv_info *hci_add_per_instance(struct hci_dev *hdev, u8 instance, u32 flags, u8 data_len, u8 *data, u32 min_interval, u32 max_interval) { struct adv_info *adv; adv = hci_add_adv_instance(hdev, instance, flags, 0, NULL, 0, NULL, 0, 0, HCI_ADV_TX_POWER_NO_PREFERENCE, min_interval, max_interval, 0); if (IS_ERR(adv)) return adv; adv->periodic = true; adv->per_adv_data_len = data_len; if (data) memcpy(adv->per_adv_data, data, data_len); return adv; } /* This function requires the caller holds hdev->lock */ int hci_set_adv_instance_data(struct hci_dev *hdev, u8 instance, u16 adv_data_len, u8 *adv_data, u16 scan_rsp_len, u8 *scan_rsp_data) { struct adv_info *adv; adv = hci_find_adv_instance(hdev, instance); /* If advertisement doesn't exist, we can't modify its data */ if (!adv) return -ENOENT; if (adv_data_len && ADV_DATA_CMP(adv, adv_data, adv_data_len)) { memset(adv->adv_data, 0, sizeof(adv->adv_data)); memcpy(adv->adv_data, adv_data, adv_data_len); adv->adv_data_len = adv_data_len; adv->adv_data_changed = true; } if (scan_rsp_len && SCAN_RSP_CMP(adv, scan_rsp_data, scan_rsp_len)) { memset(adv->scan_rsp_data, 0, sizeof(adv->scan_rsp_data)); memcpy(adv->scan_rsp_data, scan_rsp_data, scan_rsp_len); adv->scan_rsp_len = scan_rsp_len; adv->scan_rsp_changed = true; } /* Mark as changed if there are flags which would affect it */ if (((adv->flags & MGMT_ADV_FLAG_APPEARANCE) && hdev->appearance) || adv->flags & MGMT_ADV_FLAG_LOCAL_NAME) adv->scan_rsp_changed = true; return 0; } /* This function requires the caller holds hdev->lock */ u32 hci_adv_instance_flags(struct hci_dev *hdev, u8 instance) { u32 flags; struct adv_info *adv; if (instance == 0x00) { /* Instance 0 always manages the "Tx Power" and "Flags" * fields */ flags = MGMT_ADV_FLAG_TX_POWER | MGMT_ADV_FLAG_MANAGED_FLAGS; /* For instance 0, the HCI_ADVERTISING_CONNECTABLE setting * corresponds to the "connectable" instance flag. */ if (hci_dev_test_flag(hdev, HCI_ADVERTISING_CONNECTABLE)) flags |= MGMT_ADV_FLAG_CONNECTABLE; if (hci_dev_test_flag(hdev, HCI_LIMITED_DISCOVERABLE)) flags |= MGMT_ADV_FLAG_LIMITED_DISCOV; else if (hci_dev_test_flag(hdev, HCI_DISCOVERABLE)) flags |= MGMT_ADV_FLAG_DISCOV; return flags; } adv = hci_find_adv_instance(hdev, instance); /* Return 0 when we got an invalid instance identifier. */ if (!adv) return 0; return adv->flags; } bool hci_adv_instance_is_scannable(struct hci_dev *hdev, u8 instance) { struct adv_info *adv; /* Instance 0x00 always set local name */ if (instance == 0x00) return true; adv = hci_find_adv_instance(hdev, instance); if (!adv) return false; if (adv->flags & MGMT_ADV_FLAG_APPEARANCE || adv->flags & MGMT_ADV_FLAG_LOCAL_NAME) return true; return adv->scan_rsp_len ? true : false; } /* This function requires the caller holds hdev->lock */ void hci_adv_monitors_clear(struct hci_dev *hdev) { struct adv_monitor *monitor; int handle; idr_for_each_entry(&hdev->adv_monitors_idr, monitor, handle) hci_free_adv_monitor(hdev, monitor); idr_destroy(&hdev->adv_monitors_idr); } /* Frees the monitor structure and do some bookkeepings. * This function requires the caller holds hdev->lock. */ void hci_free_adv_monitor(struct hci_dev *hdev, struct adv_monitor *monitor) { struct adv_pattern *pattern; struct adv_pattern *tmp; if (!monitor) return; list_for_each_entry_safe(pattern, tmp, &monitor->patterns, list) { list_del(&pattern->list); kfree(pattern); } if (monitor->handle) idr_remove(&hdev->adv_monitors_idr, monitor->handle); if (monitor->state != ADV_MONITOR_STATE_NOT_REGISTERED) { hdev->adv_monitors_cnt--; mgmt_adv_monitor_removed(hdev, monitor->handle); } kfree(monitor); } /* Assigns handle to a monitor, and if offloading is supported and power is on, * also attempts to forward the request to the controller. * This function requires the caller holds hci_req_sync_lock. */ int hci_add_adv_monitor(struct hci_dev *hdev, struct adv_monitor *monitor) { int min, max, handle; int status = 0; if (!monitor) return -EINVAL; hci_dev_lock(hdev); min = HCI_MIN_ADV_MONITOR_HANDLE; max = HCI_MIN_ADV_MONITOR_HANDLE + HCI_MAX_ADV_MONITOR_NUM_HANDLES; handle = idr_alloc(&hdev->adv_monitors_idr, monitor, min, max, GFP_KERNEL); hci_dev_unlock(hdev); if (handle < 0) return handle; monitor->handle = handle; if (!hdev_is_powered(hdev)) return status; switch (hci_get_adv_monitor_offload_ext(hdev)) { case HCI_ADV_MONITOR_EXT_NONE: bt_dev_dbg(hdev, "add monitor %d status %d", monitor->handle, status); /* Message was not forwarded to controller - not an error */ break; case HCI_ADV_MONITOR_EXT_MSFT: status = msft_add_monitor_pattern(hdev, monitor); bt_dev_dbg(hdev, "add monitor %d msft status %d", handle, status); break; } return status; } /* Attempts to tell the controller and free the monitor. If somehow the * controller doesn't have a corresponding handle, remove anyway. * This function requires the caller holds hci_req_sync_lock. */ static int hci_remove_adv_monitor(struct hci_dev *hdev, struct adv_monitor *monitor) { int status = 0; int handle; switch (hci_get_adv_monitor_offload_ext(hdev)) { case HCI_ADV_MONITOR_EXT_NONE: /* also goes here when powered off */ bt_dev_dbg(hdev, "remove monitor %d status %d", monitor->handle, status); goto free_monitor; case HCI_ADV_MONITOR_EXT_MSFT: handle = monitor->handle; status = msft_remove_monitor(hdev, monitor); bt_dev_dbg(hdev, "remove monitor %d msft status %d", handle, status); break; } /* In case no matching handle registered, just free the monitor */ if (status == -ENOENT) goto free_monitor; return status; free_monitor: if (status == -ENOENT) bt_dev_warn(hdev, "Removing monitor with no matching handle %d", monitor->handle); hci_free_adv_monitor(hdev, monitor); return status; } /* This function requires the caller holds hci_req_sync_lock */ int hci_remove_single_adv_monitor(struct hci_dev *hdev, u16 handle) { struct adv_monitor *monitor = idr_find(&hdev->adv_monitors_idr, handle); if (!monitor) return -EINVAL; return hci_remove_adv_monitor(hdev, monitor); } /* This function requires the caller holds hci_req_sync_lock */ int hci_remove_all_adv_monitor(struct hci_dev *hdev) { struct adv_monitor *monitor; int idr_next_id = 0; int status = 0; while (1) { monitor = idr_get_next(&hdev->adv_monitors_idr, &idr_next_id); if (!monitor) break; status = hci_remove_adv_monitor(hdev, monitor); if (status) return status; idr_next_id++; } return status; } /* This function requires the caller holds hdev->lock */ bool hci_is_adv_monitoring(struct hci_dev *hdev) { return !idr_is_empty(&hdev->adv_monitors_idr); } int hci_get_adv_monitor_offload_ext(struct hci_dev *hdev) { if (msft_monitor_supported(hdev)) return HCI_ADV_MONITOR_EXT_MSFT; return HCI_ADV_MONITOR_EXT_NONE; } struct bdaddr_list *hci_bdaddr_list_lookup(struct list_head *bdaddr_list, bdaddr_t *bdaddr, u8 type) { struct bdaddr_list *b; list_for_each_entry(b, bdaddr_list, list) { if (!bacmp(&b->bdaddr, bdaddr) && b->bdaddr_type == type) return b; } return NULL; } struct bdaddr_list_with_irk *hci_bdaddr_list_lookup_with_irk( struct list_head *bdaddr_list, bdaddr_t *bdaddr, u8 type) { struct bdaddr_list_with_irk *b; list_for_each_entry(b, bdaddr_list, list) { if (!bacmp(&b->bdaddr, bdaddr) && b->bdaddr_type == type) return b; } return NULL; } struct bdaddr_list_with_flags * hci_bdaddr_list_lookup_with_flags(struct list_head *bdaddr_list, bdaddr_t *bdaddr, u8 type) { struct bdaddr_list_with_flags *b; list_for_each_entry(b, bdaddr_list, list) { if (!bacmp(&b->bdaddr, bdaddr) && b->bdaddr_type == type) return b; } return NULL; } void hci_bdaddr_list_clear(struct list_head *bdaddr_list) { struct bdaddr_list *b, *n; list_for_each_entry_safe(b, n, bdaddr_list, list) { list_del(&b->list); kfree(b); } } int hci_bdaddr_list_add(struct list_head *list, bdaddr_t *bdaddr, u8 type) { struct bdaddr_list *entry; if (!bacmp(bdaddr, BDADDR_ANY)) return -EBADF; if (hci_bdaddr_list_lookup(list, bdaddr, type)) return -EEXIST; entry = kzalloc(sizeof(*entry), GFP_KERNEL); if (!entry) return -ENOMEM; bacpy(&entry->bdaddr, bdaddr); entry->bdaddr_type = type; list_add(&entry->list, list); return 0; } int hci_bdaddr_list_add_with_irk(struct list_head *list, bdaddr_t *bdaddr, u8 type, u8 *peer_irk, u8 *local_irk) { struct bdaddr_list_with_irk *entry; if (!bacmp(bdaddr, BDADDR_ANY)) return -EBADF; if (hci_bdaddr_list_lookup(list, bdaddr, type)) return -EEXIST; entry = kzalloc(sizeof(*entry), GFP_KERNEL); if (!entry) return -ENOMEM; bacpy(&entry->bdaddr, bdaddr); entry->bdaddr_type = type; if (peer_irk) memcpy(entry->peer_irk, peer_irk, 16); if (local_irk) memcpy(entry->local_irk, local_irk, 16); list_add(&entry->list, list); return 0; } int hci_bdaddr_list_add_with_flags(struct list_head *list, bdaddr_t *bdaddr, u8 type, u32 flags) { struct bdaddr_list_with_flags *entry; if (!bacmp(bdaddr, BDADDR_ANY)) return -EBADF; if (hci_bdaddr_list_lookup(list, bdaddr, type)) return -EEXIST; entry = kzalloc(sizeof(*entry), GFP_KERNEL); if (!entry) return -ENOMEM; bacpy(&entry->bdaddr, bdaddr); entry->bdaddr_type = type; entry->flags = flags; list_add(&entry->list, list); return 0; } int hci_bdaddr_list_del(struct list_head *list, bdaddr_t *bdaddr, u8 type) { struct bdaddr_list *entry; if (!bacmp(bdaddr, BDADDR_ANY)) { hci_bdaddr_list_clear(list); return 0; } entry = hci_bdaddr_list_lookup(list, bdaddr, type); if (!entry) return -ENOENT; list_del(&entry->list); kfree(entry); return 0; } int hci_bdaddr_list_del_with_irk(struct list_head *list, bdaddr_t *bdaddr, u8 type) { struct bdaddr_list_with_irk *entry; if (!bacmp(bdaddr, BDADDR_ANY)) { hci_bdaddr_list_clear(list); return 0; } entry = hci_bdaddr_list_lookup_with_irk(list, bdaddr, type); if (!entry) return -ENOENT; list_del(&entry->list); kfree(entry); return 0; } /* This function requires the caller holds hdev->lock */ struct hci_conn_params *hci_conn_params_lookup(struct hci_dev *hdev, bdaddr_t *addr, u8 addr_type) { struct hci_conn_params *params; list_for_each_entry(params, &hdev->le_conn_params, list) { if (bacmp(¶ms->addr, addr) == 0 && params->addr_type == addr_type) { return params; } } return NULL; } /* This function requires the caller holds hdev->lock or rcu_read_lock */ struct hci_conn_params *hci_pend_le_action_lookup(struct list_head *list, bdaddr_t *addr, u8 addr_type) { struct hci_conn_params *param; rcu_read_lock(); list_for_each_entry_rcu(param, list, action) { if (bacmp(¶m->addr, addr) == 0 && param->addr_type == addr_type) { rcu_read_unlock(); return param; } } rcu_read_unlock(); return NULL; } /* This function requires the caller holds hdev->lock */ void hci_pend_le_list_del_init(struct hci_conn_params *param) { if (list_empty(¶m->action)) return; list_del_rcu(¶m->action); synchronize_rcu(); INIT_LIST_HEAD(¶m->action); } /* This function requires the caller holds hdev->lock */ void hci_pend_le_list_add(struct hci_conn_params *param, struct list_head *list) { list_add_rcu(¶m->action, list); } /* This function requires the caller holds hdev->lock */ struct hci_conn_params *hci_conn_params_add(struct hci_dev *hdev, bdaddr_t *addr, u8 addr_type) { struct hci_conn_params *params; params = hci_conn_params_lookup(hdev, addr, addr_type); if (params) return params; params = kzalloc(sizeof(*params), GFP_KERNEL); if (!params) { bt_dev_err(hdev, "out of memory"); return NULL; } bacpy(¶ms->addr, addr); params->addr_type = addr_type; list_add(¶ms->list, &hdev->le_conn_params); INIT_LIST_HEAD(¶ms->action); params->conn_min_interval = hdev->le_conn_min_interval; params->conn_max_interval = hdev->le_conn_max_interval; params->conn_latency = hdev->le_conn_latency; params->supervision_timeout = hdev->le_supv_timeout; params->auto_connect = HCI_AUTO_CONN_DISABLED; BT_DBG("addr %pMR (type %u)", addr, addr_type); return params; } void hci_conn_params_free(struct hci_conn_params *params) { hci_pend_le_list_del_init(params); if (params->conn) { hci_conn_drop(params->conn); hci_conn_put(params->conn); } list_del(¶ms->list); kfree(params); } /* This function requires the caller holds hdev->lock */ void hci_conn_params_del(struct hci_dev *hdev, bdaddr_t *addr, u8 addr_type) { struct hci_conn_params *params; params = hci_conn_params_lookup(hdev, addr, addr_type); if (!params) return; hci_conn_params_free(params); hci_update_passive_scan(hdev); BT_DBG("addr %pMR (type %u)", addr, addr_type); } /* This function requires the caller holds hdev->lock */ void hci_conn_params_clear_disabled(struct hci_dev *hdev) { struct hci_conn_params *params, *tmp; list_for_each_entry_safe(params, tmp, &hdev->le_conn_params, list) { if (params->auto_connect != HCI_AUTO_CONN_DISABLED) continue; /* If trying to establish one time connection to disabled * device, leave the params, but mark them as just once. */ if (params->explicit_connect) { params->auto_connect = HCI_AUTO_CONN_EXPLICIT; continue; } hci_conn_params_free(params); } BT_DBG("All LE disabled connection parameters were removed"); } /* This function requires the caller holds hdev->lock */ static void hci_conn_params_clear_all(struct hci_dev *hdev) { struct hci_conn_params *params, *tmp; list_for_each_entry_safe(params, tmp, &hdev->le_conn_params, list) hci_conn_params_free(params); BT_DBG("All LE connection parameters were removed"); } /* Copy the Identity Address of the controller. * * If the controller has a public BD_ADDR, then by default use that one. * If this is a LE only controller without a public address, default to * the static random address. * * For debugging purposes it is possible to force controllers with a * public address to use the static random address instead. * * In case BR/EDR has been disabled on a dual-mode controller and * userspace has configured a static address, then that address * becomes the identity address instead of the public BR/EDR address. */ void hci_copy_identity_address(struct hci_dev *hdev, bdaddr_t *bdaddr, u8 *bdaddr_type) { if (hci_dev_test_flag(hdev, HCI_FORCE_STATIC_ADDR) || !bacmp(&hdev->bdaddr, BDADDR_ANY) || (!hci_dev_test_flag(hdev, HCI_BREDR_ENABLED) && bacmp(&hdev->static_addr, BDADDR_ANY))) { bacpy(bdaddr, &hdev->static_addr); *bdaddr_type = ADDR_LE_DEV_RANDOM; } else { bacpy(bdaddr, &hdev->bdaddr); *bdaddr_type = ADDR_LE_DEV_PUBLIC; } } static void hci_clear_wake_reason(struct hci_dev *hdev) { hci_dev_lock(hdev); hdev->wake_reason = 0; bacpy(&hdev->wake_addr, BDADDR_ANY); hdev->wake_addr_type = 0; hci_dev_unlock(hdev); } static int hci_suspend_notifier(struct notifier_block *nb, unsigned long action, void *data) { struct hci_dev *hdev = container_of(nb, struct hci_dev, suspend_notifier); int ret = 0; /* Userspace has full control of this device. Do nothing. */ if (hci_dev_test_flag(hdev, HCI_USER_CHANNEL)) return NOTIFY_DONE; /* To avoid a potential race with hci_unregister_dev. */ hci_dev_hold(hdev); switch (action) { case PM_HIBERNATION_PREPARE: case PM_SUSPEND_PREPARE: ret = hci_suspend_dev(hdev); break; case PM_POST_HIBERNATION: case PM_POST_SUSPEND: ret = hci_resume_dev(hdev); break; } if (ret) bt_dev_err(hdev, "Suspend notifier action (%lu) failed: %d", action, ret); hci_dev_put(hdev); return NOTIFY_DONE; } /* Alloc HCI device */ struct hci_dev *hci_alloc_dev_priv(int sizeof_priv) { struct hci_dev *hdev; unsigned int alloc_size; alloc_size = sizeof(*hdev); if (sizeof_priv) { /* Fixme: May need ALIGN-ment? */ alloc_size += sizeof_priv; } hdev = kzalloc(alloc_size, GFP_KERNEL); if (!hdev) return NULL; hdev->pkt_type = (HCI_DM1 | HCI_DH1 | HCI_HV1); hdev->esco_type = (ESCO_HV1); hdev->link_mode = (HCI_LM_ACCEPT); hdev->num_iac = 0x01; /* One IAC support is mandatory */ hdev->io_capability = 0x03; /* No Input No Output */ hdev->manufacturer = 0xffff; /* Default to internal use */ hdev->inq_tx_power = HCI_TX_POWER_INVALID; hdev->adv_tx_power = HCI_TX_POWER_INVALID; hdev->adv_instance_cnt = 0; hdev->cur_adv_instance = 0x00; hdev->adv_instance_timeout = 0; hdev->advmon_allowlist_duration = 300; hdev->advmon_no_filter_duration = 500; hdev->enable_advmon_interleave_scan = 0x00; /* Default to disable */ hdev->sniff_max_interval = 800; hdev->sniff_min_interval = 80; hdev->le_adv_channel_map = 0x07; hdev->le_adv_min_interval = 0x0800; hdev->le_adv_max_interval = 0x0800; hdev->le_scan_interval = DISCOV_LE_SCAN_INT_FAST; hdev->le_scan_window = DISCOV_LE_SCAN_WIN_FAST; hdev->le_scan_int_suspend = DISCOV_LE_SCAN_INT_SLOW1; hdev->le_scan_window_suspend = DISCOV_LE_SCAN_WIN_SLOW1; hdev->le_scan_int_discovery = DISCOV_LE_SCAN_INT; hdev->le_scan_window_discovery = DISCOV_LE_SCAN_WIN; hdev->le_scan_int_adv_monitor = DISCOV_LE_SCAN_INT_FAST; hdev->le_scan_window_adv_monitor = DISCOV_LE_SCAN_WIN_FAST; hdev->le_scan_int_connect = DISCOV_LE_SCAN_INT_CONN; hdev->le_scan_window_connect = DISCOV_LE_SCAN_WIN_CONN; hdev->le_conn_min_interval = 0x0018; hdev->le_conn_max_interval = 0x0028; hdev->le_conn_latency = 0x0000; hdev->le_supv_timeout = 0x002a; hdev->le_def_tx_len = 0x001b; hdev->le_def_tx_time = 0x0148; hdev->le_max_tx_len = 0x001b; hdev->le_max_tx_time = 0x0148; hdev->le_max_rx_len = 0x001b; hdev->le_max_rx_time = 0x0148; hdev->le_max_key_size = SMP_MAX_ENC_KEY_SIZE; hdev->le_min_key_size = SMP_MIN_ENC_KEY_SIZE; hdev->le_tx_def_phys = HCI_LE_SET_PHY_1M; hdev->le_rx_def_phys = HCI_LE_SET_PHY_1M; hdev->le_num_of_adv_sets = HCI_MAX_ADV_INSTANCES; hdev->def_multi_adv_rotation_duration = HCI_DEFAULT_ADV_DURATION; hdev->def_le_autoconnect_timeout = HCI_LE_CONN_TIMEOUT; hdev->min_le_tx_power = HCI_TX_POWER_INVALID; hdev->max_le_tx_power = HCI_TX_POWER_INVALID; hdev->rpa_timeout = HCI_DEFAULT_RPA_TIMEOUT; hdev->discov_interleaved_timeout = DISCOV_INTERLEAVED_TIMEOUT; hdev->conn_info_min_age = DEFAULT_CONN_INFO_MIN_AGE; hdev->conn_info_max_age = DEFAULT_CONN_INFO_MAX_AGE; hdev->auth_payload_timeout = DEFAULT_AUTH_PAYLOAD_TIMEOUT; hdev->min_enc_key_size = HCI_MIN_ENC_KEY_SIZE; /* default 1.28 sec page scan */ hdev->def_page_scan_type = PAGE_SCAN_TYPE_STANDARD; hdev->def_page_scan_int = 0x0800; hdev->def_page_scan_window = 0x0012; mutex_init(&hdev->lock); mutex_init(&hdev->req_lock); ida_init(&hdev->unset_handle_ida); INIT_LIST_HEAD(&hdev->mesh_pending); INIT_LIST_HEAD(&hdev->mgmt_pending); INIT_LIST_HEAD(&hdev->reject_list); INIT_LIST_HEAD(&hdev->accept_list); INIT_LIST_HEAD(&hdev->uuids); INIT_LIST_HEAD(&hdev->link_keys); INIT_LIST_HEAD(&hdev->long_term_keys); INIT_LIST_HEAD(&hdev->identity_resolving_keys); INIT_LIST_HEAD(&hdev->remote_oob_data); INIT_LIST_HEAD(&hdev->le_accept_list); INIT_LIST_HEAD(&hdev->le_resolv_list); INIT_LIST_HEAD(&hdev->le_conn_params); INIT_LIST_HEAD(&hdev->pend_le_conns); INIT_LIST_HEAD(&hdev->pend_le_reports); INIT_LIST_HEAD(&hdev->conn_hash.list); INIT_LIST_HEAD(&hdev->adv_instances); INIT_LIST_HEAD(&hdev->blocked_keys); INIT_LIST_HEAD(&hdev->monitored_devices); INIT_LIST_HEAD(&hdev->local_codecs); INIT_WORK(&hdev->rx_work, hci_rx_work); INIT_WORK(&hdev->cmd_work, hci_cmd_work); INIT_WORK(&hdev->tx_work, hci_tx_work); INIT_WORK(&hdev->power_on, hci_power_on); INIT_WORK(&hdev->error_reset, hci_error_reset); hci_cmd_sync_init(hdev); INIT_DELAYED_WORK(&hdev->power_off, hci_power_off); skb_queue_head_init(&hdev->rx_q); skb_queue_head_init(&hdev->cmd_q); skb_queue_head_init(&hdev->raw_q); init_waitqueue_head(&hdev->req_wait_q); INIT_DELAYED_WORK(&hdev->cmd_timer, hci_cmd_timeout); INIT_DELAYED_WORK(&hdev->ncmd_timer, hci_ncmd_timeout); hci_devcd_setup(hdev); hci_init_sysfs(hdev); discovery_init(hdev); return hdev; } EXPORT_SYMBOL(hci_alloc_dev_priv); /* Free HCI device */ void hci_free_dev(struct hci_dev *hdev) { /* will free via device release */ put_device(&hdev->dev); } EXPORT_SYMBOL(hci_free_dev); /* Register HCI device */ int hci_register_dev(struct hci_dev *hdev) { int id, error; if (!hdev->open || !hdev->close || !hdev->send) return -EINVAL; id = ida_alloc_max(&hci_index_ida, HCI_MAX_ID - 1, GFP_KERNEL); if (id < 0) return id; error = dev_set_name(&hdev->dev, "hci%u", id); if (error) return error; hdev->name = dev_name(&hdev->dev); hdev->id = id; BT_DBG("%p name %s bus %d", hdev, hdev->name, hdev->bus); hdev->workqueue = alloc_ordered_workqueue("%s", WQ_HIGHPRI, hdev->name); if (!hdev->workqueue) { error = -ENOMEM; goto err; } hdev->req_workqueue = alloc_ordered_workqueue("%s", WQ_HIGHPRI, hdev->name); if (!hdev->req_workqueue) { destroy_workqueue(hdev->workqueue); error = -ENOMEM; goto err; } if (!IS_ERR_OR_NULL(bt_debugfs)) hdev->debugfs = debugfs_create_dir(hdev->name, bt_debugfs); error = device_add(&hdev->dev); if (error < 0) goto err_wqueue; hci_leds_init(hdev); hdev->rfkill = rfkill_alloc(hdev->name, &hdev->dev, RFKILL_TYPE_BLUETOOTH, &hci_rfkill_ops, hdev); if (hdev->rfkill) { if (rfkill_register(hdev->rfkill) < 0) { rfkill_destroy(hdev->rfkill); hdev->rfkill = NULL; } } if (hdev->rfkill && rfkill_blocked(hdev->rfkill)) hci_dev_set_flag(hdev, HCI_RFKILLED); hci_dev_set_flag(hdev, HCI_SETUP); hci_dev_set_flag(hdev, HCI_AUTO_OFF); /* Assume BR/EDR support until proven otherwise (such as * through reading supported features during init. */ hci_dev_set_flag(hdev, HCI_BREDR_ENABLED); write_lock(&hci_dev_list_lock); list_add(&hdev->list, &hci_dev_list); write_unlock(&hci_dev_list_lock); /* Devices that are marked for raw-only usage are unconfigured * and should not be included in normal operation. */ if (test_bit(HCI_QUIRK_RAW_DEVICE, &hdev->quirks)) hci_dev_set_flag(hdev, HCI_UNCONFIGURED); /* Mark Remote Wakeup connection flag as supported if driver has wakeup * callback. */ if (hdev->wakeup) hdev->conn_flags |= HCI_CONN_FLAG_REMOTE_WAKEUP; hci_sock_dev_event(hdev, HCI_DEV_REG); hci_dev_hold(hdev); error = hci_register_suspend_notifier(hdev); if (error) BT_WARN("register suspend notifier failed error:%d\n", error); queue_work(hdev->req_workqueue, &hdev->power_on); idr_init(&hdev->adv_monitors_idr); msft_register(hdev); return id; err_wqueue: debugfs_remove_recursive(hdev->debugfs); destroy_workqueue(hdev->workqueue); destroy_workqueue(hdev->req_workqueue); err: ida_free(&hci_index_ida, hdev->id); return error; } EXPORT_SYMBOL(hci_register_dev); /* Unregister HCI device */ void hci_unregister_dev(struct hci_dev *hdev) { BT_DBG("%p name %s bus %d", hdev, hdev->name, hdev->bus); mutex_lock(&hdev->unregister_lock); hci_dev_set_flag(hdev, HCI_UNREGISTER); mutex_unlock(&hdev->unregister_lock); write_lock(&hci_dev_list_lock); list_del(&hdev->list); write_unlock(&hci_dev_list_lock); disable_work_sync(&hdev->rx_work); disable_work_sync(&hdev->cmd_work); disable_work_sync(&hdev->tx_work); disable_work_sync(&hdev->power_on); disable_work_sync(&hdev->error_reset); hci_cmd_sync_clear(hdev); hci_unregister_suspend_notifier(hdev); hci_dev_do_close(hdev); if (!test_bit(HCI_INIT, &hdev->flags) && !hci_dev_test_flag(hdev, HCI_SETUP) && !hci_dev_test_flag(hdev, HCI_CONFIG)) { hci_dev_lock(hdev); mgmt_index_removed(hdev); hci_dev_unlock(hdev); } /* mgmt_index_removed should take care of emptying the * pending list */ BUG_ON(!list_empty(&hdev->mgmt_pending)); hci_sock_dev_event(hdev, HCI_DEV_UNREG); if (hdev->rfkill) { rfkill_unregister(hdev->rfkill); rfkill_destroy(hdev->rfkill); } device_del(&hdev->dev); /* Actual cleanup is deferred until hci_release_dev(). */ hci_dev_put(hdev); } EXPORT_SYMBOL(hci_unregister_dev); /* Release HCI device */ void hci_release_dev(struct hci_dev *hdev) { debugfs_remove_recursive(hdev->debugfs); kfree_const(hdev->hw_info); kfree_const(hdev->fw_info); destroy_workqueue(hdev->workqueue); destroy_workqueue(hdev->req_workqueue); hci_dev_lock(hdev); hci_bdaddr_list_clear(&hdev->reject_list); hci_bdaddr_list_clear(&hdev->accept_list); hci_uuids_clear(hdev); hci_link_keys_clear(hdev); hci_smp_ltks_clear(hdev); hci_smp_irks_clear(hdev); hci_remote_oob_data_clear(hdev); hci_adv_instances_clear(hdev); hci_adv_monitors_clear(hdev); hci_bdaddr_list_clear(&hdev->le_accept_list); hci_bdaddr_list_clear(&hdev->le_resolv_list); hci_conn_params_clear_all(hdev); hci_discovery_filter_clear(hdev); hci_blocked_keys_clear(hdev); hci_codec_list_clear(&hdev->local_codecs); msft_release(hdev); hci_dev_unlock(hdev); ida_destroy(&hdev->unset_handle_ida); ida_free(&hci_index_ida, hdev->id); kfree_skb(hdev->sent_cmd); kfree_skb(hdev->req_skb); kfree_skb(hdev->recv_event); kfree(hdev); } EXPORT_SYMBOL(hci_release_dev); int hci_register_suspend_notifier(struct hci_dev *hdev) { int ret = 0; if (!hdev->suspend_notifier.notifier_call && !test_bit(HCI_QUIRK_NO_SUSPEND_NOTIFIER, &hdev->quirks)) { hdev->suspend_notifier.notifier_call = hci_suspend_notifier; ret = register_pm_notifier(&hdev->suspend_notifier); } return ret; } int hci_unregister_suspend_notifier(struct hci_dev *hdev) { int ret = 0; if (hdev->suspend_notifier.notifier_call) { ret = unregister_pm_notifier(&hdev->suspend_notifier); if (!ret) hdev->suspend_notifier.notifier_call = NULL; } return ret; } /* Cancel ongoing command synchronously: * * - Cancel command timer * - Reset command counter * - Cancel command request */ static void hci_cancel_cmd_sync(struct hci_dev *hdev, int err) { bt_dev_dbg(hdev, "err 0x%2.2x", err); if (hci_dev_test_flag(hdev, HCI_UNREGISTER)) { disable_delayed_work_sync(&hdev->cmd_timer); disable_delayed_work_sync(&hdev->ncmd_timer); } else { cancel_delayed_work_sync(&hdev->cmd_timer); cancel_delayed_work_sync(&hdev->ncmd_timer); } atomic_set(&hdev->cmd_cnt, 1); hci_cmd_sync_cancel_sync(hdev, err); } /* Suspend HCI device */ int hci_suspend_dev(struct hci_dev *hdev) { int ret; bt_dev_dbg(hdev, ""); /* Suspend should only act on when powered. */ if (!hdev_is_powered(hdev) || hci_dev_test_flag(hdev, HCI_UNREGISTER)) return 0; /* If powering down don't attempt to suspend */ if (mgmt_powering_down(hdev)) return 0; /* Cancel potentially blocking sync operation before suspend */ hci_cancel_cmd_sync(hdev, EHOSTDOWN); hci_req_sync_lock(hdev); ret = hci_suspend_sync(hdev); hci_req_sync_unlock(hdev); hci_clear_wake_reason(hdev); mgmt_suspending(hdev, hdev->suspend_state); hci_sock_dev_event(hdev, HCI_DEV_SUSPEND); return ret; } EXPORT_SYMBOL(hci_suspend_dev); /* Resume HCI device */ int hci_resume_dev(struct hci_dev *hdev) { int ret; bt_dev_dbg(hdev, ""); /* Resume should only act on when powered. */ if (!hdev_is_powered(hdev) || hci_dev_test_flag(hdev, HCI_UNREGISTER)) return 0; /* If powering down don't attempt to resume */ if (mgmt_powering_down(hdev)) return 0; hci_req_sync_lock(hdev); ret = hci_resume_sync(hdev); hci_req_sync_unlock(hdev); mgmt_resuming(hdev, hdev->wake_reason, &hdev->wake_addr, hdev->wake_addr_type); hci_sock_dev_event(hdev, HCI_DEV_RESUME); return ret; } EXPORT_SYMBOL(hci_resume_dev); /* Reset HCI device */ int hci_reset_dev(struct hci_dev *hdev) { static const u8 hw_err[] = { HCI_EV_HARDWARE_ERROR, 0x01, 0x00 }; struct sk_buff *skb; skb = bt_skb_alloc(3, GFP_ATOMIC); if (!skb) return -ENOMEM; hci_skb_pkt_type(skb) = HCI_EVENT_PKT; skb_put_data(skb, hw_err, 3); bt_dev_err(hdev, "Injecting HCI hardware error event"); /* Send Hardware Error to upper stack */ return hci_recv_frame(hdev, skb); } EXPORT_SYMBOL(hci_reset_dev); static u8 hci_dev_classify_pkt_type(struct hci_dev *hdev, struct sk_buff *skb) { if (hdev->classify_pkt_type) return hdev->classify_pkt_type(hdev, skb); return hci_skb_pkt_type(skb); } /* Receive frame from HCI drivers */ int hci_recv_frame(struct hci_dev *hdev, struct sk_buff *skb) { u8 dev_pkt_type; if (!hdev || (!test_bit(HCI_UP, &hdev->flags) && !test_bit(HCI_INIT, &hdev->flags))) { kfree_skb(skb); return -ENXIO; } /* Check if the driver agree with packet type classification */ dev_pkt_type = hci_dev_classify_pkt_type(hdev, skb); if (hci_skb_pkt_type(skb) != dev_pkt_type) { hci_skb_pkt_type(skb) = dev_pkt_type; } switch (hci_skb_pkt_type(skb)) { case HCI_EVENT_PKT: break; case HCI_ACLDATA_PKT: /* Detect if ISO packet has been sent as ACL */ if (hci_conn_num(hdev, ISO_LINK)) { __u16 handle = __le16_to_cpu(hci_acl_hdr(skb)->handle); __u8 type; type = hci_conn_lookup_type(hdev, hci_handle(handle)); if (type == ISO_LINK) hci_skb_pkt_type(skb) = HCI_ISODATA_PKT; } break; case HCI_SCODATA_PKT: break; case HCI_ISODATA_PKT: break; default: kfree_skb(skb); return -EINVAL; } /* Incoming skb */ bt_cb(skb)->incoming = 1; /* Time stamp */ __net_timestamp(skb); skb_queue_tail(&hdev->rx_q, skb); queue_work(hdev->workqueue, &hdev->rx_work); return 0; } EXPORT_SYMBOL(hci_recv_frame); /* Receive diagnostic message from HCI drivers */ int hci_recv_diag(struct hci_dev *hdev, struct sk_buff *skb) { /* Mark as diagnostic packet */ hci_skb_pkt_type(skb) = HCI_DIAG_PKT; /* Time stamp */ __net_timestamp(skb); skb_queue_tail(&hdev->rx_q, skb); queue_work(hdev->workqueue, &hdev->rx_work); return 0; } EXPORT_SYMBOL(hci_recv_diag); void hci_set_hw_info(struct hci_dev *hdev, const char *fmt, ...) { va_list vargs; va_start(vargs, fmt); kfree_const(hdev->hw_info); hdev->hw_info = kvasprintf_const(GFP_KERNEL, fmt, vargs); va_end(vargs); } EXPORT_SYMBOL(hci_set_hw_info); void hci_set_fw_info(struct hci_dev *hdev, const char *fmt, ...) { va_list vargs; va_start(vargs, fmt); kfree_const(hdev->fw_info); hdev->fw_info = kvasprintf_const(GFP_KERNEL, fmt, vargs); va_end(vargs); } EXPORT_SYMBOL(hci_set_fw_info); /* ---- Interface to upper protocols ---- */ int hci_register_cb(struct hci_cb *cb) { BT_DBG("%p name %s", cb, cb->name); list_add_tail_rcu(&cb->list, &hci_cb_list); return 0; } EXPORT_SYMBOL(hci_register_cb); int hci_unregister_cb(struct hci_cb *cb) { BT_DBG("%p name %s", cb, cb->name); list_del_rcu(&cb->list); synchronize_rcu(); return 0; } EXPORT_SYMBOL(hci_unregister_cb); static int hci_send_frame(struct hci_dev *hdev, struct sk_buff *skb) { int err; BT_DBG("%s type %d len %d", hdev->name, hci_skb_pkt_type(skb), skb->len); /* Time stamp */ __net_timestamp(skb); /* Send copy to monitor */ hci_send_to_monitor(hdev, skb); if (atomic_read(&hdev->promisc)) { /* Send copy to the sockets */ hci_send_to_sock(hdev, skb); } /* Get rid of skb owner, prior to sending to the driver. */ skb_orphan(skb); if (!test_bit(HCI_RUNNING, &hdev->flags)) { kfree_skb(skb); return -EINVAL; } err = hdev->send(hdev, skb); if (err < 0) { bt_dev_err(hdev, "sending frame failed (%d)", err); kfree_skb(skb); return err; } return 0; } /* Send HCI command */ int hci_send_cmd(struct hci_dev *hdev, __u16 opcode, __u32 plen, const void *param) { struct sk_buff *skb; BT_DBG("%s opcode 0x%4.4x plen %d", hdev->name, opcode, plen); skb = hci_cmd_sync_alloc(hdev, opcode, plen, param, NULL); if (!skb) { bt_dev_err(hdev, "no memory for command"); return -ENOMEM; } /* Stand-alone HCI commands must be flagged as * single-command requests. */ bt_cb(skb)->hci.req_flags |= HCI_REQ_START; skb_queue_tail(&hdev->cmd_q, skb); queue_work(hdev->workqueue, &hdev->cmd_work); return 0; } int __hci_cmd_send(struct hci_dev *hdev, u16 opcode, u32 plen, const void *param) { struct sk_buff *skb; if (hci_opcode_ogf(opcode) != 0x3f) { /* A controller receiving a command shall respond with either * a Command Status Event or a Command Complete Event. * Therefore, all standard HCI commands must be sent via the * standard API, using hci_send_cmd or hci_cmd_sync helpers. * Some vendors do not comply with this rule for vendor-specific * commands and do not return any event. We want to support * unresponded commands for such cases only. */ bt_dev_err(hdev, "unresponded command not supported"); return -EINVAL; } skb = hci_cmd_sync_alloc(hdev, opcode, plen, param, NULL); if (!skb) { bt_dev_err(hdev, "no memory for command (opcode 0x%4.4x)", opcode); return -ENOMEM; } hci_send_frame(hdev, skb); return 0; } EXPORT_SYMBOL(__hci_cmd_send); /* Get data from the previously sent command */ static void *hci_cmd_data(struct sk_buff *skb, __u16 opcode) { struct hci_command_hdr *hdr; if (!skb || skb->len < HCI_COMMAND_HDR_SIZE) return NULL; hdr = (void *)skb->data; if (hdr->opcode != cpu_to_le16(opcode)) return NULL; return skb->data + HCI_COMMAND_HDR_SIZE; } /* Get data from the previously sent command */ void *hci_sent_cmd_data(struct hci_dev *hdev, __u16 opcode) { void *data; /* Check if opcode matches last sent command */ data = hci_cmd_data(hdev->sent_cmd, opcode); if (!data) /* Check if opcode matches last request */ data = hci_cmd_data(hdev->req_skb, opcode); return data; } /* Get data from last received event */ void *hci_recv_event_data(struct hci_dev *hdev, __u8 event) { struct hci_event_hdr *hdr; int offset; if (!hdev->recv_event) return NULL; hdr = (void *)hdev->recv_event->data; offset = sizeof(*hdr); if (hdr->evt != event) { /* In case of LE metaevent check the subevent match */ if (hdr->evt == HCI_EV_LE_META) { struct hci_ev_le_meta *ev; ev = (void *)hdev->recv_event->data + offset; offset += sizeof(*ev); if (ev->subevent == event) goto found; } return NULL; } found: bt_dev_dbg(hdev, "event 0x%2.2x", event); return hdev->recv_event->data + offset; } /* Send ACL data */ static void hci_add_acl_hdr(struct sk_buff *skb, __u16 handle, __u16 flags) { struct hci_acl_hdr *hdr; int len = skb->len; skb_push(skb, HCI_ACL_HDR_SIZE); skb_reset_transport_header(skb); hdr = (struct hci_acl_hdr *)skb_transport_header(skb); hdr->handle = cpu_to_le16(hci_handle_pack(handle, flags)); hdr->dlen = cpu_to_le16(len); } static void hci_queue_acl(struct hci_chan *chan, struct sk_buff_head *queue, struct sk_buff *skb, __u16 flags) { struct hci_conn *conn = chan->conn; struct hci_dev *hdev = conn->hdev; struct sk_buff *list; skb->len = skb_headlen(skb); skb->data_len = 0; hci_skb_pkt_type(skb) = HCI_ACLDATA_PKT; hci_add_acl_hdr(skb, conn->handle, flags); list = skb_shinfo(skb)->frag_list; if (!list) { /* Non fragmented */ BT_DBG("%s nonfrag skb %p len %d", hdev->name, skb, skb->len); skb_queue_tail(queue, skb); } else { /* Fragmented */ BT_DBG("%s frag %p len %d", hdev->name, skb, skb->len); skb_shinfo(skb)->frag_list = NULL; /* Queue all fragments atomically. We need to use spin_lock_bh * here because of 6LoWPAN links, as there this function is * called from softirq and using normal spin lock could cause * deadlocks. */ spin_lock_bh(&queue->lock); __skb_queue_tail(queue, skb); flags &= ~ACL_START; flags |= ACL_CONT; do { skb = list; list = list->next; hci_skb_pkt_type(skb) = HCI_ACLDATA_PKT; hci_add_acl_hdr(skb, conn->handle, flags); BT_DBG("%s frag %p len %d", hdev->name, skb, skb->len); __skb_queue_tail(queue, skb); } while (list); spin_unlock_bh(&queue->lock); } } void hci_send_acl(struct hci_chan *chan, struct sk_buff *skb, __u16 flags) { struct hci_dev *hdev = chan->conn->hdev; BT_DBG("%s chan %p flags 0x%4.4x", hdev->name, chan, flags); hci_queue_acl(chan, &chan->data_q, skb, flags); queue_work(hdev->workqueue, &hdev->tx_work); } /* Send SCO data */ void hci_send_sco(struct hci_conn *conn, struct sk_buff *skb) { struct hci_dev *hdev = conn->hdev; struct hci_sco_hdr hdr; BT_DBG("%s len %d", hdev->name, skb->len); hdr.handle = cpu_to_le16(conn->handle); hdr.dlen = skb->len; skb_push(skb, HCI_SCO_HDR_SIZE); skb_reset_transport_header(skb); memcpy(skb_transport_header(skb), &hdr, HCI_SCO_HDR_SIZE); hci_skb_pkt_type(skb) = HCI_SCODATA_PKT; skb_queue_tail(&conn->data_q, skb); queue_work(hdev->workqueue, &hdev->tx_work); } /* Send ISO data */ static void hci_add_iso_hdr(struct sk_buff *skb, __u16 handle, __u8 flags) { struct hci_iso_hdr *hdr; int len = skb->len; skb_push(skb, HCI_ISO_HDR_SIZE); skb_reset_transport_header(skb); hdr = (struct hci_iso_hdr *)skb_transport_header(skb); hdr->handle = cpu_to_le16(hci_handle_pack(handle, flags)); hdr->dlen = cpu_to_le16(len); } static void hci_queue_iso(struct hci_conn *conn, struct sk_buff_head *queue, struct sk_buff *skb) { struct hci_dev *hdev = conn->hdev; struct sk_buff *list; __u16 flags; skb->len = skb_headlen(skb); skb->data_len = 0; hci_skb_pkt_type(skb) = HCI_ISODATA_PKT; list = skb_shinfo(skb)->frag_list; flags = hci_iso_flags_pack(list ? ISO_START : ISO_SINGLE, 0x00); hci_add_iso_hdr(skb, conn->handle, flags); if (!list) { /* Non fragmented */ BT_DBG("%s nonfrag skb %p len %d", hdev->name, skb, skb->len); skb_queue_tail(queue, skb); } else { /* Fragmented */ BT_DBG("%s frag %p len %d", hdev->name, skb, skb->len); skb_shinfo(skb)->frag_list = NULL; __skb_queue_tail(queue, skb); do { skb = list; list = list->next; hci_skb_pkt_type(skb) = HCI_ISODATA_PKT; flags = hci_iso_flags_pack(list ? ISO_CONT : ISO_END, 0x00); hci_add_iso_hdr(skb, conn->handle, flags); BT_DBG("%s frag %p len %d", hdev->name, skb, skb->len); __skb_queue_tail(queue, skb); } while (list); } } void hci_send_iso(struct hci_conn *conn, struct sk_buff *skb) { struct hci_dev *hdev = conn->hdev; BT_DBG("%s len %d", hdev->name, skb->len); hci_queue_iso(conn, &conn->data_q, skb); queue_work(hdev->workqueue, &hdev->tx_work); } /* ---- HCI TX task (outgoing data) ---- */ /* HCI Connection scheduler */ static inline void hci_quote_sent(struct hci_conn *conn, int num, int *quote) { struct hci_dev *hdev; int cnt, q; if (!conn) { *quote = 0; return; } hdev = conn->hdev; switch (conn->type) { case ACL_LINK: cnt = hdev->acl_cnt; break; case SCO_LINK: case ESCO_LINK: cnt = hdev->sco_cnt; break; case LE_LINK: cnt = hdev->le_mtu ? hdev->le_cnt : hdev->acl_cnt; break; case ISO_LINK: cnt = hdev->iso_mtu ? hdev->iso_cnt : hdev->le_mtu ? hdev->le_cnt : hdev->acl_cnt; break; default: cnt = 0; bt_dev_err(hdev, "unknown link type %d", conn->type); } q = cnt / num; *quote = q ? q : 1; } static struct hci_conn *hci_low_sent(struct hci_dev *hdev, __u8 type, int *quote) { struct hci_conn_hash *h = &hdev->conn_hash; struct hci_conn *conn = NULL, *c; unsigned int num = 0, min = ~0; /* We don't have to lock device here. Connections are always * added and removed with TX task disabled. */ rcu_read_lock(); list_for_each_entry_rcu(c, &h->list, list) { if (c->type != type || skb_queue_empty(&c->data_q)) continue; if (c->state != BT_CONNECTED && c->state != BT_CONFIG) continue; num++; if (c->sent < min) { min = c->sent; conn = c; } if (hci_conn_num(hdev, type) == num) break; } rcu_read_unlock(); hci_quote_sent(conn, num, quote); BT_DBG("conn %p quote %d", conn, *quote); return conn; } static void hci_link_tx_to(struct hci_dev *hdev, __u8 type) { struct hci_conn_hash *h = &hdev->conn_hash; struct hci_conn *c; bt_dev_err(hdev, "link tx timeout"); rcu_read_lock(); /* Kill stalled connections */ list_for_each_entry_rcu(c, &h->list, list) { if (c->type == type && c->sent) { bt_dev_err(hdev, "killing stalled connection %pMR", &c->dst); /* hci_disconnect might sleep, so, we have to release * the RCU read lock before calling it. */ rcu_read_unlock(); hci_disconnect(c, HCI_ERROR_REMOTE_USER_TERM); rcu_read_lock(); } } rcu_read_unlock(); } static struct hci_chan *hci_chan_sent(struct hci_dev *hdev, __u8 type, int *quote) { struct hci_conn_hash *h = &hdev->conn_hash; struct hci_chan *chan = NULL; unsigned int num = 0, min = ~0, cur_prio = 0; struct hci_conn *conn; int conn_num = 0; BT_DBG("%s", hdev->name); rcu_read_lock(); list_for_each_entry_rcu(conn, &h->list, list) { struct hci_chan *tmp; if (conn->type != type) continue; if (conn->state != BT_CONNECTED && conn->state != BT_CONFIG) continue; conn_num++; list_for_each_entry_rcu(tmp, &conn->chan_list, list) { struct sk_buff *skb; if (skb_queue_empty(&tmp->data_q)) continue; skb = skb_peek(&tmp->data_q); if (skb->priority < cur_prio) continue; if (skb->priority > cur_prio) { num = 0; min = ~0; cur_prio = skb->priority; } num++; if (conn->sent < min) { min = conn->sent; chan = tmp; } } if (hci_conn_num(hdev, type) == conn_num) break; } rcu_read_unlock(); if (!chan) return NULL; hci_quote_sent(chan->conn, num, quote); BT_DBG("chan %p quote %d", chan, *quote); return chan; } static void hci_prio_recalculate(struct hci_dev *hdev, __u8 type) { struct hci_conn_hash *h = &hdev->conn_hash; struct hci_conn *conn; int num = 0; BT_DBG("%s", hdev->name); rcu_read_lock(); list_for_each_entry_rcu(conn, &h->list, list) { struct hci_chan *chan; if (conn->type != type) continue; if (conn->state != BT_CONNECTED && conn->state != BT_CONFIG) continue; num++; list_for_each_entry_rcu(chan, &conn->chan_list, list) { struct sk_buff *skb; if (chan->sent) { chan->sent = 0; continue; } if (skb_queue_empty(&chan->data_q)) continue; skb = skb_peek(&chan->data_q); if (skb->priority >= HCI_PRIO_MAX - 1) continue; skb->priority = HCI_PRIO_MAX - 1; BT_DBG("chan %p skb %p promoted to %d", chan, skb, skb->priority); } if (hci_conn_num(hdev, type) == num) break; } rcu_read_unlock(); } static void __check_timeout(struct hci_dev *hdev, unsigned int cnt, u8 type) { unsigned long last_tx; if (hci_dev_test_flag(hdev, HCI_UNCONFIGURED)) return; switch (type) { case LE_LINK: last_tx = hdev->le_last_tx; break; default: last_tx = hdev->acl_last_tx; break; } /* tx timeout must be longer than maximum link supervision timeout * (40.9 seconds) */ if (!cnt && time_after(jiffies, last_tx + HCI_ACL_TX_TIMEOUT)) hci_link_tx_to(hdev, type); } /* Schedule SCO */ static void hci_sched_sco(struct hci_dev *hdev) { struct hci_conn *conn; struct sk_buff *skb; int quote; BT_DBG("%s", hdev->name); if (!hci_conn_num(hdev, SCO_LINK)) return; while (hdev->sco_cnt && (conn = hci_low_sent(hdev, SCO_LINK, "e))) { while (quote-- && (skb = skb_dequeue(&conn->data_q))) { BT_DBG("skb %p len %d", skb, skb->len); hci_send_frame(hdev, skb); conn->sent++; if (conn->sent == ~0) conn->sent = 0; } } } static void hci_sched_esco(struct hci_dev *hdev) { struct hci_conn *conn; struct sk_buff *skb; int quote; BT_DBG("%s", hdev->name); if (!hci_conn_num(hdev, ESCO_LINK)) return; while (hdev->sco_cnt && (conn = hci_low_sent(hdev, ESCO_LINK, "e))) { while (quote-- && (skb = skb_dequeue(&conn->data_q))) { BT_DBG("skb %p len %d", skb, skb->len); hci_send_frame(hdev, skb); conn->sent++; if (conn->sent == ~0) conn->sent = 0; } } } static void hci_sched_acl_pkt(struct hci_dev *hdev) { unsigned int cnt = hdev->acl_cnt; struct hci_chan *chan; struct sk_buff *skb; int quote; __check_timeout(hdev, cnt, ACL_LINK); while (hdev->acl_cnt && (chan = hci_chan_sent(hdev, ACL_LINK, "e))) { u32 priority = (skb_peek(&chan->data_q))->priority; while (quote-- && (skb = skb_peek(&chan->data_q))) { BT_DBG("chan %p skb %p len %d priority %u", chan, skb, skb->len, skb->priority); /* Stop if priority has changed */ if (skb->priority < priority) break; skb = skb_dequeue(&chan->data_q); hci_conn_enter_active_mode(chan->conn, bt_cb(skb)->force_active); hci_send_frame(hdev, skb); hdev->acl_last_tx = jiffies; hdev->acl_cnt--; chan->sent++; chan->conn->sent++; /* Send pending SCO packets right away */ hci_sched_sco(hdev); hci_sched_esco(hdev); } } if (cnt != hdev->acl_cnt) hci_prio_recalculate(hdev, ACL_LINK); } static void hci_sched_acl(struct hci_dev *hdev) { BT_DBG("%s", hdev->name); /* No ACL link over BR/EDR controller */ if (!hci_conn_num(hdev, ACL_LINK)) return; hci_sched_acl_pkt(hdev); } static void hci_sched_le(struct hci_dev *hdev) { struct hci_chan *chan; struct sk_buff *skb; int quote, *cnt, tmp; BT_DBG("%s", hdev->name); if (!hci_conn_num(hdev, LE_LINK)) return; cnt = hdev->le_pkts ? &hdev->le_cnt : &hdev->acl_cnt; __check_timeout(hdev, *cnt, LE_LINK); tmp = *cnt; while (*cnt && (chan = hci_chan_sent(hdev, LE_LINK, "e))) { u32 priority = (skb_peek(&chan->data_q))->priority; while (quote-- && (skb = skb_peek(&chan->data_q))) { BT_DBG("chan %p skb %p len %d priority %u", chan, skb, skb->len, skb->priority); /* Stop if priority has changed */ if (skb->priority < priority) break; skb = skb_dequeue(&chan->data_q); hci_send_frame(hdev, skb); hdev->le_last_tx = jiffies; (*cnt)--; chan->sent++; chan->conn->sent++; /* Send pending SCO packets right away */ hci_sched_sco(hdev); hci_sched_esco(hdev); } } if (*cnt != tmp) hci_prio_recalculate(hdev, LE_LINK); } /* Schedule CIS */ static void hci_sched_iso(struct hci_dev *hdev) { struct hci_conn *conn; struct sk_buff *skb; int quote, *cnt; BT_DBG("%s", hdev->name); if (!hci_conn_num(hdev, ISO_LINK)) return; cnt = hdev->iso_pkts ? &hdev->iso_cnt : hdev->le_pkts ? &hdev->le_cnt : &hdev->acl_cnt; while (*cnt && (conn = hci_low_sent(hdev, ISO_LINK, "e))) { while (quote-- && (skb = skb_dequeue(&conn->data_q))) { BT_DBG("skb %p len %d", skb, skb->len); hci_send_frame(hdev, skb); conn->sent++; if (conn->sent == ~0) conn->sent = 0; (*cnt)--; } } } static void hci_tx_work(struct work_struct *work) { struct hci_dev *hdev = container_of(work, struct hci_dev, tx_work); struct sk_buff *skb; BT_DBG("%s acl %d sco %d le %d iso %d", hdev->name, hdev->acl_cnt, hdev->sco_cnt, hdev->le_cnt, hdev->iso_cnt); if (!hci_dev_test_flag(hdev, HCI_USER_CHANNEL)) { /* Schedule queues and send stuff to HCI driver */ hci_sched_sco(hdev); hci_sched_esco(hdev); hci_sched_iso(hdev); hci_sched_acl(hdev); hci_sched_le(hdev); } /* Send next queued raw (unknown type) packet */ while ((skb = skb_dequeue(&hdev->raw_q))) hci_send_frame(hdev, skb); } /* ----- HCI RX task (incoming data processing) ----- */ /* ACL data packet */ static void hci_acldata_packet(struct hci_dev *hdev, struct sk_buff *skb) { struct hci_acl_hdr *hdr; struct hci_conn *conn; __u16 handle, flags; hdr = skb_pull_data(skb, sizeof(*hdr)); if (!hdr) { bt_dev_err(hdev, "ACL packet too small"); goto drop; } handle = __le16_to_cpu(hdr->handle); flags = hci_flags(handle); handle = hci_handle(handle); bt_dev_dbg(hdev, "len %d handle 0x%4.4x flags 0x%4.4x", skb->len, handle, flags); hdev->stat.acl_rx++; hci_dev_lock(hdev); conn = hci_conn_hash_lookup_handle(hdev, handle); hci_dev_unlock(hdev); if (conn) { hci_conn_enter_active_mode(conn, BT_POWER_FORCE_ACTIVE_OFF); /* Send to upper protocol */ l2cap_recv_acldata(conn, skb, flags); return; } else { bt_dev_err(hdev, "ACL packet for unknown connection handle %d", handle); } drop: kfree_skb(skb); } /* SCO data packet */ static void hci_scodata_packet(struct hci_dev *hdev, struct sk_buff *skb) { struct hci_sco_hdr *hdr; struct hci_conn *conn; __u16 handle, flags; hdr = skb_pull_data(skb, sizeof(*hdr)); if (!hdr) { bt_dev_err(hdev, "SCO packet too small"); goto drop; } handle = __le16_to_cpu(hdr->handle); flags = hci_flags(handle); handle = hci_handle(handle); bt_dev_dbg(hdev, "len %d handle 0x%4.4x flags 0x%4.4x", skb->len, handle, flags); hdev->stat.sco_rx++; hci_dev_lock(hdev); conn = hci_conn_hash_lookup_handle(hdev, handle); hci_dev_unlock(hdev); if (conn) { /* Send to upper protocol */ hci_skb_pkt_status(skb) = flags & 0x03; sco_recv_scodata(conn, skb); return; } else { bt_dev_err_ratelimited(hdev, "SCO packet for unknown connection handle %d", handle); } drop: kfree_skb(skb); } static void hci_isodata_packet(struct hci_dev *hdev, struct sk_buff *skb) { struct hci_iso_hdr *hdr; struct hci_conn *conn; __u16 handle, flags; hdr = skb_pull_data(skb, sizeof(*hdr)); if (!hdr) { bt_dev_err(hdev, "ISO packet too small"); goto drop; } handle = __le16_to_cpu(hdr->handle); flags = hci_flags(handle); handle = hci_handle(handle); bt_dev_dbg(hdev, "len %d handle 0x%4.4x flags 0x%4.4x", skb->len, handle, flags); hci_dev_lock(hdev); conn = hci_conn_hash_lookup_handle(hdev, handle); hci_dev_unlock(hdev); if (!conn) { bt_dev_err(hdev, "ISO packet for unknown connection handle %d", handle); goto drop; } /* Send to upper protocol */ iso_recv(conn, skb, flags); return; drop: kfree_skb(skb); } static bool hci_req_is_complete(struct hci_dev *hdev) { struct sk_buff *skb; skb = skb_peek(&hdev->cmd_q); if (!skb) return true; return (bt_cb(skb)->hci.req_flags & HCI_REQ_START); } static void hci_resend_last(struct hci_dev *hdev) { struct hci_command_hdr *sent; struct sk_buff *skb; u16 opcode; if (!hdev->sent_cmd) return; sent = (void *) hdev->sent_cmd->data; opcode = __le16_to_cpu(sent->opcode); if (opcode == HCI_OP_RESET) return; skb = skb_clone(hdev->sent_cmd, GFP_KERNEL); if (!skb) return; skb_queue_head(&hdev->cmd_q, skb); queue_work(hdev->workqueue, &hdev->cmd_work); } void hci_req_cmd_complete(struct hci_dev *hdev, u16 opcode, u8 status, hci_req_complete_t *req_complete, hci_req_complete_skb_t *req_complete_skb) { struct sk_buff *skb; unsigned long flags; BT_DBG("opcode 0x%04x status 0x%02x", opcode, status); /* If the completed command doesn't match the last one that was * sent we need to do special handling of it. */ if (!hci_sent_cmd_data(hdev, opcode)) { /* Some CSR based controllers generate a spontaneous * reset complete event during init and any pending * command will never be completed. In such a case we * need to resend whatever was the last sent * command. */ if (test_bit(HCI_INIT, &hdev->flags) && opcode == HCI_OP_RESET) hci_resend_last(hdev); return; } /* If we reach this point this event matches the last command sent */ hci_dev_clear_flag(hdev, HCI_CMD_PENDING); /* If the command succeeded and there's still more commands in * this request the request is not yet complete. */ if (!status && !hci_req_is_complete(hdev)) return; skb = hdev->req_skb; /* If this was the last command in a request the complete * callback would be found in hdev->req_skb instead of the * command queue (hdev->cmd_q). */ if (skb && bt_cb(skb)->hci.req_flags & HCI_REQ_SKB) { *req_complete_skb = bt_cb(skb)->hci.req_complete_skb; return; } if (skb && bt_cb(skb)->hci.req_complete) { *req_complete = bt_cb(skb)->hci.req_complete; return; } /* Remove all pending commands belonging to this request */ spin_lock_irqsave(&hdev->cmd_q.lock, flags); while ((skb = __skb_dequeue(&hdev->cmd_q))) { if (bt_cb(skb)->hci.req_flags & HCI_REQ_START) { __skb_queue_head(&hdev->cmd_q, skb); break; } if (bt_cb(skb)->hci.req_flags & HCI_REQ_SKB) *req_complete_skb = bt_cb(skb)->hci.req_complete_skb; else *req_complete = bt_cb(skb)->hci.req_complete; dev_kfree_skb_irq(skb); } spin_unlock_irqrestore(&hdev->cmd_q.lock, flags); } static void hci_rx_work(struct work_struct *work) { struct hci_dev *hdev = container_of(work, struct hci_dev, rx_work); struct sk_buff *skb; BT_DBG("%s", hdev->name); /* The kcov_remote functions used for collecting packet parsing * coverage information from this background thread and associate * the coverage with the syscall's thread which originally injected * the packet. This helps fuzzing the kernel. */ for (; (skb = skb_dequeue(&hdev->rx_q)); kcov_remote_stop()) { kcov_remote_start_common(skb_get_kcov_handle(skb)); /* Send copy to monitor */ hci_send_to_monitor(hdev, skb); if (atomic_read(&hdev->promisc)) { /* Send copy to the sockets */ hci_send_to_sock(hdev, skb); } /* If the device has been opened in HCI_USER_CHANNEL, * the userspace has exclusive access to device. * When device is HCI_INIT, we still need to process * the data packets to the driver in order * to complete its setup(). */ if (hci_dev_test_flag(hdev, HCI_USER_CHANNEL) && !test_bit(HCI_INIT, &hdev->flags)) { kfree_skb(skb); continue; } if (test_bit(HCI_INIT, &hdev->flags)) { /* Don't process data packets in this states. */ switch (hci_skb_pkt_type(skb)) { case HCI_ACLDATA_PKT: case HCI_SCODATA_PKT: case HCI_ISODATA_PKT: kfree_skb(skb); continue; } } /* Process frame */ switch (hci_skb_pkt_type(skb)) { case HCI_EVENT_PKT: BT_DBG("%s Event packet", hdev->name); hci_event_packet(hdev, skb); break; case HCI_ACLDATA_PKT: BT_DBG("%s ACL data packet", hdev->name); hci_acldata_packet(hdev, skb); break; case HCI_SCODATA_PKT: BT_DBG("%s SCO data packet", hdev->name); hci_scodata_packet(hdev, skb); break; case HCI_ISODATA_PKT: BT_DBG("%s ISO data packet", hdev->name); hci_isodata_packet(hdev, skb); break; default: kfree_skb(skb); break; } } } static void hci_send_cmd_sync(struct hci_dev *hdev, struct sk_buff *skb) { int err; bt_dev_dbg(hdev, "skb %p", skb); kfree_skb(hdev->sent_cmd); hdev->sent_cmd = skb_clone(skb, GFP_KERNEL); if (!hdev->sent_cmd) { skb_queue_head(&hdev->cmd_q, skb); queue_work(hdev->workqueue, &hdev->cmd_work); return; } err = hci_send_frame(hdev, skb); if (err < 0) { hci_cmd_sync_cancel_sync(hdev, -err); return; } if (hdev->req_status == HCI_REQ_PEND && !hci_dev_test_and_set_flag(hdev, HCI_CMD_PENDING)) { kfree_skb(hdev->req_skb); hdev->req_skb = skb_clone(hdev->sent_cmd, GFP_KERNEL); } atomic_dec(&hdev->cmd_cnt); } static void hci_cmd_work(struct work_struct *work) { struct hci_dev *hdev = container_of(work, struct hci_dev, cmd_work); struct sk_buff *skb; BT_DBG("%s cmd_cnt %d cmd queued %d", hdev->name, atomic_read(&hdev->cmd_cnt), skb_queue_len(&hdev->cmd_q)); /* Send queued commands */ if (atomic_read(&hdev->cmd_cnt)) { skb = skb_dequeue(&hdev->cmd_q); if (!skb) return; hci_send_cmd_sync(hdev, skb); rcu_read_lock(); if (test_bit(HCI_RESET, &hdev->flags) || hci_dev_test_flag(hdev, HCI_CMD_DRAIN_WORKQUEUE)) cancel_delayed_work(&hdev->cmd_timer); else queue_delayed_work(hdev->workqueue, &hdev->cmd_timer, HCI_CMD_TIMEOUT); rcu_read_unlock(); } } |
| 58 | 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 | // SPDX-License-Identifier: GPL-2.0 /* * IPVS An implementation of the IP virtual server support for the * LINUX operating system. IPVS is now implemented as a module * over the NetFilter framework. IPVS can be used to build a * high-performance and highly available server based on a * cluster of servers. * * Version 1, is capable of handling both version 0 and 1 messages. * Version 0 is the plain old format. * Note Version 0 receivers will just drop Ver 1 messages. * Version 1 is capable of handle IPv6, Persistence data, * time-outs, and firewall marks. * In ver.1 "ip_vs_sync_conn_options" will be sent in netw. order. * Ver. 0 can be turned on by sysctl -w net.ipv4.vs.sync_version=0 * * Definitions Message: is a complete datagram * Sync_conn: is a part of a Message * Param Data is an option to a Sync_conn. * * Authors: Wensong Zhang <wensong@linuxvirtualserver.org> * * ip_vs_sync: sync connection info from master load balancer to backups * through multicast * * Changes: * Alexandre Cassen : Added master & backup support at a time. * Alexandre Cassen : Added SyncID support for incoming sync * messages filtering. * Justin Ossevoort : Fix endian problem on sync message size. * Hans Schillstrom : Added Version 1: i.e. IPv6, * Persistence support, fwmark and time-out. */ #define KMSG_COMPONENT "IPVS" #define pr_fmt(fmt) KMSG_COMPONENT ": " fmt #include <linux/module.h> #include <linux/slab.h> #include <linux/inetdevice.h> #include <linux/net.h> #include <linux/completion.h> #include <linux/delay.h> #include <linux/skbuff.h> #include <linux/in.h> #include <linux/igmp.h> /* for ip_mc_join_group */ #include <linux/udp.h> #include <linux/err.h> #include <linux/kthread.h> #include <linux/wait.h> #include <linux/kernel.h> #include <linux/sched/signal.h> #include <linux/unaligned.h> /* Used for ntoh_seq and hton_seq */ #include <net/ip.h> #include <net/sock.h> #include <net/ip_vs.h> #define IP_VS_SYNC_GROUP 0xe0000051 /* multicast addr - 224.0.0.81 */ #define IP_VS_SYNC_PORT 8848 /* multicast port */ #define SYNC_PROTO_VER 1 /* Protocol version in header */ static struct lock_class_key __ipvs_sync_key; /* * IPVS sync connection entry * Version 0, i.e. original version. */ struct ip_vs_sync_conn_v0 { __u8 reserved; /* Protocol, addresses and port numbers */ __u8 protocol; /* Which protocol (TCP/UDP) */ __be16 cport; __be16 vport; __be16 dport; __be32 caddr; /* client address */ __be32 vaddr; /* virtual address */ __be32 daddr; /* destination address */ /* Flags and state transition */ __be16 flags; /* status flags */ __be16 state; /* state info */ /* The sequence options start here */ }; struct ip_vs_sync_conn_options { struct ip_vs_seq in_seq; /* incoming seq. struct */ struct ip_vs_seq out_seq; /* outgoing seq. struct */ }; /* Sync Connection format (sync_conn) 0 1 2 3 0 1 2 3 4 5 6 7 8 9 0 1 2 3 4 5 6 7 8 9 0 1 2 3 4 5 6 7 8 9 0 1 +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ | Type | Protocol | Ver. | Size | +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ | Flags | +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ | State | cport | +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ | vport | dport | +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ | fwmark | +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ | timeout (in sec.) | +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ | ... | | IP-Addresses (v4 or v6) | | ... | +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ Optional Parameters. +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ | Param. Type | Param. Length | Param. data | +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ | | ... | | +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ | | Param Type | Param. Length | +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ | Param data | | Last Param data should be padded for 32 bit alignment | +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ */ /* * Type 0, IPv4 sync connection format */ struct ip_vs_sync_v4 { __u8 type; __u8 protocol; /* Which protocol (TCP/UDP) */ __be16 ver_size; /* Version msb 4 bits */ /* Flags and state transition */ __be32 flags; /* status flags */ __be16 state; /* state info */ /* Protocol, addresses and port numbers */ __be16 cport; __be16 vport; __be16 dport; __be32 fwmark; /* Firewall mark from skb */ __be32 timeout; /* cp timeout */ __be32 caddr; /* client address */ __be32 vaddr; /* virtual address */ __be32 daddr; /* destination address */ /* The sequence options start here */ /* PE data padded to 32bit alignment after seq. options */ }; /* * Type 2 messages IPv6 */ struct ip_vs_sync_v6 { __u8 type; __u8 protocol; /* Which protocol (TCP/UDP) */ __be16 ver_size; /* Version msb 4 bits */ /* Flags and state transition */ __be32 flags; /* status flags */ __be16 state; /* state info */ /* Protocol, addresses and port numbers */ __be16 cport; __be16 vport; __be16 dport; __be32 fwmark; /* Firewall mark from skb */ __be32 timeout; /* cp timeout */ struct in6_addr caddr; /* client address */ struct in6_addr vaddr; /* virtual address */ struct in6_addr daddr; /* destination address */ /* The sequence options start here */ /* PE data padded to 32bit alignment after seq. options */ }; union ip_vs_sync_conn { struct ip_vs_sync_v4 v4; struct ip_vs_sync_v6 v6; }; /* Bits in Type field in above */ #define STYPE_INET6 0 #define STYPE_F_INET6 (1 << STYPE_INET6) #define SVER_SHIFT 12 /* Shift to get version */ #define SVER_MASK 0x0fff /* Mask to strip version */ #define IPVS_OPT_SEQ_DATA 1 #define IPVS_OPT_PE_DATA 2 #define IPVS_OPT_PE_NAME 3 #define IPVS_OPT_PARAM 7 #define IPVS_OPT_F_SEQ_DATA (1 << (IPVS_OPT_SEQ_DATA-1)) #define IPVS_OPT_F_PE_DATA (1 << (IPVS_OPT_PE_DATA-1)) #define IPVS_OPT_F_PE_NAME (1 << (IPVS_OPT_PE_NAME-1)) #define IPVS_OPT_F_PARAM (1 << (IPVS_OPT_PARAM-1)) struct ip_vs_sync_thread_data { struct task_struct *task; struct netns_ipvs *ipvs; struct socket *sock; char *buf; int id; }; /* Version 0 definition of packet sizes */ #define SIMPLE_CONN_SIZE (sizeof(struct ip_vs_sync_conn_v0)) #define FULL_CONN_SIZE \ (sizeof(struct ip_vs_sync_conn_v0) + sizeof(struct ip_vs_sync_conn_options)) /* The master mulitcasts messages (Datagrams) to the backup load balancers in the following format. Version 1: Note, first byte should be Zero, so ver 0 receivers will drop the packet. 0 1 2 3 0 1 2 3 4 5 6 7 8 9 0 1 2 3 4 5 6 7 8 9 0 1 2 3 4 5 6 7 8 9 0 1 +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ | 0 | SyncID | Size | +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ | Count Conns | Version | Reserved, set to Zero | +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ | | | IPVS Sync Connection (1) | +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ | . | ~ . ~ | . | +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ | | | IPVS Sync Connection (n) | +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ Version 0 Header 0 1 2 3 0 1 2 3 4 5 6 7 8 9 0 1 2 3 4 5 6 7 8 9 0 1 2 3 4 5 6 7 8 9 0 1 +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ | Count Conns | SyncID | Size | +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ | IPVS Sync Connection (1) | */ /* Version 0 header */ struct ip_vs_sync_mesg_v0 { __u8 nr_conns; __u8 syncid; __be16 size; /* ip_vs_sync_conn entries start here */ }; /* Version 1 header */ struct ip_vs_sync_mesg { __u8 reserved; /* must be zero */ __u8 syncid; __be16 size; __u8 nr_conns; __s8 version; /* SYNC_PROTO_VER */ __u16 spare; /* ip_vs_sync_conn entries start here */ }; union ipvs_sockaddr { struct sockaddr_in in; struct sockaddr_in6 in6; }; struct ip_vs_sync_buff { struct list_head list; unsigned long firstuse; /* pointers for the message data */ struct ip_vs_sync_mesg *mesg; unsigned char *head; unsigned char *end; }; /* * Copy of struct ip_vs_seq * From unaligned network order to aligned host order */ static void ntoh_seq(struct ip_vs_seq *no, struct ip_vs_seq *ho) { memset(ho, 0, sizeof(*ho)); ho->init_seq = get_unaligned_be32(&no->init_seq); ho->delta = get_unaligned_be32(&no->delta); ho->previous_delta = get_unaligned_be32(&no->previous_delta); } /* * Copy of struct ip_vs_seq * From Aligned host order to unaligned network order */ static void hton_seq(struct ip_vs_seq *ho, struct ip_vs_seq *no) { put_unaligned_be32(ho->init_seq, &no->init_seq); put_unaligned_be32(ho->delta, &no->delta); put_unaligned_be32(ho->previous_delta, &no->previous_delta); } static inline struct ip_vs_sync_buff * sb_dequeue(struct netns_ipvs *ipvs, struct ipvs_master_sync_state *ms) { struct ip_vs_sync_buff *sb; spin_lock_bh(&ipvs->sync_lock); if (list_empty(&ms->sync_queue)) { sb = NULL; __set_current_state(TASK_INTERRUPTIBLE); } else { sb = list_entry(ms->sync_queue.next, struct ip_vs_sync_buff, list); list_del(&sb->list); ms->sync_queue_len--; if (!ms->sync_queue_len) ms->sync_queue_delay = 0; } spin_unlock_bh(&ipvs->sync_lock); return sb; } /* * Create a new sync buffer for Version 1 proto. */ static inline struct ip_vs_sync_buff * ip_vs_sync_buff_create(struct netns_ipvs *ipvs, unsigned int len) { struct ip_vs_sync_buff *sb; if (!(sb=kmalloc(sizeof(struct ip_vs_sync_buff), GFP_ATOMIC))) return NULL; len = max_t(unsigned int, len + sizeof(struct ip_vs_sync_mesg), ipvs->mcfg.sync_maxlen); sb->mesg = kmalloc(len, GFP_ATOMIC); if (!sb->mesg) { kfree(sb); return NULL; } sb->mesg->reserved = 0; /* old nr_conns i.e. must be zero now */ sb->mesg->version = SYNC_PROTO_VER; sb->mesg->syncid = ipvs->mcfg.syncid; sb->mesg->size = htons(sizeof(struct ip_vs_sync_mesg)); sb->mesg->nr_conns = 0; sb->mesg->spare = 0; sb->head = (unsigned char *)sb->mesg + sizeof(struct ip_vs_sync_mesg); sb->end = (unsigned char *)sb->mesg + len; sb->firstuse = jiffies; return sb; } static inline void ip_vs_sync_buff_release(struct ip_vs_sync_buff *sb) { kfree(sb->mesg); kfree(sb); } static inline void sb_queue_tail(struct netns_ipvs *ipvs, struct ipvs_master_sync_state *ms) { struct ip_vs_sync_buff *sb = ms->sync_buff; spin_lock(&ipvs->sync_lock); if (ipvs->sync_state & IP_VS_STATE_MASTER && ms->sync_queue_len < sysctl_sync_qlen_max(ipvs)) { if (!ms->sync_queue_len) schedule_delayed_work(&ms->master_wakeup_work, max(IPVS_SYNC_SEND_DELAY, 1)); ms->sync_queue_len++; list_add_tail(&sb->list, &ms->sync_queue); if ((++ms->sync_queue_delay) == IPVS_SYNC_WAKEUP_RATE) { int id = (int)(ms - ipvs->ms); wake_up_process(ipvs->master_tinfo[id].task); } } else ip_vs_sync_buff_release(sb); spin_unlock(&ipvs->sync_lock); } /* * Get the current sync buffer if it has been created for more * than the specified time or the specified time is zero. */ static inline struct ip_vs_sync_buff * get_curr_sync_buff(struct netns_ipvs *ipvs, struct ipvs_master_sync_state *ms, unsigned long time) { struct ip_vs_sync_buff *sb; spin_lock_bh(&ipvs->sync_buff_lock); sb = ms->sync_buff; if (sb && time_after_eq(jiffies - sb->firstuse, time)) { ms->sync_buff = NULL; __set_current_state(TASK_RUNNING); } else sb = NULL; spin_unlock_bh(&ipvs->sync_buff_lock); return sb; } static inline int select_master_thread_id(struct netns_ipvs *ipvs, struct ip_vs_conn *cp) { return ((long) cp >> (1 + ilog2(sizeof(*cp)))) & ipvs->threads_mask; } /* * Create a new sync buffer for Version 0 proto. */ static inline struct ip_vs_sync_buff * ip_vs_sync_buff_create_v0(struct netns_ipvs *ipvs, unsigned int len) { struct ip_vs_sync_buff *sb; struct ip_vs_sync_mesg_v0 *mesg; if (!(sb=kmalloc(sizeof(struct ip_vs_sync_buff), GFP_ATOMIC))) return NULL; len = max_t(unsigned int, len + sizeof(struct ip_vs_sync_mesg_v0), ipvs->mcfg.sync_maxlen); sb->mesg = kmalloc(len, GFP_ATOMIC); if (!sb->mesg) { kfree(sb); return NULL; } mesg = (struct ip_vs_sync_mesg_v0 *)sb->mesg; mesg->nr_conns = 0; mesg->syncid = ipvs->mcfg.syncid; mesg->size = htons(sizeof(struct ip_vs_sync_mesg_v0)); sb->head = (unsigned char *)mesg + sizeof(struct ip_vs_sync_mesg_v0); sb->end = (unsigned char *)mesg + len; sb->firstuse = jiffies; return sb; } /* Check if connection is controlled by persistence */ static inline bool in_persistence(struct ip_vs_conn *cp) { for (cp = cp->control; cp; cp = cp->control) { if (cp->flags & IP_VS_CONN_F_TEMPLATE) return true; } return false; } /* Check if conn should be synced. * pkts: conn packets, use sysctl_sync_threshold to avoid packet check * - (1) sync_refresh_period: reduce sync rate. Additionally, retry * sync_retries times with period of sync_refresh_period/8 * - (2) if both sync_refresh_period and sync_period are 0 send sync only * for state changes or only once when pkts matches sync_threshold * - (3) templates: rate can be reduced only with sync_refresh_period or * with (2) */ static int ip_vs_sync_conn_needed(struct netns_ipvs *ipvs, struct ip_vs_conn *cp, int pkts) { unsigned long orig = READ_ONCE(cp->sync_endtime); unsigned long now = jiffies; unsigned long n = (now + cp->timeout) & ~3UL; unsigned int sync_refresh_period; int sync_period; int force; /* Check if we sync in current state */ if (unlikely(cp->flags & IP_VS_CONN_F_TEMPLATE)) force = 0; else if (unlikely(sysctl_sync_persist_mode(ipvs) && in_persistence(cp))) return 0; else if (likely(cp->protocol == IPPROTO_TCP)) { if (!((1 << cp->state) & ((1 << IP_VS_TCP_S_ESTABLISHED) | (1 << IP_VS_TCP_S_FIN_WAIT) | (1 << IP_VS_TCP_S_CLOSE) | (1 << IP_VS_TCP_S_CLOSE_WAIT) | (1 << IP_VS_TCP_S_TIME_WAIT)))) return 0; force = cp->state != cp->old_state; if (force && cp->state != IP_VS_TCP_S_ESTABLISHED) goto set; } else if (unlikely(cp->protocol == IPPROTO_SCTP)) { if (!((1 << cp->state) & ((1 << IP_VS_SCTP_S_ESTABLISHED) | (1 << IP_VS_SCTP_S_SHUTDOWN_SENT) | (1 << IP_VS_SCTP_S_SHUTDOWN_RECEIVED) | (1 << IP_VS_SCTP_S_SHUTDOWN_ACK_SENT) | (1 << IP_VS_SCTP_S_CLOSED)))) return 0; force = cp->state != cp->old_state; if (force && cp->state != IP_VS_SCTP_S_ESTABLISHED) goto set; } else { /* UDP or another protocol with single state */ force = 0; } sync_refresh_period = sysctl_sync_refresh_period(ipvs); if (sync_refresh_period > 0) { long diff = n - orig; long min_diff = max(cp->timeout >> 1, 10UL * HZ); /* Avoid sync if difference is below sync_refresh_period * and below the half timeout. */ if (abs(diff) < min_t(long, sync_refresh_period, min_diff)) { int retries = orig & 3; if (retries >= sysctl_sync_retries(ipvs)) return 0; if (time_before(now, orig - cp->timeout + (sync_refresh_period >> 3))) return 0; n |= retries + 1; } } sync_period = sysctl_sync_period(ipvs); if (sync_period > 0) { if (!(cp->flags & IP_VS_CONN_F_TEMPLATE) && pkts % sync_period != sysctl_sync_threshold(ipvs)) return 0; } else if (!sync_refresh_period && pkts != sysctl_sync_threshold(ipvs)) return 0; set: cp->old_state = cp->state; n = cmpxchg(&cp->sync_endtime, orig, n); return n == orig || force; } /* * Version 0 , could be switched in by sys_ctl. * Add an ip_vs_conn information into the current sync_buff. */ static void ip_vs_sync_conn_v0(struct netns_ipvs *ipvs, struct ip_vs_conn *cp, int pkts) { struct ip_vs_sync_mesg_v0 *m; struct ip_vs_sync_conn_v0 *s; struct ip_vs_sync_buff *buff; struct ipvs_master_sync_state *ms; int id; unsigned int len; if (unlikely(cp->af != AF_INET)) return; /* Do not sync ONE PACKET */ if (cp->flags & IP_VS_CONN_F_ONE_PACKET) return; if (!ip_vs_sync_conn_needed(ipvs, cp, pkts)) return; spin_lock_bh(&ipvs->sync_buff_lock); if (!(ipvs->sync_state & IP_VS_STATE_MASTER)) { spin_unlock_bh(&ipvs->sync_buff_lock); return; } id = select_master_thread_id(ipvs, cp); ms = &ipvs->ms[id]; buff = ms->sync_buff; len = (cp->flags & IP_VS_CONN_F_SEQ_MASK) ? FULL_CONN_SIZE : SIMPLE_CONN_SIZE; if (buff) { m = (struct ip_vs_sync_mesg_v0 *) buff->mesg; /* Send buffer if it is for v1 */ if (buff->head + len > buff->end || !m->nr_conns) { sb_queue_tail(ipvs, ms); ms->sync_buff = NULL; buff = NULL; } } if (!buff) { buff = ip_vs_sync_buff_create_v0(ipvs, len); if (!buff) { spin_unlock_bh(&ipvs->sync_buff_lock); pr_err("ip_vs_sync_buff_create failed.\n"); return; } ms->sync_buff = buff; } m = (struct ip_vs_sync_mesg_v0 *) buff->mesg; s = (struct ip_vs_sync_conn_v0 *) buff->head; /* copy members */ s->reserved = 0; s->protocol = cp->protocol; s->cport = cp->cport; s->vport = cp->vport; s->dport = cp->dport; s->caddr = cp->caddr.ip; s->vaddr = cp->vaddr.ip; s->daddr = cp->daddr.ip; s->flags = htons(cp->flags & ~IP_VS_CONN_F_HASHED); s->state = htons(cp->state); if (cp->flags & IP_VS_CONN_F_SEQ_MASK) { struct ip_vs_sync_conn_options *opt = (struct ip_vs_sync_conn_options *)&s[1]; memcpy(opt, &cp->sync_conn_opt, sizeof(*opt)); } m->nr_conns++; m->size = htons(ntohs(m->size) + len); buff->head += len; spin_unlock_bh(&ipvs->sync_buff_lock); /* synchronize its controller if it has */ cp = cp->control; if (cp) { if (cp->flags & IP_VS_CONN_F_TEMPLATE) pkts = atomic_inc_return(&cp->in_pkts); else pkts = sysctl_sync_threshold(ipvs); ip_vs_sync_conn(ipvs, cp, pkts); } } /* * Add an ip_vs_conn information into the current sync_buff. * Called by ip_vs_in. * Sending Version 1 messages */ void ip_vs_sync_conn(struct netns_ipvs *ipvs, struct ip_vs_conn *cp, int pkts) { struct ip_vs_sync_mesg *m; union ip_vs_sync_conn *s; struct ip_vs_sync_buff *buff; struct ipvs_master_sync_state *ms; int id; __u8 *p; unsigned int len, pe_name_len, pad; /* Handle old version of the protocol */ if (sysctl_sync_ver(ipvs) == 0) { ip_vs_sync_conn_v0(ipvs, cp, pkts); return; } /* Do not sync ONE PACKET */ if (cp->flags & IP_VS_CONN_F_ONE_PACKET) goto control; sloop: if (!ip_vs_sync_conn_needed(ipvs, cp, pkts)) goto control; /* Sanity checks */ pe_name_len = 0; if (cp->pe_data_len) { if (!cp->pe_data || !cp->dest) { IP_VS_ERR_RL("SYNC, connection pe_data invalid\n"); return; } pe_name_len = strnlen(cp->pe->name, IP_VS_PENAME_MAXLEN); } spin_lock_bh(&ipvs->sync_buff_lock); if (!(ipvs->sync_state & IP_VS_STATE_MASTER)) { spin_unlock_bh(&ipvs->sync_buff_lock); return; } id = select_master_thread_id(ipvs, cp); ms = &ipvs->ms[id]; #ifdef CONFIG_IP_VS_IPV6 if (cp->af == AF_INET6) len = sizeof(struct ip_vs_sync_v6); else #endif len = sizeof(struct ip_vs_sync_v4); if (cp->flags & IP_VS_CONN_F_SEQ_MASK) len += sizeof(struct ip_vs_sync_conn_options) + 2; if (cp->pe_data_len) len += cp->pe_data_len + 2; /* + Param hdr field */ if (pe_name_len) len += pe_name_len + 2; /* check if there is a space for this one */ pad = 0; buff = ms->sync_buff; if (buff) { m = buff->mesg; pad = (4 - (size_t) buff->head) & 3; /* Send buffer if it is for v0 */ if (buff->head + len + pad > buff->end || m->reserved) { sb_queue_tail(ipvs, ms); ms->sync_buff = NULL; buff = NULL; pad = 0; } } if (!buff) { buff = ip_vs_sync_buff_create(ipvs, len); if (!buff) { spin_unlock_bh(&ipvs->sync_buff_lock); pr_err("ip_vs_sync_buff_create failed.\n"); return; } ms->sync_buff = buff; m = buff->mesg; } p = buff->head; buff->head += pad + len; m->size = htons(ntohs(m->size) + pad + len); /* Add ev. padding from prev. sync_conn */ while (pad--) *(p++) = 0; s = (union ip_vs_sync_conn *)p; /* Set message type & copy members */ s->v4.type = (cp->af == AF_INET6 ? STYPE_F_INET6 : 0); s->v4.ver_size = htons(len & SVER_MASK); /* Version 0 */ s->v4.flags = htonl(cp->flags & ~IP_VS_CONN_F_HASHED); s->v4.state = htons(cp->state); s->v4.protocol = cp->protocol; s->v4.cport = cp->cport; s->v4.vport = cp->vport; s->v4.dport = cp->dport; s->v4.fwmark = htonl(cp->fwmark); s->v4.timeout = htonl(cp->timeout / HZ); m->nr_conns++; #ifdef CONFIG_IP_VS_IPV6 if (cp->af == AF_INET6) { p += sizeof(struct ip_vs_sync_v6); s->v6.caddr = cp->caddr.in6; s->v6.vaddr = cp->vaddr.in6; s->v6.daddr = cp->daddr.in6; } else #endif { p += sizeof(struct ip_vs_sync_v4); /* options ptr */ s->v4.caddr = cp->caddr.ip; s->v4.vaddr = cp->vaddr.ip; s->v4.daddr = cp->daddr.ip; } if (cp->flags & IP_VS_CONN_F_SEQ_MASK) { *(p++) = IPVS_OPT_SEQ_DATA; *(p++) = sizeof(struct ip_vs_sync_conn_options); hton_seq((struct ip_vs_seq *)p, &cp->in_seq); p += sizeof(struct ip_vs_seq); hton_seq((struct ip_vs_seq *)p, &cp->out_seq); p += sizeof(struct ip_vs_seq); } /* Handle pe data */ if (cp->pe_data_len && cp->pe_data) { *(p++) = IPVS_OPT_PE_DATA; *(p++) = cp->pe_data_len; memcpy(p, cp->pe_data, cp->pe_data_len); p += cp->pe_data_len; if (pe_name_len) { /* Add PE_NAME */ *(p++) = IPVS_OPT_PE_NAME; *(p++) = pe_name_len; memcpy(p, cp->pe->name, pe_name_len); p += pe_name_len; } } spin_unlock_bh(&ipvs->sync_buff_lock); control: /* synchronize its controller if it has */ cp = cp->control; if (!cp) return; if (cp->flags & IP_VS_CONN_F_TEMPLATE) pkts = atomic_inc_return(&cp->in_pkts); else pkts = sysctl_sync_threshold(ipvs); goto sloop; } /* * fill_param used by version 1 */ static inline int ip_vs_conn_fill_param_sync(struct netns_ipvs *ipvs, int af, union ip_vs_sync_conn *sc, struct ip_vs_conn_param *p, __u8 *pe_data, unsigned int pe_data_len, __u8 *pe_name, unsigned int pe_name_len) { #ifdef CONFIG_IP_VS_IPV6 if (af == AF_INET6) ip_vs_conn_fill_param(ipvs, af, sc->v6.protocol, (const union nf_inet_addr *)&sc->v6.caddr, sc->v6.cport, (const union nf_inet_addr *)&sc->v6.vaddr, sc->v6.vport, p); else #endif ip_vs_conn_fill_param(ipvs, af, sc->v4.protocol, (const union nf_inet_addr *)&sc->v4.caddr, sc->v4.cport, (const union nf_inet_addr *)&sc->v4.vaddr, sc->v4.vport, p); /* Handle pe data */ if (pe_data_len) { if (pe_name_len) { char buff[IP_VS_PENAME_MAXLEN+1]; memcpy(buff, pe_name, pe_name_len); buff[pe_name_len]=0; p->pe = __ip_vs_pe_getbyname(buff); if (!p->pe) { IP_VS_DBG(3, "BACKUP, no %s engine found/loaded\n", buff); return 1; } } else { IP_VS_ERR_RL("BACKUP, Invalid PE parameters\n"); return 1; } p->pe_data = kmemdup(pe_data, pe_data_len, GFP_ATOMIC); if (!p->pe_data) { module_put(p->pe->module); return -ENOMEM; } p->pe_data_len = pe_data_len; } return 0; } /* * Connection Add / Update. * Common for version 0 and 1 reception of backup sync_conns. * Param: ... * timeout is in sec. */ static void ip_vs_proc_conn(struct netns_ipvs *ipvs, struct ip_vs_conn_param *param, unsigned int flags, unsigned int state, unsigned int protocol, unsigned int type, const union nf_inet_addr *daddr, __be16 dport, unsigned long timeout, __u32 fwmark, struct ip_vs_sync_conn_options *opt) { struct ip_vs_dest *dest; struct ip_vs_conn *cp; if (!(flags & IP_VS_CONN_F_TEMPLATE)) { cp = ip_vs_conn_in_get(param); if (cp && ((cp->dport != dport) || !ip_vs_addr_equal(cp->daf, &cp->daddr, daddr))) { if (!(flags & IP_VS_CONN_F_INACTIVE)) { ip_vs_conn_expire_now(cp); __ip_vs_conn_put(cp); cp = NULL; } else { /* This is the expiration message for the * connection that was already replaced, so we * just ignore it. */ __ip_vs_conn_put(cp); kfree(param->pe_data); return; } } } else { cp = ip_vs_ct_in_get(param); } if (cp) { /* Free pe_data */ kfree(param->pe_data); dest = cp->dest; spin_lock_bh(&cp->lock); if ((cp->flags ^ flags) & IP_VS_CONN_F_INACTIVE && !(flags & IP_VS_CONN_F_TEMPLATE) && dest) { if (flags & IP_VS_CONN_F_INACTIVE) { atomic_dec(&dest->activeconns); atomic_inc(&dest->inactconns); } else { atomic_inc(&dest->activeconns); atomic_dec(&dest->inactconns); } } flags &= IP_VS_CONN_F_BACKUP_UPD_MASK; flags |= cp->flags & ~IP_VS_CONN_F_BACKUP_UPD_MASK; cp->flags = flags; spin_unlock_bh(&cp->lock); if (!dest) ip_vs_try_bind_dest(cp); } else { /* * Find the appropriate destination for the connection. * If it is not found the connection will remain unbound * but still handled. */ rcu_read_lock(); /* This function is only invoked by the synchronization * code. We do not currently support heterogeneous pools * with synchronization, so we can make the assumption that * the svc_af is the same as the dest_af */ dest = ip_vs_find_dest(ipvs, type, type, daddr, dport, param->vaddr, param->vport, protocol, fwmark, flags); cp = ip_vs_conn_new(param, type, daddr, dport, flags, dest, fwmark); rcu_read_unlock(); if (!cp) { kfree(param->pe_data); IP_VS_DBG(2, "BACKUP, add new conn. failed\n"); return; } if (!(flags & IP_VS_CONN_F_TEMPLATE)) kfree(param->pe_data); } if (opt) { cp->in_seq = opt->in_seq; cp->out_seq = opt->out_seq; } atomic_set(&cp->in_pkts, sysctl_sync_threshold(ipvs)); cp->state = state; cp->old_state = cp->state; /* * For Ver 0 messages style * - Not possible to recover the right timeout for templates * - can not find the right fwmark * virtual service. If needed, we can do it for * non-fwmark persistent services. * Ver 1 messages style. * - No problem. */ if (timeout) { if (timeout > MAX_SCHEDULE_TIMEOUT / HZ) timeout = MAX_SCHEDULE_TIMEOUT / HZ; cp->timeout = timeout*HZ; } else { struct ip_vs_proto_data *pd; pd = ip_vs_proto_data_get(ipvs, protocol); if (!(flags & IP_VS_CONN_F_TEMPLATE) && pd && pd->timeout_table) cp->timeout = pd->timeout_table[state]; else cp->timeout = (3*60*HZ); } ip_vs_conn_put(cp); } /* * Process received multicast message for Version 0 */ static void ip_vs_process_message_v0(struct netns_ipvs *ipvs, const char *buffer, const size_t buflen) { struct ip_vs_sync_mesg_v0 *m = (struct ip_vs_sync_mesg_v0 *)buffer; struct ip_vs_sync_conn_v0 *s; struct ip_vs_sync_conn_options *opt; struct ip_vs_protocol *pp; struct ip_vs_conn_param param; char *p; int i; p = (char *)buffer + sizeof(struct ip_vs_sync_mesg_v0); for (i=0; i<m->nr_conns; i++) { unsigned int flags, state; if (p + SIMPLE_CONN_SIZE > buffer+buflen) { IP_VS_ERR_RL("BACKUP v0, bogus conn\n"); return; } s = (struct ip_vs_sync_conn_v0 *) p; flags = ntohs(s->flags) | IP_VS_CONN_F_SYNC; flags &= ~IP_VS_CONN_F_HASHED; if (flags & IP_VS_CONN_F_SEQ_MASK) { opt = (struct ip_vs_sync_conn_options *)&s[1]; p += FULL_CONN_SIZE; if (p > buffer+buflen) { IP_VS_ERR_RL("BACKUP v0, Dropping buffer bogus conn options\n"); return; } } else { opt = NULL; p += SIMPLE_CONN_SIZE; } state = ntohs(s->state); if (!(flags & IP_VS_CONN_F_TEMPLATE)) { pp = ip_vs_proto_get(s->protocol); if (!pp) { IP_VS_DBG(2, "BACKUP v0, Unsupported protocol %u\n", s->protocol); continue; } if (state >= pp->num_states) { IP_VS_DBG(2, "BACKUP v0, Invalid %s state %u\n", pp->name, state); continue; } } else { if (state >= IP_VS_CTPL_S_LAST) IP_VS_DBG(7, "BACKUP v0, Invalid tpl state %u\n", state); } ip_vs_conn_fill_param(ipvs, AF_INET, s->protocol, (const union nf_inet_addr *)&s->caddr, s->cport, (const union nf_inet_addr *)&s->vaddr, s->vport, ¶m); /* Send timeout as Zero */ ip_vs_proc_conn(ipvs, ¶m, flags, state, s->protocol, AF_INET, (union nf_inet_addr *)&s->daddr, s->dport, 0, 0, opt); } } /* * Handle options */ static inline int ip_vs_proc_seqopt(__u8 *p, unsigned int plen, __u32 *opt_flags, struct ip_vs_sync_conn_options *opt) { struct ip_vs_sync_conn_options *topt; topt = (struct ip_vs_sync_conn_options *)p; if (plen != sizeof(struct ip_vs_sync_conn_options)) { IP_VS_DBG(2, "BACKUP, bogus conn options length\n"); return -EINVAL; } if (*opt_flags & IPVS_OPT_F_SEQ_DATA) { IP_VS_DBG(2, "BACKUP, conn options found twice\n"); return -EINVAL; } ntoh_seq(&topt->in_seq, &opt->in_seq); ntoh_seq(&topt->out_seq, &opt->out_seq); *opt_flags |= IPVS_OPT_F_SEQ_DATA; return 0; } static int ip_vs_proc_str(__u8 *p, unsigned int plen, unsigned int *data_len, __u8 **data, unsigned int maxlen, __u32 *opt_flags, __u32 flag) { if (plen > maxlen) { IP_VS_DBG(2, "BACKUP, bogus par.data len > %d\n", maxlen); return -EINVAL; } if (*opt_flags & flag) { IP_VS_DBG(2, "BACKUP, Par.data found twice 0x%x\n", flag); return -EINVAL; } *data_len = plen; *data = p; *opt_flags |= flag; return 0; } /* * Process a Version 1 sync. connection */ static inline int ip_vs_proc_sync_conn(struct netns_ipvs *ipvs, __u8 *p, __u8 *msg_end) { struct ip_vs_sync_conn_options opt; union ip_vs_sync_conn *s; struct ip_vs_protocol *pp; struct ip_vs_conn_param param; __u32 flags; unsigned int af, state, pe_data_len=0, pe_name_len=0; __u8 *pe_data=NULL, *pe_name=NULL; __u32 opt_flags=0; int retc=0; s = (union ip_vs_sync_conn *) p; if (s->v6.type & STYPE_F_INET6) { #ifdef CONFIG_IP_VS_IPV6 af = AF_INET6; p += sizeof(struct ip_vs_sync_v6); #else IP_VS_DBG(3,"BACKUP, IPv6 msg received, and IPVS is not compiled for IPv6\n"); retc = 10; goto out; #endif } else if (!s->v4.type) { af = AF_INET; p += sizeof(struct ip_vs_sync_v4); } else { return -10; } if (p > msg_end) return -20; /* Process optional params check Type & Len. */ while (p < msg_end) { int ptype; int plen; if (p+2 > msg_end) return -30; ptype = *(p++); plen = *(p++); if (!plen || ((p + plen) > msg_end)) return -40; /* Handle seq option p = param data */ switch (ptype & ~IPVS_OPT_F_PARAM) { case IPVS_OPT_SEQ_DATA: if (ip_vs_proc_seqopt(p, plen, &opt_flags, &opt)) return -50; break; case IPVS_OPT_PE_DATA: if (ip_vs_proc_str(p, plen, &pe_data_len, &pe_data, IP_VS_PEDATA_MAXLEN, &opt_flags, IPVS_OPT_F_PE_DATA)) return -60; break; case IPVS_OPT_PE_NAME: if (ip_vs_proc_str(p, plen,&pe_name_len, &pe_name, IP_VS_PENAME_MAXLEN, &opt_flags, IPVS_OPT_F_PE_NAME)) return -70; break; default: /* Param data mandatory ? */ if (!(ptype & IPVS_OPT_F_PARAM)) { IP_VS_DBG(3, "BACKUP, Unknown mandatory param %d found\n", ptype & ~IPVS_OPT_F_PARAM); retc = 20; goto out; } } p += plen; /* Next option */ } /* Get flags and Mask off unsupported */ flags = ntohl(s->v4.flags) & IP_VS_CONN_F_BACKUP_MASK; flags |= IP_VS_CONN_F_SYNC; state = ntohs(s->v4.state); if (!(flags & IP_VS_CONN_F_TEMPLATE)) { pp = ip_vs_proto_get(s->v4.protocol); if (!pp) { IP_VS_DBG(3,"BACKUP, Unsupported protocol %u\n", s->v4.protocol); retc = 30; goto out; } if (state >= pp->num_states) { IP_VS_DBG(3, "BACKUP, Invalid %s state %u\n", pp->name, state); retc = 40; goto out; } } else { if (state >= IP_VS_CTPL_S_LAST) IP_VS_DBG(7, "BACKUP, Invalid tpl state %u\n", state); } if (ip_vs_conn_fill_param_sync(ipvs, af, s, ¶m, pe_data, pe_data_len, pe_name, pe_name_len)) { retc = 50; goto out; } /* If only IPv4, just silent skip IPv6 */ if (af == AF_INET) ip_vs_proc_conn(ipvs, ¶m, flags, state, s->v4.protocol, af, (union nf_inet_addr *)&s->v4.daddr, s->v4.dport, ntohl(s->v4.timeout), ntohl(s->v4.fwmark), (opt_flags & IPVS_OPT_F_SEQ_DATA ? &opt : NULL) ); #ifdef CONFIG_IP_VS_IPV6 else ip_vs_proc_conn(ipvs, ¶m, flags, state, s->v6.protocol, af, (union nf_inet_addr *)&s->v6.daddr, s->v6.dport, ntohl(s->v6.timeout), ntohl(s->v6.fwmark), (opt_flags & IPVS_OPT_F_SEQ_DATA ? &opt : NULL) ); #endif ip_vs_pe_put(param.pe); return 0; /* Error exit */ out: IP_VS_DBG(2, "BACKUP, Single msg dropped err:%d\n", retc); return retc; } /* * Process received multicast message and create the corresponding * ip_vs_conn entries. * Handles Version 0 & 1 */ static void ip_vs_process_message(struct netns_ipvs *ipvs, __u8 *buffer, const size_t buflen) { struct ip_vs_sync_mesg *m2 = (struct ip_vs_sync_mesg *)buffer; __u8 *p, *msg_end; int i, nr_conns; if (buflen < sizeof(struct ip_vs_sync_mesg_v0)) { IP_VS_DBG(2, "BACKUP, message header too short\n"); return; } if (buflen != ntohs(m2->size)) { IP_VS_DBG(2, "BACKUP, bogus message size\n"); return; } /* SyncID sanity check */ if (ipvs->bcfg.syncid != 0 && m2->syncid != ipvs->bcfg.syncid) { IP_VS_DBG(7, "BACKUP, Ignoring syncid = %d\n", m2->syncid); return; } /* Handle version 1 message */ if ((m2->version == SYNC_PROTO_VER) && (m2->reserved == 0) && (m2->spare == 0)) { msg_end = buffer + sizeof(struct ip_vs_sync_mesg); nr_conns = m2->nr_conns; for (i=0; i<nr_conns; i++) { union ip_vs_sync_conn *s; unsigned int size; int retc; p = msg_end; if (p + sizeof(s->v4) > buffer+buflen) { IP_VS_ERR_RL("BACKUP, Dropping buffer, too small\n"); return; } s = (union ip_vs_sync_conn *)p; size = ntohs(s->v4.ver_size) & SVER_MASK; msg_end = p + size; /* Basic sanity checks */ if (msg_end > buffer+buflen) { IP_VS_ERR_RL("BACKUP, Dropping buffer, msg > buffer\n"); return; } if (ntohs(s->v4.ver_size) >> SVER_SHIFT) { IP_VS_ERR_RL("BACKUP, Dropping buffer, Unknown version %d\n", ntohs(s->v4.ver_size) >> SVER_SHIFT); return; } /* Process a single sync_conn */ retc = ip_vs_proc_sync_conn(ipvs, p, msg_end); if (retc < 0) { IP_VS_ERR_RL("BACKUP, Dropping buffer, Err: %d in decoding\n", retc); return; } /* Make sure we have 32 bit alignment */ msg_end = p + ((size + 3) & ~3); } } else { /* Old type of message */ ip_vs_process_message_v0(ipvs, buffer, buflen); return; } } /* * Setup sndbuf (mode=1) or rcvbuf (mode=0) */ static void set_sock_size(struct sock *sk, int mode, int val) { /* setsockopt(sock, SOL_SOCKET, SO_SNDBUF, &val, sizeof(val)); */ /* setsockopt(sock, SOL_SOCKET, SO_RCVBUF, &val, sizeof(val)); */ lock_sock(sk); if (mode) { val = clamp_t(int, val, (SOCK_MIN_SNDBUF + 1) / 2, READ_ONCE(sysctl_wmem_max)); sk->sk_sndbuf = val * 2; sk->sk_userlocks |= SOCK_SNDBUF_LOCK; } else { val = clamp_t(int, val, (SOCK_MIN_RCVBUF + 1) / 2, READ_ONCE(sysctl_rmem_max)); sk->sk_rcvbuf = val * 2; sk->sk_userlocks |= SOCK_RCVBUF_LOCK; } release_sock(sk); } /* * Setup loopback of outgoing multicasts on a sending socket */ static void set_mcast_loop(struct sock *sk, u_char loop) { /* setsockopt(sock, SOL_IP, IP_MULTICAST_LOOP, &loop, sizeof(loop)); */ inet_assign_bit(MC_LOOP, sk, loop); #ifdef CONFIG_IP_VS_IPV6 if (READ_ONCE(sk->sk_family) == AF_INET6) { /* IPV6_MULTICAST_LOOP */ inet6_assign_bit(MC6_LOOP, sk, loop); } #endif } /* * Specify TTL for outgoing multicasts on a sending socket */ static void set_mcast_ttl(struct sock *sk, u_char ttl) { struct inet_sock *inet = inet_sk(sk); /* setsockopt(sock, SOL_IP, IP_MULTICAST_TTL, &ttl, sizeof(ttl)); */ lock_sock(sk); WRITE_ONCE(inet->mc_ttl, ttl); #ifdef CONFIG_IP_VS_IPV6 if (sk->sk_family == AF_INET6) { struct ipv6_pinfo *np = inet6_sk(sk); /* IPV6_MULTICAST_HOPS */ WRITE_ONCE(np->mcast_hops, ttl); } #endif release_sock(sk); } /* Control fragmentation of messages */ static void set_mcast_pmtudisc(struct sock *sk, int val) { struct inet_sock *inet = inet_sk(sk); /* setsockopt(sock, SOL_IP, IP_MTU_DISCOVER, &val, sizeof(val)); */ lock_sock(sk); WRITE_ONCE(inet->pmtudisc, val); #ifdef CONFIG_IP_VS_IPV6 if (sk->sk_family == AF_INET6) { struct ipv6_pinfo *np = inet6_sk(sk); /* IPV6_MTU_DISCOVER */ WRITE_ONCE(np->pmtudisc, val); } #endif release_sock(sk); } /* * Specifiy default interface for outgoing multicasts */ static int set_mcast_if(struct sock *sk, struct net_device *dev) { struct inet_sock *inet = inet_sk(sk); if (sk->sk_bound_dev_if && dev->ifindex != sk->sk_bound_dev_if) return -EINVAL; lock_sock(sk); inet->mc_index = dev->ifindex; /* inet->mc_addr = 0; */ #ifdef CONFIG_IP_VS_IPV6 if (sk->sk_family == AF_INET6) { struct ipv6_pinfo *np = inet6_sk(sk); /* IPV6_MULTICAST_IF */ WRITE_ONCE(np->mcast_oif, dev->ifindex); } #endif release_sock(sk); return 0; } /* * Join a multicast group. * the group is specified by a class D multicast address 224.0.0.0/8 * in the in_addr structure passed in as a parameter. */ static int join_mcast_group(struct sock *sk, struct in_addr *addr, struct net_device *dev) { struct ip_mreqn mreq; int ret; memset(&mreq, 0, sizeof(mreq)); memcpy(&mreq.imr_multiaddr, addr, sizeof(struct in_addr)); if (sk->sk_bound_dev_if && dev->ifindex != sk->sk_bound_dev_if) return -EINVAL; mreq.imr_ifindex = dev->ifindex; lock_sock(sk); ret = ip_mc_join_group(sk, &mreq); release_sock(sk); return ret; } #ifdef CONFIG_IP_VS_IPV6 static int join_mcast_group6(struct sock *sk, struct in6_addr *addr, struct net_device *dev) { int ret; if (sk->sk_bound_dev_if && dev->ifindex != sk->sk_bound_dev_if) return -EINVAL; lock_sock(sk); ret = ipv6_sock_mc_join(sk, dev->ifindex, addr); release_sock(sk); return ret; } #endif static int bind_mcastif_addr(struct socket *sock, struct net_device *dev) { __be32 addr; struct sockaddr_in sin; addr = inet_select_addr(dev, 0, RT_SCOPE_UNIVERSE); if (!addr) pr_err("You probably need to specify IP address on " "multicast interface.\n"); IP_VS_DBG(7, "binding socket with (%s) %pI4\n", dev->name, &addr); /* Now bind the socket with the address of multicast interface */ sin.sin_family = AF_INET; sin.sin_addr.s_addr = addr; sin.sin_port = 0; return kernel_bind(sock, (struct sockaddr *)&sin, sizeof(sin)); } static void get_mcast_sockaddr(union ipvs_sockaddr *sa, int *salen, struct ipvs_sync_daemon_cfg *c, int id) { if (AF_INET6 == c->mcast_af) { sa->in6 = (struct sockaddr_in6) { .sin6_family = AF_INET6, .sin6_port = htons(c->mcast_port + id), }; sa->in6.sin6_addr = c->mcast_group.in6; *salen = sizeof(sa->in6); } else { sa->in = (struct sockaddr_in) { .sin_family = AF_INET, .sin_port = htons(c->mcast_port + id), }; sa->in.sin_addr = c->mcast_group.in; *salen = sizeof(sa->in); } } /* * Set up sending multicast socket over UDP */ static int make_send_sock(struct netns_ipvs *ipvs, int id, struct net_device *dev, struct socket **sock_ret) { /* multicast addr */ union ipvs_sockaddr mcast_addr; struct socket *sock; int result, salen; /* First create a socket */ result = sock_create_kern(ipvs->net, ipvs->mcfg.mcast_af, SOCK_DGRAM, IPPROTO_UDP, &sock); if (result < 0) { pr_err("Error during creation of socket; terminating\n"); goto error; } *sock_ret = sock; result = set_mcast_if(sock->sk, dev); if (result < 0) { pr_err("Error setting outbound mcast interface\n"); goto error; } set_mcast_loop(sock->sk, 0); set_mcast_ttl(sock->sk, ipvs->mcfg.mcast_ttl); /* Allow fragmentation if MTU changes */ set_mcast_pmtudisc(sock->sk, IP_PMTUDISC_DONT); result = sysctl_sync_sock_size(ipvs); if (result > 0) set_sock_size(sock->sk, 1, result); if (AF_INET == ipvs->mcfg.mcast_af) result = bind_mcastif_addr(sock, dev); else result = 0; if (result < 0) { pr_err("Error binding address of the mcast interface\n"); goto error; } get_mcast_sockaddr(&mcast_addr, &salen, &ipvs->mcfg, id); result = kernel_connect(sock, (struct sockaddr *)&mcast_addr, salen, 0); if (result < 0) { pr_err("Error connecting to the multicast addr\n"); goto error; } return 0; error: return result; } /* * Set up receiving multicast socket over UDP */ static int make_receive_sock(struct netns_ipvs *ipvs, int id, struct net_device *dev, struct socket **sock_ret) { /* multicast addr */ union ipvs_sockaddr mcast_addr; struct socket *sock; int result, salen; /* First create a socket */ result = sock_create_kern(ipvs->net, ipvs->bcfg.mcast_af, SOCK_DGRAM, IPPROTO_UDP, &sock); if (result < 0) { pr_err("Error during creation of socket; terminating\n"); goto error; } *sock_ret = sock; /* it is equivalent to the REUSEADDR option in user-space */ sock->sk->sk_reuse = SK_CAN_REUSE; result = sysctl_sync_sock_size(ipvs); if (result > 0) set_sock_size(sock->sk, 0, result); get_mcast_sockaddr(&mcast_addr, &salen, &ipvs->bcfg, id); sock->sk->sk_bound_dev_if = dev->ifindex; result = kernel_bind(sock, (struct sockaddr *)&mcast_addr, salen); if (result < 0) { pr_err("Error binding to the multicast addr\n"); goto error; } /* join the multicast group */ #ifdef CONFIG_IP_VS_IPV6 if (ipvs->bcfg.mcast_af == AF_INET6) result = join_mcast_group6(sock->sk, &mcast_addr.in6.sin6_addr, dev); else #endif result = join_mcast_group(sock->sk, &mcast_addr.in.sin_addr, dev); if (result < 0) { pr_err("Error joining to the multicast group\n"); goto error; } return 0; error: return result; } static int ip_vs_send_async(struct socket *sock, const char *buffer, const size_t length) { struct msghdr msg = {.msg_flags = MSG_DONTWAIT|MSG_NOSIGNAL}; struct kvec iov; int len; iov.iov_base = (void *)buffer; iov.iov_len = length; len = kernel_sendmsg(sock, &msg, &iov, 1, (size_t)(length)); return len; } static int ip_vs_send_sync_msg(struct socket *sock, struct ip_vs_sync_mesg *msg) { int msize; int ret; msize = ntohs(msg->size); ret = ip_vs_send_async(sock, (char *)msg, msize); if (ret >= 0 || ret == -EAGAIN) return ret; pr_err("ip_vs_send_async error %d\n", ret); return 0; } static int ip_vs_receive(struct socket *sock, char *buffer, const size_t buflen) { struct msghdr msg = {NULL,}; struct kvec iov = {buffer, buflen}; int len; /* Receive a packet */ iov_iter_kvec(&msg.msg_iter, ITER_DEST, &iov, 1, buflen); len = sock_recvmsg(sock, &msg, MSG_DONTWAIT); if (len < 0) return len; return len; } /* Wakeup the master thread for sending */ static void master_wakeup_work_handler(struct work_struct *work) { struct ipvs_master_sync_state *ms = container_of(work, struct ipvs_master_sync_state, master_wakeup_work.work); struct netns_ipvs *ipvs = ms->ipvs; spin_lock_bh(&ipvs->sync_lock); if (ms->sync_queue_len && ms->sync_queue_delay < IPVS_SYNC_WAKEUP_RATE) { int id = (int)(ms - ipvs->ms); ms->sync_queue_delay = IPVS_SYNC_WAKEUP_RATE; wake_up_process(ipvs->master_tinfo[id].task); } spin_unlock_bh(&ipvs->sync_lock); } /* Get next buffer to send */ static inline struct ip_vs_sync_buff * next_sync_buff(struct netns_ipvs *ipvs, struct ipvs_master_sync_state *ms) { struct ip_vs_sync_buff *sb; sb = sb_dequeue(ipvs, ms); if (sb) return sb; /* Do not delay entries in buffer for more than 2 seconds */ return get_curr_sync_buff(ipvs, ms, IPVS_SYNC_FLUSH_TIME); } static int sync_thread_master(void *data) { struct ip_vs_sync_thread_data *tinfo = data; struct netns_ipvs *ipvs = tinfo->ipvs; struct ipvs_master_sync_state *ms = &ipvs->ms[tinfo->id]; struct sock *sk = tinfo->sock->sk; struct ip_vs_sync_buff *sb; pr_info("sync thread started: state = MASTER, mcast_ifn = %s, " "syncid = %d, id = %d\n", ipvs->mcfg.mcast_ifn, ipvs->mcfg.syncid, tinfo->id); for (;;) { sb = next_sync_buff(ipvs, ms); if (unlikely(kthread_should_stop())) break; if (!sb) { schedule_timeout(IPVS_SYNC_CHECK_PERIOD); continue; } while (ip_vs_send_sync_msg(tinfo->sock, sb->mesg) < 0) { /* (Ab)use interruptible sleep to avoid increasing * the load avg. */ __wait_event_interruptible(*sk_sleep(sk), sock_writeable(sk) || kthread_should_stop()); if (unlikely(kthread_should_stop())) goto done; } ip_vs_sync_buff_release(sb); } done: __set_current_state(TASK_RUNNING); if (sb) ip_vs_sync_buff_release(sb); /* clean up the sync_buff queue */ while ((sb = sb_dequeue(ipvs, ms))) ip_vs_sync_buff_release(sb); __set_current_state(TASK_RUNNING); /* clean up the current sync_buff */ sb = get_curr_sync_buff(ipvs, ms, 0); if (sb) ip_vs_sync_buff_release(sb); return 0; } static int sync_thread_backup(void *data) { struct ip_vs_sync_thread_data *tinfo = data; struct netns_ipvs *ipvs = tinfo->ipvs; struct sock *sk = tinfo->sock->sk; struct udp_sock *up = udp_sk(sk); int len; pr_info("sync thread started: state = BACKUP, mcast_ifn = %s, " "syncid = %d, id = %d\n", ipvs->bcfg.mcast_ifn, ipvs->bcfg.syncid, tinfo->id); while (!kthread_should_stop()) { wait_event_interruptible(*sk_sleep(sk), !skb_queue_empty_lockless(&sk->sk_receive_queue) || !skb_queue_empty_lockless(&up->reader_queue) || kthread_should_stop()); /* do we have data now? */ while (!skb_queue_empty_lockless(&sk->sk_receive_queue) || !skb_queue_empty_lockless(&up->reader_queue)) { len = ip_vs_receive(tinfo->sock, tinfo->buf, ipvs->bcfg.sync_maxlen); if (len <= 0) { if (len != -EAGAIN) pr_err("receiving message error\n"); break; } ip_vs_process_message(ipvs, tinfo->buf, len); } } return 0; } int start_sync_thread(struct netns_ipvs *ipvs, struct ipvs_sync_daemon_cfg *c, int state) { struct ip_vs_sync_thread_data *ti = NULL, *tinfo; struct task_struct *task; struct net_device *dev; char *name; int (*threadfn)(void *data); int id = 0, count, hlen; int result = -ENOMEM; u16 mtu, min_mtu; IP_VS_DBG(7, "%s(): pid %d\n", __func__, task_pid_nr(current)); IP_VS_DBG(7, "Each ip_vs_sync_conn entry needs %zd bytes\n", sizeof(struct ip_vs_sync_conn_v0)); /* increase the module use count */ if (!ip_vs_use_count_inc()) return -ENOPROTOOPT; /* Do not hold one mutex and then to block on another */ for (;;) { rtnl_lock(); if (mutex_trylock(&ipvs->sync_mutex)) break; rtnl_unlock(); mutex_lock(&ipvs->sync_mutex); if (rtnl_trylock()) break; mutex_unlock(&ipvs->sync_mutex); } if (!ipvs->sync_state) { count = clamp(sysctl_sync_ports(ipvs), 1, IPVS_SYNC_PORTS_MAX); ipvs->threads_mask = count - 1; } else count = ipvs->threads_mask + 1; if (c->mcast_af == AF_UNSPEC) { c->mcast_af = AF_INET; c->mcast_group.ip = cpu_to_be32(IP_VS_SYNC_GROUP); } if (!c->mcast_port) c->mcast_port = IP_VS_SYNC_PORT; if (!c->mcast_ttl) c->mcast_ttl = 1; dev = __dev_get_by_name(ipvs->net, c->mcast_ifn); if (!dev) { pr_err("Unknown mcast interface: %s\n", c->mcast_ifn); result = -ENODEV; goto out_early; } hlen = (AF_INET6 == c->mcast_af) ? sizeof(struct ipv6hdr) + sizeof(struct udphdr) : sizeof(struct iphdr) + sizeof(struct udphdr); mtu = (state == IP_VS_STATE_BACKUP) ? clamp(dev->mtu, 1500U, 65535U) : 1500U; min_mtu = (state == IP_VS_STATE_BACKUP) ? 1024 : 1; if (c->sync_maxlen) c->sync_maxlen = clamp_t(unsigned int, c->sync_maxlen, min_mtu, 65535 - hlen); else c->sync_maxlen = mtu - hlen; if (state == IP_VS_STATE_MASTER) { result = -EEXIST; if (ipvs->ms) goto out_early; ipvs->mcfg = *c; name = "ipvs-m:%d:%d"; threadfn = sync_thread_master; } else if (state == IP_VS_STATE_BACKUP) { result = -EEXIST; if (ipvs->backup_tinfo) goto out_early; ipvs->bcfg = *c; name = "ipvs-b:%d:%d"; threadfn = sync_thread_backup; } else { result = -EINVAL; goto out_early; } if (state == IP_VS_STATE_MASTER) { struct ipvs_master_sync_state *ms; result = -ENOMEM; ipvs->ms = kcalloc(count, sizeof(ipvs->ms[0]), GFP_KERNEL); if (!ipvs->ms) goto out; ms = ipvs->ms; for (id = 0; id < count; id++, ms++) { INIT_LIST_HEAD(&ms->sync_queue); ms->sync_queue_len = 0; ms->sync_queue_delay = 0; INIT_DELAYED_WORK(&ms->master_wakeup_work, master_wakeup_work_handler); ms->ipvs = ipvs; } } result = -ENOMEM; ti = kcalloc(count, sizeof(struct ip_vs_sync_thread_data), GFP_KERNEL); if (!ti) goto out; for (id = 0; id < count; id++) { tinfo = &ti[id]; tinfo->ipvs = ipvs; if (state == IP_VS_STATE_BACKUP) { result = -ENOMEM; tinfo->buf = kmalloc(ipvs->bcfg.sync_maxlen, GFP_KERNEL); if (!tinfo->buf) goto out; } tinfo->id = id; if (state == IP_VS_STATE_MASTER) result = make_send_sock(ipvs, id, dev, &tinfo->sock); else result = make_receive_sock(ipvs, id, dev, &tinfo->sock); if (result < 0) goto out; task = kthread_run(threadfn, tinfo, name, ipvs->gen, id); if (IS_ERR(task)) { result = PTR_ERR(task); goto out; } tinfo->task = task; } /* mark as active */ if (state == IP_VS_STATE_MASTER) ipvs->master_tinfo = ti; else ipvs->backup_tinfo = ti; spin_lock_bh(&ipvs->sync_buff_lock); ipvs->sync_state |= state; spin_unlock_bh(&ipvs->sync_buff_lock); mutex_unlock(&ipvs->sync_mutex); rtnl_unlock(); return 0; out: /* We do not need RTNL lock anymore, release it here so that * sock_release below can use rtnl_lock to leave the mcast group. */ rtnl_unlock(); id = min(id, count - 1); if (ti) { for (tinfo = ti + id; tinfo >= ti; tinfo--) { if (tinfo->task) kthread_stop(tinfo->task); } } if (!(ipvs->sync_state & IP_VS_STATE_MASTER)) { kfree(ipvs->ms); ipvs->ms = NULL; } mutex_unlock(&ipvs->sync_mutex); /* No more mutexes, release socks */ if (ti) { for (tinfo = ti + id; tinfo >= ti; tinfo--) { if (tinfo->sock) sock_release(tinfo->sock); kfree(tinfo->buf); } kfree(ti); } /* decrease the module use count */ ip_vs_use_count_dec(); return result; out_early: mutex_unlock(&ipvs->sync_mutex); rtnl_unlock(); /* decrease the module use count */ ip_vs_use_count_dec(); return result; } int stop_sync_thread(struct netns_ipvs *ipvs, int state) { struct ip_vs_sync_thread_data *ti, *tinfo; int id; int retc = -EINVAL; IP_VS_DBG(7, "%s(): pid %d\n", __func__, task_pid_nr(current)); mutex_lock(&ipvs->sync_mutex); if (state == IP_VS_STATE_MASTER) { retc = -ESRCH; if (!ipvs->ms) goto err; ti = ipvs->master_tinfo; /* * The lock synchronizes with sb_queue_tail(), so that we don't * add sync buffers to the queue, when we are already in * progress of stopping the master sync daemon. */ spin_lock_bh(&ipvs->sync_buff_lock); spin_lock(&ipvs->sync_lock); ipvs->sync_state &= ~IP_VS_STATE_MASTER; spin_unlock(&ipvs->sync_lock); spin_unlock_bh(&ipvs->sync_buff_lock); retc = 0; for (id = ipvs->threads_mask; id >= 0; id--) { struct ipvs_master_sync_state *ms = &ipvs->ms[id]; int ret; tinfo = &ti[id]; pr_info("stopping master sync thread %d ...\n", task_pid_nr(tinfo->task)); cancel_delayed_work_sync(&ms->master_wakeup_work); ret = kthread_stop(tinfo->task); if (retc >= 0) retc = ret; } kfree(ipvs->ms); ipvs->ms = NULL; ipvs->master_tinfo = NULL; } else if (state == IP_VS_STATE_BACKUP) { retc = -ESRCH; if (!ipvs->backup_tinfo) goto err; ti = ipvs->backup_tinfo; ipvs->sync_state &= ~IP_VS_STATE_BACKUP; retc = 0; for (id = ipvs->threads_mask; id >= 0; id--) { int ret; tinfo = &ti[id]; pr_info("stopping backup sync thread %d ...\n", task_pid_nr(tinfo->task)); ret = kthread_stop(tinfo->task); if (retc >= 0) retc = ret; } ipvs->backup_tinfo = NULL; } else { goto err; } id = ipvs->threads_mask; mutex_unlock(&ipvs->sync_mutex); /* No more mutexes, release socks */ for (tinfo = ti + id; tinfo >= ti; tinfo--) { if (tinfo->sock) sock_release(tinfo->sock); kfree(tinfo->buf); } kfree(ti); /* decrease the module use count */ ip_vs_use_count_dec(); return retc; err: mutex_unlock(&ipvs->sync_mutex); return retc; } /* * Initialize data struct for each netns */ int __net_init ip_vs_sync_net_init(struct netns_ipvs *ipvs) { __mutex_init(&ipvs->sync_mutex, "ipvs->sync_mutex", &__ipvs_sync_key); spin_lock_init(&ipvs->sync_lock); spin_lock_init(&ipvs->sync_buff_lock); return 0; } void ip_vs_sync_net_cleanup(struct netns_ipvs *ipvs) { int retc; retc = stop_sync_thread(ipvs, IP_VS_STATE_MASTER); if (retc && retc != -ESRCH) pr_err("Failed to stop Master Daemon\n"); retc = stop_sync_thread(ipvs, IP_VS_STATE_BACKUP); if (retc && retc != -ESRCH) pr_err("Failed to stop Backup Daemon\n"); } |
| 1063 260 1066 | 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 | // 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 flow_offload_ct_tcp(struct nf_conn *ct) { /* conntrack will not see all packets, disable tcp window validation. */ spin_lock_bh(&ct->lock); ct->proto.tcp.seen[0].flags |= IP_CT_TCP_FLAG_BE_LIBERAL; ct->proto.tcp.seen[1].flags |= IP_CT_TCP_FLAG_BE_LIBERAL; spin_unlock_bh(&ct->lock); } 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) flow_offload_ct_tcp(ct); __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"); |
| 6 3 6 6 6 | 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 | /* * net/tipc/monitor.c * * Copyright (c) 2016, Ericsson AB * 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 names of the copyright holders nor the names of its * contributors may be used to endorse or promote products derived from * this software without specific prior written permission. * * Alternatively, this software may be distributed under the terms of the * GNU General Public License ("GPL") version 2 as published by the Free * Software Foundation. * * 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 <net/genetlink.h> #include "core.h" #include "addr.h" #include "monitor.h" #include "bearer.h" #define MAX_MON_DOMAIN 64 #define MON_TIMEOUT 120000 #define MAX_PEER_DOWN_EVENTS 4 /* struct tipc_mon_domain: domain record to be transferred between peers * @len: actual size of domain record * @gen: current generation of sender's domain * @ack_gen: most recent generation of self's domain acked by peer * @member_cnt: number of domain member nodes described in this record * @up_map: bit map indicating which of the members the sender considers up * @members: identity of the domain members */ struct tipc_mon_domain { u16 len; u16 gen; u16 ack_gen; u16 member_cnt; u64 up_map; u32 members[MAX_MON_DOMAIN]; }; /* struct tipc_peer: state of a peer node and its domain * @addr: tipc node identity of peer * @head_map: shows which other nodes currently consider peer 'up' * @domain: most recent domain record from peer * @hash: position in hashed lookup list * @list: position in linked list, in circular ascending order by 'addr' * @applied: number of reported domain members applied on this monitor list * @is_up: peer is up as seen from this node * @is_head: peer is assigned domain head as seen from this node * @is_local: peer is in local domain and should be continuously monitored * @down_cnt: - numbers of other peers which have reported this on lost */ struct tipc_peer { u32 addr; struct tipc_mon_domain *domain; struct hlist_node hash; struct list_head list; u8 applied; u8 down_cnt; bool is_up; bool is_head; bool is_local; }; struct tipc_monitor { struct hlist_head peers[NODE_HTABLE_SIZE]; int peer_cnt; struct tipc_peer *self; rwlock_t lock; struct tipc_mon_domain cache; u16 list_gen; u16 dom_gen; struct net *net; struct timer_list timer; unsigned long timer_intv; }; static struct tipc_monitor *tipc_monitor(struct net *net, int bearer_id) { return tipc_net(net)->monitors[bearer_id]; } const int tipc_max_domain_size = sizeof(struct tipc_mon_domain); static inline u16 mon_cpu_to_le16(u16 val) { return (__force __u16)htons(val); } static inline u32 mon_cpu_to_le32(u32 val) { return (__force __u32)htonl(val); } static inline u64 mon_cpu_to_le64(u64 val) { return (__force __u64)cpu_to_be64(val); } static inline u16 mon_le16_to_cpu(u16 val) { return ntohs((__force __be16)val); } static inline u32 mon_le32_to_cpu(u32 val) { return ntohl((__force __be32)val); } static inline u64 mon_le64_to_cpu(u64 val) { return be64_to_cpu((__force __be64)val); } /* dom_rec_len(): actual length of domain record for transport */ static int dom_rec_len(struct tipc_mon_domain *dom, u16 mcnt) { return (offsetof(struct tipc_mon_domain, members)) + (mcnt * sizeof(u32)); } /* dom_size() : calculate size of own domain based on number of peers */ static int dom_size(int peers) { int i = 0; while ((i * i) < peers) i++; return min(i, MAX_MON_DOMAIN); } static void map_set(u64 *up_map, int i, unsigned int v) { *up_map &= ~(1ULL << i); *up_map |= ((u64)v << i); } static int map_get(u64 up_map, int i) { return (up_map & (1ULL << i)) >> i; } static struct tipc_peer *peer_prev(struct tipc_peer *peer) { return list_last_entry(&peer->list, struct tipc_peer, list); } static struct tipc_peer *peer_nxt(struct tipc_peer *peer) { return list_first_entry(&peer->list, struct tipc_peer, list); } static struct tipc_peer *peer_head(struct tipc_peer *peer) { while (!peer->is_head) peer = peer_prev(peer); return peer; } static struct tipc_peer *get_peer(struct tipc_monitor *mon, u32 addr) { struct tipc_peer *peer; unsigned int thash = tipc_hashfn(addr); hlist_for_each_entry(peer, &mon->peers[thash], hash) { if (peer->addr == addr) return peer; } return NULL; } static struct tipc_peer *get_self(struct net *net, int bearer_id) { struct tipc_monitor *mon = tipc_monitor(net, bearer_id); return mon->self; } static inline bool tipc_mon_is_active(struct net *net, struct tipc_monitor *mon) { struct tipc_net *tn = tipc_net(net); return mon->peer_cnt > tn->mon_threshold; } /* mon_identify_lost_members() : - identify amd mark potentially lost members */ static void mon_identify_lost_members(struct tipc_peer *peer, struct tipc_mon_domain *dom_bef, int applied_bef) { struct tipc_peer *member = peer; struct tipc_mon_domain *dom_aft = peer->domain; int applied_aft = peer->applied; int i; for (i = 0; i < applied_bef; i++) { member = peer_nxt(member); /* Do nothing if self or peer already see member as down */ if (!member->is_up || !map_get(dom_bef->up_map, i)) continue; /* Loss of local node must be detected by active probing */ if (member->is_local) continue; /* Start probing if member was removed from applied domain */ if (!applied_aft || (applied_aft < i)) { member->down_cnt = 1; continue; } /* Member loss is confirmed if it is still in applied domain */ if (!map_get(dom_aft->up_map, i)) member->down_cnt++; } } /* mon_apply_domain() : match a peer's domain record against monitor list */ static void mon_apply_domain(struct tipc_monitor *mon, struct tipc_peer *peer) { struct tipc_mon_domain *dom = peer->domain; struct tipc_peer *member; u32 addr; int i; if (!dom || !peer->is_up) return; /* Scan across domain members and match against monitor list */ peer->applied = 0; member = peer_nxt(peer); for (i = 0; i < dom->member_cnt; i++) { addr = dom->members[i]; if (addr != member->addr) return; peer->applied++; member = peer_nxt(member); } } /* mon_update_local_domain() : update after peer addition/removal/up/down */ static void mon_update_local_domain(struct tipc_monitor *mon) { struct tipc_peer *self = mon->self; struct tipc_mon_domain *cache = &mon->cache; struct tipc_mon_domain *dom = self->domain; struct tipc_peer *peer = self; u64 prev_up_map = dom->up_map; u16 member_cnt, i; bool diff; /* Update local domain size based on current size of cluster */ member_cnt = dom_size(mon->peer_cnt) - 1; self->applied = member_cnt; /* Update native and cached outgoing local domain records */ dom->len = dom_rec_len(dom, member_cnt); diff = dom->member_cnt != member_cnt; dom->member_cnt = member_cnt; for (i = 0; i < member_cnt; i++) { peer = peer_nxt(peer); diff |= dom->members[i] != peer->addr; dom->members[i] = peer->addr; map_set(&dom->up_map, i, peer->is_up); cache->members[i] = mon_cpu_to_le32(peer->addr); } diff |= dom->up_map != prev_up_map; if (!diff) return; dom->gen = ++mon->dom_gen; cache->len = mon_cpu_to_le16(dom->len); cache->gen = mon_cpu_to_le16(dom->gen); cache->member_cnt = mon_cpu_to_le16(member_cnt); cache->up_map = mon_cpu_to_le64(dom->up_map); mon_apply_domain(mon, self); } /* mon_update_neighbors() : update preceding neighbors of added/removed peer */ static void mon_update_neighbors(struct tipc_monitor *mon, struct tipc_peer *peer) { int dz, i; dz = dom_size(mon->peer_cnt); for (i = 0; i < dz; i++) { mon_apply_domain(mon, peer); peer = peer_prev(peer); } } /* mon_assign_roles() : reassign peer roles after a network change * The monitor list is consistent at this stage; i.e., each peer is monitoring * a set of domain members as matched between domain record and the monitor list */ static void mon_assign_roles(struct tipc_monitor *mon, struct tipc_peer *head) { struct tipc_peer *peer = peer_nxt(head); struct tipc_peer *self = mon->self; int i = 0; for (; peer != self; peer = peer_nxt(peer)) { peer->is_local = false; /* Update domain member */ if (i++ < head->applied) { peer->is_head = false; if (head == self) peer->is_local = true; continue; } /* Assign next domain head */ if (!peer->is_up) continue; if (peer->is_head) break; head = peer; head->is_head = true; i = 0; } mon->list_gen++; } void tipc_mon_remove_peer(struct net *net, u32 addr, int bearer_id) { struct tipc_monitor *mon = tipc_monitor(net, bearer_id); struct tipc_peer *self; struct tipc_peer *peer, *prev, *head; if (!mon) return; self = get_self(net, bearer_id); write_lock_bh(&mon->lock); peer = get_peer(mon, addr); if (!peer) goto exit; prev = peer_prev(peer); list_del(&peer->list); hlist_del(&peer->hash); kfree(peer->domain); kfree(peer); mon->peer_cnt--; head = peer_head(prev); if (head == self) mon_update_local_domain(mon); mon_update_neighbors(mon, prev); /* Revert to full-mesh monitoring if we reach threshold */ if (!tipc_mon_is_active(net, mon)) { list_for_each_entry(peer, &self->list, list) { kfree(peer->domain); peer->domain = NULL; peer->applied = 0; } } mon_assign_roles(mon, head); exit: write_unlock_bh(&mon->lock); } static bool tipc_mon_add_peer(struct tipc_monitor *mon, u32 addr, struct tipc_peer **peer) { struct tipc_peer *self = mon->self; struct tipc_peer *cur, *prev, *p; p = kzalloc(sizeof(*p), GFP_ATOMIC); *peer = p; if (!p) return false; p->addr = addr; /* Add new peer to lookup list */ INIT_LIST_HEAD(&p->list); hlist_add_head(&p->hash, &mon->peers[tipc_hashfn(addr)]); /* Sort new peer into iterator list, in ascending circular order */ prev = self; list_for_each_entry(cur, &self->list, list) { if ((addr > prev->addr) && (addr < cur->addr)) break; if (((addr < cur->addr) || (addr > prev->addr)) && (prev->addr > cur->addr)) break; prev = cur; } list_add_tail(&p->list, &cur->list); mon->peer_cnt++; mon_update_neighbors(mon, p); return true; } void tipc_mon_peer_up(struct net *net, u32 addr, int bearer_id) { struct tipc_monitor *mon = tipc_monitor(net, bearer_id); struct tipc_peer *self = get_self(net, bearer_id); struct tipc_peer *peer, *head; write_lock_bh(&mon->lock); peer = get_peer(mon, addr); if (!peer && !tipc_mon_add_peer(mon, addr, &peer)) goto exit; peer->is_up = true; head = peer_head(peer); if (head == self) mon_update_local_domain(mon); mon_assign_roles(mon, head); exit: write_unlock_bh(&mon->lock); } void tipc_mon_peer_down(struct net *net, u32 addr, int bearer_id) { struct tipc_monitor *mon = tipc_monitor(net, bearer_id); struct tipc_peer *self; struct tipc_peer *peer, *head; struct tipc_mon_domain *dom; int applied; if (!mon) return; self = get_self(net, bearer_id); write_lock_bh(&mon->lock); peer = get_peer(mon, addr); if (!peer) { pr_warn("Mon: unknown link %x/%u DOWN\n", addr, bearer_id); goto exit; } applied = peer->applied; peer->applied = 0; dom = peer->domain; peer->domain = NULL; if (peer->is_head) mon_identify_lost_members(peer, dom, applied); kfree(dom); peer->is_up = false; peer->is_head = false; peer->is_local = false; peer->down_cnt = 0; head = peer_head(peer); if (head == self) mon_update_local_domain(mon); mon_assign_roles(mon, head); exit: write_unlock_bh(&mon->lock); } /* tipc_mon_rcv - process monitor domain event message */ void tipc_mon_rcv(struct net *net, void *data, u16 dlen, u32 addr, struct tipc_mon_state *state, int bearer_id) { struct tipc_monitor *mon = tipc_monitor(net, bearer_id); struct tipc_mon_domain *arrv_dom = data; struct tipc_mon_domain dom_bef; struct tipc_mon_domain *dom; struct tipc_peer *peer; u16 new_member_cnt = mon_le16_to_cpu(arrv_dom->member_cnt); int new_dlen = dom_rec_len(arrv_dom, new_member_cnt); u16 new_gen = mon_le16_to_cpu(arrv_dom->gen); u16 acked_gen = mon_le16_to_cpu(arrv_dom->ack_gen); u16 arrv_dlen = mon_le16_to_cpu(arrv_dom->len); bool probing = state->probing; int i, applied_bef; state->probing = false; /* Sanity check received domain record */ if (new_member_cnt > MAX_MON_DOMAIN) return; if (dlen < dom_rec_len(arrv_dom, 0)) return; if (dlen != dom_rec_len(arrv_dom, new_member_cnt)) return; if (dlen < new_dlen || arrv_dlen != new_dlen) return; /* Synch generation numbers with peer if link just came up */ if (!state->synched) { state->peer_gen = new_gen - 1; state->acked_gen = acked_gen; state->synched = true; } if (more(acked_gen, state->acked_gen)) state->acked_gen = acked_gen; /* Drop duplicate unless we are waiting for a probe response */ if (!more(new_gen, state->peer_gen) && !probing) return; write_lock_bh(&mon->lock); peer = get_peer(mon, addr); if (!peer || !peer->is_up) goto exit; /* Peer is confirmed, stop any ongoing probing */ peer->down_cnt = 0; /* Task is done for duplicate record */ if (!more(new_gen, state->peer_gen)) goto exit; state->peer_gen = new_gen; /* Cache current domain record for later use */ dom_bef.member_cnt = 0; dom = peer->domain; if (dom) memcpy(&dom_bef, dom, dom->len); /* Transform and store received domain record */ if (!dom || (dom->len < new_dlen)) { kfree(dom); dom = kmalloc(new_dlen, GFP_ATOMIC); peer->domain = dom; if (!dom) goto exit; } dom->len = new_dlen; dom->gen = new_gen; dom->member_cnt = new_member_cnt; dom->up_map = mon_le64_to_cpu(arrv_dom->up_map); for (i = 0; i < new_member_cnt; i++) dom->members[i] = mon_le32_to_cpu(arrv_dom->members[i]); /* Update peers affected by this domain record */ applied_bef = peer->applied; mon_apply_domain(mon, peer); mon_identify_lost_members(peer, &dom_bef, applied_bef); mon_assign_roles(mon, peer_head(peer)); exit: write_unlock_bh(&mon->lock); } void tipc_mon_prep(struct net *net, void *data, int *dlen, struct tipc_mon_state *state, int bearer_id) { struct tipc_monitor *mon = tipc_monitor(net, bearer_id); struct tipc_mon_domain *dom = data; u16 gen = mon->dom_gen; u16 len; /* Send invalid record if not active */ if (!tipc_mon_is_active(net, mon)) { dom->len = 0; return; } /* Send only a dummy record with ack if peer has acked our last sent */ if (likely(state->acked_gen == gen)) { len = dom_rec_len(dom, 0); *dlen = len; dom->len = mon_cpu_to_le16(len); dom->gen = mon_cpu_to_le16(gen); dom->ack_gen = mon_cpu_to_le16(state->peer_gen); dom->member_cnt = 0; return; } /* Send the full record */ read_lock_bh(&mon->lock); len = mon_le16_to_cpu(mon->cache.len); *dlen = len; memcpy(data, &mon->cache, len); read_unlock_bh(&mon->lock); dom->ack_gen = mon_cpu_to_le16(state->peer_gen); } void tipc_mon_get_state(struct net *net, u32 addr, struct tipc_mon_state *state, int bearer_id) { struct tipc_monitor *mon = tipc_monitor(net, bearer_id); struct tipc_peer *peer; if (!tipc_mon_is_active(net, mon)) { state->probing = false; state->monitoring = true; return; } /* Used cached state if table has not changed */ if (!state->probing && (state->list_gen == mon->list_gen) && (state->acked_gen == mon->dom_gen)) return; read_lock_bh(&mon->lock); peer = get_peer(mon, addr); if (peer) { state->probing = state->acked_gen != mon->dom_gen; state->probing |= peer->down_cnt; state->reset |= peer->down_cnt >= MAX_PEER_DOWN_EVENTS; state->monitoring = peer->is_local; state->monitoring |= peer->is_head; state->list_gen = mon->list_gen; } read_unlock_bh(&mon->lock); } static void mon_timeout(struct timer_list *t) { struct tipc_monitor *mon = from_timer(mon, t, timer); struct tipc_peer *self; int best_member_cnt = dom_size(mon->peer_cnt) - 1; write_lock_bh(&mon->lock); self = mon->self; if (self && (best_member_cnt != self->applied)) { mon_update_local_domain(mon); mon_assign_roles(mon, self); } write_unlock_bh(&mon->lock); mod_timer(&mon->timer, jiffies + mon->timer_intv); } int tipc_mon_create(struct net *net, int bearer_id) { struct tipc_net *tn = tipc_net(net); struct tipc_monitor *mon; struct tipc_peer *self; struct tipc_mon_domain *dom; if (tn->monitors[bearer_id]) return 0; mon = kzalloc(sizeof(*mon), GFP_ATOMIC); self = kzalloc(sizeof(*self), GFP_ATOMIC); dom = kzalloc(sizeof(*dom), GFP_ATOMIC); if (!mon || !self || !dom) { kfree(mon); kfree(self); kfree(dom); return -ENOMEM; } tn->monitors[bearer_id] = mon; rwlock_init(&mon->lock); mon->net = net; mon->peer_cnt = 1; mon->self = self; self->domain = dom; self->addr = tipc_own_addr(net); self->is_up = true; self->is_head = true; INIT_LIST_HEAD(&self->list); timer_setup(&mon->timer, mon_timeout, 0); mon->timer_intv = msecs_to_jiffies(MON_TIMEOUT + (tn->random & 0xffff)); mod_timer(&mon->timer, jiffies + mon->timer_intv); return 0; } void tipc_mon_delete(struct net *net, int bearer_id) { struct tipc_net *tn = tipc_net(net); struct tipc_monitor *mon = tipc_monitor(net, bearer_id); struct tipc_peer *self; struct tipc_peer *peer, *tmp; if (!mon) return; self = get_self(net, bearer_id); write_lock_bh(&mon->lock); tn->monitors[bearer_id] = NULL; list_for_each_entry_safe(peer, tmp, &self->list, list) { list_del(&peer->list); hlist_del(&peer->hash); kfree(peer->domain); kfree(peer); } mon->self = NULL; write_unlock_bh(&mon->lock); timer_shutdown_sync(&mon->timer); kfree(self->domain); kfree(self); kfree(mon); } void tipc_mon_reinit_self(struct net *net) { struct tipc_monitor *mon; int bearer_id; for (bearer_id = 0; bearer_id < MAX_BEARERS; bearer_id++) { mon = tipc_monitor(net, bearer_id); if (!mon) continue; write_lock_bh(&mon->lock); mon->self->addr = tipc_own_addr(net); write_unlock_bh(&mon->lock); } } int tipc_nl_monitor_set_threshold(struct net *net, u32 cluster_size) { struct tipc_net *tn = tipc_net(net); if (cluster_size > TIPC_CLUSTER_SIZE) return -EINVAL; tn->mon_threshold = cluster_size; return 0; } int tipc_nl_monitor_get_threshold(struct net *net) { struct tipc_net *tn = tipc_net(net); return tn->mon_threshold; } static int __tipc_nl_add_monitor_peer(struct tipc_peer *peer, struct tipc_nl_msg *msg) { struct tipc_mon_domain *dom = peer->domain; struct nlattr *attrs; void *hdr; hdr = genlmsg_put(msg->skb, msg->portid, msg->seq, &tipc_genl_family, NLM_F_MULTI, TIPC_NL_MON_PEER_GET); if (!hdr) return -EMSGSIZE; attrs = nla_nest_start_noflag(msg->skb, TIPC_NLA_MON_PEER); if (!attrs) goto msg_full; if (nla_put_u32(msg->skb, TIPC_NLA_MON_PEER_ADDR, peer->addr)) goto attr_msg_full; if (nla_put_u32(msg->skb, TIPC_NLA_MON_PEER_APPLIED, peer->applied)) goto attr_msg_full; if (peer->is_up) if (nla_put_flag(msg->skb, TIPC_NLA_MON_PEER_UP)) goto attr_msg_full; if (peer->is_local) if (nla_put_flag(msg->skb, TIPC_NLA_MON_PEER_LOCAL)) goto attr_msg_full; if (peer->is_head) if (nla_put_flag(msg->skb, TIPC_NLA_MON_PEER_HEAD)) goto attr_msg_full; if (dom) { if (nla_put_u32(msg->skb, TIPC_NLA_MON_PEER_DOMGEN, dom->gen)) goto attr_msg_full; if (nla_put_u64_64bit(msg->skb, TIPC_NLA_MON_PEER_UPMAP, dom->up_map, TIPC_NLA_MON_PEER_PAD)) goto attr_msg_full; if (nla_put(msg->skb, TIPC_NLA_MON_PEER_MEMBERS, dom->member_cnt * sizeof(u32), &dom->members)) goto attr_msg_full; } nla_nest_end(msg->skb, attrs); genlmsg_end(msg->skb, hdr); return 0; attr_msg_full: nla_nest_cancel(msg->skb, attrs); msg_full: genlmsg_cancel(msg->skb, hdr); return -EMSGSIZE; } int tipc_nl_add_monitor_peer(struct net *net, struct tipc_nl_msg *msg, u32 bearer_id, u32 *prev_node) { struct tipc_monitor *mon = tipc_monitor(net, bearer_id); struct tipc_peer *peer; if (!mon) return -EINVAL; read_lock_bh(&mon->lock); peer = mon->self; do { if (*prev_node) { if (peer->addr == *prev_node) *prev_node = 0; else continue; } if (__tipc_nl_add_monitor_peer(peer, msg)) { *prev_node = peer->addr; read_unlock_bh(&mon->lock); return -EMSGSIZE; } } while ((peer = peer_nxt(peer)) != mon->self); read_unlock_bh(&mon->lock); return 0; } int __tipc_nl_add_monitor(struct net *net, struct tipc_nl_msg *msg, u32 bearer_id) { struct tipc_monitor *mon = tipc_monitor(net, bearer_id); char bearer_name[TIPC_MAX_BEARER_NAME]; struct nlattr *attrs; void *hdr; int ret; ret = tipc_bearer_get_name(net, bearer_name, bearer_id); if (ret || !mon) return 0; hdr = genlmsg_put(msg->skb, msg->portid, msg->seq, &tipc_genl_family, NLM_F_MULTI, TIPC_NL_MON_GET); if (!hdr) return -EMSGSIZE; attrs = nla_nest_start_noflag(msg->skb, TIPC_NLA_MON); if (!attrs) goto msg_full; read_lock_bh(&mon->lock); if (nla_put_u32(msg->skb, TIPC_NLA_MON_REF, bearer_id)) goto attr_msg_full; if (tipc_mon_is_active(net, mon)) if (nla_put_flag(msg->skb, TIPC_NLA_MON_ACTIVE)) goto attr_msg_full; if (nla_put_string(msg->skb, TIPC_NLA_MON_BEARER_NAME, bearer_name)) goto attr_msg_full; if (nla_put_u32(msg->skb, TIPC_NLA_MON_PEERCNT, mon->peer_cnt)) goto attr_msg_full; if (nla_put_u32(msg->skb, TIPC_NLA_MON_LISTGEN, mon->list_gen)) goto attr_msg_full; read_unlock_bh(&mon->lock); nla_nest_end(msg->skb, attrs); genlmsg_end(msg->skb, hdr); return 0; attr_msg_full: read_unlock_bh(&mon->lock); nla_nest_cancel(msg->skb, attrs); msg_full: genlmsg_cancel(msg->skb, hdr); return -EMSGSIZE; } |
| 6 6 | 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 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef __NET_PKT_SCHED_H #define __NET_PKT_SCHED_H #include <linux/jiffies.h> #include <linux/ktime.h> #include <linux/if_vlan.h> #include <linux/netdevice.h> #include <net/sch_generic.h> #include <net/net_namespace.h> #include <uapi/linux/pkt_sched.h> #define DEFAULT_TX_QUEUE_LEN 1000 #define STAB_SIZE_LOG_MAX 30 struct qdisc_walker { int stop; int skip; int count; int (*fn)(struct Qdisc *, unsigned long cl, struct qdisc_walker *); }; #define qdisc_priv(q) \ _Generic(q, \ const struct Qdisc * : (const void *)&q->privdata, \ struct Qdisc * : (void *)&q->privdata) static inline struct Qdisc *qdisc_from_priv(void *priv) { return container_of(priv, struct Qdisc, privdata); } /* Timer resolution MUST BE < 10% of min_schedulable_packet_size/bandwidth Normal IP packet size ~ 512byte, hence: 0.5Kbyte/1Mbyte/sec = 0.5msec, so that we need 50usec timer for 10Mbit ethernet. 10msec resolution -> <50Kbit/sec. The result: [34]86 is not good choice for QoS router :-( The things are not so bad, because we may use artificial clock evaluated by integration of network data flow in the most critical places. */ typedef u64 psched_time_t; typedef long psched_tdiff_t; /* Avoid doing 64 bit divide */ #define PSCHED_SHIFT 6 #define PSCHED_TICKS2NS(x) ((s64)(x) << PSCHED_SHIFT) #define PSCHED_NS2TICKS(x) ((x) >> PSCHED_SHIFT) #define PSCHED_TICKS_PER_SEC PSCHED_NS2TICKS(NSEC_PER_SEC) #define PSCHED_PASTPERFECT 0 static inline psched_time_t psched_get_time(void) { return PSCHED_NS2TICKS(ktime_get_ns()); } struct qdisc_watchdog { struct hrtimer timer; struct Qdisc *qdisc; }; void qdisc_watchdog_init_clockid(struct qdisc_watchdog *wd, struct Qdisc *qdisc, clockid_t clockid); void qdisc_watchdog_init(struct qdisc_watchdog *wd, struct Qdisc *qdisc); void qdisc_watchdog_schedule_range_ns(struct qdisc_watchdog *wd, u64 expires, u64 delta_ns); static inline void qdisc_watchdog_schedule_ns(struct qdisc_watchdog *wd, u64 expires) { return qdisc_watchdog_schedule_range_ns(wd, expires, 0ULL); } static inline void qdisc_watchdog_schedule(struct qdisc_watchdog *wd, psched_time_t expires) { qdisc_watchdog_schedule_ns(wd, PSCHED_TICKS2NS(expires)); } void qdisc_watchdog_cancel(struct qdisc_watchdog *wd); extern struct Qdisc_ops pfifo_qdisc_ops; extern struct Qdisc_ops bfifo_qdisc_ops; extern struct Qdisc_ops pfifo_head_drop_qdisc_ops; int fifo_set_limit(struct Qdisc *q, unsigned int limit); struct Qdisc *fifo_create_dflt(struct Qdisc *sch, struct Qdisc_ops *ops, unsigned int limit, struct netlink_ext_ack *extack); int register_qdisc(struct Qdisc_ops *qops); void unregister_qdisc(struct Qdisc_ops *qops); #define NET_SCH_ALIAS_PREFIX "net-sch-" #define MODULE_ALIAS_NET_SCH(id) MODULE_ALIAS(NET_SCH_ALIAS_PREFIX id) void qdisc_get_default(char *id, size_t len); int qdisc_set_default(const char *id); void qdisc_hash_add(struct Qdisc *q, bool invisible); void qdisc_hash_del(struct Qdisc *q); struct Qdisc *qdisc_lookup(struct net_device *dev, u32 handle); struct Qdisc *qdisc_lookup_rcu(struct net_device *dev, u32 handle); struct qdisc_rate_table *qdisc_get_rtab(struct tc_ratespec *r, struct nlattr *tab, struct netlink_ext_ack *extack); void qdisc_put_rtab(struct qdisc_rate_table *tab); void qdisc_put_stab(struct qdisc_size_table *tab); void qdisc_warn_nonwc(const char *txt, struct Qdisc *qdisc); bool sch_direct_xmit(struct sk_buff *skb, struct Qdisc *q, struct net_device *dev, struct netdev_queue *txq, spinlock_t *root_lock, bool validate); void __qdisc_run(struct Qdisc *q); static inline void qdisc_run(struct Qdisc *q) { if (qdisc_run_begin(q)) { __qdisc_run(q); qdisc_run_end(q); } } extern const struct nla_policy rtm_tca_policy[TCA_MAX + 1]; /* Calculate maximal size of packet seen by hard_start_xmit routine of this device. */ static inline unsigned int psched_mtu(const struct net_device *dev) { return READ_ONCE(dev->mtu) + dev->hard_header_len; } static inline struct net *qdisc_net(struct Qdisc *q) { return dev_net(q->dev_queue->dev); } struct tc_query_caps_base { enum tc_setup_type type; void *caps; }; struct tc_cbs_qopt_offload { u8 enable; s32 queue; s32 hicredit; s32 locredit; s32 idleslope; s32 sendslope; }; struct tc_etf_qopt_offload { u8 enable; s32 queue; }; struct tc_mqprio_caps { bool validate_queue_counts:1; }; struct tc_mqprio_qopt_offload { /* struct tc_mqprio_qopt must always be the first element */ struct tc_mqprio_qopt qopt; struct netlink_ext_ack *extack; u16 mode; u16 shaper; u32 flags; u64 min_rate[TC_QOPT_MAX_QUEUE]; u64 max_rate[TC_QOPT_MAX_QUEUE]; unsigned long preemptible_tcs; }; struct tc_taprio_caps { bool supports_queue_max_sdu:1; bool gate_mask_per_txq:1; /* Device expects lower TXQ numbers to have higher priority over higher * TXQs, regardless of their TC mapping. DO NOT USE FOR NEW DRIVERS, * INSTEAD ENFORCE A PROPER TC:TXQ MAPPING COMING FROM USER SPACE. */ bool broken_mqprio:1; }; enum tc_taprio_qopt_cmd { TAPRIO_CMD_REPLACE, TAPRIO_CMD_DESTROY, TAPRIO_CMD_STATS, TAPRIO_CMD_QUEUE_STATS, }; /** * struct tc_taprio_qopt_stats - IEEE 802.1Qbv statistics * @window_drops: Frames that were dropped because they were too large to be * transmitted in any of the allotted time windows (open gates) for their * traffic class. * @tx_overruns: Frames still being transmitted by the MAC after the * transmission gate associated with their traffic class has closed. * Equivalent to `12.29.1.1.2 TransmissionOverrun` from 802.1Q-2018. */ struct tc_taprio_qopt_stats { u64 window_drops; u64 tx_overruns; }; struct tc_taprio_qopt_queue_stats { int queue; struct tc_taprio_qopt_stats stats; }; struct tc_taprio_sched_entry { u8 command; /* TC_TAPRIO_CMD_* */ /* The gate_mask in the offloading side refers to traffic classes */ u32 gate_mask; u32 interval; }; struct tc_taprio_qopt_offload { enum tc_taprio_qopt_cmd cmd; union { /* TAPRIO_CMD_STATS */ struct tc_taprio_qopt_stats stats; /* TAPRIO_CMD_QUEUE_STATS */ struct tc_taprio_qopt_queue_stats queue_stats; /* TAPRIO_CMD_REPLACE */ struct { struct tc_mqprio_qopt_offload mqprio; struct netlink_ext_ack *extack; ktime_t base_time; u64 cycle_time; u64 cycle_time_extension; u32 max_sdu[TC_MAX_QUEUE]; size_t num_entries; struct tc_taprio_sched_entry entries[]; }; }; }; #if IS_ENABLED(CONFIG_NET_SCH_TAPRIO) /* Reference counting */ struct tc_taprio_qopt_offload *taprio_offload_get(struct tc_taprio_qopt_offload *offload); void taprio_offload_free(struct tc_taprio_qopt_offload *offload); #else /* Reference counting */ static inline struct tc_taprio_qopt_offload * taprio_offload_get(struct tc_taprio_qopt_offload *offload) { return NULL; } static inline void taprio_offload_free(struct tc_taprio_qopt_offload *offload) { } #endif /* Ensure skb_mstamp_ns, which might have been populated with the txtime, is * not mistaken for a software timestamp, because this will otherwise prevent * the dispatch of hardware timestamps to the socket. */ static inline void skb_txtime_consumed(struct sk_buff *skb) { skb->tstamp = ktime_set(0, 0); } static inline bool tc_qdisc_stats_dump(struct Qdisc *sch, unsigned long cl, struct qdisc_walker *arg) { if (arg->count >= arg->skip && arg->fn(sch, cl, arg) < 0) { arg->stop = 1; return false; } arg->count++; return true; } #endif |
| 1124 5 8459 8459 624 12 621 623 1 1 149 40 70 70 69 70 1 69 8171 8176 8169 8176 23 8170 4751 4750 4750 4752 4754 4746 9 58 58 59 59 59 211 212 3975 1081 1081 1081 8 1079 224 43 43 43 2 | 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 | // SPDX-License-Identifier: GPL-2.0 /* * Kernel timekeeping code and accessor functions. Based on code from * timer.c, moved in commit 8524070b7982. */ #include <linux/timekeeper_internal.h> #include <linux/module.h> #include <linux/interrupt.h> #include <linux/percpu.h> #include <linux/init.h> #include <linux/mm.h> #include <linux/nmi.h> #include <linux/sched.h> #include <linux/sched/loadavg.h> #include <linux/sched/clock.h> #include <linux/syscore_ops.h> #include <linux/clocksource.h> #include <linux/jiffies.h> #include <linux/time.h> #include <linux/timex.h> #include <linux/tick.h> #include <linux/stop_machine.h> #include <linux/pvclock_gtod.h> #include <linux/compiler.h> #include <linux/audit.h> #include <linux/random.h> #include "tick-internal.h" #include "ntp_internal.h" #include "timekeeping_internal.h" #define TK_CLEAR_NTP (1 << 0) #define TK_CLOCK_WAS_SET (1 << 1) #define TK_UPDATE_ALL (TK_CLEAR_NTP | TK_CLOCK_WAS_SET) enum timekeeping_adv_mode { /* Update timekeeper when a tick has passed */ TK_ADV_TICK, /* Update timekeeper on a direct frequency change */ TK_ADV_FREQ }; /* * The most important data for readout fits into a single 64 byte * cache line. */ struct tk_data { seqcount_raw_spinlock_t seq; struct timekeeper timekeeper; struct timekeeper shadow_timekeeper; raw_spinlock_t lock; } ____cacheline_aligned; static struct tk_data tk_core; /* flag for if timekeeping is suspended */ int __read_mostly timekeeping_suspended; /** * struct tk_fast - NMI safe timekeeper * @seq: Sequence counter for protecting updates. The lowest bit * is the index for the tk_read_base array * @base: tk_read_base array. Access is indexed by the lowest bit of * @seq. * * See @update_fast_timekeeper() below. */ struct tk_fast { seqcount_latch_t seq; struct tk_read_base base[2]; }; /* Suspend-time cycles value for halted fast timekeeper. */ static u64 cycles_at_suspend; static u64 dummy_clock_read(struct clocksource *cs) { if (timekeeping_suspended) return cycles_at_suspend; return local_clock(); } static struct clocksource dummy_clock = { .read = dummy_clock_read, }; /* * Boot time initialization which allows local_clock() to be utilized * during early boot when clocksources are not available. local_clock() * returns nanoseconds already so no conversion is required, hence mult=1 * and shift=0. When the first proper clocksource is installed then * the fast time keepers are updated with the correct values. */ #define FAST_TK_INIT \ { \ .clock = &dummy_clock, \ .mask = CLOCKSOURCE_MASK(64), \ .mult = 1, \ .shift = 0, \ } static struct tk_fast tk_fast_mono ____cacheline_aligned = { .seq = SEQCNT_LATCH_ZERO(tk_fast_mono.seq), .base[0] = FAST_TK_INIT, .base[1] = FAST_TK_INIT, }; static struct tk_fast tk_fast_raw ____cacheline_aligned = { .seq = SEQCNT_LATCH_ZERO(tk_fast_raw.seq), .base[0] = FAST_TK_INIT, .base[1] = FAST_TK_INIT, }; unsigned long timekeeper_lock_irqsave(void) { unsigned long flags; raw_spin_lock_irqsave(&tk_core.lock, flags); return flags; } void timekeeper_unlock_irqrestore(unsigned long flags) { raw_spin_unlock_irqrestore(&tk_core.lock, flags); } /* * Multigrain timestamps require tracking the latest fine-grained timestamp * that has been issued, and never returning a coarse-grained timestamp that is * earlier than that value. * * mg_floor represents the latest fine-grained time that has been handed out as * a file timestamp on the system. This is tracked as a monotonic ktime_t, and * converted to a realtime clock value on an as-needed basis. * * Maintaining mg_floor ensures the multigrain interfaces never issue a * timestamp earlier than one that has been previously issued. * * The exception to this rule is when there is a backward realtime clock jump. If * such an event occurs, a timestamp can appear to be earlier than a previous one. */ static __cacheline_aligned_in_smp atomic64_t mg_floor; static inline void tk_normalize_xtime(struct timekeeper *tk) { while (tk->tkr_mono.xtime_nsec >= ((u64)NSEC_PER_SEC << tk->tkr_mono.shift)) { tk->tkr_mono.xtime_nsec -= (u64)NSEC_PER_SEC << tk->tkr_mono.shift; tk->xtime_sec++; } while (tk->tkr_raw.xtime_nsec >= ((u64)NSEC_PER_SEC << tk->tkr_raw.shift)) { tk->tkr_raw.xtime_nsec -= (u64)NSEC_PER_SEC << tk->tkr_raw.shift; tk->raw_sec++; } } static inline struct timespec64 tk_xtime(const struct timekeeper *tk) { struct timespec64 ts; ts.tv_sec = tk->xtime_sec; ts.tv_nsec = (long)(tk->tkr_mono.xtime_nsec >> tk->tkr_mono.shift); return ts; } static void tk_set_xtime(struct timekeeper *tk, const struct timespec64 *ts) { tk->xtime_sec = ts->tv_sec; tk->tkr_mono.xtime_nsec = (u64)ts->tv_nsec << tk->tkr_mono.shift; } static void tk_xtime_add(struct timekeeper *tk, const struct timespec64 *ts) { tk->xtime_sec += ts->tv_sec; tk->tkr_mono.xtime_nsec += (u64)ts->tv_nsec << tk->tkr_mono.shift; tk_normalize_xtime(tk); } static void tk_set_wall_to_mono(struct timekeeper *tk, struct timespec64 wtm) { struct timespec64 tmp; /* * Verify consistency of: offset_real = -wall_to_monotonic * before modifying anything */ set_normalized_timespec64(&tmp, -tk->wall_to_monotonic.tv_sec, -tk->wall_to_monotonic.tv_nsec); WARN_ON_ONCE(tk->offs_real != timespec64_to_ktime(tmp)); tk->wall_to_monotonic = wtm; set_normalized_timespec64(&tmp, -wtm.tv_sec, -wtm.tv_nsec); /* Paired with READ_ONCE() in ktime_mono_to_any() */ WRITE_ONCE(tk->offs_real, timespec64_to_ktime(tmp)); WRITE_ONCE(tk->offs_tai, ktime_add(tk->offs_real, ktime_set(tk->tai_offset, 0))); } static inline void tk_update_sleep_time(struct timekeeper *tk, ktime_t delta) { /* Paired with READ_ONCE() in ktime_mono_to_any() */ WRITE_ONCE(tk->offs_boot, ktime_add(tk->offs_boot, delta)); /* * Timespec representation for VDSO update to avoid 64bit division * on every update. */ tk->monotonic_to_boot = ktime_to_timespec64(tk->offs_boot); } /* * tk_clock_read - atomic clocksource read() helper * * This helper is necessary to use in the read paths because, while the * seqcount ensures we don't return a bad value while structures are updated, * it doesn't protect from potential crashes. There is the possibility that * the tkr's clocksource may change between the read reference, and the * clock reference passed to the read function. This can cause crashes if * the wrong clocksource is passed to the wrong read function. * This isn't necessary to use when holding the tk_core.lock or doing * a read of the fast-timekeeper tkrs (which is protected by its own locking * and update logic). */ static inline u64 tk_clock_read(const struct tk_read_base *tkr) { struct clocksource *clock = READ_ONCE(tkr->clock); return clock->read(clock); } /** * tk_setup_internals - Set up internals to use clocksource clock. * * @tk: The target timekeeper to setup. * @clock: Pointer to clocksource. * * Calculates a fixed cycle/nsec interval for a given clocksource/adjustment * pair and interval request. * * Unless you're the timekeeping code, you should not be using this! */ static void tk_setup_internals(struct timekeeper *tk, struct clocksource *clock) { u64 interval; u64 tmp, ntpinterval; struct clocksource *old_clock; ++tk->cs_was_changed_seq; old_clock = tk->tkr_mono.clock; tk->tkr_mono.clock = clock; tk->tkr_mono.mask = clock->mask; tk->tkr_mono.cycle_last = tk_clock_read(&tk->tkr_mono); tk->tkr_raw.clock = clock; tk->tkr_raw.mask = clock->mask; tk->tkr_raw.cycle_last = tk->tkr_mono.cycle_last; /* Do the ns -> cycle conversion first, using original mult */ tmp = NTP_INTERVAL_LENGTH; tmp <<= clock->shift; ntpinterval = tmp; tmp += clock->mult/2; do_div(tmp, clock->mult); if (tmp == 0) tmp = 1; interval = (u64) tmp; tk->cycle_interval = interval; /* Go back from cycles -> shifted ns */ tk->xtime_interval = interval * clock->mult; tk->xtime_remainder = ntpinterval - tk->xtime_interval; tk->raw_interval = interval * clock->mult; /* if changing clocks, convert xtime_nsec shift units */ if (old_clock) { int shift_change = clock->shift - old_clock->shift; if (shift_change < 0) { tk->tkr_mono.xtime_nsec >>= -shift_change; tk->tkr_raw.xtime_nsec >>= -shift_change; } else { tk->tkr_mono.xtime_nsec <<= shift_change; tk->tkr_raw.xtime_nsec <<= shift_change; } } tk->tkr_mono.shift = clock->shift; tk->tkr_raw.shift = clock->shift; tk->ntp_error = 0; tk->ntp_error_shift = NTP_SCALE_SHIFT - clock->shift; tk->ntp_tick = ntpinterval << tk->ntp_error_shift; /* * The timekeeper keeps its own mult values for the currently * active clocksource. These value will be adjusted via NTP * to counteract clock drifting. */ tk->tkr_mono.mult = clock->mult; tk->tkr_raw.mult = clock->mult; tk->ntp_err_mult = 0; tk->skip_second_overflow = 0; } /* Timekeeper helper functions. */ static noinline u64 delta_to_ns_safe(const struct tk_read_base *tkr, u64 delta) { return mul_u64_u32_add_u64_shr(delta, tkr->mult, tkr->xtime_nsec, tkr->shift); } static inline u64 timekeeping_cycles_to_ns(const struct tk_read_base *tkr, u64 cycles) { /* Calculate the delta since the last update_wall_time() */ u64 mask = tkr->mask, delta = (cycles - tkr->cycle_last) & mask; /* * This detects both negative motion and the case where the delta * overflows the multiplication with tkr->mult. */ if (unlikely(delta > tkr->clock->max_cycles)) { /* * Handle clocksource inconsistency between CPUs to prevent * time from going backwards by checking for the MSB of the * mask being set in the delta. */ if (delta & ~(mask >> 1)) return tkr->xtime_nsec >> tkr->shift; return delta_to_ns_safe(tkr, delta); } return ((delta * tkr->mult) + tkr->xtime_nsec) >> tkr->shift; } static __always_inline u64 timekeeping_get_ns(const struct tk_read_base *tkr) { return timekeeping_cycles_to_ns(tkr, tk_clock_read(tkr)); } /** * update_fast_timekeeper - Update the fast and NMI safe monotonic timekeeper. * @tkr: Timekeeping readout base from which we take the update * @tkf: Pointer to NMI safe timekeeper * * We want to use this from any context including NMI and tracing / * instrumenting the timekeeping code itself. * * Employ the latch technique; see @write_seqcount_latch. * * So if a NMI hits the update of base[0] then it will use base[1] * which is still consistent. In the worst case this can result is a * slightly wrong timestamp (a few nanoseconds). See * @ktime_get_mono_fast_ns. */ static void update_fast_timekeeper(const struct tk_read_base *tkr, struct tk_fast *tkf) { struct tk_read_base *base = tkf->base; /* Force readers off to base[1] */ write_seqcount_latch_begin(&tkf->seq); /* Update base[0] */ memcpy(base, tkr, sizeof(*base)); /* Force readers back to base[0] */ write_seqcount_latch(&tkf->seq); /* Update base[1] */ memcpy(base + 1, base, sizeof(*base)); write_seqcount_latch_end(&tkf->seq); } static __always_inline u64 __ktime_get_fast_ns(struct tk_fast *tkf) { struct tk_read_base *tkr; unsigned int seq; u64 now; do { seq = read_seqcount_latch(&tkf->seq); tkr = tkf->base + (seq & 0x01); now = ktime_to_ns(tkr->base); now += timekeeping_get_ns(tkr); } while (read_seqcount_latch_retry(&tkf->seq, seq)); return now; } /** * ktime_get_mono_fast_ns - Fast NMI safe access to clock monotonic * * This timestamp is not guaranteed to be monotonic across an update. * The timestamp is calculated by: * * now = base_mono + clock_delta * slope * * So if the update lowers the slope, readers who are forced to the * not yet updated second array are still using the old steeper slope. * * tmono * ^ * | o n * | o n * | u * | o * |o * |12345678---> reader order * * o = old slope * u = update * n = new slope * * So reader 6 will observe time going backwards versus reader 5. * * While other CPUs are likely to be able to observe that, the only way * for a CPU local observation is when an NMI hits in the middle of * the update. Timestamps taken from that NMI context might be ahead * of the following timestamps. Callers need to be aware of that and * deal with it. */ u64 notrace ktime_get_mono_fast_ns(void) { return __ktime_get_fast_ns(&tk_fast_mono); } EXPORT_SYMBOL_GPL(ktime_get_mono_fast_ns); /** * ktime_get_raw_fast_ns - Fast NMI safe access to clock monotonic raw * * Contrary to ktime_get_mono_fast_ns() this is always correct because the * conversion factor is not affected by NTP/PTP correction. */ u64 notrace ktime_get_raw_fast_ns(void) { return __ktime_get_fast_ns(&tk_fast_raw); } EXPORT_SYMBOL_GPL(ktime_get_raw_fast_ns); /** * ktime_get_boot_fast_ns - NMI safe and fast access to boot clock. * * To keep it NMI safe since we're accessing from tracing, we're not using a * separate timekeeper with updates to monotonic clock and boot offset * protected with seqcounts. This has the following minor side effects: * * (1) Its possible that a timestamp be taken after the boot offset is updated * but before the timekeeper is updated. If this happens, the new boot offset * is added to the old timekeeping making the clock appear to update slightly * earlier: * CPU 0 CPU 1 * timekeeping_inject_sleeptime64() * __timekeeping_inject_sleeptime(tk, delta); * timestamp(); * timekeeping_update_staged(tkd, TK_CLEAR_NTP...); * * (2) On 32-bit systems, the 64-bit boot offset (tk->offs_boot) may be * partially updated. Since the tk->offs_boot update is a rare event, this * should be a rare occurrence which postprocessing should be able to handle. * * The caveats vs. timestamp ordering as documented for ktime_get_mono_fast_ns() * apply as well. */ u64 notrace ktime_get_boot_fast_ns(void) { struct timekeeper *tk = &tk_core.timekeeper; return (ktime_get_mono_fast_ns() + ktime_to_ns(data_race(tk->offs_boot))); } EXPORT_SYMBOL_GPL(ktime_get_boot_fast_ns); /** * ktime_get_tai_fast_ns - NMI safe and fast access to tai clock. * * The same limitations as described for ktime_get_boot_fast_ns() apply. The * mono time and the TAI offset are not read atomically which may yield wrong * readouts. However, an update of the TAI offset is an rare event e.g., caused * by settime or adjtimex with an offset. The user of this function has to deal * with the possibility of wrong timestamps in post processing. */ u64 notrace ktime_get_tai_fast_ns(void) { struct timekeeper *tk = &tk_core.timekeeper; return (ktime_get_mono_fast_ns() + ktime_to_ns(data_race(tk->offs_tai))); } EXPORT_SYMBOL_GPL(ktime_get_tai_fast_ns); /** * ktime_get_real_fast_ns: - NMI safe and fast access to clock realtime. * * See ktime_get_mono_fast_ns() for documentation of the time stamp ordering. */ u64 ktime_get_real_fast_ns(void) { struct tk_fast *tkf = &tk_fast_mono; struct tk_read_base *tkr; u64 baser, delta; unsigned int seq; do { seq = raw_read_seqcount_latch(&tkf->seq); tkr = tkf->base + (seq & 0x01); baser = ktime_to_ns(tkr->base_real); delta = timekeeping_get_ns(tkr); } while (raw_read_seqcount_latch_retry(&tkf->seq, seq)); return baser + delta; } EXPORT_SYMBOL_GPL(ktime_get_real_fast_ns); /** * halt_fast_timekeeper - Prevent fast timekeeper from accessing clocksource. * @tk: Timekeeper to snapshot. * * It generally is unsafe to access the clocksource after timekeeping has been * suspended, so take a snapshot of the readout base of @tk and use it as the * fast timekeeper's readout base while suspended. It will return the same * number of cycles every time until timekeeping is resumed at which time the * proper readout base for the fast timekeeper will be restored automatically. */ static void halt_fast_timekeeper(const struct timekeeper *tk) { static struct tk_read_base tkr_dummy; const struct tk_read_base *tkr = &tk->tkr_mono; memcpy(&tkr_dummy, tkr, sizeof(tkr_dummy)); cycles_at_suspend = tk_clock_read(tkr); tkr_dummy.clock = &dummy_clock; tkr_dummy.base_real = tkr->base + tk->offs_real; update_fast_timekeeper(&tkr_dummy, &tk_fast_mono); tkr = &tk->tkr_raw; memcpy(&tkr_dummy, tkr, sizeof(tkr_dummy)); tkr_dummy.clock = &dummy_clock; update_fast_timekeeper(&tkr_dummy, &tk_fast_raw); } static RAW_NOTIFIER_HEAD(pvclock_gtod_chain); static void update_pvclock_gtod(struct timekeeper *tk, bool was_set) { raw_notifier_call_chain(&pvclock_gtod_chain, was_set, tk); } /** * pvclock_gtod_register_notifier - register a pvclock timedata update listener * @nb: Pointer to the notifier block to register */ int pvclock_gtod_register_notifier(struct notifier_block *nb) { struct timekeeper *tk = &tk_core.timekeeper; int ret; guard(raw_spinlock_irqsave)(&tk_core.lock); ret = raw_notifier_chain_register(&pvclock_gtod_chain, nb); update_pvclock_gtod(tk, true); return ret; } EXPORT_SYMBOL_GPL(pvclock_gtod_register_notifier); /** * pvclock_gtod_unregister_notifier - unregister a pvclock * timedata update listener * @nb: Pointer to the notifier block to unregister */ int pvclock_gtod_unregister_notifier(struct notifier_block *nb) { guard(raw_spinlock_irqsave)(&tk_core.lock); return raw_notifier_chain_unregister(&pvclock_gtod_chain, nb); } EXPORT_SYMBOL_GPL(pvclock_gtod_unregister_notifier); /* * tk_update_leap_state - helper to update the next_leap_ktime */ static inline void tk_update_leap_state(struct timekeeper *tk) { tk->next_leap_ktime = ntp_get_next_leap(); if (tk->next_leap_ktime != KTIME_MAX) /* Convert to monotonic time */ tk->next_leap_ktime = ktime_sub(tk->next_leap_ktime, tk->offs_real); } /* * Leap state update for both shadow and the real timekeeper * Separate to spare a full memcpy() of the timekeeper. */ static void tk_update_leap_state_all(struct tk_data *tkd) { write_seqcount_begin(&tkd->seq); tk_update_leap_state(&tkd->shadow_timekeeper); tkd->timekeeper.next_leap_ktime = tkd->shadow_timekeeper.next_leap_ktime; write_seqcount_end(&tkd->seq); } /* * Update the ktime_t based scalar nsec members of the timekeeper */ static inline void tk_update_ktime_data(struct timekeeper *tk) { u64 seconds; u32 nsec; /* * The xtime based monotonic readout is: * nsec = (xtime_sec + wtm_sec) * 1e9 + wtm_nsec + now(); * The ktime based monotonic readout is: * nsec = base_mono + now(); * ==> base_mono = (xtime_sec + wtm_sec) * 1e9 + wtm_nsec */ seconds = (u64)(tk->xtime_sec + tk->wall_to_monotonic.tv_sec); nsec = (u32) tk->wall_to_monotonic.tv_nsec; tk->tkr_mono.base = ns_to_ktime(seconds * NSEC_PER_SEC + nsec); /* * The sum of the nanoseconds portions of xtime and * wall_to_monotonic can be greater/equal one second. Take * this into account before updating tk->ktime_sec. */ nsec += (u32)(tk->tkr_mono.xtime_nsec >> tk->tkr_mono.shift); if (nsec >= NSEC_PER_SEC) seconds++; tk->ktime_sec = seconds; /* Update the monotonic raw base */ tk->tkr_raw.base = ns_to_ktime(tk->raw_sec * NSEC_PER_SEC); } /* * Restore the shadow timekeeper from the real timekeeper. */ static void timekeeping_restore_shadow(struct tk_data *tkd) { lockdep_assert_held(&tkd->lock); memcpy(&tkd->shadow_timekeeper, &tkd->timekeeper, sizeof(tkd->timekeeper)); } static void timekeeping_update_from_shadow(struct tk_data *tkd, unsigned int action) { struct timekeeper *tk = &tk_core.shadow_timekeeper; lockdep_assert_held(&tkd->lock); /* * Block out readers before running the updates below because that * updates VDSO and other time related infrastructure. Not blocking * the readers might let a reader see time going backwards when * reading from the VDSO after the VDSO update and then reading in * the kernel from the timekeeper before that got updated. */ write_seqcount_begin(&tkd->seq); if (action & TK_CLEAR_NTP) { tk->ntp_error = 0; ntp_clear(); } tk_update_leap_state(tk); tk_update_ktime_data(tk); update_vsyscall(tk); update_pvclock_gtod(tk, action & TK_CLOCK_WAS_SET); tk->tkr_mono.base_real = tk->tkr_mono.base + tk->offs_real; update_fast_timekeeper(&tk->tkr_mono, &tk_fast_mono); update_fast_timekeeper(&tk->tkr_raw, &tk_fast_raw); if (action & TK_CLOCK_WAS_SET) tk->clock_was_set_seq++; /* * Update the real timekeeper. * * We could avoid this memcpy() by switching pointers, but that has * the downside that the reader side does not longer benefit from * the cacheline optimized data layout of the timekeeper and requires * another indirection. */ memcpy(&tkd->timekeeper, tk, sizeof(*tk)); write_seqcount_end(&tkd->seq); } /** * timekeeping_forward_now - update clock to the current time * @tk: Pointer to the timekeeper to update * * Forward the current clock to update its state since the last call to * update_wall_time(). This is useful before significant clock changes, * as it avoids having to deal with this time offset explicitly. */ static void timekeeping_forward_now(struct timekeeper *tk) { u64 cycle_now, delta; cycle_now = tk_clock_read(&tk->tkr_mono); delta = clocksource_delta(cycle_now, tk->tkr_mono.cycle_last, tk->tkr_mono.mask, tk->tkr_mono.clock->max_raw_delta); tk->tkr_mono.cycle_last = cycle_now; tk->tkr_raw.cycle_last = cycle_now; while (delta > 0) { u64 max = tk->tkr_mono.clock->max_cycles; u64 incr = delta < max ? delta : max; tk->tkr_mono.xtime_nsec += incr * tk->tkr_mono.mult; tk->tkr_raw.xtime_nsec += incr * tk->tkr_raw.mult; tk_normalize_xtime(tk); delta -= incr; } } /** * ktime_get_real_ts64 - Returns the time of day in a timespec64. * @ts: pointer to the timespec to be set * * Returns the time of day in a timespec64 (WARN if suspended). */ void ktime_get_real_ts64(struct timespec64 *ts) { struct timekeeper *tk = &tk_core.timekeeper; unsigned int seq; u64 nsecs; WARN_ON(timekeeping_suspended); do { seq = read_seqcount_begin(&tk_core.seq); ts->tv_sec = tk->xtime_sec; nsecs = timekeeping_get_ns(&tk->tkr_mono); } while (read_seqcount_retry(&tk_core.seq, seq)); ts->tv_nsec = 0; timespec64_add_ns(ts, nsecs); } EXPORT_SYMBOL(ktime_get_real_ts64); ktime_t ktime_get(void) { struct timekeeper *tk = &tk_core.timekeeper; unsigned int seq; ktime_t base; u64 nsecs; WARN_ON(timekeeping_suspended); do { seq = read_seqcount_begin(&tk_core.seq); base = tk->tkr_mono.base; nsecs = timekeeping_get_ns(&tk->tkr_mono); } while (read_seqcount_retry(&tk_core.seq, seq)); return ktime_add_ns(base, nsecs); } EXPORT_SYMBOL_GPL(ktime_get); u32 ktime_get_resolution_ns(void) { struct timekeeper *tk = &tk_core.timekeeper; unsigned int seq; u32 nsecs; WARN_ON(timekeeping_suspended); do { seq = read_seqcount_begin(&tk_core.seq); nsecs = tk->tkr_mono.mult >> tk->tkr_mono.shift; } while (read_seqcount_retry(&tk_core.seq, seq)); return nsecs; } EXPORT_SYMBOL_GPL(ktime_get_resolution_ns); static ktime_t *offsets[TK_OFFS_MAX] = { [TK_OFFS_REAL] = &tk_core.timekeeper.offs_real, [TK_OFFS_BOOT] = &tk_core.timekeeper.offs_boot, [TK_OFFS_TAI] = &tk_core.timekeeper.offs_tai, }; ktime_t ktime_get_with_offset(enum tk_offsets offs) { struct timekeeper *tk = &tk_core.timekeeper; unsigned int seq; ktime_t base, *offset = offsets[offs]; u64 nsecs; WARN_ON(timekeeping_suspended); do { seq = read_seqcount_begin(&tk_core.seq); base = ktime_add(tk->tkr_mono.base, *offset); nsecs = timekeeping_get_ns(&tk->tkr_mono); } while (read_seqcount_retry(&tk_core.seq, seq)); return ktime_add_ns(base, nsecs); } EXPORT_SYMBOL_GPL(ktime_get_with_offset); ktime_t ktime_get_coarse_with_offset(enum tk_offsets offs) { struct timekeeper *tk = &tk_core.timekeeper; unsigned int seq; ktime_t base, *offset = offsets[offs]; u64 nsecs; WARN_ON(timekeeping_suspended); do { seq = read_seqcount_begin(&tk_core.seq); base = ktime_add(tk->tkr_mono.base, *offset); nsecs = tk->tkr_mono.xtime_nsec >> tk->tkr_mono.shift; } while (read_seqcount_retry(&tk_core.seq, seq)); return ktime_add_ns(base, nsecs); } EXPORT_SYMBOL_GPL(ktime_get_coarse_with_offset); /** * ktime_mono_to_any() - convert monotonic time to any other time * @tmono: time to convert. * @offs: which offset to use */ ktime_t ktime_mono_to_any(ktime_t tmono, enum tk_offsets offs) { ktime_t *offset = offsets[offs]; unsigned int seq; ktime_t tconv; if (IS_ENABLED(CONFIG_64BIT)) { /* * Paired with WRITE_ONCE()s in tk_set_wall_to_mono() and * tk_update_sleep_time(). */ return ktime_add(tmono, READ_ONCE(*offset)); } do { seq = read_seqcount_begin(&tk_core.seq); tconv = ktime_add(tmono, *offset); } while (read_seqcount_retry(&tk_core.seq, seq)); return tconv; } EXPORT_SYMBOL_GPL(ktime_mono_to_any); /** * ktime_get_raw - Returns the raw monotonic time in ktime_t format */ ktime_t ktime_get_raw(void) { struct timekeeper *tk = &tk_core.timekeeper; unsigned int seq; ktime_t base; u64 nsecs; do { seq = read_seqcount_begin(&tk_core.seq); base = tk->tkr_raw.base; nsecs = timekeeping_get_ns(&tk->tkr_raw); } while (read_seqcount_retry(&tk_core.seq, seq)); return ktime_add_ns(base, nsecs); } EXPORT_SYMBOL_GPL(ktime_get_raw); /** * ktime_get_ts64 - get the monotonic clock in timespec64 format * @ts: pointer to timespec variable * * The function calculates the monotonic clock from the realtime * clock and the wall_to_monotonic offset and stores the result * in normalized timespec64 format in the variable pointed to by @ts. */ void ktime_get_ts64(struct timespec64 *ts) { struct timekeeper *tk = &tk_core.timekeeper; struct timespec64 tomono; unsigned int seq; u64 nsec; WARN_ON(timekeeping_suspended); do { seq = read_seqcount_begin(&tk_core.seq); ts->tv_sec = tk->xtime_sec; nsec = timekeeping_get_ns(&tk->tkr_mono); tomono = tk->wall_to_monotonic; } while (read_seqcount_retry(&tk_core.seq, seq)); ts->tv_sec += tomono.tv_sec; ts->tv_nsec = 0; timespec64_add_ns(ts, nsec + tomono.tv_nsec); } EXPORT_SYMBOL_GPL(ktime_get_ts64); /** * ktime_get_seconds - Get the seconds portion of CLOCK_MONOTONIC * * Returns the seconds portion of CLOCK_MONOTONIC with a single non * serialized read. tk->ktime_sec is of type 'unsigned long' so this * works on both 32 and 64 bit systems. On 32 bit systems the readout * covers ~136 years of uptime which should be enough to prevent * premature wrap arounds. */ time64_t ktime_get_seconds(void) { struct timekeeper *tk = &tk_core.timekeeper; WARN_ON(timekeeping_suspended); return tk->ktime_sec; } EXPORT_SYMBOL_GPL(ktime_get_seconds); /** * ktime_get_real_seconds - Get the seconds portion of CLOCK_REALTIME * * Returns the wall clock seconds since 1970. * * For 64bit systems the fast access to tk->xtime_sec is preserved. On * 32bit systems the access must be protected with the sequence * counter to provide "atomic" access to the 64bit tk->xtime_sec * value. */ time64_t ktime_get_real_seconds(void) { struct timekeeper *tk = &tk_core.timekeeper; time64_t seconds; unsigned int seq; if (IS_ENABLED(CONFIG_64BIT)) return tk->xtime_sec; do { seq = read_seqcount_begin(&tk_core.seq); seconds = tk->xtime_sec; } while (read_seqcount_retry(&tk_core.seq, seq)); return seconds; } EXPORT_SYMBOL_GPL(ktime_get_real_seconds); /** * __ktime_get_real_seconds - The same as ktime_get_real_seconds * but without the sequence counter protect. This internal function * is called just when timekeeping lock is already held. */ noinstr time64_t __ktime_get_real_seconds(void) { struct timekeeper *tk = &tk_core.timekeeper; return tk->xtime_sec; } /** * ktime_get_snapshot - snapshots the realtime/monotonic raw clocks with counter * @systime_snapshot: pointer to struct receiving the system time snapshot */ void ktime_get_snapshot(struct system_time_snapshot *systime_snapshot) { struct timekeeper *tk = &tk_core.timekeeper; unsigned int seq; ktime_t base_raw; ktime_t base_real; ktime_t base_boot; u64 nsec_raw; u64 nsec_real; u64 now; WARN_ON_ONCE(timekeeping_suspended); do { seq = read_seqcount_begin(&tk_core.seq); now = tk_clock_read(&tk->tkr_mono); systime_snapshot->cs_id = tk->tkr_mono.clock->id; systime_snapshot->cs_was_changed_seq = tk->cs_was_changed_seq; systime_snapshot->clock_was_set_seq = tk->clock_was_set_seq; base_real = ktime_add(tk->tkr_mono.base, tk_core.timekeeper.offs_real); base_boot = ktime_add(tk->tkr_mono.base, tk_core.timekeeper.offs_boot); base_raw = tk->tkr_raw.base; nsec_real = timekeeping_cycles_to_ns(&tk->tkr_mono, now); nsec_raw = timekeeping_cycles_to_ns(&tk->tkr_raw, now); } while (read_seqcount_retry(&tk_core.seq, seq)); systime_snapshot->cycles = now; systime_snapshot->real = ktime_add_ns(base_real, nsec_real); systime_snapshot->boot = ktime_add_ns(base_boot, nsec_real); systime_snapshot->raw = ktime_add_ns(base_raw, nsec_raw); } EXPORT_SYMBOL_GPL(ktime_get_snapshot); /* Scale base by mult/div checking for overflow */ static int scale64_check_overflow(u64 mult, u64 div, u64 *base) { u64 tmp, rem; tmp = div64_u64_rem(*base, div, &rem); if (((int)sizeof(u64)*8 - fls64(mult) < fls64(tmp)) || ((int)sizeof(u64)*8 - fls64(mult) < fls64(rem))) return -EOVERFLOW; tmp *= mult; rem = div64_u64(rem * mult, div); *base = tmp + rem; return 0; } /** * adjust_historical_crosststamp - adjust crosstimestamp previous to current interval * @history: Snapshot representing start of history * @partial_history_cycles: Cycle offset into history (fractional part) * @total_history_cycles: Total history length in cycles * @discontinuity: True indicates clock was set on history period * @ts: Cross timestamp that should be adjusted using * partial/total ratio * * Helper function used by get_device_system_crosststamp() to correct the * crosstimestamp corresponding to the start of the current interval to the * system counter value (timestamp point) provided by the driver. The * total_history_* quantities are the total history starting at the provided * reference point and ending at the start of the current interval. The cycle * count between the driver timestamp point and the start of the current * interval is partial_history_cycles. */ static int adjust_historical_crosststamp(struct system_time_snapshot *history, u64 partial_history_cycles, u64 total_history_cycles, bool discontinuity, struct system_device_crosststamp *ts) { struct timekeeper *tk = &tk_core.timekeeper; u64 corr_raw, corr_real; bool interp_forward; int ret; if (total_history_cycles == 0 || partial_history_cycles == 0) return 0; /* Interpolate shortest distance from beginning or end of history */ interp_forward = partial_history_cycles > total_history_cycles / 2; partial_history_cycles = interp_forward ? total_history_cycles - partial_history_cycles : partial_history_cycles; /* * Scale the monotonic raw time delta by: * partial_history_cycles / total_history_cycles */ corr_raw = (u64)ktime_to_ns( ktime_sub(ts->sys_monoraw, history->raw)); ret = scale64_check_overflow(partial_history_cycles, total_history_cycles, &corr_raw); if (ret) return ret; /* * If there is a discontinuity in the history, scale monotonic raw * correction by: * mult(real)/mult(raw) yielding the realtime correction * Otherwise, calculate the realtime correction similar to monotonic * raw calculation */ if (discontinuity) { corr_real = mul_u64_u32_div (corr_raw, tk->tkr_mono.mult, tk->tkr_raw.mult); } else { corr_real = (u64)ktime_to_ns( ktime_sub(ts->sys_realtime, history->real)); ret = scale64_check_overflow(partial_history_cycles, total_history_cycles, &corr_real); if (ret) return ret; } /* Fixup monotonic raw and real time time values */ if (interp_forward) { ts->sys_monoraw = ktime_add_ns(history->raw, corr_raw); ts->sys_realtime = ktime_add_ns(history->real, corr_real); } else { ts->sys_monoraw = ktime_sub_ns(ts->sys_monoraw, corr_raw); ts->sys_realtime = ktime_sub_ns(ts->sys_realtime, corr_real); } return 0; } /* * timestamp_in_interval - true if ts is chronologically in [start, end] * * True if ts occurs chronologically at or after start, and before or at end. */ static bool timestamp_in_interval(u64 start, u64 end, u64 ts) { if (ts >= start && ts <= end) return true; if (start > end && (ts >= start || ts <= end)) return true; return false; } static bool convert_clock(u64 *val, u32 numerator, u32 denominator) { u64 rem, res; if (!numerator || !denominator) return false; res = div64_u64_rem(*val, denominator, &rem) * numerator; *val = res + div_u64(rem * numerator, denominator); return true; } static bool convert_base_to_cs(struct system_counterval_t *scv) { struct clocksource *cs = tk_core.timekeeper.tkr_mono.clock; struct clocksource_base *base; u32 num, den; /* The timestamp was taken from the time keeper clock source */ if (cs->id == scv->cs_id) return true; /* * Check whether cs_id matches the base clock. Prevent the compiler from * re-evaluating @base as the clocksource might change concurrently. */ base = READ_ONCE(cs->base); if (!base || base->id != scv->cs_id) return false; num = scv->use_nsecs ? cs->freq_khz : base->numerator; den = scv->use_nsecs ? USEC_PER_SEC : base->denominator; if (!convert_clock(&scv->cycles, num, den)) return false; scv->cycles += base->offset; return true; } static bool convert_cs_to_base(u64 *cycles, enum clocksource_ids base_id) { struct clocksource *cs = tk_core.timekeeper.tkr_mono.clock; struct clocksource_base *base; /* * Check whether base_id matches the base clock. Prevent the compiler from * re-evaluating @base as the clocksource might change concurrently. */ base = READ_ONCE(cs->base); if (!base || base->id != base_id) return false; *cycles -= base->offset; if (!convert_clock(cycles, base->denominator, base->numerator)) return false; return true; } static bool convert_ns_to_cs(u64 *delta) { struct tk_read_base *tkr = &tk_core.timekeeper.tkr_mono; if (BITS_TO_BYTES(fls64(*delta) + tkr->shift) >= sizeof(*delta)) return false; *delta = div_u64((*delta << tkr->shift) - tkr->xtime_nsec, tkr->mult); return true; } /** * ktime_real_to_base_clock() - Convert CLOCK_REALTIME timestamp to a base clock timestamp * @treal: CLOCK_REALTIME timestamp to convert * @base_id: base clocksource id * @cycles: pointer to store the converted base clock timestamp * * Converts a supplied, future realtime clock value to the corresponding base clock value. * * Return: true if the conversion is successful, false otherwise. */ bool ktime_real_to_base_clock(ktime_t treal, enum clocksource_ids base_id, u64 *cycles) { struct timekeeper *tk = &tk_core.timekeeper; unsigned int seq; u64 delta; do { seq = read_seqcount_begin(&tk_core.seq); if ((u64)treal < tk->tkr_mono.base_real) return false; delta = (u64)treal - tk->tkr_mono.base_real; if (!convert_ns_to_cs(&delta)) return false; *cycles = tk->tkr_mono.cycle_last + delta; if (!convert_cs_to_base(cycles, base_id)) return false; } while (read_seqcount_retry(&tk_core.seq, seq)); return true; } EXPORT_SYMBOL_GPL(ktime_real_to_base_clock); /** * get_device_system_crosststamp - Synchronously capture system/device timestamp * @get_time_fn: Callback to get simultaneous device time and * system counter from the device driver * @ctx: Context passed to get_time_fn() * @history_begin: Historical reference point used to interpolate system * time when counter provided by the driver is before the current interval * @xtstamp: Receives simultaneously captured system and device time * * Reads a timestamp from a device and correlates it to system time */ int get_device_system_crosststamp(int (*get_time_fn) (ktime_t *device_time, struct system_counterval_t *sys_counterval, void *ctx), void *ctx, struct system_time_snapshot *history_begin, struct system_device_crosststamp *xtstamp) { struct system_counterval_t system_counterval; struct timekeeper *tk = &tk_core.timekeeper; u64 cycles, now, interval_start; unsigned int clock_was_set_seq = 0; ktime_t base_real, base_raw; u64 nsec_real, nsec_raw; u8 cs_was_changed_seq; unsigned int seq; bool do_interp; int ret; do { seq = read_seqcount_begin(&tk_core.seq); /* * Try to synchronously capture device time and a system * counter value calling back into the device driver */ ret = get_time_fn(&xtstamp->device, &system_counterval, ctx); if (ret) return ret; /* * Verify that the clocksource ID associated with the captured * system counter value is the same as for the currently * installed timekeeper clocksource */ if (system_counterval.cs_id == CSID_GENERIC || !convert_base_to_cs(&system_counterval)) return -ENODEV; cycles = system_counterval.cycles; /* * Check whether the system counter value provided by the * device driver is on the current timekeeping interval. */ now = tk_clock_read(&tk->tkr_mono); interval_start = tk->tkr_mono.cycle_last; if (!timestamp_in_interval(interval_start, now, cycles)) { clock_was_set_seq = tk->clock_was_set_seq; cs_was_changed_seq = tk->cs_was_changed_seq; cycles = interval_start; do_interp = true; } else { do_interp = false; } base_real = ktime_add(tk->tkr_mono.base, tk_core.timekeeper.offs_real); base_raw = tk->tkr_raw.base; nsec_real = timekeeping_cycles_to_ns(&tk->tkr_mono, cycles); nsec_raw = timekeeping_cycles_to_ns(&tk->tkr_raw, cycles); } while (read_seqcount_retry(&tk_core.seq, seq)); xtstamp->sys_realtime = ktime_add_ns(base_real, nsec_real); xtstamp->sys_monoraw = ktime_add_ns(base_raw, nsec_raw); /* * Interpolate if necessary, adjusting back from the start of the * current interval */ if (do_interp) { u64 partial_history_cycles, total_history_cycles; bool discontinuity; /* * Check that the counter value is not before the provided * history reference and that the history doesn't cross a * clocksource change */ if (!history_begin || !timestamp_in_interval(history_begin->cycles, cycles, system_counterval.cycles) || history_begin->cs_was_changed_seq != cs_was_changed_seq) return -EINVAL; partial_history_cycles = cycles - system_counterval.cycles; total_history_cycles = cycles - history_begin->cycles; discontinuity = history_begin->clock_was_set_seq != clock_was_set_seq; ret = adjust_historical_crosststamp(history_begin, partial_history_cycles, total_history_cycles, discontinuity, xtstamp); if (ret) return ret; } return 0; } EXPORT_SYMBOL_GPL(get_device_system_crosststamp); /** * timekeeping_clocksource_has_base - Check whether the current clocksource * is based on given a base clock * @id: base clocksource ID * * Note: The return value is a snapshot which can become invalid right * after the function returns. * * Return: true if the timekeeper clocksource has a base clock with @id, * false otherwise */ bool timekeeping_clocksource_has_base(enum clocksource_ids id) { /* * This is a snapshot, so no point in using the sequence * count. Just prevent the compiler from re-evaluating @base as the * clocksource might change concurrently. */ struct clocksource_base *base = READ_ONCE(tk_core.timekeeper.tkr_mono.clock->base); return base ? base->id == id : false; } EXPORT_SYMBOL_GPL(timekeeping_clocksource_has_base); /** * do_settimeofday64 - Sets the time of day. * @ts: pointer to the timespec64 variable containing the new time * * Sets the time of day to the new time and update NTP and notify hrtimers */ int do_settimeofday64(const struct timespec64 *ts) { struct timespec64 ts_delta, xt; if (!timespec64_valid_settod(ts)) return -EINVAL; scoped_guard (raw_spinlock_irqsave, &tk_core.lock) { struct timekeeper *tks = &tk_core.shadow_timekeeper; timekeeping_forward_now(tks); xt = tk_xtime(tks); ts_delta = timespec64_sub(*ts, xt); if (timespec64_compare(&tks->wall_to_monotonic, &ts_delta) > 0) { timekeeping_restore_shadow(&tk_core); return -EINVAL; } tk_set_wall_to_mono(tks, timespec64_sub(tks->wall_to_monotonic, ts_delta)); tk_set_xtime(tks, ts); timekeeping_update_from_shadow(&tk_core, TK_UPDATE_ALL); } /* Signal hrtimers about time change */ clock_was_set(CLOCK_SET_WALL); audit_tk_injoffset(ts_delta); add_device_randomness(ts, sizeof(*ts)); return 0; } EXPORT_SYMBOL(do_settimeofday64); /** * timekeeping_inject_offset - Adds or subtracts from the current time. * @ts: Pointer to the timespec variable containing the offset * * Adds or subtracts an offset value from the current time. */ static int timekeeping_inject_offset(const struct timespec64 *ts) { if (ts->tv_nsec < 0 || ts->tv_nsec >= NSEC_PER_SEC) return -EINVAL; scoped_guard (raw_spinlock_irqsave, &tk_core.lock) { struct timekeeper *tks = &tk_core.shadow_timekeeper; struct timespec64 tmp; timekeeping_forward_now(tks); /* Make sure the proposed value is valid */ tmp = timespec64_add(tk_xtime(tks), *ts); if (timespec64_compare(&tks->wall_to_monotonic, ts) > 0 || !timespec64_valid_settod(&tmp)) { timekeeping_restore_shadow(&tk_core); return -EINVAL; } tk_xtime_add(tks, ts); tk_set_wall_to_mono(tks, timespec64_sub(tks->wall_to_monotonic, *ts)); timekeeping_update_from_shadow(&tk_core, TK_UPDATE_ALL); } /* Signal hrtimers about time change */ clock_was_set(CLOCK_SET_WALL); return 0; } /* * Indicates if there is an offset between the system clock and the hardware * clock/persistent clock/rtc. */ int persistent_clock_is_local; /* * Adjust the time obtained from the CMOS to be UTC time instead of * local time. * * This is ugly, but preferable to the alternatives. Otherwise we * would either need to write a program to do it in /etc/rc (and risk * confusion if the program gets run more than once; it would also be * hard to make the program warp the clock precisely n hours) or * compile in the timezone information into the kernel. Bad, bad.... * * - TYT, 1992-01-01 * * The best thing to do is to keep the CMOS clock in universal time (UTC) * as real UNIX machines always do it. This avoids all headaches about * daylight saving times and warping kernel clocks. */ void timekeeping_warp_clock(void) { if (sys_tz.tz_minuteswest != 0) { struct timespec64 adjust; persistent_clock_is_local = 1; adjust.tv_sec = sys_tz.tz_minuteswest * 60; adjust.tv_nsec = 0; timekeeping_inject_offset(&adjust); } } /* * __timekeeping_set_tai_offset - Sets the TAI offset from UTC and monotonic */ static void __timekeeping_set_tai_offset(struct timekeeper *tk, s32 tai_offset) { tk->tai_offset = tai_offset; tk->offs_tai = ktime_add(tk->offs_real, ktime_set(tai_offset, 0)); } /* * change_clocksource - Swaps clocksources if a new one is available * * Accumulates current time interval and initializes new clocksource */ static int change_clocksource(void *data) { struct clocksource *new = data, *old = NULL; /* * If the clocksource is in a module, get a module reference. * Succeeds for built-in code (owner == NULL) as well. Abort if the * reference can't be acquired. */ if (!try_module_get(new->owner)) return 0; /* Abort if the device can't be enabled */ if (new->enable && new->enable(new) != 0) { module_put(new->owner); return 0; } scoped_guard (raw_spinlock_irqsave, &tk_core.lock) { struct timekeeper *tks = &tk_core.shadow_timekeeper; timekeeping_forward_now(tks); old = tks->tkr_mono.clock; tk_setup_internals(tks, new); timekeeping_update_from_shadow(&tk_core, TK_UPDATE_ALL); } if (old) { if (old->disable) old->disable(old); module_put(old->owner); } return 0; } /** * timekeeping_notify - Install a new clock source * @clock: pointer to the clock source * * This function is called from clocksource.c after a new, better clock * source has been registered. The caller holds the clocksource_mutex. */ int timekeeping_notify(struct clocksource *clock) { struct timekeeper *tk = &tk_core.timekeeper; if (tk->tkr_mono.clock == clock) return 0; stop_machine(change_clocksource, clock, NULL); tick_clock_notify(); return tk->tkr_mono.clock == clock ? 0 : -1; } /** * ktime_get_raw_ts64 - Returns the raw monotonic time in a timespec * @ts: pointer to the timespec64 to be set * * Returns the raw monotonic time (completely un-modified by ntp) */ void ktime_get_raw_ts64(struct timespec64 *ts) { struct timekeeper *tk = &tk_core.timekeeper; unsigned int seq; u64 nsecs; do { seq = read_seqcount_begin(&tk_core.seq); ts->tv_sec = tk->raw_sec; nsecs = timekeeping_get_ns(&tk->tkr_raw); } while (read_seqcount_retry(&tk_core.seq, seq)); ts->tv_nsec = 0; timespec64_add_ns(ts, nsecs); } EXPORT_SYMBOL(ktime_get_raw_ts64); /** * timekeeping_valid_for_hres - Check if timekeeping is suitable for hres */ int timekeeping_valid_for_hres(void) { struct timekeeper *tk = &tk_core.timekeeper; unsigned int seq; int ret; do { seq = read_seqcount_begin(&tk_core.seq); ret = tk->tkr_mono.clock->flags & CLOCK_SOURCE_VALID_FOR_HRES; } while (read_seqcount_retry(&tk_core.seq, seq)); return ret; } /** * timekeeping_max_deferment - Returns max time the clocksource can be deferred */ u64 timekeeping_max_deferment(void) { struct timekeeper *tk = &tk_core.timekeeper; unsigned int seq; u64 ret; do { seq = read_seqcount_begin(&tk_core.seq); ret = tk->tkr_mono.clock->max_idle_ns; } while (read_seqcount_retry(&tk_core.seq, seq)); return ret; } /** * read_persistent_clock64 - Return time from the persistent clock. * @ts: Pointer to the storage for the readout value * * Weak dummy function for arches that do not yet support it. * Reads the time from the battery backed persistent clock. * Returns a timespec with tv_sec=0 and tv_nsec=0 if unsupported. * * XXX - Do be sure to remove it once all arches implement it. */ void __weak read_persistent_clock64(struct timespec64 *ts) { ts->tv_sec = 0; ts->tv_nsec = 0; } /** * read_persistent_wall_and_boot_offset - Read persistent clock, and also offset * from the boot. * @wall_time: current time as returned by persistent clock * @boot_offset: offset that is defined as wall_time - boot_time * * Weak dummy function for arches that do not yet support it. * * The default function calculates offset based on the current value of * local_clock(). This way architectures that support sched_clock() but don't * support dedicated boot time clock will provide the best estimate of the * boot time. */ void __weak __init read_persistent_wall_and_boot_offset(struct timespec64 *wall_time, struct timespec64 *boot_offset) { read_persistent_clock64(wall_time); *boot_offset = ns_to_timespec64(local_clock()); } static __init void tkd_basic_setup(struct tk_data *tkd) { raw_spin_lock_init(&tkd->lock); seqcount_raw_spinlock_init(&tkd->seq, &tkd->lock); } /* * Flag reflecting whether timekeeping_resume() has injected sleeptime. * * The flag starts of false and is only set when a suspend reaches * timekeeping_suspend(), timekeeping_resume() sets it to false when the * timekeeper clocksource is not stopping across suspend and has been * used to update sleep time. If the timekeeper clocksource has stopped * then the flag stays true and is used by the RTC resume code to decide * whether sleeptime must be injected and if so the flag gets false then. * * If a suspend fails before reaching timekeeping_resume() then the flag * stays false and prevents erroneous sleeptime injection. */ static bool suspend_timing_needed; /* Flag for if there is a persistent clock on this platform */ static bool persistent_clock_exists; /* * timekeeping_init - Initializes the clocksource and common timekeeping values */ void __init timekeeping_init(void) { struct timespec64 wall_time, boot_offset, wall_to_mono; struct timekeeper *tks = &tk_core.shadow_timekeeper; struct clocksource *clock; tkd_basic_setup(&tk_core); read_persistent_wall_and_boot_offset(&wall_time, &boot_offset); if (timespec64_valid_settod(&wall_time) && timespec64_to_ns(&wall_time) > 0) { persistent_clock_exists = true; } else if (timespec64_to_ns(&wall_time) != 0) { pr_warn("Persistent clock returned invalid value"); wall_time = (struct timespec64){0}; } if (timespec64_compare(&wall_time, &boot_offset) < 0) boot_offset = (struct timespec64){0}; /* * We want set wall_to_mono, so the following is true: * wall time + wall_to_mono = boot time */ wall_to_mono = timespec64_sub(boot_offset, wall_time); guard(raw_spinlock_irqsave)(&tk_core.lock); ntp_init(); clock = clocksource_default_clock(); if (clock->enable) clock->enable(clock); tk_setup_internals(tks, clock); tk_set_xtime(tks, &wall_time); tks->raw_sec = 0; tk_set_wall_to_mono(tks, wall_to_mono); timekeeping_update_from_shadow(&tk_core, TK_CLOCK_WAS_SET); } /* time in seconds when suspend began for persistent clock */ static struct timespec64 timekeeping_suspend_time; /** * __timekeeping_inject_sleeptime - Internal function to add sleep interval * @tk: Pointer to the timekeeper to be updated * @delta: Pointer to the delta value in timespec64 format * * Takes a timespec offset measuring a suspend interval and properly * adds the sleep offset to the timekeeping variables. */ static void __timekeeping_inject_sleeptime(struct timekeeper *tk, const struct timespec64 *delta) { if (!timespec64_valid_strict(delta)) { printk_deferred(KERN_WARNING "__timekeeping_inject_sleeptime: Invalid " "sleep delta value!\n"); return; } tk_xtime_add(tk, delta); tk_set_wall_to_mono(tk, timespec64_sub(tk->wall_to_monotonic, *delta)); tk_update_sleep_time(tk, timespec64_to_ktime(*delta)); tk_debug_account_sleep_time(delta); } #if defined(CONFIG_PM_SLEEP) && defined(CONFIG_RTC_HCTOSYS_DEVICE) /* * We have three kinds of time sources to use for sleep time * injection, the preference order is: * 1) non-stop clocksource * 2) persistent clock (ie: RTC accessible when irqs are off) * 3) RTC * * 1) and 2) are used by timekeeping, 3) by RTC subsystem. * If system has neither 1) nor 2), 3) will be used finally. * * * If timekeeping has injected sleeptime via either 1) or 2), * 3) becomes needless, so in this case we don't need to call * rtc_resume(), and this is what timekeeping_rtc_skipresume() * means. */ bool timekeeping_rtc_skipresume(void) { return !suspend_timing_needed; } /* * 1) can be determined whether to use or not only when doing * timekeeping_resume() which is invoked after rtc_suspend(), * so we can't skip rtc_suspend() surely if system has 1). * * But if system has 2), 2) will definitely be used, so in this * case we don't need to call rtc_suspend(), and this is what * timekeeping_rtc_skipsuspend() means. */ bool timekeeping_rtc_skipsuspend(void) { return persistent_clock_exists; } /** * timekeeping_inject_sleeptime64 - Adds suspend interval to timeekeeping values * @delta: pointer to a timespec64 delta value * * This hook is for architectures that cannot support read_persistent_clock64 * because their RTC/persistent clock is only accessible when irqs are enabled. * and also don't have an effective nonstop clocksource. * * This function should only be called by rtc_resume(), and allows * a suspend offset to be injected into the timekeeping values. */ void timekeeping_inject_sleeptime64(const struct timespec64 *delta) { scoped_guard(raw_spinlock_irqsave, &tk_core.lock) { struct timekeeper *tks = &tk_core.shadow_timekeeper; suspend_timing_needed = false; timekeeping_forward_now(tks); __timekeeping_inject_sleeptime(tks, delta); timekeeping_update_from_shadow(&tk_core, TK_UPDATE_ALL); } /* Signal hrtimers about time change */ clock_was_set(CLOCK_SET_WALL | CLOCK_SET_BOOT); } #endif /** * timekeeping_resume - Resumes the generic timekeeping subsystem. */ void timekeeping_resume(void) { struct timekeeper *tks = &tk_core.shadow_timekeeper; struct clocksource *clock = tks->tkr_mono.clock; struct timespec64 ts_new, ts_delta; bool inject_sleeptime = false; u64 cycle_now, nsec; unsigned long flags; read_persistent_clock64(&ts_new); clockevents_resume(); clocksource_resume(); raw_spin_lock_irqsave(&tk_core.lock, flags); /* * After system resumes, we need to calculate the suspended time and * compensate it for the OS time. There are 3 sources that could be * used: Nonstop clocksource during suspend, persistent clock and rtc * device. * * One specific platform may have 1 or 2 or all of them, and the * preference will be: * suspend-nonstop clocksource -> persistent clock -> rtc * The less preferred source will only be tried if there is no better * usable source. The rtc part is handled separately in rtc core code. */ cycle_now = tk_clock_read(&tks->tkr_mono); nsec = clocksource_stop_suspend_timing(clock, cycle_now); if (nsec > 0) { ts_delta = ns_to_timespec64(nsec); inject_sleeptime = true; } else if (timespec64_compare(&ts_new, &timekeeping_suspend_time) > 0) { ts_delta = timespec64_sub(ts_new, timekeeping_suspend_time); inject_sleeptime = true; } if (inject_sleeptime) { suspend_timing_needed = false; __timekeeping_inject_sleeptime(tks, &ts_delta); } /* Re-base the last cycle value */ tks->tkr_mono.cycle_last = cycle_now; tks->tkr_raw.cycle_last = cycle_now; tks->ntp_error = 0; timekeeping_suspended = 0; timekeeping_update_from_shadow(&tk_core, TK_CLOCK_WAS_SET); raw_spin_unlock_irqrestore(&tk_core.lock, flags); touch_softlockup_watchdog(); /* Resume the clockevent device(s) and hrtimers */ tick_resume(); /* Notify timerfd as resume is equivalent to clock_was_set() */ timerfd_resume(); } int timekeeping_suspend(void) { struct timekeeper *tks = &tk_core.shadow_timekeeper; struct timespec64 delta, delta_delta; static struct timespec64 old_delta; struct clocksource *curr_clock; unsigned long flags; u64 cycle_now; read_persistent_clock64(&timekeeping_suspend_time); /* * On some systems the persistent_clock can not be detected at * timekeeping_init by its return value, so if we see a valid * value returned, update the persistent_clock_exists flag. */ if (timekeeping_suspend_time.tv_sec || timekeeping_suspend_time.tv_nsec) persistent_clock_exists = true; suspend_timing_needed = true; raw_spin_lock_irqsave(&tk_core.lock, flags); timekeeping_forward_now(tks); timekeeping_suspended = 1; /* * Since we've called forward_now, cycle_last stores the value * just read from the current clocksource. Save this to potentially * use in suspend timing. */ curr_clock = tks->tkr_mono.clock; cycle_now = tks->tkr_mono.cycle_last; clocksource_start_suspend_timing(curr_clock, cycle_now); if (persistent_clock_exists) { /* * To avoid drift caused by repeated suspend/resumes, * which each can add ~1 second drift error, * try to compensate so the difference in system time * and persistent_clock time stays close to constant. */ delta = timespec64_sub(tk_xtime(tks), timekeeping_suspend_time); delta_delta = timespec64_sub(delta, old_delta); if (abs(delta_delta.tv_sec) >= 2) { /* * if delta_delta is too large, assume time correction * has occurred and set old_delta to the current delta. */ old_delta = delta; } else { /* Otherwise try to adjust old_system to compensate */ timekeeping_suspend_time = timespec64_add(timekeeping_suspend_time, delta_delta); } } timekeeping_update_from_shadow(&tk_core, 0); halt_fast_timekeeper(tks); raw_spin_unlock_irqrestore(&tk_core.lock, flags); tick_suspend(); clocksource_suspend(); clockevents_suspend(); return 0; } /* sysfs resume/suspend bits for timekeeping */ static struct syscore_ops timekeeping_syscore_ops = { .resume = timekeeping_resume, .suspend = timekeeping_suspend, }; static int __init timekeeping_init_ops(void) { register_syscore_ops(&timekeeping_syscore_ops); return 0; } device_initcall(timekeeping_init_ops); /* * Apply a multiplier adjustment to the timekeeper */ static __always_inline void timekeeping_apply_adjustment(struct timekeeper *tk, s64 offset, s32 mult_adj) { s64 interval = tk->cycle_interval; if (mult_adj == 0) { return; } else if (mult_adj == -1) { interval = -interval; offset = -offset; } else if (mult_adj != 1) { interval *= mult_adj; offset *= mult_adj; } /* * So the following can be confusing. * * To keep things simple, lets assume mult_adj == 1 for now. * * When mult_adj != 1, remember that the interval and offset values * have been appropriately scaled so the math is the same. * * The basic idea here is that we're increasing the multiplier * by one, this causes the xtime_interval to be incremented by * one cycle_interval. This is because: * xtime_interval = cycle_interval * mult * So if mult is being incremented by one: * xtime_interval = cycle_interval * (mult + 1) * Its the same as: * xtime_interval = (cycle_interval * mult) + cycle_interval * Which can be shortened to: * xtime_interval += cycle_interval * * So offset stores the non-accumulated cycles. Thus the current * time (in shifted nanoseconds) is: * now = (offset * adj) + xtime_nsec * Now, even though we're adjusting the clock frequency, we have * to keep time consistent. In other words, we can't jump back * in time, and we also want to avoid jumping forward in time. * * So given the same offset value, we need the time to be the same * both before and after the freq adjustment. * now = (offset * adj_1) + xtime_nsec_1 * now = (offset * adj_2) + xtime_nsec_2 * So: * (offset * adj_1) + xtime_nsec_1 = * (offset * adj_2) + xtime_nsec_2 * And we know: * adj_2 = adj_1 + 1 * So: * (offset * adj_1) + xtime_nsec_1 = * (offset * (adj_1+1)) + xtime_nsec_2 * (offset * adj_1) + xtime_nsec_1 = * (offset * adj_1) + offset + xtime_nsec_2 * Canceling the sides: * xtime_nsec_1 = offset + xtime_nsec_2 * Which gives us: * xtime_nsec_2 = xtime_nsec_1 - offset * Which simplifies to: * xtime_nsec -= offset */ if ((mult_adj > 0) && (tk->tkr_mono.mult + mult_adj < mult_adj)) { /* NTP adjustment caused clocksource mult overflow */ WARN_ON_ONCE(1); return; } tk->tkr_mono.mult += mult_adj; tk->xtime_interval += interval; tk->tkr_mono.xtime_nsec -= offset; } /* * Adjust the timekeeper's multiplier to the correct frequency * and also to reduce the accumulated error value. */ static void timekeeping_adjust(struct timekeeper *tk, s64 offset) { u64 ntp_tl = ntp_tick_length(); u32 mult; /* * Determine the multiplier from the current NTP tick length. * Avoid expensive division when the tick length doesn't change. */ if (likely(tk->ntp_tick == ntp_tl)) { mult = tk->tkr_mono.mult - tk->ntp_err_mult; } else { tk->ntp_tick = ntp_tl; mult = div64_u64((tk->ntp_tick >> tk->ntp_error_shift) - tk->xtime_remainder, tk->cycle_interval); } /* * If the clock is behind the NTP time, increase the multiplier by 1 * to catch up with it. If it's ahead and there was a remainder in the * tick division, the clock will slow down. Otherwise it will stay * ahead until the tick length changes to a non-divisible value. */ tk->ntp_err_mult = tk->ntp_error > 0 ? 1 : 0; mult += tk->ntp_err_mult; timekeeping_apply_adjustment(tk, offset, mult - tk->tkr_mono.mult); if (unlikely(tk->tkr_mono.clock->maxadj && (abs(tk->tkr_mono.mult - tk->tkr_mono.clock->mult) > tk->tkr_mono.clock->maxadj))) { printk_once(KERN_WARNING "Adjusting %s more than 11%% (%ld vs %ld)\n", tk->tkr_mono.clock->name, (long)tk->tkr_mono.mult, (long)tk->tkr_mono.clock->mult + tk->tkr_mono.clock->maxadj); } /* * It may be possible that when we entered this function, xtime_nsec * was very small. Further, if we're slightly speeding the clocksource * in the code above, its possible the required corrective factor to * xtime_nsec could cause it to underflow. * * Now, since we have already accumulated the second and the NTP * subsystem has been notified via second_overflow(), we need to skip * the next update. */ if (unlikely((s64)tk->tkr_mono.xtime_nsec < 0)) { tk->tkr_mono.xtime_nsec += (u64)NSEC_PER_SEC << tk->tkr_mono.shift; tk->xtime_sec--; tk->skip_second_overflow = 1; } } /* * accumulate_nsecs_to_secs - Accumulates nsecs into secs * * Helper function that accumulates the nsecs greater than a second * from the xtime_nsec field to the xtime_secs field. * It also calls into the NTP code to handle leapsecond processing. */ static inline unsigned int accumulate_nsecs_to_secs(struct timekeeper *tk) { u64 nsecps = (u64)NSEC_PER_SEC << tk->tkr_mono.shift; unsigned int clock_set = 0; while (tk->tkr_mono.xtime_nsec >= nsecps) { int leap; tk->tkr_mono.xtime_nsec -= nsecps; tk->xtime_sec++; /* * Skip NTP update if this second was accumulated before, * i.e. xtime_nsec underflowed in timekeeping_adjust() */ if (unlikely(tk->skip_second_overflow)) { tk->skip_second_overflow = 0; continue; } /* Figure out if its a leap sec and apply if needed */ leap = second_overflow(tk->xtime_sec); if (unlikely(leap)) { struct timespec64 ts; tk->xtime_sec += leap; ts.tv_sec = leap; ts.tv_nsec = 0; tk_set_wall_to_mono(tk, timespec64_sub(tk->wall_to_monotonic, ts)); __timekeeping_set_tai_offset(tk, tk->tai_offset - leap); clock_set = TK_CLOCK_WAS_SET; } } return clock_set; } /* * logarithmic_accumulation - shifted accumulation of cycles * * This functions accumulates a shifted interval of cycles into * a shifted interval nanoseconds. Allows for O(log) accumulation * loop. * * Returns the unconsumed cycles. */ static u64 logarithmic_accumulation(struct timekeeper *tk, u64 offset, u32 shift, unsigned int *clock_set) { u64 interval = tk->cycle_interval << shift; u64 snsec_per_sec; /* If the offset is smaller than a shifted interval, do nothing */ if (offset < interval) return offset; /* Accumulate one shifted interval */ offset -= interval; tk->tkr_mono.cycle_last += interval; tk->tkr_raw.cycle_last += interval; tk->tkr_mono.xtime_nsec += tk->xtime_interval << shift; *clock_set |= accumulate_nsecs_to_secs(tk); /* Accumulate raw time */ tk->tkr_raw.xtime_nsec += tk->raw_interval << shift; snsec_per_sec = (u64)NSEC_PER_SEC << tk->tkr_raw.shift; while (tk->tkr_raw.xtime_nsec >= snsec_per_sec) { tk->tkr_raw.xtime_nsec -= snsec_per_sec; tk->raw_sec++; } /* Accumulate error between NTP and clock interval */ tk->ntp_error += tk->ntp_tick << shift; tk->ntp_error -= (tk->xtime_interval + tk->xtime_remainder) << (tk->ntp_error_shift + shift); return offset; } /* * timekeeping_advance - Updates the timekeeper to the current time and * current NTP tick length */ static bool timekeeping_advance(enum timekeeping_adv_mode mode) { struct timekeeper *tk = &tk_core.shadow_timekeeper; struct timekeeper *real_tk = &tk_core.timekeeper; unsigned int clock_set = 0; int shift = 0, maxshift; u64 offset; guard(raw_spinlock_irqsave)(&tk_core.lock); /* Make sure we're fully resumed: */ if (unlikely(timekeeping_suspended)) return false; offset = clocksource_delta(tk_clock_read(&tk->tkr_mono), tk->tkr_mono.cycle_last, tk->tkr_mono.mask, tk->tkr_mono.clock->max_raw_delta); /* Check if there's really nothing to do */ if (offset < real_tk->cycle_interval && mode == TK_ADV_TICK) return false; /* * With NO_HZ we may have to accumulate many cycle_intervals * (think "ticks") worth of time at once. To do this efficiently, * we calculate the largest doubling multiple of cycle_intervals * that is smaller than the offset. We then accumulate that * chunk in one go, and then try to consume the next smaller * doubled multiple. */ shift = ilog2(offset) - ilog2(tk->cycle_interval); shift = max(0, shift); /* Bound shift to one less than what overflows tick_length */ maxshift = (64 - (ilog2(ntp_tick_length())+1)) - 1; shift = min(shift, maxshift); while (offset >= tk->cycle_interval) { offset = logarithmic_accumulation(tk, offset, shift, &clock_set); if (offset < tk->cycle_interval<<shift) shift--; } /* Adjust the multiplier to correct NTP error */ timekeeping_adjust(tk, offset); /* * Finally, make sure that after the rounding * xtime_nsec isn't larger than NSEC_PER_SEC */ clock_set |= accumulate_nsecs_to_secs(tk); timekeeping_update_from_shadow(&tk_core, clock_set); return !!clock_set; } /** * update_wall_time - Uses the current clocksource to increment the wall time * */ void update_wall_time(void) { if (timekeeping_advance(TK_ADV_TICK)) clock_was_set_delayed(); } /** * getboottime64 - Return the real time of system boot. * @ts: pointer to the timespec64 to be set * * Returns the wall-time of boot in a timespec64. * * This is based on the wall_to_monotonic offset and the total suspend * time. Calls to settimeofday will affect the value returned (which * basically means that however wrong your real time clock is at boot time, * you get the right time here). */ void getboottime64(struct timespec64 *ts) { struct timekeeper *tk = &tk_core.timekeeper; ktime_t t = ktime_sub(tk->offs_real, tk->offs_boot); *ts = ktime_to_timespec64(t); } EXPORT_SYMBOL_GPL(getboottime64); void ktime_get_coarse_real_ts64(struct timespec64 *ts) { struct timekeeper *tk = &tk_core.timekeeper; unsigned int seq; do { seq = read_seqcount_begin(&tk_core.seq); *ts = tk_xtime(tk); } while (read_seqcount_retry(&tk_core.seq, seq)); } EXPORT_SYMBOL(ktime_get_coarse_real_ts64); /** * ktime_get_coarse_real_ts64_mg - return latter of coarse grained time or floor * @ts: timespec64 to be filled * * Fetch the global mg_floor value, convert it to realtime and compare it * to the current coarse-grained time. Fill @ts with whichever is * latest. Note that this is a filesystem-specific interface and should be * avoided outside of that context. */ void ktime_get_coarse_real_ts64_mg(struct timespec64 *ts) { struct timekeeper *tk = &tk_core.timekeeper; u64 floor = atomic64_read(&mg_floor); ktime_t f_real, offset, coarse; unsigned int seq; do { seq = read_seqcount_begin(&tk_core.seq); *ts = tk_xtime(tk); offset = tk_core.timekeeper.offs_real; } while (read_seqcount_retry(&tk_core.seq, seq)); coarse = timespec64_to_ktime(*ts); f_real = ktime_add(floor, offset); if (ktime_after(f_real, coarse)) *ts = ktime_to_timespec64(f_real); } /** * ktime_get_real_ts64_mg - attempt to update floor value and return result * @ts: pointer to the timespec to be set * * Get a monotonic fine-grained time value and attempt to swap it into * mg_floor. If that succeeds then accept the new floor value. If it fails * then another task raced in during the interim time and updated the * floor. Since any update to the floor must be later than the previous * floor, either outcome is acceptable. * * Typically this will be called after calling ktime_get_coarse_real_ts64_mg(), * and determining that the resulting coarse-grained timestamp did not effect * a change in ctime. Any more recent floor value would effect a change to * ctime, so there is no need to retry the atomic64_try_cmpxchg() on failure. * * @ts will be filled with the latest floor value, regardless of the outcome of * the cmpxchg. Note that this is a filesystem specific interface and should be * avoided outside of that context. */ void ktime_get_real_ts64_mg(struct timespec64 *ts) { struct timekeeper *tk = &tk_core.timekeeper; ktime_t old = atomic64_read(&mg_floor); ktime_t offset, mono; unsigned int seq; u64 nsecs; do { seq = read_seqcount_begin(&tk_core.seq); ts->tv_sec = tk->xtime_sec; mono = tk->tkr_mono.base; nsecs = timekeeping_get_ns(&tk->tkr_mono); offset = tk_core.timekeeper.offs_real; } while (read_seqcount_retry(&tk_core.seq, seq)); mono = ktime_add_ns(mono, nsecs); /* * Attempt to update the floor with the new time value. As any * update must be later then the existing floor, and would effect * a change to ctime from the perspective of the current task, * accept the resulting floor value regardless of the outcome of * the swap. */ if (atomic64_try_cmpxchg(&mg_floor, &old, mono)) { ts->tv_nsec = 0; timespec64_add_ns(ts, nsecs); timekeeping_inc_mg_floor_swaps(); } else { /* * Another task changed mg_floor since "old" was fetched. * "old" has been updated with the latest value of "mg_floor". * That value is newer than the previous floor value, which * is enough to effect a change to ctime. Accept it. */ *ts = ktime_to_timespec64(ktime_add(old, offset)); } } void ktime_get_coarse_ts64(struct timespec64 *ts) { struct timekeeper *tk = &tk_core.timekeeper; struct timespec64 now, mono; unsigned int seq; do { seq = read_seqcount_begin(&tk_core.seq); now = tk_xtime(tk); mono = tk->wall_to_monotonic; } while (read_seqcount_retry(&tk_core.seq, seq)); set_normalized_timespec64(ts, now.tv_sec + mono.tv_sec, now.tv_nsec + mono.tv_nsec); } EXPORT_SYMBOL(ktime_get_coarse_ts64); /* * Must hold jiffies_lock */ void do_timer(unsigned long ticks) { jiffies_64 += ticks; calc_global_load(); } /** * ktime_get_update_offsets_now - hrtimer helper * @cwsseq: pointer to check and store the clock was set sequence number * @offs_real: pointer to storage for monotonic -> realtime offset * @offs_boot: pointer to storage for monotonic -> boottime offset * @offs_tai: pointer to storage for monotonic -> clock tai offset * * Returns current monotonic time and updates the offsets if the * sequence number in @cwsseq and timekeeper.clock_was_set_seq are * different. * * Called from hrtimer_interrupt() or retrigger_next_event() */ ktime_t ktime_get_update_offsets_now(unsigned int *cwsseq, ktime_t *offs_real, ktime_t *offs_boot, ktime_t *offs_tai) { struct timekeeper *tk = &tk_core.timekeeper; unsigned int seq; ktime_t base; u64 nsecs; do { seq = read_seqcount_begin(&tk_core.seq); base = tk->tkr_mono.base; nsecs = timekeeping_get_ns(&tk->tkr_mono); base = ktime_add_ns(base, nsecs); if (*cwsseq != tk->clock_was_set_seq) { *cwsseq = tk->clock_was_set_seq; *offs_real = tk->offs_real; *offs_boot = tk->offs_boot; *offs_tai = tk->offs_tai; } /* Handle leapsecond insertion adjustments */ if (unlikely(base >= tk->next_leap_ktime)) *offs_real = ktime_sub(tk->offs_real, ktime_set(1, 0)); } while (read_seqcount_retry(&tk_core.seq, seq)); return base; } /* * timekeeping_validate_timex - Ensures the timex is ok for use in do_adjtimex */ static int timekeeping_validate_timex(const struct __kernel_timex *txc) { if (txc->modes & ADJ_ADJTIME) { /* singleshot must not be used with any other mode bits */ if (!(txc->modes & ADJ_OFFSET_SINGLESHOT)) return -EINVAL; if (!(txc->modes & ADJ_OFFSET_READONLY) && !capable(CAP_SYS_TIME)) return -EPERM; } else { /* In order to modify anything, you gotta be super-user! */ if (txc->modes && !capable(CAP_SYS_TIME)) return -EPERM; /* * if the quartz is off by more than 10% then * something is VERY wrong! */ if (txc->modes & ADJ_TICK && (txc->tick < 900000/USER_HZ || txc->tick > 1100000/USER_HZ)) return -EINVAL; } if (txc->modes & ADJ_SETOFFSET) { /* In order to inject time, you gotta be super-user! */ if (!capable(CAP_SYS_TIME)) return -EPERM; /* * Validate if a timespec/timeval used to inject a time * offset is valid. Offsets can be positive or negative, so * we don't check tv_sec. The value of the timeval/timespec * is the sum of its fields,but *NOTE*: * The field tv_usec/tv_nsec must always be non-negative and * we can't have more nanoseconds/microseconds than a second. */ if (txc->time.tv_usec < 0) return -EINVAL; if (txc->modes & ADJ_NANO) { if (txc->time.tv_usec >= NSEC_PER_SEC) return -EINVAL; } else { if (txc->time.tv_usec >= USEC_PER_SEC) return -EINVAL; } } /* * Check for potential multiplication overflows that can * only happen on 64-bit systems: */ if ((txc->modes & ADJ_FREQUENCY) && (BITS_PER_LONG == 64)) { if (LLONG_MIN / PPM_SCALE > txc->freq) return -EINVAL; if (LLONG_MAX / PPM_SCALE < txc->freq) return -EINVAL; } return 0; } /** * random_get_entropy_fallback - Returns the raw clock source value, * used by random.c for platforms with no valid random_get_entropy(). */ unsigned long random_get_entropy_fallback(void) { struct tk_read_base *tkr = &tk_core.timekeeper.tkr_mono; struct clocksource *clock = READ_ONCE(tkr->clock); if (unlikely(timekeeping_suspended || !clock)) return 0; return clock->read(clock); } EXPORT_SYMBOL_GPL(random_get_entropy_fallback); /** * do_adjtimex() - Accessor function to NTP __do_adjtimex function * @txc: Pointer to kernel_timex structure containing NTP parameters */ int do_adjtimex(struct __kernel_timex *txc) { struct audit_ntp_data ad; bool offset_set = false; bool clock_set = false; struct timespec64 ts; int ret; /* Validate the data before disabling interrupts */ ret = timekeeping_validate_timex(txc); if (ret) return ret; add_device_randomness(txc, sizeof(*txc)); if (txc->modes & ADJ_SETOFFSET) { struct timespec64 delta; delta.tv_sec = txc->time.tv_sec; delta.tv_nsec = txc->time.tv_usec; if (!(txc->modes & ADJ_NANO)) delta.tv_nsec *= 1000; ret = timekeeping_inject_offset(&delta); if (ret) return ret; offset_set = delta.tv_sec != 0; audit_tk_injoffset(delta); } audit_ntp_init(&ad); ktime_get_real_ts64(&ts); add_device_randomness(&ts, sizeof(ts)); scoped_guard (raw_spinlock_irqsave, &tk_core.lock) { struct timekeeper *tks = &tk_core.shadow_timekeeper; s32 orig_tai, tai; orig_tai = tai = tks->tai_offset; ret = __do_adjtimex(txc, &ts, &tai, &ad); if (tai != orig_tai) { __timekeeping_set_tai_offset(tks, tai); timekeeping_update_from_shadow(&tk_core, TK_CLOCK_WAS_SET); clock_set = true; } else { tk_update_leap_state_all(&tk_core); } } audit_ntp_log(&ad); /* Update the multiplier immediately if frequency was set directly */ if (txc->modes & (ADJ_FREQUENCY | ADJ_TICK)) clock_set |= timekeeping_advance(TK_ADV_FREQ); if (clock_set) clock_was_set(CLOCK_SET_WALL); ntp_notify_cmos_timer(offset_set); return ret; } #ifdef CONFIG_NTP_PPS /** * hardpps() - Accessor function to NTP __hardpps function * @phase_ts: Pointer to timespec64 structure representing phase timestamp * @raw_ts: Pointer to timespec64 structure representing raw timestamp */ void hardpps(const struct timespec64 *phase_ts, const struct timespec64 *raw_ts) { guard(raw_spinlock_irqsave)(&tk_core.lock); __hardpps(phase_ts, raw_ts); } EXPORT_SYMBOL(hardpps); #endif /* CONFIG_NTP_PPS */ |
| 2913 | 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 | /* SPDX-License-Identifier: GPL-2.0-or-later */ /* * include/net/dsa.h - Driver for Distributed Switch Architecture switch chips * Copyright (c) 2008-2009 Marvell Semiconductor */ #ifndef __LINUX_NET_DSA_H #define __LINUX_NET_DSA_H #include <linux/if.h> #include <linux/if_ether.h> #include <linux/list.h> #include <linux/notifier.h> #include <linux/timer.h> #include <linux/workqueue.h> #include <linux/of.h> #include <linux/ethtool.h> #include <linux/net_tstamp.h> #include <linux/phy.h> #include <linux/platform_data/dsa.h> #include <linux/phylink.h> #include <net/devlink.h> #include <net/switchdev.h> struct dsa_8021q_context; struct tc_action; #define DSA_TAG_PROTO_NONE_VALUE 0 #define DSA_TAG_PROTO_BRCM_VALUE 1 #define DSA_TAG_PROTO_BRCM_PREPEND_VALUE 2 #define DSA_TAG_PROTO_DSA_VALUE 3 #define DSA_TAG_PROTO_EDSA_VALUE 4 #define DSA_TAG_PROTO_GSWIP_VALUE 5 #define DSA_TAG_PROTO_KSZ9477_VALUE 6 #define DSA_TAG_PROTO_KSZ9893_VALUE 7 #define DSA_TAG_PROTO_LAN9303_VALUE 8 #define DSA_TAG_PROTO_MTK_VALUE 9 #define DSA_TAG_PROTO_QCA_VALUE 10 #define DSA_TAG_PROTO_TRAILER_VALUE 11 #define DSA_TAG_PROTO_8021Q_VALUE 12 #define DSA_TAG_PROTO_SJA1105_VALUE 13 #define DSA_TAG_PROTO_KSZ8795_VALUE 14 #define DSA_TAG_PROTO_OCELOT_VALUE 15 #define DSA_TAG_PROTO_AR9331_VALUE 16 #define DSA_TAG_PROTO_RTL4_A_VALUE 17 #define DSA_TAG_PROTO_HELLCREEK_VALUE 18 #define DSA_TAG_PROTO_XRS700X_VALUE 19 #define DSA_TAG_PROTO_OCELOT_8021Q_VALUE 20 #define DSA_TAG_PROTO_SEVILLE_VALUE 21 #define DSA_TAG_PROTO_BRCM_LEGACY_VALUE 22 #define DSA_TAG_PROTO_SJA1110_VALUE 23 #define DSA_TAG_PROTO_RTL8_4_VALUE 24 #define DSA_TAG_PROTO_RTL8_4T_VALUE 25 #define DSA_TAG_PROTO_RZN1_A5PSW_VALUE 26 #define DSA_TAG_PROTO_LAN937X_VALUE 27 #define DSA_TAG_PROTO_VSC73XX_8021Q_VALUE 28 enum dsa_tag_protocol { DSA_TAG_PROTO_NONE = DSA_TAG_PROTO_NONE_VALUE, DSA_TAG_PROTO_BRCM = DSA_TAG_PROTO_BRCM_VALUE, DSA_TAG_PROTO_BRCM_LEGACY = DSA_TAG_PROTO_BRCM_LEGACY_VALUE, DSA_TAG_PROTO_BRCM_PREPEND = DSA_TAG_PROTO_BRCM_PREPEND_VALUE, DSA_TAG_PROTO_DSA = DSA_TAG_PROTO_DSA_VALUE, DSA_TAG_PROTO_EDSA = DSA_TAG_PROTO_EDSA_VALUE, DSA_TAG_PROTO_GSWIP = DSA_TAG_PROTO_GSWIP_VALUE, DSA_TAG_PROTO_KSZ9477 = DSA_TAG_PROTO_KSZ9477_VALUE, DSA_TAG_PROTO_KSZ9893 = DSA_TAG_PROTO_KSZ9893_VALUE, DSA_TAG_PROTO_LAN9303 = DSA_TAG_PROTO_LAN9303_VALUE, DSA_TAG_PROTO_MTK = DSA_TAG_PROTO_MTK_VALUE, DSA_TAG_PROTO_QCA = DSA_TAG_PROTO_QCA_VALUE, DSA_TAG_PROTO_TRAILER = DSA_TAG_PROTO_TRAILER_VALUE, DSA_TAG_PROTO_8021Q = DSA_TAG_PROTO_8021Q_VALUE, DSA_TAG_PROTO_SJA1105 = DSA_TAG_PROTO_SJA1105_VALUE, DSA_TAG_PROTO_KSZ8795 = DSA_TAG_PROTO_KSZ8795_VALUE, DSA_TAG_PROTO_OCELOT = DSA_TAG_PROTO_OCELOT_VALUE, DSA_TAG_PROTO_AR9331 = DSA_TAG_PROTO_AR9331_VALUE, DSA_TAG_PROTO_RTL4_A = DSA_TAG_PROTO_RTL4_A_VALUE, DSA_TAG_PROTO_HELLCREEK = DSA_TAG_PROTO_HELLCREEK_VALUE, DSA_TAG_PROTO_XRS700X = DSA_TAG_PROTO_XRS700X_VALUE, DSA_TAG_PROTO_OCELOT_8021Q = DSA_TAG_PROTO_OCELOT_8021Q_VALUE, DSA_TAG_PROTO_SEVILLE = DSA_TAG_PROTO_SEVILLE_VALUE, DSA_TAG_PROTO_SJA1110 = DSA_TAG_PROTO_SJA1110_VALUE, DSA_TAG_PROTO_RTL8_4 = DSA_TAG_PROTO_RTL8_4_VALUE, DSA_TAG_PROTO_RTL8_4T = DSA_TAG_PROTO_RTL8_4T_VALUE, DSA_TAG_PROTO_RZN1_A5PSW = DSA_TAG_PROTO_RZN1_A5PSW_VALUE, DSA_TAG_PROTO_LAN937X = DSA_TAG_PROTO_LAN937X_VALUE, DSA_TAG_PROTO_VSC73XX_8021Q = DSA_TAG_PROTO_VSC73XX_8021Q_VALUE, }; struct dsa_switch; struct dsa_device_ops { struct sk_buff *(*xmit)(struct sk_buff *skb, struct net_device *dev); struct sk_buff *(*rcv)(struct sk_buff *skb, struct net_device *dev); void (*flow_dissect)(const struct sk_buff *skb, __be16 *proto, int *offset); int (*connect)(struct dsa_switch *ds); void (*disconnect)(struct dsa_switch *ds); unsigned int needed_headroom; unsigned int needed_tailroom; const char *name; enum dsa_tag_protocol proto; /* Some tagging protocols either mangle or shift the destination MAC * address, in which case the DSA conduit would drop packets on ingress * if what it understands out of the destination MAC address is not in * its RX filter. */ bool promisc_on_conduit; }; struct dsa_lag { struct net_device *dev; unsigned int id; struct mutex fdb_lock; struct list_head fdbs; refcount_t refcount; }; struct dsa_switch_tree { struct list_head list; /* List of switch ports */ struct list_head ports; /* Notifier chain for switch-wide events */ struct raw_notifier_head nh; /* Tree identifier */ unsigned int index; /* Number of switches attached to this tree */ struct kref refcount; /* Maps offloaded LAG netdevs to a zero-based linear ID for * drivers that need it. */ struct dsa_lag **lags; /* Tagging protocol operations */ const struct dsa_device_ops *tag_ops; /* Default tagging protocol preferred by the switches in this * tree. */ enum dsa_tag_protocol default_proto; /* Has this tree been applied to the hardware? */ bool setup; /* * Configuration data for the platform device that owns * this dsa switch tree instance. */ struct dsa_platform_data *pd; /* List of DSA links composing the routing table */ struct list_head rtable; /* Length of "lags" array */ unsigned int lags_len; /* Track the largest switch index within a tree */ unsigned int last_switch; }; /* LAG IDs are one-based, the dst->lags array is zero-based */ #define dsa_lags_foreach_id(_id, _dst) \ for ((_id) = 1; (_id) <= (_dst)->lags_len; (_id)++) \ if ((_dst)->lags[(_id) - 1]) #define dsa_lag_foreach_port(_dp, _dst, _lag) \ list_for_each_entry((_dp), &(_dst)->ports, list) \ if (dsa_port_offloads_lag((_dp), (_lag))) #define dsa_hsr_foreach_port(_dp, _ds, _hsr) \ list_for_each_entry((_dp), &(_ds)->dst->ports, list) \ if ((_dp)->ds == (_ds) && (_dp)->hsr_dev == (_hsr)) static inline struct dsa_lag *dsa_lag_by_id(struct dsa_switch_tree *dst, unsigned int id) { /* DSA LAG IDs are one-based, dst->lags is zero-based */ return dst->lags[id - 1]; } static inline int dsa_lag_id(struct dsa_switch_tree *dst, struct net_device *lag_dev) { unsigned int id; dsa_lags_foreach_id(id, dst) { struct dsa_lag *lag = dsa_lag_by_id(dst, id); if (lag->dev == lag_dev) return lag->id; } return -ENODEV; } /* TC matchall action types */ enum dsa_port_mall_action_type { DSA_PORT_MALL_MIRROR, DSA_PORT_MALL_POLICER, }; /* TC mirroring entry */ struct dsa_mall_mirror_tc_entry { u8 to_local_port; bool ingress; }; /* TC port policer entry */ struct dsa_mall_policer_tc_entry { u32 burst; u64 rate_bytes_per_sec; }; /* TC matchall entry */ struct dsa_mall_tc_entry { struct list_head list; unsigned long cookie; enum dsa_port_mall_action_type type; union { struct dsa_mall_mirror_tc_entry mirror; struct dsa_mall_policer_tc_entry policer; }; }; struct dsa_bridge { struct net_device *dev; unsigned int num; bool tx_fwd_offload; refcount_t refcount; }; struct dsa_port { /* A CPU port is physically connected to a conduit device. A user port * exposes a network device to user-space, called 'user' here. */ union { struct net_device *conduit; struct net_device *user; }; /* Copy of the tagging protocol operations, for quicker access * in the data path. Valid only for the CPU ports. */ const struct dsa_device_ops *tag_ops; /* Copies for faster access in conduit receive hot path */ struct dsa_switch_tree *dst; struct sk_buff *(*rcv)(struct sk_buff *skb, struct net_device *dev); struct dsa_switch *ds; unsigned int index; enum { DSA_PORT_TYPE_UNUSED = 0, DSA_PORT_TYPE_CPU, DSA_PORT_TYPE_DSA, DSA_PORT_TYPE_USER, } type; const char *name; struct dsa_port *cpu_dp; u8 mac[ETH_ALEN]; u8 stp_state; /* Warning: the following bit fields are not atomic, and updating them * can only be done from code paths where concurrency is not possible * (probe time or under rtnl_lock). */ u8 vlan_filtering:1; /* Managed by DSA on user ports and by drivers on CPU and DSA ports */ u8 learning:1; u8 lag_tx_enabled:1; /* conduit state bits, valid only on CPU ports */ u8 conduit_admin_up:1; u8 conduit_oper_up:1; /* Valid only on user ports */ u8 cpu_port_in_lag:1; u8 setup:1; struct device_node *dn; unsigned int ageing_time; struct dsa_bridge *bridge; struct devlink_port devlink_port; struct phylink *pl; struct phylink_config pl_config; struct dsa_lag *lag; struct net_device *hsr_dev; struct list_head list; /* * Original copy of the conduit netdev ethtool_ops */ const struct ethtool_ops *orig_ethtool_ops; /* List of MAC addresses that must be forwarded on this port. * These are only valid on CPU ports and DSA links. */ struct mutex addr_lists_lock; struct list_head fdbs; struct list_head mdbs; struct mutex vlans_lock; union { /* List of VLANs that CPU and DSA ports are members of. * Access to this is serialized by the sleepable @vlans_lock. */ struct list_head vlans; /* List of VLANs that user ports are members of. * Access to this is serialized by netif_addr_lock_bh(). */ struct list_head user_vlans; }; }; static inline struct dsa_port * dsa_phylink_to_port(struct phylink_config *config) { return container_of(config, struct dsa_port, pl_config); } /* TODO: ideally DSA ports would have a single dp->link_dp member, * and no dst->rtable nor this struct dsa_link would be needed, * but this would require some more complex tree walking, * so keep it stupid at the moment and list them all. */ struct dsa_link { struct dsa_port *dp; struct dsa_port *link_dp; struct list_head list; }; enum dsa_db_type { DSA_DB_PORT, DSA_DB_LAG, DSA_DB_BRIDGE, }; struct dsa_db { enum dsa_db_type type; union { const struct dsa_port *dp; struct dsa_lag lag; struct dsa_bridge bridge; }; }; struct dsa_mac_addr { unsigned char addr[ETH_ALEN]; u16 vid; refcount_t refcount; struct list_head list; struct dsa_db db; }; struct dsa_vlan { u16 vid; refcount_t refcount; struct list_head list; }; struct dsa_switch { struct device *dev; /* * Parent switch tree, and switch index. */ struct dsa_switch_tree *dst; unsigned int index; /* Warning: the following bit fields are not atomic, and updating them * can only be done from code paths where concurrency is not possible * (probe time or under rtnl_lock). */ u32 setup:1; /* Disallow bridge core from requesting different VLAN awareness * settings on ports if not hardware-supported */ u32 vlan_filtering_is_global:1; /* Keep VLAN filtering enabled on ports not offloading any upper */ u32 needs_standalone_vlan_filtering:1; /* Pass .port_vlan_add and .port_vlan_del to drivers even for bridges * that have vlan_filtering=0. All drivers should ideally set this (and * then the option would get removed), but it is unknown whether this * would break things or not. */ u32 configure_vlan_while_not_filtering:1; /* Pop the default_pvid of VLAN-unaware bridge ports from tagged frames. * DEPRECATED: Do NOT set this field in new drivers. Instead look at * the dsa_software_vlan_untag() comments. */ u32 untag_bridge_pvid:1; /* Pop the default_pvid of VLAN-aware bridge ports from tagged frames. * Useful if the switch cannot preserve the VLAN tag as seen on the * wire for user port ingress, and chooses to send all frames as * VLAN-tagged to the CPU, including those which were originally * untagged. */ u32 untag_vlan_aware_bridge_pvid:1; /* Let DSA manage the FDB entries towards the * CPU, based on the software bridge database. */ u32 assisted_learning_on_cpu_port:1; /* In case vlan_filtering_is_global is set, the VLAN awareness state * should be retrieved from here and not from the per-port settings. */ u32 vlan_filtering:1; /* For switches that only have the MRU configurable. To ensure the * configured MTU is not exceeded, normalization of MRU on all bridged * interfaces is needed. */ u32 mtu_enforcement_ingress:1; /* Drivers that isolate the FDBs of multiple bridges must set this * to true to receive the bridge as an argument in .port_fdb_{add,del} * and .port_mdb_{add,del}. Otherwise, the bridge.num will always be * passed as zero. */ u32 fdb_isolation:1; /* Drivers that have global DSCP mapping settings must set this to * true to automatically apply the settings to all ports. */ u32 dscp_prio_mapping_is_global:1; /* Listener for switch fabric events */ struct notifier_block nb; /* * Give the switch driver somewhere to hang its private data * structure. */ void *priv; void *tagger_data; /* * Configuration data for this switch. */ struct dsa_chip_data *cd; /* * The switch operations. */ const struct dsa_switch_ops *ops; /* * Allow a DSA switch driver to override the phylink MAC ops */ const struct phylink_mac_ops *phylink_mac_ops; /* * User mii_bus and devices for the individual ports. */ u32 phys_mii_mask; struct mii_bus *user_mii_bus; /* Ageing Time limits in msecs */ unsigned int ageing_time_min; unsigned int ageing_time_max; /* Storage for drivers using tag_8021q */ struct dsa_8021q_context *tag_8021q_ctx; /* devlink used to represent this switch device */ struct devlink *devlink; /* Number of switch port queues */ unsigned int num_tx_queues; /* Drivers that benefit from having an ID associated with each * offloaded LAG should set this to the maximum number of * supported IDs. DSA will then maintain a mapping of _at * least_ these many IDs, accessible to drivers via * dsa_lag_id(). */ unsigned int num_lag_ids; /* Drivers that support bridge forwarding offload or FDB isolation * should set this to the maximum number of bridges spanning the same * switch tree (or all trees, in the case of cross-tree bridging * support) that can be offloaded. */ unsigned int max_num_bridges; unsigned int num_ports; }; static inline struct dsa_port *dsa_to_port(struct dsa_switch *ds, int p) { struct dsa_switch_tree *dst = ds->dst; struct dsa_port *dp; list_for_each_entry(dp, &dst->ports, list) if (dp->ds == ds && dp->index == p) return dp; return NULL; } static inline bool dsa_port_is_dsa(struct dsa_port *port) { return port->type == DSA_PORT_TYPE_DSA; } static inline bool dsa_port_is_cpu(struct dsa_port *port) { return port->type == DSA_PORT_TYPE_CPU; } static inline bool dsa_port_is_user(struct dsa_port *dp) { return dp->type == DSA_PORT_TYPE_USER; } static inline bool dsa_port_is_unused(struct dsa_port *dp) { return dp->type == DSA_PORT_TYPE_UNUSED; } static inline bool dsa_port_conduit_is_operational(struct dsa_port *dp) { return dsa_port_is_cpu(dp) && dp->conduit_admin_up && dp->conduit_oper_up; } static inline bool dsa_is_unused_port(struct dsa_switch *ds, int p) { return dsa_to_port(ds, p)->type == DSA_PORT_TYPE_UNUSED; } static inline bool dsa_is_cpu_port(struct dsa_switch *ds, int p) { return dsa_to_port(ds, p)->type == DSA_PORT_TYPE_CPU; } static inline bool dsa_is_dsa_port(struct dsa_switch *ds, int p) { return dsa_to_port(ds, p)->type == DSA_PORT_TYPE_DSA; } static inline bool dsa_is_user_port(struct dsa_switch *ds, int p) { return dsa_to_port(ds, p)->type == DSA_PORT_TYPE_USER; } #define dsa_tree_for_each_user_port(_dp, _dst) \ list_for_each_entry((_dp), &(_dst)->ports, list) \ if (dsa_port_is_user((_dp))) #define dsa_tree_for_each_user_port_continue_reverse(_dp, _dst) \ list_for_each_entry_continue_reverse((_dp), &(_dst)->ports, list) \ if (dsa_port_is_user((_dp))) #define dsa_tree_for_each_cpu_port(_dp, _dst) \ list_for_each_entry((_dp), &(_dst)->ports, list) \ if (dsa_port_is_cpu((_dp))) #define dsa_switch_for_each_port(_dp, _ds) \ list_for_each_entry((_dp), &(_ds)->dst->ports, list) \ if ((_dp)->ds == (_ds)) #define dsa_switch_for_each_port_safe(_dp, _next, _ds) \ list_for_each_entry_safe((_dp), (_next), &(_ds)->dst->ports, list) \ if ((_dp)->ds == (_ds)) #define dsa_switch_for_each_port_continue_reverse(_dp, _ds) \ list_for_each_entry_continue_reverse((_dp), &(_ds)->dst->ports, list) \ if ((_dp)->ds == (_ds)) #define dsa_switch_for_each_available_port(_dp, _ds) \ dsa_switch_for_each_port((_dp), (_ds)) \ if (!dsa_port_is_unused((_dp))) #define dsa_switch_for_each_user_port(_dp, _ds) \ dsa_switch_for_each_port((_dp), (_ds)) \ if (dsa_port_is_user((_dp))) #define dsa_switch_for_each_user_port_continue_reverse(_dp, _ds) \ dsa_switch_for_each_port_continue_reverse((_dp), (_ds)) \ if (dsa_port_is_user((_dp))) #define dsa_switch_for_each_cpu_port(_dp, _ds) \ dsa_switch_for_each_port((_dp), (_ds)) \ if (dsa_port_is_cpu((_dp))) #define dsa_switch_for_each_cpu_port_continue_reverse(_dp, _ds) \ dsa_switch_for_each_port_continue_reverse((_dp), (_ds)) \ if (dsa_port_is_cpu((_dp))) static inline u32 dsa_user_ports(struct dsa_switch *ds) { struct dsa_port *dp; u32 mask = 0; dsa_switch_for_each_user_port(dp, ds) mask |= BIT(dp->index); return mask; } static inline u32 dsa_cpu_ports(struct dsa_switch *ds) { struct dsa_port *cpu_dp; u32 mask = 0; dsa_switch_for_each_cpu_port(cpu_dp, ds) mask |= BIT(cpu_dp->index); return mask; } /* Return the local port used to reach an arbitrary switch device */ static inline unsigned int dsa_routing_port(struct dsa_switch *ds, int device) { struct dsa_switch_tree *dst = ds->dst; struct dsa_link *dl; list_for_each_entry(dl, &dst->rtable, list) if (dl->dp->ds == ds && dl->link_dp->ds->index == device) return dl->dp->index; return ds->num_ports; } /* Return the local port used to reach an arbitrary switch port */ static inline unsigned int dsa_towards_port(struct dsa_switch *ds, int device, int port) { if (device == ds->index) return port; else return dsa_routing_port(ds, device); } /* Return the local port used to reach the dedicated CPU port */ static inline unsigned int dsa_upstream_port(struct dsa_switch *ds, int port) { const struct dsa_port *dp = dsa_to_port(ds, port); const struct dsa_port *cpu_dp = dp->cpu_dp; if (!cpu_dp) return port; return dsa_towards_port(ds, cpu_dp->ds->index, cpu_dp->index); } /* Return true if this is the local port used to reach the CPU port */ static inline bool dsa_is_upstream_port(struct dsa_switch *ds, int port) { if (dsa_is_unused_port(ds, port)) return false; return port == dsa_upstream_port(ds, port); } /* Return true if this is a DSA port leading away from the CPU */ static inline bool dsa_is_downstream_port(struct dsa_switch *ds, int port) { return dsa_is_dsa_port(ds, port) && !dsa_is_upstream_port(ds, port); } /* Return the local port used to reach the CPU port */ static inline unsigned int dsa_switch_upstream_port(struct dsa_switch *ds) { struct dsa_port *dp; dsa_switch_for_each_available_port(dp, ds) { return dsa_upstream_port(ds, dp->index); } return ds->num_ports; } /* Return true if @upstream_ds is an upstream switch of @downstream_ds, meaning * that the routing port from @downstream_ds to @upstream_ds is also the port * which @downstream_ds uses to reach its dedicated CPU. */ static inline bool dsa_switch_is_upstream_of(struct dsa_switch *upstream_ds, struct dsa_switch *downstream_ds) { int routing_port; if (upstream_ds == downstream_ds) return true; routing_port = dsa_routing_port(downstream_ds, upstream_ds->index); return dsa_is_upstream_port(downstream_ds, routing_port); } static inline bool dsa_port_is_vlan_filtering(const struct dsa_port *dp) { const struct dsa_switch *ds = dp->ds; if (ds->vlan_filtering_is_global) return ds->vlan_filtering; else return dp->vlan_filtering; } static inline unsigned int dsa_port_lag_id_get(struct dsa_port *dp) { return dp->lag ? dp->lag->id : 0; } static inline struct net_device *dsa_port_lag_dev_get(struct dsa_port *dp) { return dp->lag ? dp->lag->dev : NULL; } static inline bool dsa_port_offloads_lag(struct dsa_port *dp, const struct dsa_lag *lag) { return dsa_port_lag_dev_get(dp) == lag->dev; } static inline struct net_device *dsa_port_to_conduit(const struct dsa_port *dp) { if (dp->cpu_port_in_lag) return dsa_port_lag_dev_get(dp->cpu_dp); return dp->cpu_dp->conduit; } static inline struct net_device *dsa_port_to_bridge_port(const struct dsa_port *dp) { if (!dp->bridge) return NULL; if (dp->lag) return dp->lag->dev; else if (dp->hsr_dev) return dp->hsr_dev; return dp->user; } static inline struct net_device * dsa_port_bridge_dev_get(const struct dsa_port *dp) { return dp->bridge ? dp->bridge->dev : NULL; } static inline unsigned int dsa_port_bridge_num_get(struct dsa_port *dp) { return dp->bridge ? dp->bridge->num : 0; } static inline bool dsa_port_bridge_same(const struct dsa_port *a, const struct dsa_port *b) { struct net_device *br_a = dsa_port_bridge_dev_get(a); struct net_device *br_b = dsa_port_bridge_dev_get(b); /* Standalone ports are not in the same bridge with one another */ return (!br_a || !br_b) ? false : (br_a == br_b); } static inline bool dsa_port_offloads_bridge_port(struct dsa_port *dp, const struct net_device *dev) { return dsa_port_to_bridge_port(dp) == dev; } static inline bool dsa_port_offloads_bridge_dev(struct dsa_port *dp, const struct net_device *bridge_dev) { /* DSA ports connected to a bridge, and event was emitted * for the bridge. */ return dsa_port_bridge_dev_get(dp) == bridge_dev; } static inline bool dsa_port_offloads_bridge(struct dsa_port *dp, const struct dsa_bridge *bridge) { return dsa_port_bridge_dev_get(dp) == bridge->dev; } /* Returns true if any port of this tree offloads the given net_device */ static inline bool dsa_tree_offloads_bridge_port(struct dsa_switch_tree *dst, const struct net_device *dev) { struct dsa_port *dp; list_for_each_entry(dp, &dst->ports, list) if (dsa_port_offloads_bridge_port(dp, dev)) return true; return false; } /* Returns true if any port of this tree offloads the given bridge */ static inline bool dsa_tree_offloads_bridge_dev(struct dsa_switch_tree *dst, const struct net_device *bridge_dev) { struct dsa_port *dp; list_for_each_entry(dp, &dst->ports, list) if (dsa_port_offloads_bridge_dev(dp, bridge_dev)) return true; return false; } static inline bool dsa_port_tree_same(const struct dsa_port *a, const struct dsa_port *b) { return a->ds->dst == b->ds->dst; } typedef int dsa_fdb_dump_cb_t(const unsigned char *addr, u16 vid, bool is_static, void *data); struct dsa_switch_ops { /* * Tagging protocol helpers called for the CPU ports and DSA links. * @get_tag_protocol retrieves the initial tagging protocol and is * mandatory. Switches which can operate using multiple tagging * protocols should implement @change_tag_protocol and report in * @get_tag_protocol the tagger in current use. */ enum dsa_tag_protocol (*get_tag_protocol)(struct dsa_switch *ds, int port, enum dsa_tag_protocol mprot); int (*change_tag_protocol)(struct dsa_switch *ds, enum dsa_tag_protocol proto); /* * Method for switch drivers to connect to the tagging protocol driver * in current use. The switch driver can provide handlers for certain * types of packets for switch management. */ int (*connect_tag_protocol)(struct dsa_switch *ds, enum dsa_tag_protocol proto); int (*port_change_conduit)(struct dsa_switch *ds, int port, struct net_device *conduit, struct netlink_ext_ack *extack); /* Optional switch-wide initialization and destruction methods */ int (*setup)(struct dsa_switch *ds); void (*teardown)(struct dsa_switch *ds); /* Per-port initialization and destruction methods. Mandatory if the * driver registers devlink port regions, optional otherwise. */ int (*port_setup)(struct dsa_switch *ds, int port); void (*port_teardown)(struct dsa_switch *ds, int port); u32 (*get_phy_flags)(struct dsa_switch *ds, int port); /* * Access to the switch's PHY registers. */ int (*phy_read)(struct dsa_switch *ds, int port, int regnum); int (*phy_write)(struct dsa_switch *ds, int port, int regnum, u16 val); /* * PHYLINK integration */ void (*phylink_get_caps)(struct dsa_switch *ds, int port, struct phylink_config *config); void (*phylink_fixed_state)(struct dsa_switch *ds, int port, struct phylink_link_state *state); /* * Port statistics counters. */ void (*get_strings)(struct dsa_switch *ds, int port, u32 stringset, uint8_t *data); void (*get_ethtool_stats)(struct dsa_switch *ds, int port, uint64_t *data); int (*get_sset_count)(struct dsa_switch *ds, int port, int sset); void (*get_ethtool_phy_stats)(struct dsa_switch *ds, int port, uint64_t *data); void (*get_eth_phy_stats)(struct dsa_switch *ds, int port, struct ethtool_eth_phy_stats *phy_stats); void (*get_eth_mac_stats)(struct dsa_switch *ds, int port, struct ethtool_eth_mac_stats *mac_stats); void (*get_eth_ctrl_stats)(struct dsa_switch *ds, int port, struct ethtool_eth_ctrl_stats *ctrl_stats); void (*get_rmon_stats)(struct dsa_switch *ds, int port, struct ethtool_rmon_stats *rmon_stats, const struct ethtool_rmon_hist_range **ranges); void (*get_ts_stats)(struct dsa_switch *ds, int port, struct ethtool_ts_stats *ts_stats); void (*get_stats64)(struct dsa_switch *ds, int port, struct rtnl_link_stats64 *s); void (*get_pause_stats)(struct dsa_switch *ds, int port, struct ethtool_pause_stats *pause_stats); void (*self_test)(struct dsa_switch *ds, int port, struct ethtool_test *etest, u64 *data); /* * ethtool Wake-on-LAN */ void (*get_wol)(struct dsa_switch *ds, int port, struct ethtool_wolinfo *w); int (*set_wol)(struct dsa_switch *ds, int port, struct ethtool_wolinfo *w); /* * ethtool timestamp info */ int (*get_ts_info)(struct dsa_switch *ds, int port, struct kernel_ethtool_ts_info *ts); /* * ethtool MAC merge layer */ int (*get_mm)(struct dsa_switch *ds, int port, struct ethtool_mm_state *state); int (*set_mm)(struct dsa_switch *ds, int port, struct ethtool_mm_cfg *cfg, struct netlink_ext_ack *extack); void (*get_mm_stats)(struct dsa_switch *ds, int port, struct ethtool_mm_stats *stats); /* * DCB ops */ int (*port_get_default_prio)(struct dsa_switch *ds, int port); int (*port_set_default_prio)(struct dsa_switch *ds, int port, u8 prio); int (*port_get_dscp_prio)(struct dsa_switch *ds, int port, u8 dscp); int (*port_add_dscp_prio)(struct dsa_switch *ds, int port, u8 dscp, u8 prio); int (*port_del_dscp_prio)(struct dsa_switch *ds, int port, u8 dscp, u8 prio); int (*port_set_apptrust)(struct dsa_switch *ds, int port, const u8 *sel, int nsel); int (*port_get_apptrust)(struct dsa_switch *ds, int port, u8 *sel, int *nsel); /* * Suspend and resume */ int (*suspend)(struct dsa_switch *ds); int (*resume)(struct dsa_switch *ds); /* * Port enable/disable */ int (*port_enable)(struct dsa_switch *ds, int port, struct phy_device *phy); void (*port_disable)(struct dsa_switch *ds, int port); /* * Notification for MAC address changes on user ports. Drivers can * currently only veto operations. They should not use the method to * program the hardware, since the operation is not rolled back in case * of other errors. */ int (*port_set_mac_address)(struct dsa_switch *ds, int port, const unsigned char *addr); /* * Compatibility between device trees defining multiple CPU ports and * drivers which are not OK to use by default the numerically smallest * CPU port of a switch for its local ports. This can return NULL, * meaning "don't know/don't care". */ struct dsa_port *(*preferred_default_local_cpu_port)(struct dsa_switch *ds); /* * Port's MAC EEE settings */ bool (*support_eee)(struct dsa_switch *ds, int port); int (*set_mac_eee)(struct dsa_switch *ds, int port, struct ethtool_keee *e); /* EEPROM access */ int (*get_eeprom_len)(struct dsa_switch *ds); int (*get_eeprom)(struct dsa_switch *ds, struct ethtool_eeprom *eeprom, u8 *data); int (*set_eeprom)(struct dsa_switch *ds, struct ethtool_eeprom *eeprom, u8 *data); /* * Register access. */ int (*get_regs_len)(struct dsa_switch *ds, int port); void (*get_regs)(struct dsa_switch *ds, int port, struct ethtool_regs *regs, void *p); /* * Upper device tracking. */ int (*port_prechangeupper)(struct dsa_switch *ds, int port, struct netdev_notifier_changeupper_info *info); /* * Bridge integration */ int (*set_ageing_time)(struct dsa_switch *ds, unsigned int msecs); int (*port_bridge_join)(struct dsa_switch *ds, int port, struct dsa_bridge bridge, bool *tx_fwd_offload, struct netlink_ext_ack *extack); void (*port_bridge_leave)(struct dsa_switch *ds, int port, struct dsa_bridge bridge); void (*port_stp_state_set)(struct dsa_switch *ds, int port, u8 state); int (*port_mst_state_set)(struct dsa_switch *ds, int port, const struct switchdev_mst_state *state); void (*port_fast_age)(struct dsa_switch *ds, int port); int (*port_vlan_fast_age)(struct dsa_switch *ds, int port, u16 vid); int (*port_pre_bridge_flags)(struct dsa_switch *ds, int port, struct switchdev_brport_flags flags, struct netlink_ext_ack *extack); int (*port_bridge_flags)(struct dsa_switch *ds, int port, struct switchdev_brport_flags flags, struct netlink_ext_ack *extack); void (*port_set_host_flood)(struct dsa_switch *ds, int port, bool uc, bool mc); /* * VLAN support */ int (*port_vlan_filtering)(struct dsa_switch *ds, int port, bool vlan_filtering, struct netlink_ext_ack *extack); int (*port_vlan_add)(struct dsa_switch *ds, int port, const struct switchdev_obj_port_vlan *vlan, struct netlink_ext_ack *extack); int (*port_vlan_del)(struct dsa_switch *ds, int port, const struct switchdev_obj_port_vlan *vlan); int (*vlan_msti_set)(struct dsa_switch *ds, struct dsa_bridge bridge, const struct switchdev_vlan_msti *msti); /* * Forwarding database */ int (*port_fdb_add)(struct dsa_switch *ds, int port, const unsigned char *addr, u16 vid, struct dsa_db db); int (*port_fdb_del)(struct dsa_switch *ds, int port, const unsigned char *addr, u16 vid, struct dsa_db db); int (*port_fdb_dump)(struct dsa_switch *ds, int port, dsa_fdb_dump_cb_t *cb, void *data); int (*lag_fdb_add)(struct dsa_switch *ds, struct dsa_lag lag, const unsigned char *addr, u16 vid, struct dsa_db db); int (*lag_fdb_del)(struct dsa_switch *ds, struct dsa_lag lag, const unsigned char *addr, u16 vid, struct dsa_db db); /* * Multicast database */ int (*port_mdb_add)(struct dsa_switch *ds, int port, const struct switchdev_obj_port_mdb *mdb, struct dsa_db db); int (*port_mdb_del)(struct dsa_switch *ds, int port, const struct switchdev_obj_port_mdb *mdb, struct dsa_db db); /* * RXNFC */ int (*get_rxnfc)(struct dsa_switch *ds, int port, struct ethtool_rxnfc *nfc, u32 *rule_locs); int (*set_rxnfc)(struct dsa_switch *ds, int port, struct ethtool_rxnfc *nfc); /* * TC integration */ int (*cls_flower_add)(struct dsa_switch *ds, int port, struct flow_cls_offload *cls, bool ingress); int (*cls_flower_del)(struct dsa_switch *ds, int port, struct flow_cls_offload *cls, bool ingress); int (*cls_flower_stats)(struct dsa_switch *ds, int port, struct flow_cls_offload *cls, bool ingress); int (*port_mirror_add)(struct dsa_switch *ds, int port, struct dsa_mall_mirror_tc_entry *mirror, bool ingress, struct netlink_ext_ack *extack); void (*port_mirror_del)(struct dsa_switch *ds, int port, struct dsa_mall_mirror_tc_entry *mirror); int (*port_policer_add)(struct dsa_switch *ds, int port, struct dsa_mall_policer_tc_entry *policer); void (*port_policer_del)(struct dsa_switch *ds, int port); int (*port_setup_tc)(struct dsa_switch *ds, int port, enum tc_setup_type type, void *type_data); /* * Cross-chip operations */ int (*crosschip_bridge_join)(struct dsa_switch *ds, int tree_index, int sw_index, int port, struct dsa_bridge bridge, struct netlink_ext_ack *extack); void (*crosschip_bridge_leave)(struct dsa_switch *ds, int tree_index, int sw_index, int port, struct dsa_bridge bridge); int (*crosschip_lag_change)(struct dsa_switch *ds, int sw_index, int port); int (*crosschip_lag_join)(struct dsa_switch *ds, int sw_index, int port, struct dsa_lag lag, struct netdev_lag_upper_info *info, struct netlink_ext_ack *extack); int (*crosschip_lag_leave)(struct dsa_switch *ds, int sw_index, int port, struct dsa_lag lag); /* * PTP functionality */ int (*port_hwtstamp_get)(struct dsa_switch *ds, int port, struct ifreq *ifr); int (*port_hwtstamp_set)(struct dsa_switch *ds, int port, struct ifreq *ifr); void (*port_txtstamp)(struct dsa_switch *ds, int port, struct sk_buff *skb); bool (*port_rxtstamp)(struct dsa_switch *ds, int port, struct sk_buff *skb, unsigned int type); /* Devlink parameters, etc */ int (*devlink_param_get)(struct dsa_switch *ds, u32 id, struct devlink_param_gset_ctx *ctx); int (*devlink_param_set)(struct dsa_switch *ds, u32 id, struct devlink_param_gset_ctx *ctx); int (*devlink_info_get)(struct dsa_switch *ds, struct devlink_info_req *req, struct netlink_ext_ack *extack); int (*devlink_sb_pool_get)(struct dsa_switch *ds, unsigned int sb_index, u16 pool_index, struct devlink_sb_pool_info *pool_info); int (*devlink_sb_pool_set)(struct dsa_switch *ds, unsigned int sb_index, u16 pool_index, u32 size, enum devlink_sb_threshold_type threshold_type, struct netlink_ext_ack *extack); int (*devlink_sb_port_pool_get)(struct dsa_switch *ds, int port, unsigned int sb_index, u16 pool_index, u32 *p_threshold); int (*devlink_sb_port_pool_set)(struct dsa_switch *ds, int port, unsigned int sb_index, u16 pool_index, u32 threshold, struct netlink_ext_ack *extack); int (*devlink_sb_tc_pool_bind_get)(struct dsa_switch *ds, int port, unsigned int sb_index, u16 tc_index, enum devlink_sb_pool_type pool_type, u16 *p_pool_index, u32 *p_threshold); int (*devlink_sb_tc_pool_bind_set)(struct dsa_switch *ds, int port, unsigned int sb_index, u16 tc_index, enum devlink_sb_pool_type pool_type, u16 pool_index, u32 threshold, struct netlink_ext_ack *extack); int (*devlink_sb_occ_snapshot)(struct dsa_switch *ds, unsigned int sb_index); int (*devlink_sb_occ_max_clear)(struct dsa_switch *ds, unsigned int sb_index); int (*devlink_sb_occ_port_pool_get)(struct dsa_switch *ds, int port, unsigned int sb_index, u16 pool_index, u32 *p_cur, u32 *p_max); int (*devlink_sb_occ_tc_port_bind_get)(struct dsa_switch *ds, int port, unsigned int sb_index, u16 tc_index, enum devlink_sb_pool_type pool_type, u32 *p_cur, u32 *p_max); /* * MTU change functionality. Switches can also adjust their MRU through * this method. By MTU, one understands the SDU (L2 payload) length. * If the switch needs to account for the DSA tag on the CPU port, this * method needs to do so privately. */ int (*port_change_mtu)(struct dsa_switch *ds, int port, int new_mtu); int (*port_max_mtu)(struct dsa_switch *ds, int port); /* * LAG integration */ int (*port_lag_change)(struct dsa_switch *ds, int port); int (*port_lag_join)(struct dsa_switch *ds, int port, struct dsa_lag lag, struct netdev_lag_upper_info *info, struct netlink_ext_ack *extack); int (*port_lag_leave)(struct dsa_switch *ds, int port, struct dsa_lag lag); /* * HSR integration */ int (*port_hsr_join)(struct dsa_switch *ds, int port, struct net_device *hsr, struct netlink_ext_ack *extack); int (*port_hsr_leave)(struct dsa_switch *ds, int port, struct net_device *hsr); /* * MRP integration */ int (*port_mrp_add)(struct dsa_switch *ds, int port, const struct switchdev_obj_mrp *mrp); int (*port_mrp_del)(struct dsa_switch *ds, int port, const struct switchdev_obj_mrp *mrp); int (*port_mrp_add_ring_role)(struct dsa_switch *ds, int port, const struct switchdev_obj_ring_role_mrp *mrp); int (*port_mrp_del_ring_role)(struct dsa_switch *ds, int port, const struct switchdev_obj_ring_role_mrp *mrp); /* * tag_8021q operations */ int (*tag_8021q_vlan_add)(struct dsa_switch *ds, int port, u16 vid, u16 flags); int (*tag_8021q_vlan_del)(struct dsa_switch *ds, int port, u16 vid); /* * DSA conduit tracking operations */ void (*conduit_state_change)(struct dsa_switch *ds, const struct net_device *conduit, bool operational); }; #define DSA_DEVLINK_PARAM_DRIVER(_id, _name, _type, _cmodes) \ DEVLINK_PARAM_DRIVER(_id, _name, _type, _cmodes, \ dsa_devlink_param_get, dsa_devlink_param_set, NULL) int dsa_devlink_param_get(struct devlink *dl, u32 id, struct devlink_param_gset_ctx *ctx); int dsa_devlink_param_set(struct devlink *dl, u32 id, struct devlink_param_gset_ctx *ctx, struct netlink_ext_ack *extack); int dsa_devlink_params_register(struct dsa_switch *ds, const struct devlink_param *params, size_t params_count); void dsa_devlink_params_unregister(struct dsa_switch *ds, const struct devlink_param *params, size_t params_count); int dsa_devlink_resource_register(struct dsa_switch *ds, const char *resource_name, u64 resource_size, u64 resource_id, u64 parent_resource_id, const struct devlink_resource_size_params *size_params); void dsa_devlink_resources_unregister(struct dsa_switch *ds); void dsa_devlink_resource_occ_get_register(struct dsa_switch *ds, u64 resource_id, devlink_resource_occ_get_t *occ_get, void *occ_get_priv); void dsa_devlink_resource_occ_get_unregister(struct dsa_switch *ds, u64 resource_id); struct devlink_region * dsa_devlink_region_create(struct dsa_switch *ds, const struct devlink_region_ops *ops, u32 region_max_snapshots, u64 region_size); struct devlink_region * dsa_devlink_port_region_create(struct dsa_switch *ds, int port, const struct devlink_port_region_ops *ops, u32 region_max_snapshots, u64 region_size); void dsa_devlink_region_destroy(struct devlink_region *region); struct dsa_port *dsa_port_from_netdev(struct net_device *netdev); struct dsa_devlink_priv { struct dsa_switch *ds; }; static inline struct dsa_switch *dsa_devlink_to_ds(struct devlink *dl) { struct dsa_devlink_priv *dl_priv = devlink_priv(dl); return dl_priv->ds; } static inline struct dsa_switch *dsa_devlink_port_to_ds(struct devlink_port *port) { struct devlink *dl = port->devlink; struct dsa_devlink_priv *dl_priv = devlink_priv(dl); return dl_priv->ds; } static inline int dsa_devlink_port_to_port(struct devlink_port *port) { return port->index; } struct dsa_switch_driver { struct list_head list; const struct dsa_switch_ops *ops; }; bool dsa_fdb_present_in_other_db(struct dsa_switch *ds, int port, const unsigned char *addr, u16 vid, struct dsa_db db); bool dsa_mdb_present_in_other_db(struct dsa_switch *ds, int port, const struct switchdev_obj_port_mdb *mdb, struct dsa_db db); /* Keep inline for faster access in hot path */ static inline bool netdev_uses_dsa(const struct net_device *dev) { #if IS_ENABLED(CONFIG_NET_DSA) return dev->dsa_ptr && dev->dsa_ptr->rcv; #endif return false; } /* All DSA tags that push the EtherType to the right (basically all except tail * tags, which don't break dissection) can be treated the same from the * perspective of the flow dissector. * * We need to return: * - offset: the (B - A) difference between: * A. the position of the real EtherType and * B. the current skb->data (aka ETH_HLEN bytes into the frame, aka 2 bytes * after the normal EtherType was supposed to be) * The offset in bytes is exactly equal to the tagger overhead (and half of * that, in __be16 shorts). * * - proto: the value of the real EtherType. */ static inline void dsa_tag_generic_flow_dissect(const struct sk_buff *skb, __be16 *proto, int *offset) { #if IS_ENABLED(CONFIG_NET_DSA) const struct dsa_device_ops *ops = skb->dev->dsa_ptr->tag_ops; int tag_len = ops->needed_headroom; *offset = tag_len; *proto = ((__be16 *)skb->data)[(tag_len / 2) - 1]; #endif } void dsa_unregister_switch(struct dsa_switch *ds); int dsa_register_switch(struct dsa_switch *ds); void dsa_switch_shutdown(struct dsa_switch *ds); struct dsa_switch *dsa_switch_find(int tree_index, int sw_index); void dsa_flush_workqueue(void); #ifdef CONFIG_PM_SLEEP int dsa_switch_suspend(struct dsa_switch *ds); int dsa_switch_resume(struct dsa_switch *ds); #else static inline int dsa_switch_suspend(struct dsa_switch *ds) { return 0; } static inline int dsa_switch_resume(struct dsa_switch *ds) { return 0; } #endif /* CONFIG_PM_SLEEP */ #if IS_ENABLED(CONFIG_NET_DSA) bool dsa_user_dev_check(const struct net_device *dev); #else static inline bool dsa_user_dev_check(const struct net_device *dev) { return false; } #endif netdev_tx_t dsa_enqueue_skb(struct sk_buff *skb, struct net_device *dev); void dsa_port_phylink_mac_change(struct dsa_switch *ds, int port, bool up); bool dsa_supports_eee(struct dsa_switch *ds, int port); #endif |
| 60 121 120 121 121 121 121 450 179 180 178 | 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 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef __LINUX_GRE_H #define __LINUX_GRE_H #include <linux/skbuff.h> #include <net/ip_tunnels.h> struct gre_base_hdr { __be16 flags; __be16 protocol; } __packed; struct gre_full_hdr { struct gre_base_hdr fixed_header; __be16 csum; __be16 reserved1; __be32 key; __be32 seq; } __packed; #define GRE_HEADER_SECTION 4 #define GREPROTO_CISCO 0 #define GREPROTO_PPTP 1 #define GREPROTO_MAX 2 #define GRE_IP_PROTO_MAX 2 struct gre_protocol { int (*handler)(struct sk_buff *skb); void (*err_handler)(struct sk_buff *skb, u32 info); }; int gre_add_protocol(const struct gre_protocol *proto, u8 version); int gre_del_protocol(const struct gre_protocol *proto, u8 version); struct net_device *gretap_fb_dev_create(struct net *net, const char *name, u8 name_assign_type); int gre_parse_header(struct sk_buff *skb, struct tnl_ptk_info *tpi, bool *csum_err, __be16 proto, int nhs); static inline bool netif_is_gretap(const struct net_device *dev) { return dev->rtnl_link_ops && !strcmp(dev->rtnl_link_ops->kind, "gretap"); } static inline bool netif_is_ip6gretap(const struct net_device *dev) { return dev->rtnl_link_ops && !strcmp(dev->rtnl_link_ops->kind, "ip6gretap"); } static inline int gre_calc_hlen(const unsigned long *o_flags) { int addend = 4; if (test_bit(IP_TUNNEL_CSUM_BIT, o_flags)) addend += 4; if (test_bit(IP_TUNNEL_KEY_BIT, o_flags)) addend += 4; if (test_bit(IP_TUNNEL_SEQ_BIT, o_flags)) addend += 4; return addend; } static inline void gre_flags_to_tnl_flags(unsigned long *dst, __be16 flags) { IP_TUNNEL_DECLARE_FLAGS(res) = { }; __assign_bit(IP_TUNNEL_CSUM_BIT, res, flags & GRE_CSUM); __assign_bit(IP_TUNNEL_ROUTING_BIT, res, flags & GRE_ROUTING); __assign_bit(IP_TUNNEL_KEY_BIT, res, flags & GRE_KEY); __assign_bit(IP_TUNNEL_SEQ_BIT, res, flags & GRE_SEQ); __assign_bit(IP_TUNNEL_STRICT_BIT, res, flags & GRE_STRICT); __assign_bit(IP_TUNNEL_REC_BIT, res, flags & GRE_REC); __assign_bit(IP_TUNNEL_VERSION_BIT, res, flags & GRE_VERSION); ip_tunnel_flags_copy(dst, res); } static inline __be16 gre_tnl_flags_to_gre_flags(const unsigned long *tflags) { __be16 flags = 0; if (test_bit(IP_TUNNEL_CSUM_BIT, tflags)) flags |= GRE_CSUM; if (test_bit(IP_TUNNEL_ROUTING_BIT, tflags)) flags |= GRE_ROUTING; if (test_bit(IP_TUNNEL_KEY_BIT, tflags)) flags |= GRE_KEY; if (test_bit(IP_TUNNEL_SEQ_BIT, tflags)) flags |= GRE_SEQ; if (test_bit(IP_TUNNEL_STRICT_BIT, tflags)) flags |= GRE_STRICT; if (test_bit(IP_TUNNEL_REC_BIT, tflags)) flags |= GRE_REC; if (test_bit(IP_TUNNEL_VERSION_BIT, tflags)) flags |= GRE_VERSION; return flags; } static inline void gre_build_header(struct sk_buff *skb, int hdr_len, const unsigned long *flags, __be16 proto, __be32 key, __be32 seq) { IP_TUNNEL_DECLARE_FLAGS(cond) = { }; struct gre_base_hdr *greh; skb_push(skb, hdr_len); skb_set_inner_protocol(skb, proto); skb_reset_transport_header(skb); greh = (struct gre_base_hdr *)skb->data; greh->flags = gre_tnl_flags_to_gre_flags(flags); greh->protocol = proto; __set_bit(IP_TUNNEL_KEY_BIT, cond); __set_bit(IP_TUNNEL_CSUM_BIT, cond); __set_bit(IP_TUNNEL_SEQ_BIT, cond); if (ip_tunnel_flags_intersect(flags, cond)) { __be32 *ptr = (__be32 *)(((u8 *)greh) + hdr_len - 4); if (test_bit(IP_TUNNEL_SEQ_BIT, flags)) { *ptr = seq; ptr--; } if (test_bit(IP_TUNNEL_KEY_BIT, flags)) { *ptr = key; ptr--; } if (test_bit(IP_TUNNEL_CSUM_BIT, flags) && !(skb_shinfo(skb)->gso_type & (SKB_GSO_GRE | SKB_GSO_GRE_CSUM))) { *ptr = 0; if (skb->ip_summed == CHECKSUM_PARTIAL) { *(__sum16 *)ptr = csum_fold(lco_csum(skb)); } else { skb->ip_summed = CHECKSUM_PARTIAL; skb->csum_start = skb_transport_header(skb) - skb->head; skb->csum_offset = sizeof(*greh); } } } } #endif |
| 216 11487 384 383 217 14 216 | 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 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef __X86_KERNEL_FPU_XSTATE_H #define __X86_KERNEL_FPU_XSTATE_H #include <asm/cpufeature.h> #include <asm/fpu/xstate.h> #include <asm/fpu/xcr.h> #ifdef CONFIG_X86_64 DECLARE_PER_CPU(u64, xfd_state); #endif static inline void xstate_init_xcomp_bv(struct xregs_state *xsave, u64 mask) { /* * XRSTORS requires these bits set in xcomp_bv, or it will * trigger #GP: */ if (cpu_feature_enabled(X86_FEATURE_XCOMPACTED)) xsave->header.xcomp_bv = mask | XCOMP_BV_COMPACTED_FORMAT; } static inline u64 xstate_get_group_perm(bool guest) { struct fpu *fpu = ¤t->group_leader->thread.fpu; struct fpu_state_perm *perm; /* Pairs with WRITE_ONCE() in xstate_request_perm() */ perm = guest ? &fpu->guest_perm : &fpu->perm; return READ_ONCE(perm->__state_perm); } static inline u64 xstate_get_host_group_perm(void) { return xstate_get_group_perm(false); } enum xstate_copy_mode { XSTATE_COPY_FP, XSTATE_COPY_FX, XSTATE_COPY_XSAVE, }; struct membuf; extern void __copy_xstate_to_uabi_buf(struct membuf to, struct fpstate *fpstate, u64 xfeatures, u32 pkru_val, enum xstate_copy_mode copy_mode); extern void copy_xstate_to_uabi_buf(struct membuf to, struct task_struct *tsk, enum xstate_copy_mode mode); extern int copy_uabi_from_kernel_to_xstate(struct fpstate *fpstate, const void *kbuf, u32 *pkru); extern int copy_sigframe_from_user_to_xstate(struct task_struct *tsk, const void __user *ubuf); extern void fpu__init_cpu_xstate(void); extern void fpu__init_system_xstate(unsigned int legacy_size); extern void __user *get_xsave_addr_user(struct xregs_state __user *xsave, int xfeature_nr); static inline u64 xfeatures_mask_supervisor(void) { return fpu_kernel_cfg.max_features & XFEATURE_MASK_SUPERVISOR_SUPPORTED; } static inline u64 xfeatures_mask_independent(void) { if (!cpu_feature_enabled(X86_FEATURE_ARCH_LBR)) return fpu_kernel_cfg.independent_features & ~XFEATURE_MASK_LBR; return fpu_kernel_cfg.independent_features; } /* * Update the value of PKRU register that was already pushed onto the signal frame. */ static inline int update_pkru_in_sigframe(struct xregs_state __user *buf, u64 mask, u32 pkru) { u64 xstate_bv; int err; if (unlikely(!cpu_feature_enabled(X86_FEATURE_OSPKE))) return 0; /* Mark PKRU as in-use so that it is restored correctly. */ xstate_bv = (mask & xfeatures_in_use()) | XFEATURE_MASK_PKRU; err = __put_user(xstate_bv, &buf->header.xfeatures); if (err) return err; /* Update PKRU value in the userspace xsave buffer. */ return __put_user(pkru, (unsigned int __user *)get_xsave_addr_user(buf, XFEATURE_PKRU)); } /* XSAVE/XRSTOR wrapper functions */ #ifdef CONFIG_X86_64 #define REX_PREFIX "0x48, " #else #define REX_PREFIX #endif /* These macros all use (%edi)/(%rdi) as the single memory argument. */ #define XSAVE ".byte " REX_PREFIX "0x0f,0xae,0x27" #define XSAVEOPT ".byte " REX_PREFIX "0x0f,0xae,0x37" #define XSAVEC ".byte " REX_PREFIX "0x0f,0xc7,0x27" #define XSAVES ".byte " REX_PREFIX "0x0f,0xc7,0x2f" #define XRSTOR ".byte " REX_PREFIX "0x0f,0xae,0x2f" #define XRSTORS ".byte " REX_PREFIX "0x0f,0xc7,0x1f" /* * After this @err contains 0 on success or the trap number when the * operation raises an exception. */ #define XSTATE_OP(op, st, lmask, hmask, err) \ asm volatile("1:" op "\n\t" \ "xor %[err], %[err]\n" \ "2:\n\t" \ _ASM_EXTABLE_TYPE(1b, 2b, EX_TYPE_FAULT_MCE_SAFE) \ : [err] "=a" (err) \ : "D" (st), "m" (*st), "a" (lmask), "d" (hmask) \ : "memory") /* * If XSAVES is enabled, it replaces XSAVEC because it supports supervisor * states in addition to XSAVEC. * * Otherwise if XSAVEC is enabled, it replaces XSAVEOPT because it supports * compacted storage format in addition to XSAVEOPT. * * Otherwise, if XSAVEOPT is enabled, XSAVEOPT replaces XSAVE because XSAVEOPT * supports modified optimization which is not supported by XSAVE. * * Use XSAVE as a fallback. */ #define XSTATE_XSAVE(st, lmask, hmask, err) \ asm volatile("1: " ALTERNATIVE_3(XSAVE, \ XSAVEOPT, X86_FEATURE_XSAVEOPT, \ XSAVEC, X86_FEATURE_XSAVEC, \ XSAVES, X86_FEATURE_XSAVES) \ "\n" \ "xor %[err], %[err]\n" \ "3:\n" \ _ASM_EXTABLE_TYPE_REG(1b, 3b, EX_TYPE_EFAULT_REG, %[err]) \ : [err] "=r" (err) \ : "D" (st), "m" (*st), "a" (lmask), "d" (hmask) \ : "memory") /* * Use XRSTORS to restore context if it is enabled. XRSTORS supports compact * XSAVE area format. */ #define XSTATE_XRESTORE(st, lmask, hmask) \ asm volatile("1: " ALTERNATIVE(XRSTOR, \ XRSTORS, X86_FEATURE_XSAVES) \ "\n" \ "3:\n" \ _ASM_EXTABLE_TYPE(1b, 3b, EX_TYPE_FPU_RESTORE) \ : \ : "D" (st), "m" (*st), "a" (lmask), "d" (hmask) \ : "memory") #if defined(CONFIG_X86_64) && defined(CONFIG_X86_DEBUG_FPU) extern void xfd_validate_state(struct fpstate *fpstate, u64 mask, bool rstor); #else static inline void xfd_validate_state(struct fpstate *fpstate, u64 mask, bool rstor) { } #endif #ifdef CONFIG_X86_64 static inline void xfd_set_state(u64 xfd) { wrmsrl(MSR_IA32_XFD, xfd); __this_cpu_write(xfd_state, xfd); } static inline void xfd_update_state(struct fpstate *fpstate) { if (fpu_state_size_dynamic()) { u64 xfd = fpstate->xfd; if (__this_cpu_read(xfd_state) != xfd) xfd_set_state(xfd); } } extern int __xfd_enable_feature(u64 which, struct fpu_guest *guest_fpu); #else static inline void xfd_set_state(u64 xfd) { } static inline void xfd_update_state(struct fpstate *fpstate) { } static inline int __xfd_enable_feature(u64 which, struct fpu_guest *guest_fpu) { return -EPERM; } #endif /* * Save processor xstate to xsave area. * * Uses either XSAVE or XSAVEOPT or XSAVES depending on the CPU features * and command line options. The choice is permanent until the next reboot. */ static inline void os_xsave(struct fpstate *fpstate) { u64 mask = fpstate->xfeatures; u32 lmask = mask; u32 hmask = mask >> 32; int err; WARN_ON_FPU(!alternatives_patched); xfd_validate_state(fpstate, mask, false); XSTATE_XSAVE(&fpstate->regs.xsave, lmask, hmask, err); /* We should never fault when copying to a kernel buffer: */ WARN_ON_FPU(err); } /* * Restore processor xstate from xsave area. * * Uses XRSTORS when XSAVES is used, XRSTOR otherwise. */ static inline void os_xrstor(struct fpstate *fpstate, u64 mask) { u32 lmask = mask; u32 hmask = mask >> 32; xfd_validate_state(fpstate, mask, true); XSTATE_XRESTORE(&fpstate->regs.xsave, lmask, hmask); } /* Restore of supervisor state. Does not require XFD */ static inline void os_xrstor_supervisor(struct fpstate *fpstate) { u64 mask = xfeatures_mask_supervisor(); u32 lmask = mask; u32 hmask = mask >> 32; XSTATE_XRESTORE(&fpstate->regs.xsave, lmask, hmask); } /* * XSAVE itself always writes all requested xfeatures. Removing features * from the request bitmap reduces the features which are written. * Generate a mask of features which must be written to a sigframe. The * unset features can be optimized away and not written. * * This optimization is user-visible. Only use for states where * uninitialized sigframe contents are tolerable, like dynamic features. * * Users of buffers produced with this optimization must check XSTATE_BV * to determine which features have been optimized out. */ static inline u64 xfeatures_need_sigframe_write(void) { u64 xfeaures_to_write; /* In-use features must be written: */ xfeaures_to_write = xfeatures_in_use(); /* Also write all non-optimizable sigframe features: */ xfeaures_to_write |= XFEATURE_MASK_USER_SUPPORTED & ~XFEATURE_MASK_SIGFRAME_INITOPT; return xfeaures_to_write; } /* * Save xstate to user space xsave area. * * We don't use modified optimization because xrstor/xrstors might track * a different application. * * We don't use compacted format xsave area for backward compatibility for * old applications which don't understand the compacted format of the * xsave area. * * The caller has to zero buf::header before calling this because XSAVE* * does not touch the reserved fields in the header. */ static inline int xsave_to_user_sigframe(struct xregs_state __user *buf, u32 pkru) { /* * Include the features which are not xsaved/rstored by the kernel * internally, e.g. PKRU. That's user space ABI and also required * to allow the signal handler to modify PKRU. */ struct fpstate *fpstate = current->thread.fpu.fpstate; u64 mask = fpstate->user_xfeatures; u32 lmask; u32 hmask; int err; /* Optimize away writing unnecessary xfeatures: */ if (fpu_state_size_dynamic()) mask &= xfeatures_need_sigframe_write(); lmask = mask; hmask = mask >> 32; xfd_validate_state(fpstate, mask, false); stac(); XSTATE_OP(XSAVE, buf, lmask, hmask, err); clac(); if (!err) err = update_pkru_in_sigframe(buf, mask, pkru); return err; } /* * Restore xstate from user space xsave area. */ static inline int xrstor_from_user_sigframe(struct xregs_state __user *buf, u64 mask) { struct xregs_state *xstate = ((__force struct xregs_state *)buf); u32 lmask = mask; u32 hmask = mask >> 32; int err; xfd_validate_state(current->thread.fpu.fpstate, mask, true); stac(); XSTATE_OP(XRSTOR, xstate, lmask, hmask, err); clac(); return err; } /* * Restore xstate from kernel space xsave area, return an error code instead of * an exception. */ static inline int os_xrstor_safe(struct fpstate *fpstate, u64 mask) { struct xregs_state *xstate = &fpstate->regs.xsave; u32 lmask = mask; u32 hmask = mask >> 32; int err; /* Ensure that XFD is up to date */ xfd_update_state(fpstate); if (cpu_feature_enabled(X86_FEATURE_XSAVES)) XSTATE_OP(XRSTORS, xstate, lmask, hmask, err); else XSTATE_OP(XRSTOR, xstate, lmask, hmask, err); return err; } #endif |
| 154 154 | 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 | // SPDX-License-Identifier: GPL-2.0 /* * drivers/base/power/wakeup.c - System wakeup events framework * * Copyright (c) 2010 Rafael J. Wysocki <rjw@sisk.pl>, Novell Inc. */ #define pr_fmt(fmt) "PM: " fmt #include <linux/device.h> #include <linux/slab.h> #include <linux/sched/signal.h> #include <linux/capability.h> #include <linux/export.h> #include <linux/suspend.h> #include <linux/seq_file.h> #include <linux/debugfs.h> #include <linux/pm_wakeirq.h> #include <trace/events/power.h> #include "power.h" #define list_for_each_entry_rcu_locked(pos, head, member) \ list_for_each_entry_rcu(pos, head, member, \ srcu_read_lock_held(&wakeup_srcu)) /* * If set, the suspend/hibernate code will abort transitions to a sleep state * if wakeup events are registered during or immediately before the transition. */ bool events_check_enabled __read_mostly; /* First wakeup IRQ seen by the kernel in the last cycle. */ static unsigned int wakeup_irq[2] __read_mostly; static DEFINE_RAW_SPINLOCK(wakeup_irq_lock); /* If greater than 0 and the system is suspending, terminate the suspend. */ static atomic_t pm_abort_suspend __read_mostly; /* * Combined counters of registered wakeup events and wakeup events in progress. * They need to be modified together atomically, so it's better to use one * atomic variable to hold them both. */ static atomic_t combined_event_count = ATOMIC_INIT(0); #define IN_PROGRESS_BITS (sizeof(int) * 4) #define MAX_IN_PROGRESS ((1 << IN_PROGRESS_BITS) - 1) static void split_counters(unsigned int *cnt, unsigned int *inpr) { unsigned int comb = atomic_read(&combined_event_count); *cnt = (comb >> IN_PROGRESS_BITS); *inpr = comb & MAX_IN_PROGRESS; } /* A preserved old value of the events counter. */ static unsigned int saved_count; static DEFINE_RAW_SPINLOCK(events_lock); static void pm_wakeup_timer_fn(struct timer_list *t); static LIST_HEAD(wakeup_sources); static DECLARE_WAIT_QUEUE_HEAD(wakeup_count_wait_queue); DEFINE_STATIC_SRCU(wakeup_srcu); static struct wakeup_source deleted_ws = { .name = "deleted", .lock = __SPIN_LOCK_UNLOCKED(deleted_ws.lock), }; static DEFINE_IDA(wakeup_ida); /** * wakeup_source_create - Create a struct wakeup_source object. * @name: Name of the new wakeup source. */ struct wakeup_source *wakeup_source_create(const char *name) { struct wakeup_source *ws; const char *ws_name; int id; ws = kzalloc(sizeof(*ws), GFP_KERNEL); if (!ws) goto err_ws; ws_name = kstrdup_const(name, GFP_KERNEL); if (!ws_name) goto err_name; ws->name = ws_name; id = ida_alloc(&wakeup_ida, GFP_KERNEL); if (id < 0) goto err_id; ws->id = id; return ws; err_id: kfree_const(ws->name); err_name: kfree(ws); err_ws: return NULL; } EXPORT_SYMBOL_GPL(wakeup_source_create); /* * Record wakeup_source statistics being deleted into a dummy wakeup_source. */ static void wakeup_source_record(struct wakeup_source *ws) { unsigned long flags; spin_lock_irqsave(&deleted_ws.lock, flags); if (ws->event_count) { deleted_ws.total_time = ktime_add(deleted_ws.total_time, ws->total_time); deleted_ws.prevent_sleep_time = ktime_add(deleted_ws.prevent_sleep_time, ws->prevent_sleep_time); deleted_ws.max_time = ktime_compare(deleted_ws.max_time, ws->max_time) > 0 ? deleted_ws.max_time : ws->max_time; deleted_ws.event_count += ws->event_count; deleted_ws.active_count += ws->active_count; deleted_ws.relax_count += ws->relax_count; deleted_ws.expire_count += ws->expire_count; deleted_ws.wakeup_count += ws->wakeup_count; } spin_unlock_irqrestore(&deleted_ws.lock, flags); } static void wakeup_source_free(struct wakeup_source *ws) { ida_free(&wakeup_ida, ws->id); kfree_const(ws->name); kfree(ws); } /** * wakeup_source_destroy - Destroy a struct wakeup_source object. * @ws: Wakeup source to destroy. * * Use only for wakeup source objects created with wakeup_source_create(). */ void wakeup_source_destroy(struct wakeup_source *ws) { if (!ws) return; __pm_relax(ws); wakeup_source_record(ws); wakeup_source_free(ws); } EXPORT_SYMBOL_GPL(wakeup_source_destroy); /** * wakeup_source_add - Add given object to the list of wakeup sources. * @ws: Wakeup source object to add to the list. */ void wakeup_source_add(struct wakeup_source *ws) { unsigned long flags; if (WARN_ON(!ws)) return; spin_lock_init(&ws->lock); timer_setup(&ws->timer, pm_wakeup_timer_fn, 0); ws->active = false; raw_spin_lock_irqsave(&events_lock, flags); list_add_rcu(&ws->entry, &wakeup_sources); raw_spin_unlock_irqrestore(&events_lock, flags); } EXPORT_SYMBOL_GPL(wakeup_source_add); /** * wakeup_source_remove - Remove given object from the wakeup sources list. * @ws: Wakeup source object to remove from the list. */ void wakeup_source_remove(struct wakeup_source *ws) { unsigned long flags; if (WARN_ON(!ws)) return; raw_spin_lock_irqsave(&events_lock, flags); list_del_rcu(&ws->entry); raw_spin_unlock_irqrestore(&events_lock, flags); synchronize_srcu(&wakeup_srcu); del_timer_sync(&ws->timer); /* * Clear timer.function to make wakeup_source_not_registered() treat * this wakeup source as not registered. */ ws->timer.function = NULL; } EXPORT_SYMBOL_GPL(wakeup_source_remove); /** * wakeup_source_register - Create wakeup source and add it to the list. * @dev: Device this wakeup source is associated with (or NULL if virtual). * @name: Name of the wakeup source to register. */ struct wakeup_source *wakeup_source_register(struct device *dev, const char *name) { struct wakeup_source *ws; int ret; ws = wakeup_source_create(name); if (ws) { if (!dev || device_is_registered(dev)) { ret = wakeup_source_sysfs_add(dev, ws); if (ret) { wakeup_source_free(ws); return NULL; } } wakeup_source_add(ws); } return ws; } EXPORT_SYMBOL_GPL(wakeup_source_register); /** * wakeup_source_unregister - Remove wakeup source from the list and remove it. * @ws: Wakeup source object to unregister. */ void wakeup_source_unregister(struct wakeup_source *ws) { if (ws) { wakeup_source_remove(ws); if (ws->dev) wakeup_source_sysfs_remove(ws); wakeup_source_destroy(ws); } } EXPORT_SYMBOL_GPL(wakeup_source_unregister); /** * wakeup_sources_read_lock - Lock wakeup source list for read. * * Returns an index of srcu lock for struct wakeup_srcu. * This index must be passed to the matching wakeup_sources_read_unlock(). */ int wakeup_sources_read_lock(void) { return srcu_read_lock(&wakeup_srcu); } EXPORT_SYMBOL_GPL(wakeup_sources_read_lock); /** * wakeup_sources_read_unlock - Unlock wakeup source list. * @idx: return value from corresponding wakeup_sources_read_lock() */ void wakeup_sources_read_unlock(int idx) { srcu_read_unlock(&wakeup_srcu, idx); } EXPORT_SYMBOL_GPL(wakeup_sources_read_unlock); /** * wakeup_sources_walk_start - Begin a walk on wakeup source list * * Returns first object of the list of wakeup sources. * * Note that to be safe, wakeup sources list needs to be locked by calling * wakeup_source_read_lock() for this. */ struct wakeup_source *wakeup_sources_walk_start(void) { struct list_head *ws_head = &wakeup_sources; return list_entry_rcu(ws_head->next, struct wakeup_source, entry); } EXPORT_SYMBOL_GPL(wakeup_sources_walk_start); /** * wakeup_sources_walk_next - Get next wakeup source from the list * @ws: Previous wakeup source object * * Note that to be safe, wakeup sources list needs to be locked by calling * wakeup_source_read_lock() for this. */ struct wakeup_source *wakeup_sources_walk_next(struct wakeup_source *ws) { struct list_head *ws_head = &wakeup_sources; return list_next_or_null_rcu(ws_head, &ws->entry, struct wakeup_source, entry); } EXPORT_SYMBOL_GPL(wakeup_sources_walk_next); /** * device_wakeup_attach - Attach a wakeup source object to a device object. * @dev: Device to handle. * @ws: Wakeup source object to attach to @dev. * * This causes @dev to be treated as a wakeup device. */ static int device_wakeup_attach(struct device *dev, struct wakeup_source *ws) { spin_lock_irq(&dev->power.lock); if (dev->power.wakeup) { spin_unlock_irq(&dev->power.lock); return -EEXIST; } dev->power.wakeup = ws; if (dev->power.wakeirq) device_wakeup_attach_irq(dev, dev->power.wakeirq); spin_unlock_irq(&dev->power.lock); return 0; } /** * device_wakeup_enable - Enable given device to be a wakeup source. * @dev: Device to handle. * * Create a wakeup source object, register it and attach it to @dev. */ int device_wakeup_enable(struct device *dev) { struct wakeup_source *ws; int ret; if (!dev || !dev->power.can_wakeup) return -EINVAL; if (pm_suspend_target_state != PM_SUSPEND_ON) dev_dbg(dev, "Suspicious %s() during system transition!\n", __func__); ws = wakeup_source_register(dev, dev_name(dev)); if (!ws) return -ENOMEM; ret = device_wakeup_attach(dev, ws); if (ret) wakeup_source_unregister(ws); return ret; } EXPORT_SYMBOL_GPL(device_wakeup_enable); /** * device_wakeup_attach_irq - Attach a wakeirq to a wakeup source * @dev: Device to handle * @wakeirq: Device specific wakeirq entry * * Attach a device wakeirq to the wakeup source so the device * wake IRQ can be configured automatically for suspend and * resume. * * Call under the device's power.lock lock. */ void device_wakeup_attach_irq(struct device *dev, struct wake_irq *wakeirq) { struct wakeup_source *ws; ws = dev->power.wakeup; if (!ws) return; if (ws->wakeirq) dev_err(dev, "Leftover wakeup IRQ found, overriding\n"); ws->wakeirq = wakeirq; } /** * device_wakeup_detach_irq - Detach a wakeirq from a wakeup source * @dev: Device to handle * * Removes a device wakeirq from the wakeup source. * * Call under the device's power.lock lock. */ void device_wakeup_detach_irq(struct device *dev) { struct wakeup_source *ws; ws = dev->power.wakeup; if (ws) ws->wakeirq = NULL; } /** * device_wakeup_arm_wake_irqs - * * Iterates over the list of device wakeirqs to arm them. */ void device_wakeup_arm_wake_irqs(void) { struct wakeup_source *ws; int srcuidx; srcuidx = srcu_read_lock(&wakeup_srcu); list_for_each_entry_rcu_locked(ws, &wakeup_sources, entry) dev_pm_arm_wake_irq(ws->wakeirq); srcu_read_unlock(&wakeup_srcu, srcuidx); } /** * device_wakeup_disarm_wake_irqs - * * Iterates over the list of device wakeirqs to disarm them. */ void device_wakeup_disarm_wake_irqs(void) { struct wakeup_source *ws; int srcuidx; srcuidx = srcu_read_lock(&wakeup_srcu); list_for_each_entry_rcu_locked(ws, &wakeup_sources, entry) dev_pm_disarm_wake_irq(ws->wakeirq); srcu_read_unlock(&wakeup_srcu, srcuidx); } /** * device_wakeup_detach - Detach a device's wakeup source object from it. * @dev: Device to detach the wakeup source object from. * * After it returns, @dev will not be treated as a wakeup device any more. */ static struct wakeup_source *device_wakeup_detach(struct device *dev) { struct wakeup_source *ws; spin_lock_irq(&dev->power.lock); ws = dev->power.wakeup; dev->power.wakeup = NULL; spin_unlock_irq(&dev->power.lock); return ws; } /** * device_wakeup_disable - Do not regard a device as a wakeup source any more. * @dev: Device to handle. * * Detach the @dev's wakeup source object from it, unregister this wakeup source * object and destroy it. */ void device_wakeup_disable(struct device *dev) { struct wakeup_source *ws; if (!dev || !dev->power.can_wakeup) return; ws = device_wakeup_detach(dev); wakeup_source_unregister(ws); } EXPORT_SYMBOL_GPL(device_wakeup_disable); /** * device_set_wakeup_capable - Set/reset device wakeup capability flag. * @dev: Device to handle. * @capable: Whether or not @dev is capable of waking up the system from sleep. * * If @capable is set, set the @dev's power.can_wakeup flag and add its * wakeup-related attributes to sysfs. Otherwise, unset the @dev's * power.can_wakeup flag and remove its wakeup-related attributes from sysfs. * * This function may sleep and it can't be called from any context where * sleeping is not allowed. */ void device_set_wakeup_capable(struct device *dev, bool capable) { if (!!dev->power.can_wakeup == !!capable) return; dev->power.can_wakeup = capable; if (device_is_registered(dev) && !list_empty(&dev->power.entry)) { if (capable) { int ret = wakeup_sysfs_add(dev); if (ret) dev_info(dev, "Wakeup sysfs attributes not added\n"); } else { wakeup_sysfs_remove(dev); } } } EXPORT_SYMBOL_GPL(device_set_wakeup_capable); /** * device_set_wakeup_enable - Enable or disable a device to wake up the system. * @dev: Device to handle. * @enable: enable/disable flag */ int device_set_wakeup_enable(struct device *dev, bool enable) { if (enable) return device_wakeup_enable(dev); device_wakeup_disable(dev); return 0; } EXPORT_SYMBOL_GPL(device_set_wakeup_enable); /** * wakeup_source_not_registered - validate the given wakeup source. * @ws: Wakeup source to be validated. */ static bool wakeup_source_not_registered(struct wakeup_source *ws) { /* * Use timer struct to check if the given source is initialized * by wakeup_source_add. */ return ws->timer.function != pm_wakeup_timer_fn; } /* * The functions below use the observation that each wakeup event starts a * period in which the system should not be suspended. The moment this period * will end depends on how the wakeup event is going to be processed after being * detected and all of the possible cases can be divided into two distinct * groups. * * First, a wakeup event may be detected by the same functional unit that will * carry out the entire processing of it and possibly will pass it to user space * for further processing. In that case the functional unit that has detected * the event may later "close" the "no suspend" period associated with it * directly as soon as it has been dealt with. The pair of pm_stay_awake() and * pm_relax(), balanced with each other, is supposed to be used in such * situations. * * Second, a wakeup event may be detected by one functional unit and processed * by another one. In that case the unit that has detected it cannot really * "close" the "no suspend" period associated with it, unless it knows in * advance what's going to happen to the event during processing. This * knowledge, however, may not be available to it, so it can simply specify time * to wait before the system can be suspended and pass it as the second * argument of pm_wakeup_event(). * * It is valid to call pm_relax() after pm_wakeup_event(), in which case the * "no suspend" period will be ended either by the pm_relax(), or by the timer * function executed when the timer expires, whichever comes first. */ /** * wakeup_source_activate - Mark given wakeup source as active. * @ws: Wakeup source to handle. * * Update the @ws' statistics and, if @ws has just been activated, notify the PM * core of the event by incrementing the counter of the wakeup events being * processed. */ static void wakeup_source_activate(struct wakeup_source *ws) { unsigned int cec; if (WARN_ONCE(wakeup_source_not_registered(ws), "unregistered wakeup source\n")) return; ws->active = true; ws->active_count++; ws->last_time = ktime_get(); if (ws->autosleep_enabled) ws->start_prevent_time = ws->last_time; /* Increment the counter of events in progress. */ cec = atomic_inc_return(&combined_event_count); trace_wakeup_source_activate(ws->name, cec); } /** * wakeup_source_report_event - Report wakeup event using the given source. * @ws: Wakeup source to report the event for. * @hard: If set, abort suspends in progress and wake up from suspend-to-idle. */ static void wakeup_source_report_event(struct wakeup_source *ws, bool hard) { ws->event_count++; /* This is racy, but the counter is approximate anyway. */ if (events_check_enabled) ws->wakeup_count++; if (!ws->active) wakeup_source_activate(ws); if (hard) pm_system_wakeup(); } /** * __pm_stay_awake - Notify the PM core of a wakeup event. * @ws: Wakeup source object associated with the source of the event. * * It is safe to call this function from interrupt context. */ void __pm_stay_awake(struct wakeup_source *ws) { unsigned long flags; if (!ws) return; spin_lock_irqsave(&ws->lock, flags); wakeup_source_report_event(ws, false); del_timer(&ws->timer); ws->timer_expires = 0; spin_unlock_irqrestore(&ws->lock, flags); } EXPORT_SYMBOL_GPL(__pm_stay_awake); /** * pm_stay_awake - Notify the PM core that a wakeup event is being processed. * @dev: Device the wakeup event is related to. * * Notify the PM core of a wakeup event (signaled by @dev) by calling * __pm_stay_awake for the @dev's wakeup source object. * * Call this function after detecting of a wakeup event if pm_relax() is going * to be called directly after processing the event (and possibly passing it to * user space for further processing). */ void pm_stay_awake(struct device *dev) { unsigned long flags; if (!dev) return; spin_lock_irqsave(&dev->power.lock, flags); __pm_stay_awake(dev->power.wakeup); spin_unlock_irqrestore(&dev->power.lock, flags); } EXPORT_SYMBOL_GPL(pm_stay_awake); #ifdef CONFIG_PM_AUTOSLEEP static void update_prevent_sleep_time(struct wakeup_source *ws, ktime_t now) { ktime_t delta = ktime_sub(now, ws->start_prevent_time); ws->prevent_sleep_time = ktime_add(ws->prevent_sleep_time, delta); } #else static inline void update_prevent_sleep_time(struct wakeup_source *ws, ktime_t now) {} #endif /** * wakeup_source_deactivate - Mark given wakeup source as inactive. * @ws: Wakeup source to handle. * * Update the @ws' statistics and notify the PM core that the wakeup source has * become inactive by decrementing the counter of wakeup events being processed * and incrementing the counter of registered wakeup events. */ static void wakeup_source_deactivate(struct wakeup_source *ws) { unsigned int cnt, inpr, cec; ktime_t duration; ktime_t now; ws->relax_count++; /* * __pm_relax() may be called directly or from a timer function. * If it is called directly right after the timer function has been * started, but before the timer function calls __pm_relax(), it is * possible that __pm_stay_awake() will be called in the meantime and * will set ws->active. Then, ws->active may be cleared immediately * by the __pm_relax() called from the timer function, but in such a * case ws->relax_count will be different from ws->active_count. */ if (ws->relax_count != ws->active_count) { ws->relax_count--; return; } ws->active = false; now = ktime_get(); duration = ktime_sub(now, ws->last_time); ws->total_time = ktime_add(ws->total_time, duration); if (ktime_to_ns(duration) > ktime_to_ns(ws->max_time)) ws->max_time = duration; ws->last_time = now; del_timer(&ws->timer); ws->timer_expires = 0; if (ws->autosleep_enabled) update_prevent_sleep_time(ws, now); /* * Increment the counter of registered wakeup events and decrement the * counter of wakeup events in progress simultaneously. */ cec = atomic_add_return(MAX_IN_PROGRESS, &combined_event_count); trace_wakeup_source_deactivate(ws->name, cec); split_counters(&cnt, &inpr); if (!inpr && waitqueue_active(&wakeup_count_wait_queue)) wake_up(&wakeup_count_wait_queue); } /** * __pm_relax - Notify the PM core that processing of a wakeup event has ended. * @ws: Wakeup source object associated with the source of the event. * * Call this function for wakeup events whose processing started with calling * __pm_stay_awake(). * * It is safe to call it from interrupt context. */ void __pm_relax(struct wakeup_source *ws) { unsigned long flags; if (!ws) return; spin_lock_irqsave(&ws->lock, flags); if (ws->active) wakeup_source_deactivate(ws); spin_unlock_irqrestore(&ws->lock, flags); } EXPORT_SYMBOL_GPL(__pm_relax); /** * pm_relax - Notify the PM core that processing of a wakeup event has ended. * @dev: Device that signaled the event. * * Execute __pm_relax() for the @dev's wakeup source object. */ void pm_relax(struct device *dev) { unsigned long flags; if (!dev) return; spin_lock_irqsave(&dev->power.lock, flags); __pm_relax(dev->power.wakeup); spin_unlock_irqrestore(&dev->power.lock, flags); } EXPORT_SYMBOL_GPL(pm_relax); /** * pm_wakeup_timer_fn - Delayed finalization of a wakeup event. * @t: timer list * * Call wakeup_source_deactivate() for the wakeup source whose address is stored * in @data if it is currently active and its timer has not been canceled and * the expiration time of the timer is not in future. */ static void pm_wakeup_timer_fn(struct timer_list *t) { struct wakeup_source *ws = from_timer(ws, t, timer); unsigned long flags; spin_lock_irqsave(&ws->lock, flags); if (ws->active && ws->timer_expires && time_after_eq(jiffies, ws->timer_expires)) { wakeup_source_deactivate(ws); ws->expire_count++; } spin_unlock_irqrestore(&ws->lock, flags); } /** * pm_wakeup_ws_event - Notify the PM core of a wakeup event. * @ws: Wakeup source object associated with the event source. * @msec: Anticipated event processing time (in milliseconds). * @hard: If set, abort suspends in progress and wake up from suspend-to-idle. * * Notify the PM core of a wakeup event whose source is @ws that will take * approximately @msec milliseconds to be processed by the kernel. If @ws is * not active, activate it. If @msec is nonzero, set up the @ws' timer to * execute pm_wakeup_timer_fn() in future. * * It is safe to call this function from interrupt context. */ void pm_wakeup_ws_event(struct wakeup_source *ws, unsigned int msec, bool hard) { unsigned long flags; unsigned long expires; if (!ws) return; spin_lock_irqsave(&ws->lock, flags); wakeup_source_report_event(ws, hard); if (!msec) { wakeup_source_deactivate(ws); goto unlock; } expires = jiffies + msecs_to_jiffies(msec); if (!expires) expires = 1; if (!ws->timer_expires || time_after(expires, ws->timer_expires)) { mod_timer(&ws->timer, expires); ws->timer_expires = expires; } unlock: spin_unlock_irqrestore(&ws->lock, flags); } EXPORT_SYMBOL_GPL(pm_wakeup_ws_event); /** * pm_wakeup_dev_event - Notify the PM core of a wakeup event. * @dev: Device the wakeup event is related to. * @msec: Anticipated event processing time (in milliseconds). * @hard: If set, abort suspends in progress and wake up from suspend-to-idle. * * Call pm_wakeup_ws_event() for the @dev's wakeup source object. */ void pm_wakeup_dev_event(struct device *dev, unsigned int msec, bool hard) { unsigned long flags; if (!dev) return; spin_lock_irqsave(&dev->power.lock, flags); pm_wakeup_ws_event(dev->power.wakeup, msec, hard); spin_unlock_irqrestore(&dev->power.lock, flags); } EXPORT_SYMBOL_GPL(pm_wakeup_dev_event); void pm_print_active_wakeup_sources(void) { struct wakeup_source *ws; int srcuidx, active = 0; struct wakeup_source *last_activity_ws = NULL; srcuidx = srcu_read_lock(&wakeup_srcu); list_for_each_entry_rcu_locked(ws, &wakeup_sources, entry) { if (ws->active) { pm_pr_dbg("active wakeup source: %s\n", ws->name); active = 1; } else if (!active && (!last_activity_ws || ktime_to_ns(ws->last_time) > ktime_to_ns(last_activity_ws->last_time))) { last_activity_ws = ws; } } if (!active && last_activity_ws) pm_pr_dbg("last active wakeup source: %s\n", last_activity_ws->name); srcu_read_unlock(&wakeup_srcu, srcuidx); } EXPORT_SYMBOL_GPL(pm_print_active_wakeup_sources); /** * pm_wakeup_pending - Check if power transition in progress should be aborted. * * Compare the current number of registered wakeup events with its preserved * value from the past and return true if new wakeup events have been registered * since the old value was stored. Also return true if the current number of * wakeup events being processed is different from zero. */ bool pm_wakeup_pending(void) { unsigned long flags; bool ret = false; raw_spin_lock_irqsave(&events_lock, flags); if (events_check_enabled) { unsigned int cnt, inpr; split_counters(&cnt, &inpr); ret = (cnt != saved_count || inpr > 0); events_check_enabled = !ret; } raw_spin_unlock_irqrestore(&events_lock, flags); if (ret) { pm_pr_dbg("Wakeup pending, aborting suspend\n"); pm_print_active_wakeup_sources(); } return ret || atomic_read(&pm_abort_suspend) > 0; } EXPORT_SYMBOL_GPL(pm_wakeup_pending); void pm_system_wakeup(void) { atomic_inc(&pm_abort_suspend); s2idle_wake(); } EXPORT_SYMBOL_GPL(pm_system_wakeup); void pm_system_cancel_wakeup(void) { atomic_dec_if_positive(&pm_abort_suspend); } void pm_wakeup_clear(unsigned int irq_number) { raw_spin_lock_irq(&wakeup_irq_lock); if (irq_number && wakeup_irq[0] == irq_number) wakeup_irq[0] = wakeup_irq[1]; else wakeup_irq[0] = 0; wakeup_irq[1] = 0; raw_spin_unlock_irq(&wakeup_irq_lock); if (!irq_number) atomic_set(&pm_abort_suspend, 0); } void pm_system_irq_wakeup(unsigned int irq_number) { unsigned long flags; raw_spin_lock_irqsave(&wakeup_irq_lock, flags); if (wakeup_irq[0] == 0) wakeup_irq[0] = irq_number; else if (wakeup_irq[1] == 0) wakeup_irq[1] = irq_number; else irq_number = 0; pm_pr_dbg("Triggering wakeup from IRQ %d\n", irq_number); raw_spin_unlock_irqrestore(&wakeup_irq_lock, flags); if (irq_number) pm_system_wakeup(); } unsigned int pm_wakeup_irq(void) { return wakeup_irq[0]; } /** * pm_get_wakeup_count - Read the number of registered wakeup events. * @count: Address to store the value at. * @block: Whether or not to block. * * Store the number of registered wakeup events at the address in @count. If * @block is set, block until the current number of wakeup events being * processed is zero. * * Return 'false' if the current number of wakeup events being processed is * nonzero. Otherwise return 'true'. */ bool pm_get_wakeup_count(unsigned int *count, bool block) { unsigned int cnt, inpr; if (block) { DEFINE_WAIT(wait); for (;;) { prepare_to_wait(&wakeup_count_wait_queue, &wait, TASK_INTERRUPTIBLE); split_counters(&cnt, &inpr); if (inpr == 0 || signal_pending(current)) break; pm_print_active_wakeup_sources(); schedule(); } finish_wait(&wakeup_count_wait_queue, &wait); } split_counters(&cnt, &inpr); *count = cnt; return !inpr; } /** * pm_save_wakeup_count - Save the current number of registered wakeup events. * @count: Value to compare with the current number of registered wakeup events. * * If @count is equal to the current number of registered wakeup events and the * current number of wakeup events being processed is zero, store @count as the * old number of registered wakeup events for pm_check_wakeup_events(), enable * wakeup events detection and return 'true'. Otherwise disable wakeup events * detection and return 'false'. */ bool pm_save_wakeup_count(unsigned int count) { unsigned int cnt, inpr; unsigned long flags; events_check_enabled = false; raw_spin_lock_irqsave(&events_lock, flags); split_counters(&cnt, &inpr); if (cnt == count && inpr == 0) { saved_count = count; events_check_enabled = true; } raw_spin_unlock_irqrestore(&events_lock, flags); return events_check_enabled; } #ifdef CONFIG_PM_AUTOSLEEP /** * pm_wakep_autosleep_enabled - Modify autosleep_enabled for all wakeup sources. * @set: Whether to set or to clear the autosleep_enabled flags. */ void pm_wakep_autosleep_enabled(bool set) { struct wakeup_source *ws; ktime_t now = ktime_get(); int srcuidx; srcuidx = srcu_read_lock(&wakeup_srcu); list_for_each_entry_rcu_locked(ws, &wakeup_sources, entry) { spin_lock_irq(&ws->lock); if (ws->autosleep_enabled != set) { ws->autosleep_enabled = set; if (ws->active) { if (set) ws->start_prevent_time = now; else update_prevent_sleep_time(ws, now); } } spin_unlock_irq(&ws->lock); } srcu_read_unlock(&wakeup_srcu, srcuidx); } #endif /* CONFIG_PM_AUTOSLEEP */ /** * print_wakeup_source_stats - Print wakeup source statistics information. * @m: seq_file to print the statistics into. * @ws: Wakeup source object to print the statistics for. */ static int print_wakeup_source_stats(struct seq_file *m, struct wakeup_source *ws) { unsigned long flags; ktime_t total_time; ktime_t max_time; unsigned long active_count; ktime_t active_time; ktime_t prevent_sleep_time; spin_lock_irqsave(&ws->lock, flags); total_time = ws->total_time; max_time = ws->max_time; prevent_sleep_time = ws->prevent_sleep_time; active_count = ws->active_count; if (ws->active) { ktime_t now = ktime_get(); active_time = ktime_sub(now, ws->last_time); total_time = ktime_add(total_time, active_time); if (active_time > max_time) max_time = active_time; if (ws->autosleep_enabled) prevent_sleep_time = ktime_add(prevent_sleep_time, ktime_sub(now, ws->start_prevent_time)); } else { active_time = 0; } seq_printf(m, "%-12s\t%lu\t\t%lu\t\t%lu\t\t%lu\t\t%lld\t\t%lld\t\t%lld\t\t%lld\t\t%lld\n", ws->name, active_count, ws->event_count, ws->wakeup_count, ws->expire_count, ktime_to_ms(active_time), ktime_to_ms(total_time), ktime_to_ms(max_time), ktime_to_ms(ws->last_time), ktime_to_ms(prevent_sleep_time)); spin_unlock_irqrestore(&ws->lock, flags); return 0; } static void *wakeup_sources_stats_seq_start(struct seq_file *m, loff_t *pos) { struct wakeup_source *ws; loff_t n = *pos; int *srcuidx = m->private; if (n == 0) { seq_puts(m, "name\t\tactive_count\tevent_count\twakeup_count\t" "expire_count\tactive_since\ttotal_time\tmax_time\t" "last_change\tprevent_suspend_time\n"); } *srcuidx = srcu_read_lock(&wakeup_srcu); list_for_each_entry_rcu_locked(ws, &wakeup_sources, entry) { if (n-- <= 0) return ws; } return NULL; } static void *wakeup_sources_stats_seq_next(struct seq_file *m, void *v, loff_t *pos) { struct wakeup_source *ws = v; struct wakeup_source *next_ws = NULL; ++(*pos); list_for_each_entry_continue_rcu(ws, &wakeup_sources, entry) { next_ws = ws; break; } if (!next_ws) print_wakeup_source_stats(m, &deleted_ws); return next_ws; } static void wakeup_sources_stats_seq_stop(struct seq_file *m, void *v) { int *srcuidx = m->private; srcu_read_unlock(&wakeup_srcu, *srcuidx); } /** * wakeup_sources_stats_seq_show - Print wakeup sources statistics information. * @m: seq_file to print the statistics into. * @v: wakeup_source of each iteration */ static int wakeup_sources_stats_seq_show(struct seq_file *m, void *v) { struct wakeup_source *ws = v; print_wakeup_source_stats(m, ws); return 0; } static const struct seq_operations wakeup_sources_stats_seq_ops = { .start = wakeup_sources_stats_seq_start, .next = wakeup_sources_stats_seq_next, .stop = wakeup_sources_stats_seq_stop, .show = wakeup_sources_stats_seq_show, }; static int wakeup_sources_stats_open(struct inode *inode, struct file *file) { return seq_open_private(file, &wakeup_sources_stats_seq_ops, sizeof(int)); } static const struct file_operations wakeup_sources_stats_fops = { .owner = THIS_MODULE, .open = wakeup_sources_stats_open, .read = seq_read, .llseek = seq_lseek, .release = seq_release_private, }; static int __init wakeup_sources_debugfs_init(void) { debugfs_create_file("wakeup_sources", 0444, NULL, NULL, &wakeup_sources_stats_fops); return 0; } postcore_initcall(wakeup_sources_debugfs_init); |
| 58 | 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 | // SPDX-License-Identifier: GPL-2.0-only /* * Connection tracking protocol helper module for GRE. * * GRE is a generic encapsulation protocol, which is generally not very * suited for NAT, as it has no protocol-specific part as port numbers. * * It has an optional key field, which may help us distinguishing two * connections between the same two hosts. * * GRE is defined in RFC 1701 and RFC 1702, as well as RFC 2784 * * PPTP is built on top of a modified version of GRE, and has a mandatory * field called "CallID", which serves us for the same purpose as the key * field in plain GRE. * * Documentation about PPTP can be found in RFC 2637 * * (C) 2000-2005 by Harald Welte <laforge@gnumonks.org> * * Development of this code funded by Astaro AG (http://www.astaro.com/) * * (C) 2006-2012 Patrick McHardy <kaber@trash.net> */ #include <linux/module.h> #include <linux/types.h> #include <linux/timer.h> #include <linux/list.h> #include <linux/seq_file.h> #include <linux/in.h> #include <linux/netdevice.h> #include <linux/skbuff.h> #include <linux/slab.h> #include <net/dst.h> #include <net/net_namespace.h> #include <net/netns/generic.h> #include <net/netfilter/nf_conntrack_l4proto.h> #include <net/netfilter/nf_conntrack_helper.h> #include <net/netfilter/nf_conntrack_core.h> #include <net/netfilter/nf_conntrack_timeout.h> #include <linux/netfilter/nf_conntrack_proto_gre.h> #include <linux/netfilter/nf_conntrack_pptp.h> static const unsigned int gre_timeouts[GRE_CT_MAX] = { [GRE_CT_UNREPLIED] = 30*HZ, [GRE_CT_REPLIED] = 180*HZ, }; /* used when expectation is added */ static DEFINE_SPINLOCK(keymap_lock); static inline struct nf_gre_net *gre_pernet(struct net *net) { return &net->ct.nf_ct_proto.gre; } static inline int gre_key_cmpfn(const struct nf_ct_gre_keymap *km, const struct nf_conntrack_tuple *t) { return km->tuple.src.l3num == t->src.l3num && !memcmp(&km->tuple.src.u3, &t->src.u3, sizeof(t->src.u3)) && !memcmp(&km->tuple.dst.u3, &t->dst.u3, sizeof(t->dst.u3)) && km->tuple.dst.protonum == t->dst.protonum && km->tuple.dst.u.all == t->dst.u.all; } /* look up the source key for a given tuple */ static __be16 gre_keymap_lookup(struct net *net, struct nf_conntrack_tuple *t) { struct nf_gre_net *net_gre = gre_pernet(net); struct nf_ct_gre_keymap *km; __be16 key = 0; list_for_each_entry_rcu(km, &net_gre->keymap_list, list) { if (gre_key_cmpfn(km, t)) { key = km->tuple.src.u.gre.key; break; } } pr_debug("lookup src key 0x%x for ", key); nf_ct_dump_tuple(t); return key; } /* add a single keymap entry, associate with specified master ct */ int nf_ct_gre_keymap_add(struct nf_conn *ct, enum ip_conntrack_dir dir, struct nf_conntrack_tuple *t) { struct net *net = nf_ct_net(ct); struct nf_gre_net *net_gre = gre_pernet(net); struct nf_ct_pptp_master *ct_pptp_info = nfct_help_data(ct); struct nf_ct_gre_keymap **kmp, *km; kmp = &ct_pptp_info->keymap[dir]; if (*kmp) { /* check whether it's a retransmission */ list_for_each_entry_rcu(km, &net_gre->keymap_list, list) { if (gre_key_cmpfn(km, t) && km == *kmp) return 0; } pr_debug("trying to override keymap_%s for ct %p\n", dir == IP_CT_DIR_REPLY ? "reply" : "orig", ct); return -EEXIST; } km = kmalloc(sizeof(*km), GFP_ATOMIC); if (!km) return -ENOMEM; memcpy(&km->tuple, t, sizeof(*t)); *kmp = km; pr_debug("adding new entry %p: ", km); nf_ct_dump_tuple(&km->tuple); spin_lock_bh(&keymap_lock); list_add_tail(&km->list, &net_gre->keymap_list); spin_unlock_bh(&keymap_lock); return 0; } EXPORT_SYMBOL_GPL(nf_ct_gre_keymap_add); /* destroy the keymap entries associated with specified master ct */ void nf_ct_gre_keymap_destroy(struct nf_conn *ct) { struct nf_ct_pptp_master *ct_pptp_info = nfct_help_data(ct); enum ip_conntrack_dir dir; pr_debug("entering for ct %p\n", ct); spin_lock_bh(&keymap_lock); for (dir = IP_CT_DIR_ORIGINAL; dir < IP_CT_DIR_MAX; dir++) { if (ct_pptp_info->keymap[dir]) { pr_debug("removing %p from list\n", ct_pptp_info->keymap[dir]); list_del_rcu(&ct_pptp_info->keymap[dir]->list); kfree_rcu(ct_pptp_info->keymap[dir], rcu); ct_pptp_info->keymap[dir] = NULL; } } spin_unlock_bh(&keymap_lock); } EXPORT_SYMBOL_GPL(nf_ct_gre_keymap_destroy); /* PUBLIC CONNTRACK PROTO HELPER FUNCTIONS */ /* gre hdr info to tuple */ bool gre_pkt_to_tuple(const struct sk_buff *skb, unsigned int dataoff, struct net *net, struct nf_conntrack_tuple *tuple) { const struct pptp_gre_header *pgrehdr; struct pptp_gre_header _pgrehdr; __be16 srckey; const struct gre_base_hdr *grehdr; struct gre_base_hdr _grehdr; /* first only delinearize old RFC1701 GRE header */ grehdr = skb_header_pointer(skb, dataoff, sizeof(_grehdr), &_grehdr); if (!grehdr || (grehdr->flags & GRE_VERSION) != GRE_VERSION_1) { /* try to behave like "nf_conntrack_proto_generic" */ tuple->src.u.all = 0; tuple->dst.u.all = 0; return true; } /* PPTP header is variable length, only need up to the call_id field */ pgrehdr = skb_header_pointer(skb, dataoff, 8, &_pgrehdr); if (!pgrehdr) return true; if (grehdr->protocol != GRE_PROTO_PPP) { pr_debug("Unsupported GRE proto(0x%x)\n", ntohs(grehdr->protocol)); return false; } tuple->dst.u.gre.key = pgrehdr->call_id; srckey = gre_keymap_lookup(net, tuple); tuple->src.u.gre.key = srckey; return true; } #ifdef CONFIG_NF_CONNTRACK_PROCFS /* print private data for conntrack */ static void gre_print_conntrack(struct seq_file *s, struct nf_conn *ct) { seq_printf(s, "timeout=%u, stream_timeout=%u ", (ct->proto.gre.timeout / HZ), (ct->proto.gre.stream_timeout / HZ)); } #endif static unsigned int *gre_get_timeouts(struct net *net) { return gre_pernet(net)->timeouts; } /* Returns verdict for packet, and may modify conntrack */ int nf_conntrack_gre_packet(struct nf_conn *ct, struct sk_buff *skb, unsigned int dataoff, enum ip_conntrack_info ctinfo, const struct nf_hook_state *state) { unsigned long status; if (!nf_ct_is_confirmed(ct)) { unsigned int *timeouts = nf_ct_timeout_lookup(ct); if (!timeouts) timeouts = gre_get_timeouts(nf_ct_net(ct)); /* initialize to sane value. Ideally a conntrack helper * (e.g. in case of pptp) is increasing them */ ct->proto.gre.stream_timeout = timeouts[GRE_CT_REPLIED]; ct->proto.gre.timeout = timeouts[GRE_CT_UNREPLIED]; } status = READ_ONCE(ct->status); /* If we've seen traffic both ways, this is a GRE connection. * Extend timeout. */ if (status & IPS_SEEN_REPLY) { nf_ct_refresh_acct(ct, ctinfo, skb, ct->proto.gre.stream_timeout); /* never set ASSURED for IPS_NAT_CLASH, they time out soon */ if (unlikely((status & IPS_NAT_CLASH))) return NF_ACCEPT; /* Also, more likely to be important, and not a probe. */ if (!test_and_set_bit(IPS_ASSURED_BIT, &ct->status)) nf_conntrack_event_cache(IPCT_ASSURED, ct); } else nf_ct_refresh_acct(ct, ctinfo, skb, ct->proto.gre.timeout); return NF_ACCEPT; } #ifdef CONFIG_NF_CONNTRACK_TIMEOUT #include <linux/netfilter/nfnetlink.h> #include <linux/netfilter/nfnetlink_cttimeout.h> static int gre_timeout_nlattr_to_obj(struct nlattr *tb[], struct net *net, void *data) { unsigned int *timeouts = data; struct nf_gre_net *net_gre = gre_pernet(net); if (!timeouts) timeouts = gre_get_timeouts(net); /* set default timeouts for GRE. */ timeouts[GRE_CT_UNREPLIED] = net_gre->timeouts[GRE_CT_UNREPLIED]; timeouts[GRE_CT_REPLIED] = net_gre->timeouts[GRE_CT_REPLIED]; if (tb[CTA_TIMEOUT_GRE_UNREPLIED]) { timeouts[GRE_CT_UNREPLIED] = ntohl(nla_get_be32(tb[CTA_TIMEOUT_GRE_UNREPLIED])) * HZ; } if (tb[CTA_TIMEOUT_GRE_REPLIED]) { timeouts[GRE_CT_REPLIED] = ntohl(nla_get_be32(tb[CTA_TIMEOUT_GRE_REPLIED])) * HZ; } return 0; } static int gre_timeout_obj_to_nlattr(struct sk_buff *skb, const void *data) { const unsigned int *timeouts = data; if (nla_put_be32(skb, CTA_TIMEOUT_GRE_UNREPLIED, htonl(timeouts[GRE_CT_UNREPLIED] / HZ)) || nla_put_be32(skb, CTA_TIMEOUT_GRE_REPLIED, htonl(timeouts[GRE_CT_REPLIED] / HZ))) goto nla_put_failure; return 0; nla_put_failure: return -ENOSPC; } static const struct nla_policy gre_timeout_nla_policy[CTA_TIMEOUT_GRE_MAX+1] = { [CTA_TIMEOUT_GRE_UNREPLIED] = { .type = NLA_U32 }, [CTA_TIMEOUT_GRE_REPLIED] = { .type = NLA_U32 }, }; #endif /* CONFIG_NF_CONNTRACK_TIMEOUT */ void nf_conntrack_gre_init_net(struct net *net) { struct nf_gre_net *net_gre = gre_pernet(net); int i; INIT_LIST_HEAD(&net_gre->keymap_list); for (i = 0; i < GRE_CT_MAX; i++) net_gre->timeouts[i] = gre_timeouts[i]; } /* protocol helper struct */ const struct nf_conntrack_l4proto nf_conntrack_l4proto_gre = { .l4proto = IPPROTO_GRE, .allow_clash = true, #ifdef CONFIG_NF_CONNTRACK_PROCFS .print_conntrack = gre_print_conntrack, #endif #if IS_ENABLED(CONFIG_NF_CT_NETLINK) .tuple_to_nlattr = nf_ct_port_tuple_to_nlattr, .nlattr_tuple_size = nf_ct_port_nlattr_tuple_size, .nlattr_to_tuple = nf_ct_port_nlattr_to_tuple, .nla_policy = nf_ct_port_nla_policy, #endif #ifdef CONFIG_NF_CONNTRACK_TIMEOUT .ctnl_timeout = { .nlattr_to_obj = gre_timeout_nlattr_to_obj, .obj_to_nlattr = gre_timeout_obj_to_nlattr, .nlattr_max = CTA_TIMEOUT_GRE_MAX, .obj_size = sizeof(unsigned int) * GRE_CT_MAX, .nla_policy = gre_timeout_nla_policy, }, #endif /* CONFIG_NF_CONNTRACK_TIMEOUT */ }; |
| 327 324 325 324 | 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 | // SPDX-License-Identifier: GPL-2.0-only /* * fs/userfaultfd.c * * Copyright (C) 2007 Davide Libenzi <davidel@xmailserver.org> * Copyright (C) 2008-2009 Red Hat, Inc. * Copyright (C) 2015 Red Hat, Inc. * * Some part derived from fs/eventfd.c (anon inode setup) and * mm/ksm.c (mm hashing). */ #include <linux/list.h> #include <linux/hashtable.h> #include <linux/sched/signal.h> #include <linux/sched/mm.h> #include <linux/mm.h> #include <linux/mm_inline.h> #include <linux/mmu_notifier.h> #include <linux/poll.h> #include <linux/slab.h> #include <linux/seq_file.h> #include <linux/file.h> #include <linux/bug.h> #include <linux/anon_inodes.h> #include <linux/syscalls.h> #include <linux/userfaultfd_k.h> #include <linux/mempolicy.h> #include <linux/ioctl.h> #include <linux/security.h> #include <linux/hugetlb.h> #include <linux/swapops.h> #include <linux/miscdevice.h> #include <linux/uio.h> static int sysctl_unprivileged_userfaultfd __read_mostly; #ifdef CONFIG_SYSCTL static const struct ctl_table vm_userfaultfd_table[] = { { .procname = "unprivileged_userfaultfd", .data = &sysctl_unprivileged_userfaultfd, .maxlen = sizeof(sysctl_unprivileged_userfaultfd), .mode = 0644, .proc_handler = proc_dointvec_minmax, .extra1 = SYSCTL_ZERO, .extra2 = SYSCTL_ONE, }, }; #endif static struct kmem_cache *userfaultfd_ctx_cachep __ro_after_init; struct userfaultfd_fork_ctx { struct userfaultfd_ctx *orig; struct userfaultfd_ctx *new; struct list_head list; }; struct userfaultfd_unmap_ctx { struct userfaultfd_ctx *ctx; unsigned long start; unsigned long end; struct list_head list; }; struct userfaultfd_wait_queue { struct uffd_msg msg; wait_queue_entry_t wq; struct userfaultfd_ctx *ctx; bool waken; }; struct userfaultfd_wake_range { unsigned long start; unsigned long len; }; /* internal indication that UFFD_API ioctl was successfully executed */ #define UFFD_FEATURE_INITIALIZED (1u << 31) static bool userfaultfd_is_initialized(struct userfaultfd_ctx *ctx) { return ctx->features & UFFD_FEATURE_INITIALIZED; } static bool userfaultfd_wp_async_ctx(struct userfaultfd_ctx *ctx) { return ctx && (ctx->features & UFFD_FEATURE_WP_ASYNC); } /* * Whether WP_UNPOPULATED is enabled on the uffd context. It is only * meaningful when userfaultfd_wp()==true on the vma and when it's * anonymous. */ bool userfaultfd_wp_unpopulated(struct vm_area_struct *vma) { struct userfaultfd_ctx *ctx = vma->vm_userfaultfd_ctx.ctx; if (!ctx) return false; return ctx->features & UFFD_FEATURE_WP_UNPOPULATED; } static int userfaultfd_wake_function(wait_queue_entry_t *wq, unsigned mode, int wake_flags, void *key) { struct userfaultfd_wake_range *range = key; int ret; struct userfaultfd_wait_queue *uwq; unsigned long start, len; uwq = container_of(wq, struct userfaultfd_wait_queue, wq); ret = 0; /* len == 0 means wake all */ start = range->start; len = range->len; if (len && (start > uwq->msg.arg.pagefault.address || start + len <= uwq->msg.arg.pagefault.address)) goto out; WRITE_ONCE(uwq->waken, true); /* * The Program-Order guarantees provided by the scheduler * ensure uwq->waken is visible before the task is woken. */ ret = wake_up_state(wq->private, mode); if (ret) { /* * Wake only once, autoremove behavior. * * After the effect of list_del_init is visible to the other * CPUs, the waitqueue may disappear from under us, see the * !list_empty_careful() in handle_userfault(). * * try_to_wake_up() has an implicit smp_mb(), and the * wq->private is read before calling the extern function * "wake_up_state" (which in turns calls try_to_wake_up). */ list_del_init(&wq->entry); } out: return ret; } /** * userfaultfd_ctx_get - Acquires a reference to the internal userfaultfd * context. * @ctx: [in] Pointer to the userfaultfd context. */ static void userfaultfd_ctx_get(struct userfaultfd_ctx *ctx) { refcount_inc(&ctx->refcount); } /** * userfaultfd_ctx_put - Releases a reference to the internal userfaultfd * context. * @ctx: [in] Pointer to userfaultfd context. * * The userfaultfd context reference must have been previously acquired either * with userfaultfd_ctx_get() or userfaultfd_ctx_fdget(). */ static void userfaultfd_ctx_put(struct userfaultfd_ctx *ctx) { if (refcount_dec_and_test(&ctx->refcount)) { VM_BUG_ON(spin_is_locked(&ctx->fault_pending_wqh.lock)); VM_BUG_ON(waitqueue_active(&ctx->fault_pending_wqh)); VM_BUG_ON(spin_is_locked(&ctx->fault_wqh.lock)); VM_BUG_ON(waitqueue_active(&ctx->fault_wqh)); VM_BUG_ON(spin_is_locked(&ctx->event_wqh.lock)); VM_BUG_ON(waitqueue_active(&ctx->event_wqh)); VM_BUG_ON(spin_is_locked(&ctx->fd_wqh.lock)); VM_BUG_ON(waitqueue_active(&ctx->fd_wqh)); mmdrop(ctx->mm); kmem_cache_free(userfaultfd_ctx_cachep, ctx); } } static inline void msg_init(struct uffd_msg *msg) { BUILD_BUG_ON(sizeof(struct uffd_msg) != 32); /* * Must use memset to zero out the paddings or kernel data is * leaked to userland. */ memset(msg, 0, sizeof(struct uffd_msg)); } static inline struct uffd_msg userfault_msg(unsigned long address, unsigned long real_address, unsigned int flags, unsigned long reason, unsigned int features) { struct uffd_msg msg; msg_init(&msg); msg.event = UFFD_EVENT_PAGEFAULT; msg.arg.pagefault.address = (features & UFFD_FEATURE_EXACT_ADDRESS) ? real_address : address; /* * These flags indicate why the userfault occurred: * - UFFD_PAGEFAULT_FLAG_WP indicates a write protect fault. * - UFFD_PAGEFAULT_FLAG_MINOR indicates a minor fault. * - Neither of these flags being set indicates a MISSING fault. * * Separately, UFFD_PAGEFAULT_FLAG_WRITE indicates it was a write * fault. Otherwise, it was a read fault. */ if (flags & FAULT_FLAG_WRITE) msg.arg.pagefault.flags |= UFFD_PAGEFAULT_FLAG_WRITE; if (reason & VM_UFFD_WP) msg.arg.pagefault.flags |= UFFD_PAGEFAULT_FLAG_WP; if (reason & VM_UFFD_MINOR) msg.arg.pagefault.flags |= UFFD_PAGEFAULT_FLAG_MINOR; if (features & UFFD_FEATURE_THREAD_ID) msg.arg.pagefault.feat.ptid = task_pid_vnr(current); return msg; } #ifdef CONFIG_HUGETLB_PAGE /* * Same functionality as userfaultfd_must_wait below with modifications for * hugepmd ranges. */ static inline bool userfaultfd_huge_must_wait(struct userfaultfd_ctx *ctx, struct vm_fault *vmf, unsigned long reason) { struct vm_area_struct *vma = vmf->vma; pte_t *ptep, pte; bool ret = true; assert_fault_locked(vmf); ptep = hugetlb_walk(vma, vmf->address, vma_mmu_pagesize(vma)); if (!ptep) goto out; ret = false; pte = huge_ptep_get(vma->vm_mm, vmf->address, ptep); /* * Lockless access: we're in a wait_event so it's ok if it * changes under us. PTE markers should be handled the same as none * ptes here. */ if (huge_pte_none_mostly(pte)) ret = true; if (!huge_pte_write(pte) && (reason & VM_UFFD_WP)) ret = true; out: return ret; } #else static inline bool userfaultfd_huge_must_wait(struct userfaultfd_ctx *ctx, struct vm_fault *vmf, unsigned long reason) { return false; /* should never get here */ } #endif /* CONFIG_HUGETLB_PAGE */ /* * Verify the pagetables are still not ok after having reigstered into * the fault_pending_wqh to avoid userland having to UFFDIO_WAKE any * userfault that has already been resolved, if userfaultfd_read_iter and * UFFDIO_COPY|ZEROPAGE are being run simultaneously on two different * threads. */ static inline bool userfaultfd_must_wait(struct userfaultfd_ctx *ctx, struct vm_fault *vmf, unsigned long reason) { struct mm_struct *mm = ctx->mm; unsigned long address = vmf->address; pgd_t *pgd; p4d_t *p4d; pud_t *pud; pmd_t *pmd, _pmd; pte_t *pte; pte_t ptent; bool ret = true; assert_fault_locked(vmf); 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); again: _pmd = pmdp_get_lockless(pmd); if (pmd_none(_pmd)) goto out; ret = false; if (!pmd_present(_pmd) || pmd_devmap(_pmd)) goto out; if (pmd_trans_huge(_pmd)) { if (!pmd_write(_pmd) && (reason & VM_UFFD_WP)) ret = true; goto out; } pte = pte_offset_map(pmd, address); if (!pte) { ret = true; goto again; } /* * Lockless access: we're in a wait_event so it's ok if it * changes under us. PTE markers should be handled the same as none * ptes here. */ ptent = ptep_get(pte); if (pte_none_mostly(ptent)) ret = true; if (!pte_write(ptent) && (reason & VM_UFFD_WP)) ret = true; pte_unmap(pte); out: return ret; } static inline unsigned int userfaultfd_get_blocking_state(unsigned int flags) { if (flags & FAULT_FLAG_INTERRUPTIBLE) return TASK_INTERRUPTIBLE; if (flags & FAULT_FLAG_KILLABLE) return TASK_KILLABLE; return TASK_UNINTERRUPTIBLE; } /* * The locking rules involved in returning VM_FAULT_RETRY depending on * FAULT_FLAG_ALLOW_RETRY, FAULT_FLAG_RETRY_NOWAIT and * FAULT_FLAG_KILLABLE are not straightforward. The "Caution" * recommendation in __lock_page_or_retry is not an understatement. * * If FAULT_FLAG_ALLOW_RETRY is set, the mmap_lock must be released * before returning VM_FAULT_RETRY only if FAULT_FLAG_RETRY_NOWAIT is * not set. * * If FAULT_FLAG_ALLOW_RETRY is set but FAULT_FLAG_KILLABLE is not * set, VM_FAULT_RETRY can still be returned if and only if there are * fatal_signal_pending()s, and the mmap_lock must be released before * returning it. */ vm_fault_t handle_userfault(struct vm_fault *vmf, unsigned long reason) { struct vm_area_struct *vma = vmf->vma; struct mm_struct *mm = vma->vm_mm; struct userfaultfd_ctx *ctx; struct userfaultfd_wait_queue uwq; vm_fault_t ret = VM_FAULT_SIGBUS; bool must_wait; unsigned int blocking_state; /* * We don't do userfault handling for the final child pid update * and when coredumping (faults triggered by get_dump_page()). */ if (current->flags & (PF_EXITING|PF_DUMPCORE)) goto out; assert_fault_locked(vmf); ctx = vma->vm_userfaultfd_ctx.ctx; if (!ctx) goto out; BUG_ON(ctx->mm != mm); /* Any unrecognized flag is a bug. */ VM_BUG_ON(reason & ~__VM_UFFD_FLAGS); /* 0 or > 1 flags set is a bug; we expect exactly 1. */ VM_BUG_ON(!reason || (reason & (reason - 1))); if (ctx->features & UFFD_FEATURE_SIGBUS) goto out; if (!(vmf->flags & FAULT_FLAG_USER) && (ctx->flags & UFFD_USER_MODE_ONLY)) goto out; /* * If it's already released don't get it. This avoids to loop * in __get_user_pages if userfaultfd_release waits on the * caller of handle_userfault to release the mmap_lock. */ if (unlikely(READ_ONCE(ctx->released))) { /* * Don't return VM_FAULT_SIGBUS in this case, so a non * cooperative manager can close the uffd after the * last UFFDIO_COPY, without risking to trigger an * involuntary SIGBUS if the process was starting the * userfaultfd while the userfaultfd was still armed * (but after the last UFFDIO_COPY). If the uffd * wasn't already closed when the userfault reached * this point, that would normally be solved by * userfaultfd_must_wait returning 'false'. * * If we were to return VM_FAULT_SIGBUS here, the non * cooperative manager would be instead forced to * always call UFFDIO_UNREGISTER before it can safely * close the uffd. */ ret = VM_FAULT_NOPAGE; goto out; } /* * Check that we can return VM_FAULT_RETRY. * * NOTE: it should become possible to return VM_FAULT_RETRY * even if FAULT_FLAG_TRIED is set without leading to gup() * -EBUSY failures, if the userfaultfd is to be extended for * VM_UFFD_WP tracking and we intend to arm the userfault * without first stopping userland access to the memory. For * VM_UFFD_MISSING userfaults this is enough for now. */ if (unlikely(!(vmf->flags & FAULT_FLAG_ALLOW_RETRY))) { /* * Validate the invariant that nowait must allow retry * to be sure not to return SIGBUS erroneously on * nowait invocations. */ BUG_ON(vmf->flags & FAULT_FLAG_RETRY_NOWAIT); #ifdef CONFIG_DEBUG_VM if (printk_ratelimit()) { printk(KERN_WARNING "FAULT_FLAG_ALLOW_RETRY missing %x\n", vmf->flags); dump_stack(); } #endif goto out; } /* * Handle nowait, not much to do other than tell it to retry * and wait. */ ret = VM_FAULT_RETRY; if (vmf->flags & FAULT_FLAG_RETRY_NOWAIT) goto out; /* take the reference before dropping the mmap_lock */ userfaultfd_ctx_get(ctx); init_waitqueue_func_entry(&uwq.wq, userfaultfd_wake_function); uwq.wq.private = current; uwq.msg = userfault_msg(vmf->address, vmf->real_address, vmf->flags, reason, ctx->features); uwq.ctx = ctx; uwq.waken = false; blocking_state = userfaultfd_get_blocking_state(vmf->flags); /* * Take the vma lock now, in order to safely call * userfaultfd_huge_must_wait() later. Since acquiring the * (sleepable) vma lock can modify the current task state, that * must be before explicitly calling set_current_state(). */ if (is_vm_hugetlb_page(vma)) hugetlb_vma_lock_read(vma); spin_lock_irq(&ctx->fault_pending_wqh.lock); /* * After the __add_wait_queue the uwq is visible to userland * through poll/read(). */ __add_wait_queue(&ctx->fault_pending_wqh, &uwq.wq); /* * The smp_mb() after __set_current_state prevents the reads * following the spin_unlock to happen before the list_add in * __add_wait_queue. */ set_current_state(blocking_state); spin_unlock_irq(&ctx->fault_pending_wqh.lock); if (!is_vm_hugetlb_page(vma)) must_wait = userfaultfd_must_wait(ctx, vmf, reason); else must_wait = userfaultfd_huge_must_wait(ctx, vmf, reason); if (is_vm_hugetlb_page(vma)) hugetlb_vma_unlock_read(vma); release_fault_lock(vmf); if (likely(must_wait && !READ_ONCE(ctx->released))) { wake_up_poll(&ctx->fd_wqh, EPOLLIN); schedule(); } __set_current_state(TASK_RUNNING); /* * Here we race with the list_del; list_add in * userfaultfd_ctx_read(), however because we don't ever run * list_del_init() to refile across the two lists, the prev * and next pointers will never point to self. list_add also * would never let any of the two pointers to point to * self. So list_empty_careful won't risk to see both pointers * pointing to self at any time during the list refile. The * only case where list_del_init() is called is the full * removal in the wake function and there we don't re-list_add * and it's fine not to block on the spinlock. The uwq on this * kernel stack can be released after the list_del_init. */ if (!list_empty_careful(&uwq.wq.entry)) { spin_lock_irq(&ctx->fault_pending_wqh.lock); /* * No need of list_del_init(), the uwq on the stack * will be freed shortly anyway. */ list_del(&uwq.wq.entry); spin_unlock_irq(&ctx->fault_pending_wqh.lock); } /* * ctx may go away after this if the userfault pseudo fd is * already released. */ userfaultfd_ctx_put(ctx); out: return ret; } static void userfaultfd_event_wait_completion(struct userfaultfd_ctx *ctx, struct userfaultfd_wait_queue *ewq) { struct userfaultfd_ctx *release_new_ctx; if (WARN_ON_ONCE(current->flags & PF_EXITING)) goto out; ewq->ctx = ctx; init_waitqueue_entry(&ewq->wq, current); release_new_ctx = NULL; spin_lock_irq(&ctx->event_wqh.lock); /* * After the __add_wait_queue the uwq is visible to userland * through poll/read(). */ __add_wait_queue(&ctx->event_wqh, &ewq->wq); for (;;) { set_current_state(TASK_KILLABLE); if (ewq->msg.event == 0) break; if (READ_ONCE(ctx->released) || fatal_signal_pending(current)) { /* * &ewq->wq may be queued in fork_event, but * __remove_wait_queue ignores the head * parameter. It would be a problem if it * didn't. */ __remove_wait_queue(&ctx->event_wqh, &ewq->wq); if (ewq->msg.event == UFFD_EVENT_FORK) { struct userfaultfd_ctx *new; new = (struct userfaultfd_ctx *) (unsigned long) ewq->msg.arg.reserved.reserved1; release_new_ctx = new; } break; } spin_unlock_irq(&ctx->event_wqh.lock); wake_up_poll(&ctx->fd_wqh, EPOLLIN); schedule(); spin_lock_irq(&ctx->event_wqh.lock); } __set_current_state(TASK_RUNNING); spin_unlock_irq(&ctx->event_wqh.lock); if (release_new_ctx) { userfaultfd_release_new(release_new_ctx); userfaultfd_ctx_put(release_new_ctx); } /* * ctx may go away after this if the userfault pseudo fd is * already released. */ out: atomic_dec(&ctx->mmap_changing); VM_BUG_ON(atomic_read(&ctx->mmap_changing) < 0); userfaultfd_ctx_put(ctx); } static void userfaultfd_event_complete(struct userfaultfd_ctx *ctx, struct userfaultfd_wait_queue *ewq) { ewq->msg.event = 0; wake_up_locked(&ctx->event_wqh); __remove_wait_queue(&ctx->event_wqh, &ewq->wq); } int dup_userfaultfd(struct vm_area_struct *vma, struct list_head *fcs) { struct userfaultfd_ctx *ctx = NULL, *octx; struct userfaultfd_fork_ctx *fctx; octx = vma->vm_userfaultfd_ctx.ctx; if (!octx) return 0; if (!(octx->features & UFFD_FEATURE_EVENT_FORK)) { userfaultfd_reset_ctx(vma); return 0; } list_for_each_entry(fctx, fcs, list) if (fctx->orig == octx) { ctx = fctx->new; break; } if (!ctx) { fctx = kmalloc(sizeof(*fctx), GFP_KERNEL); if (!fctx) return -ENOMEM; ctx = kmem_cache_alloc(userfaultfd_ctx_cachep, GFP_KERNEL); if (!ctx) { kfree(fctx); return -ENOMEM; } refcount_set(&ctx->refcount, 1); ctx->flags = octx->flags; ctx->features = octx->features; ctx->released = false; init_rwsem(&ctx->map_changing_lock); atomic_set(&ctx->mmap_changing, 0); ctx->mm = vma->vm_mm; mmgrab(ctx->mm); userfaultfd_ctx_get(octx); down_write(&octx->map_changing_lock); atomic_inc(&octx->mmap_changing); up_write(&octx->map_changing_lock); fctx->orig = octx; fctx->new = ctx; list_add_tail(&fctx->list, fcs); } vma->vm_userfaultfd_ctx.ctx = ctx; return 0; } static void dup_fctx(struct userfaultfd_fork_ctx *fctx) { struct userfaultfd_ctx *ctx = fctx->orig; struct userfaultfd_wait_queue ewq; msg_init(&ewq.msg); ewq.msg.event = UFFD_EVENT_FORK; ewq.msg.arg.reserved.reserved1 = (unsigned long)fctx->new; userfaultfd_event_wait_completion(ctx, &ewq); } void dup_userfaultfd_complete(struct list_head *fcs) { struct userfaultfd_fork_ctx *fctx, *n; list_for_each_entry_safe(fctx, n, fcs, list) { dup_fctx(fctx); list_del(&fctx->list); kfree(fctx); } } void dup_userfaultfd_fail(struct list_head *fcs) { struct userfaultfd_fork_ctx *fctx, *n; /* * An error has occurred on fork, we will tear memory down, but have * allocated memory for fctx's and raised reference counts for both the * original and child contexts (and on the mm for each as a result). * * These would ordinarily be taken care of by a user handling the event, * but we are no longer doing so, so manually clean up here. * * mm tear down will take care of cleaning up VMA contexts. */ list_for_each_entry_safe(fctx, n, fcs, list) { struct userfaultfd_ctx *octx = fctx->orig; struct userfaultfd_ctx *ctx = fctx->new; atomic_dec(&octx->mmap_changing); VM_BUG_ON(atomic_read(&octx->mmap_changing) < 0); userfaultfd_ctx_put(octx); userfaultfd_ctx_put(ctx); list_del(&fctx->list); kfree(fctx); } } void mremap_userfaultfd_prep(struct vm_area_struct *vma, struct vm_userfaultfd_ctx *vm_ctx) { struct userfaultfd_ctx *ctx; ctx = vma->vm_userfaultfd_ctx.ctx; if (!ctx) return; if (ctx->features & UFFD_FEATURE_EVENT_REMAP) { vm_ctx->ctx = ctx; userfaultfd_ctx_get(ctx); down_write(&ctx->map_changing_lock); atomic_inc(&ctx->mmap_changing); up_write(&ctx->map_changing_lock); } else { /* Drop uffd context if remap feature not enabled */ userfaultfd_reset_ctx(vma); } } void mremap_userfaultfd_complete(struct vm_userfaultfd_ctx *vm_ctx, unsigned long from, unsigned long to, unsigned long len) { struct userfaultfd_ctx *ctx = vm_ctx->ctx; struct userfaultfd_wait_queue ewq; if (!ctx) return; if (to & ~PAGE_MASK) { userfaultfd_ctx_put(ctx); return; } msg_init(&ewq.msg); ewq.msg.event = UFFD_EVENT_REMAP; ewq.msg.arg.remap.from = from; ewq.msg.arg.remap.to = to; ewq.msg.arg.remap.len = len; userfaultfd_event_wait_completion(ctx, &ewq); } bool userfaultfd_remove(struct vm_area_struct *vma, unsigned long start, unsigned long end) { struct mm_struct *mm = vma->vm_mm; struct userfaultfd_ctx *ctx; struct userfaultfd_wait_queue ewq; ctx = vma->vm_userfaultfd_ctx.ctx; if (!ctx || !(ctx->features & UFFD_FEATURE_EVENT_REMOVE)) return true; userfaultfd_ctx_get(ctx); down_write(&ctx->map_changing_lock); atomic_inc(&ctx->mmap_changing); up_write(&ctx->map_changing_lock); mmap_read_unlock(mm); msg_init(&ewq.msg); ewq.msg.event = UFFD_EVENT_REMOVE; ewq.msg.arg.remove.start = start; ewq.msg.arg.remove.end = end; userfaultfd_event_wait_completion(ctx, &ewq); return false; } static bool has_unmap_ctx(struct userfaultfd_ctx *ctx, struct list_head *unmaps, unsigned long start, unsigned long end) { struct userfaultfd_unmap_ctx *unmap_ctx; list_for_each_entry(unmap_ctx, unmaps, list) if (unmap_ctx->ctx == ctx && unmap_ctx->start == start && unmap_ctx->end == end) return true; return false; } int userfaultfd_unmap_prep(struct vm_area_struct *vma, unsigned long start, unsigned long end, struct list_head *unmaps) { struct userfaultfd_unmap_ctx *unmap_ctx; struct userfaultfd_ctx *ctx = vma->vm_userfaultfd_ctx.ctx; if (!ctx || !(ctx->features & UFFD_FEATURE_EVENT_UNMAP) || has_unmap_ctx(ctx, unmaps, start, end)) return 0; unmap_ctx = kzalloc(sizeof(*unmap_ctx), GFP_KERNEL); if (!unmap_ctx) return -ENOMEM; userfaultfd_ctx_get(ctx); down_write(&ctx->map_changing_lock); atomic_inc(&ctx->mmap_changing); up_write(&ctx->map_changing_lock); unmap_ctx->ctx = ctx; unmap_ctx->start = start; unmap_ctx->end = end; list_add_tail(&unmap_ctx->list, unmaps); return 0; } void userfaultfd_unmap_complete(struct mm_struct *mm, struct list_head *uf) { struct userfaultfd_unmap_ctx *ctx, *n; struct userfaultfd_wait_queue ewq; list_for_each_entry_safe(ctx, n, uf, list) { msg_init(&ewq.msg); ewq.msg.event = UFFD_EVENT_UNMAP; ewq.msg.arg.remove.start = ctx->start; ewq.msg.arg.remove.end = ctx->end; userfaultfd_event_wait_completion(ctx->ctx, &ewq); list_del(&ctx->list); kfree(ctx); } } static int userfaultfd_release(struct inode *inode, struct file *file) { struct userfaultfd_ctx *ctx = file->private_data; struct mm_struct *mm = ctx->mm; /* len == 0 means wake all */ struct userfaultfd_wake_range range = { .len = 0, }; WRITE_ONCE(ctx->released, true); userfaultfd_release_all(mm, ctx); /* * After no new page faults can wait on this fault_*wqh, flush * the last page faults that may have been already waiting on * the fault_*wqh. */ spin_lock_irq(&ctx->fault_pending_wqh.lock); __wake_up_locked_key(&ctx->fault_pending_wqh, TASK_NORMAL, &range); __wake_up(&ctx->fault_wqh, TASK_NORMAL, 1, &range); spin_unlock_irq(&ctx->fault_pending_wqh.lock); /* Flush pending events that may still wait on event_wqh */ wake_up_all(&ctx->event_wqh); wake_up_poll(&ctx->fd_wqh, EPOLLHUP); userfaultfd_ctx_put(ctx); return 0; } /* fault_pending_wqh.lock must be hold by the caller */ static inline struct userfaultfd_wait_queue *find_userfault_in( wait_queue_head_t *wqh) { wait_queue_entry_t *wq; struct userfaultfd_wait_queue *uwq; lockdep_assert_held(&wqh->lock); uwq = NULL; if (!waitqueue_active(wqh)) goto out; /* walk in reverse to provide FIFO behavior to read userfaults */ wq = list_last_entry(&wqh->head, typeof(*wq), entry); uwq = container_of(wq, struct userfaultfd_wait_queue, wq); out: return uwq; } static inline struct userfaultfd_wait_queue *find_userfault( struct userfaultfd_ctx *ctx) { return find_userfault_in(&ctx->fault_pending_wqh); } static inline struct userfaultfd_wait_queue *find_userfault_evt( struct userfaultfd_ctx *ctx) { return find_userfault_in(&ctx->event_wqh); } static __poll_t userfaultfd_poll(struct file *file, poll_table *wait) { struct userfaultfd_ctx *ctx = file->private_data; __poll_t ret; poll_wait(file, &ctx->fd_wqh, wait); if (!userfaultfd_is_initialized(ctx)) return EPOLLERR; /* * poll() never guarantees that read won't block. * userfaults can be waken before they're read(). */ if (unlikely(!(file->f_flags & O_NONBLOCK))) return EPOLLERR; /* * lockless access to see if there are pending faults * __pollwait last action is the add_wait_queue but * the spin_unlock would allow the waitqueue_active to * pass above the actual list_add inside * add_wait_queue critical section. So use a full * memory barrier to serialize the list_add write of * add_wait_queue() with the waitqueue_active read * below. */ ret = 0; smp_mb(); if (waitqueue_active(&ctx->fault_pending_wqh)) ret = EPOLLIN; else if (waitqueue_active(&ctx->event_wqh)) ret = EPOLLIN; return ret; } static const struct file_operations userfaultfd_fops; static int resolve_userfault_fork(struct userfaultfd_ctx *new, struct inode *inode, struct uffd_msg *msg) { int fd; fd = anon_inode_create_getfd("[userfaultfd]", &userfaultfd_fops, new, O_RDONLY | (new->flags & UFFD_SHARED_FCNTL_FLAGS), inode); if (fd < 0) return fd; msg->arg.reserved.reserved1 = 0; msg->arg.fork.ufd = fd; return 0; } static ssize_t userfaultfd_ctx_read(struct userfaultfd_ctx *ctx, int no_wait, struct uffd_msg *msg, struct inode *inode) { ssize_t ret; DECLARE_WAITQUEUE(wait, current); struct userfaultfd_wait_queue *uwq; /* * Handling fork event requires sleeping operations, so * we drop the event_wqh lock, then do these ops, then * lock it back and wake up the waiter. While the lock is * dropped the ewq may go away so we keep track of it * carefully. */ LIST_HEAD(fork_event); struct userfaultfd_ctx *fork_nctx = NULL; /* always take the fd_wqh lock before the fault_pending_wqh lock */ spin_lock_irq(&ctx->fd_wqh.lock); __add_wait_queue(&ctx->fd_wqh, &wait); for (;;) { set_current_state(TASK_INTERRUPTIBLE); spin_lock(&ctx->fault_pending_wqh.lock); uwq = find_userfault(ctx); if (uwq) { /* * Use a seqcount to repeat the lockless check * in wake_userfault() to avoid missing * wakeups because during the refile both * waitqueue could become empty if this is the * only userfault. */ write_seqcount_begin(&ctx->refile_seq); /* * The fault_pending_wqh.lock prevents the uwq * to disappear from under us. * * Refile this userfault from * fault_pending_wqh to fault_wqh, it's not * pending anymore after we read it. * * Use list_del() by hand (as * userfaultfd_wake_function also uses * list_del_init() by hand) to be sure nobody * changes __remove_wait_queue() to use * list_del_init() in turn breaking the * !list_empty_careful() check in * handle_userfault(). The uwq->wq.head list * must never be empty at any time during the * refile, or the waitqueue could disappear * from under us. The "wait_queue_head_t" * parameter of __remove_wait_queue() is unused * anyway. */ list_del(&uwq->wq.entry); add_wait_queue(&ctx->fault_wqh, &uwq->wq); write_seqcount_end(&ctx->refile_seq); /* careful to always initialize msg if ret == 0 */ *msg = uwq->msg; spin_unlock(&ctx->fault_pending_wqh.lock); ret = 0; break; } spin_unlock(&ctx->fault_pending_wqh.lock); spin_lock(&ctx->event_wqh.lock); uwq = find_userfault_evt(ctx); if (uwq) { *msg = uwq->msg; if (uwq->msg.event == UFFD_EVENT_FORK) { fork_nctx = (struct userfaultfd_ctx *) (unsigned long) uwq->msg.arg.reserved.reserved1; list_move(&uwq->wq.entry, &fork_event); /* * fork_nctx can be freed as soon as * we drop the lock, unless we take a * reference on it. */ userfaultfd_ctx_get(fork_nctx); spin_unlock(&ctx->event_wqh.lock); ret = 0; break; } userfaultfd_event_complete(ctx, uwq); spin_unlock(&ctx->event_wqh.lock); ret = 0; break; } spin_unlock(&ctx->event_wqh.lock); if (signal_pending(current)) { ret = -ERESTARTSYS; break; } if (no_wait) { ret = -EAGAIN; break; } spin_unlock_irq(&ctx->fd_wqh.lock); schedule(); spin_lock_irq(&ctx->fd_wqh.lock); } __remove_wait_queue(&ctx->fd_wqh, &wait); __set_current_state(TASK_RUNNING); spin_unlock_irq(&ctx->fd_wqh.lock); if (!ret && msg->event == UFFD_EVENT_FORK) { ret = resolve_userfault_fork(fork_nctx, inode, msg); spin_lock_irq(&ctx->event_wqh.lock); if (!list_empty(&fork_event)) { /* * The fork thread didn't abort, so we can * drop the temporary refcount. */ userfaultfd_ctx_put(fork_nctx); uwq = list_first_entry(&fork_event, typeof(*uwq), wq.entry); /* * If fork_event list wasn't empty and in turn * the event wasn't already released by fork * (the event is allocated on fork kernel * stack), put the event back to its place in * the event_wq. fork_event head will be freed * as soon as we return so the event cannot * stay queued there no matter the current * "ret" value. */ list_del(&uwq->wq.entry); __add_wait_queue(&ctx->event_wqh, &uwq->wq); /* * Leave the event in the waitqueue and report * error to userland if we failed to resolve * the userfault fork. */ if (likely(!ret)) userfaultfd_event_complete(ctx, uwq); } else { /* * Here the fork thread aborted and the * refcount from the fork thread on fork_nctx * has already been released. We still hold * the reference we took before releasing the * lock above. If resolve_userfault_fork * failed we've to drop it because the * fork_nctx has to be freed in such case. If * it succeeded we'll hold it because the new * uffd references it. */ if (ret) userfaultfd_ctx_put(fork_nctx); } spin_unlock_irq(&ctx->event_wqh.lock); } return ret; } static ssize_t userfaultfd_read_iter(struct kiocb *iocb, struct iov_iter *to) { struct file *file = iocb->ki_filp; struct userfaultfd_ctx *ctx = file->private_data; ssize_t _ret, ret = 0; struct uffd_msg msg; struct inode *inode = file_inode(file); bool no_wait; if (!userfaultfd_is_initialized(ctx)) return -EINVAL; no_wait = file->f_flags & O_NONBLOCK || iocb->ki_flags & IOCB_NOWAIT; for (;;) { if (iov_iter_count(to) < sizeof(msg)) return ret ? ret : -EINVAL; _ret = userfaultfd_ctx_read(ctx, no_wait, &msg, inode); if (_ret < 0) return ret ? ret : _ret; _ret = !copy_to_iter_full(&msg, sizeof(msg), to); if (_ret) return ret ? ret : -EFAULT; ret += sizeof(msg); /* * Allow to read more than one fault at time but only * block if waiting for the very first one. */ no_wait = true; } } static void __wake_userfault(struct userfaultfd_ctx *ctx, struct userfaultfd_wake_range *range) { spin_lock_irq(&ctx->fault_pending_wqh.lock); /* wake all in the range and autoremove */ if (waitqueue_active(&ctx->fault_pending_wqh)) __wake_up_locked_key(&ctx->fault_pending_wqh, TASK_NORMAL, range); if (waitqueue_active(&ctx->fault_wqh)) __wake_up(&ctx->fault_wqh, TASK_NORMAL, 1, range); spin_unlock_irq(&ctx->fault_pending_wqh.lock); } static __always_inline void wake_userfault(struct userfaultfd_ctx *ctx, struct userfaultfd_wake_range *range) { unsigned seq; bool need_wakeup; /* * To be sure waitqueue_active() is not reordered by the CPU * before the pagetable update, use an explicit SMP memory * barrier here. PT lock release or mmap_read_unlock(mm) still * have release semantics that can allow the * waitqueue_active() to be reordered before the pte update. */ smp_mb(); /* * Use waitqueue_active because it's very frequent to * change the address space atomically even if there are no * userfaults yet. So we take the spinlock only when we're * sure we've userfaults to wake. */ do { seq = read_seqcount_begin(&ctx->refile_seq); need_wakeup = waitqueue_active(&ctx->fault_pending_wqh) || waitqueue_active(&ctx->fault_wqh); cond_resched(); } while (read_seqcount_retry(&ctx->refile_seq, seq)); if (need_wakeup) __wake_userfault(ctx, range); } static __always_inline int validate_unaligned_range( struct mm_struct *mm, __u64 start, __u64 len) { __u64 task_size = mm->task_size; if (len & ~PAGE_MASK) return -EINVAL; if (!len) return -EINVAL; if (start < mmap_min_addr) return -EINVAL; if (start >= task_size) return -EINVAL; if (len > task_size - start) return -EINVAL; if (start + len <= start) return -EINVAL; return 0; } static __always_inline int validate_range(struct mm_struct *mm, __u64 start, __u64 len) { if (start & ~PAGE_MASK) return -EINVAL; return validate_unaligned_range(mm, start, len); } static int userfaultfd_register(struct userfaultfd_ctx *ctx, unsigned long arg) { struct mm_struct *mm = ctx->mm; struct vm_area_struct *vma, *cur; int ret; struct uffdio_register uffdio_register; struct uffdio_register __user *user_uffdio_register; unsigned long vm_flags; bool found; bool basic_ioctls; unsigned long start, end; struct vma_iterator vmi; bool wp_async = userfaultfd_wp_async_ctx(ctx); user_uffdio_register = (struct uffdio_register __user *) arg; ret = -EFAULT; if (copy_from_user(&uffdio_register, user_uffdio_register, sizeof(uffdio_register)-sizeof(__u64))) goto out; ret = -EINVAL; if (!uffdio_register.mode) goto out; if (uffdio_register.mode & ~UFFD_API_REGISTER_MODES) goto out; vm_flags = 0; if (uffdio_register.mode & UFFDIO_REGISTER_MODE_MISSING) vm_flags |= VM_UFFD_MISSING; if (uffdio_register.mode & UFFDIO_REGISTER_MODE_WP) { #ifndef CONFIG_HAVE_ARCH_USERFAULTFD_WP goto out; #endif vm_flags |= VM_UFFD_WP; } if (uffdio_register.mode & UFFDIO_REGISTER_MODE_MINOR) { #ifndef CONFIG_HAVE_ARCH_USERFAULTFD_MINOR goto out; #endif vm_flags |= VM_UFFD_MINOR; } ret = validate_range(mm, uffdio_register.range.start, uffdio_register.range.len); if (ret) goto out; start = uffdio_register.range.start; end = start + uffdio_register.range.len; ret = -ENOMEM; if (!mmget_not_zero(mm)) goto out; ret = -EINVAL; mmap_write_lock(mm); vma_iter_init(&vmi, mm, start); vma = vma_find(&vmi, end); if (!vma) goto out_unlock; /* * If the first vma contains huge pages, make sure start address * is aligned to huge page size. */ if (is_vm_hugetlb_page(vma)) { unsigned long vma_hpagesize = vma_kernel_pagesize(vma); if (start & (vma_hpagesize - 1)) goto out_unlock; } /* * Search for not compatible vmas. */ found = false; basic_ioctls = false; cur = vma; do { cond_resched(); BUG_ON(!!cur->vm_userfaultfd_ctx.ctx ^ !!(cur->vm_flags & __VM_UFFD_FLAGS)); /* check not compatible vmas */ ret = -EINVAL; if (!vma_can_userfault(cur, vm_flags, wp_async)) goto out_unlock; /* * UFFDIO_COPY will fill file holes even without * PROT_WRITE. This check enforces that if this is a * MAP_SHARED, the process has write permission to the backing * file. If VM_MAYWRITE is set it also enforces that on a * MAP_SHARED vma: there is no F_WRITE_SEAL and no further * F_WRITE_SEAL can be taken until the vma is destroyed. */ ret = -EPERM; if (unlikely(!(cur->vm_flags & VM_MAYWRITE))) goto out_unlock; /* * If this vma contains ending address, and huge pages * check alignment. */ if (is_vm_hugetlb_page(cur) && end <= cur->vm_end && end > cur->vm_start) { unsigned long vma_hpagesize = vma_kernel_pagesize(cur); ret = -EINVAL; if (end & (vma_hpagesize - 1)) goto out_unlock; } if ((vm_flags & VM_UFFD_WP) && !(cur->vm_flags & VM_MAYWRITE)) goto out_unlock; /* * Check that this vma isn't already owned by a * different userfaultfd. We can't allow more than one * userfaultfd to own a single vma simultaneously or we * wouldn't know which one to deliver the userfaults to. */ ret = -EBUSY; if (cur->vm_userfaultfd_ctx.ctx && cur->vm_userfaultfd_ctx.ctx != ctx) goto out_unlock; /* * Note vmas containing huge pages */ if (is_vm_hugetlb_page(cur)) basic_ioctls = true; found = true; } for_each_vma_range(vmi, cur, end); BUG_ON(!found); ret = userfaultfd_register_range(ctx, vma, vm_flags, start, end, wp_async); out_unlock: mmap_write_unlock(mm); mmput(mm); if (!ret) { __u64 ioctls_out; ioctls_out = basic_ioctls ? UFFD_API_RANGE_IOCTLS_BASIC : UFFD_API_RANGE_IOCTLS; /* * Declare the WP ioctl only if the WP mode is * specified and all checks passed with the range */ if (!(uffdio_register.mode & UFFDIO_REGISTER_MODE_WP)) ioctls_out &= ~((__u64)1 << _UFFDIO_WRITEPROTECT); /* CONTINUE ioctl is only supported for MINOR ranges. */ if (!(uffdio_register.mode & UFFDIO_REGISTER_MODE_MINOR)) ioctls_out &= ~((__u64)1 << _UFFDIO_CONTINUE); /* * Now that we scanned all vmas we can already tell * userland which ioctls methods are guaranteed to * succeed on this range. */ if (put_user(ioctls_out, &user_uffdio_register->ioctls)) ret = -EFAULT; } out: return ret; } static int userfaultfd_unregister(struct userfaultfd_ctx *ctx, unsigned long arg) { struct mm_struct *mm = ctx->mm; struct vm_area_struct *vma, *prev, *cur; int ret; struct uffdio_range uffdio_unregister; bool found; unsigned long start, end, vma_end; const void __user *buf = (void __user *)arg; struct vma_iterator vmi; bool wp_async = userfaultfd_wp_async_ctx(ctx); ret = -EFAULT; if (copy_from_user(&uffdio_unregister, buf, sizeof(uffdio_unregister))) goto out; ret = validate_range(mm, uffdio_unregister.start, uffdio_unregister.len); if (ret) goto out; start = uffdio_unregister.start; end = start + uffdio_unregister.len; ret = -ENOMEM; if (!mmget_not_zero(mm)) goto out; mmap_write_lock(mm); ret = -EINVAL; vma_iter_init(&vmi, mm, start); vma = vma_find(&vmi, end); if (!vma) goto out_unlock; /* * If the first vma contains huge pages, make sure start address * is aligned to huge page size. */ if (is_vm_hugetlb_page(vma)) { unsigned long vma_hpagesize = vma_kernel_pagesize(vma); if (start & (vma_hpagesize - 1)) goto out_unlock; } /* * Search for not compatible vmas. */ found = false; cur = vma; do { cond_resched(); BUG_ON(!!cur->vm_userfaultfd_ctx.ctx ^ !!(cur->vm_flags & __VM_UFFD_FLAGS)); /* * Check not compatible vmas, not strictly required * here as not compatible vmas cannot have an * userfaultfd_ctx registered on them, but this * provides for more strict behavior to notice * unregistration errors. */ if (!vma_can_userfault(cur, cur->vm_flags, wp_async)) goto out_unlock; found = true; } for_each_vma_range(vmi, cur, end); BUG_ON(!found); vma_iter_set(&vmi, start); prev = vma_prev(&vmi); if (vma->vm_start < start) prev = vma; ret = 0; for_each_vma_range(vmi, vma, end) { cond_resched(); BUG_ON(!vma_can_userfault(vma, vma->vm_flags, wp_async)); /* * Nothing to do: this vma is already registered into this * userfaultfd and with the right tracking mode too. */ if (!vma->vm_userfaultfd_ctx.ctx) goto skip; WARN_ON(!(vma->vm_flags & VM_MAYWRITE)); if (vma->vm_start > start) start = vma->vm_start; vma_end = min(end, vma->vm_end); if (userfaultfd_missing(vma)) { /* * Wake any concurrent pending userfault while * we unregister, so they will not hang * permanently and it avoids userland to call * UFFDIO_WAKE explicitly. */ struct userfaultfd_wake_range range; range.start = start; range.len = vma_end - start; wake_userfault(vma->vm_userfaultfd_ctx.ctx, &range); } vma = userfaultfd_clear_vma(&vmi, prev, vma, start, vma_end); if (IS_ERR(vma)) { ret = PTR_ERR(vma); break; } skip: prev = vma; start = vma->vm_end; } out_unlock: mmap_write_unlock(mm); mmput(mm); out: return ret; } /* * userfaultfd_wake may be used in combination with the * UFFDIO_*_MODE_DONTWAKE to wakeup userfaults in batches. */ static int userfaultfd_wake(struct userfaultfd_ctx *ctx, unsigned long arg) { int ret; struct uffdio_range uffdio_wake; struct userfaultfd_wake_range range; const void __user *buf = (void __user *)arg; ret = -EFAULT; if (copy_from_user(&uffdio_wake, buf, sizeof(uffdio_wake))) goto out; ret = validate_range(ctx->mm, uffdio_wake.start, uffdio_wake.len); if (ret) goto out; range.start = uffdio_wake.start; range.len = uffdio_wake.len; /* * len == 0 means wake all and we don't want to wake all here, * so check it again to be sure. */ VM_BUG_ON(!range.len); wake_userfault(ctx, &range); ret = 0; out: return ret; } static int userfaultfd_copy(struct userfaultfd_ctx *ctx, unsigned long arg) { __s64 ret; struct uffdio_copy uffdio_copy; struct uffdio_copy __user *user_uffdio_copy; struct userfaultfd_wake_range range; uffd_flags_t flags = 0; user_uffdio_copy = (struct uffdio_copy __user *) arg; ret = -EAGAIN; if (atomic_read(&ctx->mmap_changing)) goto out; ret = -EFAULT; if (copy_from_user(&uffdio_copy, user_uffdio_copy, /* don't copy "copy" last field */ sizeof(uffdio_copy)-sizeof(__s64))) goto out; ret = validate_unaligned_range(ctx->mm, uffdio_copy.src, uffdio_copy.len); if (ret) goto out; ret = validate_range(ctx->mm, uffdio_copy.dst, uffdio_copy.len); if (ret) goto out; ret = -EINVAL; if (uffdio_copy.mode & ~(UFFDIO_COPY_MODE_DONTWAKE|UFFDIO_COPY_MODE_WP)) goto out; if (uffdio_copy.mode & UFFDIO_COPY_MODE_WP) flags |= MFILL_ATOMIC_WP; if (mmget_not_zero(ctx->mm)) { ret = mfill_atomic_copy(ctx, uffdio_copy.dst, uffdio_copy.src, uffdio_copy.len, flags); mmput(ctx->mm); } else { return -ESRCH; } if (unlikely(put_user(ret, &user_uffdio_copy->copy))) return -EFAULT; if (ret < 0) goto out; BUG_ON(!ret); /* len == 0 would wake all */ range.len = ret; if (!(uffdio_copy.mode & UFFDIO_COPY_MODE_DONTWAKE)) { range.start = uffdio_copy.dst; wake_userfault(ctx, &range); } ret = range.len == uffdio_copy.len ? 0 : -EAGAIN; out: return ret; } static int userfaultfd_zeropage(struct userfaultfd_ctx *ctx, unsigned long arg) { __s64 ret; struct uffdio_zeropage uffdio_zeropage; struct uffdio_zeropage __user *user_uffdio_zeropage; struct userfaultfd_wake_range range; user_uffdio_zeropage = (struct uffdio_zeropage __user *) arg; ret = -EAGAIN; if (atomic_read(&ctx->mmap_changing)) goto out; ret = -EFAULT; if (copy_from_user(&uffdio_zeropage, user_uffdio_zeropage, /* don't copy "zeropage" last field */ sizeof(uffdio_zeropage)-sizeof(__s64))) goto out; ret = validate_range(ctx->mm, uffdio_zeropage.range.start, uffdio_zeropage.range.len); if (ret) goto out; ret = -EINVAL; if (uffdio_zeropage.mode & ~UFFDIO_ZEROPAGE_MODE_DONTWAKE) goto out; if (mmget_not_zero(ctx->mm)) { ret = mfill_atomic_zeropage(ctx, uffdio_zeropage.range.start, uffdio_zeropage.range.len); mmput(ctx->mm); } else { return -ESRCH; } if (unlikely(put_user(ret, &user_uffdio_zeropage->zeropage))) return -EFAULT; if (ret < 0) goto out; /* len == 0 would wake all */ BUG_ON(!ret); range.len = ret; if (!(uffdio_zeropage.mode & UFFDIO_ZEROPAGE_MODE_DONTWAKE)) { range.start = uffdio_zeropage.range.start; wake_userfault(ctx, &range); } ret = range.len == uffdio_zeropage.range.len ? 0 : -EAGAIN; out: return ret; } static int userfaultfd_writeprotect(struct userfaultfd_ctx *ctx, unsigned long arg) { int ret; struct uffdio_writeprotect uffdio_wp; struct uffdio_writeprotect __user *user_uffdio_wp; struct userfaultfd_wake_range range; bool mode_wp, mode_dontwake; if (atomic_read(&ctx->mmap_changing)) return -EAGAIN; user_uffdio_wp = (struct uffdio_writeprotect __user *) arg; if (copy_from_user(&uffdio_wp, user_uffdio_wp, sizeof(struct uffdio_writeprotect))) return -EFAULT; ret = validate_range(ctx->mm, uffdio_wp.range.start, uffdio_wp.range.len); if (ret) return ret; if (uffdio_wp.mode & ~(UFFDIO_WRITEPROTECT_MODE_DONTWAKE | UFFDIO_WRITEPROTECT_MODE_WP)) return -EINVAL; mode_wp = uffdio_wp.mode & UFFDIO_WRITEPROTECT_MODE_WP; mode_dontwake = uffdio_wp.mode & UFFDIO_WRITEPROTECT_MODE_DONTWAKE; if (mode_wp && mode_dontwake) return -EINVAL; if (mmget_not_zero(ctx->mm)) { ret = mwriteprotect_range(ctx, uffdio_wp.range.start, uffdio_wp.range.len, mode_wp); mmput(ctx->mm); } else { return -ESRCH; } if (ret) return ret; if (!mode_wp && !mode_dontwake) { range.start = uffdio_wp.range.start; range.len = uffdio_wp.range.len; wake_userfault(ctx, &range); } return ret; } static int userfaultfd_continue(struct userfaultfd_ctx *ctx, unsigned long arg) { __s64 ret; struct uffdio_continue uffdio_continue; struct uffdio_continue __user *user_uffdio_continue; struct userfaultfd_wake_range range; uffd_flags_t flags = 0; user_uffdio_continue = (struct uffdio_continue __user *)arg; ret = -EAGAIN; if (atomic_read(&ctx->mmap_changing)) goto out; ret = -EFAULT; if (copy_from_user(&uffdio_continue, user_uffdio_continue, /* don't copy the output fields */ sizeof(uffdio_continue) - (sizeof(__s64)))) goto out; ret = validate_range(ctx->mm, uffdio_continue.range.start, uffdio_continue.range.len); if (ret) goto out; ret = -EINVAL; if (uffdio_continue.mode & ~(UFFDIO_CONTINUE_MODE_DONTWAKE | UFFDIO_CONTINUE_MODE_WP)) goto out; if (uffdio_continue.mode & UFFDIO_CONTINUE_MODE_WP) flags |= MFILL_ATOMIC_WP; if (mmget_not_zero(ctx->mm)) { ret = mfill_atomic_continue(ctx, uffdio_continue.range.start, uffdio_continue.range.len, flags); mmput(ctx->mm); } else { return -ESRCH; } if (unlikely(put_user(ret, &user_uffdio_continue->mapped))) return -EFAULT; if (ret < 0) goto out; /* len == 0 would wake all */ BUG_ON(!ret); range.len = ret; if (!(uffdio_continue.mode & UFFDIO_CONTINUE_MODE_DONTWAKE)) { range.start = uffdio_continue.range.start; wake_userfault(ctx, &range); } ret = range.len == uffdio_continue.range.len ? 0 : -EAGAIN; out: return ret; } static inline int userfaultfd_poison(struct userfaultfd_ctx *ctx, unsigned long arg) { __s64 ret; struct uffdio_poison uffdio_poison; struct uffdio_poison __user *user_uffdio_poison; struct userfaultfd_wake_range range; user_uffdio_poison = (struct uffdio_poison __user *)arg; ret = -EAGAIN; if (atomic_read(&ctx->mmap_changing)) goto out; ret = -EFAULT; if (copy_from_user(&uffdio_poison, user_uffdio_poison, /* don't copy the output fields */ sizeof(uffdio_poison) - (sizeof(__s64)))) goto out; ret = validate_range(ctx->mm, uffdio_poison.range.start, uffdio_poison.range.len); if (ret) goto out; ret = -EINVAL; if (uffdio_poison.mode & ~UFFDIO_POISON_MODE_DONTWAKE) goto out; if (mmget_not_zero(ctx->mm)) { ret = mfill_atomic_poison(ctx, uffdio_poison.range.start, uffdio_poison.range.len, 0); mmput(ctx->mm); } else { return -ESRCH; } if (unlikely(put_user(ret, &user_uffdio_poison->updated))) return -EFAULT; if (ret < 0) goto out; /* len == 0 would wake all */ BUG_ON(!ret); range.len = ret; if (!(uffdio_poison.mode & UFFDIO_POISON_MODE_DONTWAKE)) { range.start = uffdio_poison.range.start; wake_userfault(ctx, &range); } ret = range.len == uffdio_poison.range.len ? 0 : -EAGAIN; out: return ret; } bool userfaultfd_wp_async(struct vm_area_struct *vma) { return userfaultfd_wp_async_ctx(vma->vm_userfaultfd_ctx.ctx); } static inline unsigned int uffd_ctx_features(__u64 user_features) { /* * For the current set of features the bits just coincide. Set * UFFD_FEATURE_INITIALIZED to mark the features as enabled. */ return (unsigned int)user_features | UFFD_FEATURE_INITIALIZED; } static int userfaultfd_move(struct userfaultfd_ctx *ctx, unsigned long arg) { __s64 ret; struct uffdio_move uffdio_move; struct uffdio_move __user *user_uffdio_move; struct userfaultfd_wake_range range; struct mm_struct *mm = ctx->mm; user_uffdio_move = (struct uffdio_move __user *) arg; if (atomic_read(&ctx->mmap_changing)) return -EAGAIN; if (copy_from_user(&uffdio_move, user_uffdio_move, /* don't copy "move" last field */ sizeof(uffdio_move)-sizeof(__s64))) return -EFAULT; /* Do not allow cross-mm moves. */ if (mm != current->mm) return -EINVAL; ret = validate_range(mm, uffdio_move.dst, uffdio_move.len); if (ret) return ret; ret = validate_range(mm, uffdio_move.src, uffdio_move.len); if (ret) return ret; if (uffdio_move.mode & ~(UFFDIO_MOVE_MODE_ALLOW_SRC_HOLES| UFFDIO_MOVE_MODE_DONTWAKE)) return -EINVAL; if (mmget_not_zero(mm)) { ret = move_pages(ctx, uffdio_move.dst, uffdio_move.src, uffdio_move.len, uffdio_move.mode); mmput(mm); } else { return -ESRCH; } if (unlikely(put_user(ret, &user_uffdio_move->move))) return -EFAULT; if (ret < 0) goto out; /* len == 0 would wake all */ VM_WARN_ON(!ret); range.len = ret; if (!(uffdio_move.mode & UFFDIO_MOVE_MODE_DONTWAKE)) { range.start = uffdio_move.dst; wake_userfault(ctx, &range); } ret = range.len == uffdio_move.len ? 0 : -EAGAIN; out: return ret; } /* * userland asks for a certain API version and we return which bits * and ioctl commands are implemented in this kernel for such API * version or -EINVAL if unknown. */ static int userfaultfd_api(struct userfaultfd_ctx *ctx, unsigned long arg) { struct uffdio_api uffdio_api; void __user *buf = (void __user *)arg; unsigned int ctx_features; int ret; __u64 features; ret = -EFAULT; if (copy_from_user(&uffdio_api, buf, sizeof(uffdio_api))) goto out; features = uffdio_api.features; ret = -EINVAL; if (uffdio_api.api != UFFD_API) goto err_out; ret = -EPERM; if ((features & UFFD_FEATURE_EVENT_FORK) && !capable(CAP_SYS_PTRACE)) goto err_out; /* WP_ASYNC relies on WP_UNPOPULATED, choose it unconditionally */ if (features & UFFD_FEATURE_WP_ASYNC) features |= UFFD_FEATURE_WP_UNPOPULATED; /* report all available features and ioctls to userland */ uffdio_api.features = UFFD_API_FEATURES; #ifndef CONFIG_HAVE_ARCH_USERFAULTFD_MINOR uffdio_api.features &= ~(UFFD_FEATURE_MINOR_HUGETLBFS | UFFD_FEATURE_MINOR_SHMEM); #endif #ifndef CONFIG_HAVE_ARCH_USERFAULTFD_WP uffdio_api.features &= ~UFFD_FEATURE_PAGEFAULT_FLAG_WP; #endif #ifndef CONFIG_PTE_MARKER_UFFD_WP uffdio_api.features &= ~UFFD_FEATURE_WP_HUGETLBFS_SHMEM; uffdio_api.features &= ~UFFD_FEATURE_WP_UNPOPULATED; uffdio_api.features &= ~UFFD_FEATURE_WP_ASYNC; #endif ret = -EINVAL; if (features & ~uffdio_api.features) goto err_out; uffdio_api.ioctls = UFFD_API_IOCTLS; ret = -EFAULT; if (copy_to_user(buf, &uffdio_api, sizeof(uffdio_api))) goto out; /* only enable the requested features for this uffd context */ ctx_features = uffd_ctx_features(features); ret = -EINVAL; if (cmpxchg(&ctx->features, 0, ctx_features) != 0) goto err_out; ret = 0; out: return ret; err_out: memset(&uffdio_api, 0, sizeof(uffdio_api)); if (copy_to_user(buf, &uffdio_api, sizeof(uffdio_api))) ret = -EFAULT; goto out; } static long userfaultfd_ioctl(struct file *file, unsigned cmd, unsigned long arg) { int ret = -EINVAL; struct userfaultfd_ctx *ctx = file->private_data; if (cmd != UFFDIO_API && !userfaultfd_is_initialized(ctx)) return -EINVAL; switch(cmd) { case UFFDIO_API: ret = userfaultfd_api(ctx, arg); break; case UFFDIO_REGISTER: ret = userfaultfd_register(ctx, arg); break; case UFFDIO_UNREGISTER: ret = userfaultfd_unregister(ctx, arg); break; case UFFDIO_WAKE: ret = userfaultfd_wake(ctx, arg); break; case UFFDIO_COPY: ret = userfaultfd_copy(ctx, arg); break; case UFFDIO_ZEROPAGE: ret = userfaultfd_zeropage(ctx, arg); break; case UFFDIO_MOVE: ret = userfaultfd_move(ctx, arg); break; case UFFDIO_WRITEPROTECT: ret = userfaultfd_writeprotect(ctx, arg); break; case UFFDIO_CONTINUE: ret = userfaultfd_continue(ctx, arg); break; case UFFDIO_POISON: ret = userfaultfd_poison(ctx, arg); break; } return ret; } #ifdef CONFIG_PROC_FS static void userfaultfd_show_fdinfo(struct seq_file *m, struct file *f) { struct userfaultfd_ctx *ctx = f->private_data; wait_queue_entry_t *wq; unsigned long pending = 0, total = 0; spin_lock_irq(&ctx->fault_pending_wqh.lock); list_for_each_entry(wq, &ctx->fault_pending_wqh.head, entry) { pending++; total++; } list_for_each_entry(wq, &ctx->fault_wqh.head, entry) { total++; } spin_unlock_irq(&ctx->fault_pending_wqh.lock); /* * If more protocols will be added, there will be all shown * separated by a space. Like this: * protocols: aa:... bb:... */ seq_printf(m, "pending:\t%lu\ntotal:\t%lu\nAPI:\t%Lx:%x:%Lx\n", pending, total, UFFD_API, ctx->features, UFFD_API_IOCTLS|UFFD_API_RANGE_IOCTLS); } #endif static const struct file_operations userfaultfd_fops = { #ifdef CONFIG_PROC_FS .show_fdinfo = userfaultfd_show_fdinfo, #endif .release = userfaultfd_release, .poll = userfaultfd_poll, .read_iter = userfaultfd_read_iter, .unlocked_ioctl = userfaultfd_ioctl, .compat_ioctl = compat_ptr_ioctl, .llseek = noop_llseek, }; static void init_once_userfaultfd_ctx(void *mem) { struct userfaultfd_ctx *ctx = (struct userfaultfd_ctx *) mem; init_waitqueue_head(&ctx->fault_pending_wqh); init_waitqueue_head(&ctx->fault_wqh); init_waitqueue_head(&ctx->event_wqh); init_waitqueue_head(&ctx->fd_wqh); seqcount_spinlock_init(&ctx->refile_seq, &ctx->fault_pending_wqh.lock); } static int new_userfaultfd(int flags) { struct userfaultfd_ctx *ctx; struct file *file; int fd; BUG_ON(!current->mm); /* Check the UFFD_* constants for consistency. */ BUILD_BUG_ON(UFFD_USER_MODE_ONLY & UFFD_SHARED_FCNTL_FLAGS); BUILD_BUG_ON(UFFD_CLOEXEC != O_CLOEXEC); BUILD_BUG_ON(UFFD_NONBLOCK != O_NONBLOCK); if (flags & ~(UFFD_SHARED_FCNTL_FLAGS | UFFD_USER_MODE_ONLY)) return -EINVAL; ctx = kmem_cache_alloc(userfaultfd_ctx_cachep, GFP_KERNEL); if (!ctx) return -ENOMEM; refcount_set(&ctx->refcount, 1); ctx->flags = flags; ctx->features = 0; ctx->released = false; init_rwsem(&ctx->map_changing_lock); atomic_set(&ctx->mmap_changing, 0); ctx->mm = current->mm; fd = get_unused_fd_flags(flags & UFFD_SHARED_FCNTL_FLAGS); if (fd < 0) goto err_out; /* Create a new inode so that the LSM can block the creation. */ file = anon_inode_create_getfile("[userfaultfd]", &userfaultfd_fops, ctx, O_RDONLY | (flags & UFFD_SHARED_FCNTL_FLAGS), NULL); if (IS_ERR(file)) { put_unused_fd(fd); fd = PTR_ERR(file); goto err_out; } /* prevent the mm struct to be freed */ mmgrab(ctx->mm); file->f_mode |= FMODE_NOWAIT; fd_install(fd, file); return fd; err_out: kmem_cache_free(userfaultfd_ctx_cachep, ctx); return fd; } static inline bool userfaultfd_syscall_allowed(int flags) { /* Userspace-only page faults are always allowed */ if (flags & UFFD_USER_MODE_ONLY) return true; /* * The user is requesting a userfaultfd which can handle kernel faults. * Privileged users are always allowed to do this. */ if (capable(CAP_SYS_PTRACE)) return true; /* Otherwise, access to kernel fault handling is sysctl controlled. */ return sysctl_unprivileged_userfaultfd; } SYSCALL_DEFINE1(userfaultfd, int, flags) { if (!userfaultfd_syscall_allowed(flags)) return -EPERM; return new_userfaultfd(flags); } static long userfaultfd_dev_ioctl(struct file *file, unsigned int cmd, unsigned long flags) { if (cmd != USERFAULTFD_IOC_NEW) return -EINVAL; return new_userfaultfd(flags); } static const struct file_operations userfaultfd_dev_fops = { .unlocked_ioctl = userfaultfd_dev_ioctl, .compat_ioctl = userfaultfd_dev_ioctl, .owner = THIS_MODULE, .llseek = noop_llseek, }; static struct miscdevice userfaultfd_misc = { .minor = MISC_DYNAMIC_MINOR, .name = "userfaultfd", .fops = &userfaultfd_dev_fops }; static int __init userfaultfd_init(void) { int ret; ret = misc_register(&userfaultfd_misc); if (ret) return ret; userfaultfd_ctx_cachep = kmem_cache_create("userfaultfd_ctx_cache", sizeof(struct userfaultfd_ctx), 0, SLAB_HWCACHE_ALIGN|SLAB_PANIC, init_once_userfaultfd_ctx); #ifdef CONFIG_SYSCTL register_sysctl_init("vm", vm_userfaultfd_table); #endif return 0; } __initcall(userfaultfd_init); |
| 58 | 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 | // SPDX-License-Identifier: GPL-2.0-only /* * DCCP connection tracking protocol helper * * Copyright (c) 2005, 2006, 2008 Patrick McHardy <kaber@trash.net> */ #include <linux/kernel.h> #include <linux/init.h> #include <linux/sysctl.h> #include <linux/spinlock.h> #include <linux/skbuff.h> #include <linux/dccp.h> #include <linux/slab.h> #include <net/net_namespace.h> #include <net/netns/generic.h> #include <linux/netfilter/nfnetlink_conntrack.h> #include <net/netfilter/nf_conntrack.h> #include <net/netfilter/nf_conntrack_l4proto.h> #include <net/netfilter/nf_conntrack_ecache.h> #include <net/netfilter/nf_conntrack_timeout.h> #include <net/netfilter/nf_log.h> /* Timeouts are based on values from RFC4340: * * - REQUEST: * * 8.1.2. Client Request * * A client MAY give up on its DCCP-Requests after some time * (3 minutes, for example). * * - RESPOND: * * 8.1.3. Server Response * * It MAY also leave the RESPOND state for CLOSED after a timeout of * not less than 4MSL (8 minutes); * * - PARTOPEN: * * 8.1.5. Handshake Completion * * If the client remains in PARTOPEN for more than 4MSL (8 minutes), * it SHOULD reset the connection with Reset Code 2, "Aborted". * * - OPEN: * * The DCCP timestamp overflows after 11.9 hours. If the connection * stays idle this long the sequence number won't be recognized * as valid anymore. * * - CLOSEREQ/CLOSING: * * 8.3. Termination * * The retransmission timer should initially be set to go off in two * round-trip times and should back off to not less than once every * 64 seconds ... * * - TIMEWAIT: * * 4.3. States * * A server or client socket remains in this state for 2MSL (4 minutes) * after the connection has been town down, ... */ #define DCCP_MSL (2 * 60 * HZ) #ifdef CONFIG_NF_CONNTRACK_PROCFS static const char * const dccp_state_names[] = { [CT_DCCP_NONE] = "NONE", [CT_DCCP_REQUEST] = "REQUEST", [CT_DCCP_RESPOND] = "RESPOND", [CT_DCCP_PARTOPEN] = "PARTOPEN", [CT_DCCP_OPEN] = "OPEN", [CT_DCCP_CLOSEREQ] = "CLOSEREQ", [CT_DCCP_CLOSING] = "CLOSING", [CT_DCCP_TIMEWAIT] = "TIMEWAIT", [CT_DCCP_IGNORE] = "IGNORE", [CT_DCCP_INVALID] = "INVALID", }; #endif #define sNO CT_DCCP_NONE #define sRQ CT_DCCP_REQUEST #define sRS CT_DCCP_RESPOND #define sPO CT_DCCP_PARTOPEN #define sOP CT_DCCP_OPEN #define sCR CT_DCCP_CLOSEREQ #define sCG CT_DCCP_CLOSING #define sTW CT_DCCP_TIMEWAIT #define sIG CT_DCCP_IGNORE #define sIV CT_DCCP_INVALID /* * DCCP state transition table * * The assumption is the same as for TCP tracking: * * We are the man in the middle. All the packets go through us but might * get lost in transit to the destination. It is assumed that the destination * can't receive segments we haven't seen. * * The following states exist: * * NONE: Initial state, expecting Request * REQUEST: Request seen, waiting for Response from server * RESPOND: Response from server seen, waiting for Ack from client * PARTOPEN: Ack after Response seen, waiting for packet other than Response, * Reset or Sync from server * OPEN: Packet other than Response, Reset or Sync seen * CLOSEREQ: CloseReq from server seen, expecting Close from client * CLOSING: Close seen, expecting Reset * TIMEWAIT: Reset seen * IGNORE: Not determinable whether packet is valid * * Some states exist only on one side of the connection: REQUEST, RESPOND, * PARTOPEN, CLOSEREQ. For the other side these states are equivalent to * the one it was in before. * * Packets are marked as ignored (sIG) if we don't know if they're valid * (for example a reincarnation of a connection we didn't notice is dead * already) and the server may send back a connection closing Reset or a * Response. They're also used for Sync/SyncAck packets, which we don't * care about. */ static const u_int8_t dccp_state_table[CT_DCCP_ROLE_MAX + 1][DCCP_PKT_SYNCACK + 1][CT_DCCP_MAX + 1] = { [CT_DCCP_ROLE_CLIENT] = { [DCCP_PKT_REQUEST] = { /* * sNO -> sRQ Regular Request * sRQ -> sRQ Retransmitted Request or reincarnation * sRS -> sRS Retransmitted Request (apparently Response * got lost after we saw it) or reincarnation * sPO -> sIG Ignore, conntrack might be out of sync * sOP -> sIG Ignore, conntrack might be out of sync * sCR -> sIG Ignore, conntrack might be out of sync * sCG -> sIG Ignore, conntrack might be out of sync * sTW -> sRQ Reincarnation * * sNO, sRQ, sRS, sPO. sOP, sCR, sCG, sTW, */ sRQ, sRQ, sRS, sIG, sIG, sIG, sIG, sRQ, }, [DCCP_PKT_RESPONSE] = { /* * sNO -> sIV Invalid * sRQ -> sIG Ignore, might be response to ignored Request * sRS -> sIG Ignore, might be response to ignored Request * sPO -> sIG Ignore, might be response to ignored Request * sOP -> sIG Ignore, might be response to ignored Request * sCR -> sIG Ignore, might be response to ignored Request * sCG -> sIG Ignore, might be response to ignored Request * sTW -> sIV Invalid, reincarnation in reverse direction * goes through sRQ * * sNO, sRQ, sRS, sPO, sOP, sCR, sCG, sTW */ sIV, sIG, sIG, sIG, sIG, sIG, sIG, sIV, }, [DCCP_PKT_ACK] = { /* * sNO -> sIV No connection * sRQ -> sIV No connection * sRS -> sPO Ack for Response, move to PARTOPEN (8.1.5.) * sPO -> sPO Retransmitted Ack for Response, remain in PARTOPEN * sOP -> sOP Regular ACK, remain in OPEN * sCR -> sCR Ack in CLOSEREQ MAY be processed (8.3.) * sCG -> sCG Ack in CLOSING MAY be processed (8.3.) * sTW -> sIV * * sNO, sRQ, sRS, sPO, sOP, sCR, sCG, sTW */ sIV, sIV, sPO, sPO, sOP, sCR, sCG, sIV }, [DCCP_PKT_DATA] = { /* * sNO -> sIV No connection * sRQ -> sIV No connection * sRS -> sIV No connection * sPO -> sIV MUST use DataAck in PARTOPEN state (8.1.5.) * sOP -> sOP Regular Data packet * sCR -> sCR Data in CLOSEREQ MAY be processed (8.3.) * sCG -> sCG Data in CLOSING MAY be processed (8.3.) * sTW -> sIV * * sNO, sRQ, sRS, sPO, sOP, sCR, sCG, sTW */ sIV, sIV, sIV, sIV, sOP, sCR, sCG, sIV, }, [DCCP_PKT_DATAACK] = { /* * sNO -> sIV No connection * sRQ -> sIV No connection * sRS -> sPO Ack for Response, move to PARTOPEN (8.1.5.) * sPO -> sPO Remain in PARTOPEN state * sOP -> sOP Regular DataAck packet in OPEN state * sCR -> sCR DataAck in CLOSEREQ MAY be processed (8.3.) * sCG -> sCG DataAck in CLOSING MAY be processed (8.3.) * sTW -> sIV * * sNO, sRQ, sRS, sPO, sOP, sCR, sCG, sTW */ sIV, sIV, sPO, sPO, sOP, sCR, sCG, sIV }, [DCCP_PKT_CLOSEREQ] = { /* * CLOSEREQ may only be sent by the server. * * sNO, sRQ, sRS, sPO, sOP, sCR, sCG, sTW */ sIV, sIV, sIV, sIV, sIV, sIV, sIV, sIV }, [DCCP_PKT_CLOSE] = { /* * sNO -> sIV No connection * sRQ -> sIV No connection * sRS -> sIV No connection * sPO -> sCG Client-initiated close * sOP -> sCG Client-initiated close * sCR -> sCG Close in response to CloseReq (8.3.) * sCG -> sCG Retransmit * sTW -> sIV Late retransmit, already in TIME_WAIT * * sNO, sRQ, sRS, sPO, sOP, sCR, sCG, sTW */ sIV, sIV, sIV, sCG, sCG, sCG, sIV, sIV }, [DCCP_PKT_RESET] = { /* * sNO -> sIV No connection * sRQ -> sTW Sync received or timeout, SHOULD send Reset (8.1.1.) * sRS -> sTW Response received without Request * sPO -> sTW Timeout, SHOULD send Reset (8.1.5.) * sOP -> sTW Connection reset * sCR -> sTW Connection reset * sCG -> sTW Connection reset * sTW -> sIG Ignore (don't refresh timer) * * sNO, sRQ, sRS, sPO, sOP, sCR, sCG, sTW */ sIV, sTW, sTW, sTW, sTW, sTW, sTW, sIG }, [DCCP_PKT_SYNC] = { /* * We currently ignore Sync packets * * sNO, sRQ, sRS, sPO, sOP, sCR, sCG, sTW */ sIV, sIG, sIG, sIG, sIG, sIG, sIG, sIG, }, [DCCP_PKT_SYNCACK] = { /* * We currently ignore SyncAck packets * * sNO, sRQ, sRS, sPO, sOP, sCR, sCG, sTW */ sIV, sIG, sIG, sIG, sIG, sIG, sIG, sIG, }, }, [CT_DCCP_ROLE_SERVER] = { [DCCP_PKT_REQUEST] = { /* * sNO -> sIV Invalid * sRQ -> sIG Ignore, conntrack might be out of sync * sRS -> sIG Ignore, conntrack might be out of sync * sPO -> sIG Ignore, conntrack might be out of sync * sOP -> sIG Ignore, conntrack might be out of sync * sCR -> sIG Ignore, conntrack might be out of sync * sCG -> sIG Ignore, conntrack might be out of sync * sTW -> sRQ Reincarnation, must reverse roles * * sNO, sRQ, sRS, sPO, sOP, sCR, sCG, sTW */ sIV, sIG, sIG, sIG, sIG, sIG, sIG, sRQ }, [DCCP_PKT_RESPONSE] = { /* * sNO -> sIV Response without Request * sRQ -> sRS Response to clients Request * sRS -> sRS Retransmitted Response (8.1.3. SHOULD NOT) * sPO -> sIG Response to an ignored Request or late retransmit * sOP -> sIG Ignore, might be response to ignored Request * sCR -> sIG Ignore, might be response to ignored Request * sCG -> sIG Ignore, might be response to ignored Request * sTW -> sIV Invalid, Request from client in sTW moves to sRQ * * sNO, sRQ, sRS, sPO, sOP, sCR, sCG, sTW */ sIV, sRS, sRS, sIG, sIG, sIG, sIG, sIV }, [DCCP_PKT_ACK] = { /* * sNO -> sIV No connection * sRQ -> sIV No connection * sRS -> sIV No connection * sPO -> sOP Enter OPEN state (8.1.5.) * sOP -> sOP Regular Ack in OPEN state * sCR -> sIV Waiting for Close from client * sCG -> sCG Ack in CLOSING MAY be processed (8.3.) * sTW -> sIV * * sNO, sRQ, sRS, sPO, sOP, sCR, sCG, sTW */ sIV, sIV, sIV, sOP, sOP, sIV, sCG, sIV }, [DCCP_PKT_DATA] = { /* * sNO -> sIV No connection * sRQ -> sIV No connection * sRS -> sIV No connection * sPO -> sOP Enter OPEN state (8.1.5.) * sOP -> sOP Regular Data packet in OPEN state * sCR -> sIV Waiting for Close from client * sCG -> sCG Data in CLOSING MAY be processed (8.3.) * sTW -> sIV * * sNO, sRQ, sRS, sPO, sOP, sCR, sCG, sTW */ sIV, sIV, sIV, sOP, sOP, sIV, sCG, sIV }, [DCCP_PKT_DATAACK] = { /* * sNO -> sIV No connection * sRQ -> sIV No connection * sRS -> sIV No connection * sPO -> sOP Enter OPEN state (8.1.5.) * sOP -> sOP Regular DataAck in OPEN state * sCR -> sIV Waiting for Close from client * sCG -> sCG Data in CLOSING MAY be processed (8.3.) * sTW -> sIV * * sNO, sRQ, sRS, sPO, sOP, sCR, sCG, sTW */ sIV, sIV, sIV, sOP, sOP, sIV, sCG, sIV }, [DCCP_PKT_CLOSEREQ] = { /* * sNO -> sIV No connection * sRQ -> sIV No connection * sRS -> sIV No connection * sPO -> sOP -> sCR Move directly to CLOSEREQ (8.1.5.) * sOP -> sCR CloseReq in OPEN state * sCR -> sCR Retransmit * sCG -> sCR Simultaneous close, client sends another Close * sTW -> sIV Already closed * * sNO, sRQ, sRS, sPO, sOP, sCR, sCG, sTW */ sIV, sIV, sIV, sCR, sCR, sCR, sCR, sIV }, [DCCP_PKT_CLOSE] = { /* * sNO -> sIV No connection * sRQ -> sIV No connection * sRS -> sIV No connection * sPO -> sOP -> sCG Move direcly to CLOSING * sOP -> sCG Move to CLOSING * sCR -> sIV Close after CloseReq is invalid * sCG -> sCG Retransmit * sTW -> sIV Already closed * * sNO, sRQ, sRS, sPO, sOP, sCR, sCG, sTW */ sIV, sIV, sIV, sCG, sCG, sIV, sCG, sIV }, [DCCP_PKT_RESET] = { /* * sNO -> sIV No connection * sRQ -> sTW Reset in response to Request * sRS -> sTW Timeout, SHOULD send Reset (8.1.3.) * sPO -> sTW Timeout, SHOULD send Reset (8.1.3.) * sOP -> sTW * sCR -> sTW * sCG -> sTW * sTW -> sIG Ignore (don't refresh timer) * * sNO, sRQ, sRS, sPO, sOP, sCR, sCG, sTW, sTW */ sIV, sTW, sTW, sTW, sTW, sTW, sTW, sTW, sIG }, [DCCP_PKT_SYNC] = { /* * We currently ignore Sync packets * * sNO, sRQ, sRS, sPO, sOP, sCR, sCG, sTW */ sIV, sIG, sIG, sIG, sIG, sIG, sIG, sIG, }, [DCCP_PKT_SYNCACK] = { /* * We currently ignore SyncAck packets * * sNO, sRQ, sRS, sPO, sOP, sCR, sCG, sTW */ sIV, sIG, sIG, sIG, sIG, sIG, sIG, sIG, }, }, }; static noinline bool dccp_new(struct nf_conn *ct, const struct sk_buff *skb, const struct dccp_hdr *dh, const struct nf_hook_state *hook_state) { struct net *net = nf_ct_net(ct); struct nf_dccp_net *dn; const char *msg; u_int8_t state; state = dccp_state_table[CT_DCCP_ROLE_CLIENT][dh->dccph_type][CT_DCCP_NONE]; switch (state) { default: dn = nf_dccp_pernet(net); if (dn->dccp_loose == 0) { msg = "not picking up existing connection "; goto out_invalid; } break; case CT_DCCP_REQUEST: break; case CT_DCCP_INVALID: msg = "invalid state transition "; goto out_invalid; } ct->proto.dccp.role[IP_CT_DIR_ORIGINAL] = CT_DCCP_ROLE_CLIENT; ct->proto.dccp.role[IP_CT_DIR_REPLY] = CT_DCCP_ROLE_SERVER; ct->proto.dccp.state = CT_DCCP_NONE; ct->proto.dccp.last_pkt = DCCP_PKT_REQUEST; ct->proto.dccp.last_dir = IP_CT_DIR_ORIGINAL; ct->proto.dccp.handshake_seq = 0; return true; out_invalid: nf_ct_l4proto_log_invalid(skb, ct, hook_state, "%s", msg); return false; } static u64 dccp_ack_seq(const struct dccp_hdr *dh) { const struct dccp_hdr_ack_bits *dhack; dhack = (void *)dh + __dccp_basic_hdr_len(dh); return ((u64)ntohs(dhack->dccph_ack_nr_high) << 32) + ntohl(dhack->dccph_ack_nr_low); } static bool dccp_error(const struct dccp_hdr *dh, struct sk_buff *skb, unsigned int dataoff, const struct nf_hook_state *state) { static const unsigned long require_seq48 = 1 << DCCP_PKT_REQUEST | 1 << DCCP_PKT_RESPONSE | 1 << DCCP_PKT_CLOSEREQ | 1 << DCCP_PKT_CLOSE | 1 << DCCP_PKT_RESET | 1 << DCCP_PKT_SYNC | 1 << DCCP_PKT_SYNCACK; unsigned int dccp_len = skb->len - dataoff; unsigned int cscov; const char *msg; u8 type; BUILD_BUG_ON(DCCP_PKT_INVALID >= BITS_PER_LONG); if (dh->dccph_doff * 4 < sizeof(struct dccp_hdr) || dh->dccph_doff * 4 > dccp_len) { msg = "nf_ct_dccp: truncated/malformed packet "; goto out_invalid; } cscov = dccp_len; if (dh->dccph_cscov) { cscov = (dh->dccph_cscov - 1) * 4; if (cscov > dccp_len) { msg = "nf_ct_dccp: bad checksum coverage "; goto out_invalid; } } if (state->hook == NF_INET_PRE_ROUTING && state->net->ct.sysctl_checksum && nf_checksum_partial(skb, state->hook, dataoff, cscov, IPPROTO_DCCP, state->pf)) { msg = "nf_ct_dccp: bad checksum "; goto out_invalid; } type = dh->dccph_type; if (type >= DCCP_PKT_INVALID) { msg = "nf_ct_dccp: reserved packet type "; goto out_invalid; } if (test_bit(type, &require_seq48) && !dh->dccph_x) { msg = "nf_ct_dccp: type lacks 48bit sequence numbers"; goto out_invalid; } return false; out_invalid: nf_l4proto_log_invalid(skb, state, IPPROTO_DCCP, "%s", msg); return true; } struct nf_conntrack_dccp_buf { struct dccp_hdr dh; /* generic header part */ struct dccp_hdr_ext ext; /* optional depending dh->dccph_x */ union { /* depends on header type */ struct dccp_hdr_ack_bits ack; struct dccp_hdr_request req; struct dccp_hdr_response response; struct dccp_hdr_reset rst; } u; }; static struct dccp_hdr * dccp_header_pointer(const struct sk_buff *skb, int offset, const struct dccp_hdr *dh, struct nf_conntrack_dccp_buf *buf) { unsigned int hdrlen = __dccp_hdr_len(dh); if (hdrlen > sizeof(*buf)) return NULL; return skb_header_pointer(skb, offset, hdrlen, buf); } int nf_conntrack_dccp_packet(struct nf_conn *ct, struct sk_buff *skb, unsigned int dataoff, enum ip_conntrack_info ctinfo, const struct nf_hook_state *state) { enum ip_conntrack_dir dir = CTINFO2DIR(ctinfo); struct nf_conntrack_dccp_buf _dh; u_int8_t type, old_state, new_state; enum ct_dccp_roles role; unsigned int *timeouts; struct dccp_hdr *dh; dh = skb_header_pointer(skb, dataoff, sizeof(*dh), &_dh.dh); if (!dh) return -NF_ACCEPT; if (dccp_error(dh, skb, dataoff, state)) return -NF_ACCEPT; /* pull again, including possible 48 bit sequences and subtype header */ dh = dccp_header_pointer(skb, dataoff, dh, &_dh); if (!dh) return -NF_ACCEPT; type = dh->dccph_type; if (!nf_ct_is_confirmed(ct) && !dccp_new(ct, skb, dh, state)) return -NF_ACCEPT; if (type == DCCP_PKT_RESET && !test_bit(IPS_SEEN_REPLY_BIT, &ct->status)) { /* Tear down connection immediately if only reply is a RESET */ nf_ct_kill_acct(ct, ctinfo, skb); return NF_ACCEPT; } spin_lock_bh(&ct->lock); role = ct->proto.dccp.role[dir]; old_state = ct->proto.dccp.state; new_state = dccp_state_table[role][type][old_state]; switch (new_state) { case CT_DCCP_REQUEST: if (old_state == CT_DCCP_TIMEWAIT && role == CT_DCCP_ROLE_SERVER) { /* Reincarnation in the reverse direction: reopen and * reverse client/server roles. */ ct->proto.dccp.role[dir] = CT_DCCP_ROLE_CLIENT; ct->proto.dccp.role[!dir] = CT_DCCP_ROLE_SERVER; } break; case CT_DCCP_RESPOND: if (old_state == CT_DCCP_REQUEST) ct->proto.dccp.handshake_seq = dccp_hdr_seq(dh); break; case CT_DCCP_PARTOPEN: if (old_state == CT_DCCP_RESPOND && type == DCCP_PKT_ACK && dccp_ack_seq(dh) == ct->proto.dccp.handshake_seq) set_bit(IPS_ASSURED_BIT, &ct->status); break; case CT_DCCP_IGNORE: /* * Connection tracking might be out of sync, so we ignore * packets that might establish a new connection and resync * if the server responds with a valid Response. */ if (ct->proto.dccp.last_dir == !dir && ct->proto.dccp.last_pkt == DCCP_PKT_REQUEST && type == DCCP_PKT_RESPONSE) { ct->proto.dccp.role[!dir] = CT_DCCP_ROLE_CLIENT; ct->proto.dccp.role[dir] = CT_DCCP_ROLE_SERVER; ct->proto.dccp.handshake_seq = dccp_hdr_seq(dh); new_state = CT_DCCP_RESPOND; break; } ct->proto.dccp.last_dir = dir; ct->proto.dccp.last_pkt = type; spin_unlock_bh(&ct->lock); nf_ct_l4proto_log_invalid(skb, ct, state, "%s", "invalid packet"); return NF_ACCEPT; case CT_DCCP_INVALID: spin_unlock_bh(&ct->lock); nf_ct_l4proto_log_invalid(skb, ct, state, "%s", "invalid state transition"); return -NF_ACCEPT; } ct->proto.dccp.last_dir = dir; ct->proto.dccp.last_pkt = type; ct->proto.dccp.state = new_state; spin_unlock_bh(&ct->lock); if (new_state != old_state) nf_conntrack_event_cache(IPCT_PROTOINFO, ct); timeouts = nf_ct_timeout_lookup(ct); if (!timeouts) timeouts = nf_dccp_pernet(nf_ct_net(ct))->dccp_timeout; nf_ct_refresh_acct(ct, ctinfo, skb, timeouts[new_state]); return NF_ACCEPT; } static bool dccp_can_early_drop(const struct nf_conn *ct) { switch (ct->proto.dccp.state) { case CT_DCCP_CLOSEREQ: case CT_DCCP_CLOSING: case CT_DCCP_TIMEWAIT: return true; default: break; } return false; } #ifdef CONFIG_NF_CONNTRACK_PROCFS static void dccp_print_conntrack(struct seq_file *s, struct nf_conn *ct) { seq_printf(s, "%s ", dccp_state_names[ct->proto.dccp.state]); } #endif #if IS_ENABLED(CONFIG_NF_CT_NETLINK) static int dccp_to_nlattr(struct sk_buff *skb, struct nlattr *nla, struct nf_conn *ct, bool destroy) { struct nlattr *nest_parms; spin_lock_bh(&ct->lock); nest_parms = nla_nest_start(skb, CTA_PROTOINFO_DCCP); if (!nest_parms) goto nla_put_failure; if (nla_put_u8(skb, CTA_PROTOINFO_DCCP_STATE, ct->proto.dccp.state)) goto nla_put_failure; if (destroy) goto skip_state; if (nla_put_u8(skb, CTA_PROTOINFO_DCCP_ROLE, ct->proto.dccp.role[IP_CT_DIR_ORIGINAL]) || nla_put_be64(skb, CTA_PROTOINFO_DCCP_HANDSHAKE_SEQ, cpu_to_be64(ct->proto.dccp.handshake_seq), CTA_PROTOINFO_DCCP_PAD)) goto nla_put_failure; skip_state: nla_nest_end(skb, nest_parms); spin_unlock_bh(&ct->lock); return 0; nla_put_failure: spin_unlock_bh(&ct->lock); return -1; } static const struct nla_policy dccp_nla_policy[CTA_PROTOINFO_DCCP_MAX + 1] = { [CTA_PROTOINFO_DCCP_STATE] = { .type = NLA_U8 }, [CTA_PROTOINFO_DCCP_ROLE] = { .type = NLA_U8 }, [CTA_PROTOINFO_DCCP_HANDSHAKE_SEQ] = { .type = NLA_U64 }, [CTA_PROTOINFO_DCCP_PAD] = { .type = NLA_UNSPEC }, }; #define DCCP_NLATTR_SIZE ( \ NLA_ALIGN(NLA_HDRLEN + 1) + \ NLA_ALIGN(NLA_HDRLEN + 1) + \ NLA_ALIGN(NLA_HDRLEN + sizeof(u64)) + \ NLA_ALIGN(NLA_HDRLEN + 0)) static int nlattr_to_dccp(struct nlattr *cda[], struct nf_conn *ct) { struct nlattr *attr = cda[CTA_PROTOINFO_DCCP]; struct nlattr *tb[CTA_PROTOINFO_DCCP_MAX + 1]; int err; if (!attr) return 0; err = nla_parse_nested_deprecated(tb, CTA_PROTOINFO_DCCP_MAX, attr, dccp_nla_policy, NULL); if (err < 0) return err; if (!tb[CTA_PROTOINFO_DCCP_STATE] || !tb[CTA_PROTOINFO_DCCP_ROLE] || nla_get_u8(tb[CTA_PROTOINFO_DCCP_ROLE]) > CT_DCCP_ROLE_MAX || nla_get_u8(tb[CTA_PROTOINFO_DCCP_STATE]) >= CT_DCCP_IGNORE) { return -EINVAL; } spin_lock_bh(&ct->lock); ct->proto.dccp.state = nla_get_u8(tb[CTA_PROTOINFO_DCCP_STATE]); if (nla_get_u8(tb[CTA_PROTOINFO_DCCP_ROLE]) == CT_DCCP_ROLE_CLIENT) { ct->proto.dccp.role[IP_CT_DIR_ORIGINAL] = CT_DCCP_ROLE_CLIENT; ct->proto.dccp.role[IP_CT_DIR_REPLY] = CT_DCCP_ROLE_SERVER; } else { ct->proto.dccp.role[IP_CT_DIR_ORIGINAL] = CT_DCCP_ROLE_SERVER; ct->proto.dccp.role[IP_CT_DIR_REPLY] = CT_DCCP_ROLE_CLIENT; } if (tb[CTA_PROTOINFO_DCCP_HANDSHAKE_SEQ]) { ct->proto.dccp.handshake_seq = be64_to_cpu(nla_get_be64(tb[CTA_PROTOINFO_DCCP_HANDSHAKE_SEQ])); } spin_unlock_bh(&ct->lock); return 0; } #endif #ifdef CONFIG_NF_CONNTRACK_TIMEOUT #include <linux/netfilter/nfnetlink.h> #include <linux/netfilter/nfnetlink_cttimeout.h> static int dccp_timeout_nlattr_to_obj(struct nlattr *tb[], struct net *net, void *data) { struct nf_dccp_net *dn = nf_dccp_pernet(net); unsigned int *timeouts = data; int i; if (!timeouts) timeouts = dn->dccp_timeout; /* set default DCCP timeouts. */ for (i=0; i<CT_DCCP_MAX; i++) timeouts[i] = dn->dccp_timeout[i]; /* there's a 1:1 mapping between attributes and protocol states. */ for (i=CTA_TIMEOUT_DCCP_UNSPEC+1; i<CTA_TIMEOUT_DCCP_MAX+1; i++) { if (tb[i]) { timeouts[i] = ntohl(nla_get_be32(tb[i])) * HZ; } } timeouts[CTA_TIMEOUT_DCCP_UNSPEC] = timeouts[CTA_TIMEOUT_DCCP_REQUEST]; return 0; } static int dccp_timeout_obj_to_nlattr(struct sk_buff *skb, const void *data) { const unsigned int *timeouts = data; int i; for (i=CTA_TIMEOUT_DCCP_UNSPEC+1; i<CTA_TIMEOUT_DCCP_MAX+1; i++) { if (nla_put_be32(skb, i, htonl(timeouts[i] / HZ))) goto nla_put_failure; } return 0; nla_put_failure: return -ENOSPC; } static const struct nla_policy dccp_timeout_nla_policy[CTA_TIMEOUT_DCCP_MAX+1] = { [CTA_TIMEOUT_DCCP_REQUEST] = { .type = NLA_U32 }, [CTA_TIMEOUT_DCCP_RESPOND] = { .type = NLA_U32 }, [CTA_TIMEOUT_DCCP_PARTOPEN] = { .type = NLA_U32 }, [CTA_TIMEOUT_DCCP_OPEN] = { .type = NLA_U32 }, [CTA_TIMEOUT_DCCP_CLOSEREQ] = { .type = NLA_U32 }, [CTA_TIMEOUT_DCCP_CLOSING] = { .type = NLA_U32 }, [CTA_TIMEOUT_DCCP_TIMEWAIT] = { .type = NLA_U32 }, }; #endif /* CONFIG_NF_CONNTRACK_TIMEOUT */ void nf_conntrack_dccp_init_net(struct net *net) { struct nf_dccp_net *dn = nf_dccp_pernet(net); /* default values */ dn->dccp_loose = 1; dn->dccp_timeout[CT_DCCP_REQUEST] = 2 * DCCP_MSL; dn->dccp_timeout[CT_DCCP_RESPOND] = 4 * DCCP_MSL; dn->dccp_timeout[CT_DCCP_PARTOPEN] = 4 * DCCP_MSL; dn->dccp_timeout[CT_DCCP_OPEN] = 12 * 3600 * HZ; dn->dccp_timeout[CT_DCCP_CLOSEREQ] = 64 * HZ; dn->dccp_timeout[CT_DCCP_CLOSING] = 64 * HZ; dn->dccp_timeout[CT_DCCP_TIMEWAIT] = 2 * DCCP_MSL; /* timeouts[0] is unused, make it same as SYN_SENT so * ->timeouts[0] contains 'new' timeout, like udp or icmp. */ dn->dccp_timeout[CT_DCCP_NONE] = dn->dccp_timeout[CT_DCCP_REQUEST]; } const struct nf_conntrack_l4proto nf_conntrack_l4proto_dccp = { .l4proto = IPPROTO_DCCP, .can_early_drop = dccp_can_early_drop, #ifdef CONFIG_NF_CONNTRACK_PROCFS .print_conntrack = dccp_print_conntrack, #endif #if IS_ENABLED(CONFIG_NF_CT_NETLINK) .nlattr_size = DCCP_NLATTR_SIZE, .to_nlattr = dccp_to_nlattr, .from_nlattr = nlattr_to_dccp, .tuple_to_nlattr = nf_ct_port_tuple_to_nlattr, .nlattr_tuple_size = nf_ct_port_nlattr_tuple_size, .nlattr_to_tuple = nf_ct_port_nlattr_to_tuple, .nla_policy = nf_ct_port_nla_policy, #endif #ifdef CONFIG_NF_CONNTRACK_TIMEOUT .ctnl_timeout = { .nlattr_to_obj = dccp_timeout_nlattr_to_obj, .obj_to_nlattr = dccp_timeout_obj_to_nlattr, .nlattr_max = CTA_TIMEOUT_DCCP_MAX, .obj_size = sizeof(unsigned int) * CT_DCCP_MAX, .nla_policy = dccp_timeout_nla_policy, }, #endif /* CONFIG_NF_CONNTRACK_TIMEOUT */ }; |
| 377 378 378 376 378 378 1303 1304 397 399 397 399 397 399 34 379 378 379 379 | 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 | // SPDX-License-Identifier: GPL-2.0-only /* * fs/fs-writeback.c * * Copyright (C) 2002, Linus Torvalds. * * Contains all the functions related to writing back and waiting * upon dirty inodes against superblocks, and writing back dirty * pages against inodes. ie: data writeback. Writeout of the * inode itself is not handled here. * * 10Apr2002 Andrew Morton * Split out of fs/inode.c * Additions for address_space-based writeback */ #include <linux/kernel.h> #include <linux/export.h> #include <linux/spinlock.h> #include <linux/slab.h> #include <linux/sched.h> #include <linux/fs.h> #include <linux/mm.h> #include <linux/pagemap.h> #include <linux/kthread.h> #include <linux/writeback.h> #include <linux/blkdev.h> #include <linux/backing-dev.h> #include <linux/tracepoint.h> #include <linux/device.h> #include <linux/memcontrol.h> #include "internal.h" /* * 4MB minimal write chunk size */ #define MIN_WRITEBACK_PAGES (4096UL >> (PAGE_SHIFT - 10)) /* * Passed into wb_writeback(), essentially a subset of writeback_control */ struct wb_writeback_work { long nr_pages; struct super_block *sb; enum writeback_sync_modes sync_mode; unsigned int tagged_writepages:1; unsigned int for_kupdate:1; unsigned int range_cyclic:1; unsigned int for_background:1; unsigned int for_sync:1; /* sync(2) WB_SYNC_ALL writeback */ unsigned int auto_free:1; /* free on completion */ enum wb_reason reason; /* why was writeback initiated? */ struct list_head list; /* pending work list */ struct wb_completion *done; /* set if the caller waits */ }; /* * If an inode is constantly having its pages dirtied, but then the * updates stop dirtytime_expire_interval seconds in the past, it's * possible for the worst case time between when an inode has its * timestamps updated and when they finally get written out to be two * dirtytime_expire_intervals. We set the default to 12 hours (in * seconds), which means most of the time inodes will have their * timestamps written to disk after 12 hours, but in the worst case a * few inodes might not their timestamps updated for 24 hours. */ unsigned int dirtytime_expire_interval = 12 * 60 * 60; static inline struct inode *wb_inode(struct list_head *head) { return list_entry(head, struct inode, i_io_list); } /* * Include the creation of the trace points after defining the * wb_writeback_work structure and inline functions so that the definition * remains local to this file. */ #define CREATE_TRACE_POINTS #include <trace/events/writeback.h> EXPORT_TRACEPOINT_SYMBOL_GPL(wbc_writepage); static bool wb_io_lists_populated(struct bdi_writeback *wb) { if (wb_has_dirty_io(wb)) { return false; } else { set_bit(WB_has_dirty_io, &wb->state); WARN_ON_ONCE(!wb->avg_write_bandwidth); atomic_long_add(wb->avg_write_bandwidth, &wb->bdi->tot_write_bandwidth); return true; } } static void wb_io_lists_depopulated(struct bdi_writeback *wb) { if (wb_has_dirty_io(wb) && list_empty(&wb->b_dirty) && list_empty(&wb->b_io) && list_empty(&wb->b_more_io)) { clear_bit(WB_has_dirty_io, &wb->state); WARN_ON_ONCE(atomic_long_sub_return(wb->avg_write_bandwidth, &wb->bdi->tot_write_bandwidth) < 0); } } /** * inode_io_list_move_locked - move an inode onto a bdi_writeback IO list * @inode: inode to be moved * @wb: target bdi_writeback * @head: one of @wb->b_{dirty|io|more_io|dirty_time} * * Move @inode->i_io_list to @list of @wb and set %WB_has_dirty_io. * Returns %true if @inode is the first occupant of the !dirty_time IO * lists; otherwise, %false. */ static bool inode_io_list_move_locked(struct inode *inode, struct bdi_writeback *wb, struct list_head *head) { assert_spin_locked(&wb->list_lock); assert_spin_locked(&inode->i_lock); WARN_ON_ONCE(inode->i_state & I_FREEING); list_move(&inode->i_io_list, head); /* dirty_time doesn't count as dirty_io until expiration */ if (head != &wb->b_dirty_time) return wb_io_lists_populated(wb); wb_io_lists_depopulated(wb); return false; } static void wb_wakeup(struct bdi_writeback *wb) { spin_lock_irq(&wb->work_lock); if (test_bit(WB_registered, &wb->state)) mod_delayed_work(bdi_wq, &wb->dwork, 0); spin_unlock_irq(&wb->work_lock); } /* * This function is used when the first inode for this wb is marked dirty. It * wakes-up the corresponding bdi thread which should then take care of the * periodic background write-out of dirty inodes. Since the write-out would * starts only 'dirty_writeback_interval' centisecs from now anyway, we just * set up a timer which wakes the bdi thread up later. * * Note, we wouldn't bother setting up the timer, but this function is on the * fast-path (used by '__mark_inode_dirty()'), so we save few context switches * by delaying the wake-up. * * We have to be careful not to postpone flush work if it is scheduled for * earlier. Thus we use queue_delayed_work(). */ static void wb_wakeup_delayed(struct bdi_writeback *wb) { unsigned long timeout; timeout = msecs_to_jiffies(dirty_writeback_interval * 10); spin_lock_irq(&wb->work_lock); if (test_bit(WB_registered, &wb->state)) queue_delayed_work(bdi_wq, &wb->dwork, timeout); spin_unlock_irq(&wb->work_lock); } static void finish_writeback_work(struct wb_writeback_work *work) { struct wb_completion *done = work->done; if (work->auto_free) kfree(work); if (done) { wait_queue_head_t *waitq = done->waitq; /* @done can't be accessed after the following dec */ if (atomic_dec_and_test(&done->cnt)) wake_up_all(waitq); } } static void wb_queue_work(struct bdi_writeback *wb, struct wb_writeback_work *work) { trace_writeback_queue(wb, work); if (work->done) atomic_inc(&work->done->cnt); spin_lock_irq(&wb->work_lock); if (test_bit(WB_registered, &wb->state)) { list_add_tail(&work->list, &wb->work_list); mod_delayed_work(bdi_wq, &wb->dwork, 0); } else finish_writeback_work(work); spin_unlock_irq(&wb->work_lock); } /** * wb_wait_for_completion - wait for completion of bdi_writeback_works * @done: target wb_completion * * Wait for one or more work items issued to @bdi with their ->done field * set to @done, which should have been initialized with * DEFINE_WB_COMPLETION(). This function returns after all such work items * are completed. Work items which are waited upon aren't freed * automatically on completion. */ void wb_wait_for_completion(struct wb_completion *done) { atomic_dec(&done->cnt); /* put down the initial count */ wait_event(*done->waitq, !atomic_read(&done->cnt)); } #ifdef CONFIG_CGROUP_WRITEBACK /* * Parameters for foreign inode detection, see wbc_detach_inode() to see * how they're used. * * These paramters are inherently heuristical as the detection target * itself is fuzzy. All we want to do is detaching an inode from the * current owner if it's being written to by some other cgroups too much. * * The current cgroup writeback is built on the assumption that multiple * cgroups writing to the same inode concurrently is very rare and a mode * of operation which isn't well supported. As such, the goal is not * taking too long when a different cgroup takes over an inode while * avoiding too aggressive flip-flops from occasional foreign writes. * * We record, very roughly, 2s worth of IO time history and if more than * half of that is foreign, trigger the switch. The recording is quantized * to 16 slots. To avoid tiny writes from swinging the decision too much, * writes smaller than 1/8 of avg size are ignored. */ #define WB_FRN_TIME_SHIFT 13 /* 1s = 2^13, upto 8 secs w/ 16bit */ #define WB_FRN_TIME_AVG_SHIFT 3 /* avg = avg * 7/8 + new * 1/8 */ #define WB_FRN_TIME_CUT_DIV 8 /* ignore rounds < avg / 8 */ #define WB_FRN_TIME_PERIOD (2 * (1 << WB_FRN_TIME_SHIFT)) /* 2s */ #define WB_FRN_HIST_SLOTS 16 /* inode->i_wb_frn_history is 16bit */ #define WB_FRN_HIST_UNIT (WB_FRN_TIME_PERIOD / WB_FRN_HIST_SLOTS) /* each slot's duration is 2s / 16 */ #define WB_FRN_HIST_THR_SLOTS (WB_FRN_HIST_SLOTS / 2) /* if foreign slots >= 8, switch */ #define WB_FRN_HIST_MAX_SLOTS (WB_FRN_HIST_THR_SLOTS / 2 + 1) /* one round can affect upto 5 slots */ #define WB_FRN_MAX_IN_FLIGHT 1024 /* don't queue too many concurrently */ /* * Maximum inodes per isw. A specific value has been chosen to make * struct inode_switch_wbs_context fit into 1024 bytes kmalloc. */ #define WB_MAX_INODES_PER_ISW ((1024UL - sizeof(struct inode_switch_wbs_context)) \ / sizeof(struct inode *)) static atomic_t isw_nr_in_flight = ATOMIC_INIT(0); static struct workqueue_struct *isw_wq; void __inode_attach_wb(struct inode *inode, struct folio *folio) { struct backing_dev_info *bdi = inode_to_bdi(inode); struct bdi_writeback *wb = NULL; if (inode_cgwb_enabled(inode)) { struct cgroup_subsys_state *memcg_css; if (folio) { memcg_css = mem_cgroup_css_from_folio(folio); wb = wb_get_create(bdi, memcg_css, GFP_ATOMIC); } else { /* must pin memcg_css, see wb_get_create() */ memcg_css = task_get_css(current, memory_cgrp_id); wb = wb_get_create(bdi, memcg_css, GFP_ATOMIC); css_put(memcg_css); } } if (!wb) wb = &bdi->wb; /* * There may be multiple instances of this function racing to * update the same inode. Use cmpxchg() to tell the winner. */ if (unlikely(cmpxchg(&inode->i_wb, NULL, wb))) wb_put(wb); } /** * inode_cgwb_move_to_attached - put the inode onto wb->b_attached list * @inode: inode of interest with i_lock held * @wb: target bdi_writeback * * Remove the inode from wb's io lists and if necessarily put onto b_attached * list. Only inodes attached to cgwb's are kept on this list. */ static void inode_cgwb_move_to_attached(struct inode *inode, struct bdi_writeback *wb) { assert_spin_locked(&wb->list_lock); assert_spin_locked(&inode->i_lock); WARN_ON_ONCE(inode->i_state & I_FREEING); inode->i_state &= ~I_SYNC_QUEUED; if (wb != &wb->bdi->wb) list_move(&inode->i_io_list, &wb->b_attached); else list_del_init(&inode->i_io_list); wb_io_lists_depopulated(wb); } /** * locked_inode_to_wb_and_lock_list - determine a locked inode's wb and lock it * @inode: inode of interest with i_lock held * * Returns @inode's wb with its list_lock held. @inode->i_lock must be * held on entry and is released on return. The returned wb is guaranteed * to stay @inode's associated wb until its list_lock is released. */ static struct bdi_writeback * locked_inode_to_wb_and_lock_list(struct inode *inode) __releases(&inode->i_lock) __acquires(&wb->list_lock) { while (true) { struct bdi_writeback *wb = inode_to_wb(inode); /* * inode_to_wb() association is protected by both * @inode->i_lock and @wb->list_lock but list_lock nests * outside i_lock. Drop i_lock and verify that the * association hasn't changed after acquiring list_lock. */ wb_get(wb); spin_unlock(&inode->i_lock); spin_lock(&wb->list_lock); /* i_wb may have changed inbetween, can't use inode_to_wb() */ if (likely(wb == inode->i_wb)) { wb_put(wb); /* @inode already has ref */ return wb; } spin_unlock(&wb->list_lock); wb_put(wb); cpu_relax(); spin_lock(&inode->i_lock); } } /** * inode_to_wb_and_lock_list - determine an inode's wb and lock it * @inode: inode of interest * * Same as locked_inode_to_wb_and_lock_list() but @inode->i_lock isn't held * on entry. */ static struct bdi_writeback *inode_to_wb_and_lock_list(struct inode *inode) __acquires(&wb->list_lock) { spin_lock(&inode->i_lock); return locked_inode_to_wb_and_lock_list(inode); } struct inode_switch_wbs_context { struct rcu_work work; /* * Multiple inodes can be switched at once. The switching procedure * consists of two parts, separated by a RCU grace period. To make * sure that the second part is executed for each inode gone through * the first part, all inode pointers are placed into a NULL-terminated * array embedded into struct inode_switch_wbs_context. Otherwise * an inode could be left in a non-consistent state. */ struct bdi_writeback *new_wb; struct inode *inodes[]; }; static void bdi_down_write_wb_switch_rwsem(struct backing_dev_info *bdi) { down_write(&bdi->wb_switch_rwsem); } static void bdi_up_write_wb_switch_rwsem(struct backing_dev_info *bdi) { up_write(&bdi->wb_switch_rwsem); } static bool inode_do_switch_wbs(struct inode *inode, struct bdi_writeback *old_wb, struct bdi_writeback *new_wb) { struct address_space *mapping = inode->i_mapping; XA_STATE(xas, &mapping->i_pages, 0); struct folio *folio; bool switched = false; spin_lock(&inode->i_lock); xa_lock_irq(&mapping->i_pages); /* * Once I_FREEING or I_WILL_FREE are visible under i_lock, the eviction * path owns the inode and we shouldn't modify ->i_io_list. */ if (unlikely(inode->i_state & (I_FREEING | I_WILL_FREE))) goto skip_switch; trace_inode_switch_wbs(inode, old_wb, new_wb); /* * Count and transfer stats. Note that PAGECACHE_TAG_DIRTY points * to possibly dirty folios while PAGECACHE_TAG_WRITEBACK points to * folios actually under writeback. */ xas_for_each_marked(&xas, folio, ULONG_MAX, PAGECACHE_TAG_DIRTY) { if (folio_test_dirty(folio)) { long nr = folio_nr_pages(folio); wb_stat_mod(old_wb, WB_RECLAIMABLE, -nr); wb_stat_mod(new_wb, WB_RECLAIMABLE, nr); } } xas_set(&xas, 0); xas_for_each_marked(&xas, folio, ULONG_MAX, PAGECACHE_TAG_WRITEBACK) { long nr = folio_nr_pages(folio); WARN_ON_ONCE(!folio_test_writeback(folio)); wb_stat_mod(old_wb, WB_WRITEBACK, -nr); wb_stat_mod(new_wb, WB_WRITEBACK, nr); } if (mapping_tagged(mapping, PAGECACHE_TAG_WRITEBACK)) { atomic_dec(&old_wb->writeback_inodes); atomic_inc(&new_wb->writeback_inodes); } wb_get(new_wb); /* * Transfer to @new_wb's IO list if necessary. If the @inode is dirty, * the specific list @inode was on is ignored and the @inode is put on * ->b_dirty which is always correct including from ->b_dirty_time. * The transfer preserves @inode->dirtied_when ordering. If the @inode * was clean, it means it was on the b_attached list, so move it onto * the b_attached list of @new_wb. */ if (!list_empty(&inode->i_io_list)) { inode->i_wb = new_wb; if (inode->i_state & I_DIRTY_ALL) { struct inode *pos; list_for_each_entry(pos, &new_wb->b_dirty, i_io_list) if (time_after_eq(inode->dirtied_when, pos->dirtied_when)) break; inode_io_list_move_locked(inode, new_wb, pos->i_io_list.prev); } else { inode_cgwb_move_to_attached(inode, new_wb); } } else { inode->i_wb = new_wb; } /* ->i_wb_frn updates may race wbc_detach_inode() but doesn't matter */ inode->i_wb_frn_winner = 0; inode->i_wb_frn_avg_time = 0; inode->i_wb_frn_history = 0; switched = true; skip_switch: /* * Paired with load_acquire in unlocked_inode_to_wb_begin() and * ensures that the new wb is visible if they see !I_WB_SWITCH. */ smp_store_release(&inode->i_state, inode->i_state & ~I_WB_SWITCH); xa_unlock_irq(&mapping->i_pages); spin_unlock(&inode->i_lock); return switched; } static void inode_switch_wbs_work_fn(struct work_struct *work) { struct inode_switch_wbs_context *isw = container_of(to_rcu_work(work), struct inode_switch_wbs_context, work); struct backing_dev_info *bdi = inode_to_bdi(isw->inodes[0]); struct bdi_writeback *old_wb = isw->inodes[0]->i_wb; struct bdi_writeback *new_wb = isw->new_wb; unsigned long nr_switched = 0; struct inode **inodep; /* * If @inode switches cgwb membership while sync_inodes_sb() is * being issued, sync_inodes_sb() might miss it. Synchronize. */ down_read(&bdi->wb_switch_rwsem); /* * By the time control reaches here, RCU grace period has passed * since I_WB_SWITCH assertion and all wb stat update transactions * between unlocked_inode_to_wb_begin/end() are guaranteed to be * synchronizing against the i_pages lock. * * Grabbing old_wb->list_lock, inode->i_lock and the i_pages lock * gives us exclusion against all wb related operations on @inode * including IO list manipulations and stat updates. */ if (old_wb < new_wb) { spin_lock(&old_wb->list_lock); spin_lock_nested(&new_wb->list_lock, SINGLE_DEPTH_NESTING); } else { spin_lock(&new_wb->list_lock); spin_lock_nested(&old_wb->list_lock, SINGLE_DEPTH_NESTING); } for (inodep = isw->inodes; *inodep; inodep++) { WARN_ON_ONCE((*inodep)->i_wb != old_wb); if (inode_do_switch_wbs(*inodep, old_wb, new_wb)) nr_switched++; } spin_unlock(&new_wb->list_lock); spin_unlock(&old_wb->list_lock); up_read(&bdi->wb_switch_rwsem); if (nr_switched) { wb_wakeup(new_wb); wb_put_many(old_wb, nr_switched); } for (inodep = isw->inodes; *inodep; inodep++) iput(*inodep); wb_put(new_wb); kfree(isw); atomic_dec(&isw_nr_in_flight); } static bool inode_prepare_wbs_switch(struct inode *inode, struct bdi_writeback *new_wb) { /* * Paired with smp_mb() in cgroup_writeback_umount(). * isw_nr_in_flight must be increased before checking SB_ACTIVE and * grabbing an inode, otherwise isw_nr_in_flight can be observed as 0 * in cgroup_writeback_umount() and the isw_wq will be not flushed. */ smp_mb(); if (IS_DAX(inode)) return false; /* while holding I_WB_SWITCH, no one else can update the association */ spin_lock(&inode->i_lock); if (!(inode->i_sb->s_flags & SB_ACTIVE) || inode->i_state & (I_WB_SWITCH | I_FREEING | I_WILL_FREE) || inode_to_wb(inode) == new_wb) { spin_unlock(&inode->i_lock); return false; } inode->i_state |= I_WB_SWITCH; __iget(inode); spin_unlock(&inode->i_lock); return true; } /** * inode_switch_wbs - change the wb association of an inode * @inode: target inode * @new_wb_id: ID of the new wb * * Switch @inode's wb association to the wb identified by @new_wb_id. The * switching is performed asynchronously and may fail silently. */ static void inode_switch_wbs(struct inode *inode, int new_wb_id) { struct backing_dev_info *bdi = inode_to_bdi(inode); struct cgroup_subsys_state *memcg_css; struct inode_switch_wbs_context *isw; /* noop if seems to be already in progress */ if (inode->i_state & I_WB_SWITCH) return; /* avoid queueing a new switch if too many are already in flight */ if (atomic_read(&isw_nr_in_flight) > WB_FRN_MAX_IN_FLIGHT) return; isw = kzalloc(struct_size(isw, inodes, 2), GFP_ATOMIC); if (!isw) return; atomic_inc(&isw_nr_in_flight); /* find and pin the new wb */ rcu_read_lock(); memcg_css = css_from_id(new_wb_id, &memory_cgrp_subsys); if (memcg_css && !css_tryget(memcg_css)) memcg_css = NULL; rcu_read_unlock(); if (!memcg_css) goto out_free; isw->new_wb = wb_get_create(bdi, memcg_css, GFP_ATOMIC); css_put(memcg_css); if (!isw->new_wb) goto out_free; if (!inode_prepare_wbs_switch(inode, isw->new_wb)) goto out_free; isw->inodes[0] = inode; /* * In addition to synchronizing among switchers, I_WB_SWITCH tells * the RCU protected stat update paths to grab the i_page * lock so that stat transfer can synchronize against them. * Let's continue after I_WB_SWITCH is guaranteed to be visible. */ INIT_RCU_WORK(&isw->work, inode_switch_wbs_work_fn); queue_rcu_work(isw_wq, &isw->work); return; out_free: atomic_dec(&isw_nr_in_flight); if (isw->new_wb) wb_put(isw->new_wb); kfree(isw); } static bool isw_prepare_wbs_switch(struct inode_switch_wbs_context *isw, struct list_head *list, int *nr) { struct inode *inode; list_for_each_entry(inode, list, i_io_list) { if (!inode_prepare_wbs_switch(inode, isw->new_wb)) continue; isw->inodes[*nr] = inode; (*nr)++; if (*nr >= WB_MAX_INODES_PER_ISW - 1) return true; } return false; } /** * cleanup_offline_cgwb - detach associated inodes * @wb: target wb * * Switch all inodes attached to @wb to a nearest living ancestor's wb in order * to eventually release the dying @wb. Returns %true if not all inodes were * switched and the function has to be restarted. */ bool cleanup_offline_cgwb(struct bdi_writeback *wb) { struct cgroup_subsys_state *memcg_css; struct inode_switch_wbs_context *isw; int nr; bool restart = false; isw = kzalloc(struct_size(isw, inodes, WB_MAX_INODES_PER_ISW), GFP_KERNEL); if (!isw) return restart; atomic_inc(&isw_nr_in_flight); for (memcg_css = wb->memcg_css->parent; memcg_css; memcg_css = memcg_css->parent) { isw->new_wb = wb_get_create(wb->bdi, memcg_css, GFP_KERNEL); if (isw->new_wb) break; } if (unlikely(!isw->new_wb)) isw->new_wb = &wb->bdi->wb; /* wb_get() is noop for bdi's wb */ nr = 0; spin_lock(&wb->list_lock); /* * In addition to the inodes that have completed writeback, also switch * cgwbs for those inodes only with dirty timestamps. Otherwise, those * inodes won't be written back for a long time when lazytime is * enabled, and thus pinning the dying cgwbs. It won't break the * bandwidth restrictions, as writeback of inode metadata is not * accounted for. */ restart = isw_prepare_wbs_switch(isw, &wb->b_attached, &nr); if (!restart) restart = isw_prepare_wbs_switch(isw, &wb->b_dirty_time, &nr); spin_unlock(&wb->list_lock); /* no attached inodes? bail out */ if (nr == 0) { atomic_dec(&isw_nr_in_flight); wb_put(isw->new_wb); kfree(isw); return restart; } /* * In addition to synchronizing among switchers, I_WB_SWITCH tells * the RCU protected stat update paths to grab the i_page * lock so that stat transfer can synchronize against them. * Let's continue after I_WB_SWITCH is guaranteed to be visible. */ INIT_RCU_WORK(&isw->work, inode_switch_wbs_work_fn); queue_rcu_work(isw_wq, &isw->work); return restart; } /** * wbc_attach_and_unlock_inode - associate wbc with target inode and unlock it * @wbc: writeback_control of interest * @inode: target inode * * @inode is locked and about to be written back under the control of @wbc. * Record @inode's writeback context into @wbc and unlock the i_lock. On * writeback completion, wbc_detach_inode() should be called. This is used * to track the cgroup writeback context. */ static void wbc_attach_and_unlock_inode(struct writeback_control *wbc, struct inode *inode) __releases(&inode->i_lock) { if (!inode_cgwb_enabled(inode)) { spin_unlock(&inode->i_lock); return; } wbc->wb = inode_to_wb(inode); wbc->inode = inode; wbc->wb_id = wbc->wb->memcg_css->id; wbc->wb_lcand_id = inode->i_wb_frn_winner; wbc->wb_tcand_id = 0; wbc->wb_bytes = 0; wbc->wb_lcand_bytes = 0; wbc->wb_tcand_bytes = 0; wb_get(wbc->wb); spin_unlock(&inode->i_lock); /* * A dying wb indicates that either the blkcg associated with the * memcg changed or the associated memcg is dying. In the first * case, a replacement wb should already be available and we should * refresh the wb immediately. In the second case, trying to * refresh will keep failing. */ if (unlikely(wb_dying(wbc->wb) && !css_is_dying(wbc->wb->memcg_css))) inode_switch_wbs(inode, wbc->wb_id); } /** * wbc_attach_fdatawrite_inode - associate wbc and inode for fdatawrite * @wbc: writeback_control of interest * @inode: target inode * * This function is to be used by __filemap_fdatawrite_range(), which is an * alternative entry point into writeback code, and first ensures @inode is * associated with a bdi_writeback and attaches it to @wbc. */ void wbc_attach_fdatawrite_inode(struct writeback_control *wbc, struct inode *inode) { spin_lock(&inode->i_lock); inode_attach_wb(inode, NULL); wbc_attach_and_unlock_inode(wbc, inode); } EXPORT_SYMBOL_GPL(wbc_attach_fdatawrite_inode); /** * wbc_detach_inode - disassociate wbc from inode and perform foreign detection * @wbc: writeback_control of the just finished writeback * * To be called after a writeback attempt of an inode finishes and undoes * wbc_attach_and_unlock_inode(). Can be called under any context. * * As concurrent write sharing of an inode is expected to be very rare and * memcg only tracks page ownership on first-use basis severely confining * the usefulness of such sharing, cgroup writeback tracks ownership * per-inode. While the support for concurrent write sharing of an inode * is deemed unnecessary, an inode being written to by different cgroups at * different points in time is a lot more common, and, more importantly, * charging only by first-use can too readily lead to grossly incorrect * behaviors (single foreign page can lead to gigabytes of writeback to be * incorrectly attributed). * * To resolve this issue, cgroup writeback detects the majority dirtier of * an inode and transfers the ownership to it. To avoid unnecessary * oscillation, the detection mechanism keeps track of history and gives * out the switch verdict only if the foreign usage pattern is stable over * a certain amount of time and/or writeback attempts. * * On each writeback attempt, @wbc tries to detect the majority writer * using Boyer-Moore majority vote algorithm. In addition to the byte * count from the majority voting, it also counts the bytes written for the * current wb and the last round's winner wb (max of last round's current * wb, the winner from two rounds ago, and the last round's majority * candidate). Keeping track of the historical winner helps the algorithm * to semi-reliably detect the most active writer even when it's not the * absolute majority. * * Once the winner of the round is determined, whether the winner is * foreign or not and how much IO time the round consumed is recorded in * inode->i_wb_frn_history. If the amount of recorded foreign IO time is * over a certain threshold, the switch verdict is given. */ void wbc_detach_inode(struct writeback_control *wbc) { struct bdi_writeback *wb = wbc->wb; struct inode *inode = wbc->inode; unsigned long avg_time, max_bytes, max_time; u16 history; int max_id; if (!wb) return; history = inode->i_wb_frn_history; avg_time = inode->i_wb_frn_avg_time; /* pick the winner of this round */ if (wbc->wb_bytes >= wbc->wb_lcand_bytes && wbc->wb_bytes >= wbc->wb_tcand_bytes) { max_id = wbc->wb_id; max_bytes = wbc->wb_bytes; } else if (wbc->wb_lcand_bytes >= wbc->wb_tcand_bytes) { max_id = wbc->wb_lcand_id; max_bytes = wbc->wb_lcand_bytes; } else { max_id = wbc->wb_tcand_id; max_bytes = wbc->wb_tcand_bytes; } /* * Calculate the amount of IO time the winner consumed and fold it * into the running average kept per inode. If the consumed IO * time is lower than avag / WB_FRN_TIME_CUT_DIV, ignore it for * deciding whether to switch or not. This is to prevent one-off * small dirtiers from skewing the verdict. */ max_time = DIV_ROUND_UP((max_bytes >> PAGE_SHIFT) << WB_FRN_TIME_SHIFT, wb->avg_write_bandwidth); if (avg_time) avg_time += (max_time >> WB_FRN_TIME_AVG_SHIFT) - (avg_time >> WB_FRN_TIME_AVG_SHIFT); else avg_time = max_time; /* immediate catch up on first run */ if (max_time >= avg_time / WB_FRN_TIME_CUT_DIV) { int slots; /* * The switch verdict is reached if foreign wb's consume * more than a certain proportion of IO time in a * WB_FRN_TIME_PERIOD. This is loosely tracked by 16 slot * history mask where each bit represents one sixteenth of * the period. Determine the number of slots to shift into * history from @max_time. */ slots = min(DIV_ROUND_UP(max_time, WB_FRN_HIST_UNIT), (unsigned long)WB_FRN_HIST_MAX_SLOTS); history <<= slots; if (wbc->wb_id != max_id) history |= (1U << slots) - 1; if (history) trace_inode_foreign_history(inode, wbc, history); /* * Switch if the current wb isn't the consistent winner. * If there are multiple closely competing dirtiers, the * inode may switch across them repeatedly over time, which * is okay. The main goal is avoiding keeping an inode on * the wrong wb for an extended period of time. */ if (hweight16(history) > WB_FRN_HIST_THR_SLOTS) inode_switch_wbs(inode, max_id); } /* * Multiple instances of this function may race to update the * following fields but we don't mind occassional inaccuracies. */ inode->i_wb_frn_winner = max_id; inode->i_wb_frn_avg_time = min(avg_time, (unsigned long)U16_MAX); inode->i_wb_frn_history = history; wb_put(wbc->wb); wbc->wb = NULL; } EXPORT_SYMBOL_GPL(wbc_detach_inode); /** * wbc_account_cgroup_owner - account writeback to update inode cgroup ownership * @wbc: writeback_control of the writeback in progress * @folio: folio being written out * @bytes: number of bytes being written out * * @bytes from @folio are about to written out during the writeback * controlled by @wbc. Keep the book for foreign inode detection. See * wbc_detach_inode(). */ void wbc_account_cgroup_owner(struct writeback_control *wbc, struct folio *folio, size_t bytes) { struct cgroup_subsys_state *css; int id; /* * pageout() path doesn't attach @wbc to the inode being written * out. This is intentional as we don't want the function to block * behind a slow cgroup. Ultimately, we want pageout() to kick off * regular writeback instead of writing things out itself. */ if (!wbc->wb || wbc->no_cgroup_owner) return; css = mem_cgroup_css_from_folio(folio); /* dead cgroups shouldn't contribute to inode ownership arbitration */ if (!(css->flags & CSS_ONLINE)) return; id = css->id; if (id == wbc->wb_id) { wbc->wb_bytes += bytes; return; } if (id == wbc->wb_lcand_id) wbc->wb_lcand_bytes += bytes; /* Boyer-Moore majority vote algorithm */ if (!wbc->wb_tcand_bytes) wbc->wb_tcand_id = id; if (id == wbc->wb_tcand_id) wbc->wb_tcand_bytes += bytes; else wbc->wb_tcand_bytes -= min(bytes, wbc->wb_tcand_bytes); } EXPORT_SYMBOL_GPL(wbc_account_cgroup_owner); /** * wb_split_bdi_pages - split nr_pages to write according to bandwidth * @wb: target bdi_writeback to split @nr_pages to * @nr_pages: number of pages to write for the whole bdi * * Split @wb's portion of @nr_pages according to @wb's write bandwidth in * relation to the total write bandwidth of all wb's w/ dirty inodes on * @wb->bdi. */ static long wb_split_bdi_pages(struct bdi_writeback *wb, long nr_pages) { unsigned long this_bw = wb->avg_write_bandwidth; unsigned long tot_bw = atomic_long_read(&wb->bdi->tot_write_bandwidth); if (nr_pages == LONG_MAX) return LONG_MAX; /* * This may be called on clean wb's and proportional distribution * may not make sense, just use the original @nr_pages in those * cases. In general, we wanna err on the side of writing more. */ if (!tot_bw || this_bw >= tot_bw) return nr_pages; else return DIV_ROUND_UP_ULL((u64)nr_pages * this_bw, tot_bw); } /** * bdi_split_work_to_wbs - split a wb_writeback_work to all wb's of a bdi * @bdi: target backing_dev_info * @base_work: wb_writeback_work to issue * @skip_if_busy: skip wb's which already have writeback in progress * * Split and issue @base_work to all wb's (bdi_writeback's) of @bdi which * have dirty inodes. If @base_work->nr_page isn't %LONG_MAX, it's * distributed to the busy wbs according to each wb's proportion in the * total active write bandwidth of @bdi. */ static void bdi_split_work_to_wbs(struct backing_dev_info *bdi, struct wb_writeback_work *base_work, bool skip_if_busy) { struct bdi_writeback *last_wb = NULL; struct bdi_writeback *wb = list_entry(&bdi->wb_list, struct bdi_writeback, bdi_node); might_sleep(); restart: rcu_read_lock(); list_for_each_entry_continue_rcu(wb, &bdi->wb_list, bdi_node) { DEFINE_WB_COMPLETION(fallback_work_done, bdi); struct wb_writeback_work fallback_work; struct wb_writeback_work *work; long nr_pages; if (last_wb) { wb_put(last_wb); last_wb = NULL; } /* SYNC_ALL writes out I_DIRTY_TIME too */ if (!wb_has_dirty_io(wb) && (base_work->sync_mode == WB_SYNC_NONE || list_empty(&wb->b_dirty_time))) continue; if (skip_if_busy && writeback_in_progress(wb)) continue; nr_pages = wb_split_bdi_pages(wb, base_work->nr_pages); work = kmalloc(sizeof(*work), GFP_ATOMIC); if (work) { *work = *base_work; work->nr_pages = nr_pages; work->auto_free = 1; wb_queue_work(wb, work); continue; } /* * If wb_tryget fails, the wb has been shutdown, skip it. * * Pin @wb so that it stays on @bdi->wb_list. This allows * continuing iteration from @wb after dropping and * regrabbing rcu read lock. */ if (!wb_tryget(wb)) continue; /* alloc failed, execute synchronously using on-stack fallback */ work = &fallback_work; *work = *base_work; work->nr_pages = nr_pages; work->auto_free = 0; work->done = &fallback_work_done; wb_queue_work(wb, work); last_wb = wb; rcu_read_unlock(); wb_wait_for_completion(&fallback_work_done); goto restart; } rcu_read_unlock(); if (last_wb) wb_put(last_wb); } /** * cgroup_writeback_by_id - initiate cgroup writeback from bdi and memcg IDs * @bdi_id: target bdi id * @memcg_id: target memcg css id * @reason: reason why some writeback work initiated * @done: target wb_completion * * Initiate flush of the bdi_writeback identified by @bdi_id and @memcg_id * with the specified parameters. */ int cgroup_writeback_by_id(u64 bdi_id, int memcg_id, enum wb_reason reason, struct wb_completion *done) { struct backing_dev_info *bdi; struct cgroup_subsys_state *memcg_css; struct bdi_writeback *wb; struct wb_writeback_work *work; unsigned long dirty; int ret; /* lookup bdi and memcg */ bdi = bdi_get_by_id(bdi_id); if (!bdi) return -ENOENT; rcu_read_lock(); memcg_css = css_from_id(memcg_id, &memory_cgrp_subsys); if (memcg_css && !css_tryget(memcg_css)) memcg_css = NULL; rcu_read_unlock(); if (!memcg_css) { ret = -ENOENT; goto out_bdi_put; } /* * And find the associated wb. If the wb isn't there already * there's nothing to flush, don't create one. */ wb = wb_get_lookup(bdi, memcg_css); if (!wb) { ret = -ENOENT; goto out_css_put; } /* * The caller is attempting to write out most of * the currently dirty pages. Let's take the current dirty page * count and inflate it by 25% which should be large enough to * flush out most dirty pages while avoiding getting livelocked by * concurrent dirtiers. * * BTW the memcg stats are flushed periodically and this is best-effort * estimation, so some potential error is ok. */ dirty = memcg_page_state(mem_cgroup_from_css(memcg_css), NR_FILE_DIRTY); dirty = dirty * 10 / 8; /* issue the writeback work */ work = kzalloc(sizeof(*work), GFP_NOWAIT | __GFP_NOWARN); if (work) { work->nr_pages = dirty; work->sync_mode = WB_SYNC_NONE; work->range_cyclic = 1; work->reason = reason; work->done = done; work->auto_free = 1; wb_queue_work(wb, work); ret = 0; } else { ret = -ENOMEM; } wb_put(wb); out_css_put: css_put(memcg_css); out_bdi_put: bdi_put(bdi); return ret; } /** * cgroup_writeback_umount - flush inode wb switches for umount * @sb: target super_block * * This function is called when a super_block is about to be destroyed and * flushes in-flight inode wb switches. An inode wb switch goes through * RCU and then workqueue, so the two need to be flushed in order to ensure * that all previously scheduled switches are finished. As wb switches are * rare occurrences and synchronize_rcu() can take a while, perform * flushing iff wb switches are in flight. */ void cgroup_writeback_umount(struct super_block *sb) { if (!(sb->s_bdi->capabilities & BDI_CAP_WRITEBACK)) return; /* * SB_ACTIVE should be reliably cleared before checking * isw_nr_in_flight, see generic_shutdown_super(). */ smp_mb(); if (atomic_read(&isw_nr_in_flight)) { /* * Use rcu_barrier() to wait for all pending callbacks to * ensure that all in-flight wb switches are in the workqueue. */ rcu_barrier(); flush_workqueue(isw_wq); } } static int __init cgroup_writeback_init(void) { isw_wq = alloc_workqueue("inode_switch_wbs", 0, 0); if (!isw_wq) return -ENOMEM; return 0; } fs_initcall(cgroup_writeback_init); #else /* CONFIG_CGROUP_WRITEBACK */ static void bdi_down_write_wb_switch_rwsem(struct backing_dev_info *bdi) { } static void bdi_up_write_wb_switch_rwsem(struct backing_dev_info *bdi) { } static void inode_cgwb_move_to_attached(struct inode *inode, struct bdi_writeback *wb) { assert_spin_locked(&wb->list_lock); assert_spin_locked(&inode->i_lock); WARN_ON_ONCE(inode->i_state & I_FREEING); inode->i_state &= ~I_SYNC_QUEUED; list_del_init(&inode->i_io_list); wb_io_lists_depopulated(wb); } static struct bdi_writeback * locked_inode_to_wb_and_lock_list(struct inode *inode) __releases(&inode->i_lock) __acquires(&wb->list_lock) { struct bdi_writeback *wb = inode_to_wb(inode); spin_unlock(&inode->i_lock); spin_lock(&wb->list_lock); return wb; } static struct bdi_writeback *inode_to_wb_and_lock_list(struct inode *inode) __acquires(&wb->list_lock) { struct bdi_writeback *wb = inode_to_wb(inode); spin_lock(&wb->list_lock); return wb; } static long wb_split_bdi_pages(struct bdi_writeback *wb, long nr_pages) { return nr_pages; } static void bdi_split_work_to_wbs(struct backing_dev_info *bdi, struct wb_writeback_work *base_work, bool skip_if_busy) { might_sleep(); if (!skip_if_busy || !writeback_in_progress(&bdi->wb)) { base_work->auto_free = 0; wb_queue_work(&bdi->wb, base_work); } } static inline void wbc_attach_and_unlock_inode(struct writeback_control *wbc, struct inode *inode) __releases(&inode->i_lock) { spin_unlock(&inode->i_lock); } #endif /* CONFIG_CGROUP_WRITEBACK */ /* * Add in the number of potentially dirty inodes, because each inode * write can dirty pagecache in the underlying blockdev. */ static unsigned long get_nr_dirty_pages(void) { return global_node_page_state(NR_FILE_DIRTY) + get_nr_dirty_inodes(); } static void wb_start_writeback(struct bdi_writeback *wb, enum wb_reason reason) { if (!wb_has_dirty_io(wb)) return; /* * All callers of this function want to start writeback of all * dirty pages. Places like vmscan can call this at a very * high frequency, causing pointless allocations of tons of * work items and keeping the flusher threads busy retrieving * that work. Ensure that we only allow one of them pending and * inflight at the time. */ if (test_bit(WB_start_all, &wb->state) || test_and_set_bit(WB_start_all, &wb->state)) return; wb->start_all_reason = reason; wb_wakeup(wb); } /** * wb_start_background_writeback - start background writeback * @wb: bdi_writback to write from * * Description: * This makes sure WB_SYNC_NONE background writeback happens. When * this function returns, it is only guaranteed that for given wb * some IO is happening if we are over background dirty threshold. * Caller need not hold sb s_umount semaphore. */ void wb_start_background_writeback(struct bdi_writeback *wb) { /* * We just wake up the flusher thread. It will perform background * writeback as soon as there is no other work to do. */ trace_writeback_wake_background(wb); wb_wakeup(wb); } /* * Remove the inode from the writeback list it is on. */ void inode_io_list_del(struct inode *inode) { struct bdi_writeback *wb; wb = inode_to_wb_and_lock_list(inode); spin_lock(&inode->i_lock); inode->i_state &= ~I_SYNC_QUEUED; list_del_init(&inode->i_io_list); wb_io_lists_depopulated(wb); spin_unlock(&inode->i_lock); spin_unlock(&wb->list_lock); } EXPORT_SYMBOL(inode_io_list_del); /* * mark an inode as under writeback on the sb */ void sb_mark_inode_writeback(struct inode *inode) { struct super_block *sb = inode->i_sb; unsigned long flags; if (list_empty(&inode->i_wb_list)) { spin_lock_irqsave(&sb->s_inode_wblist_lock, flags); if (list_empty(&inode->i_wb_list)) { list_add_tail(&inode->i_wb_list, &sb->s_inodes_wb); trace_sb_mark_inode_writeback(inode); } spin_unlock_irqrestore(&sb->s_inode_wblist_lock, flags); } } /* * clear an inode as under writeback on the sb */ void sb_clear_inode_writeback(struct inode *inode) { struct super_block *sb = inode->i_sb; unsigned long flags; if (!list_empty(&inode->i_wb_list)) { spin_lock_irqsave(&sb->s_inode_wblist_lock, flags); if (!list_empty(&inode->i_wb_list)) { list_del_init(&inode->i_wb_list); trace_sb_clear_inode_writeback(inode); } spin_unlock_irqrestore(&sb->s_inode_wblist_lock, flags); } } /* * Redirty an inode: set its when-it-was dirtied timestamp and move it to the * furthest end of its superblock's dirty-inode list. * * Before stamping the inode's ->dirtied_when, we check to see whether it is * already the most-recently-dirtied inode on the b_dirty list. If that is * the case then the inode must have been redirtied while it was being written * out and we don't reset its dirtied_when. */ static void redirty_tail_locked(struct inode *inode, struct bdi_writeback *wb) { assert_spin_locked(&inode->i_lock); inode->i_state &= ~I_SYNC_QUEUED; /* * When the inode is being freed just don't bother with dirty list * tracking. Flush worker will ignore this inode anyway and it will * trigger assertions in inode_io_list_move_locked(). */ if (inode->i_state & I_FREEING) { list_del_init(&inode->i_io_list); wb_io_lists_depopulated(wb); return; } if (!list_empty(&wb->b_dirty)) { struct inode *tail; tail = wb_inode(wb->b_dirty.next); if (time_before(inode->dirtied_when, tail->dirtied_when)) inode->dirtied_when = jiffies; } inode_io_list_move_locked(inode, wb, &wb->b_dirty); } static void redirty_tail(struct inode *inode, struct bdi_writeback *wb) { spin_lock(&inode->i_lock); redirty_tail_locked(inode, wb); spin_unlock(&inode->i_lock); } /* * requeue inode for re-scanning after bdi->b_io list is exhausted. */ static void requeue_io(struct inode *inode, struct bdi_writeback *wb) { inode_io_list_move_locked(inode, wb, &wb->b_more_io); } static void inode_sync_complete(struct inode *inode) { assert_spin_locked(&inode->i_lock); inode->i_state &= ~I_SYNC; /* If inode is clean an unused, put it into LRU now... */ inode_add_lru(inode); /* Called with inode->i_lock which ensures memory ordering. */ inode_wake_up_bit(inode, __I_SYNC); } static bool inode_dirtied_after(struct inode *inode, unsigned long t) { bool ret = time_after(inode->dirtied_when, t); #ifndef CONFIG_64BIT /* * For inodes being constantly redirtied, dirtied_when can get stuck. * It _appears_ to be in the future, but is actually in distant past. * This test is necessary to prevent such wrapped-around relative times * from permanently stopping the whole bdi writeback. */ ret = ret && time_before_eq(inode->dirtied_when, jiffies); #endif return ret; } /* * Move expired (dirtied before dirtied_before) dirty inodes from * @delaying_queue to @dispatch_queue. */ static int move_expired_inodes(struct list_head *delaying_queue, struct list_head *dispatch_queue, unsigned long dirtied_before) { LIST_HEAD(tmp); struct list_head *pos, *node; struct super_block *sb = NULL; struct inode *inode; int do_sb_sort = 0; int moved = 0; while (!list_empty(delaying_queue)) { inode = wb_inode(delaying_queue->prev); if (inode_dirtied_after(inode, dirtied_before)) break; spin_lock(&inode->i_lock); list_move(&inode->i_io_list, &tmp); moved++; inode->i_state |= I_SYNC_QUEUED; spin_unlock(&inode->i_lock); if (sb_is_blkdev_sb(inode->i_sb)) continue; if (sb && sb != inode->i_sb) do_sb_sort = 1; sb = inode->i_sb; } /* just one sb in list, splice to dispatch_queue and we're done */ if (!do_sb_sort) { list_splice(&tmp, dispatch_queue); goto out; } /* * Although inode's i_io_list is moved from 'tmp' to 'dispatch_queue', * we don't take inode->i_lock here because it is just a pointless overhead. * Inode is already marked as I_SYNC_QUEUED so writeback list handling is * fully under our control. */ while (!list_empty(&tmp)) { sb = wb_inode(tmp.prev)->i_sb; list_for_each_prev_safe(pos, node, &tmp) { inode = wb_inode(pos); if (inode->i_sb == sb) list_move(&inode->i_io_list, dispatch_queue); } } out: return moved; } /* * Queue all expired dirty inodes for io, eldest first. * Before * newly dirtied b_dirty b_io b_more_io * =============> gf edc BA * After * newly dirtied b_dirty b_io b_more_io * =============> g fBAedc * | * +--> dequeue for IO */ static void queue_io(struct bdi_writeback *wb, struct wb_writeback_work *work, unsigned long dirtied_before) { int moved; unsigned long time_expire_jif = dirtied_before; assert_spin_locked(&wb->list_lock); list_splice_init(&wb->b_more_io, &wb->b_io); moved = move_expired_inodes(&wb->b_dirty, &wb->b_io, dirtied_before); if (!work->for_sync) time_expire_jif = jiffies - dirtytime_expire_interval * HZ; moved += move_expired_inodes(&wb->b_dirty_time, &wb->b_io, time_expire_jif); if (moved) wb_io_lists_populated(wb); trace_writeback_queue_io(wb, work, dirtied_before, moved); } static int write_inode(struct inode *inode, struct writeback_control *wbc) { int ret; if (inode->i_sb->s_op->write_inode && !is_bad_inode(inode)) { trace_writeback_write_inode_start(inode, wbc); ret = inode->i_sb->s_op->write_inode(inode, wbc); trace_writeback_write_inode(inode, wbc); return ret; } return 0; } /* * Wait for writeback on an inode to complete. Called with i_lock held. * Caller must make sure inode cannot go away when we drop i_lock. */ void inode_wait_for_writeback(struct inode *inode) { struct wait_bit_queue_entry wqe; struct wait_queue_head *wq_head; assert_spin_locked(&inode->i_lock); if (!(inode->i_state & I_SYNC)) return; wq_head = inode_bit_waitqueue(&wqe, inode, __I_SYNC); for (;;) { prepare_to_wait_event(wq_head, &wqe.wq_entry, TASK_UNINTERRUPTIBLE); /* Checking I_SYNC with inode->i_lock guarantees memory ordering. */ if (!(inode->i_state & I_SYNC)) break; spin_unlock(&inode->i_lock); schedule(); spin_lock(&inode->i_lock); } finish_wait(wq_head, &wqe.wq_entry); } /* * Sleep until I_SYNC is cleared. This function must be called with i_lock * held and drops it. It is aimed for callers not holding any inode reference * so once i_lock is dropped, inode can go away. */ static void inode_sleep_on_writeback(struct inode *inode) __releases(inode->i_lock) { struct wait_bit_queue_entry wqe; struct wait_queue_head *wq_head; bool sleep; assert_spin_locked(&inode->i_lock); wq_head = inode_bit_waitqueue(&wqe, inode, __I_SYNC); prepare_to_wait_event(wq_head, &wqe.wq_entry, TASK_UNINTERRUPTIBLE); /* Checking I_SYNC with inode->i_lock guarantees memory ordering. */ sleep = !!(inode->i_state & I_SYNC); spin_unlock(&inode->i_lock); if (sleep) schedule(); finish_wait(wq_head, &wqe.wq_entry); } /* * Find proper writeback list for the inode depending on its current state and * possibly also change of its state while we were doing writeback. Here we * handle things such as livelock prevention or fairness of writeback among * inodes. This function can be called only by flusher thread - noone else * processes all inodes in writeback lists and requeueing inodes behind flusher * thread's back can have unexpected consequences. */ static void requeue_inode(struct inode *inode, struct bdi_writeback *wb, struct writeback_control *wbc, unsigned long dirtied_before) { if (inode->i_state & I_FREEING) return; /* * Sync livelock prevention. Each inode is tagged and synced in one * shot. If still dirty, it will be redirty_tail()'ed below. Update * the dirty time to prevent enqueue and sync it again. */ if ((inode->i_state & I_DIRTY) && (wbc->sync_mode == WB_SYNC_ALL || wbc->tagged_writepages)) inode->dirtied_when = jiffies; if (wbc->pages_skipped) { /* * Writeback is not making progress due to locked buffers. * Skip this inode for now. Although having skipped pages * is odd for clean inodes, it can happen for some * filesystems so handle that gracefully. */ if (inode->i_state & I_DIRTY_ALL) redirty_tail_locked(inode, wb); else inode_cgwb_move_to_attached(inode, wb); return; } if (mapping_tagged(inode->i_mapping, PAGECACHE_TAG_DIRTY)) { /* * We didn't write back all the pages. nfs_writepages() * sometimes bales out without doing anything. */ if (wbc->nr_to_write <= 0 && !inode_dirtied_after(inode, dirtied_before)) { /* Slice used up. Queue for next turn. */ requeue_io(inode, wb); } else { /* * Writeback blocked by something other than * congestion. Delay the inode for some time to * avoid spinning on the CPU (100% iowait) * retrying writeback of the dirty page/inode * that cannot be performed immediately. */ redirty_tail_locked(inode, wb); } } else if (inode->i_state & I_DIRTY) { /* * Filesystems can dirty the inode during writeback operations, * such as delayed allocation during submission or metadata * updates after data IO completion. */ redirty_tail_locked(inode, wb); } else if (inode->i_state & I_DIRTY_TIME) { inode->dirtied_when = jiffies; inode_io_list_move_locked(inode, wb, &wb->b_dirty_time); inode->i_state &= ~I_SYNC_QUEUED; } else { /* The inode is clean. Remove from writeback lists. */ inode_cgwb_move_to_attached(inode, wb); } } /* * Write out an inode and its dirty pages (or some of its dirty pages, depending * on @wbc->nr_to_write), and clear the relevant dirty flags from i_state. * * This doesn't remove the inode from the writeback list it is on, except * potentially to move it from b_dirty_time to b_dirty due to timestamp * expiration. The caller is otherwise responsible for writeback list handling. * * The caller is also responsible for setting the I_SYNC flag beforehand and * calling inode_sync_complete() to clear it afterwards. */ static int __writeback_single_inode(struct inode *inode, struct writeback_control *wbc) { struct address_space *mapping = inode->i_mapping; long nr_to_write = wbc->nr_to_write; unsigned dirty; int ret; WARN_ON(!(inode->i_state & I_SYNC)); trace_writeback_single_inode_start(inode, wbc, nr_to_write); ret = do_writepages(mapping, wbc); /* * Make sure to wait on the data before writing out the metadata. * This is important for filesystems that modify metadata on data * I/O completion. We don't do it for sync(2) writeback because it has a * separate, external IO completion path and ->sync_fs for guaranteeing * inode metadata is written back correctly. */ if (wbc->sync_mode == WB_SYNC_ALL && !wbc->for_sync) { int err = filemap_fdatawait(mapping); if (ret == 0) ret = err; } /* * If the inode has dirty timestamps and we need to write them, call * mark_inode_dirty_sync() to notify the filesystem about it and to * change I_DIRTY_TIME into I_DIRTY_SYNC. */ if ((inode->i_state & I_DIRTY_TIME) && (wbc->sync_mode == WB_SYNC_ALL || time_after(jiffies, inode->dirtied_time_when + dirtytime_expire_interval * HZ))) { trace_writeback_lazytime(inode); mark_inode_dirty_sync(inode); } /* * Get and clear the dirty flags from i_state. This needs to be done * after calling writepages because some filesystems may redirty the * inode during writepages due to delalloc. It also needs to be done * after handling timestamp expiration, as that may dirty the inode too. */ spin_lock(&inode->i_lock); dirty = inode->i_state & I_DIRTY; inode->i_state &= ~dirty; /* * Paired with smp_mb() in __mark_inode_dirty(). This allows * __mark_inode_dirty() to test i_state without grabbing i_lock - * either they see the I_DIRTY bits cleared or we see the dirtied * inode. * * I_DIRTY_PAGES is always cleared together above even if @mapping * still has dirty pages. The flag is reinstated after smp_mb() if * necessary. This guarantees that either __mark_inode_dirty() * sees clear I_DIRTY_PAGES or we see PAGECACHE_TAG_DIRTY. */ smp_mb(); if (mapping_tagged(mapping, PAGECACHE_TAG_DIRTY)) inode->i_state |= I_DIRTY_PAGES; else if (unlikely(inode->i_state & I_PINNING_NETFS_WB)) { if (!(inode->i_state & I_DIRTY_PAGES)) { inode->i_state &= ~I_PINNING_NETFS_WB; wbc->unpinned_netfs_wb = true; dirty |= I_PINNING_NETFS_WB; /* Cause write_inode */ } } spin_unlock(&inode->i_lock); /* Don't write the inode if only I_DIRTY_PAGES was set */ if (dirty & ~I_DIRTY_PAGES) { int err = write_inode(inode, wbc); if (ret == 0) ret = err; } wbc->unpinned_netfs_wb = false; trace_writeback_single_inode(inode, wbc, nr_to_write); return ret; } /* * Write out an inode's dirty data and metadata on-demand, i.e. separately from * the regular batched writeback done by the flusher threads in * writeback_sb_inodes(). @wbc controls various aspects of the write, such as * whether it is a data-integrity sync (%WB_SYNC_ALL) or not (%WB_SYNC_NONE). * * To prevent the inode from going away, either the caller must have a reference * to the inode, or the inode must have I_WILL_FREE or I_FREEING set. */ static int writeback_single_inode(struct inode *inode, struct writeback_control *wbc) { struct bdi_writeback *wb; int ret = 0; spin_lock(&inode->i_lock); if (!atomic_read(&inode->i_count)) WARN_ON(!(inode->i_state & (I_WILL_FREE|I_FREEING))); else WARN_ON(inode->i_state & I_WILL_FREE); if (inode->i_state & I_SYNC) { /* * Writeback is already running on the inode. For WB_SYNC_NONE, * that's enough and we can just return. For WB_SYNC_ALL, we * must wait for the existing writeback to complete, then do * writeback again if there's anything left. */ if (wbc->sync_mode != WB_SYNC_ALL) goto out; inode_wait_for_writeback(inode); } WARN_ON(inode->i_state & I_SYNC); /* * If the inode is already fully clean, then there's nothing to do. * * For data-integrity syncs we also need to check whether any pages are * still under writeback, e.g. due to prior WB_SYNC_NONE writeback. If * there are any such pages, we'll need to wait for them. */ if (!(inode->i_state & I_DIRTY_ALL) && (wbc->sync_mode != WB_SYNC_ALL || !mapping_tagged(inode->i_mapping, PAGECACHE_TAG_WRITEBACK))) goto out; inode->i_state |= I_SYNC; wbc_attach_and_unlock_inode(wbc, inode); ret = __writeback_single_inode(inode, wbc); wbc_detach_inode(wbc); wb = inode_to_wb_and_lock_list(inode); spin_lock(&inode->i_lock); /* * If the inode is freeing, its i_io_list shoudn't be updated * as it can be finally deleted at this moment. */ if (!(inode->i_state & I_FREEING)) { /* * If the inode is now fully clean, then it can be safely * removed from its writeback list (if any). Otherwise the * flusher threads are responsible for the writeback lists. */ if (!(inode->i_state & I_DIRTY_ALL)) inode_cgwb_move_to_attached(inode, wb); else if (!(inode->i_state & I_SYNC_QUEUED)) { if ((inode->i_state & I_DIRTY)) redirty_tail_locked(inode, wb); else if (inode->i_state & I_DIRTY_TIME) { inode->dirtied_when = jiffies; inode_io_list_move_locked(inode, wb, &wb->b_dirty_time); } } } spin_unlock(&wb->list_lock); inode_sync_complete(inode); out: spin_unlock(&inode->i_lock); return ret; } static long writeback_chunk_size(struct bdi_writeback *wb, struct wb_writeback_work *work) { long pages; /* * WB_SYNC_ALL mode does livelock avoidance by syncing dirty * inodes/pages in one big loop. Setting wbc.nr_to_write=LONG_MAX * here avoids calling into writeback_inodes_wb() more than once. * * The intended call sequence for WB_SYNC_ALL writeback is: * * wb_writeback() * writeback_sb_inodes() <== called only once * write_cache_pages() <== called once for each inode * (quickly) tag currently dirty pages * (maybe slowly) sync all tagged pages */ if (work->sync_mode == WB_SYNC_ALL || work->tagged_writepages) pages = LONG_MAX; else { pages = min(wb->avg_write_bandwidth / 2, global_wb_domain.dirty_limit / DIRTY_SCOPE); pages = min(pages, work->nr_pages); pages = round_down(pages + MIN_WRITEBACK_PAGES, MIN_WRITEBACK_PAGES); } return pages; } /* * Write a portion of b_io inodes which belong to @sb. * * Return the number of pages and/or inodes written. * * NOTE! This is called with wb->list_lock held, and will * unlock and relock that for each inode it ends up doing * IO for. */ static long writeback_sb_inodes(struct super_block *sb, struct bdi_writeback *wb, struct wb_writeback_work *work) { struct writeback_control wbc = { .sync_mode = work->sync_mode, .tagged_writepages = work->tagged_writepages, .for_kupdate = work->for_kupdate, .for_background = work->for_background, .for_sync = work->for_sync, .range_cyclic = work->range_cyclic, .range_start = 0, .range_end = LLONG_MAX, }; unsigned long start_time = jiffies; long write_chunk; long total_wrote = 0; /* count both pages and inodes */ unsigned long dirtied_before = jiffies; if (work->for_kupdate) dirtied_before = jiffies - msecs_to_jiffies(dirty_expire_interval * 10); while (!list_empty(&wb->b_io)) { struct inode *inode = wb_inode(wb->b_io.prev); struct bdi_writeback *tmp_wb; long wrote; if (inode->i_sb != sb) { if (work->sb) { /* * We only want to write back data for this * superblock, move all inodes not belonging * to it back onto the dirty list. */ redirty_tail(inode, wb); continue; } /* * The inode belongs to a different superblock. * Bounce back to the caller to unpin this and * pin the next superblock. */ break; } /* * Don't bother with new inodes or inodes being freed, first * kind does not need periodic writeout yet, and for the latter * kind writeout is handled by the freer. */ spin_lock(&inode->i_lock); if (inode->i_state & (I_NEW | I_FREEING | I_WILL_FREE)) { redirty_tail_locked(inode, wb); spin_unlock(&inode->i_lock); continue; } if ((inode->i_state & I_SYNC) && wbc.sync_mode != WB_SYNC_ALL) { /* * If this inode is locked for writeback and we are not * doing writeback-for-data-integrity, move it to * b_more_io so that writeback can proceed with the * other inodes on s_io. * * We'll have another go at writing back this inode * when we completed a full scan of b_io. */ requeue_io(inode, wb); spin_unlock(&inode->i_lock); trace_writeback_sb_inodes_requeue(inode); continue; } spin_unlock(&wb->list_lock); /* * We already requeued the inode if it had I_SYNC set and we * are doing WB_SYNC_NONE writeback. So this catches only the * WB_SYNC_ALL case. */ if (inode->i_state & I_SYNC) { /* Wait for I_SYNC. This function drops i_lock... */ inode_sleep_on_writeback(inode); /* Inode may be gone, start again */ spin_lock(&wb->list_lock); continue; } inode->i_state |= I_SYNC; wbc_attach_and_unlock_inode(&wbc, inode); write_chunk = writeback_chunk_size(wb, work); wbc.nr_to_write = write_chunk; wbc.pages_skipped = 0; /* * We use I_SYNC to pin the inode in memory. While it is set * evict_inode() will wait so the inode cannot be freed. */ __writeback_single_inode(inode, &wbc); wbc_detach_inode(&wbc); work->nr_pages -= write_chunk - wbc.nr_to_write; wrote = write_chunk - wbc.nr_to_write - wbc.pages_skipped; wrote = wrote < 0 ? 0 : wrote; total_wrote += wrote; if (need_resched()) { /* * We're trying to balance between building up a nice * long list of IOs to improve our merge rate, and * getting those IOs out quickly for anyone throttling * in balance_dirty_pages(). cond_resched() doesn't * unplug, so get our IOs out the door before we * give up the CPU. */ blk_flush_plug(current->plug, false); cond_resched(); } /* * Requeue @inode if still dirty. Be careful as @inode may * have been switched to another wb in the meantime. */ tmp_wb = inode_to_wb_and_lock_list(inode); spin_lock(&inode->i_lock); if (!(inode->i_state & I_DIRTY_ALL)) total_wrote++; requeue_inode(inode, tmp_wb, &wbc, dirtied_before); inode_sync_complete(inode); spin_unlock(&inode->i_lock); if (unlikely(tmp_wb != wb)) { spin_unlock(&tmp_wb->list_lock); spin_lock(&wb->list_lock); } /* * bail out to wb_writeback() often enough to check * background threshold and other termination conditions. */ if (total_wrote) { if (time_is_before_jiffies(start_time + HZ / 10UL)) break; if (work->nr_pages <= 0) break; } } return total_wrote; } static long __writeback_inodes_wb(struct bdi_writeback *wb, struct wb_writeback_work *work) { unsigned long start_time = jiffies; long wrote = 0; while (!list_empty(&wb->b_io)) { struct inode *inode = wb_inode(wb->b_io.prev); struct super_block *sb = inode->i_sb; if (!super_trylock_shared(sb)) { /* * super_trylock_shared() may fail consistently due to * s_umount being grabbed by someone else. Don't use * requeue_io() to avoid busy retrying the inode/sb. */ redirty_tail(inode, wb); continue; } wrote += writeback_sb_inodes(sb, wb, work); up_read(&sb->s_umount); /* refer to the same tests at the end of writeback_sb_inodes */ if (wrote) { if (time_is_before_jiffies(start_time + HZ / 10UL)) break; if (work->nr_pages <= 0) break; } } /* Leave any unwritten inodes on b_io */ return wrote; } static long writeback_inodes_wb(struct bdi_writeback *wb, long nr_pages, enum wb_reason reason) { struct wb_writeback_work work = { .nr_pages = nr_pages, .sync_mode = WB_SYNC_NONE, .range_cyclic = 1, .reason = reason, }; struct blk_plug plug; blk_start_plug(&plug); spin_lock(&wb->list_lock); if (list_empty(&wb->b_io)) queue_io(wb, &work, jiffies); __writeback_inodes_wb(wb, &work); spin_unlock(&wb->list_lock); blk_finish_plug(&plug); return nr_pages - work.nr_pages; } /* * Explicit flushing or periodic writeback of "old" data. * * Define "old": the first time one of an inode's pages is dirtied, we mark the * dirtying-time in the inode's address_space. So this periodic writeback code * just walks the superblock inode list, writing back any inodes which are * older than a specific point in time. * * Try to run once per dirty_writeback_interval. But if a writeback event * takes longer than a dirty_writeback_interval interval, then leave a * one-second gap. * * dirtied_before takes precedence over nr_to_write. So we'll only write back * all dirty pages if they are all attached to "old" mappings. */ static long wb_writeback(struct bdi_writeback *wb, struct wb_writeback_work *work) { long nr_pages = work->nr_pages; unsigned long dirtied_before = jiffies; struct inode *inode; long progress; struct blk_plug plug; bool queued = false; blk_start_plug(&plug); for (;;) { /* * Stop writeback when nr_pages has been consumed */ if (work->nr_pages <= 0) break; /* * Background writeout and kupdate-style writeback may * run forever. Stop them if there is other work to do * so that e.g. sync can proceed. They'll be restarted * after the other works are all done. */ if ((work->for_background || work->for_kupdate) && !list_empty(&wb->work_list)) break; /* * For background writeout, stop when we are below the * background dirty threshold */ if (work->for_background && !wb_over_bg_thresh(wb)) break; spin_lock(&wb->list_lock); trace_writeback_start(wb, work); if (list_empty(&wb->b_io)) { /* * Kupdate and background works are special and we want * to include all inodes that need writing. Livelock * avoidance is handled by these works yielding to any * other work so we are safe. */ if (work->for_kupdate) { dirtied_before = jiffies - msecs_to_jiffies(dirty_expire_interval * 10); } else if (work->for_background) dirtied_before = jiffies; queue_io(wb, work, dirtied_before); queued = true; } if (work->sb) progress = writeback_sb_inodes(work->sb, wb, work); else progress = __writeback_inodes_wb(wb, work); trace_writeback_written(wb, work); /* * Did we write something? Try for more * * Dirty inodes are moved to b_io for writeback in batches. * The completion of the current batch does not necessarily * mean the overall work is done. So we keep looping as long * as made some progress on cleaning pages or inodes. */ if (progress || !queued) { spin_unlock(&wb->list_lock); continue; } /* * No more inodes for IO, bail */ if (list_empty(&wb->b_more_io)) { spin_unlock(&wb->list_lock); break; } /* * Nothing written. Wait for some inode to * become available for writeback. Otherwise * we'll just busyloop. */ trace_writeback_wait(wb, work); inode = wb_inode(wb->b_more_io.prev); spin_lock(&inode->i_lock); spin_unlock(&wb->list_lock); /* This function drops i_lock... */ inode_sleep_on_writeback(inode); } blk_finish_plug(&plug); return nr_pages - work->nr_pages; } /* * Return the next wb_writeback_work struct that hasn't been processed yet. */ static struct wb_writeback_work *get_next_work_item(struct bdi_writeback *wb) { struct wb_writeback_work *work = NULL; spin_lock_irq(&wb->work_lock); if (!list_empty(&wb->work_list)) { work = list_entry(wb->work_list.next, struct wb_writeback_work, list); list_del_init(&work->list); } spin_unlock_irq(&wb->work_lock); return work; } static long wb_check_background_flush(struct bdi_writeback *wb) { if (wb_over_bg_thresh(wb)) { struct wb_writeback_work work = { .nr_pages = LONG_MAX, .sync_mode = WB_SYNC_NONE, .for_background = 1, .range_cyclic = 1, .reason = WB_REASON_BACKGROUND, }; return wb_writeback(wb, &work); } return 0; } static long wb_check_old_data_flush(struct bdi_writeback *wb) { unsigned long expired; long nr_pages; /* * When set to zero, disable periodic writeback */ if (!dirty_writeback_interval) return 0; expired = wb->last_old_flush + msecs_to_jiffies(dirty_writeback_interval * 10); if (time_before(jiffies, expired)) return 0; wb->last_old_flush = jiffies; nr_pages = get_nr_dirty_pages(); if (nr_pages) { struct wb_writeback_work work = { .nr_pages = nr_pages, .sync_mode = WB_SYNC_NONE, .for_kupdate = 1, .range_cyclic = 1, .reason = WB_REASON_PERIODIC, }; return wb_writeback(wb, &work); } return 0; } static long wb_check_start_all(struct bdi_writeback *wb) { long nr_pages; if (!test_bit(WB_start_all, &wb->state)) return 0; nr_pages = get_nr_dirty_pages(); if (nr_pages) { struct wb_writeback_work work = { .nr_pages = wb_split_bdi_pages(wb, nr_pages), .sync_mode = WB_SYNC_NONE, .range_cyclic = 1, .reason = wb->start_all_reason, }; nr_pages = wb_writeback(wb, &work); } clear_bit(WB_start_all, &wb->state); return nr_pages; } /* * Retrieve work items and do the writeback they describe */ static long wb_do_writeback(struct bdi_writeback *wb) { struct wb_writeback_work *work; long wrote = 0; set_bit(WB_writeback_running, &wb->state); while ((work = get_next_work_item(wb)) != NULL) { trace_writeback_exec(wb, work); wrote += wb_writeback(wb, work); finish_writeback_work(work); } /* * Check for a flush-everything request */ wrote += wb_check_start_all(wb); /* * Check for periodic writeback, kupdated() style */ wrote += wb_check_old_data_flush(wb); wrote += wb_check_background_flush(wb); clear_bit(WB_writeback_running, &wb->state); return wrote; } /* * Handle writeback of dirty data for the device backed by this bdi. Also * reschedules periodically and does kupdated style flushing. */ void wb_workfn(struct work_struct *work) { struct bdi_writeback *wb = container_of(to_delayed_work(work), struct bdi_writeback, dwork); long pages_written; set_worker_desc("flush-%s", bdi_dev_name(wb->bdi)); if (likely(!current_is_workqueue_rescuer() || !test_bit(WB_registered, &wb->state))) { /* * The normal path. Keep writing back @wb until its * work_list is empty. Note that this path is also taken * if @wb is shutting down even when we're running off the * rescuer as work_list needs to be drained. */ do { pages_written = wb_do_writeback(wb); trace_writeback_pages_written(pages_written); } while (!list_empty(&wb->work_list)); } else { /* * bdi_wq can't get enough workers and we're running off * the emergency worker. Don't hog it. Hopefully, 1024 is * enough for efficient IO. */ pages_written = writeback_inodes_wb(wb, 1024, WB_REASON_FORKER_THREAD); trace_writeback_pages_written(pages_written); } if (!list_empty(&wb->work_list)) wb_wakeup(wb); else if (wb_has_dirty_io(wb) && dirty_writeback_interval) wb_wakeup_delayed(wb); } /* * Start writeback of all dirty pages on this bdi. */ static void __wakeup_flusher_threads_bdi(struct backing_dev_info *bdi, enum wb_reason reason) { struct bdi_writeback *wb; if (!bdi_has_dirty_io(bdi)) return; list_for_each_entry_rcu(wb, &bdi->wb_list, bdi_node) wb_start_writeback(wb, reason); } void wakeup_flusher_threads_bdi(struct backing_dev_info *bdi, enum wb_reason reason) { rcu_read_lock(); __wakeup_flusher_threads_bdi(bdi, reason); rcu_read_unlock(); } /* * Wakeup the flusher threads to start writeback of all currently dirty pages */ void wakeup_flusher_threads(enum wb_reason reason) { struct backing_dev_info *bdi; /* * If we are expecting writeback progress we must submit plugged IO. */ blk_flush_plug(current->plug, true); rcu_read_lock(); list_for_each_entry_rcu(bdi, &bdi_list, bdi_list) __wakeup_flusher_threads_bdi(bdi, reason); rcu_read_unlock(); } /* * Wake up bdi's periodically to make sure dirtytime inodes gets * written back periodically. We deliberately do *not* check the * b_dirtytime list in wb_has_dirty_io(), since this would cause the * kernel to be constantly waking up once there are any dirtytime * inodes on the system. So instead we define a separate delayed work * function which gets called much more rarely. (By default, only * once every 12 hours.) * * If there is any other write activity going on in the file system, * this function won't be necessary. But if the only thing that has * happened on the file system is a dirtytime inode caused by an atime * update, we need this infrastructure below to make sure that inode * eventually gets pushed out to disk. */ static void wakeup_dirtytime_writeback(struct work_struct *w); static DECLARE_DELAYED_WORK(dirtytime_work, wakeup_dirtytime_writeback); static void wakeup_dirtytime_writeback(struct work_struct *w) { struct backing_dev_info *bdi; rcu_read_lock(); list_for_each_entry_rcu(bdi, &bdi_list, bdi_list) { struct bdi_writeback *wb; list_for_each_entry_rcu(wb, &bdi->wb_list, bdi_node) if (!list_empty(&wb->b_dirty_time)) wb_wakeup(wb); } rcu_read_unlock(); schedule_delayed_work(&dirtytime_work, dirtytime_expire_interval * HZ); } static int __init start_dirtytime_writeback(void) { schedule_delayed_work(&dirtytime_work, dirtytime_expire_interval * HZ); return 0; } __initcall(start_dirtytime_writeback); int dirtytime_interval_handler(const struct ctl_table *table, int write, void *buffer, size_t *lenp, loff_t *ppos) { int ret; ret = proc_dointvec_minmax(table, write, buffer, lenp, ppos); if (ret == 0 && write) mod_delayed_work(system_wq, &dirtytime_work, 0); return ret; } /** * __mark_inode_dirty - internal function to mark an inode dirty * * @inode: inode to mark * @flags: what kind of dirty, e.g. I_DIRTY_SYNC. This can be a combination of * multiple I_DIRTY_* flags, except that I_DIRTY_TIME can't be combined * with I_DIRTY_PAGES. * * Mark an inode as dirty. We notify the filesystem, then update the inode's * dirty flags. Then, if needed we add the inode to the appropriate dirty list. * * Most callers should use mark_inode_dirty() or mark_inode_dirty_sync() * instead of calling this directly. * * CAREFUL! We only add the inode to the dirty list if it is hashed or if it * refers to a blockdev. Unhashed inodes will never be added to the dirty list * even if they are later hashed, as they will have been marked dirty already. * * In short, ensure you hash any inodes _before_ you start marking them dirty. * * Note that for blockdevs, inode->dirtied_when represents the dirtying time of * the block-special inode (/dev/hda1) itself. And the ->dirtied_when field of * the kernel-internal blockdev inode represents the dirtying time of the * blockdev's pages. This is why for I_DIRTY_PAGES we always use * page->mapping->host, so the page-dirtying time is recorded in the internal * blockdev inode. */ void __mark_inode_dirty(struct inode *inode, int flags) { struct super_block *sb = inode->i_sb; int dirtytime = 0; struct bdi_writeback *wb = NULL; trace_writeback_mark_inode_dirty(inode, flags); if (flags & I_DIRTY_INODE) { /* * Inode timestamp update will piggback on this dirtying. * We tell ->dirty_inode callback that timestamps need to * be updated by setting I_DIRTY_TIME in flags. */ if (inode->i_state & I_DIRTY_TIME) { spin_lock(&inode->i_lock); if (inode->i_state & I_DIRTY_TIME) { inode->i_state &= ~I_DIRTY_TIME; flags |= I_DIRTY_TIME; } spin_unlock(&inode->i_lock); } /* * Notify the filesystem about the inode being dirtied, so that * (if needed) it can update on-disk fields and journal the * inode. This is only needed when the inode itself is being * dirtied now. I.e. it's only needed for I_DIRTY_INODE, not * for just I_DIRTY_PAGES or I_DIRTY_TIME. */ trace_writeback_dirty_inode_start(inode, flags); if (sb->s_op->dirty_inode) sb->s_op->dirty_inode(inode, flags & (I_DIRTY_INODE | I_DIRTY_TIME)); trace_writeback_dirty_inode(inode, flags); /* I_DIRTY_INODE supersedes I_DIRTY_TIME. */ flags &= ~I_DIRTY_TIME; } else { /* * Else it's either I_DIRTY_PAGES, I_DIRTY_TIME, or nothing. * (We don't support setting both I_DIRTY_PAGES and I_DIRTY_TIME * in one call to __mark_inode_dirty().) */ dirtytime = flags & I_DIRTY_TIME; WARN_ON_ONCE(dirtytime && flags != I_DIRTY_TIME); } /* * Paired with smp_mb() in __writeback_single_inode() for the * following lockless i_state test. See there for details. */ smp_mb(); if ((inode->i_state & flags) == flags) return; spin_lock(&inode->i_lock); if ((inode->i_state & flags) != flags) { const int was_dirty = inode->i_state & I_DIRTY; inode_attach_wb(inode, NULL); inode->i_state |= flags; /* * Grab inode's wb early because it requires dropping i_lock and we * need to make sure following checks happen atomically with dirty * list handling so that we don't move inodes under flush worker's * hands. */ if (!was_dirty) { wb = locked_inode_to_wb_and_lock_list(inode); spin_lock(&inode->i_lock); } /* * If the inode is queued for writeback by flush worker, just * update its dirty state. Once the flush worker is done with * the inode it will place it on the appropriate superblock * list, based upon its state. */ if (inode->i_state & I_SYNC_QUEUED) goto out_unlock; /* * Only add valid (hashed) inodes to the superblock's * dirty list. Add blockdev inodes as well. */ if (!S_ISBLK(inode->i_mode)) { if (inode_unhashed(inode)) goto out_unlock; } if (inode->i_state & I_FREEING) goto out_unlock; /* * If the inode was already on b_dirty/b_io/b_more_io, don't * reposition it (that would break b_dirty time-ordering). */ if (!was_dirty) { struct list_head *dirty_list; bool wakeup_bdi = false; inode->dirtied_when = jiffies; if (dirtytime) inode->dirtied_time_when = jiffies; if (inode->i_state & I_DIRTY) dirty_list = &wb->b_dirty; else dirty_list = &wb->b_dirty_time; wakeup_bdi = inode_io_list_move_locked(inode, wb, dirty_list); spin_unlock(&wb->list_lock); spin_unlock(&inode->i_lock); trace_writeback_dirty_inode_enqueue(inode); /* * If this is the first dirty inode for this bdi, * we have to wake-up the corresponding bdi thread * to make sure background write-back happens * later. */ if (wakeup_bdi && (wb->bdi->capabilities & BDI_CAP_WRITEBACK)) wb_wakeup_delayed(wb); return; } } out_unlock: if (wb) spin_unlock(&wb->list_lock); spin_unlock(&inode->i_lock); } EXPORT_SYMBOL(__mark_inode_dirty); /* * The @s_sync_lock is used to serialise concurrent sync operations * to avoid lock contention problems with concurrent wait_sb_inodes() calls. * Concurrent callers will block on the s_sync_lock rather than doing contending * walks. The queueing maintains sync(2) required behaviour as all the IO that * has been issued up to the time this function is enter is guaranteed to be * completed by the time we have gained the lock and waited for all IO that is * in progress regardless of the order callers are granted the lock. */ static void wait_sb_inodes(struct super_block *sb) { LIST_HEAD(sync_list); /* * We need to be protected against the filesystem going from * r/o to r/w or vice versa. */ WARN_ON(!rwsem_is_locked(&sb->s_umount)); mutex_lock(&sb->s_sync_lock); /* * Splice the writeback list onto a temporary list to avoid waiting on * inodes that have started writeback after this point. * * Use rcu_read_lock() to keep the inodes around until we have a * reference. s_inode_wblist_lock protects sb->s_inodes_wb as well as * the local list because inodes can be dropped from either by writeback * completion. */ rcu_read_lock(); spin_lock_irq(&sb->s_inode_wblist_lock); list_splice_init(&sb->s_inodes_wb, &sync_list); /* * Data integrity sync. Must wait for all pages under writeback, because * there may have been pages dirtied before our sync call, but which had * writeout started before we write it out. In which case, the inode * may not be on the dirty list, but we still have to wait for that * writeout. */ while (!list_empty(&sync_list)) { struct inode *inode = list_first_entry(&sync_list, struct inode, i_wb_list); struct address_space *mapping = inode->i_mapping; /* * Move each inode back to the wb list before we drop the lock * to preserve consistency between i_wb_list and the mapping * writeback tag. Writeback completion is responsible to remove * the inode from either list once the writeback tag is cleared. */ list_move_tail(&inode->i_wb_list, &sb->s_inodes_wb); /* * The mapping can appear untagged while still on-list since we * do not have the mapping lock. Skip it here, wb completion * will remove it. */ if (!mapping_tagged(mapping, PAGECACHE_TAG_WRITEBACK)) continue; spin_unlock_irq(&sb->s_inode_wblist_lock); spin_lock(&inode->i_lock); if (inode->i_state & (I_FREEING|I_WILL_FREE|I_NEW)) { spin_unlock(&inode->i_lock); spin_lock_irq(&sb->s_inode_wblist_lock); continue; } __iget(inode); spin_unlock(&inode->i_lock); rcu_read_unlock(); /* * We keep the error status of individual mapping so that * applications can catch the writeback error using fsync(2). * See filemap_fdatawait_keep_errors() for details. */ filemap_fdatawait_keep_errors(mapping); cond_resched(); iput(inode); rcu_read_lock(); spin_lock_irq(&sb->s_inode_wblist_lock); } spin_unlock_irq(&sb->s_inode_wblist_lock); rcu_read_unlock(); mutex_unlock(&sb->s_sync_lock); } static void __writeback_inodes_sb_nr(struct super_block *sb, unsigned long nr, enum wb_reason reason, bool skip_if_busy) { struct backing_dev_info *bdi = sb->s_bdi; DEFINE_WB_COMPLETION(done, bdi); struct wb_writeback_work work = { .sb = sb, .sync_mode = WB_SYNC_NONE, .tagged_writepages = 1, .done = &done, .nr_pages = nr, .reason = reason, }; if (!bdi_has_dirty_io(bdi) || bdi == &noop_backing_dev_info) return; WARN_ON(!rwsem_is_locked(&sb->s_umount)); bdi_split_work_to_wbs(sb->s_bdi, &work, skip_if_busy); wb_wait_for_completion(&done); } /** * writeback_inodes_sb_nr - writeback dirty inodes from given super_block * @sb: the superblock * @nr: the number of pages to write * @reason: reason why some writeback work initiated * * Start writeback on some inodes on this super_block. No guarantees are made * on how many (if any) will be written, and this function does not wait * for IO completion of submitted IO. */ void writeback_inodes_sb_nr(struct super_block *sb, unsigned long nr, enum wb_reason reason) { __writeback_inodes_sb_nr(sb, nr, reason, false); } EXPORT_SYMBOL(writeback_inodes_sb_nr); /** * writeback_inodes_sb - writeback dirty inodes from given super_block * @sb: the superblock * @reason: reason why some writeback work was initiated * * Start writeback on some inodes on this super_block. No guarantees are made * on how many (if any) will be written, and this function does not wait * for IO completion of submitted IO. */ void writeback_inodes_sb(struct super_block *sb, enum wb_reason reason) { writeback_inodes_sb_nr(sb, get_nr_dirty_pages(), reason); } EXPORT_SYMBOL(writeback_inodes_sb); /** * try_to_writeback_inodes_sb - try to start writeback if none underway * @sb: the superblock * @reason: reason why some writeback work was initiated * * Invoke __writeback_inodes_sb_nr if no writeback is currently underway. */ void try_to_writeback_inodes_sb(struct super_block *sb, enum wb_reason reason) { if (!down_read_trylock(&sb->s_umount)) return; __writeback_inodes_sb_nr(sb, get_nr_dirty_pages(), reason, true); up_read(&sb->s_umount); } EXPORT_SYMBOL(try_to_writeback_inodes_sb); /** * sync_inodes_sb - sync sb inode pages * @sb: the superblock * * This function writes and waits on any dirty inode belonging to this * super_block. */ void sync_inodes_sb(struct super_block *sb) { struct backing_dev_info *bdi = sb->s_bdi; DEFINE_WB_COMPLETION(done, bdi); struct wb_writeback_work work = { .sb = sb, .sync_mode = WB_SYNC_ALL, .nr_pages = LONG_MAX, .range_cyclic = 0, .done = &done, .reason = WB_REASON_SYNC, .for_sync = 1, }; /* * Can't skip on !bdi_has_dirty() because we should wait for !dirty * inodes under writeback and I_DIRTY_TIME inodes ignored by * bdi_has_dirty() need to be written out too. */ if (bdi == &noop_backing_dev_info) return; WARN_ON(!rwsem_is_locked(&sb->s_umount)); /* protect against inode wb switch, see inode_switch_wbs_work_fn() */ bdi_down_write_wb_switch_rwsem(bdi); bdi_split_work_to_wbs(bdi, &work, false); wb_wait_for_completion(&done); bdi_up_write_wb_switch_rwsem(bdi); wait_sb_inodes(sb); } EXPORT_SYMBOL(sync_inodes_sb); /** * write_inode_now - write an inode to disk * @inode: inode to write to disk * @sync: whether the write should be synchronous or not * * This function commits an inode to disk immediately if it is dirty. This is * primarily needed by knfsd. * * The caller must either have a ref on the inode or must have set I_WILL_FREE. */ int write_inode_now(struct inode *inode, int sync) { struct writeback_control wbc = { .nr_to_write = LONG_MAX, .sync_mode = sync ? WB_SYNC_ALL : WB_SYNC_NONE, .range_start = 0, .range_end = LLONG_MAX, }; if (!mapping_can_writeback(inode->i_mapping)) wbc.nr_to_write = 0; might_sleep(); return writeback_single_inode(inode, &wbc); } EXPORT_SYMBOL(write_inode_now); /** * sync_inode_metadata - write an inode to disk * @inode: the inode to sync * @wait: wait for I/O to complete. * * Write an inode to disk and adjust its dirty state after completion. * * Note: only writes the actual inode, no associated data or other metadata. */ int sync_inode_metadata(struct inode *inode, int wait) { struct writeback_control wbc = { .sync_mode = wait ? WB_SYNC_ALL : WB_SYNC_NONE, .nr_to_write = 0, /* metadata-only */ }; return writeback_single_inode(inode, &wbc); } EXPORT_SYMBOL(sync_inode_metadata); |
| 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 | // SPDX-License-Identifier: GPL-2.0 /* Copyright (C) 2017 Netronome Systems, Inc. * Copyright (C) 2019 Mellanox Technologies. All rights reserved */ #include <linux/completion.h> #include <linux/device.h> #include <linux/idr.h> #include <linux/kernel.h> #include <linux/list.h> #include <linux/mutex.h> #include <linux/refcount.h> #include <linux/slab.h> #include <linux/sysfs.h> #include "netdevsim.h" static DEFINE_IDA(nsim_bus_dev_ids); static LIST_HEAD(nsim_bus_dev_list); static DEFINE_MUTEX(nsim_bus_dev_list_lock); static bool nsim_bus_enable; static refcount_t nsim_bus_devs; /* Including the bus itself. */ static DECLARE_COMPLETION(nsim_bus_devs_released); static struct nsim_bus_dev *to_nsim_bus_dev(struct device *dev) { return container_of(dev, struct nsim_bus_dev, dev); } static ssize_t nsim_bus_dev_numvfs_store(struct device *dev, struct device_attribute *attr, const char *buf, size_t count) { struct nsim_bus_dev *nsim_bus_dev = to_nsim_bus_dev(dev); unsigned int num_vfs; int ret; ret = kstrtouint(buf, 0, &num_vfs); if (ret) return ret; device_lock(dev); ret = -ENOENT; if (dev_get_drvdata(dev)) ret = nsim_drv_configure_vfs(nsim_bus_dev, num_vfs); device_unlock(dev); return ret ? ret : count; } static ssize_t nsim_bus_dev_numvfs_show(struct device *dev, struct device_attribute *attr, char *buf) { struct nsim_bus_dev *nsim_bus_dev = to_nsim_bus_dev(dev); return sprintf(buf, "%u\n", nsim_bus_dev->num_vfs); } static struct device_attribute nsim_bus_dev_numvfs_attr = __ATTR(sriov_numvfs, 0664, nsim_bus_dev_numvfs_show, nsim_bus_dev_numvfs_store); static ssize_t new_port_store(struct device *dev, struct device_attribute *attr, const char *buf, size_t count) { struct nsim_bus_dev *nsim_bus_dev = to_nsim_bus_dev(dev); unsigned int port_index; int ret; /* Prevent to use nsim_bus_dev before initialization. */ if (!smp_load_acquire(&nsim_bus_dev->init)) return -EBUSY; ret = kstrtouint(buf, 0, &port_index); if (ret) return ret; ret = nsim_drv_port_add(nsim_bus_dev, NSIM_DEV_PORT_TYPE_PF, port_index); return ret ? ret : count; } static struct device_attribute nsim_bus_dev_new_port_attr = __ATTR_WO(new_port); static ssize_t del_port_store(struct device *dev, struct device_attribute *attr, const char *buf, size_t count) { struct nsim_bus_dev *nsim_bus_dev = to_nsim_bus_dev(dev); unsigned int port_index; int ret; /* Prevent to use nsim_bus_dev before initialization. */ if (!smp_load_acquire(&nsim_bus_dev->init)) return -EBUSY; ret = kstrtouint(buf, 0, &port_index); if (ret) return ret; ret = nsim_drv_port_del(nsim_bus_dev, NSIM_DEV_PORT_TYPE_PF, port_index); return ret ? ret : count; } static struct device_attribute nsim_bus_dev_del_port_attr = __ATTR_WO(del_port); static struct attribute *nsim_bus_dev_attrs[] = { &nsim_bus_dev_numvfs_attr.attr, &nsim_bus_dev_new_port_attr.attr, &nsim_bus_dev_del_port_attr.attr, NULL, }; static const struct attribute_group nsim_bus_dev_attr_group = { .attrs = nsim_bus_dev_attrs, }; static const struct attribute_group *nsim_bus_dev_attr_groups[] = { &nsim_bus_dev_attr_group, NULL, }; static void nsim_bus_dev_release(struct device *dev) { struct nsim_bus_dev *nsim_bus_dev; nsim_bus_dev = container_of(dev, struct nsim_bus_dev, dev); kfree(nsim_bus_dev); if (refcount_dec_and_test(&nsim_bus_devs)) complete(&nsim_bus_devs_released); } static const struct device_type nsim_bus_dev_type = { .groups = nsim_bus_dev_attr_groups, .release = nsim_bus_dev_release, }; static struct nsim_bus_dev * nsim_bus_dev_new(unsigned int id, unsigned int port_count, unsigned int num_queues); static ssize_t new_device_store(const struct bus_type *bus, const char *buf, size_t count) { unsigned int id, port_count, num_queues; struct nsim_bus_dev *nsim_bus_dev; int err; err = sscanf(buf, "%u %u %u", &id, &port_count, &num_queues); switch (err) { case 1: port_count = 1; fallthrough; case 2: num_queues = 1; fallthrough; case 3: if (id > INT_MAX) { pr_err("Value of \"id\" is too big.\n"); return -EINVAL; } break; default: pr_err("Format for adding new device is \"id port_count num_queues\" (uint uint unit).\n"); return -EINVAL; } mutex_lock(&nsim_bus_dev_list_lock); /* Prevent to use resource before initialization. */ if (!smp_load_acquire(&nsim_bus_enable)) { err = -EBUSY; goto err; } nsim_bus_dev = nsim_bus_dev_new(id, port_count, num_queues); if (IS_ERR(nsim_bus_dev)) { err = PTR_ERR(nsim_bus_dev); goto err; } refcount_inc(&nsim_bus_devs); /* Allow using nsim_bus_dev */ smp_store_release(&nsim_bus_dev->init, true); list_add_tail(&nsim_bus_dev->list, &nsim_bus_dev_list); mutex_unlock(&nsim_bus_dev_list_lock); return count; err: mutex_unlock(&nsim_bus_dev_list_lock); return err; } static BUS_ATTR_WO(new_device); static void nsim_bus_dev_del(struct nsim_bus_dev *nsim_bus_dev); static ssize_t del_device_store(const struct bus_type *bus, const char *buf, size_t count) { struct nsim_bus_dev *nsim_bus_dev, *tmp; unsigned int id; int err; err = sscanf(buf, "%u", &id); switch (err) { case 1: if (id > INT_MAX) { pr_err("Value of \"id\" is too big.\n"); return -EINVAL; } break; default: pr_err("Format for deleting device is \"id\" (uint).\n"); return -EINVAL; } err = -ENOENT; mutex_lock(&nsim_bus_dev_list_lock); /* Prevent to use resource before initialization. */ if (!smp_load_acquire(&nsim_bus_enable)) { mutex_unlock(&nsim_bus_dev_list_lock); return -EBUSY; } list_for_each_entry_safe(nsim_bus_dev, tmp, &nsim_bus_dev_list, list) { if (nsim_bus_dev->dev.id != id) continue; list_del(&nsim_bus_dev->list); nsim_bus_dev_del(nsim_bus_dev); err = 0; break; } mutex_unlock(&nsim_bus_dev_list_lock); return !err ? count : err; } static BUS_ATTR_WO(del_device); static ssize_t link_device_store(const struct bus_type *bus, const char *buf, size_t count) { struct netdevsim *nsim_a, *nsim_b, *peer; struct net_device *dev_a, *dev_b; unsigned int ifidx_a, ifidx_b; int netnsfd_a, netnsfd_b, err; struct net *ns_a, *ns_b; err = sscanf(buf, "%d:%u %d:%u", &netnsfd_a, &ifidx_a, &netnsfd_b, &ifidx_b); if (err != 4) { pr_err("Format for linking two devices is \"netnsfd_a:ifidx_a netnsfd_b:ifidx_b\" (int uint int uint).\n"); return -EINVAL; } ns_a = get_net_ns_by_fd(netnsfd_a); if (IS_ERR(ns_a)) { pr_err("Could not find netns with fd: %d\n", netnsfd_a); return -EINVAL; } ns_b = get_net_ns_by_fd(netnsfd_b); if (IS_ERR(ns_b)) { pr_err("Could not find netns with fd: %d\n", netnsfd_b); put_net(ns_a); return -EINVAL; } err = -EINVAL; rtnl_lock(); dev_a = __dev_get_by_index(ns_a, ifidx_a); if (!dev_a) { pr_err("Could not find device with ifindex %u in netnsfd %d\n", ifidx_a, netnsfd_a); goto out_err; } if (!netdev_is_nsim(dev_a)) { pr_err("Device with ifindex %u in netnsfd %d is not a netdevsim\n", ifidx_a, netnsfd_a); goto out_err; } dev_b = __dev_get_by_index(ns_b, ifidx_b); if (!dev_b) { pr_err("Could not find device with ifindex %u in netnsfd %d\n", ifidx_b, netnsfd_b); goto out_err; } if (!netdev_is_nsim(dev_b)) { pr_err("Device with ifindex %u in netnsfd %d is not a netdevsim\n", ifidx_b, netnsfd_b); goto out_err; } if (dev_a == dev_b) { pr_err("Cannot link a netdevsim to itself\n"); goto out_err; } err = -EBUSY; nsim_a = netdev_priv(dev_a); peer = rtnl_dereference(nsim_a->peer); if (peer) { pr_err("Netdevsim %d:%u is already linked\n", netnsfd_a, ifidx_a); goto out_err; } nsim_b = netdev_priv(dev_b); peer = rtnl_dereference(nsim_b->peer); if (peer) { pr_err("Netdevsim %d:%u is already linked\n", netnsfd_b, ifidx_b); goto out_err; } err = 0; rcu_assign_pointer(nsim_a->peer, nsim_b); rcu_assign_pointer(nsim_b->peer, nsim_a); out_err: put_net(ns_b); put_net(ns_a); rtnl_unlock(); return !err ? count : err; } static BUS_ATTR_WO(link_device); static ssize_t unlink_device_store(const struct bus_type *bus, const char *buf, size_t count) { struct netdevsim *nsim, *peer; struct net_device *dev; unsigned int ifidx; int netnsfd, err; struct net *ns; err = sscanf(buf, "%u:%u", &netnsfd, &ifidx); if (err != 2) { pr_err("Format for unlinking a device is \"netnsfd:ifidx\" (int uint).\n"); return -EINVAL; } ns = get_net_ns_by_fd(netnsfd); if (IS_ERR(ns)) { pr_err("Could not find netns with fd: %d\n", netnsfd); return -EINVAL; } err = -EINVAL; rtnl_lock(); dev = __dev_get_by_index(ns, ifidx); if (!dev) { pr_err("Could not find device with ifindex %u in netnsfd %d\n", ifidx, netnsfd); goto out_put_netns; } if (!netdev_is_nsim(dev)) { pr_err("Device with ifindex %u in netnsfd %d is not a netdevsim\n", ifidx, netnsfd); goto out_put_netns; } nsim = netdev_priv(dev); peer = rtnl_dereference(nsim->peer); if (!peer) goto out_put_netns; err = 0; RCU_INIT_POINTER(nsim->peer, NULL); RCU_INIT_POINTER(peer->peer, NULL); out_put_netns: put_net(ns); rtnl_unlock(); return !err ? count : err; } static BUS_ATTR_WO(unlink_device); static struct attribute *nsim_bus_attrs[] = { &bus_attr_new_device.attr, &bus_attr_del_device.attr, &bus_attr_link_device.attr, &bus_attr_unlink_device.attr, NULL }; ATTRIBUTE_GROUPS(nsim_bus); static int nsim_bus_probe(struct device *dev) { struct nsim_bus_dev *nsim_bus_dev = to_nsim_bus_dev(dev); return nsim_drv_probe(nsim_bus_dev); } static void nsim_bus_remove(struct device *dev) { struct nsim_bus_dev *nsim_bus_dev = to_nsim_bus_dev(dev); nsim_drv_remove(nsim_bus_dev); } static int nsim_num_vf(struct device *dev) { struct nsim_bus_dev *nsim_bus_dev = to_nsim_bus_dev(dev); return nsim_bus_dev->num_vfs; } static const struct bus_type nsim_bus = { .name = DRV_NAME, .dev_name = DRV_NAME, .bus_groups = nsim_bus_groups, .probe = nsim_bus_probe, .remove = nsim_bus_remove, .num_vf = nsim_num_vf, }; #define NSIM_BUS_DEV_MAX_VFS 4 static struct nsim_bus_dev * nsim_bus_dev_new(unsigned int id, unsigned int port_count, unsigned int num_queues) { struct nsim_bus_dev *nsim_bus_dev; int err; nsim_bus_dev = kzalloc(sizeof(*nsim_bus_dev), GFP_KERNEL); if (!nsim_bus_dev) return ERR_PTR(-ENOMEM); err = ida_alloc_range(&nsim_bus_dev_ids, id, id, GFP_KERNEL); if (err < 0) goto err_nsim_bus_dev_free; nsim_bus_dev->dev.id = err; nsim_bus_dev->dev.bus = &nsim_bus; nsim_bus_dev->dev.type = &nsim_bus_dev_type; nsim_bus_dev->port_count = port_count; nsim_bus_dev->num_queues = num_queues; nsim_bus_dev->initial_net = current->nsproxy->net_ns; nsim_bus_dev->max_vfs = NSIM_BUS_DEV_MAX_VFS; /* Disallow using nsim_bus_dev */ smp_store_release(&nsim_bus_dev->init, false); err = device_register(&nsim_bus_dev->dev); if (err) goto err_nsim_bus_dev_id_free; return nsim_bus_dev; err_nsim_bus_dev_id_free: ida_free(&nsim_bus_dev_ids, nsim_bus_dev->dev.id); put_device(&nsim_bus_dev->dev); nsim_bus_dev = NULL; err_nsim_bus_dev_free: kfree(nsim_bus_dev); return ERR_PTR(err); } static void nsim_bus_dev_del(struct nsim_bus_dev *nsim_bus_dev) { /* Disallow using nsim_bus_dev */ smp_store_release(&nsim_bus_dev->init, false); ida_free(&nsim_bus_dev_ids, nsim_bus_dev->dev.id); device_unregister(&nsim_bus_dev->dev); } static struct device_driver nsim_driver = { .name = DRV_NAME, .bus = &nsim_bus, .owner = THIS_MODULE, }; int nsim_bus_init(void) { int err; err = bus_register(&nsim_bus); if (err) return err; err = driver_register(&nsim_driver); if (err) goto err_bus_unregister; refcount_set(&nsim_bus_devs, 1); /* Allow using resources */ smp_store_release(&nsim_bus_enable, true); return 0; err_bus_unregister: bus_unregister(&nsim_bus); return err; } void nsim_bus_exit(void) { struct nsim_bus_dev *nsim_bus_dev, *tmp; /* Disallow using resources */ smp_store_release(&nsim_bus_enable, false); if (refcount_dec_and_test(&nsim_bus_devs)) complete(&nsim_bus_devs_released); mutex_lock(&nsim_bus_dev_list_lock); list_for_each_entry_safe(nsim_bus_dev, tmp, &nsim_bus_dev_list, list) { list_del(&nsim_bus_dev->list); nsim_bus_dev_del(nsim_bus_dev); } mutex_unlock(&nsim_bus_dev_list_lock); wait_for_completion(&nsim_bus_devs_released); driver_unregister(&nsim_driver); bus_unregister(&nsim_bus); } |
| 3 3 3 3 3 3 3 3 3 3 3 3 3 3 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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 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-or-later /* * Copyright (c) 2016 Mellanox Technologies. All rights reserved. * Copyright (c) 2016 Jiri Pirko <jiri@mellanox.com> */ #include <net/genetlink.h> #include <net/sock.h> #include <trace/events/devlink.h> #include "devl_internal.h" struct devlink_fmsg_item { struct list_head list; int attrtype; u8 nla_type; u16 len; int value[]; }; struct devlink_fmsg { struct list_head item_list; int err; /* first error encountered on some devlink_fmsg_XXX() call */ bool putting_binary; /* This flag forces enclosing of binary data * in an array brackets. It forces using * of designated API: * devlink_fmsg_binary_pair_nest_start() * devlink_fmsg_binary_pair_nest_end() */ }; static struct devlink_fmsg *devlink_fmsg_alloc(void) { struct devlink_fmsg *fmsg; fmsg = kzalloc(sizeof(*fmsg), GFP_KERNEL); if (!fmsg) return NULL; INIT_LIST_HEAD(&fmsg->item_list); return fmsg; } static void devlink_fmsg_free(struct devlink_fmsg *fmsg) { struct devlink_fmsg_item *item, *tmp; list_for_each_entry_safe(item, tmp, &fmsg->item_list, list) { list_del(&item->list); kfree(item); } kfree(fmsg); } struct devlink_health_reporter { struct list_head list; void *priv; const struct devlink_health_reporter_ops *ops; struct devlink *devlink; struct devlink_port *devlink_port; struct devlink_fmsg *dump_fmsg; u64 graceful_period; bool auto_recover; bool auto_dump; u8 health_state; u64 dump_ts; u64 dump_real_ts; u64 error_count; u64 recovery_count; u64 last_recovery_ts; }; void * devlink_health_reporter_priv(struct devlink_health_reporter *reporter) { return reporter->priv; } EXPORT_SYMBOL_GPL(devlink_health_reporter_priv); static struct devlink_health_reporter * __devlink_health_reporter_find_by_name(struct list_head *reporter_list, const char *reporter_name) { struct devlink_health_reporter *reporter; list_for_each_entry(reporter, reporter_list, list) if (!strcmp(reporter->ops->name, reporter_name)) return reporter; return NULL; } static struct devlink_health_reporter * devlink_health_reporter_find_by_name(struct devlink *devlink, const char *reporter_name) { return __devlink_health_reporter_find_by_name(&devlink->reporter_list, reporter_name); } static struct devlink_health_reporter * devlink_port_health_reporter_find_by_name(struct devlink_port *devlink_port, const char *reporter_name) { return __devlink_health_reporter_find_by_name(&devlink_port->reporter_list, reporter_name); } static struct devlink_health_reporter * __devlink_health_reporter_create(struct devlink *devlink, const struct devlink_health_reporter_ops *ops, u64 graceful_period, void *priv) { struct devlink_health_reporter *reporter; if (WARN_ON(graceful_period && !ops->recover)) return ERR_PTR(-EINVAL); reporter = kzalloc(sizeof(*reporter), GFP_KERNEL); if (!reporter) return ERR_PTR(-ENOMEM); reporter->priv = priv; reporter->ops = ops; reporter->devlink = devlink; reporter->graceful_period = graceful_period; reporter->auto_recover = !!ops->recover; reporter->auto_dump = !!ops->dump; return reporter; } /** * devl_port_health_reporter_create() - create devlink health reporter for * specified port instance * * @port: devlink_port to which health reports will relate * @ops: devlink health reporter ops * @graceful_period: min time (in msec) between recovery attempts * @priv: driver priv pointer */ struct devlink_health_reporter * devl_port_health_reporter_create(struct devlink_port *port, const struct devlink_health_reporter_ops *ops, u64 graceful_period, void *priv) { struct devlink_health_reporter *reporter; devl_assert_locked(port->devlink); if (__devlink_health_reporter_find_by_name(&port->reporter_list, ops->name)) return ERR_PTR(-EEXIST); reporter = __devlink_health_reporter_create(port->devlink, ops, graceful_period, priv); if (IS_ERR(reporter)) return reporter; reporter->devlink_port = port; list_add_tail(&reporter->list, &port->reporter_list); return reporter; } EXPORT_SYMBOL_GPL(devl_port_health_reporter_create); struct devlink_health_reporter * devlink_port_health_reporter_create(struct devlink_port *port, const struct devlink_health_reporter_ops *ops, u64 graceful_period, void *priv) { struct devlink_health_reporter *reporter; struct devlink *devlink = port->devlink; devl_lock(devlink); reporter = devl_port_health_reporter_create(port, ops, graceful_period, priv); devl_unlock(devlink); return reporter; } EXPORT_SYMBOL_GPL(devlink_port_health_reporter_create); /** * devl_health_reporter_create - create devlink health reporter * * @devlink: devlink instance which the health reports will relate * @ops: devlink health reporter ops * @graceful_period: min time (in msec) between recovery attempts * @priv: driver priv pointer */ struct devlink_health_reporter * devl_health_reporter_create(struct devlink *devlink, const struct devlink_health_reporter_ops *ops, u64 graceful_period, void *priv) { struct devlink_health_reporter *reporter; devl_assert_locked(devlink); if (devlink_health_reporter_find_by_name(devlink, ops->name)) return ERR_PTR(-EEXIST); reporter = __devlink_health_reporter_create(devlink, ops, graceful_period, priv); if (IS_ERR(reporter)) return reporter; list_add_tail(&reporter->list, &devlink->reporter_list); return reporter; } EXPORT_SYMBOL_GPL(devl_health_reporter_create); struct devlink_health_reporter * devlink_health_reporter_create(struct devlink *devlink, const struct devlink_health_reporter_ops *ops, u64 graceful_period, void *priv) { struct devlink_health_reporter *reporter; devl_lock(devlink); reporter = devl_health_reporter_create(devlink, ops, graceful_period, priv); devl_unlock(devlink); return reporter; } EXPORT_SYMBOL_GPL(devlink_health_reporter_create); static void devlink_health_reporter_free(struct devlink_health_reporter *reporter) { if (reporter->dump_fmsg) devlink_fmsg_free(reporter->dump_fmsg); kfree(reporter); } /** * devl_health_reporter_destroy() - destroy devlink health reporter * * @reporter: devlink health reporter to destroy */ void devl_health_reporter_destroy(struct devlink_health_reporter *reporter) { devl_assert_locked(reporter->devlink); list_del(&reporter->list); devlink_health_reporter_free(reporter); } EXPORT_SYMBOL_GPL(devl_health_reporter_destroy); void devlink_health_reporter_destroy(struct devlink_health_reporter *reporter) { struct devlink *devlink = reporter->devlink; devl_lock(devlink); devl_health_reporter_destroy(reporter); devl_unlock(devlink); } EXPORT_SYMBOL_GPL(devlink_health_reporter_destroy); static int devlink_nl_health_reporter_fill(struct sk_buff *msg, struct devlink_health_reporter *reporter, enum devlink_command cmd, u32 portid, u32 seq, int flags) { struct devlink *devlink = reporter->devlink; struct nlattr *reporter_attr; void *hdr; hdr = genlmsg_put(msg, portid, seq, &devlink_nl_family, flags, cmd); if (!hdr) return -EMSGSIZE; if (devlink_nl_put_handle(msg, devlink)) goto genlmsg_cancel; if (reporter->devlink_port) { if (nla_put_u32(msg, DEVLINK_ATTR_PORT_INDEX, reporter->devlink_port->index)) goto genlmsg_cancel; } reporter_attr = nla_nest_start_noflag(msg, DEVLINK_ATTR_HEALTH_REPORTER); if (!reporter_attr) goto genlmsg_cancel; if (nla_put_string(msg, DEVLINK_ATTR_HEALTH_REPORTER_NAME, reporter->ops->name)) goto reporter_nest_cancel; if (nla_put_u8(msg, DEVLINK_ATTR_HEALTH_REPORTER_STATE, reporter->health_state)) goto reporter_nest_cancel; if (devlink_nl_put_u64(msg, DEVLINK_ATTR_HEALTH_REPORTER_ERR_COUNT, reporter->error_count)) goto reporter_nest_cancel; if (devlink_nl_put_u64(msg, DEVLINK_ATTR_HEALTH_REPORTER_RECOVER_COUNT, reporter->recovery_count)) goto reporter_nest_cancel; if (reporter->ops->recover && devlink_nl_put_u64(msg, DEVLINK_ATTR_HEALTH_REPORTER_GRACEFUL_PERIOD, reporter->graceful_period)) goto reporter_nest_cancel; if (reporter->ops->recover && nla_put_u8(msg, DEVLINK_ATTR_HEALTH_REPORTER_AUTO_RECOVER, reporter->auto_recover)) goto reporter_nest_cancel; if (reporter->dump_fmsg && devlink_nl_put_u64(msg, DEVLINK_ATTR_HEALTH_REPORTER_DUMP_TS, jiffies_to_msecs(reporter->dump_ts))) goto reporter_nest_cancel; if (reporter->dump_fmsg && devlink_nl_put_u64(msg, DEVLINK_ATTR_HEALTH_REPORTER_DUMP_TS_NS, reporter->dump_real_ts)) goto reporter_nest_cancel; if (reporter->ops->dump && nla_put_u8(msg, DEVLINK_ATTR_HEALTH_REPORTER_AUTO_DUMP, reporter->auto_dump)) goto reporter_nest_cancel; nla_nest_end(msg, reporter_attr); genlmsg_end(msg, hdr); return 0; reporter_nest_cancel: nla_nest_cancel(msg, reporter_attr); genlmsg_cancel: genlmsg_cancel(msg, hdr); return -EMSGSIZE; } static struct devlink_health_reporter * devlink_health_reporter_get_from_attrs(struct devlink *devlink, struct nlattr **attrs) { struct devlink_port *devlink_port; char *reporter_name; if (!attrs[DEVLINK_ATTR_HEALTH_REPORTER_NAME]) return NULL; reporter_name = nla_data(attrs[DEVLINK_ATTR_HEALTH_REPORTER_NAME]); devlink_port = devlink_port_get_from_attrs(devlink, attrs); if (IS_ERR(devlink_port)) return devlink_health_reporter_find_by_name(devlink, reporter_name); else return devlink_port_health_reporter_find_by_name(devlink_port, reporter_name); } static struct devlink_health_reporter * devlink_health_reporter_get_from_info(struct devlink *devlink, struct genl_info *info) { return devlink_health_reporter_get_from_attrs(devlink, info->attrs); } int devlink_nl_health_reporter_get_doit(struct sk_buff *skb, struct genl_info *info) { struct devlink *devlink = info->user_ptr[0]; struct devlink_health_reporter *reporter; struct sk_buff *msg; int err; reporter = devlink_health_reporter_get_from_info(devlink, info); if (!reporter) return -EINVAL; msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL); if (!msg) return -ENOMEM; err = devlink_nl_health_reporter_fill(msg, reporter, DEVLINK_CMD_HEALTH_REPORTER_GET, info->snd_portid, info->snd_seq, 0); if (err) { nlmsg_free(msg); return err; } return genlmsg_reply(msg, info); } static int devlink_nl_health_reporter_get_dump_one(struct sk_buff *msg, struct devlink *devlink, struct netlink_callback *cb, int flags) { struct devlink_nl_dump_state *state = devlink_dump_state(cb); const struct genl_info *info = genl_info_dump(cb); struct devlink_health_reporter *reporter; unsigned long port_index_end = ULONG_MAX; struct nlattr **attrs = info->attrs; unsigned long port_index_start = 0; struct devlink_port *port; unsigned long port_index; int idx = 0; int err; if (attrs && attrs[DEVLINK_ATTR_PORT_INDEX]) { port_index_start = nla_get_u32(attrs[DEVLINK_ATTR_PORT_INDEX]); port_index_end = port_index_start; flags |= NLM_F_DUMP_FILTERED; goto per_port_dump; } list_for_each_entry(reporter, &devlink->reporter_list, list) { if (idx < state->idx) { idx++; continue; } err = devlink_nl_health_reporter_fill(msg, reporter, DEVLINK_CMD_HEALTH_REPORTER_GET, NETLINK_CB(cb->skb).portid, cb->nlh->nlmsg_seq, flags); if (err) { state->idx = idx; return err; } idx++; } per_port_dump: xa_for_each_range(&devlink->ports, port_index, port, port_index_start, port_index_end) { list_for_each_entry(reporter, &port->reporter_list, list) { if (idx < state->idx) { idx++; continue; } err = devlink_nl_health_reporter_fill(msg, reporter, DEVLINK_CMD_HEALTH_REPORTER_GET, NETLINK_CB(cb->skb).portid, cb->nlh->nlmsg_seq, flags); if (err) { state->idx = idx; return err; } idx++; } } return 0; } int devlink_nl_health_reporter_get_dumpit(struct sk_buff *skb, struct netlink_callback *cb) { return devlink_nl_dumpit(skb, cb, devlink_nl_health_reporter_get_dump_one); } int devlink_nl_health_reporter_set_doit(struct sk_buff *skb, struct genl_info *info) { struct devlink *devlink = info->user_ptr[0]; struct devlink_health_reporter *reporter; reporter = devlink_health_reporter_get_from_info(devlink, info); if (!reporter) return -EINVAL; if (!reporter->ops->recover && (info->attrs[DEVLINK_ATTR_HEALTH_REPORTER_GRACEFUL_PERIOD] || info->attrs[DEVLINK_ATTR_HEALTH_REPORTER_AUTO_RECOVER])) return -EOPNOTSUPP; if (!reporter->ops->dump && info->attrs[DEVLINK_ATTR_HEALTH_REPORTER_AUTO_DUMP]) return -EOPNOTSUPP; if (info->attrs[DEVLINK_ATTR_HEALTH_REPORTER_GRACEFUL_PERIOD]) reporter->graceful_period = nla_get_u64(info->attrs[DEVLINK_ATTR_HEALTH_REPORTER_GRACEFUL_PERIOD]); if (info->attrs[DEVLINK_ATTR_HEALTH_REPORTER_AUTO_RECOVER]) reporter->auto_recover = nla_get_u8(info->attrs[DEVLINK_ATTR_HEALTH_REPORTER_AUTO_RECOVER]); if (info->attrs[DEVLINK_ATTR_HEALTH_REPORTER_AUTO_DUMP]) reporter->auto_dump = nla_get_u8(info->attrs[DEVLINK_ATTR_HEALTH_REPORTER_AUTO_DUMP]); return 0; } static void devlink_recover_notify(struct devlink_health_reporter *reporter, enum devlink_command cmd) { struct devlink *devlink = reporter->devlink; struct devlink_obj_desc desc; struct sk_buff *msg; int err; WARN_ON(cmd != DEVLINK_CMD_HEALTH_REPORTER_RECOVER); ASSERT_DEVLINK_REGISTERED(devlink); if (!devlink_nl_notify_need(devlink)) return; msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL); if (!msg) return; err = devlink_nl_health_reporter_fill(msg, reporter, cmd, 0, 0, 0); if (err) { nlmsg_free(msg); return; } devlink_nl_obj_desc_init(&desc, devlink); if (reporter->devlink_port) devlink_nl_obj_desc_port_set(&desc, reporter->devlink_port); devlink_nl_notify_send_desc(devlink, msg, &desc); } void devlink_health_reporter_recovery_done(struct devlink_health_reporter *reporter) { reporter->recovery_count++; reporter->last_recovery_ts = jiffies; } EXPORT_SYMBOL_GPL(devlink_health_reporter_recovery_done); static int devlink_health_reporter_recover(struct devlink_health_reporter *reporter, void *priv_ctx, struct netlink_ext_ack *extack) { int err; if (reporter->health_state == DEVLINK_HEALTH_REPORTER_STATE_HEALTHY) return 0; if (!reporter->ops->recover) return -EOPNOTSUPP; err = reporter->ops->recover(reporter, priv_ctx, extack); if (err) return err; devlink_health_reporter_recovery_done(reporter); reporter->health_state = DEVLINK_HEALTH_REPORTER_STATE_HEALTHY; devlink_recover_notify(reporter, DEVLINK_CMD_HEALTH_REPORTER_RECOVER); return 0; } static void devlink_health_dump_clear(struct devlink_health_reporter *reporter) { if (!reporter->dump_fmsg) return; devlink_fmsg_free(reporter->dump_fmsg); reporter->dump_fmsg = NULL; } static int devlink_health_do_dump(struct devlink_health_reporter *reporter, void *priv_ctx, struct netlink_ext_ack *extack) { int err; if (!reporter->ops->dump) return 0; if (reporter->dump_fmsg) return 0; reporter->dump_fmsg = devlink_fmsg_alloc(); if (!reporter->dump_fmsg) return -ENOMEM; devlink_fmsg_obj_nest_start(reporter->dump_fmsg); err = reporter->ops->dump(reporter, reporter->dump_fmsg, priv_ctx, extack); if (err) goto dump_err; devlink_fmsg_obj_nest_end(reporter->dump_fmsg); err = reporter->dump_fmsg->err; if (err) goto dump_err; reporter->dump_ts = jiffies; reporter->dump_real_ts = ktime_get_real_ns(); return 0; dump_err: devlink_health_dump_clear(reporter); return err; } int devlink_health_report(struct devlink_health_reporter *reporter, const char *msg, void *priv_ctx) { enum devlink_health_reporter_state prev_health_state; struct devlink *devlink = reporter->devlink; unsigned long recover_ts_threshold; int ret; /* write a log message of the current error */ WARN_ON(!msg); trace_devlink_health_report(devlink, reporter->ops->name, msg); reporter->error_count++; prev_health_state = reporter->health_state; reporter->health_state = DEVLINK_HEALTH_REPORTER_STATE_ERROR; devlink_recover_notify(reporter, DEVLINK_CMD_HEALTH_REPORTER_RECOVER); /* abort if the previous error wasn't recovered */ recover_ts_threshold = reporter->last_recovery_ts + msecs_to_jiffies(reporter->graceful_period); if (reporter->auto_recover && (prev_health_state != DEVLINK_HEALTH_REPORTER_STATE_HEALTHY || (reporter->last_recovery_ts && reporter->recovery_count && time_is_after_jiffies(recover_ts_threshold)))) { trace_devlink_health_recover_aborted(devlink, reporter->ops->name, reporter->health_state, jiffies - reporter->last_recovery_ts); return -ECANCELED; } if (reporter->auto_dump) { devl_lock(devlink); /* store current dump of current error, for later analysis */ devlink_health_do_dump(reporter, priv_ctx, NULL); devl_unlock(devlink); } if (!reporter->auto_recover) return 0; devl_lock(devlink); ret = devlink_health_reporter_recover(reporter, priv_ctx, NULL); devl_unlock(devlink); return ret; } EXPORT_SYMBOL_GPL(devlink_health_report); void devlink_health_reporter_state_update(struct devlink_health_reporter *reporter, enum devlink_health_reporter_state state) { if (WARN_ON(state != DEVLINK_HEALTH_REPORTER_STATE_HEALTHY && state != DEVLINK_HEALTH_REPORTER_STATE_ERROR)) return; if (reporter->health_state == state) return; reporter->health_state = state; trace_devlink_health_reporter_state_update(reporter->devlink, reporter->ops->name, state); devlink_recover_notify(reporter, DEVLINK_CMD_HEALTH_REPORTER_RECOVER); } EXPORT_SYMBOL_GPL(devlink_health_reporter_state_update); int devlink_nl_health_reporter_recover_doit(struct sk_buff *skb, struct genl_info *info) { struct devlink *devlink = info->user_ptr[0]; struct devlink_health_reporter *reporter; reporter = devlink_health_reporter_get_from_info(devlink, info); if (!reporter) return -EINVAL; return devlink_health_reporter_recover(reporter, NULL, info->extack); } static void devlink_fmsg_err_if_binary(struct devlink_fmsg *fmsg) { if (!fmsg->err && fmsg->putting_binary) fmsg->err = -EINVAL; } static void devlink_fmsg_nest_common(struct devlink_fmsg *fmsg, int attrtype) { struct devlink_fmsg_item *item; if (fmsg->err) return; item = kzalloc(sizeof(*item), GFP_KERNEL); if (!item) { fmsg->err = -ENOMEM; return; } item->attrtype = attrtype; list_add_tail(&item->list, &fmsg->item_list); } void devlink_fmsg_obj_nest_start(struct devlink_fmsg *fmsg) { devlink_fmsg_err_if_binary(fmsg); devlink_fmsg_nest_common(fmsg, DEVLINK_ATTR_FMSG_OBJ_NEST_START); } EXPORT_SYMBOL_GPL(devlink_fmsg_obj_nest_start); static void devlink_fmsg_nest_end(struct devlink_fmsg *fmsg) { devlink_fmsg_err_if_binary(fmsg); devlink_fmsg_nest_common(fmsg, DEVLINK_ATTR_FMSG_NEST_END); } void devlink_fmsg_obj_nest_end(struct devlink_fmsg *fmsg) { devlink_fmsg_nest_end(fmsg); } EXPORT_SYMBOL_GPL(devlink_fmsg_obj_nest_end); #define DEVLINK_FMSG_MAX_SIZE (GENLMSG_DEFAULT_SIZE - GENL_HDRLEN - NLA_HDRLEN) static void devlink_fmsg_put_name(struct devlink_fmsg *fmsg, const char *name) { struct devlink_fmsg_item *item; devlink_fmsg_err_if_binary(fmsg); if (fmsg->err) return; if (strlen(name) + 1 > DEVLINK_FMSG_MAX_SIZE) { fmsg->err = -EMSGSIZE; return; } item = kzalloc(sizeof(*item) + strlen(name) + 1, GFP_KERNEL); if (!item) { fmsg->err = -ENOMEM; return; } item->nla_type = NLA_NUL_STRING; item->len = strlen(name) + 1; item->attrtype = DEVLINK_ATTR_FMSG_OBJ_NAME; memcpy(&item->value, name, item->len); list_add_tail(&item->list, &fmsg->item_list); } void devlink_fmsg_pair_nest_start(struct devlink_fmsg *fmsg, const char *name) { devlink_fmsg_err_if_binary(fmsg); devlink_fmsg_nest_common(fmsg, DEVLINK_ATTR_FMSG_PAIR_NEST_START); devlink_fmsg_put_name(fmsg, name); } EXPORT_SYMBOL_GPL(devlink_fmsg_pair_nest_start); void devlink_fmsg_pair_nest_end(struct devlink_fmsg *fmsg) { devlink_fmsg_nest_end(fmsg); } EXPORT_SYMBOL_GPL(devlink_fmsg_pair_nest_end); void devlink_fmsg_arr_pair_nest_start(struct devlink_fmsg *fmsg, const char *name) { devlink_fmsg_pair_nest_start(fmsg, name); devlink_fmsg_nest_common(fmsg, DEVLINK_ATTR_FMSG_ARR_NEST_START); } EXPORT_SYMBOL_GPL(devlink_fmsg_arr_pair_nest_start); void devlink_fmsg_arr_pair_nest_end(struct devlink_fmsg *fmsg) { devlink_fmsg_nest_end(fmsg); devlink_fmsg_nest_end(fmsg); } EXPORT_SYMBOL_GPL(devlink_fmsg_arr_pair_nest_end); void devlink_fmsg_binary_pair_nest_start(struct devlink_fmsg *fmsg, const char *name) { devlink_fmsg_arr_pair_nest_start(fmsg, name); fmsg->putting_binary = true; } EXPORT_SYMBOL_GPL(devlink_fmsg_binary_pair_nest_start); void devlink_fmsg_binary_pair_nest_end(struct devlink_fmsg *fmsg) { if (fmsg->err) return; if (!fmsg->putting_binary) fmsg->err = -EINVAL; fmsg->putting_binary = false; devlink_fmsg_arr_pair_nest_end(fmsg); } EXPORT_SYMBOL_GPL(devlink_fmsg_binary_pair_nest_end); static void devlink_fmsg_put_value(struct devlink_fmsg *fmsg, const void *value, u16 value_len, u8 value_nla_type) { struct devlink_fmsg_item *item; if (fmsg->err) return; if (value_len > DEVLINK_FMSG_MAX_SIZE) { fmsg->err = -EMSGSIZE; return; } item = kzalloc(sizeof(*item) + value_len, GFP_KERNEL); if (!item) { fmsg->err = -ENOMEM; return; } item->nla_type = value_nla_type; item->len = value_len; item->attrtype = DEVLINK_ATTR_FMSG_OBJ_VALUE_DATA; memcpy(&item->value, value, item->len); list_add_tail(&item->list, &fmsg->item_list); } static void devlink_fmsg_bool_put(struct devlink_fmsg *fmsg, bool value) { devlink_fmsg_err_if_binary(fmsg); devlink_fmsg_put_value(fmsg, &value, sizeof(value), NLA_FLAG); } static void devlink_fmsg_u8_put(struct devlink_fmsg *fmsg, u8 value) { devlink_fmsg_err_if_binary(fmsg); devlink_fmsg_put_value(fmsg, &value, sizeof(value), NLA_U8); } void devlink_fmsg_u32_put(struct devlink_fmsg *fmsg, u32 value) { devlink_fmsg_err_if_binary(fmsg); devlink_fmsg_put_value(fmsg, &value, sizeof(value), NLA_U32); } EXPORT_SYMBOL_GPL(devlink_fmsg_u32_put); static void devlink_fmsg_u64_put(struct devlink_fmsg *fmsg, u64 value) { devlink_fmsg_err_if_binary(fmsg); devlink_fmsg_put_value(fmsg, &value, sizeof(value), NLA_U64); } void devlink_fmsg_string_put(struct devlink_fmsg *fmsg, const char *value) { devlink_fmsg_err_if_binary(fmsg); devlink_fmsg_put_value(fmsg, value, strlen(value) + 1, NLA_NUL_STRING); } EXPORT_SYMBOL_GPL(devlink_fmsg_string_put); void devlink_fmsg_binary_put(struct devlink_fmsg *fmsg, const void *value, u16 value_len) { if (!fmsg->err && !fmsg->putting_binary) fmsg->err = -EINVAL; devlink_fmsg_put_value(fmsg, value, value_len, NLA_BINARY); } EXPORT_SYMBOL_GPL(devlink_fmsg_binary_put); void devlink_fmsg_bool_pair_put(struct devlink_fmsg *fmsg, const char *name, bool value) { devlink_fmsg_pair_nest_start(fmsg, name); devlink_fmsg_bool_put(fmsg, value); devlink_fmsg_pair_nest_end(fmsg); } EXPORT_SYMBOL_GPL(devlink_fmsg_bool_pair_put); void devlink_fmsg_u8_pair_put(struct devlink_fmsg *fmsg, const char *name, u8 value) { devlink_fmsg_pair_nest_start(fmsg, name); devlink_fmsg_u8_put(fmsg, value); devlink_fmsg_pair_nest_end(fmsg); } EXPORT_SYMBOL_GPL(devlink_fmsg_u8_pair_put); void devlink_fmsg_u32_pair_put(struct devlink_fmsg *fmsg, const char *name, u32 value) { devlink_fmsg_pair_nest_start(fmsg, name); devlink_fmsg_u32_put(fmsg, value); devlink_fmsg_pair_nest_end(fmsg); } EXPORT_SYMBOL_GPL(devlink_fmsg_u32_pair_put); void devlink_fmsg_u64_pair_put(struct devlink_fmsg *fmsg, const char *name, u64 value) { devlink_fmsg_pair_nest_start(fmsg, name); devlink_fmsg_u64_put(fmsg, value); devlink_fmsg_pair_nest_end(fmsg); } EXPORT_SYMBOL_GPL(devlink_fmsg_u64_pair_put); void devlink_fmsg_string_pair_put(struct devlink_fmsg *fmsg, const char *name, const char *value) { devlink_fmsg_pair_nest_start(fmsg, name); devlink_fmsg_string_put(fmsg, value); devlink_fmsg_pair_nest_end(fmsg); } EXPORT_SYMBOL_GPL(devlink_fmsg_string_pair_put); void devlink_fmsg_binary_pair_put(struct devlink_fmsg *fmsg, const char *name, const void *value, u32 value_len) { u32 data_size; u32 offset; devlink_fmsg_binary_pair_nest_start(fmsg, name); for (offset = 0; offset < value_len; offset += data_size) { data_size = value_len - offset; if (data_size > DEVLINK_FMSG_MAX_SIZE) data_size = DEVLINK_FMSG_MAX_SIZE; devlink_fmsg_binary_put(fmsg, value + offset, data_size); } devlink_fmsg_binary_pair_nest_end(fmsg); fmsg->putting_binary = false; } EXPORT_SYMBOL_GPL(devlink_fmsg_binary_pair_put); static int devlink_fmsg_item_fill_type(struct devlink_fmsg_item *msg, struct sk_buff *skb) { switch (msg->nla_type) { case NLA_FLAG: case NLA_U8: case NLA_U32: case NLA_U64: case NLA_NUL_STRING: case NLA_BINARY: return nla_put_u8(skb, DEVLINK_ATTR_FMSG_OBJ_VALUE_TYPE, msg->nla_type); default: return -EINVAL; } } static int devlink_fmsg_item_fill_data(struct devlink_fmsg_item *msg, struct sk_buff *skb) { int attrtype = DEVLINK_ATTR_FMSG_OBJ_VALUE_DATA; u8 tmp; switch (msg->nla_type) { case NLA_FLAG: /* Always provide flag data, regardless of its value */ tmp = *(bool *)msg->value; return nla_put_u8(skb, attrtype, tmp); case NLA_U8: return nla_put_u8(skb, attrtype, *(u8 *)msg->value); case NLA_U32: return nla_put_u32(skb, attrtype, *(u32 *)msg->value); case NLA_U64: return devlink_nl_put_u64(skb, attrtype, *(u64 *)msg->value); case NLA_NUL_STRING: return nla_put_string(skb, attrtype, (char *)&msg->value); case NLA_BINARY: return nla_put(skb, attrtype, msg->len, (void *)&msg->value); default: return -EINVAL; } } static int devlink_fmsg_prepare_skb(struct devlink_fmsg *fmsg, struct sk_buff *skb, int *start) { struct devlink_fmsg_item *item; struct nlattr *fmsg_nlattr; int err = 0; int i = 0; fmsg_nlattr = nla_nest_start_noflag(skb, DEVLINK_ATTR_FMSG); if (!fmsg_nlattr) return -EMSGSIZE; list_for_each_entry(item, &fmsg->item_list, list) { if (i < *start) { i++; continue; } switch (item->attrtype) { case DEVLINK_ATTR_FMSG_OBJ_NEST_START: case DEVLINK_ATTR_FMSG_PAIR_NEST_START: case DEVLINK_ATTR_FMSG_ARR_NEST_START: case DEVLINK_ATTR_FMSG_NEST_END: err = nla_put_flag(skb, item->attrtype); break; case DEVLINK_ATTR_FMSG_OBJ_VALUE_DATA: err = devlink_fmsg_item_fill_type(item, skb); if (err) break; err = devlink_fmsg_item_fill_data(item, skb); break; case DEVLINK_ATTR_FMSG_OBJ_NAME: err = nla_put_string(skb, item->attrtype, (char *)&item->value); break; default: err = -EINVAL; break; } if (!err) *start = ++i; else break; } nla_nest_end(skb, fmsg_nlattr); return err; } static int devlink_fmsg_snd(struct devlink_fmsg *fmsg, struct genl_info *info, enum devlink_command cmd, int flags) { struct nlmsghdr *nlh; struct sk_buff *skb; bool last = false; int index = 0; void *hdr; int err; if (fmsg->err) return fmsg->err; while (!last) { int tmp_index = index; skb = genlmsg_new(GENLMSG_DEFAULT_SIZE, GFP_KERNEL); if (!skb) return -ENOMEM; hdr = genlmsg_put(skb, info->snd_portid, info->snd_seq, &devlink_nl_family, flags | NLM_F_MULTI, cmd); if (!hdr) { err = -EMSGSIZE; goto nla_put_failure; } err = devlink_fmsg_prepare_skb(fmsg, skb, &index); if (!err) last = true; else if (err != -EMSGSIZE || tmp_index == index) goto nla_put_failure; genlmsg_end(skb, hdr); err = genlmsg_reply(skb, info); if (err) return err; } skb = genlmsg_new(GENLMSG_DEFAULT_SIZE, GFP_KERNEL); if (!skb) return -ENOMEM; nlh = nlmsg_put(skb, info->snd_portid, info->snd_seq, NLMSG_DONE, 0, flags | NLM_F_MULTI); if (!nlh) { err = -EMSGSIZE; goto nla_put_failure; } return genlmsg_reply(skb, info); nla_put_failure: nlmsg_free(skb); return err; } static int devlink_fmsg_dumpit(struct devlink_fmsg *fmsg, struct sk_buff *skb, struct netlink_callback *cb, enum devlink_command cmd) { struct devlink_nl_dump_state *state = devlink_dump_state(cb); int index = state->idx; int tmp_index = index; void *hdr; int err; if (fmsg->err) return fmsg->err; hdr = genlmsg_put(skb, NETLINK_CB(cb->skb).portid, cb->nlh->nlmsg_seq, &devlink_nl_family, NLM_F_ACK | NLM_F_MULTI, cmd); if (!hdr) { err = -EMSGSIZE; goto nla_put_failure; } err = devlink_fmsg_prepare_skb(fmsg, skb, &index); if ((err && err != -EMSGSIZE) || tmp_index == index) goto nla_put_failure; state->idx = index; genlmsg_end(skb, hdr); return skb->len; nla_put_failure: genlmsg_cancel(skb, hdr); return err; } int devlink_nl_health_reporter_diagnose_doit(struct sk_buff *skb, struct genl_info *info) { struct devlink *devlink = info->user_ptr[0]; struct devlink_health_reporter *reporter; struct devlink_fmsg *fmsg; int err; reporter = devlink_health_reporter_get_from_info(devlink, info); if (!reporter) return -EINVAL; if (!reporter->ops->diagnose) return -EOPNOTSUPP; fmsg = devlink_fmsg_alloc(); if (!fmsg) return -ENOMEM; devlink_fmsg_obj_nest_start(fmsg); err = reporter->ops->diagnose(reporter, fmsg, info->extack); if (err) goto out; devlink_fmsg_obj_nest_end(fmsg); err = devlink_fmsg_snd(fmsg, info, DEVLINK_CMD_HEALTH_REPORTER_DIAGNOSE, 0); out: devlink_fmsg_free(fmsg); return err; } static struct devlink_health_reporter * devlink_health_reporter_get_from_cb_lock(struct netlink_callback *cb) { const struct genl_info *info = genl_info_dump(cb); struct devlink_health_reporter *reporter; struct nlattr **attrs = info->attrs; struct devlink *devlink; devlink = devlink_get_from_attrs_lock(sock_net(cb->skb->sk), attrs, false); if (IS_ERR(devlink)) return NULL; reporter = devlink_health_reporter_get_from_attrs(devlink, attrs); if (!reporter) { devl_unlock(devlink); devlink_put(devlink); } return reporter; } int devlink_nl_health_reporter_dump_get_dumpit(struct sk_buff *skb, struct netlink_callback *cb) { struct devlink_nl_dump_state *state = devlink_dump_state(cb); struct devlink_health_reporter *reporter; struct devlink *devlink; int err; reporter = devlink_health_reporter_get_from_cb_lock(cb); if (!reporter) return -EINVAL; devlink = reporter->devlink; if (!reporter->ops->dump) { devl_unlock(devlink); devlink_put(devlink); return -EOPNOTSUPP; } if (!state->idx) { err = devlink_health_do_dump(reporter, NULL, cb->extack); if (err) goto unlock; state->dump_ts = reporter->dump_ts; } if (!reporter->dump_fmsg || state->dump_ts != reporter->dump_ts) { NL_SET_ERR_MSG(cb->extack, "Dump trampled, please retry"); err = -EAGAIN; goto unlock; } err = devlink_fmsg_dumpit(reporter->dump_fmsg, skb, cb, DEVLINK_CMD_HEALTH_REPORTER_DUMP_GET); unlock: devl_unlock(devlink); devlink_put(devlink); return err; } int devlink_nl_health_reporter_dump_clear_doit(struct sk_buff *skb, struct genl_info *info) { struct devlink *devlink = info->user_ptr[0]; struct devlink_health_reporter *reporter; reporter = devlink_health_reporter_get_from_info(devlink, info); if (!reporter) return -EINVAL; if (!reporter->ops->dump) return -EOPNOTSUPP; devlink_health_dump_clear(reporter); return 0; } int devlink_nl_health_reporter_test_doit(struct sk_buff *skb, struct genl_info *info) { struct devlink *devlink = info->user_ptr[0]; struct devlink_health_reporter *reporter; reporter = devlink_health_reporter_get_from_info(devlink, info); if (!reporter) return -EINVAL; if (!reporter->ops->test) return -EOPNOTSUPP; return reporter->ops->test(reporter, info->extack); } /** * devlink_fmsg_dump_skb - Dump sk_buffer structure * @fmsg: devlink formatted message pointer * @skb: pointer to skb * * Dump diagnostic information about sk_buff structure, like headroom, length, * tailroom, MAC, etc. */ void devlink_fmsg_dump_skb(struct devlink_fmsg *fmsg, const struct sk_buff *skb) { struct skb_shared_info *sh = skb_shinfo(skb); struct sock *sk = skb->sk; bool has_mac, has_trans; has_mac = skb_mac_header_was_set(skb); has_trans = skb_transport_header_was_set(skb); devlink_fmsg_pair_nest_start(fmsg, "skb"); devlink_fmsg_obj_nest_start(fmsg); devlink_fmsg_put(fmsg, "actual len", skb->len); devlink_fmsg_put(fmsg, "head len", skb_headlen(skb)); devlink_fmsg_put(fmsg, "data len", skb->data_len); devlink_fmsg_put(fmsg, "tail len", skb_tailroom(skb)); devlink_fmsg_put(fmsg, "MAC", has_mac ? skb->mac_header : -1); devlink_fmsg_put(fmsg, "MAC len", has_mac ? skb_mac_header_len(skb) : -1); devlink_fmsg_put(fmsg, "network hdr", skb->network_header); devlink_fmsg_put(fmsg, "network hdr len", has_trans ? skb_network_header_len(skb) : -1); devlink_fmsg_put(fmsg, "transport hdr", has_trans ? skb->transport_header : -1); devlink_fmsg_put(fmsg, "csum", (__force u32)skb->csum); devlink_fmsg_put(fmsg, "csum_ip_summed", (u8)skb->ip_summed); devlink_fmsg_put(fmsg, "csum_complete_sw", !!skb->csum_complete_sw); devlink_fmsg_put(fmsg, "csum_valid", !!skb->csum_valid); devlink_fmsg_put(fmsg, "csum_level", (u8)skb->csum_level); devlink_fmsg_put(fmsg, "sw_hash", !!skb->sw_hash); devlink_fmsg_put(fmsg, "l4_hash", !!skb->l4_hash); devlink_fmsg_put(fmsg, "proto", ntohs(skb->protocol)); devlink_fmsg_put(fmsg, "pkt_type", (u8)skb->pkt_type); devlink_fmsg_put(fmsg, "iif", skb->skb_iif); if (sk) { devlink_fmsg_pair_nest_start(fmsg, "sk"); devlink_fmsg_obj_nest_start(fmsg); devlink_fmsg_put(fmsg, "family", sk->sk_type); devlink_fmsg_put(fmsg, "type", sk->sk_type); devlink_fmsg_put(fmsg, "proto", sk->sk_protocol); devlink_fmsg_obj_nest_end(fmsg); devlink_fmsg_pair_nest_end(fmsg); } devlink_fmsg_obj_nest_end(fmsg); devlink_fmsg_pair_nest_end(fmsg); devlink_fmsg_pair_nest_start(fmsg, "shinfo"); devlink_fmsg_obj_nest_start(fmsg); devlink_fmsg_put(fmsg, "tx_flags", sh->tx_flags); devlink_fmsg_put(fmsg, "nr_frags", sh->nr_frags); devlink_fmsg_put(fmsg, "gso_size", sh->gso_size); devlink_fmsg_put(fmsg, "gso_type", sh->gso_type); devlink_fmsg_put(fmsg, "gso_segs", sh->gso_segs); devlink_fmsg_obj_nest_end(fmsg); devlink_fmsg_pair_nest_end(fmsg); } EXPORT_SYMBOL_GPL(devlink_fmsg_dump_skb); |
| 58 58 58 | 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 | // SPDX-License-Identifier: GPL-2.0-or-later /* * (C) 2011 Pablo Neira Ayuso <pablo@netfilter.org> * (C) 2011 Intra2net AG <https://www.intra2net.com> */ #include <linux/init.h> #include <linux/module.h> #include <linux/kernel.h> #include <linux/skbuff.h> #include <linux/atomic.h> #include <linux/refcount.h> #include <linux/netlink.h> #include <linux/rculist.h> #include <linux/slab.h> #include <linux/types.h> #include <linux/errno.h> #include <net/netlink.h> #include <net/sock.h> #include <net/netns/generic.h> #include <linux/netfilter.h> #include <linux/netfilter/nfnetlink.h> #include <linux/netfilter/nfnetlink_acct.h> MODULE_LICENSE("GPL"); MODULE_AUTHOR("Pablo Neira Ayuso <pablo@netfilter.org>"); MODULE_DESCRIPTION("nfacct: Extended Netfilter accounting infrastructure"); struct nf_acct { atomic64_t pkts; atomic64_t bytes; unsigned long flags; struct list_head head; refcount_t refcnt; char name[NFACCT_NAME_MAX]; struct rcu_head rcu_head; char data[]; }; struct nfacct_filter { u32 value; u32 mask; }; struct nfnl_acct_net { struct list_head nfnl_acct_list; }; static unsigned int nfnl_acct_net_id __read_mostly; static inline struct nfnl_acct_net *nfnl_acct_pernet(struct net *net) { return net_generic(net, nfnl_acct_net_id); } #define NFACCT_F_QUOTA (NFACCT_F_QUOTA_PKTS | NFACCT_F_QUOTA_BYTES) #define NFACCT_OVERQUOTA_BIT 2 /* NFACCT_F_OVERQUOTA */ static int nfnl_acct_new(struct sk_buff *skb, const struct nfnl_info *info, const struct nlattr * const tb[]) { struct nfnl_acct_net *nfnl_acct_net = nfnl_acct_pernet(info->net); struct nf_acct *nfacct, *matching = NULL; unsigned int size = 0; char *acct_name; u32 flags = 0; if (!tb[NFACCT_NAME]) return -EINVAL; acct_name = nla_data(tb[NFACCT_NAME]); if (strlen(acct_name) == 0) return -EINVAL; list_for_each_entry(nfacct, &nfnl_acct_net->nfnl_acct_list, head) { if (strncmp(nfacct->name, acct_name, NFACCT_NAME_MAX) != 0) continue; if (info->nlh->nlmsg_flags & NLM_F_EXCL) return -EEXIST; matching = nfacct; break; } if (matching) { if (info->nlh->nlmsg_flags & NLM_F_REPLACE) { /* reset counters if you request a replacement. */ atomic64_set(&matching->pkts, 0); atomic64_set(&matching->bytes, 0); smp_mb__before_atomic(); /* reset overquota flag if quota is enabled. */ if ((matching->flags & NFACCT_F_QUOTA)) clear_bit(NFACCT_OVERQUOTA_BIT, &matching->flags); return 0; } return -EBUSY; } if (tb[NFACCT_FLAGS]) { flags = ntohl(nla_get_be32(tb[NFACCT_FLAGS])); if (flags & ~NFACCT_F_QUOTA) return -EOPNOTSUPP; if ((flags & NFACCT_F_QUOTA) == NFACCT_F_QUOTA) return -EINVAL; if (flags & NFACCT_F_OVERQUOTA) return -EINVAL; if ((flags & NFACCT_F_QUOTA) && !tb[NFACCT_QUOTA]) return -EINVAL; size += sizeof(u64); } nfacct = kzalloc(sizeof(struct nf_acct) + size, GFP_KERNEL); if (nfacct == NULL) return -ENOMEM; if (flags & NFACCT_F_QUOTA) { u64 *quota = (u64 *)nfacct->data; *quota = be64_to_cpu(nla_get_be64(tb[NFACCT_QUOTA])); nfacct->flags = flags; } nla_strscpy(nfacct->name, tb[NFACCT_NAME], NFACCT_NAME_MAX); if (tb[NFACCT_BYTES]) { atomic64_set(&nfacct->bytes, be64_to_cpu(nla_get_be64(tb[NFACCT_BYTES]))); } if (tb[NFACCT_PKTS]) { atomic64_set(&nfacct->pkts, be64_to_cpu(nla_get_be64(tb[NFACCT_PKTS]))); } refcount_set(&nfacct->refcnt, 1); list_add_tail_rcu(&nfacct->head, &nfnl_acct_net->nfnl_acct_list); return 0; } static int nfnl_acct_fill_info(struct sk_buff *skb, u32 portid, u32 seq, u32 type, int event, struct nf_acct *acct) { struct nlmsghdr *nlh; unsigned int flags = portid ? NLM_F_MULTI : 0; u64 pkts, bytes; u32 old_flags; event = nfnl_msg_type(NFNL_SUBSYS_ACCT, event); nlh = nfnl_msg_put(skb, portid, seq, event, flags, AF_UNSPEC, NFNETLINK_V0, 0); if (!nlh) goto nlmsg_failure; if (nla_put_string(skb, NFACCT_NAME, acct->name)) goto nla_put_failure; old_flags = acct->flags; if (type == NFNL_MSG_ACCT_GET_CTRZERO) { pkts = atomic64_xchg(&acct->pkts, 0); bytes = atomic64_xchg(&acct->bytes, 0); smp_mb__before_atomic(); if (acct->flags & NFACCT_F_QUOTA) clear_bit(NFACCT_OVERQUOTA_BIT, &acct->flags); } else { pkts = atomic64_read(&acct->pkts); bytes = atomic64_read(&acct->bytes); } if (nla_put_be64(skb, NFACCT_PKTS, cpu_to_be64(pkts), NFACCT_PAD) || nla_put_be64(skb, NFACCT_BYTES, cpu_to_be64(bytes), NFACCT_PAD) || nla_put_be32(skb, NFACCT_USE, htonl(refcount_read(&acct->refcnt)))) goto nla_put_failure; if (acct->flags & NFACCT_F_QUOTA) { u64 *quota = (u64 *)acct->data; if (nla_put_be32(skb, NFACCT_FLAGS, htonl(old_flags)) || nla_put_be64(skb, NFACCT_QUOTA, cpu_to_be64(*quota), NFACCT_PAD)) goto nla_put_failure; } nlmsg_end(skb, nlh); return skb->len; nlmsg_failure: nla_put_failure: nlmsg_cancel(skb, nlh); return -1; } static int nfnl_acct_dump(struct sk_buff *skb, struct netlink_callback *cb) { struct net *net = sock_net(skb->sk); struct nfnl_acct_net *nfnl_acct_net = nfnl_acct_pernet(net); struct nf_acct *cur, *last; const struct nfacct_filter *filter = cb->data; if (cb->args[2]) return 0; last = (struct nf_acct *)cb->args[1]; if (cb->args[1]) cb->args[1] = 0; rcu_read_lock(); list_for_each_entry_rcu(cur, &nfnl_acct_net->nfnl_acct_list, head) { if (last) { if (cur != last) continue; last = NULL; } if (filter && (cur->flags & filter->mask) != filter->value) continue; if (nfnl_acct_fill_info(skb, NETLINK_CB(cb->skb).portid, cb->nlh->nlmsg_seq, NFNL_MSG_TYPE(cb->nlh->nlmsg_type), NFNL_MSG_ACCT_NEW, cur) < 0) { cb->args[1] = (unsigned long)cur; break; } } if (!cb->args[1]) cb->args[2] = 1; rcu_read_unlock(); return skb->len; } static int nfnl_acct_done(struct netlink_callback *cb) { kfree(cb->data); return 0; } static const struct nla_policy filter_policy[NFACCT_FILTER_MAX + 1] = { [NFACCT_FILTER_MASK] = { .type = NLA_U32 }, [NFACCT_FILTER_VALUE] = { .type = NLA_U32 }, }; static int nfnl_acct_start(struct netlink_callback *cb) { const struct nlattr *const attr = cb->data; struct nlattr *tb[NFACCT_FILTER_MAX + 1]; struct nfacct_filter *filter; int err; if (!attr) return 0; err = nla_parse_nested_deprecated(tb, NFACCT_FILTER_MAX, attr, filter_policy, NULL); if (err < 0) return err; if (!tb[NFACCT_FILTER_MASK] || !tb[NFACCT_FILTER_VALUE]) return -EINVAL; filter = kzalloc(sizeof(struct nfacct_filter), GFP_KERNEL); if (!filter) return -ENOMEM; filter->mask = ntohl(nla_get_be32(tb[NFACCT_FILTER_MASK])); filter->value = ntohl(nla_get_be32(tb[NFACCT_FILTER_VALUE])); cb->data = filter; return 0; } static int nfnl_acct_get(struct sk_buff *skb, const struct nfnl_info *info, const struct nlattr * const tb[]) { struct nfnl_acct_net *nfnl_acct_net = nfnl_acct_pernet(info->net); int ret = -ENOENT; struct nf_acct *cur; char *acct_name; if (info->nlh->nlmsg_flags & NLM_F_DUMP) { struct netlink_dump_control c = { .dump = nfnl_acct_dump, .start = nfnl_acct_start, .done = nfnl_acct_done, .data = (void *)tb[NFACCT_FILTER], }; return netlink_dump_start(info->sk, skb, info->nlh, &c); } if (!tb[NFACCT_NAME]) return -EINVAL; acct_name = nla_data(tb[NFACCT_NAME]); list_for_each_entry(cur, &nfnl_acct_net->nfnl_acct_list, head) { struct sk_buff *skb2; if (strncmp(cur->name, acct_name, NFACCT_NAME_MAX)!= 0) continue; skb2 = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL); if (skb2 == NULL) { ret = -ENOMEM; break; } ret = nfnl_acct_fill_info(skb2, NETLINK_CB(skb).portid, info->nlh->nlmsg_seq, NFNL_MSG_TYPE(info->nlh->nlmsg_type), NFNL_MSG_ACCT_NEW, cur); if (ret <= 0) { kfree_skb(skb2); break; } ret = nfnetlink_unicast(skb2, info->net, NETLINK_CB(skb).portid); break; } return ret; } /* try to delete object, fail if it is still in use. */ static int nfnl_acct_try_del(struct nf_acct *cur) { int ret = 0; /* We want to avoid races with nfnl_acct_put. So only when the current * refcnt is 1, we decrease it to 0. */ if (refcount_dec_if_one(&cur->refcnt)) { /* We are protected by nfnl mutex. */ list_del_rcu(&cur->head); kfree_rcu(cur, rcu_head); } else { ret = -EBUSY; } return ret; } static int nfnl_acct_del(struct sk_buff *skb, const struct nfnl_info *info, const struct nlattr * const tb[]) { struct nfnl_acct_net *nfnl_acct_net = nfnl_acct_pernet(info->net); struct nf_acct *cur, *tmp; int ret = -ENOENT; char *acct_name; if (!tb[NFACCT_NAME]) { list_for_each_entry_safe(cur, tmp, &nfnl_acct_net->nfnl_acct_list, head) nfnl_acct_try_del(cur); return 0; } acct_name = nla_data(tb[NFACCT_NAME]); list_for_each_entry(cur, &nfnl_acct_net->nfnl_acct_list, head) { if (strncmp(cur->name, acct_name, NFACCT_NAME_MAX) != 0) continue; ret = nfnl_acct_try_del(cur); if (ret < 0) return ret; break; } return ret; } static const struct nla_policy nfnl_acct_policy[NFACCT_MAX+1] = { [NFACCT_NAME] = { .type = NLA_NUL_STRING, .len = NFACCT_NAME_MAX-1 }, [NFACCT_BYTES] = { .type = NLA_U64 }, [NFACCT_PKTS] = { .type = NLA_U64 }, [NFACCT_FLAGS] = { .type = NLA_U32 }, [NFACCT_QUOTA] = { .type = NLA_U64 }, [NFACCT_FILTER] = {.type = NLA_NESTED }, }; static const struct nfnl_callback nfnl_acct_cb[NFNL_MSG_ACCT_MAX] = { [NFNL_MSG_ACCT_NEW] = { .call = nfnl_acct_new, .type = NFNL_CB_MUTEX, .attr_count = NFACCT_MAX, .policy = nfnl_acct_policy }, [NFNL_MSG_ACCT_GET] = { .call = nfnl_acct_get, .type = NFNL_CB_MUTEX, .attr_count = NFACCT_MAX, .policy = nfnl_acct_policy }, [NFNL_MSG_ACCT_GET_CTRZERO] = { .call = nfnl_acct_get, .type = NFNL_CB_MUTEX, .attr_count = NFACCT_MAX, .policy = nfnl_acct_policy }, [NFNL_MSG_ACCT_DEL] = { .call = nfnl_acct_del, .type = NFNL_CB_MUTEX, .attr_count = NFACCT_MAX, .policy = nfnl_acct_policy }, }; static const struct nfnetlink_subsystem nfnl_acct_subsys = { .name = "acct", .subsys_id = NFNL_SUBSYS_ACCT, .cb_count = NFNL_MSG_ACCT_MAX, .cb = nfnl_acct_cb, }; MODULE_ALIAS_NFNL_SUBSYS(NFNL_SUBSYS_ACCT); struct nf_acct *nfnl_acct_find_get(struct net *net, const char *acct_name) { struct nfnl_acct_net *nfnl_acct_net = nfnl_acct_pernet(net); struct nf_acct *cur, *acct = NULL; rcu_read_lock(); list_for_each_entry_rcu(cur, &nfnl_acct_net->nfnl_acct_list, head) { if (strncmp(cur->name, acct_name, NFACCT_NAME_MAX)!= 0) continue; if (!try_module_get(THIS_MODULE)) goto err; if (!refcount_inc_not_zero(&cur->refcnt)) { module_put(THIS_MODULE); goto err; } acct = cur; break; } err: rcu_read_unlock(); return acct; } EXPORT_SYMBOL_GPL(nfnl_acct_find_get); void nfnl_acct_put(struct nf_acct *acct) { if (refcount_dec_and_test(&acct->refcnt)) kfree_rcu(acct, rcu_head); module_put(THIS_MODULE); } EXPORT_SYMBOL_GPL(nfnl_acct_put); void nfnl_acct_update(const struct sk_buff *skb, struct nf_acct *nfacct) { atomic64_inc(&nfacct->pkts); atomic64_add(skb->len, &nfacct->bytes); } EXPORT_SYMBOL_GPL(nfnl_acct_update); static void nfnl_overquota_report(struct net *net, struct nf_acct *nfacct) { int ret; struct sk_buff *skb; skb = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_ATOMIC); if (skb == NULL) return; ret = nfnl_acct_fill_info(skb, 0, 0, NFNL_MSG_ACCT_OVERQUOTA, 0, nfacct); if (ret <= 0) { kfree_skb(skb); return; } nfnetlink_broadcast(net, skb, 0, NFNLGRP_ACCT_QUOTA, GFP_ATOMIC); } int nfnl_acct_overquota(struct net *net, struct nf_acct *nfacct) { u64 now; u64 *quota; int ret = NFACCT_UNDERQUOTA; /* no place here if we don't have a quota */ if (!(nfacct->flags & NFACCT_F_QUOTA)) return NFACCT_NO_QUOTA; quota = (u64 *)nfacct->data; now = (nfacct->flags & NFACCT_F_QUOTA_PKTS) ? atomic64_read(&nfacct->pkts) : atomic64_read(&nfacct->bytes); ret = now > *quota; if (now >= *quota && !test_and_set_bit(NFACCT_OVERQUOTA_BIT, &nfacct->flags)) { nfnl_overquota_report(net, nfacct); } return ret; } EXPORT_SYMBOL_GPL(nfnl_acct_overquota); static int __net_init nfnl_acct_net_init(struct net *net) { INIT_LIST_HEAD(&nfnl_acct_pernet(net)->nfnl_acct_list); return 0; } static void __net_exit nfnl_acct_net_exit(struct net *net) { struct nfnl_acct_net *nfnl_acct_net = nfnl_acct_pernet(net); struct nf_acct *cur, *tmp; list_for_each_entry_safe(cur, tmp, &nfnl_acct_net->nfnl_acct_list, head) { list_del_rcu(&cur->head); if (refcount_dec_and_test(&cur->refcnt)) kfree_rcu(cur, rcu_head); } } static struct pernet_operations nfnl_acct_ops = { .init = nfnl_acct_net_init, .exit = nfnl_acct_net_exit, .id = &nfnl_acct_net_id, .size = sizeof(struct nfnl_acct_net), }; static int __init nfnl_acct_init(void) { int ret; ret = register_pernet_subsys(&nfnl_acct_ops); if (ret < 0) { pr_err("nfnl_acct_init: failed to register pernet ops\n"); goto err_out; } ret = nfnetlink_subsys_register(&nfnl_acct_subsys); if (ret < 0) { pr_err("nfnl_acct_init: cannot register with nfnetlink.\n"); goto cleanup_pernet; } return 0; cleanup_pernet: unregister_pernet_subsys(&nfnl_acct_ops); err_out: return ret; } static void __exit nfnl_acct_exit(void) { nfnetlink_subsys_unregister(&nfnl_acct_subsys); unregister_pernet_subsys(&nfnl_acct_ops); } module_init(nfnl_acct_init); module_exit(nfnl_acct_exit); |
| 25 25 148 18 18 18 18 18 12 12 18 18 | 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 | // SPDX-License-Identifier: GPL-2.0-or-later /* SCTP kernel implementation * (C) Copyright IBM Corp. 2001, 2004 * Copyright (c) 1999-2000 Cisco, Inc. * Copyright (c) 1999-2001 Motorola, Inc. * Copyright (c) 2001 Intel Corp. * * This file is part of the SCTP kernel implementation * * These functions manipulate sctp tsn mapping array. * * Please send any bug reports or fixes you make to the * email address(es): * lksctp developers <linux-sctp@vger.kernel.org> * * Written or modified by: * La Monte H.P. Yarroll <piggy@acm.org> * Jon Grimm <jgrimm@us.ibm.com> * Karl Knutson <karl@athena.chicago.il.us> * Sridhar Samudrala <sri@us.ibm.com> */ #include <linux/slab.h> #include <linux/types.h> #include <linux/bitmap.h> #include <net/sctp/sctp.h> #include <net/sctp/sm.h> static void sctp_tsnmap_update(struct sctp_tsnmap *map); static void sctp_tsnmap_find_gap_ack(unsigned long *map, __u16 off, __u16 len, __u16 *start, __u16 *end); static int sctp_tsnmap_grow(struct sctp_tsnmap *map, u16 size); /* Initialize a block of memory as a tsnmap. */ struct sctp_tsnmap *sctp_tsnmap_init(struct sctp_tsnmap *map, __u16 len, __u32 initial_tsn, gfp_t gfp) { if (!map->tsn_map) { map->tsn_map = kzalloc(len>>3, gfp); if (map->tsn_map == NULL) return NULL; map->len = len; } else { bitmap_zero(map->tsn_map, map->len); } /* Keep track of TSNs represented by tsn_map. */ map->base_tsn = initial_tsn; map->cumulative_tsn_ack_point = initial_tsn - 1; map->max_tsn_seen = map->cumulative_tsn_ack_point; map->num_dup_tsns = 0; return map; } void sctp_tsnmap_free(struct sctp_tsnmap *map) { map->len = 0; kfree(map->tsn_map); } /* Test the tracking state of this TSN. * Returns: * 0 if the TSN has not yet been seen * >0 if the TSN has been seen (duplicate) * <0 if the TSN is invalid (too large to track) */ int sctp_tsnmap_check(const struct sctp_tsnmap *map, __u32 tsn) { u32 gap; /* Check to see if this is an old TSN */ if (TSN_lte(tsn, map->cumulative_tsn_ack_point)) return 1; /* Verify that we can hold this TSN and that it will not * overflow our map */ if (!TSN_lt(tsn, map->base_tsn + SCTP_TSN_MAP_SIZE)) return -1; /* Calculate the index into the mapping arrays. */ gap = tsn - map->base_tsn; /* Check to see if TSN has already been recorded. */ if (gap < map->len && test_bit(gap, map->tsn_map)) return 1; else return 0; } /* Mark this TSN as seen. */ int sctp_tsnmap_mark(struct sctp_tsnmap *map, __u32 tsn, struct sctp_transport *trans) { u16 gap; if (TSN_lt(tsn, map->base_tsn)) return 0; gap = tsn - map->base_tsn; if (gap >= map->len && !sctp_tsnmap_grow(map, gap + 1)) return -ENOMEM; if (!sctp_tsnmap_has_gap(map) && gap == 0) { /* In this case the map has no gaps and the tsn we are * recording is the next expected tsn. We don't touch * the map but simply bump the values. */ map->max_tsn_seen++; map->cumulative_tsn_ack_point++; if (trans) trans->sack_generation = trans->asoc->peer.sack_generation; map->base_tsn++; } else { /* Either we already have a gap, or about to record a gap, so * have work to do. * * Bump the max. */ if (TSN_lt(map->max_tsn_seen, tsn)) map->max_tsn_seen = tsn; /* Mark the TSN as received. */ set_bit(gap, map->tsn_map); /* Go fixup any internal TSN mapping variables including * cumulative_tsn_ack_point. */ sctp_tsnmap_update(map); } return 0; } /* Initialize a Gap Ack Block iterator from memory being provided. */ static void sctp_tsnmap_iter_init(const struct sctp_tsnmap *map, struct sctp_tsnmap_iter *iter) { /* Only start looking one past the Cumulative TSN Ack Point. */ iter->start = map->cumulative_tsn_ack_point + 1; } /* Get the next Gap Ack Blocks. Returns 0 if there was not another block * to get. */ static int sctp_tsnmap_next_gap_ack(const struct sctp_tsnmap *map, struct sctp_tsnmap_iter *iter, __u16 *start, __u16 *end) { int ended = 0; __u16 start_ = 0, end_ = 0, offset; /* If there are no more gap acks possible, get out fast. */ if (TSN_lte(map->max_tsn_seen, iter->start)) return 0; offset = iter->start - map->base_tsn; sctp_tsnmap_find_gap_ack(map->tsn_map, offset, map->len, &start_, &end_); /* The Gap Ack Block happens to end at the end of the map. */ if (start_ && !end_) end_ = map->len - 1; /* If we found a Gap Ack Block, return the start and end and * bump the iterator forward. */ if (end_) { /* Fix up the start and end based on the * Cumulative TSN Ack which is always 1 behind base. */ *start = start_ + 1; *end = end_ + 1; /* Move the iterator forward. */ iter->start = map->cumulative_tsn_ack_point + *end + 1; ended = 1; } return ended; } /* Mark this and any lower TSN as seen. */ void sctp_tsnmap_skip(struct sctp_tsnmap *map, __u32 tsn) { u32 gap; if (TSN_lt(tsn, map->base_tsn)) return; if (!TSN_lt(tsn, map->base_tsn + SCTP_TSN_MAP_SIZE)) return; /* Bump the max. */ if (TSN_lt(map->max_tsn_seen, tsn)) map->max_tsn_seen = tsn; gap = tsn - map->base_tsn + 1; map->base_tsn += gap; map->cumulative_tsn_ack_point += gap; if (gap >= map->len) { /* If our gap is larger then the map size, just * zero out the map. */ bitmap_zero(map->tsn_map, map->len); } else { /* If the gap is smaller than the map size, * shift the map by 'gap' bits and update further. */ bitmap_shift_right(map->tsn_map, map->tsn_map, gap, map->len); sctp_tsnmap_update(map); } } /******************************************************************** * 2nd Level Abstractions ********************************************************************/ /* This private helper function updates the tsnmap buffers and * the Cumulative TSN Ack Point. */ static void sctp_tsnmap_update(struct sctp_tsnmap *map) { u16 len; unsigned long zero_bit; len = map->max_tsn_seen - map->cumulative_tsn_ack_point; zero_bit = find_first_zero_bit(map->tsn_map, len); if (!zero_bit) return; /* The first 0-bit is bit 0. nothing to do */ map->base_tsn += zero_bit; map->cumulative_tsn_ack_point += zero_bit; bitmap_shift_right(map->tsn_map, map->tsn_map, zero_bit, map->len); } /* How many data chunks are we missing from our peer? */ __u16 sctp_tsnmap_pending(struct sctp_tsnmap *map) { __u32 cum_tsn = map->cumulative_tsn_ack_point; __u32 max_tsn = map->max_tsn_seen; __u32 base_tsn = map->base_tsn; __u16 pending_data; u32 gap; pending_data = max_tsn - cum_tsn; gap = max_tsn - base_tsn; if (gap == 0 || gap >= map->len) goto out; pending_data -= bitmap_weight(map->tsn_map, gap + 1); out: return pending_data; } /* This is a private helper for finding Gap Ack Blocks. It searches a * single array for the start and end of a Gap Ack Block. * * The flags "started" and "ended" tell is if we found the beginning * or (respectively) the end of a Gap Ack Block. */ static void sctp_tsnmap_find_gap_ack(unsigned long *map, __u16 off, __u16 len, __u16 *start, __u16 *end) { int i = off; /* Look through the entire array, but break out * early if we have found the end of the Gap Ack Block. */ /* Also, stop looking past the maximum TSN seen. */ /* Look for the start. */ i = find_next_bit(map, len, off); if (i < len) *start = i; /* Look for the end. */ if (*start) { /* We have found the start, let's find the * end. If we find the end, break out. */ i = find_next_zero_bit(map, len, i); if (i < len) *end = i - 1; } } /* Renege that we have seen a TSN. */ void sctp_tsnmap_renege(struct sctp_tsnmap *map, __u32 tsn) { u32 gap; if (TSN_lt(tsn, map->base_tsn)) return; /* Assert: TSN is in range. */ if (!TSN_lt(tsn, map->base_tsn + map->len)) return; gap = tsn - map->base_tsn; /* Pretend we never saw the TSN. */ clear_bit(gap, map->tsn_map); } /* How many gap ack blocks do we have recorded? */ __u16 sctp_tsnmap_num_gabs(struct sctp_tsnmap *map, struct sctp_gap_ack_block *gabs) { struct sctp_tsnmap_iter iter; int ngaps = 0; /* Refresh the gap ack information. */ if (sctp_tsnmap_has_gap(map)) { __u16 start = 0, end = 0; sctp_tsnmap_iter_init(map, &iter); while (sctp_tsnmap_next_gap_ack(map, &iter, &start, &end)) { gabs[ngaps].start = htons(start); gabs[ngaps].end = htons(end); ngaps++; if (ngaps >= SCTP_MAX_GABS) break; } } return ngaps; } static int sctp_tsnmap_grow(struct sctp_tsnmap *map, u16 size) { unsigned long *new; unsigned long inc; u16 len; if (size > SCTP_TSN_MAP_SIZE) return 0; inc = ALIGN((size - map->len), BITS_PER_LONG) + SCTP_TSN_MAP_INCREMENT; len = min_t(u16, map->len + inc, SCTP_TSN_MAP_SIZE); new = kzalloc(len>>3, GFP_ATOMIC); if (!new) return 0; bitmap_copy(new, map->tsn_map, map->max_tsn_seen - map->cumulative_tsn_ack_point); kfree(map->tsn_map); map->tsn_map = new; map->len = len; return 1; } |
| 20 16 20 20 20 2 20 80 2 2 2 2 17 20 20 4 20 20 20 20 17 2 17 20 20 20 19 20 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 | // SPDX-License-Identifier: GPL-2.0-or-later /* * net/core/gen_stats.c * * Authors: Thomas Graf <tgraf@suug.ch> * Jamal Hadi Salim * Alexey Kuznetsov, <kuznet@ms2.inr.ac.ru> * * See Documentation/networking/gen_stats.rst */ #include <linux/types.h> #include <linux/kernel.h> #include <linux/module.h> #include <linux/interrupt.h> #include <linux/socket.h> #include <linux/rtnetlink.h> #include <linux/gen_stats.h> #include <net/netlink.h> #include <net/gen_stats.h> #include <net/sch_generic.h> static inline int gnet_stats_copy(struct gnet_dump *d, int type, void *buf, int size, int padattr) { if (nla_put_64bit(d->skb, type, size, buf, padattr)) goto nla_put_failure; return 0; nla_put_failure: if (d->lock) spin_unlock_bh(d->lock); kfree(d->xstats); d->xstats = NULL; d->xstats_len = 0; return -1; } /** * gnet_stats_start_copy_compat - start dumping procedure in compatibility mode * @skb: socket buffer to put statistics TLVs into * @type: TLV type for top level statistic TLV * @tc_stats_type: TLV type for backward compatibility struct tc_stats TLV * @xstats_type: TLV type for backward compatibility xstats TLV * @lock: statistics lock * @d: dumping handle * @padattr: padding attribute * * Initializes the dumping handle, grabs the statistic lock and appends * an empty TLV header to the socket buffer for use a container for all * other statistic TLVS. * * The dumping handle is marked to be in backward compatibility mode telling * all gnet_stats_copy_XXX() functions to fill a local copy of struct tc_stats. * * Returns 0 on success or -1 if the room in the socket buffer was not sufficient. */ int gnet_stats_start_copy_compat(struct sk_buff *skb, int type, int tc_stats_type, int xstats_type, spinlock_t *lock, struct gnet_dump *d, int padattr) __acquires(lock) { memset(d, 0, sizeof(*d)); if (type) d->tail = (struct nlattr *)skb_tail_pointer(skb); d->skb = skb; d->compat_tc_stats = tc_stats_type; d->compat_xstats = xstats_type; d->padattr = padattr; if (lock) { d->lock = lock; spin_lock_bh(lock); } if (d->tail) { int ret = gnet_stats_copy(d, type, NULL, 0, padattr); /* The initial attribute added in gnet_stats_copy() may be * preceded by a padding attribute, in which case d->tail will * end up pointing at the padding instead of the real attribute. * Fix this so gnet_stats_finish_copy() adjusts the length of * the right attribute. */ if (ret == 0 && d->tail->nla_type == padattr) d->tail = (struct nlattr *)((char *)d->tail + NLA_ALIGN(d->tail->nla_len)); return ret; } return 0; } EXPORT_SYMBOL(gnet_stats_start_copy_compat); /** * gnet_stats_start_copy - start dumping procedure in compatibility mode * @skb: socket buffer to put statistics TLVs into * @type: TLV type for top level statistic TLV * @lock: statistics lock * @d: dumping handle * @padattr: padding attribute * * Initializes the dumping handle, grabs the statistic lock and appends * an empty TLV header to the socket buffer for use a container for all * other statistic TLVS. * * Returns 0 on success or -1 if the room in the socket buffer was not sufficient. */ int gnet_stats_start_copy(struct sk_buff *skb, int type, spinlock_t *lock, struct gnet_dump *d, int padattr) { return gnet_stats_start_copy_compat(skb, type, 0, 0, lock, d, padattr); } EXPORT_SYMBOL(gnet_stats_start_copy); /* Must not be inlined, due to u64_stats seqcount_t lockdep key */ void gnet_stats_basic_sync_init(struct gnet_stats_basic_sync *b) { u64_stats_set(&b->bytes, 0); u64_stats_set(&b->packets, 0); u64_stats_init(&b->syncp); } EXPORT_SYMBOL(gnet_stats_basic_sync_init); static void gnet_stats_add_basic_cpu(struct gnet_stats_basic_sync *bstats, struct gnet_stats_basic_sync __percpu *cpu) { u64 t_bytes = 0, t_packets = 0; int i; for_each_possible_cpu(i) { struct gnet_stats_basic_sync *bcpu = per_cpu_ptr(cpu, i); unsigned int start; u64 bytes, packets; do { start = u64_stats_fetch_begin(&bcpu->syncp); bytes = u64_stats_read(&bcpu->bytes); packets = u64_stats_read(&bcpu->packets); } while (u64_stats_fetch_retry(&bcpu->syncp, start)); t_bytes += bytes; t_packets += packets; } _bstats_update(bstats, t_bytes, t_packets); } void gnet_stats_add_basic(struct gnet_stats_basic_sync *bstats, struct gnet_stats_basic_sync __percpu *cpu, struct gnet_stats_basic_sync *b, bool running) { unsigned int start; u64 bytes = 0; u64 packets = 0; WARN_ON_ONCE((cpu || running) && in_hardirq()); if (cpu) { gnet_stats_add_basic_cpu(bstats, cpu); return; } do { if (running) start = u64_stats_fetch_begin(&b->syncp); bytes = u64_stats_read(&b->bytes); packets = u64_stats_read(&b->packets); } while (running && u64_stats_fetch_retry(&b->syncp, start)); _bstats_update(bstats, bytes, packets); } EXPORT_SYMBOL(gnet_stats_add_basic); static void gnet_stats_read_basic(u64 *ret_bytes, u64 *ret_packets, struct gnet_stats_basic_sync __percpu *cpu, struct gnet_stats_basic_sync *b, bool running) { unsigned int start; if (cpu) { u64 t_bytes = 0, t_packets = 0; int i; for_each_possible_cpu(i) { struct gnet_stats_basic_sync *bcpu = per_cpu_ptr(cpu, i); unsigned int start; u64 bytes, packets; do { start = u64_stats_fetch_begin(&bcpu->syncp); bytes = u64_stats_read(&bcpu->bytes); packets = u64_stats_read(&bcpu->packets); } while (u64_stats_fetch_retry(&bcpu->syncp, start)); t_bytes += bytes; t_packets += packets; } *ret_bytes = t_bytes; *ret_packets = t_packets; return; } do { if (running) start = u64_stats_fetch_begin(&b->syncp); *ret_bytes = u64_stats_read(&b->bytes); *ret_packets = u64_stats_read(&b->packets); } while (running && u64_stats_fetch_retry(&b->syncp, start)); } static int ___gnet_stats_copy_basic(struct gnet_dump *d, struct gnet_stats_basic_sync __percpu *cpu, struct gnet_stats_basic_sync *b, int type, bool running) { u64 bstats_bytes, bstats_packets; gnet_stats_read_basic(&bstats_bytes, &bstats_packets, cpu, b, running); if (d->compat_tc_stats && type == TCA_STATS_BASIC) { d->tc_stats.bytes = bstats_bytes; d->tc_stats.packets = bstats_packets; } if (d->tail) { struct gnet_stats_basic sb; int res; memset(&sb, 0, sizeof(sb)); sb.bytes = bstats_bytes; sb.packets = bstats_packets; res = gnet_stats_copy(d, type, &sb, sizeof(sb), TCA_STATS_PAD); if (res < 0 || sb.packets == bstats_packets) return res; /* emit 64bit stats only if needed */ return gnet_stats_copy(d, TCA_STATS_PKT64, &bstats_packets, sizeof(bstats_packets), TCA_STATS_PAD); } return 0; } /** * gnet_stats_copy_basic - copy basic statistics into statistic TLV * @d: dumping handle * @cpu: copy statistic per cpu * @b: basic statistics * @running: true if @b represents a running qdisc, thus @b's * internal values might change during basic reads. * Only used if @cpu is NULL * * Context: task; must not be run from IRQ or BH contexts * * Appends the basic statistics to the top level TLV created by * gnet_stats_start_copy(). * * Returns 0 on success or -1 with the statistic lock released * if the room in the socket buffer was not sufficient. */ int gnet_stats_copy_basic(struct gnet_dump *d, struct gnet_stats_basic_sync __percpu *cpu, struct gnet_stats_basic_sync *b, bool running) { return ___gnet_stats_copy_basic(d, cpu, b, TCA_STATS_BASIC, running); } EXPORT_SYMBOL(gnet_stats_copy_basic); /** * gnet_stats_copy_basic_hw - copy basic hw statistics into statistic TLV * @d: dumping handle * @cpu: copy statistic per cpu * @b: basic statistics * @running: true if @b represents a running qdisc, thus @b's * internal values might change during basic reads. * Only used if @cpu is NULL * * Context: task; must not be run from IRQ or BH contexts * * Appends the basic statistics to the top level TLV created by * gnet_stats_start_copy(). * * Returns 0 on success or -1 with the statistic lock released * if the room in the socket buffer was not sufficient. */ int gnet_stats_copy_basic_hw(struct gnet_dump *d, struct gnet_stats_basic_sync __percpu *cpu, struct gnet_stats_basic_sync *b, bool running) { return ___gnet_stats_copy_basic(d, cpu, b, TCA_STATS_BASIC_HW, running); } EXPORT_SYMBOL(gnet_stats_copy_basic_hw); /** * gnet_stats_copy_rate_est - copy rate estimator statistics into statistics TLV * @d: dumping handle * @rate_est: rate estimator * * Appends the rate estimator statistics to the top level TLV created by * gnet_stats_start_copy(). * * Returns 0 on success or -1 with the statistic lock released * if the room in the socket buffer was not sufficient. */ int gnet_stats_copy_rate_est(struct gnet_dump *d, struct net_rate_estimator __rcu **rate_est) { struct gnet_stats_rate_est64 sample; struct gnet_stats_rate_est est; int res; if (!gen_estimator_read(rate_est, &sample)) return 0; est.bps = min_t(u64, UINT_MAX, sample.bps); /* we have some time before reaching 2^32 packets per second */ est.pps = sample.pps; if (d->compat_tc_stats) { d->tc_stats.bps = est.bps; d->tc_stats.pps = est.pps; } if (d->tail) { res = gnet_stats_copy(d, TCA_STATS_RATE_EST, &est, sizeof(est), TCA_STATS_PAD); if (res < 0 || est.bps == sample.bps) return res; /* emit 64bit stats only if needed */ return gnet_stats_copy(d, TCA_STATS_RATE_EST64, &sample, sizeof(sample), TCA_STATS_PAD); } return 0; } EXPORT_SYMBOL(gnet_stats_copy_rate_est); static void gnet_stats_add_queue_cpu(struct gnet_stats_queue *qstats, const struct gnet_stats_queue __percpu *q) { int i; for_each_possible_cpu(i) { const struct gnet_stats_queue *qcpu = per_cpu_ptr(q, i); qstats->qlen += qcpu->qlen; qstats->backlog += qcpu->backlog; qstats->drops += qcpu->drops; qstats->requeues += qcpu->requeues; qstats->overlimits += qcpu->overlimits; } } void gnet_stats_add_queue(struct gnet_stats_queue *qstats, const struct gnet_stats_queue __percpu *cpu, const struct gnet_stats_queue *q) { if (cpu) { gnet_stats_add_queue_cpu(qstats, cpu); } else { qstats->qlen += q->qlen; qstats->backlog += q->backlog; qstats->drops += q->drops; qstats->requeues += q->requeues; qstats->overlimits += q->overlimits; } } EXPORT_SYMBOL(gnet_stats_add_queue); /** * gnet_stats_copy_queue - copy queue statistics into statistics TLV * @d: dumping handle * @cpu_q: per cpu queue statistics * @q: queue statistics * @qlen: queue length statistics * * Appends the queue statistics to the top level TLV created by * gnet_stats_start_copy(). Using per cpu queue statistics if * they are available. * * Returns 0 on success or -1 with the statistic lock released * if the room in the socket buffer was not sufficient. */ int gnet_stats_copy_queue(struct gnet_dump *d, struct gnet_stats_queue __percpu *cpu_q, struct gnet_stats_queue *q, __u32 qlen) { struct gnet_stats_queue qstats = {0}; gnet_stats_add_queue(&qstats, cpu_q, q); qstats.qlen = qlen; if (d->compat_tc_stats) { d->tc_stats.drops = qstats.drops; d->tc_stats.qlen = qstats.qlen; d->tc_stats.backlog = qstats.backlog; d->tc_stats.overlimits = qstats.overlimits; } if (d->tail) return gnet_stats_copy(d, TCA_STATS_QUEUE, &qstats, sizeof(qstats), TCA_STATS_PAD); return 0; } EXPORT_SYMBOL(gnet_stats_copy_queue); /** * gnet_stats_copy_app - copy application specific statistics into statistics TLV * @d: dumping handle * @st: application specific statistics data * @len: length of data * * Appends the application specific statistics to the top level TLV created by * gnet_stats_start_copy() and remembers the data for XSTATS if the dumping * handle is in backward compatibility mode. * * Returns 0 on success or -1 with the statistic lock released * if the room in the socket buffer was not sufficient. */ int gnet_stats_copy_app(struct gnet_dump *d, void *st, int len) { if (d->compat_xstats) { d->xstats = kmemdup(st, len, GFP_ATOMIC); if (!d->xstats) goto err_out; d->xstats_len = len; } if (d->tail) return gnet_stats_copy(d, TCA_STATS_APP, st, len, TCA_STATS_PAD); return 0; err_out: if (d->lock) spin_unlock_bh(d->lock); d->xstats_len = 0; return -1; } EXPORT_SYMBOL(gnet_stats_copy_app); /** * gnet_stats_finish_copy - finish dumping procedure * @d: dumping handle * * Corrects the length of the top level TLV to include all TLVs added * by gnet_stats_copy_XXX() calls. Adds the backward compatibility TLVs * if gnet_stats_start_copy_compat() was used and releases the statistics * lock. * * Returns 0 on success or -1 with the statistic lock released * if the room in the socket buffer was not sufficient. */ int gnet_stats_finish_copy(struct gnet_dump *d) { if (d->tail) d->tail->nla_len = skb_tail_pointer(d->skb) - (u8 *)d->tail; if (d->compat_tc_stats) if (gnet_stats_copy(d, d->compat_tc_stats, &d->tc_stats, sizeof(d->tc_stats), d->padattr) < 0) return -1; if (d->compat_xstats && d->xstats) { if (gnet_stats_copy(d, d->compat_xstats, d->xstats, d->xstats_len, d->padattr) < 0) return -1; } if (d->lock) spin_unlock_bh(d->lock); kfree(d->xstats); d->xstats = NULL; d->xstats_len = 0; return 0; } EXPORT_SYMBOL(gnet_stats_finish_copy); |
| 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 | /* SPDX-License-Identifier: GPL-2.0-or-later */ /* * INET An implementation of the TCP/IP protocol suite for the LINUX * operating system. INET is implemented using the BSD Socket * interface as the means of communication with the user level. * * Definitions for the IP protocol. * * Version: @(#)ip.h 1.0.2 04/28/93 * * Authors: Fred N. van Kempen, <waltje@uWalt.NL.Mugnet.ORG> */ #ifndef _LINUX_IP_H #define _LINUX_IP_H #include <linux/skbuff.h> #include <uapi/linux/ip.h> static inline struct iphdr *ip_hdr(const struct sk_buff *skb) { return (struct iphdr *)skb_network_header(skb); } static inline struct iphdr *inner_ip_hdr(const struct sk_buff *skb) { return (struct iphdr *)skb_inner_network_header(skb); } static inline struct iphdr *ipip_hdr(const struct sk_buff *skb) { return (struct iphdr *)skb_transport_header(skb); } static inline unsigned int ip_transport_len(const struct sk_buff *skb) { return ntohs(ip_hdr(skb)->tot_len) - skb_network_header_len(skb); } static inline unsigned int iph_totlen(const struct sk_buff *skb, const struct iphdr *iph) { u32 len = ntohs(iph->tot_len); return (len || !skb_is_gso(skb) || !skb_is_gso_tcp(skb)) ? len : skb->len - skb_network_offset(skb); } static inline unsigned int skb_ip_totlen(const struct sk_buff *skb) { return iph_totlen(skb, ip_hdr(skb)); } /* IPv4 datagram length is stored into 16bit field (tot_len) */ #define IP_MAX_MTU 0xFFFFU static inline void iph_set_totlen(struct iphdr *iph, unsigned int len) { iph->tot_len = len <= IP_MAX_MTU ? htons(len) : 0; } #endif /* _LINUX_IP_H */ |
| 4678 69 678 679 5515 420 4678 681 5464 | 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 | /* SPDX-License-Identifier: GPL-2.0-or-later */ /* I/O iterator iteration building functions. * * Copyright (C) 2023 Red Hat, Inc. All Rights Reserved. * Written by David Howells (dhowells@redhat.com) */ #ifndef _LINUX_IOV_ITER_H #define _LINUX_IOV_ITER_H #include <linux/uio.h> #include <linux/bvec.h> #include <linux/folio_queue.h> typedef size_t (*iov_step_f)(void *iter_base, size_t progress, size_t len, void *priv, void *priv2); typedef size_t (*iov_ustep_f)(void __user *iter_base, size_t progress, size_t len, void *priv, void *priv2); /* * Handle ITER_UBUF. */ static __always_inline size_t iterate_ubuf(struct iov_iter *iter, size_t len, void *priv, void *priv2, iov_ustep_f step) { void __user *base = iter->ubuf; size_t progress = 0, remain; remain = step(base + iter->iov_offset, 0, len, priv, priv2); progress = len - remain; iter->iov_offset += progress; iter->count -= progress; return progress; } /* * Handle ITER_IOVEC. */ static __always_inline size_t iterate_iovec(struct iov_iter *iter, size_t len, void *priv, void *priv2, iov_ustep_f step) { const struct iovec *p = iter->__iov; size_t progress = 0, skip = iter->iov_offset; do { size_t remain, consumed; size_t part = min(len, p->iov_len - skip); if (likely(part)) { remain = step(p->iov_base + skip, progress, part, priv, priv2); consumed = part - remain; progress += consumed; skip += consumed; len -= consumed; if (skip < p->iov_len) break; } p++; skip = 0; } while (len); iter->nr_segs -= p - iter->__iov; iter->__iov = p; iter->iov_offset = skip; iter->count -= progress; return progress; } /* * Handle ITER_KVEC. */ static __always_inline size_t iterate_kvec(struct iov_iter *iter, size_t len, void *priv, void *priv2, iov_step_f step) { const struct kvec *p = iter->kvec; size_t progress = 0, skip = iter->iov_offset; do { size_t remain, consumed; size_t part = min(len, p->iov_len - skip); if (likely(part)) { remain = step(p->iov_base + skip, progress, part, priv, priv2); consumed = part - remain; progress += consumed; skip += consumed; len -= consumed; if (skip < p->iov_len) break; } p++; skip = 0; } while (len); iter->nr_segs -= p - iter->kvec; iter->kvec = p; iter->iov_offset = skip; iter->count -= progress; return progress; } /* * Handle ITER_BVEC. */ static __always_inline size_t iterate_bvec(struct iov_iter *iter, size_t len, void *priv, void *priv2, iov_step_f step) { const struct bio_vec *p = iter->bvec; size_t progress = 0, skip = iter->iov_offset; do { size_t remain, consumed; size_t offset = p->bv_offset + skip, part; void *kaddr = kmap_local_page(p->bv_page + offset / PAGE_SIZE); part = min3(len, (size_t)(p->bv_len - skip), (size_t)(PAGE_SIZE - offset % PAGE_SIZE)); remain = step(kaddr + offset % PAGE_SIZE, progress, part, priv, priv2); kunmap_local(kaddr); consumed = part - remain; len -= consumed; progress += consumed; skip += consumed; if (skip >= p->bv_len) { skip = 0; p++; } if (remain) break; } while (len); iter->nr_segs -= p - iter->bvec; iter->bvec = p; iter->iov_offset = skip; iter->count -= progress; return progress; } /* * Handle ITER_FOLIOQ. */ static __always_inline size_t iterate_folioq(struct iov_iter *iter, size_t len, void *priv, void *priv2, iov_step_f step) { const struct folio_queue *folioq = iter->folioq; unsigned int slot = iter->folioq_slot; size_t progress = 0, skip = iter->iov_offset; if (slot == folioq_nr_slots(folioq)) { /* The iterator may have been extended. */ folioq = folioq->next; slot = 0; } do { struct folio *folio = folioq_folio(folioq, slot); size_t part, remain, consumed; size_t fsize; void *base; if (!folio) break; fsize = folioq_folio_size(folioq, slot); base = kmap_local_folio(folio, skip); part = umin(len, PAGE_SIZE - skip % PAGE_SIZE); remain = step(base, progress, part, priv, priv2); kunmap_local(base); consumed = part - remain; len -= consumed; progress += consumed; skip += consumed; if (skip >= fsize) { skip = 0; slot++; if (slot == folioq_nr_slots(folioq) && folioq->next) { folioq = folioq->next; slot = 0; } } if (remain) break; } while (len); iter->folioq_slot = slot; iter->folioq = folioq; iter->iov_offset = skip; iter->count -= progress; return progress; } /* * Handle ITER_XARRAY. */ static __always_inline size_t iterate_xarray(struct iov_iter *iter, size_t len, void *priv, void *priv2, iov_step_f step) { struct folio *folio; size_t progress = 0; loff_t start = iter->xarray_start + iter->iov_offset; pgoff_t index = start / PAGE_SIZE; XA_STATE(xas, iter->xarray, index); rcu_read_lock(); xas_for_each(&xas, folio, ULONG_MAX) { size_t remain, consumed, offset, part, flen; if (xas_retry(&xas, folio)) continue; if (WARN_ON(xa_is_value(folio))) break; if (WARN_ON(folio_test_hugetlb(folio))) break; offset = offset_in_folio(folio, start + progress); flen = min(folio_size(folio) - offset, len); while (flen) { void *base = kmap_local_folio(folio, offset); part = min_t(size_t, flen, PAGE_SIZE - offset_in_page(offset)); remain = step(base, progress, part, priv, priv2); kunmap_local(base); consumed = part - remain; progress += consumed; len -= consumed; if (remain || len == 0) goto out; flen -= consumed; offset += consumed; } } out: rcu_read_unlock(); iter->iov_offset += progress; iter->count -= progress; return progress; } /* * Handle ITER_DISCARD. */ static __always_inline size_t iterate_discard(struct iov_iter *iter, size_t len, void *priv, void *priv2, iov_step_f step) { size_t progress = len; iter->count -= progress; return progress; } /** * iterate_and_advance2 - Iterate over an iterator * @iter: The iterator to iterate over. * @len: The amount to iterate over. * @priv: Data for the step functions. * @priv2: More data for the step functions. * @ustep: Function for UBUF/IOVEC iterators; given __user addresses. * @step: Function for other iterators; given kernel addresses. * * Iterate over the next part of an iterator, up to the specified length. The * buffer is presented in segments, which for kernel iteration are broken up by * physical pages and mapped, with the mapped address being presented. * * Two step functions, @step and @ustep, must be provided, one for handling * mapped kernel addresses and the other is given user addresses which have the * potential to fault since no pinning is performed. * * The step functions are passed the address and length of the segment, @priv, * @priv2 and the amount of data so far iterated over (which can, for example, * be added to @priv to point to the right part of a second buffer). The step * functions should return the amount of the segment they didn't process (ie. 0 * indicates complete processsing). * * This function returns the amount of data processed (ie. 0 means nothing was * processed and the value of @len means processes to completion). */ static __always_inline size_t iterate_and_advance2(struct iov_iter *iter, size_t len, void *priv, void *priv2, iov_ustep_f ustep, iov_step_f step) { if (unlikely(iter->count < len)) len = iter->count; if (unlikely(!len)) return 0; if (likely(iter_is_ubuf(iter))) return iterate_ubuf(iter, len, priv, priv2, ustep); if (likely(iter_is_iovec(iter))) return iterate_iovec(iter, len, priv, priv2, ustep); if (iov_iter_is_bvec(iter)) return iterate_bvec(iter, len, priv, priv2, step); if (iov_iter_is_kvec(iter)) return iterate_kvec(iter, len, priv, priv2, step); if (iov_iter_is_folioq(iter)) return iterate_folioq(iter, len, priv, priv2, step); if (iov_iter_is_xarray(iter)) return iterate_xarray(iter, len, priv, priv2, step); return iterate_discard(iter, len, priv, priv2, step); } /** * iterate_and_advance - Iterate over an iterator * @iter: The iterator to iterate over. * @len: The amount to iterate over. * @priv: Data for the step functions. * @ustep: Function for UBUF/IOVEC iterators; given __user addresses. * @step: Function for other iterators; given kernel addresses. * * As iterate_and_advance2(), but priv2 is always NULL. */ static __always_inline size_t iterate_and_advance(struct iov_iter *iter, size_t len, void *priv, iov_ustep_f ustep, iov_step_f step) { return iterate_and_advance2(iter, len, priv, NULL, ustep, step); } /** * iterate_and_advance_kernel - Iterate over a kernel-internal iterator * @iter: The iterator to iterate over. * @len: The amount to iterate over. * @priv: Data for the step functions. * @priv2: More data for the step functions. * @step: Function for other iterators; given kernel addresses. * * Iterate over the next part of an iterator, up to the specified length. The * buffer is presented in segments, which for kernel iteration are broken up by * physical pages and mapped, with the mapped address being presented. * * [!] Note This will only handle BVEC, KVEC, FOLIOQ, XARRAY and DISCARD-type * iterators; it will not handle UBUF or IOVEC-type iterators. * * A step functions, @step, must be provided, one for handling mapped kernel * addresses and the other is given user addresses which have the potential to * fault since no pinning is performed. * * The step functions are passed the address and length of the segment, @priv, * @priv2 and the amount of data so far iterated over (which can, for example, * be added to @priv to point to the right part of a second buffer). The step * functions should return the amount of the segment they didn't process (ie. 0 * indicates complete processsing). * * This function returns the amount of data processed (ie. 0 means nothing was * processed and the value of @len means processes to completion). */ static __always_inline size_t iterate_and_advance_kernel(struct iov_iter *iter, size_t len, void *priv, void *priv2, iov_step_f step) { if (unlikely(iter->count < len)) len = iter->count; if (unlikely(!len)) return 0; if (iov_iter_is_bvec(iter)) return iterate_bvec(iter, len, priv, priv2, step); if (iov_iter_is_kvec(iter)) return iterate_kvec(iter, len, priv, priv2, step); if (iov_iter_is_folioq(iter)) return iterate_folioq(iter, len, priv, priv2, step); if (iov_iter_is_xarray(iter)) return iterate_xarray(iter, len, priv, priv2, step); return iterate_discard(iter, len, priv, priv2, step); } #endif /* _LINUX_IOV_ITER_H */ |
| 58 | 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 | // SPDX-License-Identifier: GPL-2.0-only /* (C) 1999-2001 Paul `Rusty' Russell * (C) 2002-2004 Netfilter Core Team <coreteam@netfilter.org> * (C) 2006-2010 Patrick McHardy <kaber@trash.net> */ #include <linux/types.h> #include <linux/timer.h> #include <linux/netfilter.h> #include <linux/in.h> #include <linux/icmp.h> #include <linux/seq_file.h> #include <net/ip.h> #include <net/checksum.h> #include <linux/netfilter_ipv4.h> #include <net/netfilter/nf_conntrack_tuple.h> #include <net/netfilter/nf_conntrack_l4proto.h> #include <net/netfilter/nf_conntrack_core.h> #include <net/netfilter/nf_conntrack_timeout.h> #include <net/netfilter/nf_conntrack_zones.h> #include <net/netfilter/nf_log.h> #include "nf_internals.h" static const unsigned int nf_ct_icmp_timeout = 30*HZ; bool icmp_pkt_to_tuple(const struct sk_buff *skb, unsigned int dataoff, struct net *net, struct nf_conntrack_tuple *tuple) { const struct icmphdr *hp; struct icmphdr _hdr; hp = skb_header_pointer(skb, dataoff, sizeof(_hdr), &_hdr); if (hp == NULL) return false; tuple->dst.u.icmp.type = hp->type; tuple->src.u.icmp.id = hp->un.echo.id; tuple->dst.u.icmp.code = hp->code; return true; } /* Add 1; spaces filled with 0. */ static const u_int8_t invmap[] = { [ICMP_ECHO] = ICMP_ECHOREPLY + 1, [ICMP_ECHOREPLY] = ICMP_ECHO + 1, [ICMP_TIMESTAMP] = ICMP_TIMESTAMPREPLY + 1, [ICMP_TIMESTAMPREPLY] = ICMP_TIMESTAMP + 1, [ICMP_INFO_REQUEST] = ICMP_INFO_REPLY + 1, [ICMP_INFO_REPLY] = ICMP_INFO_REQUEST + 1, [ICMP_ADDRESS] = ICMP_ADDRESSREPLY + 1, [ICMP_ADDRESSREPLY] = ICMP_ADDRESS + 1 }; bool nf_conntrack_invert_icmp_tuple(struct nf_conntrack_tuple *tuple, const struct nf_conntrack_tuple *orig) { if (orig->dst.u.icmp.type >= sizeof(invmap) || !invmap[orig->dst.u.icmp.type]) return false; tuple->src.u.icmp.id = orig->src.u.icmp.id; tuple->dst.u.icmp.type = invmap[orig->dst.u.icmp.type] - 1; tuple->dst.u.icmp.code = orig->dst.u.icmp.code; return true; } /* Returns verdict for packet, or -1 for invalid. */ int nf_conntrack_icmp_packet(struct nf_conn *ct, struct sk_buff *skb, enum ip_conntrack_info ctinfo, const struct nf_hook_state *state) { /* Do not immediately delete the connection after the first successful reply to avoid excessive conntrackd traffic and also to handle correctly ICMP echo reply duplicates. */ unsigned int *timeout = nf_ct_timeout_lookup(ct); static const u_int8_t valid_new[] = { [ICMP_ECHO] = 1, [ICMP_TIMESTAMP] = 1, [ICMP_INFO_REQUEST] = 1, [ICMP_ADDRESS] = 1 }; if (state->pf != NFPROTO_IPV4) return -NF_ACCEPT; if (ct->tuplehash[0].tuple.dst.u.icmp.type >= sizeof(valid_new) || !valid_new[ct->tuplehash[0].tuple.dst.u.icmp.type]) { /* Can't create a new ICMP `conn' with this. */ pr_debug("icmp: can't create new conn with type %u\n", ct->tuplehash[0].tuple.dst.u.icmp.type); nf_ct_dump_tuple_ip(&ct->tuplehash[0].tuple); return -NF_ACCEPT; } if (!timeout) timeout = &nf_icmp_pernet(nf_ct_net(ct))->timeout; nf_ct_refresh_acct(ct, ctinfo, skb, *timeout); return NF_ACCEPT; } /* Check inner header is related to any of the existing connections */ int nf_conntrack_inet_error(struct nf_conn *tmpl, struct sk_buff *skb, unsigned int dataoff, const struct nf_hook_state *state, u8 l4proto, union nf_inet_addr *outer_daddr) { struct nf_conntrack_tuple innertuple, origtuple; const struct nf_conntrack_tuple_hash *h; const struct nf_conntrack_zone *zone; enum ip_conntrack_info ctinfo; struct nf_conntrack_zone tmp; union nf_inet_addr *ct_daddr; enum ip_conntrack_dir dir; struct nf_conn *ct; WARN_ON(skb_nfct(skb)); zone = nf_ct_zone_tmpl(tmpl, skb, &tmp); /* Are they talking about one of our connections? */ if (!nf_ct_get_tuplepr(skb, dataoff, state->pf, state->net, &origtuple)) return -NF_ACCEPT; /* Ordinarily, we'd expect the inverted tupleproto, but it's been preserved inside the ICMP. */ if (!nf_ct_invert_tuple(&innertuple, &origtuple)) return -NF_ACCEPT; h = nf_conntrack_find_get(state->net, zone, &innertuple); if (!h) return -NF_ACCEPT; /* Consider: A -> T (=This machine) -> B * Conntrack entry will look like this: * Original: A->B * Reply: B->T (SNAT case) OR A * * When this function runs, we got packet that looks like this: * iphdr|icmphdr|inner_iphdr|l4header (tcp, udp, ..). * * Above nf_conntrack_find_get() makes lookup based on inner_hdr, * so we should expect that destination of the found connection * matches outer header destination address. * * In above example, we can consider these two cases: * 1. Error coming in reply direction from B or M (middle box) to * T (SNAT case) or A. * Inner saddr will be B, dst will be T or A. * The found conntrack will be reply tuple (B->T/A). * 2. Error coming in original direction from A or M to B. * Inner saddr will be A, inner daddr will be B. * The found conntrack will be original tuple (A->B). * * In both cases, conntrack[dir].dst == inner.dst. * * A bogus packet could look like this: * Inner: B->T * Outer: B->X (other machine reachable by T). * * In this case, lookup yields connection A->B and will * set packet from B->X as *RELATED*, even though no connection * from X was ever seen. */ ct = nf_ct_tuplehash_to_ctrack(h); dir = NF_CT_DIRECTION(h); ct_daddr = &ct->tuplehash[dir].tuple.dst.u3; if (!nf_inet_addr_cmp(outer_daddr, ct_daddr)) { if (state->pf == AF_INET) { nf_l4proto_log_invalid(skb, state, l4proto, "outer daddr %pI4 != inner %pI4", &outer_daddr->ip, &ct_daddr->ip); } else if (state->pf == AF_INET6) { nf_l4proto_log_invalid(skb, state, l4proto, "outer daddr %pI6 != inner %pI6", &outer_daddr->ip6, &ct_daddr->ip6); } nf_ct_put(ct); return -NF_ACCEPT; } ctinfo = IP_CT_RELATED; if (dir == IP_CT_DIR_REPLY) ctinfo += IP_CT_IS_REPLY; /* Update skb to refer to this connection */ nf_ct_set(skb, ct, ctinfo); return NF_ACCEPT; } static void icmp_error_log(const struct sk_buff *skb, const struct nf_hook_state *state, const char *msg) { nf_l4proto_log_invalid(skb, state, IPPROTO_ICMP, "%s", msg); } /* Small and modified version of icmp_rcv */ int nf_conntrack_icmpv4_error(struct nf_conn *tmpl, struct sk_buff *skb, unsigned int dataoff, const struct nf_hook_state *state) { union nf_inet_addr outer_daddr; const struct icmphdr *icmph; struct icmphdr _ih; /* Not enough header? */ icmph = skb_header_pointer(skb, dataoff, sizeof(_ih), &_ih); if (icmph == NULL) { icmp_error_log(skb, state, "short packet"); return -NF_ACCEPT; } /* See nf_conntrack_proto_tcp.c */ if (state->net->ct.sysctl_checksum && state->hook == NF_INET_PRE_ROUTING && nf_ip_checksum(skb, state->hook, dataoff, IPPROTO_ICMP)) { icmp_error_log(skb, state, "bad hw icmp checksum"); return -NF_ACCEPT; } /* * 18 is the highest 'known' ICMP type. Anything else is a mystery * * RFC 1122: 3.2.2 Unknown ICMP messages types MUST be silently * discarded. */ if (icmph->type > NR_ICMP_TYPES) { icmp_error_log(skb, state, "invalid icmp type"); return -NF_ACCEPT; } /* Need to track icmp error message? */ if (!icmp_is_err(icmph->type)) return NF_ACCEPT; memset(&outer_daddr, 0, sizeof(outer_daddr)); outer_daddr.ip = ip_hdr(skb)->daddr; dataoff += sizeof(*icmph); return nf_conntrack_inet_error(tmpl, skb, dataoff, state, IPPROTO_ICMP, &outer_daddr); } #if IS_ENABLED(CONFIG_NF_CT_NETLINK) #include <linux/netfilter/nfnetlink.h> #include <linux/netfilter/nfnetlink_conntrack.h> static int icmp_tuple_to_nlattr(struct sk_buff *skb, const struct nf_conntrack_tuple *t) { if (nla_put_be16(skb, CTA_PROTO_ICMP_ID, t->src.u.icmp.id) || nla_put_u8(skb, CTA_PROTO_ICMP_TYPE, t->dst.u.icmp.type) || nla_put_u8(skb, CTA_PROTO_ICMP_CODE, t->dst.u.icmp.code)) goto nla_put_failure; return 0; nla_put_failure: return -1; } static const struct nla_policy icmp_nla_policy[CTA_PROTO_MAX+1] = { [CTA_PROTO_ICMP_TYPE] = { .type = NLA_U8 }, [CTA_PROTO_ICMP_CODE] = { .type = NLA_U8 }, [CTA_PROTO_ICMP_ID] = { .type = NLA_U16 }, }; static int icmp_nlattr_to_tuple(struct nlattr *tb[], struct nf_conntrack_tuple *tuple, u_int32_t flags) { if (flags & CTA_FILTER_FLAG(CTA_PROTO_ICMP_TYPE)) { if (!tb[CTA_PROTO_ICMP_TYPE]) return -EINVAL; tuple->dst.u.icmp.type = nla_get_u8(tb[CTA_PROTO_ICMP_TYPE]); if (tuple->dst.u.icmp.type >= sizeof(invmap) || !invmap[tuple->dst.u.icmp.type]) return -EINVAL; } if (flags & CTA_FILTER_FLAG(CTA_PROTO_ICMP_CODE)) { if (!tb[CTA_PROTO_ICMP_CODE]) return -EINVAL; tuple->dst.u.icmp.code = nla_get_u8(tb[CTA_PROTO_ICMP_CODE]); } if (flags & CTA_FILTER_FLAG(CTA_PROTO_ICMP_ID)) { if (!tb[CTA_PROTO_ICMP_ID]) return -EINVAL; tuple->src.u.icmp.id = nla_get_be16(tb[CTA_PROTO_ICMP_ID]); } return 0; } static unsigned int icmp_nlattr_tuple_size(void) { static unsigned int size __read_mostly; if (!size) size = nla_policy_len(icmp_nla_policy, CTA_PROTO_MAX + 1); return size; } #endif #ifdef CONFIG_NF_CONNTRACK_TIMEOUT #include <linux/netfilter/nfnetlink.h> #include <linux/netfilter/nfnetlink_cttimeout.h> static int icmp_timeout_nlattr_to_obj(struct nlattr *tb[], struct net *net, void *data) { unsigned int *timeout = data; struct nf_icmp_net *in = nf_icmp_pernet(net); if (tb[CTA_TIMEOUT_ICMP_TIMEOUT]) { if (!timeout) timeout = &in->timeout; *timeout = ntohl(nla_get_be32(tb[CTA_TIMEOUT_ICMP_TIMEOUT])) * HZ; } else if (timeout) { /* Set default ICMP timeout. */ *timeout = in->timeout; } return 0; } static int icmp_timeout_obj_to_nlattr(struct sk_buff *skb, const void *data) { const unsigned int *timeout = data; if (nla_put_be32(skb, CTA_TIMEOUT_ICMP_TIMEOUT, htonl(*timeout / HZ))) goto nla_put_failure; return 0; nla_put_failure: return -ENOSPC; } static const struct nla_policy icmp_timeout_nla_policy[CTA_TIMEOUT_ICMP_MAX+1] = { [CTA_TIMEOUT_ICMP_TIMEOUT] = { .type = NLA_U32 }, }; #endif /* CONFIG_NF_CONNTRACK_TIMEOUT */ void nf_conntrack_icmp_init_net(struct net *net) { struct nf_icmp_net *in = nf_icmp_pernet(net); in->timeout = nf_ct_icmp_timeout; } const struct nf_conntrack_l4proto nf_conntrack_l4proto_icmp = { .l4proto = IPPROTO_ICMP, #if IS_ENABLED(CONFIG_NF_CT_NETLINK) .tuple_to_nlattr = icmp_tuple_to_nlattr, .nlattr_tuple_size = icmp_nlattr_tuple_size, .nlattr_to_tuple = icmp_nlattr_to_tuple, .nla_policy = icmp_nla_policy, #endif #ifdef CONFIG_NF_CONNTRACK_TIMEOUT .ctnl_timeout = { .nlattr_to_obj = icmp_timeout_nlattr_to_obj, .obj_to_nlattr = icmp_timeout_obj_to_nlattr, .nlattr_max = CTA_TIMEOUT_ICMP_MAX, .obj_size = sizeof(unsigned int), .nla_policy = icmp_timeout_nla_policy, }, #endif /* CONFIG_NF_CONNTRACK_TIMEOUT */ }; |
| 673 86 85 41 84 85 85 85 413 568 410 369 109 109 108 9 1 9 301 1 785 | 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 | /* SPDX-License-Identifier: GPL-2.0-or-later */ /* * Linux INET6 implementation * * Authors: * Pedro Roque <roque@di.fc.ul.pt> */ #ifndef _IP6_FIB_H #define _IP6_FIB_H #include <linux/ipv6_route.h> #include <linux/rtnetlink.h> #include <linux/spinlock.h> #include <linux/notifier.h> #include <net/dst.h> #include <net/flow.h> #include <net/ip_fib.h> #include <net/netlink.h> #include <net/inetpeer.h> #include <net/fib_notifier.h> #include <linux/indirect_call_wrapper.h> #include <uapi/linux/bpf.h> #ifdef CONFIG_IPV6_MULTIPLE_TABLES #define FIB6_TABLE_HASHSZ 256 #else #define FIB6_TABLE_HASHSZ 1 #endif #define RT6_DEBUG 2 struct rt6_info; struct fib6_info; struct fib6_config { u32 fc_table; u32 fc_metric; int fc_dst_len; int fc_src_len; int fc_ifindex; u32 fc_flags; u32 fc_protocol; u16 fc_type; /* only 8 bits are used */ u16 fc_delete_all_nh : 1, fc_ignore_dev_down:1, __unused : 14; u32 fc_nh_id; struct in6_addr fc_dst; struct in6_addr fc_src; struct in6_addr fc_prefsrc; struct in6_addr fc_gateway; unsigned long fc_expires; struct nlattr *fc_mx; int fc_mx_len; int fc_mp_len; struct nlattr *fc_mp; struct nl_info fc_nlinfo; struct nlattr *fc_encap; u16 fc_encap_type; bool fc_is_fdb; }; struct fib6_node { struct fib6_node __rcu *parent; struct fib6_node __rcu *left; struct fib6_node __rcu *right; #ifdef CONFIG_IPV6_SUBTREES struct fib6_node __rcu *subtree; #endif struct fib6_info __rcu *leaf; __u16 fn_bit; /* bit key */ __u16 fn_flags; int fn_sernum; struct fib6_info __rcu *rr_ptr; struct rcu_head rcu; }; struct fib6_gc_args { int timeout; int more; }; #ifndef CONFIG_IPV6_SUBTREES #define FIB6_SUBTREE(fn) NULL static inline bool fib6_routes_require_src(const struct net *net) { return false; } static inline void fib6_routes_require_src_inc(struct net *net) {} static inline void fib6_routes_require_src_dec(struct net *net) {} #else static inline bool fib6_routes_require_src(const struct net *net) { return net->ipv6.fib6_routes_require_src > 0; } static inline void fib6_routes_require_src_inc(struct net *net) { net->ipv6.fib6_routes_require_src++; } static inline void fib6_routes_require_src_dec(struct net *net) { net->ipv6.fib6_routes_require_src--; } #define FIB6_SUBTREE(fn) (rcu_dereference_protected((fn)->subtree, 1)) #endif /* * routing information * */ struct rt6key { struct in6_addr addr; int plen; }; struct fib6_table; struct rt6_exception_bucket { struct hlist_head chain; int depth; }; struct rt6_exception { struct hlist_node hlist; struct rt6_info *rt6i; unsigned long stamp; struct rcu_head rcu; }; #define FIB6_EXCEPTION_BUCKET_SIZE_SHIFT 10 #define FIB6_EXCEPTION_BUCKET_SIZE (1 << FIB6_EXCEPTION_BUCKET_SIZE_SHIFT) #define FIB6_MAX_DEPTH 5 struct fib6_nh { struct fib_nh_common nh_common; #ifdef CONFIG_IPV6_ROUTER_PREF unsigned long last_probe; #endif struct rt6_info * __percpu *rt6i_pcpu; struct rt6_exception_bucket __rcu *rt6i_exception_bucket; }; struct fib6_info { struct fib6_table *fib6_table; struct fib6_info __rcu *fib6_next; struct fib6_node __rcu *fib6_node; /* Multipath routes: * siblings is a list of fib6_info that have the same metric/weight, * destination, but not the same gateway. nsiblings is just a cache * to speed up lookup. */ union { struct list_head fib6_siblings; struct list_head nh_list; }; unsigned int fib6_nsiblings; refcount_t fib6_ref; unsigned long expires; struct hlist_node gc_link; struct dst_metrics *fib6_metrics; #define fib6_pmtu fib6_metrics->metrics[RTAX_MTU-1] struct rt6key fib6_dst; u32 fib6_flags; struct rt6key fib6_src; struct rt6key fib6_prefsrc; u32 fib6_metric; u8 fib6_protocol; u8 fib6_type; u8 offload; u8 trap; u8 offload_failed; u8 should_flush:1, dst_nocount:1, dst_nopolicy:1, fib6_destroying:1, unused:4; struct rcu_head rcu; struct nexthop *nh; struct fib6_nh fib6_nh[]; }; struct rt6_info { struct dst_entry dst; struct fib6_info __rcu *from; int sernum; struct rt6key rt6i_dst; struct rt6key rt6i_src; struct in6_addr rt6i_gateway; struct inet6_dev *rt6i_idev; u32 rt6i_flags; /* more non-fragment space at head required */ unsigned short rt6i_nfheader_len; }; struct fib6_result { struct fib6_nh *nh; struct fib6_info *f6i; u32 fib6_flags; u8 fib6_type; struct rt6_info *rt6; }; #define for_each_fib6_node_rt_rcu(fn) \ for (rt = rcu_dereference((fn)->leaf); rt; \ rt = rcu_dereference(rt->fib6_next)) #define for_each_fib6_walker_rt(w) \ for (rt = (w)->leaf; rt; \ rt = rcu_dereference_protected(rt->fib6_next, 1)) #define dst_rt6_info(_ptr) container_of_const(_ptr, struct rt6_info, dst) static inline struct inet6_dev *ip6_dst_idev(const struct dst_entry *dst) { return dst_rt6_info(dst)->rt6i_idev; } static inline bool fib6_requires_src(const struct fib6_info *rt) { return rt->fib6_src.plen > 0; } /* The callers should hold f6i->fib6_table->tb6_lock if a route has ever * been added to a table before. */ static inline void fib6_clean_expires(struct fib6_info *f6i) { f6i->fib6_flags &= ~RTF_EXPIRES; f6i->expires = 0; } /* The callers should hold f6i->fib6_table->tb6_lock if a route has ever * been added to a table before. */ static inline void fib6_set_expires(struct fib6_info *f6i, unsigned long expires) { f6i->expires = expires; f6i->fib6_flags |= RTF_EXPIRES; } static inline bool fib6_check_expired(const struct fib6_info *f6i) { if (f6i->fib6_flags & RTF_EXPIRES) return time_after(jiffies, f6i->expires); return false; } /* Function to safely get fn->fn_sernum for passed in rt * and store result in passed in cookie. * Return true if we can get cookie safely * Return false if not */ static inline bool fib6_get_cookie_safe(const struct fib6_info *f6i, u32 *cookie) { struct fib6_node *fn; bool status = false; fn = rcu_dereference(f6i->fib6_node); if (fn) { *cookie = READ_ONCE(fn->fn_sernum); /* pairs with smp_wmb() in __fib6_update_sernum_upto_root() */ smp_rmb(); status = true; } return status; } static inline u32 rt6_get_cookie(const struct rt6_info *rt) { struct fib6_info *from; u32 cookie = 0; if (rt->sernum) return rt->sernum; rcu_read_lock(); from = rcu_dereference(rt->from); if (from) fib6_get_cookie_safe(from, &cookie); rcu_read_unlock(); return cookie; } static inline void ip6_rt_put(struct rt6_info *rt) { /* dst_release() accepts a NULL parameter. * We rely on dst being first structure in struct rt6_info */ BUILD_BUG_ON(offsetof(struct rt6_info, dst) != 0); dst_release(&rt->dst); } struct fib6_info *fib6_info_alloc(gfp_t gfp_flags, bool with_fib6_nh); void fib6_info_destroy_rcu(struct rcu_head *head); static inline void fib6_info_hold(struct fib6_info *f6i) { refcount_inc(&f6i->fib6_ref); } static inline bool fib6_info_hold_safe(struct fib6_info *f6i) { return refcount_inc_not_zero(&f6i->fib6_ref); } static inline void fib6_info_release(struct fib6_info *f6i) { if (f6i && refcount_dec_and_test(&f6i->fib6_ref)) { DEBUG_NET_WARN_ON_ONCE(!hlist_unhashed(&f6i->gc_link)); call_rcu_hurry(&f6i->rcu, fib6_info_destroy_rcu); } } enum fib6_walk_state { #ifdef CONFIG_IPV6_SUBTREES FWS_S, #endif FWS_L, FWS_R, FWS_C, FWS_U }; struct fib6_walker { struct list_head lh; struct fib6_node *root, *node; struct fib6_info *leaf; enum fib6_walk_state state; unsigned int skip; unsigned int count; unsigned int skip_in_node; int (*func)(struct fib6_walker *); void *args; }; struct rt6_statistics { __u32 fib_nodes; /* all fib6 nodes */ __u32 fib_route_nodes; /* intermediate nodes */ __u32 fib_rt_entries; /* rt entries in fib table */ __u32 fib_rt_cache; /* cached rt entries in exception table */ __u32 fib_discarded_routes; /* total number of routes delete */ /* The following stat is not protected by any lock */ atomic_t fib_rt_alloc; /* total number of routes alloced */ }; #define RTN_TL_ROOT 0x0001 #define RTN_ROOT 0x0002 /* tree root node */ #define RTN_RTINFO 0x0004 /* node with valid routing info */ /* * priority levels (or metrics) * */ struct fib6_table { struct hlist_node tb6_hlist; u32 tb6_id; spinlock_t tb6_lock; struct fib6_node tb6_root; struct inet_peer_base tb6_peers; unsigned int flags; unsigned int fib_seq; /* writes protected by rtnl_mutex */ struct hlist_head tb6_gc_hlist; /* GC candidates */ #define RT6_TABLE_HAS_DFLT_ROUTER BIT(0) }; #define RT6_TABLE_UNSPEC RT_TABLE_UNSPEC #define RT6_TABLE_MAIN RT_TABLE_MAIN #define RT6_TABLE_DFLT RT6_TABLE_MAIN #define RT6_TABLE_INFO RT6_TABLE_MAIN #define RT6_TABLE_PREFIX RT6_TABLE_MAIN #ifdef CONFIG_IPV6_MULTIPLE_TABLES #define FIB6_TABLE_MIN 1 #define FIB6_TABLE_MAX RT_TABLE_MAX #define RT6_TABLE_LOCAL RT_TABLE_LOCAL #else #define FIB6_TABLE_MIN RT_TABLE_MAIN #define FIB6_TABLE_MAX FIB6_TABLE_MIN #define RT6_TABLE_LOCAL RT6_TABLE_MAIN #endif typedef struct rt6_info *(*pol_lookup_t)(struct net *, struct fib6_table *, struct flowi6 *, const struct sk_buff *, int); struct fib6_entry_notifier_info { struct fib_notifier_info info; /* must be first */ struct fib6_info *rt; unsigned int nsiblings; }; /* * exported functions */ struct fib6_table *fib6_get_table(struct net *net, u32 id); struct fib6_table *fib6_new_table(struct net *net, u32 id); struct dst_entry *fib6_rule_lookup(struct net *net, struct flowi6 *fl6, const struct sk_buff *skb, int flags, pol_lookup_t lookup); /* called with rcu lock held; can return error pointer * caller needs to select path */ int fib6_lookup(struct net *net, int oif, struct flowi6 *fl6, struct fib6_result *res, int flags); /* called with rcu lock held; caller needs to select path */ int fib6_table_lookup(struct net *net, struct fib6_table *table, int oif, struct flowi6 *fl6, struct fib6_result *res, int strict); void fib6_select_path(const struct net *net, struct fib6_result *res, struct flowi6 *fl6, int oif, bool have_oif_match, const struct sk_buff *skb, int strict); struct fib6_node *fib6_node_lookup(struct fib6_node *root, const struct in6_addr *daddr, const struct in6_addr *saddr); 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); void fib6_clean_all(struct net *net, int (*func)(struct fib6_info *, void *arg), void *arg); void fib6_clean_all_skip_notify(struct net *net, int (*func)(struct fib6_info *, void *arg), void *arg); int fib6_add(struct fib6_node *root, struct fib6_info *rt, struct nl_info *info, struct netlink_ext_ack *extack); int fib6_del(struct fib6_info *rt, struct nl_info *info); static inline void rt6_get_prefsrc(const struct rt6_info *rt, struct in6_addr *addr) { const struct fib6_info *from; rcu_read_lock(); from = rcu_dereference(rt->from); if (from) *addr = from->fib6_prefsrc.addr; else *addr = in6addr_any; rcu_read_unlock(); } int fib6_nh_init(struct net *net, struct fib6_nh *fib6_nh, struct fib6_config *cfg, gfp_t gfp_flags, struct netlink_ext_ack *extack); void fib6_nh_release(struct fib6_nh *fib6_nh); void fib6_nh_release_dsts(struct fib6_nh *fib6_nh); int call_fib6_entry_notifiers(struct net *net, enum fib_event_type event_type, struct fib6_info *rt, struct netlink_ext_ack *extack); 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); int call_fib6_entry_notifiers_replace(struct net *net, struct fib6_info *rt); void fib6_rt_update(struct net *net, struct fib6_info *rt, struct nl_info *info); void inet6_rt_notify(int event, struct fib6_info *rt, struct nl_info *info, unsigned int flags); void fib6_run_gc(unsigned long expires, struct net *net, bool force); void fib6_gc_cleanup(void); int fib6_init(void); /* Add the route to the gc list if it is not already there * * The callers should hold f6i->fib6_table->tb6_lock. */ static inline void fib6_add_gc_list(struct fib6_info *f6i) { /* If fib6_node is null, the f6i is not in (or removed from) the * table. * * There is a gap between finding the f6i from the table and * calling this function without the protection of the tb6_lock. * This check makes sure the f6i is not added to the gc list when * it is not on the table. */ if (!rcu_dereference_protected(f6i->fib6_node, lockdep_is_held(&f6i->fib6_table->tb6_lock))) return; if (hlist_unhashed(&f6i->gc_link)) hlist_add_head(&f6i->gc_link, &f6i->fib6_table->tb6_gc_hlist); } /* Remove the route from the gc list if it is on the list. * * The callers should hold f6i->fib6_table->tb6_lock. */ static inline void fib6_remove_gc_list(struct fib6_info *f6i) { if (!hlist_unhashed(&f6i->gc_link)) hlist_del_init(&f6i->gc_link); } struct ipv6_route_iter { struct seq_net_private p; struct fib6_walker w; loff_t skip; struct fib6_table *tbl; int sernum; }; extern const struct seq_operations ipv6_route_seq_ops; int call_fib6_notifier(struct notifier_block *nb, enum fib_event_type event_type, struct fib_notifier_info *info); int call_fib6_notifiers(struct net *net, enum fib_event_type event_type, struct fib_notifier_info *info); int __net_init fib6_notifier_init(struct net *net); void __net_exit fib6_notifier_exit(struct net *net); unsigned int fib6_tables_seq_read(const struct net *net); int fib6_tables_dump(struct net *net, struct notifier_block *nb, struct netlink_ext_ack *extack); void fib6_update_sernum(struct net *net, struct fib6_info *rt); void fib6_update_sernum_upto_root(struct net *net, struct fib6_info *rt); void fib6_update_sernum_stub(struct net *net, struct fib6_info *f6i); void fib6_metric_set(struct fib6_info *f6i, int metric, u32 val); static inline bool fib6_metric_locked(struct fib6_info *f6i, int metric) { return !!(f6i->fib6_metrics->metrics[RTAX_LOCK - 1] & (1 << metric)); } void fib6_info_hw_flags_set(struct net *net, struct fib6_info *f6i, bool offload, bool trap, bool offload_failed); #if IS_BUILTIN(CONFIG_IPV6) && defined(CONFIG_BPF_SYSCALL) struct bpf_iter__ipv6_route { __bpf_md_ptr(struct bpf_iter_meta *, meta); __bpf_md_ptr(struct fib6_info *, rt); }; #endif INDIRECT_CALLABLE_DECLARE(struct rt6_info *ip6_pol_route_output(struct net *net, struct fib6_table *table, struct flowi6 *fl6, const struct sk_buff *skb, int flags)); INDIRECT_CALLABLE_DECLARE(struct rt6_info *ip6_pol_route_input(struct net *net, struct fib6_table *table, struct flowi6 *fl6, const struct sk_buff *skb, int flags)); INDIRECT_CALLABLE_DECLARE(struct rt6_info *__ip6_route_redirect(struct net *net, struct fib6_table *table, struct flowi6 *fl6, const struct sk_buff *skb, int flags)); INDIRECT_CALLABLE_DECLARE(struct rt6_info *ip6_pol_route_lookup(struct net *net, struct fib6_table *table, struct flowi6 *fl6, const struct sk_buff *skb, int flags)); static inline struct rt6_info *pol_lookup_func(pol_lookup_t lookup, struct net *net, struct fib6_table *table, struct flowi6 *fl6, const struct sk_buff *skb, int flags) { return INDIRECT_CALL_4(lookup, ip6_pol_route_output, ip6_pol_route_input, ip6_pol_route_lookup, __ip6_route_redirect, net, table, fl6, skb, flags); } #ifdef CONFIG_IPV6_MULTIPLE_TABLES static inline bool fib6_has_custom_rules(const struct net *net) { return net->ipv6.fib6_has_custom_rules; } int fib6_rules_init(void); void fib6_rules_cleanup(void); bool fib6_rule_default(const struct fib_rule *rule); int fib6_rules_dump(struct net *net, struct notifier_block *nb, struct netlink_ext_ack *extack); unsigned int fib6_rules_seq_read(const struct net *net); static inline bool fib6_rules_early_flow_dissect(struct net *net, struct sk_buff *skb, struct flowi6 *fl6, struct flow_keys *flkeys) { unsigned int flag = FLOW_DISSECTOR_F_STOP_AT_ENCAP; if (!net->ipv6.fib6_rules_require_fldissect) return false; memset(flkeys, 0, sizeof(*flkeys)); __skb_flow_dissect(net, skb, &flow_keys_dissector, flkeys, NULL, 0, 0, 0, flag); fl6->fl6_sport = flkeys->ports.src; fl6->fl6_dport = flkeys->ports.dst; fl6->flowi6_proto = flkeys->basic.ip_proto; return true; } #else static inline bool fib6_has_custom_rules(const struct net *net) { return false; } static inline int fib6_rules_init(void) { return 0; } static inline void fib6_rules_cleanup(void) { return ; } static inline bool fib6_rule_default(const struct fib_rule *rule) { return true; } static inline int fib6_rules_dump(struct net *net, struct notifier_block *nb, struct netlink_ext_ack *extack) { return 0; } static inline unsigned int fib6_rules_seq_read(const struct net *net) { return 0; } static inline bool fib6_rules_early_flow_dissect(struct net *net, struct sk_buff *skb, struct flowi6 *fl6, struct flow_keys *flkeys) { return false; } #endif #endif |
| 18 18 12 12 18 73 73 4 4 4 21 1 1 1 9 10 1 1 219 147 75 11 75 104 211 21 220 103 54 51 219 106 38 188 222 223 222 221 223 222 223 223 21 223 211 212 212 97 31 106 220 18 18 22 22 22 18 87 214 1 212 211 212 13 13 1 13 103 18 102 212 73 4 22 21 1 2 76 22 188 188 21 21 223 22 223 223 | 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 | // SPDX-License-Identifier: GPL-2.0-or-later /* SCTP kernel implementation * (C) Copyright IBM Corp. 2001, 2004 * Copyright (c) 1999 Cisco, Inc. * Copyright (c) 1999-2001 Motorola, Inc. * * This file is part of the SCTP kernel implementation * * These functions work with the state functions in sctp_sm_statefuns.c * to implement that state operations. These functions implement the * steps which require modifying existing data structures. * * Please send any bug reports or fixes you make to the * email address(es): * lksctp developers <linux-sctp@vger.kernel.org> * * Written or modified by: * La Monte H.P. Yarroll <piggy@acm.org> * Karl Knutson <karl@athena.chicago.il.us> * Jon Grimm <jgrimm@austin.ibm.com> * Hui Huang <hui.huang@nokia.com> * Dajiang Zhang <dajiang.zhang@nokia.com> * Daisy Chang <daisyc@us.ibm.com> * Sridhar Samudrala <sri@us.ibm.com> * Ardelle Fan <ardelle.fan@intel.com> */ #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt #include <linux/skbuff.h> #include <linux/types.h> #include <linux/socket.h> #include <linux/ip.h> #include <linux/gfp.h> #include <net/sock.h> #include <net/sctp/sctp.h> #include <net/sctp/sm.h> #include <net/sctp/stream_sched.h> static int sctp_cmd_interpreter(enum sctp_event_type event_type, union sctp_subtype subtype, enum sctp_state state, struct sctp_endpoint *ep, struct sctp_association *asoc, void *event_arg, enum sctp_disposition status, struct sctp_cmd_seq *commands, gfp_t gfp); static int sctp_side_effects(enum sctp_event_type event_type, union sctp_subtype subtype, enum sctp_state state, struct sctp_endpoint *ep, struct sctp_association **asoc, void *event_arg, enum sctp_disposition status, struct sctp_cmd_seq *commands, gfp_t gfp); /******************************************************************** * Helper functions ********************************************************************/ /* A helper function for delayed processing of INET ECN CE bit. */ static void sctp_do_ecn_ce_work(struct sctp_association *asoc, __u32 lowest_tsn) { /* Save the TSN away for comparison when we receive CWR */ asoc->last_ecne_tsn = lowest_tsn; asoc->need_ecne = 1; } /* Helper function for delayed processing of SCTP ECNE chunk. */ /* RFC 2960 Appendix A * * RFC 2481 details a specific bit for a sender to send in * the header of its next outbound TCP segment to indicate to * its peer that it has reduced its congestion window. This * is termed the CWR bit. For SCTP the same indication is made * by including the CWR chunk. This chunk contains one data * element, i.e. the TSN number that was sent in the ECNE chunk. * This element represents the lowest TSN number in the datagram * that was originally marked with the CE bit. */ static struct sctp_chunk *sctp_do_ecn_ecne_work(struct sctp_association *asoc, __u32 lowest_tsn, struct sctp_chunk *chunk) { struct sctp_chunk *repl; /* Our previously transmitted packet ran into some congestion * so we should take action by reducing cwnd and ssthresh * and then ACK our peer that we we've done so by * sending a CWR. */ /* First, try to determine if we want to actually lower * our cwnd variables. Only lower them if the ECNE looks more * recent than the last response. */ if (TSN_lt(asoc->last_cwr_tsn, lowest_tsn)) { struct sctp_transport *transport; /* Find which transport's congestion variables * need to be adjusted. */ transport = sctp_assoc_lookup_tsn(asoc, lowest_tsn); /* Update the congestion variables. */ if (transport) sctp_transport_lower_cwnd(transport, SCTP_LOWER_CWND_ECNE); asoc->last_cwr_tsn = lowest_tsn; } /* Always try to quiet the other end. In case of lost CWR, * resend last_cwr_tsn. */ repl = sctp_make_cwr(asoc, asoc->last_cwr_tsn, chunk); /* If we run out of memory, it will look like a lost CWR. We'll * get back in sync eventually. */ return repl; } /* Helper function to do delayed processing of ECN CWR chunk. */ static void sctp_do_ecn_cwr_work(struct sctp_association *asoc, __u32 lowest_tsn) { /* Turn off ECNE getting auto-prepended to every outgoing * packet */ asoc->need_ecne = 0; } /* Generate SACK if necessary. We call this at the end of a packet. */ static int sctp_gen_sack(struct sctp_association *asoc, int force, struct sctp_cmd_seq *commands) { struct sctp_transport *trans = asoc->peer.last_data_from; __u32 ctsn, max_tsn_seen; struct sctp_chunk *sack; int error = 0; if (force || (!trans && (asoc->param_flags & SPP_SACKDELAY_DISABLE)) || (trans && (trans->param_flags & SPP_SACKDELAY_DISABLE))) asoc->peer.sack_needed = 1; ctsn = sctp_tsnmap_get_ctsn(&asoc->peer.tsn_map); max_tsn_seen = sctp_tsnmap_get_max_tsn_seen(&asoc->peer.tsn_map); /* From 12.2 Parameters necessary per association (i.e. the TCB): * * Ack State : This flag indicates if the next received packet * : is to be responded to with a SACK. ... * : When DATA chunks are out of order, SACK's * : are not delayed (see Section 6). * * [This is actually not mentioned in Section 6, but we * implement it here anyway. --piggy] */ if (max_tsn_seen != ctsn) asoc->peer.sack_needed = 1; /* From 6.2 Acknowledgement on Reception of DATA Chunks: * * Section 4.2 of [RFC2581] SHOULD be followed. Specifically, * an acknowledgement SHOULD be generated for at least every * second packet (not every second DATA chunk) received, and * SHOULD be generated within 200 ms of the arrival of any * unacknowledged DATA chunk. ... */ if (!asoc->peer.sack_needed) { asoc->peer.sack_cnt++; /* Set the SACK delay timeout based on the * SACK delay for the last transport * data was received from, or the default * for the association. */ if (trans) { /* We will need a SACK for the next packet. */ if (asoc->peer.sack_cnt >= trans->sackfreq - 1) asoc->peer.sack_needed = 1; asoc->timeouts[SCTP_EVENT_TIMEOUT_SACK] = trans->sackdelay; } else { /* We will need a SACK for the next packet. */ if (asoc->peer.sack_cnt >= asoc->sackfreq - 1) asoc->peer.sack_needed = 1; asoc->timeouts[SCTP_EVENT_TIMEOUT_SACK] = asoc->sackdelay; } /* Restart the SACK timer. */ sctp_add_cmd_sf(commands, SCTP_CMD_TIMER_RESTART, SCTP_TO(SCTP_EVENT_TIMEOUT_SACK)); } else { __u32 old_a_rwnd = asoc->a_rwnd; asoc->a_rwnd = asoc->rwnd; sack = sctp_make_sack(asoc); if (!sack) { asoc->a_rwnd = old_a_rwnd; goto nomem; } asoc->peer.sack_needed = 0; asoc->peer.sack_cnt = 0; sctp_add_cmd_sf(commands, SCTP_CMD_REPLY, SCTP_CHUNK(sack)); /* Stop the SACK timer. */ sctp_add_cmd_sf(commands, SCTP_CMD_TIMER_STOP, SCTP_TO(SCTP_EVENT_TIMEOUT_SACK)); } return error; nomem: error = -ENOMEM; return error; } /* When the T3-RTX timer expires, it calls this function to create the * relevant state machine event. */ void sctp_generate_t3_rtx_event(struct timer_list *t) { struct sctp_transport *transport = from_timer(transport, t, T3_rtx_timer); struct sctp_association *asoc = transport->asoc; struct sock *sk = asoc->base.sk; struct net *net = sock_net(sk); int error; /* Check whether a task is in the sock. */ bh_lock_sock(sk); if (sock_owned_by_user(sk)) { pr_debug("%s: sock is busy\n", __func__); /* Try again later. */ if (!mod_timer(&transport->T3_rtx_timer, jiffies + (HZ/20))) sctp_transport_hold(transport); goto out_unlock; } /* Run through the state machine. */ error = sctp_do_sm(net, SCTP_EVENT_T_TIMEOUT, SCTP_ST_TIMEOUT(SCTP_EVENT_TIMEOUT_T3_RTX), asoc->state, asoc->ep, asoc, transport, GFP_ATOMIC); if (error) sk->sk_err = -error; out_unlock: bh_unlock_sock(sk); sctp_transport_put(transport); } /* This is a sa interface for producing timeout events. It works * for timeouts which use the association as their parameter. */ static void sctp_generate_timeout_event(struct sctp_association *asoc, enum sctp_event_timeout timeout_type) { struct sock *sk = asoc->base.sk; struct net *net = sock_net(sk); int error = 0; bh_lock_sock(sk); if (sock_owned_by_user(sk)) { pr_debug("%s: sock is busy: timer %d\n", __func__, timeout_type); /* Try again later. */ if (!mod_timer(&asoc->timers[timeout_type], jiffies + (HZ/20))) sctp_association_hold(asoc); goto out_unlock; } /* Is this association really dead and just waiting around for * the timer to let go of the reference? */ if (asoc->base.dead) goto out_unlock; /* Run through the state machine. */ error = sctp_do_sm(net, SCTP_EVENT_T_TIMEOUT, SCTP_ST_TIMEOUT(timeout_type), asoc->state, asoc->ep, asoc, (void *)timeout_type, GFP_ATOMIC); if (error) sk->sk_err = -error; out_unlock: bh_unlock_sock(sk); sctp_association_put(asoc); } static void sctp_generate_t1_cookie_event(struct timer_list *t) { struct sctp_association *asoc = from_timer(asoc, t, timers[SCTP_EVENT_TIMEOUT_T1_COOKIE]); sctp_generate_timeout_event(asoc, SCTP_EVENT_TIMEOUT_T1_COOKIE); } static void sctp_generate_t1_init_event(struct timer_list *t) { struct sctp_association *asoc = from_timer(asoc, t, timers[SCTP_EVENT_TIMEOUT_T1_INIT]); sctp_generate_timeout_event(asoc, SCTP_EVENT_TIMEOUT_T1_INIT); } static void sctp_generate_t2_shutdown_event(struct timer_list *t) { struct sctp_association *asoc = from_timer(asoc, t, timers[SCTP_EVENT_TIMEOUT_T2_SHUTDOWN]); sctp_generate_timeout_event(asoc, SCTP_EVENT_TIMEOUT_T2_SHUTDOWN); } static void sctp_generate_t4_rto_event(struct timer_list *t) { struct sctp_association *asoc = from_timer(asoc, t, timers[SCTP_EVENT_TIMEOUT_T4_RTO]); sctp_generate_timeout_event(asoc, SCTP_EVENT_TIMEOUT_T4_RTO); } static void sctp_generate_t5_shutdown_guard_event(struct timer_list *t) { struct sctp_association *asoc = from_timer(asoc, t, timers[SCTP_EVENT_TIMEOUT_T5_SHUTDOWN_GUARD]); sctp_generate_timeout_event(asoc, SCTP_EVENT_TIMEOUT_T5_SHUTDOWN_GUARD); } /* sctp_generate_t5_shutdown_guard_event() */ static void sctp_generate_autoclose_event(struct timer_list *t) { struct sctp_association *asoc = from_timer(asoc, t, timers[SCTP_EVENT_TIMEOUT_AUTOCLOSE]); sctp_generate_timeout_event(asoc, SCTP_EVENT_TIMEOUT_AUTOCLOSE); } /* Generate a heart beat event. If the sock is busy, reschedule. Make * sure that the transport is still valid. */ void sctp_generate_heartbeat_event(struct timer_list *t) { struct sctp_transport *transport = from_timer(transport, t, hb_timer); struct sctp_association *asoc = transport->asoc; struct sock *sk = asoc->base.sk; struct net *net = sock_net(sk); u32 elapsed, timeout; int error = 0; bh_lock_sock(sk); if (sock_owned_by_user(sk)) { pr_debug("%s: sock is busy\n", __func__); /* Try again later. */ if (!mod_timer(&transport->hb_timer, jiffies + (HZ/20))) sctp_transport_hold(transport); goto out_unlock; } /* Check if we should still send the heartbeat or reschedule */ elapsed = jiffies - transport->last_time_sent; timeout = sctp_transport_timeout(transport); if (elapsed < timeout) { elapsed = timeout - elapsed; if (!mod_timer(&transport->hb_timer, jiffies + elapsed)) sctp_transport_hold(transport); goto out_unlock; } error = sctp_do_sm(net, SCTP_EVENT_T_TIMEOUT, SCTP_ST_TIMEOUT(SCTP_EVENT_TIMEOUT_HEARTBEAT), asoc->state, asoc->ep, asoc, transport, GFP_ATOMIC); if (error) sk->sk_err = -error; out_unlock: bh_unlock_sock(sk); sctp_transport_put(transport); } /* Handle the timeout of the ICMP protocol unreachable timer. Trigger * the correct state machine transition that will close the association. */ void sctp_generate_proto_unreach_event(struct timer_list *t) { struct sctp_transport *transport = from_timer(transport, t, proto_unreach_timer); struct sctp_association *asoc = transport->asoc; struct sock *sk = asoc->base.sk; struct net *net = sock_net(sk); bh_lock_sock(sk); if (sock_owned_by_user(sk)) { pr_debug("%s: sock is busy\n", __func__); /* Try again later. */ if (!mod_timer(&transport->proto_unreach_timer, jiffies + (HZ/20))) sctp_transport_hold(transport); goto out_unlock; } /* Is this structure just waiting around for us to actually * get destroyed? */ if (asoc->base.dead) goto out_unlock; sctp_do_sm(net, SCTP_EVENT_T_OTHER, SCTP_ST_OTHER(SCTP_EVENT_ICMP_PROTO_UNREACH), asoc->state, asoc->ep, asoc, transport, GFP_ATOMIC); out_unlock: bh_unlock_sock(sk); sctp_transport_put(transport); } /* Handle the timeout of the RE-CONFIG timer. */ void sctp_generate_reconf_event(struct timer_list *t) { struct sctp_transport *transport = from_timer(transport, t, reconf_timer); struct sctp_association *asoc = transport->asoc; struct sock *sk = asoc->base.sk; struct net *net = sock_net(sk); int error = 0; bh_lock_sock(sk); if (sock_owned_by_user(sk)) { pr_debug("%s: sock is busy\n", __func__); /* Try again later. */ if (!mod_timer(&transport->reconf_timer, jiffies + (HZ / 20))) sctp_transport_hold(transport); goto out_unlock; } /* This happens when the response arrives after the timer is triggered. */ if (!asoc->strreset_chunk) goto out_unlock; error = sctp_do_sm(net, SCTP_EVENT_T_TIMEOUT, SCTP_ST_TIMEOUT(SCTP_EVENT_TIMEOUT_RECONF), asoc->state, asoc->ep, asoc, transport, GFP_ATOMIC); if (error) sk->sk_err = -error; out_unlock: bh_unlock_sock(sk); sctp_transport_put(transport); } /* Handle the timeout of the probe timer. */ void sctp_generate_probe_event(struct timer_list *t) { struct sctp_transport *transport = from_timer(transport, t, probe_timer); struct sctp_association *asoc = transport->asoc; struct sock *sk = asoc->base.sk; struct net *net = sock_net(sk); int error = 0; bh_lock_sock(sk); if (sock_owned_by_user(sk)) { pr_debug("%s: sock is busy\n", __func__); /* Try again later. */ if (!mod_timer(&transport->probe_timer, jiffies + (HZ / 20))) sctp_transport_hold(transport); goto out_unlock; } error = sctp_do_sm(net, SCTP_EVENT_T_TIMEOUT, SCTP_ST_TIMEOUT(SCTP_EVENT_TIMEOUT_PROBE), asoc->state, asoc->ep, asoc, transport, GFP_ATOMIC); if (error) sk->sk_err = -error; out_unlock: bh_unlock_sock(sk); sctp_transport_put(transport); } /* Inject a SACK Timeout event into the state machine. */ static void sctp_generate_sack_event(struct timer_list *t) { struct sctp_association *asoc = from_timer(asoc, t, timers[SCTP_EVENT_TIMEOUT_SACK]); sctp_generate_timeout_event(asoc, SCTP_EVENT_TIMEOUT_SACK); } sctp_timer_event_t *sctp_timer_events[SCTP_NUM_TIMEOUT_TYPES] = { [SCTP_EVENT_TIMEOUT_NONE] = NULL, [SCTP_EVENT_TIMEOUT_T1_COOKIE] = sctp_generate_t1_cookie_event, [SCTP_EVENT_TIMEOUT_T1_INIT] = sctp_generate_t1_init_event, [SCTP_EVENT_TIMEOUT_T2_SHUTDOWN] = sctp_generate_t2_shutdown_event, [SCTP_EVENT_TIMEOUT_T3_RTX] = NULL, [SCTP_EVENT_TIMEOUT_T4_RTO] = sctp_generate_t4_rto_event, [SCTP_EVENT_TIMEOUT_T5_SHUTDOWN_GUARD] = sctp_generate_t5_shutdown_guard_event, [SCTP_EVENT_TIMEOUT_HEARTBEAT] = NULL, [SCTP_EVENT_TIMEOUT_RECONF] = NULL, [SCTP_EVENT_TIMEOUT_SACK] = sctp_generate_sack_event, [SCTP_EVENT_TIMEOUT_AUTOCLOSE] = sctp_generate_autoclose_event, }; /* RFC 2960 8.2 Path Failure Detection * * When its peer endpoint is multi-homed, an endpoint should keep a * error counter for each of the destination transport addresses of the * peer endpoint. * * Each time the T3-rtx timer expires on any address, or when a * HEARTBEAT sent to an idle address is not acknowledged within a RTO, * the error counter of that destination address will be incremented. * When the value in the error counter exceeds the protocol parameter * 'Path.Max.Retrans' of that destination address, the endpoint should * mark the destination transport address as inactive, and a * notification SHOULD be sent to the upper layer. * */ static void sctp_do_8_2_transport_strike(struct sctp_cmd_seq *commands, struct sctp_association *asoc, struct sctp_transport *transport, int is_hb) { /* The check for association's overall error counter exceeding the * threshold is done in the state function. */ /* We are here due to a timer expiration. If the timer was * not a HEARTBEAT, then normal error tracking is done. * If the timer was a heartbeat, we only increment error counts * when we already have an outstanding HEARTBEAT that has not * been acknowledged. * Additionally, some tranport states inhibit error increments. */ if (!is_hb) { asoc->overall_error_count++; if (transport->state != SCTP_INACTIVE) transport->error_count++; } else if (transport->hb_sent) { if (transport->state != SCTP_UNCONFIRMED) asoc->overall_error_count++; if (transport->state != SCTP_INACTIVE) transport->error_count++; } /* If the transport error count is greater than the pf_retrans * threshold, and less than pathmaxrtx, and if the current state * is SCTP_ACTIVE, then mark this transport as Partially Failed, * see SCTP Quick Failover Draft, section 5.1 */ if (asoc->base.net->sctp.pf_enable && transport->state == SCTP_ACTIVE && transport->error_count < transport->pathmaxrxt && transport->error_count > transport->pf_retrans) { sctp_assoc_control_transport(asoc, transport, SCTP_TRANSPORT_PF, 0); /* Update the hb timer to resend a heartbeat every rto */ sctp_transport_reset_hb_timer(transport); } if (transport->state != SCTP_INACTIVE && (transport->error_count > transport->pathmaxrxt)) { pr_debug("%s: association:%p transport addr:%pISpc failed\n", __func__, asoc, &transport->ipaddr.sa); sctp_assoc_control_transport(asoc, transport, SCTP_TRANSPORT_DOWN, SCTP_FAILED_THRESHOLD); } if (transport->error_count > transport->ps_retrans && asoc->peer.primary_path == transport && asoc->peer.active_path != transport) sctp_assoc_set_primary(asoc, asoc->peer.active_path); /* E2) For the destination address for which the timer * expires, set RTO <- RTO * 2 ("back off the timer"). The * maximum value discussed in rule C7 above (RTO.max) may be * used to provide an upper bound to this doubling operation. * * Special Case: the first HB doesn't trigger exponential backoff. * The first unacknowledged HB triggers it. We do this with a flag * that indicates that we have an outstanding HB. */ if (!is_hb || transport->hb_sent) { transport->rto = min((transport->rto * 2), transport->asoc->rto_max); sctp_max_rto(asoc, transport); } } /* Worker routine to handle INIT command failure. */ static void sctp_cmd_init_failed(struct sctp_cmd_seq *commands, struct sctp_association *asoc, unsigned int error) { struct sctp_ulpevent *event; event = sctp_ulpevent_make_assoc_change(asoc, 0, SCTP_CANT_STR_ASSOC, (__u16)error, 0, 0, NULL, GFP_ATOMIC); if (event) sctp_add_cmd_sf(commands, SCTP_CMD_EVENT_ULP, SCTP_ULPEVENT(event)); sctp_add_cmd_sf(commands, SCTP_CMD_NEW_STATE, SCTP_STATE(SCTP_STATE_CLOSED)); /* SEND_FAILED sent later when cleaning up the association. */ asoc->outqueue.error = error; sctp_add_cmd_sf(commands, SCTP_CMD_DELETE_TCB, SCTP_NULL()); } /* Worker routine to handle SCTP_CMD_ASSOC_FAILED. */ static void sctp_cmd_assoc_failed(struct sctp_cmd_seq *commands, struct sctp_association *asoc, enum sctp_event_type event_type, union sctp_subtype subtype, struct sctp_chunk *chunk, unsigned int error) { struct sctp_ulpevent *event; struct sctp_chunk *abort; /* Cancel any partial delivery in progress. */ asoc->stream.si->abort_pd(&asoc->ulpq, GFP_ATOMIC); if (event_type == SCTP_EVENT_T_CHUNK && subtype.chunk == SCTP_CID_ABORT) event = sctp_ulpevent_make_assoc_change(asoc, 0, SCTP_COMM_LOST, (__u16)error, 0, 0, chunk, GFP_ATOMIC); else event = sctp_ulpevent_make_assoc_change(asoc, 0, SCTP_COMM_LOST, (__u16)error, 0, 0, NULL, GFP_ATOMIC); if (event) sctp_add_cmd_sf(commands, SCTP_CMD_EVENT_ULP, SCTP_ULPEVENT(event)); if (asoc->overall_error_count >= asoc->max_retrans) { abort = sctp_make_violation_max_retrans(asoc, chunk); if (abort) sctp_add_cmd_sf(commands, SCTP_CMD_REPLY, SCTP_CHUNK(abort)); } sctp_add_cmd_sf(commands, SCTP_CMD_NEW_STATE, SCTP_STATE(SCTP_STATE_CLOSED)); /* SEND_FAILED sent later when cleaning up the association. */ asoc->outqueue.error = error; sctp_add_cmd_sf(commands, SCTP_CMD_DELETE_TCB, SCTP_NULL()); } /* Process an init chunk (may be real INIT/INIT-ACK or an embedded INIT * inside the cookie. In reality, this is only used for INIT-ACK processing * since all other cases use "temporary" associations and can do all * their work in statefuns directly. */ static int sctp_cmd_process_init(struct sctp_cmd_seq *commands, struct sctp_association *asoc, struct sctp_chunk *chunk, struct sctp_init_chunk *peer_init, gfp_t gfp) { int error; /* We only process the init as a sideeffect in a single * case. This is when we process the INIT-ACK. If we * fail during INIT processing (due to malloc problems), * just return the error and stop processing the stack. */ if (!sctp_process_init(asoc, chunk, sctp_source(chunk), peer_init, gfp)) error = -ENOMEM; else error = 0; return error; } /* Helper function to break out starting up of heartbeat timers. */ static void sctp_cmd_hb_timers_start(struct sctp_cmd_seq *cmds, struct sctp_association *asoc) { struct sctp_transport *t; /* Start a heartbeat timer for each transport on the association. * hold a reference on the transport to make sure none of * the needed data structures go away. */ list_for_each_entry(t, &asoc->peer.transport_addr_list, transports) sctp_transport_reset_hb_timer(t); } static void sctp_cmd_hb_timers_stop(struct sctp_cmd_seq *cmds, struct sctp_association *asoc) { struct sctp_transport *t; /* Stop all heartbeat timers. */ list_for_each_entry(t, &asoc->peer.transport_addr_list, transports) { if (del_timer(&t->hb_timer)) sctp_transport_put(t); } } /* Helper function to stop any pending T3-RTX timers */ static void sctp_cmd_t3_rtx_timers_stop(struct sctp_cmd_seq *cmds, struct sctp_association *asoc) { struct sctp_transport *t; list_for_each_entry(t, &asoc->peer.transport_addr_list, transports) { if (del_timer(&t->T3_rtx_timer)) sctp_transport_put(t); } } /* Helper function to handle the reception of an HEARTBEAT ACK. */ static void sctp_cmd_transport_on(struct sctp_cmd_seq *cmds, struct sctp_association *asoc, struct sctp_transport *t, struct sctp_chunk *chunk) { struct sctp_sender_hb_info *hbinfo; int was_unconfirmed = 0; /* 8.3 Upon the receipt of the HEARTBEAT ACK, the sender of the * HEARTBEAT should clear the error counter of the destination * transport address to which the HEARTBEAT was sent. */ t->error_count = 0; /* * Although RFC4960 specifies that the overall error count must * be cleared when a HEARTBEAT ACK is received, we make an * exception while in SHUTDOWN PENDING. If the peer keeps its * window shut forever, we may never be able to transmit our * outstanding data and rely on the retransmission limit be reached * to shutdown the association. */ if (t->asoc->state < SCTP_STATE_SHUTDOWN_PENDING) t->asoc->overall_error_count = 0; /* Clear the hb_sent flag to signal that we had a good * acknowledgement. */ t->hb_sent = 0; /* Mark the destination transport address as active if it is not so * marked. */ if ((t->state == SCTP_INACTIVE) || (t->state == SCTP_UNCONFIRMED)) { was_unconfirmed = 1; sctp_assoc_control_transport(asoc, t, SCTP_TRANSPORT_UP, SCTP_HEARTBEAT_SUCCESS); } if (t->state == SCTP_PF) sctp_assoc_control_transport(asoc, t, SCTP_TRANSPORT_UP, SCTP_HEARTBEAT_SUCCESS); /* HB-ACK was received for a the proper HB. Consider this * forward progress. */ if (t->dst) sctp_transport_dst_confirm(t); /* The receiver of the HEARTBEAT ACK should also perform an * RTT measurement for that destination transport address * using the time value carried in the HEARTBEAT ACK chunk. * If the transport's rto_pending variable has been cleared, * it was most likely due to a retransmit. However, we want * to re-enable it to properly update the rto. */ if (t->rto_pending == 0) t->rto_pending = 1; hbinfo = (struct sctp_sender_hb_info *)chunk->skb->data; sctp_transport_update_rto(t, (jiffies - hbinfo->sent_at)); /* Update the heartbeat timer. */ sctp_transport_reset_hb_timer(t); if (was_unconfirmed && asoc->peer.transport_count == 1) sctp_transport_immediate_rtx(t); } /* Helper function to process the process SACK command. */ static int sctp_cmd_process_sack(struct sctp_cmd_seq *cmds, struct sctp_association *asoc, struct sctp_chunk *chunk) { int err = 0; if (sctp_outq_sack(&asoc->outqueue, chunk)) { /* There are no more TSNs awaiting SACK. */ err = sctp_do_sm(asoc->base.net, SCTP_EVENT_T_OTHER, SCTP_ST_OTHER(SCTP_EVENT_NO_PENDING_TSN), asoc->state, asoc->ep, asoc, NULL, GFP_ATOMIC); } return err; } /* Helper function to set the timeout value for T2-SHUTDOWN timer and to set * the transport for a shutdown chunk. */ static void sctp_cmd_setup_t2(struct sctp_cmd_seq *cmds, struct sctp_association *asoc, struct sctp_chunk *chunk) { struct sctp_transport *t; if (chunk->transport) t = chunk->transport; else { t = sctp_assoc_choose_alter_transport(asoc, asoc->shutdown_last_sent_to); chunk->transport = t; } asoc->shutdown_last_sent_to = t; asoc->timeouts[SCTP_EVENT_TIMEOUT_T2_SHUTDOWN] = t->rto; } /* Helper function to change the state of an association. */ static void sctp_cmd_new_state(struct sctp_cmd_seq *cmds, struct sctp_association *asoc, enum sctp_state state) { struct sock *sk = asoc->base.sk; asoc->state = state; pr_debug("%s: asoc:%p[%s]\n", __func__, asoc, sctp_state_tbl[state]); if (sctp_style(sk, TCP)) { /* Change the sk->sk_state of a TCP-style socket that has * successfully completed a connect() call. */ if (sctp_state(asoc, ESTABLISHED) && sctp_sstate(sk, CLOSED)) inet_sk_set_state(sk, SCTP_SS_ESTABLISHED); /* Set the RCV_SHUTDOWN flag when a SHUTDOWN is received. */ if (sctp_state(asoc, SHUTDOWN_RECEIVED) && sctp_sstate(sk, ESTABLISHED)) { inet_sk_set_state(sk, SCTP_SS_CLOSING); sk->sk_shutdown |= RCV_SHUTDOWN; } } if (sctp_state(asoc, COOKIE_WAIT)) { /* Reset init timeouts since they may have been * increased due to timer expirations. */ asoc->timeouts[SCTP_EVENT_TIMEOUT_T1_INIT] = asoc->rto_initial; asoc->timeouts[SCTP_EVENT_TIMEOUT_T1_COOKIE] = asoc->rto_initial; } if (sctp_state(asoc, ESTABLISHED)) { kfree(asoc->peer.cookie); asoc->peer.cookie = NULL; } if (sctp_state(asoc, ESTABLISHED) || sctp_state(asoc, CLOSED) || sctp_state(asoc, SHUTDOWN_RECEIVED)) { /* Wake up any processes waiting in the asoc's wait queue in * sctp_wait_for_connect() or sctp_wait_for_sndbuf(). */ if (waitqueue_active(&asoc->wait)) wake_up_interruptible(&asoc->wait); /* Wake up any processes waiting in the sk's sleep queue of * a TCP-style or UDP-style peeled-off socket in * sctp_wait_for_accept() or sctp_wait_for_packet(). * For a UDP-style socket, the waiters are woken up by the * notifications. */ if (!sctp_style(sk, UDP)) sk->sk_state_change(sk); } if (sctp_state(asoc, SHUTDOWN_PENDING) && !sctp_outq_is_empty(&asoc->outqueue)) sctp_outq_uncork(&asoc->outqueue, GFP_ATOMIC); } /* Helper function to delete an association. */ static void sctp_cmd_delete_tcb(struct sctp_cmd_seq *cmds, struct sctp_association *asoc) { struct sock *sk = asoc->base.sk; /* If it is a non-temporary association belonging to a TCP-style * listening socket that is not closed, do not free it so that accept() * can pick it up later. */ if (sctp_style(sk, TCP) && sctp_sstate(sk, LISTENING) && (!asoc->temp) && (sk->sk_shutdown != SHUTDOWN_MASK)) return; sctp_association_free(asoc); } /* * ADDIP Section 4.1 ASCONF Chunk Procedures * A4) Start a T-4 RTO timer, using the RTO value of the selected * destination address (we use active path instead of primary path just * because primary path may be inactive. */ static void sctp_cmd_setup_t4(struct sctp_cmd_seq *cmds, struct sctp_association *asoc, struct sctp_chunk *chunk) { struct sctp_transport *t; t = sctp_assoc_choose_alter_transport(asoc, chunk->transport); asoc->timeouts[SCTP_EVENT_TIMEOUT_T4_RTO] = t->rto; chunk->transport = t; } /* Process an incoming Operation Error Chunk. */ static void sctp_cmd_process_operr(struct sctp_cmd_seq *cmds, struct sctp_association *asoc, struct sctp_chunk *chunk) { struct sctp_errhdr *err_hdr; struct sctp_ulpevent *ev; while (chunk->chunk_end > chunk->skb->data) { err_hdr = (struct sctp_errhdr *)(chunk->skb->data); ev = sctp_ulpevent_make_remote_error(asoc, chunk, 0, GFP_ATOMIC); if (!ev) return; asoc->stream.si->enqueue_event(&asoc->ulpq, ev); switch (err_hdr->cause) { case SCTP_ERROR_UNKNOWN_CHUNK: { struct sctp_chunkhdr *unk_chunk_hdr; unk_chunk_hdr = (struct sctp_chunkhdr *)(err_hdr + 1); switch (unk_chunk_hdr->type) { /* ADDIP 4.1 A9) If the peer responds to an ASCONF with * an ERROR chunk reporting that it did not recognized * the ASCONF chunk type, the sender of the ASCONF MUST * NOT send any further ASCONF chunks and MUST stop its * T-4 timer. */ case SCTP_CID_ASCONF: if (asoc->peer.asconf_capable == 0) break; asoc->peer.asconf_capable = 0; sctp_add_cmd_sf(cmds, SCTP_CMD_TIMER_STOP, SCTP_TO(SCTP_EVENT_TIMEOUT_T4_RTO)); break; default: break; } break; } default: break; } } } /* Helper function to remove the association non-primary peer * transports. */ static void sctp_cmd_del_non_primary(struct sctp_association *asoc) { struct sctp_transport *t; struct list_head *temp; struct list_head *pos; list_for_each_safe(pos, temp, &asoc->peer.transport_addr_list) { t = list_entry(pos, struct sctp_transport, transports); if (!sctp_cmp_addr_exact(&t->ipaddr, &asoc->peer.primary_addr)) { sctp_assoc_rm_peer(asoc, t); } } } /* Helper function to set sk_err on a 1-1 style socket. */ static void sctp_cmd_set_sk_err(struct sctp_association *asoc, int error) { struct sock *sk = asoc->base.sk; if (!sctp_style(sk, UDP)) sk->sk_err = error; } /* Helper function to generate an association change event */ static void sctp_cmd_assoc_change(struct sctp_cmd_seq *commands, struct sctp_association *asoc, u8 state) { struct sctp_ulpevent *ev; ev = sctp_ulpevent_make_assoc_change(asoc, 0, state, 0, asoc->c.sinit_num_ostreams, asoc->c.sinit_max_instreams, NULL, GFP_ATOMIC); if (ev) asoc->stream.si->enqueue_event(&asoc->ulpq, ev); } static void sctp_cmd_peer_no_auth(struct sctp_cmd_seq *commands, struct sctp_association *asoc) { struct sctp_ulpevent *ev; ev = sctp_ulpevent_make_authkey(asoc, 0, SCTP_AUTH_NO_AUTH, GFP_ATOMIC); if (ev) asoc->stream.si->enqueue_event(&asoc->ulpq, ev); } /* Helper function to generate an adaptation indication event */ static void sctp_cmd_adaptation_ind(struct sctp_cmd_seq *commands, struct sctp_association *asoc) { struct sctp_ulpevent *ev; ev = sctp_ulpevent_make_adaptation_indication(asoc, GFP_ATOMIC); if (ev) asoc->stream.si->enqueue_event(&asoc->ulpq, ev); } static void sctp_cmd_t1_timer_update(struct sctp_association *asoc, enum sctp_event_timeout timer, char *name) { struct sctp_transport *t; t = asoc->init_last_sent_to; asoc->init_err_counter++; if (t->init_sent_count > (asoc->init_cycle + 1)) { asoc->timeouts[timer] *= 2; if (asoc->timeouts[timer] > asoc->max_init_timeo) { asoc->timeouts[timer] = asoc->max_init_timeo; } asoc->init_cycle++; pr_debug("%s: T1[%s] timeout adjustment init_err_counter:%d" " cycle:%d timeout:%ld\n", __func__, name, asoc->init_err_counter, asoc->init_cycle, asoc->timeouts[timer]); } } /* Send the whole message, chunk by chunk, to the outqueue. * This way the whole message is queued up and bundling if * encouraged for small fragments. */ static void sctp_cmd_send_msg(struct sctp_association *asoc, struct sctp_datamsg *msg, gfp_t gfp) { struct sctp_chunk *chunk; list_for_each_entry(chunk, &msg->chunks, frag_list) sctp_outq_tail(&asoc->outqueue, chunk, gfp); asoc->outqueue.sched->enqueue(&asoc->outqueue, msg); } /* These three macros allow us to pull the debugging code out of the * main flow of sctp_do_sm() to keep attention focused on the real * functionality there. */ #define debug_pre_sfn() \ pr_debug("%s[pre-fn]: ep:%p, %s, %s, asoc:%p[%s], %s\n", __func__, \ ep, sctp_evttype_tbl[event_type], (*debug_fn)(subtype), \ asoc, sctp_state_tbl[state], state_fn->name) #define debug_post_sfn() \ pr_debug("%s[post-fn]: asoc:%p, status:%s\n", __func__, asoc, \ sctp_status_tbl[status]) #define debug_post_sfx() \ pr_debug("%s[post-sfx]: error:%d, asoc:%p[%s]\n", __func__, error, \ asoc, sctp_state_tbl[(asoc && sctp_id2assoc(ep->base.sk, \ sctp_assoc2id(asoc))) ? asoc->state : SCTP_STATE_CLOSED]) /* * This is the master state machine processing function. * * If you want to understand all of lksctp, this is a * good place to start. */ int sctp_do_sm(struct net *net, enum sctp_event_type event_type, union sctp_subtype subtype, enum sctp_state state, struct sctp_endpoint *ep, struct sctp_association *asoc, void *event_arg, gfp_t gfp) { typedef const char *(printfn_t)(union sctp_subtype); static printfn_t *table[] = { NULL, sctp_cname, sctp_tname, sctp_oname, sctp_pname, }; printfn_t *debug_fn __attribute__ ((unused)) = table[event_type]; const struct sctp_sm_table_entry *state_fn; struct sctp_cmd_seq commands; enum sctp_disposition status; int error = 0; /* Look up the state function, run it, and then process the * side effects. These three steps are the heart of lksctp. */ state_fn = sctp_sm_lookup_event(net, event_type, state, subtype); sctp_init_cmd_seq(&commands); debug_pre_sfn(); status = state_fn->fn(net, ep, asoc, subtype, event_arg, &commands); debug_post_sfn(); error = sctp_side_effects(event_type, subtype, state, ep, &asoc, event_arg, status, &commands, gfp); debug_post_sfx(); return error; } /***************************************************************** * This the master state function side effect processing function. *****************************************************************/ static int sctp_side_effects(enum sctp_event_type event_type, union sctp_subtype subtype, enum sctp_state state, struct sctp_endpoint *ep, struct sctp_association **asoc, void *event_arg, enum sctp_disposition status, struct sctp_cmd_seq *commands, gfp_t gfp) { int error; /* FIXME - Most of the dispositions left today would be categorized * as "exceptional" dispositions. For those dispositions, it * may not be proper to run through any of the commands at all. * For example, the command interpreter might be run only with * disposition SCTP_DISPOSITION_CONSUME. */ if (0 != (error = sctp_cmd_interpreter(event_type, subtype, state, ep, *asoc, event_arg, status, commands, gfp))) goto bail; switch (status) { case SCTP_DISPOSITION_DISCARD: pr_debug("%s: ignored sctp protocol event - state:%d, " "event_type:%d, event_id:%d\n", __func__, state, event_type, subtype.chunk); break; case SCTP_DISPOSITION_NOMEM: /* We ran out of memory, so we need to discard this * packet. */ /* BUG--we should now recover some memory, probably by * reneging... */ error = -ENOMEM; break; case SCTP_DISPOSITION_DELETE_TCB: case SCTP_DISPOSITION_ABORT: /* This should now be a command. */ *asoc = NULL; break; case SCTP_DISPOSITION_CONSUME: /* * We should no longer have much work to do here as the * real work has been done as explicit commands above. */ break; case SCTP_DISPOSITION_VIOLATION: net_err_ratelimited("protocol violation state %d chunkid %d\n", state, subtype.chunk); break; case SCTP_DISPOSITION_NOT_IMPL: pr_warn("unimplemented feature in state %d, event_type %d, event_id %d\n", state, event_type, subtype.chunk); break; case SCTP_DISPOSITION_BUG: pr_err("bug in state %d, event_type %d, event_id %d\n", state, event_type, subtype.chunk); BUG(); break; default: pr_err("impossible disposition %d in state %d, event_type %d, event_id %d\n", status, state, event_type, subtype.chunk); error = status; if (error >= 0) error = -EINVAL; WARN_ON_ONCE(1); break; } bail: return error; } /******************************************************************** * 2nd Level Abstractions ********************************************************************/ /* This is the side-effect interpreter. */ static int sctp_cmd_interpreter(enum sctp_event_type event_type, union sctp_subtype subtype, enum sctp_state state, struct sctp_endpoint *ep, struct sctp_association *asoc, void *event_arg, enum sctp_disposition status, struct sctp_cmd_seq *commands, gfp_t gfp) { struct sctp_sock *sp = sctp_sk(ep->base.sk); struct sctp_chunk *chunk = NULL, *new_obj; struct sctp_packet *packet; struct sctp_sackhdr sackh; struct timer_list *timer; struct sctp_transport *t; unsigned long timeout; struct sctp_cmd *cmd; int local_cork = 0; int error = 0; int force; if (SCTP_EVENT_T_TIMEOUT != event_type) chunk = event_arg; /* Note: This whole file is a huge candidate for rework. * For example, each command could either have its own handler, so * the loop would look like: * while (cmds) * cmd->handle(x, y, z) * --jgrimm */ while (NULL != (cmd = sctp_next_cmd(commands))) { switch (cmd->verb) { case SCTP_CMD_NOP: /* Do nothing. */ break; case SCTP_CMD_NEW_ASOC: /* Register a new association. */ if (local_cork) { sctp_outq_uncork(&asoc->outqueue, gfp); local_cork = 0; } /* Register with the endpoint. */ asoc = cmd->obj.asoc; BUG_ON(asoc->peer.primary_path == NULL); sctp_endpoint_add_asoc(ep, asoc); break; case SCTP_CMD_PURGE_OUTQUEUE: sctp_outq_teardown(&asoc->outqueue); break; case SCTP_CMD_DELETE_TCB: if (local_cork) { sctp_outq_uncork(&asoc->outqueue, gfp); local_cork = 0; } /* Delete the current association. */ sctp_cmd_delete_tcb(commands, asoc); asoc = NULL; break; case SCTP_CMD_NEW_STATE: /* Enter a new state. */ sctp_cmd_new_state(commands, asoc, cmd->obj.state); break; case SCTP_CMD_REPORT_TSN: /* Record the arrival of a TSN. */ error = sctp_tsnmap_mark(&asoc->peer.tsn_map, cmd->obj.u32, NULL); break; case SCTP_CMD_REPORT_FWDTSN: asoc->stream.si->report_ftsn(&asoc->ulpq, cmd->obj.u32); break; case SCTP_CMD_PROCESS_FWDTSN: asoc->stream.si->handle_ftsn(&asoc->ulpq, cmd->obj.chunk); break; case SCTP_CMD_GEN_SACK: /* Generate a Selective ACK. * The argument tells us whether to just count * the packet and MAYBE generate a SACK, or * force a SACK out. */ force = cmd->obj.i32; error = sctp_gen_sack(asoc, force, commands); break; case SCTP_CMD_PROCESS_SACK: /* Process an inbound SACK. */ error = sctp_cmd_process_sack(commands, asoc, cmd->obj.chunk); break; case SCTP_CMD_GEN_INIT_ACK: /* Generate an INIT ACK chunk. */ new_obj = sctp_make_init_ack(asoc, chunk, GFP_ATOMIC, 0); if (!new_obj) { error = -ENOMEM; break; } sctp_add_cmd_sf(commands, SCTP_CMD_REPLY, SCTP_CHUNK(new_obj)); break; case SCTP_CMD_PEER_INIT: /* Process a unified INIT from the peer. * Note: Only used during INIT-ACK processing. If * there is an error just return to the outter * layer which will bail. */ error = sctp_cmd_process_init(commands, asoc, chunk, cmd->obj.init, gfp); break; case SCTP_CMD_GEN_COOKIE_ECHO: /* Generate a COOKIE ECHO chunk. */ new_obj = sctp_make_cookie_echo(asoc, chunk); if (!new_obj) { if (cmd->obj.chunk) sctp_chunk_free(cmd->obj.chunk); error = -ENOMEM; break; } sctp_add_cmd_sf(commands, SCTP_CMD_REPLY, SCTP_CHUNK(new_obj)); /* If there is an ERROR chunk to be sent along with * the COOKIE_ECHO, send it, too. */ if (cmd->obj.chunk) sctp_add_cmd_sf(commands, SCTP_CMD_REPLY, SCTP_CHUNK(cmd->obj.chunk)); if (new_obj->transport) { new_obj->transport->init_sent_count++; asoc->init_last_sent_to = new_obj->transport; } /* FIXME - Eventually come up with a cleaner way to * enabling COOKIE-ECHO + DATA bundling during * multihoming stale cookie scenarios, the following * command plays with asoc->peer.retran_path to * avoid the problem of sending the COOKIE-ECHO and * DATA in different paths, which could result * in the association being ABORTed if the DATA chunk * is processed first by the server. Checking the * init error counter simply causes this command * to be executed only during failed attempts of * association establishment. */ if ((asoc->peer.retran_path != asoc->peer.primary_path) && (asoc->init_err_counter > 0)) { sctp_add_cmd_sf(commands, SCTP_CMD_FORCE_PRIM_RETRAN, SCTP_NULL()); } break; case SCTP_CMD_GEN_SHUTDOWN: /* Generate SHUTDOWN when in SHUTDOWN_SENT state. * Reset error counts. */ asoc->overall_error_count = 0; /* Generate a SHUTDOWN chunk. */ new_obj = sctp_make_shutdown(asoc, chunk); if (!new_obj) { error = -ENOMEM; break; } sctp_add_cmd_sf(commands, SCTP_CMD_REPLY, SCTP_CHUNK(new_obj)); break; case SCTP_CMD_CHUNK_ULP: /* Send a chunk to the sockets layer. */ pr_debug("%s: sm_sideff: chunk_up:%p, ulpq:%p\n", __func__, cmd->obj.chunk, &asoc->ulpq); asoc->stream.si->ulpevent_data(&asoc->ulpq, cmd->obj.chunk, GFP_ATOMIC); break; case SCTP_CMD_EVENT_ULP: /* Send a notification to the sockets layer. */ pr_debug("%s: sm_sideff: event_up:%p, ulpq:%p\n", __func__, cmd->obj.ulpevent, &asoc->ulpq); asoc->stream.si->enqueue_event(&asoc->ulpq, cmd->obj.ulpevent); break; case SCTP_CMD_REPLY: /* If an caller has not already corked, do cork. */ if (!asoc->outqueue.cork) { sctp_outq_cork(&asoc->outqueue); local_cork = 1; } /* Send a chunk to our peer. */ sctp_outq_tail(&asoc->outqueue, cmd->obj.chunk, gfp); break; case SCTP_CMD_SEND_PKT: /* Send a full packet to our peer. */ packet = cmd->obj.packet; sctp_packet_transmit(packet, gfp); sctp_ootb_pkt_free(packet); break; case SCTP_CMD_T1_RETRAN: /* Mark a transport for retransmission. */ sctp_retransmit(&asoc->outqueue, cmd->obj.transport, SCTP_RTXR_T1_RTX); break; case SCTP_CMD_RETRAN: /* Mark a transport for retransmission. */ sctp_retransmit(&asoc->outqueue, cmd->obj.transport, SCTP_RTXR_T3_RTX); break; case SCTP_CMD_ECN_CE: /* Do delayed CE processing. */ sctp_do_ecn_ce_work(asoc, cmd->obj.u32); break; case SCTP_CMD_ECN_ECNE: /* Do delayed ECNE processing. */ new_obj = sctp_do_ecn_ecne_work(asoc, cmd->obj.u32, chunk); if (new_obj) sctp_add_cmd_sf(commands, SCTP_CMD_REPLY, SCTP_CHUNK(new_obj)); break; case SCTP_CMD_ECN_CWR: /* Do delayed CWR processing. */ sctp_do_ecn_cwr_work(asoc, cmd->obj.u32); break; case SCTP_CMD_SETUP_T2: sctp_cmd_setup_t2(commands, asoc, cmd->obj.chunk); break; case SCTP_CMD_TIMER_START_ONCE: timer = &asoc->timers[cmd->obj.to]; if (timer_pending(timer)) break; fallthrough; case SCTP_CMD_TIMER_START: timer = &asoc->timers[cmd->obj.to]; timeout = asoc->timeouts[cmd->obj.to]; BUG_ON(!timeout); /* * SCTP has a hard time with timer starts. Because we process * timer starts as side effects, it can be hard to tell if we * have already started a timer or not, which leads to BUG * halts when we call add_timer. So here, instead of just starting * a timer, if the timer is already started, and just mod * the timer with the shorter of the two expiration times */ if (!timer_pending(timer)) sctp_association_hold(asoc); timer_reduce(timer, jiffies + timeout); break; case SCTP_CMD_TIMER_RESTART: timer = &asoc->timers[cmd->obj.to]; timeout = asoc->timeouts[cmd->obj.to]; if (!mod_timer(timer, jiffies + timeout)) sctp_association_hold(asoc); break; case SCTP_CMD_TIMER_STOP: timer = &asoc->timers[cmd->obj.to]; if (del_timer(timer)) sctp_association_put(asoc); break; case SCTP_CMD_INIT_CHOOSE_TRANSPORT: chunk = cmd->obj.chunk; t = sctp_assoc_choose_alter_transport(asoc, asoc->init_last_sent_to); asoc->init_last_sent_to = t; chunk->transport = t; t->init_sent_count++; /* Set the new transport as primary */ sctp_assoc_set_primary(asoc, t); break; case SCTP_CMD_INIT_RESTART: /* Do the needed accounting and updates * associated with restarting an initialization * timer. Only multiply the timeout by two if * all transports have been tried at the current * timeout. */ sctp_cmd_t1_timer_update(asoc, SCTP_EVENT_TIMEOUT_T1_INIT, "INIT"); sctp_add_cmd_sf(commands, SCTP_CMD_TIMER_RESTART, SCTP_TO(SCTP_EVENT_TIMEOUT_T1_INIT)); break; case SCTP_CMD_COOKIEECHO_RESTART: /* Do the needed accounting and updates * associated with restarting an initialization * timer. Only multiply the timeout by two if * all transports have been tried at the current * timeout. */ sctp_cmd_t1_timer_update(asoc, SCTP_EVENT_TIMEOUT_T1_COOKIE, "COOKIE"); /* If we've sent any data bundled with * COOKIE-ECHO we need to resend. */ list_for_each_entry(t, &asoc->peer.transport_addr_list, transports) { sctp_retransmit_mark(&asoc->outqueue, t, SCTP_RTXR_T1_RTX); } sctp_add_cmd_sf(commands, SCTP_CMD_TIMER_RESTART, SCTP_TO(SCTP_EVENT_TIMEOUT_T1_COOKIE)); break; case SCTP_CMD_INIT_FAILED: sctp_cmd_init_failed(commands, asoc, cmd->obj.u16); break; case SCTP_CMD_ASSOC_FAILED: sctp_cmd_assoc_failed(commands, asoc, event_type, subtype, chunk, cmd->obj.u16); break; case SCTP_CMD_INIT_COUNTER_INC: asoc->init_err_counter++; break; case SCTP_CMD_INIT_COUNTER_RESET: asoc->init_err_counter = 0; asoc->init_cycle = 0; list_for_each_entry(t, &asoc->peer.transport_addr_list, transports) { t->init_sent_count = 0; } break; case SCTP_CMD_REPORT_DUP: sctp_tsnmap_mark_dup(&asoc->peer.tsn_map, cmd->obj.u32); break; case SCTP_CMD_REPORT_BAD_TAG: pr_debug("%s: vtag mismatch!\n", __func__); break; case SCTP_CMD_STRIKE: /* Mark one strike against a transport. */ sctp_do_8_2_transport_strike(commands, asoc, cmd->obj.transport, 0); break; case SCTP_CMD_TRANSPORT_IDLE: t = cmd->obj.transport; sctp_transport_lower_cwnd(t, SCTP_LOWER_CWND_INACTIVE); break; case SCTP_CMD_TRANSPORT_HB_SENT: t = cmd->obj.transport; sctp_do_8_2_transport_strike(commands, asoc, t, 1); t->hb_sent = 1; break; case SCTP_CMD_TRANSPORT_ON: t = cmd->obj.transport; sctp_cmd_transport_on(commands, asoc, t, chunk); break; case SCTP_CMD_HB_TIMERS_START: sctp_cmd_hb_timers_start(commands, asoc); break; case SCTP_CMD_HB_TIMER_UPDATE: t = cmd->obj.transport; sctp_transport_reset_hb_timer(t); break; case SCTP_CMD_HB_TIMERS_STOP: sctp_cmd_hb_timers_stop(commands, asoc); break; case SCTP_CMD_PROBE_TIMER_UPDATE: t = cmd->obj.transport; sctp_transport_reset_probe_timer(t); break; case SCTP_CMD_REPORT_ERROR: error = cmd->obj.error; break; case SCTP_CMD_PROCESS_CTSN: /* Dummy up a SACK for processing. */ sackh.cum_tsn_ack = cmd->obj.be32; sackh.a_rwnd = htonl(asoc->peer.rwnd + asoc->outqueue.outstanding_bytes); sackh.num_gap_ack_blocks = 0; sackh.num_dup_tsns = 0; chunk->subh.sack_hdr = &sackh; sctp_add_cmd_sf(commands, SCTP_CMD_PROCESS_SACK, SCTP_CHUNK(chunk)); break; case SCTP_CMD_DISCARD_PACKET: /* We need to discard the whole packet. * Uncork the queue since there might be * responses pending */ chunk->pdiscard = 1; if (asoc) { sctp_outq_uncork(&asoc->outqueue, gfp); local_cork = 0; } break; case SCTP_CMD_RTO_PENDING: t = cmd->obj.transport; t->rto_pending = 1; break; case SCTP_CMD_PART_DELIVER: asoc->stream.si->start_pd(&asoc->ulpq, GFP_ATOMIC); break; case SCTP_CMD_RENEGE: asoc->stream.si->renege_events(&asoc->ulpq, cmd->obj.chunk, GFP_ATOMIC); break; case SCTP_CMD_SETUP_T4: sctp_cmd_setup_t4(commands, asoc, cmd->obj.chunk); break; case SCTP_CMD_PROCESS_OPERR: sctp_cmd_process_operr(commands, asoc, chunk); break; case SCTP_CMD_CLEAR_INIT_TAG: asoc->peer.i.init_tag = 0; break; case SCTP_CMD_DEL_NON_PRIMARY: sctp_cmd_del_non_primary(asoc); break; case SCTP_CMD_T3_RTX_TIMERS_STOP: sctp_cmd_t3_rtx_timers_stop(commands, asoc); break; case SCTP_CMD_FORCE_PRIM_RETRAN: t = asoc->peer.retran_path; asoc->peer.retran_path = asoc->peer.primary_path; sctp_outq_uncork(&asoc->outqueue, gfp); local_cork = 0; asoc->peer.retran_path = t; break; case SCTP_CMD_SET_SK_ERR: sctp_cmd_set_sk_err(asoc, cmd->obj.error); break; case SCTP_CMD_ASSOC_CHANGE: sctp_cmd_assoc_change(commands, asoc, cmd->obj.u8); break; case SCTP_CMD_ADAPTATION_IND: sctp_cmd_adaptation_ind(commands, asoc); break; case SCTP_CMD_PEER_NO_AUTH: sctp_cmd_peer_no_auth(commands, asoc); break; case SCTP_CMD_ASSOC_SHKEY: error = sctp_auth_asoc_init_active_key(asoc, GFP_ATOMIC); break; case SCTP_CMD_UPDATE_INITTAG: asoc->peer.i.init_tag = cmd->obj.u32; break; case SCTP_CMD_SEND_MSG: if (!asoc->outqueue.cork) { sctp_outq_cork(&asoc->outqueue); local_cork = 1; } sctp_cmd_send_msg(asoc, cmd->obj.msg, gfp); break; case SCTP_CMD_PURGE_ASCONF_QUEUE: sctp_asconf_queue_teardown(asoc); break; case SCTP_CMD_SET_ASOC: if (asoc && local_cork) { sctp_outq_uncork(&asoc->outqueue, gfp); local_cork = 0; } asoc = cmd->obj.asoc; break; default: pr_warn("Impossible command: %u\n", cmd->verb); break; } if (error) { cmd = sctp_next_cmd(commands); while (cmd) { if (cmd->verb == SCTP_CMD_REPLY) sctp_chunk_free(cmd->obj.chunk); cmd = sctp_next_cmd(commands); } break; } } /* If this is in response to a received chunk, wait until * we are done with the packet to open the queue so that we don't * send multiple packets in response to a single request. */ if (asoc && SCTP_EVENT_T_CHUNK == event_type && chunk) { if (chunk->end_of_packet || chunk->singleton) sctp_outq_uncork(&asoc->outqueue, gfp); } else if (local_cork) sctp_outq_uncork(&asoc->outqueue, gfp); if (sp->data_ready_signalled) sp->data_ready_signalled = 0; return error; } |
| 17 4 63 2 | 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 | #undef TRACE_SYSTEM #define TRACE_SYSTEM bridge #if !defined(_TRACE_BRIDGE_H) || defined(TRACE_HEADER_MULTI_READ) #define _TRACE_BRIDGE_H #include <linux/netdevice.h> #include <linux/tracepoint.h> #include "../../../net/bridge/br_private.h" TRACE_EVENT(br_fdb_add, TP_PROTO(struct ndmsg *ndm, struct net_device *dev, const unsigned char *addr, u16 vid, u16 nlh_flags), TP_ARGS(ndm, dev, addr, vid, nlh_flags), TP_STRUCT__entry( __field(u8, ndm_flags) __string(dev, dev->name) __array(unsigned char, addr, ETH_ALEN) __field(u16, vid) __field(u16, nlh_flags) ), TP_fast_assign( __assign_str(dev); memcpy(__entry->addr, addr, ETH_ALEN); __entry->vid = vid; __entry->nlh_flags = nlh_flags; __entry->ndm_flags = ndm->ndm_flags; ), TP_printk("dev %s addr %02x:%02x:%02x:%02x:%02x:%02x vid %u nlh_flags %04x ndm_flags %02x", __get_str(dev), __entry->addr[0], __entry->addr[1], __entry->addr[2], __entry->addr[3], __entry->addr[4], __entry->addr[5], __entry->vid, __entry->nlh_flags, __entry->ndm_flags) ); TRACE_EVENT(br_fdb_external_learn_add, TP_PROTO(struct net_bridge *br, struct net_bridge_port *p, const unsigned char *addr, u16 vid), TP_ARGS(br, p, addr, vid), TP_STRUCT__entry( __string(br_dev, br->dev->name) __string(dev, p ? p->dev->name : "null") __array(unsigned char, addr, ETH_ALEN) __field(u16, vid) ), TP_fast_assign( __assign_str(br_dev); __assign_str(dev); memcpy(__entry->addr, addr, ETH_ALEN); __entry->vid = vid; ), TP_printk("br_dev %s port %s addr %02x:%02x:%02x:%02x:%02x:%02x vid %u", __get_str(br_dev), __get_str(dev), __entry->addr[0], __entry->addr[1], __entry->addr[2], __entry->addr[3], __entry->addr[4], __entry->addr[5], __entry->vid) ); TRACE_EVENT(fdb_delete, TP_PROTO(struct net_bridge *br, struct net_bridge_fdb_entry *f), TP_ARGS(br, f), TP_STRUCT__entry( __string(br_dev, br->dev->name) __string(dev, f->dst ? f->dst->dev->name : "null") __array(unsigned char, addr, ETH_ALEN) __field(u16, vid) ), TP_fast_assign( __assign_str(br_dev); __assign_str(dev); memcpy(__entry->addr, f->key.addr.addr, ETH_ALEN); __entry->vid = f->key.vlan_id; ), TP_printk("br_dev %s dev %s addr %02x:%02x:%02x:%02x:%02x:%02x vid %u", __get_str(br_dev), __get_str(dev), __entry->addr[0], __entry->addr[1], __entry->addr[2], __entry->addr[3], __entry->addr[4], __entry->addr[5], __entry->vid) ); TRACE_EVENT(br_fdb_update, TP_PROTO(struct net_bridge *br, struct net_bridge_port *source, const unsigned char *addr, u16 vid, unsigned long flags), TP_ARGS(br, source, addr, vid, flags), TP_STRUCT__entry( __string(br_dev, br->dev->name) __string(dev, source->dev->name) __array(unsigned char, addr, ETH_ALEN) __field(u16, vid) __field(unsigned long, flags) ), TP_fast_assign( __assign_str(br_dev); __assign_str(dev); memcpy(__entry->addr, addr, ETH_ALEN); __entry->vid = vid; __entry->flags = flags; ), TP_printk("br_dev %s source %s addr %02x:%02x:%02x:%02x:%02x:%02x vid %u flags 0x%lx", __get_str(br_dev), __get_str(dev), __entry->addr[0], __entry->addr[1], __entry->addr[2], __entry->addr[3], __entry->addr[4], __entry->addr[5], __entry->vid, __entry->flags) ); TRACE_EVENT(br_mdb_full, TP_PROTO(const struct net_device *dev, const struct br_ip *group), TP_ARGS(dev, group), TP_STRUCT__entry( __string(dev, dev->name) __field(int, af) __field(u16, vid) __array(__u8, src, 16) __array(__u8, grp, 16) __array(__u8, grpmac, ETH_ALEN) /* For af == 0. */ ), TP_fast_assign( struct in6_addr *in6; __assign_str(dev); __entry->vid = group->vid; if (!group->proto) { __entry->af = 0; memset(__entry->src, 0, sizeof(__entry->src)); memset(__entry->grp, 0, sizeof(__entry->grp)); memcpy(__entry->grpmac, group->dst.mac_addr, ETH_ALEN); } else if (group->proto == htons(ETH_P_IP)) { __entry->af = AF_INET; in6 = (struct in6_addr *)__entry->src; ipv6_addr_set_v4mapped(group->src.ip4, in6); in6 = (struct in6_addr *)__entry->grp; ipv6_addr_set_v4mapped(group->dst.ip4, in6); memset(__entry->grpmac, 0, ETH_ALEN); #if IS_ENABLED(CONFIG_IPV6) } else { __entry->af = AF_INET6; in6 = (struct in6_addr *)__entry->src; *in6 = group->src.ip6; in6 = (struct in6_addr *)__entry->grp; *in6 = group->dst.ip6; memset(__entry->grpmac, 0, ETH_ALEN); #endif } ), TP_printk("dev %s af %u src %pI6c grp %pI6c/%pM vid %u", __get_str(dev), __entry->af, __entry->src, __entry->grp, __entry->grpmac, __entry->vid) ); #endif /* _TRACE_BRIDGE_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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _ASM_X86_SPECIAL_INSNS_H #define _ASM_X86_SPECIAL_INSNS_H #ifdef __KERNEL__ #include <asm/nops.h> #include <asm/processor-flags.h> #include <linux/errno.h> #include <linux/irqflags.h> #include <linux/jump_label.h> /* * The compiler should not reorder volatile asm statements with respect to each * other: they should execute in program order. However GCC 4.9.x and 5.x have * a bug (which was fixed in 8.1, 7.3 and 6.5) where they might reorder * volatile asm. The write functions are not affected since they have memory * clobbers preventing reordering. To prevent reads from being reordered with * respect to writes, use a dummy memory operand. */ #define __FORCE_ORDER "m"(*(unsigned int *)0x1000UL) void native_write_cr0(unsigned long val); static inline unsigned long native_read_cr0(void) { unsigned long val; asm volatile("mov %%cr0,%0\n\t" : "=r" (val) : __FORCE_ORDER); return val; } static __always_inline unsigned long native_read_cr2(void) { unsigned long val; asm volatile("mov %%cr2,%0\n\t" : "=r" (val) : __FORCE_ORDER); return val; } static __always_inline void native_write_cr2(unsigned long val) { asm volatile("mov %0,%%cr2": : "r" (val) : "memory"); } static inline unsigned long __native_read_cr3(void) { unsigned long val; asm volatile("mov %%cr3,%0\n\t" : "=r" (val) : __FORCE_ORDER); return val; } static inline void native_write_cr3(unsigned long val) { asm volatile("mov %0,%%cr3": : "r" (val) : "memory"); } static inline unsigned long native_read_cr4(void) { unsigned long val; #ifdef CONFIG_X86_32 /* * This could fault if CR4 does not exist. Non-existent CR4 * is functionally equivalent to CR4 == 0. Keep it simple and pretend * that CR4 == 0 on CPUs that don't have CR4. */ asm volatile("1: mov %%cr4, %0\n" "2:\n" _ASM_EXTABLE(1b, 2b) : "=r" (val) : "0" (0), __FORCE_ORDER); #else /* CR4 always exists on x86_64. */ asm volatile("mov %%cr4,%0\n\t" : "=r" (val) : __FORCE_ORDER); #endif return val; } void native_write_cr4(unsigned long val); #ifdef CONFIG_X86_INTEL_MEMORY_PROTECTION_KEYS static inline u32 rdpkru(void) { u32 ecx = 0; u32 edx, pkru; /* * "rdpkru" instruction. Places PKRU contents in to EAX, * clears EDX and requires that ecx=0. */ asm volatile(".byte 0x0f,0x01,0xee\n\t" : "=a" (pkru), "=d" (edx) : "c" (ecx)); return pkru; } static inline void wrpkru(u32 pkru) { u32 ecx = 0, edx = 0; /* * "wrpkru" instruction. Loads contents in EAX to PKRU, * requires that ecx = edx = 0. */ asm volatile(".byte 0x0f,0x01,0xef\n\t" : : "a" (pkru), "c"(ecx), "d"(edx)); } #else static inline u32 rdpkru(void) { return 0; } static inline void wrpkru(u32 pkru) { } #endif static __always_inline void wbinvd(void) { asm volatile("wbinvd": : :"memory"); } static inline unsigned long __read_cr4(void) { return native_read_cr4(); } #ifdef CONFIG_PARAVIRT_XXL #include <asm/paravirt.h> #else static inline unsigned long read_cr0(void) { return native_read_cr0(); } static inline void write_cr0(unsigned long x) { native_write_cr0(x); } static __always_inline unsigned long read_cr2(void) { return native_read_cr2(); } static __always_inline void write_cr2(unsigned long x) { native_write_cr2(x); } /* * Careful! CR3 contains more than just an address. You probably want * read_cr3_pa() instead. */ static inline unsigned long __read_cr3(void) { return __native_read_cr3(); } static inline void write_cr3(unsigned long x) { native_write_cr3(x); } static inline void __write_cr4(unsigned long x) { native_write_cr4(x); } #endif /* CONFIG_PARAVIRT_XXL */ static __always_inline void clflush(volatile void *__p) { asm volatile("clflush %0" : "+m" (*(volatile char __force *)__p)); } static inline void clflushopt(volatile void *__p) { alternative_io(".byte 0x3e; clflush %0", ".byte 0x66; clflush %0", X86_FEATURE_CLFLUSHOPT, "+m" (*(volatile char __force *)__p)); } static inline void clwb(volatile void *__p) { volatile struct { char x[64]; } *p = __p; asm volatile(ALTERNATIVE_2( ".byte 0x3e; clflush (%[pax])", ".byte 0x66; clflush (%[pax])", /* clflushopt (%%rax) */ X86_FEATURE_CLFLUSHOPT, ".byte 0x66, 0x0f, 0xae, 0x30", /* clwb (%%rax) */ X86_FEATURE_CLWB) : [p] "+m" (*p) : [pax] "a" (p)); } #ifdef CONFIG_X86_USER_SHADOW_STACK static inline int write_user_shstk_64(u64 __user *addr, u64 val) { asm goto("1: wrussq %[val], %[addr]\n" _ASM_EXTABLE(1b, %l[fail]) :: [addr] "m" (*addr), [val] "r" (val) :: fail); return 0; fail: return -EFAULT; } #endif /* CONFIG_X86_USER_SHADOW_STACK */ #define nop() asm volatile ("nop") static __always_inline void serialize(void) { /* Instruction opcode for SERIALIZE; supported in binutils >= 2.35. */ asm volatile(".byte 0xf, 0x1, 0xe8" ::: "memory"); } /* The dst parameter must be 64-bytes aligned */ static inline void movdir64b(void *dst, const void *src) { const struct { char _[64]; } *__src = src; struct { char _[64]; } *__dst = dst; /* * MOVDIR64B %(rdx), rax. * * Both __src and __dst must be memory constraints in order to tell the * compiler that no other memory accesses should be reordered around * this one. * * Also, both must be supplied as lvalues because this tells * the compiler what the object is (its size) the instruction accesses. * I.e., not the pointers but what they point to, thus the deref'ing '*'. */ asm volatile(".byte 0x66, 0x0f, 0x38, 0xf8, 0x02" : "+m" (*__dst) : "m" (*__src), "a" (__dst), "d" (__src)); } static inline void movdir64b_io(void __iomem *dst, const void *src) { movdir64b((void __force *)dst, src); } /** * enqcmds - Enqueue a command in supervisor (CPL0) mode * @dst: destination, in MMIO space (must be 512-bit aligned) * @src: 512 bits memory operand * * The ENQCMDS instruction allows software to write a 512-bit command to * a 512-bit-aligned special MMIO region that supports the instruction. * A return status is loaded into the ZF flag in the RFLAGS register. * ZF = 0 equates to success, and ZF = 1 indicates retry or error. * * This function issues the ENQCMDS instruction to submit data from * kernel space to MMIO space, in a unit of 512 bits. Order of data access * is not guaranteed, nor is a memory barrier performed afterwards. It * returns 0 on success and -EAGAIN on failure. * * Warning: Do not use this helper unless your driver has checked that the * ENQCMDS instruction is supported on the platform and the device accepts * ENQCMDS. */ static inline int enqcmds(void __iomem *dst, const void *src) { const struct { char _[64]; } *__src = src; struct { char _[64]; } __iomem *__dst = dst; bool zf; /* * ENQCMDS %(rdx), rax * * See movdir64b()'s comment on operand specification. */ asm volatile(".byte 0xf3, 0x0f, 0x38, 0xf8, 0x02, 0x66, 0x90" CC_SET(z) : CC_OUT(z) (zf), "+m" (*__dst) : "m" (*__src), "a" (__dst), "d" (__src)); /* Submission failure is indicated via EFLAGS.ZF=1 */ if (zf) return -EAGAIN; return 0; } static __always_inline void tile_release(void) { /* * Instruction opcode for TILERELEASE; supported in binutils * version >= 2.36. */ asm volatile(".byte 0xc4, 0xe2, 0x78, 0x49, 0xc0"); } #endif /* __KERNEL__ */ #endif /* _ASM_X86_SPECIAL_INSNS_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 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _LINUX_VMALLOC_H #define _LINUX_VMALLOC_H #include <linux/alloc_tag.h> #include <linux/sched.h> #include <linux/spinlock.h> #include <linux/init.h> #include <linux/list.h> #include <linux/llist.h> #include <asm/page.h> /* pgprot_t */ #include <linux/rbtree.h> #include <linux/overflow.h> #include <asm/vmalloc.h> struct vm_area_struct; /* vma defining user mapping in mm_types.h */ struct notifier_block; /* in notifier.h */ struct iov_iter; /* in uio.h */ /* bits in flags of vmalloc's vm_struct below */ #define VM_IOREMAP 0x00000001 /* ioremap() and friends */ #define VM_ALLOC 0x00000002 /* vmalloc() */ #define VM_MAP 0x00000004 /* vmap()ed pages */ #define VM_USERMAP 0x00000008 /* suitable for remap_vmalloc_range */ #define VM_DMA_COHERENT 0x00000010 /* dma_alloc_coherent */ #define VM_UNINITIALIZED 0x00000020 /* vm_struct is not fully initialized */ #define VM_NO_GUARD 0x00000040 /* ***DANGEROUS*** don't add guard page */ #define VM_KASAN 0x00000080 /* has allocated kasan shadow memory */ #define VM_FLUSH_RESET_PERMS 0x00000100 /* reset direct map and flush TLB on unmap, can't be freed in atomic context */ #define VM_MAP_PUT_PAGES 0x00000200 /* put pages and free array in vfree */ #define VM_ALLOW_HUGE_VMAP 0x00000400 /* Allow for huge pages on archs with HAVE_ARCH_HUGE_VMALLOC */ #if (defined(CONFIG_KASAN_GENERIC) || defined(CONFIG_KASAN_SW_TAGS)) && \ !defined(CONFIG_KASAN_VMALLOC) #define VM_DEFER_KMEMLEAK 0x00000800 /* defer kmemleak object creation */ #else #define VM_DEFER_KMEMLEAK 0 #endif #define VM_SPARSE 0x00001000 /* sparse vm_area. not all pages are present. */ /* bits [20..32] reserved for arch specific ioremap internals */ /* * Maximum alignment for ioremap() regions. * Can be overridden by arch-specific value. */ #ifndef IOREMAP_MAX_ORDER #define IOREMAP_MAX_ORDER (7 + PAGE_SHIFT) /* 128 pages */ #endif struct vm_struct { struct vm_struct *next; void *addr; unsigned long size; unsigned long flags; struct page **pages; #ifdef CONFIG_HAVE_ARCH_HUGE_VMALLOC unsigned int page_order; #endif unsigned int nr_pages; phys_addr_t phys_addr; const void *caller; }; struct vmap_area { unsigned long va_start; unsigned long va_end; struct rb_node rb_node; /* address sorted rbtree */ struct list_head list; /* address sorted list */ /* * The following two variables can be packed, because * a vmap_area object can be either: * 1) in "free" tree (root is free_vmap_area_root) * 2) or "busy" tree (root is vmap_area_root) */ union { unsigned long subtree_max_size; /* in "free" tree */ struct vm_struct *vm; /* in "busy" tree */ }; unsigned long flags; /* mark type of vm_map_ram area */ }; /* archs that select HAVE_ARCH_HUGE_VMAP should override one or more of these */ #ifndef arch_vmap_p4d_supported static inline bool arch_vmap_p4d_supported(pgprot_t prot) { return false; } #endif #ifndef arch_vmap_pud_supported static inline bool arch_vmap_pud_supported(pgprot_t prot) { return false; } #endif #ifndef arch_vmap_pmd_supported static inline bool arch_vmap_pmd_supported(pgprot_t prot) { return false; } #endif #ifndef arch_vmap_pte_range_map_size static inline unsigned long arch_vmap_pte_range_map_size(unsigned long addr, unsigned long end, u64 pfn, unsigned int max_page_shift) { return PAGE_SIZE; } #endif #ifndef arch_vmap_pte_supported_shift static inline int arch_vmap_pte_supported_shift(unsigned long size) { return PAGE_SHIFT; } #endif #ifndef arch_vmap_pgprot_tagged static inline pgprot_t arch_vmap_pgprot_tagged(pgprot_t prot) { return prot; } #endif /* * Highlevel APIs for driver use */ extern void vm_unmap_ram(const void *mem, unsigned int count); extern void *vm_map_ram(struct page **pages, unsigned int count, int node); extern void vm_unmap_aliases(void); extern void *vmalloc_noprof(unsigned long size) __alloc_size(1); #define vmalloc(...) alloc_hooks(vmalloc_noprof(__VA_ARGS__)) extern void *vzalloc_noprof(unsigned long size) __alloc_size(1); #define vzalloc(...) alloc_hooks(vzalloc_noprof(__VA_ARGS__)) extern void *vmalloc_user_noprof(unsigned long size) __alloc_size(1); #define vmalloc_user(...) alloc_hooks(vmalloc_user_noprof(__VA_ARGS__)) extern void *vmalloc_node_noprof(unsigned long size, int node) __alloc_size(1); #define vmalloc_node(...) alloc_hooks(vmalloc_node_noprof(__VA_ARGS__)) extern void *vzalloc_node_noprof(unsigned long size, int node) __alloc_size(1); #define vzalloc_node(...) alloc_hooks(vzalloc_node_noprof(__VA_ARGS__)) extern void *vmalloc_32_noprof(unsigned long size) __alloc_size(1); #define vmalloc_32(...) alloc_hooks(vmalloc_32_noprof(__VA_ARGS__)) extern void *vmalloc_32_user_noprof(unsigned long size) __alloc_size(1); #define vmalloc_32_user(...) alloc_hooks(vmalloc_32_user_noprof(__VA_ARGS__)) extern void *__vmalloc_noprof(unsigned long size, gfp_t gfp_mask) __alloc_size(1); #define __vmalloc(...) alloc_hooks(__vmalloc_noprof(__VA_ARGS__)) extern void *__vmalloc_node_range_noprof(unsigned long size, unsigned long align, unsigned long start, unsigned long end, gfp_t gfp_mask, pgprot_t prot, unsigned long vm_flags, int node, const void *caller) __alloc_size(1); #define __vmalloc_node_range(...) alloc_hooks(__vmalloc_node_range_noprof(__VA_ARGS__)) void *__vmalloc_node_noprof(unsigned long size, unsigned long align, gfp_t gfp_mask, int node, const void *caller) __alloc_size(1); #define __vmalloc_node(...) alloc_hooks(__vmalloc_node_noprof(__VA_ARGS__)) void *vmalloc_huge_noprof(unsigned long size, gfp_t gfp_mask) __alloc_size(1); #define vmalloc_huge(...) alloc_hooks(vmalloc_huge_noprof(__VA_ARGS__)) extern void *__vmalloc_array_noprof(size_t n, size_t size, gfp_t flags) __alloc_size(1, 2); #define __vmalloc_array(...) alloc_hooks(__vmalloc_array_noprof(__VA_ARGS__)) extern void *vmalloc_array_noprof(size_t n, size_t size) __alloc_size(1, 2); #define vmalloc_array(...) alloc_hooks(vmalloc_array_noprof(__VA_ARGS__)) extern void *__vcalloc_noprof(size_t n, size_t size, gfp_t flags) __alloc_size(1, 2); #define __vcalloc(...) alloc_hooks(__vcalloc_noprof(__VA_ARGS__)) extern void *vcalloc_noprof(size_t n, size_t size) __alloc_size(1, 2); #define vcalloc(...) alloc_hooks(vcalloc_noprof(__VA_ARGS__)) void * __must_check vrealloc_noprof(const void *p, size_t size, gfp_t flags) __realloc_size(2); #define vrealloc(...) alloc_hooks(vrealloc_noprof(__VA_ARGS__)) extern void vfree(const void *addr); extern void vfree_atomic(const void *addr); extern void *vmap(struct page **pages, unsigned int count, unsigned long flags, pgprot_t prot); void *vmap_pfn(unsigned long *pfns, unsigned int count, pgprot_t prot); extern void vunmap(const void *addr); extern int remap_vmalloc_range_partial(struct vm_area_struct *vma, unsigned long uaddr, void *kaddr, unsigned long pgoff, unsigned long size); extern int remap_vmalloc_range(struct vm_area_struct *vma, void *addr, unsigned long pgoff); int vmap_pages_range(unsigned long addr, unsigned long end, pgprot_t prot, struct page **pages, unsigned int page_shift); /* * Architectures can set this mask to a combination of PGTBL_P?D_MODIFIED values * and let generic vmalloc and ioremap code know when arch_sync_kernel_mappings() * needs to be called. */ #ifndef ARCH_PAGE_TABLE_SYNC_MASK #define ARCH_PAGE_TABLE_SYNC_MASK 0 #endif /* * There is no default implementation for arch_sync_kernel_mappings(). It is * relied upon the compiler to optimize calls out if ARCH_PAGE_TABLE_SYNC_MASK * is 0. */ void arch_sync_kernel_mappings(unsigned long start, unsigned long end); /* * Lowlevel-APIs (not for driver use!) */ static inline size_t get_vm_area_size(const struct vm_struct *area) { if (!(area->flags & VM_NO_GUARD)) /* return actual size without guard page */ return area->size - PAGE_SIZE; else return area->size; } extern struct vm_struct *get_vm_area(unsigned long size, unsigned long flags); extern struct vm_struct *get_vm_area_caller(unsigned long size, unsigned long flags, const void *caller); extern struct vm_struct *__get_vm_area_caller(unsigned long size, unsigned long flags, unsigned long start, unsigned long end, const void *caller); void free_vm_area(struct vm_struct *area); extern struct vm_struct *remove_vm_area(const void *addr); extern struct vm_struct *find_vm_area(const void *addr); struct vmap_area *find_vmap_area(unsigned long addr); static inline bool is_vm_area_hugepages(const void *addr) { /* * This may not 100% tell if the area is mapped with > PAGE_SIZE * page table entries, if for some reason the architecture indicates * larger sizes are available but decides not to use them, nothing * prevents that. This only indicates the size of the physical page * allocated in the vmalloc layer. */ #ifdef CONFIG_HAVE_ARCH_HUGE_VMALLOC return find_vm_area(addr)->page_order > 0; #else return false; #endif } /* for /proc/kcore */ long vread_iter(struct iov_iter *iter, const char *addr, size_t count); /* * Internals. Don't use.. */ __init void vm_area_add_early(struct vm_struct *vm); __init void vm_area_register_early(struct vm_struct *vm, size_t align); int register_vmap_purge_notifier(struct notifier_block *nb); int unregister_vmap_purge_notifier(struct notifier_block *nb); #ifdef CONFIG_MMU #define VMALLOC_TOTAL (VMALLOC_END - VMALLOC_START) unsigned long vmalloc_nr_pages(void); int vm_area_map_pages(struct vm_struct *area, unsigned long start, unsigned long end, struct page **pages); void vm_area_unmap_pages(struct vm_struct *area, unsigned long start, unsigned long end); void vunmap_range(unsigned long addr, unsigned long end); static inline void set_vm_flush_reset_perms(void *addr) { struct vm_struct *vm = find_vm_area(addr); if (vm) vm->flags |= VM_FLUSH_RESET_PERMS; } #else /* !CONFIG_MMU */ #define VMALLOC_TOTAL 0UL static inline unsigned long vmalloc_nr_pages(void) { return 0; } static inline void set_vm_flush_reset_perms(void *addr) {} #endif /* CONFIG_MMU */ #if defined(CONFIG_MMU) && defined(CONFIG_SMP) struct vm_struct **pcpu_get_vm_areas(const unsigned long *offsets, const size_t *sizes, int nr_vms, size_t align); void pcpu_free_vm_areas(struct vm_struct **vms, int nr_vms); # else static inline struct vm_struct ** pcpu_get_vm_areas(const unsigned long *offsets, const size_t *sizes, int nr_vms, size_t align) { return NULL; } static inline void pcpu_free_vm_areas(struct vm_struct **vms, int nr_vms) {} #endif #if defined(CONFIG_MMU) && defined(CONFIG_PRINTK) bool vmalloc_dump_obj(void *object); #else static inline bool vmalloc_dump_obj(void *object) { return false; } #endif #endif /* _LINUX_VMALLOC_H */ |
| 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 | /* SPDX-License-Identifier: GPL-2.0 */ #undef TRACE_SYSTEM #define TRACE_SYSTEM dccp #if !defined(_TRACE_DCCP_H) || defined(TRACE_HEADER_MULTI_READ) #define _TRACE_DCCP_H #include <net/sock.h> #include "dccp.h" #include "ccids/ccid3.h" #include <linux/tracepoint.h> #include <trace/events/net_probe_common.h> TRACE_EVENT(dccp_probe, TP_PROTO(struct sock *sk, size_t size), TP_ARGS(sk, size), TP_STRUCT__entry( /* sockaddr_in6 is always bigger than sockaddr_in */ __array(__u8, saddr, sizeof(struct sockaddr_in6)) __array(__u8, daddr, sizeof(struct sockaddr_in6)) __field(__u16, sport) __field(__u16, dport) __field(__u16, size) __field(__u16, tx_s) __field(__u32, tx_rtt) __field(__u32, tx_p) __field(__u32, tx_x_calc) __field(__u64, tx_x_recv) __field(__u64, tx_x) __field(__u32, tx_t_ipi) ), TP_fast_assign( const struct inet_sock *inet = inet_sk(sk); struct ccid3_hc_tx_sock *hc = NULL; if (ccid_get_current_tx_ccid(dccp_sk(sk)) == DCCPC_CCID3) hc = ccid3_hc_tx_sk(sk); memset(__entry->saddr, 0, sizeof(struct sockaddr_in6)); memset(__entry->daddr, 0, sizeof(struct sockaddr_in6)); TP_STORE_ADDR_PORTS(__entry, inet, sk); /* For filtering use */ __entry->sport = ntohs(inet->inet_sport); __entry->dport = ntohs(inet->inet_dport); __entry->size = size; if (hc) { __entry->tx_s = hc->tx_s; __entry->tx_rtt = hc->tx_rtt; __entry->tx_p = hc->tx_p; __entry->tx_x_calc = hc->tx_x_calc; __entry->tx_x_recv = hc->tx_x_recv >> 6; __entry->tx_x = hc->tx_x >> 6; __entry->tx_t_ipi = hc->tx_t_ipi; } else { __entry->tx_s = 0; memset_startat(__entry, 0, tx_rtt); } ), TP_printk("src=%pISpc dest=%pISpc size=%d tx_s=%d tx_rtt=%d " "tx_p=%d tx_x_calc=%u tx_x_recv=%llu tx_x=%llu tx_t_ipi=%d", __entry->saddr, __entry->daddr, __entry->size, __entry->tx_s, __entry->tx_rtt, __entry->tx_p, __entry->tx_x_calc, __entry->tx_x_recv, __entry->tx_x, __entry->tx_t_ipi) ); #endif /* _TRACE_TCP_H */ /* This part must be outside protection */ #undef TRACE_INCLUDE_PATH #define TRACE_INCLUDE_PATH . #undef TRACE_INCLUDE_FILE #define TRACE_INCLUDE_FILE trace #include <trace/define_trace.h> |
| 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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 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 | // SPDX-License-Identifier: GPL-2.0 /* * linux/ipc/shm.c * Copyright (C) 1992, 1993 Krishna Balasubramanian * Many improvements/fixes by Bruno Haible. * Replaced `struct shm_desc' by `struct vm_area_struct', July 1994. * Fixed the shm swap deallocation (shm_unuse()), August 1998 Andrea Arcangeli. * * /proc/sysvipc/shm support (c) 1999 Dragos Acostachioaie <dragos@iname.com> * BIGMEM support, Andrea Arcangeli <andrea@suse.de> * SMP thread shm, Jean-Luc Boyard <jean-luc.boyard@siemens.fr> * HIGHMEM support, Ingo Molnar <mingo@redhat.com> * Make shmmax, shmall, shmmni sysctl'able, Christoph Rohland <cr@sap.com> * Shared /dev/zero support, Kanoj Sarcar <kanoj@sgi.com> * Move the mm functionality over to mm/shmem.c, Christoph Rohland <cr@sap.com> * * support for audit of ipc object properties and permission changes * Dustin Kirkland <dustin.kirkland@us.ibm.com> * * namespaces support * OpenVZ, SWsoft Inc. * Pavel Emelianov <xemul@openvz.org> * * Better ipc lock (kern_ipc_perm.lock) handling * Davidlohr Bueso <davidlohr.bueso@hp.com>, June 2013. */ #include <linux/slab.h> #include <linux/mm.h> #include <linux/hugetlb.h> #include <linux/shm.h> #include <uapi/linux/shm.h> #include <linux/init.h> #include <linux/file.h> #include <linux/mman.h> #include <linux/shmem_fs.h> #include <linux/security.h> #include <linux/syscalls.h> #include <linux/audit.h> #include <linux/capability.h> #include <linux/ptrace.h> #include <linux/seq_file.h> #include <linux/rwsem.h> #include <linux/nsproxy.h> #include <linux/mount.h> #include <linux/ipc_namespace.h> #include <linux/rhashtable.h> #include <linux/uaccess.h> #include "util.h" struct shmid_kernel /* private to the kernel */ { struct kern_ipc_perm shm_perm; struct file *shm_file; unsigned long shm_nattch; unsigned long shm_segsz; time64_t shm_atim; time64_t shm_dtim; time64_t shm_ctim; struct pid *shm_cprid; struct pid *shm_lprid; struct ucounts *mlock_ucounts; /* * The task created the shm object, for * task_lock(shp->shm_creator) */ struct task_struct *shm_creator; /* * List by creator. task_lock(->shm_creator) required for read/write. * If list_empty(), then the creator is dead already. */ struct list_head shm_clist; struct ipc_namespace *ns; } __randomize_layout; /* shm_mode upper byte flags */ #define SHM_DEST 01000 /* segment will be destroyed on last detach */ #define SHM_LOCKED 02000 /* segment will not be swapped */ struct shm_file_data { int id; struct ipc_namespace *ns; struct file *file; const struct vm_operations_struct *vm_ops; }; #define shm_file_data(file) (*((struct shm_file_data **)&(file)->private_data)) static const struct file_operations shm_file_operations; static const struct vm_operations_struct shm_vm_ops; #define shm_ids(ns) ((ns)->ids[IPC_SHM_IDS]) #define shm_unlock(shp) \ ipc_unlock(&(shp)->shm_perm) static int newseg(struct ipc_namespace *, struct ipc_params *); static void shm_open(struct vm_area_struct *vma); static void shm_close(struct vm_area_struct *vma); static void shm_destroy(struct ipc_namespace *ns, struct shmid_kernel *shp); #ifdef CONFIG_PROC_FS static int sysvipc_shm_proc_show(struct seq_file *s, void *it); #endif void shm_init_ns(struct ipc_namespace *ns) { ns->shm_ctlmax = SHMMAX; ns->shm_ctlall = SHMALL; ns->shm_ctlmni = SHMMNI; ns->shm_rmid_forced = 0; ns->shm_tot = 0; ipc_init_ids(&shm_ids(ns)); } /* * Called with shm_ids.rwsem (writer) and the shp structure locked. * Only shm_ids.rwsem remains locked on exit. */ static void do_shm_rmid(struct ipc_namespace *ns, struct kern_ipc_perm *ipcp) { struct shmid_kernel *shp; shp = container_of(ipcp, struct shmid_kernel, shm_perm); WARN_ON(ns != shp->ns); if (shp->shm_nattch) { shp->shm_perm.mode |= SHM_DEST; /* Do not find it any more */ ipc_set_key_private(&shm_ids(ns), &shp->shm_perm); shm_unlock(shp); } else shm_destroy(ns, shp); } #ifdef CONFIG_IPC_NS void shm_exit_ns(struct ipc_namespace *ns) { free_ipcs(ns, &shm_ids(ns), do_shm_rmid); idr_destroy(&ns->ids[IPC_SHM_IDS].ipcs_idr); rhashtable_destroy(&ns->ids[IPC_SHM_IDS].key_ht); } #endif static int __init ipc_ns_init(void) { shm_init_ns(&init_ipc_ns); return 0; } pure_initcall(ipc_ns_init); void __init shm_init(void) { ipc_init_proc_interface("sysvipc/shm", #if BITS_PER_LONG <= 32 " key shmid perms size cpid lpid nattch uid gid cuid cgid atime dtime ctime rss swap\n", #else " key shmid perms size cpid lpid nattch uid gid cuid cgid atime dtime ctime rss swap\n", #endif IPC_SHM_IDS, sysvipc_shm_proc_show); } static inline struct shmid_kernel *shm_obtain_object(struct ipc_namespace *ns, int id) { struct kern_ipc_perm *ipcp = ipc_obtain_object_idr(&shm_ids(ns), id); if (IS_ERR(ipcp)) return ERR_CAST(ipcp); return container_of(ipcp, struct shmid_kernel, shm_perm); } static inline struct shmid_kernel *shm_obtain_object_check(struct ipc_namespace *ns, int id) { struct kern_ipc_perm *ipcp = ipc_obtain_object_check(&shm_ids(ns), id); if (IS_ERR(ipcp)) return ERR_CAST(ipcp); return container_of(ipcp, struct shmid_kernel, shm_perm); } /* * shm_lock_(check_) routines are called in the paths where the rwsem * is not necessarily held. */ static inline struct shmid_kernel *shm_lock(struct ipc_namespace *ns, int id) { struct kern_ipc_perm *ipcp; rcu_read_lock(); ipcp = ipc_obtain_object_idr(&shm_ids(ns), id); if (IS_ERR(ipcp)) goto err; ipc_lock_object(ipcp); /* * ipc_rmid() may have already freed the ID while ipc_lock_object() * was spinning: here verify that the structure is still valid. * Upon races with RMID, return -EIDRM, thus indicating that * the ID points to a removed identifier. */ if (ipc_valid_object(ipcp)) { /* return a locked ipc object upon success */ return container_of(ipcp, struct shmid_kernel, shm_perm); } ipc_unlock_object(ipcp); ipcp = ERR_PTR(-EIDRM); err: rcu_read_unlock(); /* * Callers of shm_lock() must validate the status of the returned ipc * object pointer and error out as appropriate. */ return ERR_CAST(ipcp); } static inline void shm_lock_by_ptr(struct shmid_kernel *ipcp) { rcu_read_lock(); ipc_lock_object(&ipcp->shm_perm); } static void shm_rcu_free(struct rcu_head *head) { struct kern_ipc_perm *ptr = container_of(head, struct kern_ipc_perm, rcu); struct shmid_kernel *shp = container_of(ptr, struct shmid_kernel, shm_perm); security_shm_free(&shp->shm_perm); kfree(shp); } /* * It has to be called with shp locked. * It must be called before ipc_rmid() */ static inline void shm_clist_rm(struct shmid_kernel *shp) { struct task_struct *creator; /* ensure that shm_creator does not disappear */ rcu_read_lock(); /* * A concurrent exit_shm may do a list_del_init() as well. * Just do nothing if exit_shm already did the work */ if (!list_empty(&shp->shm_clist)) { /* * shp->shm_creator is guaranteed to be valid *only* * if shp->shm_clist is not empty. */ creator = shp->shm_creator; task_lock(creator); /* * list_del_init() is a nop if the entry was already removed * from the list. */ list_del_init(&shp->shm_clist); task_unlock(creator); } rcu_read_unlock(); } static inline void shm_rmid(struct shmid_kernel *s) { shm_clist_rm(s); ipc_rmid(&shm_ids(s->ns), &s->shm_perm); } static int __shm_open(struct shm_file_data *sfd) { struct shmid_kernel *shp; shp = shm_lock(sfd->ns, sfd->id); if (IS_ERR(shp)) return PTR_ERR(shp); if (shp->shm_file != sfd->file) { /* ID was reused */ shm_unlock(shp); return -EINVAL; } shp->shm_atim = ktime_get_real_seconds(); ipc_update_pid(&shp->shm_lprid, task_tgid(current)); shp->shm_nattch++; shm_unlock(shp); return 0; } /* This is called by fork, once for every shm attach. */ static void shm_open(struct vm_area_struct *vma) { struct file *file = vma->vm_file; struct shm_file_data *sfd = shm_file_data(file); int err; /* Always call underlying open if present */ if (sfd->vm_ops->open) sfd->vm_ops->open(vma); err = __shm_open(sfd); /* * We raced in the idr lookup or with shm_destroy(). * Either way, the ID is busted. */ WARN_ON_ONCE(err); } /* * shm_destroy - free the struct shmid_kernel * * @ns: namespace * @shp: struct to free * * It has to be called with shp and shm_ids.rwsem (writer) locked, * but returns with shp unlocked and freed. */ static void shm_destroy(struct ipc_namespace *ns, struct shmid_kernel *shp) { struct file *shm_file; shm_file = shp->shm_file; shp->shm_file = NULL; ns->shm_tot -= (shp->shm_segsz + PAGE_SIZE - 1) >> PAGE_SHIFT; shm_rmid(shp); shm_unlock(shp); if (!is_file_hugepages(shm_file)) shmem_lock(shm_file, 0, shp->mlock_ucounts); fput(shm_file); ipc_update_pid(&shp->shm_cprid, NULL); ipc_update_pid(&shp->shm_lprid, NULL); ipc_rcu_putref(&shp->shm_perm, shm_rcu_free); } /* * shm_may_destroy - identifies whether shm segment should be destroyed now * * Returns true if and only if there are no active users of the segment and * one of the following is true: * * 1) shmctl(id, IPC_RMID, NULL) was called for this shp * * 2) sysctl kernel.shm_rmid_forced is set to 1. */ static bool shm_may_destroy(struct shmid_kernel *shp) { return (shp->shm_nattch == 0) && (shp->ns->shm_rmid_forced || (shp->shm_perm.mode & SHM_DEST)); } /* * remove the attach descriptor vma. * free memory for segment if it is marked destroyed. * The descriptor has already been removed from the current->mm->mmap list * and will later be kfree()d. */ static void __shm_close(struct shm_file_data *sfd) { struct shmid_kernel *shp; struct ipc_namespace *ns = sfd->ns; down_write(&shm_ids(ns).rwsem); /* remove from the list of attaches of the shm segment */ shp = shm_lock(ns, sfd->id); /* * We raced in the idr lookup or with shm_destroy(). * Either way, the ID is busted. */ if (WARN_ON_ONCE(IS_ERR(shp))) goto done; /* no-op */ ipc_update_pid(&shp->shm_lprid, task_tgid(current)); shp->shm_dtim = ktime_get_real_seconds(); shp->shm_nattch--; if (shm_may_destroy(shp)) shm_destroy(ns, shp); else shm_unlock(shp); done: up_write(&shm_ids(ns).rwsem); } static void shm_close(struct vm_area_struct *vma) { struct file *file = vma->vm_file; struct shm_file_data *sfd = shm_file_data(file); /* Always call underlying close if present */ if (sfd->vm_ops->close) sfd->vm_ops->close(vma); __shm_close(sfd); } /* Called with ns->shm_ids(ns).rwsem locked */ static int shm_try_destroy_orphaned(int id, void *p, void *data) { struct ipc_namespace *ns = data; struct kern_ipc_perm *ipcp = p; struct shmid_kernel *shp = container_of(ipcp, struct shmid_kernel, shm_perm); /* * We want to destroy segments without users and with already * exit'ed originating process. * * As shp->* are changed under rwsem, it's safe to skip shp locking. */ if (!list_empty(&shp->shm_clist)) return 0; if (shm_may_destroy(shp)) { shm_lock_by_ptr(shp); shm_destroy(ns, shp); } return 0; } void shm_destroy_orphaned(struct ipc_namespace *ns) { down_write(&shm_ids(ns).rwsem); if (shm_ids(ns).in_use) idr_for_each(&shm_ids(ns).ipcs_idr, &shm_try_destroy_orphaned, ns); up_write(&shm_ids(ns).rwsem); } /* Locking assumes this will only be called with task == current */ void exit_shm(struct task_struct *task) { for (;;) { struct shmid_kernel *shp; struct ipc_namespace *ns; task_lock(task); if (list_empty(&task->sysvshm.shm_clist)) { task_unlock(task); break; } shp = list_first_entry(&task->sysvshm.shm_clist, struct shmid_kernel, shm_clist); /* * 1) Get pointer to the ipc namespace. It is worth to say * that this pointer is guaranteed to be valid because * shp lifetime is always shorter than namespace lifetime * in which shp lives. * We taken task_lock it means that shp won't be freed. */ ns = shp->ns; /* * 2) If kernel.shm_rmid_forced is not set then only keep track of * which shmids are orphaned, so that a later set of the sysctl * can clean them up. */ if (!ns->shm_rmid_forced) goto unlink_continue; /* * 3) get a reference to the namespace. * The refcount could be already 0. If it is 0, then * the shm objects will be free by free_ipc_work(). */ ns = get_ipc_ns_not_zero(ns); if (!ns) { unlink_continue: list_del_init(&shp->shm_clist); task_unlock(task); continue; } /* * 4) get a reference to shp. * This cannot fail: shm_clist_rm() is called before * ipc_rmid(), thus the refcount cannot be 0. */ WARN_ON(!ipc_rcu_getref(&shp->shm_perm)); /* * 5) unlink the shm segment from the list of segments * created by current. * This must be done last. After unlinking, * only the refcounts obtained above prevent IPC_RMID * from destroying the segment or the namespace. */ list_del_init(&shp->shm_clist); task_unlock(task); /* * 6) we have all references * Thus lock & if needed destroy shp. */ down_write(&shm_ids(ns).rwsem); shm_lock_by_ptr(shp); /* * rcu_read_lock was implicitly taken in shm_lock_by_ptr, it's * safe to call ipc_rcu_putref here */ ipc_rcu_putref(&shp->shm_perm, shm_rcu_free); if (ipc_valid_object(&shp->shm_perm)) { if (shm_may_destroy(shp)) shm_destroy(ns, shp); else shm_unlock(shp); } else { /* * Someone else deleted the shp from namespace * idr/kht while we have waited. * Just unlock and continue. */ shm_unlock(shp); } up_write(&shm_ids(ns).rwsem); put_ipc_ns(ns); /* paired with get_ipc_ns_not_zero */ } } static vm_fault_t shm_fault(struct vm_fault *vmf) { struct file *file = vmf->vma->vm_file; struct shm_file_data *sfd = shm_file_data(file); return sfd->vm_ops->fault(vmf); } static int shm_may_split(struct vm_area_struct *vma, unsigned long addr) { struct file *file = vma->vm_file; struct shm_file_data *sfd = shm_file_data(file); if (sfd->vm_ops->may_split) return sfd->vm_ops->may_split(vma, addr); return 0; } static unsigned long shm_pagesize(struct vm_area_struct *vma) { struct file *file = vma->vm_file; struct shm_file_data *sfd = shm_file_data(file); if (sfd->vm_ops->pagesize) return sfd->vm_ops->pagesize(vma); return PAGE_SIZE; } #ifdef CONFIG_NUMA static int shm_set_policy(struct vm_area_struct *vma, struct mempolicy *mpol) { struct shm_file_data *sfd = shm_file_data(vma->vm_file); int err = 0; if (sfd->vm_ops->set_policy) err = sfd->vm_ops->set_policy(vma, mpol); return err; } static struct mempolicy *shm_get_policy(struct vm_area_struct *vma, unsigned long addr, pgoff_t *ilx) { struct shm_file_data *sfd = shm_file_data(vma->vm_file); struct mempolicy *mpol = vma->vm_policy; if (sfd->vm_ops->get_policy) mpol = sfd->vm_ops->get_policy(vma, addr, ilx); return mpol; } #endif static int shm_mmap(struct file *file, struct vm_area_struct *vma) { struct shm_file_data *sfd = shm_file_data(file); int ret; /* * In case of remap_file_pages() emulation, the file can represent an * IPC ID that was removed, and possibly even reused by another shm * segment already. Propagate this case as an error to caller. */ ret = __shm_open(sfd); if (ret) return ret; ret = call_mmap(sfd->file, vma); if (ret) { __shm_close(sfd); return ret; } sfd->vm_ops = vma->vm_ops; #ifdef CONFIG_MMU WARN_ON(!sfd->vm_ops->fault); #endif vma->vm_ops = &shm_vm_ops; return 0; } static int shm_release(struct inode *ino, struct file *file) { struct shm_file_data *sfd = shm_file_data(file); put_ipc_ns(sfd->ns); fput(sfd->file); shm_file_data(file) = NULL; kfree(sfd); return 0; } static int shm_fsync(struct file *file, loff_t start, loff_t end, int datasync) { struct shm_file_data *sfd = shm_file_data(file); if (!sfd->file->f_op->fsync) return -EINVAL; return sfd->file->f_op->fsync(sfd->file, start, end, datasync); } static long shm_fallocate(struct file *file, int mode, loff_t offset, loff_t len) { struct shm_file_data *sfd = shm_file_data(file); if (!sfd->file->f_op->fallocate) return -EOPNOTSUPP; return sfd->file->f_op->fallocate(file, mode, offset, len); } static unsigned long shm_get_unmapped_area(struct file *file, unsigned long addr, unsigned long len, unsigned long pgoff, unsigned long flags) { struct shm_file_data *sfd = shm_file_data(file); return sfd->file->f_op->get_unmapped_area(sfd->file, addr, len, pgoff, flags); } static const struct file_operations shm_file_operations = { .mmap = shm_mmap, .fsync = shm_fsync, .release = shm_release, .get_unmapped_area = shm_get_unmapped_area, .llseek = noop_llseek, .fallocate = shm_fallocate, }; /* * shm_file_operations_huge is now identical to shm_file_operations * except for fop_flags */ static const struct file_operations shm_file_operations_huge = { .mmap = shm_mmap, .fsync = shm_fsync, .release = shm_release, .get_unmapped_area = shm_get_unmapped_area, .llseek = noop_llseek, .fallocate = shm_fallocate, .fop_flags = FOP_HUGE_PAGES, }; static const struct vm_operations_struct shm_vm_ops = { .open = shm_open, /* callback for a new vm-area open */ .close = shm_close, /* callback for when the vm-area is released */ .fault = shm_fault, .may_split = shm_may_split, .pagesize = shm_pagesize, #if defined(CONFIG_NUMA) .set_policy = shm_set_policy, .get_policy = shm_get_policy, #endif }; /** * newseg - Create a new shared memory segment * @ns: namespace * @params: ptr to the structure that contains key, size and shmflg * * Called with shm_ids.rwsem held as a writer. */ static int newseg(struct ipc_namespace *ns, struct ipc_params *params) { key_t key = params->key; int shmflg = params->flg; size_t size = params->u.size; int error; struct shmid_kernel *shp; size_t numpages = (size + PAGE_SIZE - 1) >> PAGE_SHIFT; struct file *file; char name[13]; vm_flags_t acctflag = 0; if (size < SHMMIN || size > ns->shm_ctlmax) return -EINVAL; if (numpages << PAGE_SHIFT < size) return -ENOSPC; if (ns->shm_tot + numpages < ns->shm_tot || ns->shm_tot + numpages > ns->shm_ctlall) return -ENOSPC; shp = kmalloc(sizeof(*shp), GFP_KERNEL_ACCOUNT); if (unlikely(!shp)) return -ENOMEM; shp->shm_perm.key = key; shp->shm_perm.mode = (shmflg & S_IRWXUGO); shp->mlock_ucounts = NULL; shp->shm_perm.security = NULL; error = security_shm_alloc(&shp->shm_perm); if (error) { kfree(shp); return error; } sprintf(name, "SYSV%08x", key); if (shmflg & SHM_HUGETLB) { struct hstate *hs; size_t hugesize; hs = hstate_sizelog((shmflg >> SHM_HUGE_SHIFT) & SHM_HUGE_MASK); if (!hs) { error = -EINVAL; goto no_file; } hugesize = ALIGN(size, huge_page_size(hs)); /* hugetlb_file_setup applies strict accounting */ if (shmflg & SHM_NORESERVE) acctflag = VM_NORESERVE; file = hugetlb_file_setup(name, hugesize, acctflag, HUGETLB_SHMFS_INODE, (shmflg >> SHM_HUGE_SHIFT) & SHM_HUGE_MASK); } else { /* * Do not allow no accounting for OVERCOMMIT_NEVER, even * if it's asked for. */ if ((shmflg & SHM_NORESERVE) && sysctl_overcommit_memory != OVERCOMMIT_NEVER) acctflag = VM_NORESERVE; file = shmem_kernel_file_setup(name, size, acctflag); } error = PTR_ERR(file); if (IS_ERR(file)) goto no_file; shp->shm_cprid = get_pid(task_tgid(current)); shp->shm_lprid = NULL; shp->shm_atim = shp->shm_dtim = 0; shp->shm_ctim = ktime_get_real_seconds(); shp->shm_segsz = size; shp->shm_nattch = 0; shp->shm_file = file; shp->shm_creator = current; /* ipc_addid() locks shp upon success. */ error = ipc_addid(&shm_ids(ns), &shp->shm_perm, ns->shm_ctlmni); if (error < 0) goto no_id; shp->ns = ns; task_lock(current); list_add(&shp->shm_clist, ¤t->sysvshm.shm_clist); task_unlock(current); /* * shmid gets reported as "inode#" in /proc/pid/maps. * proc-ps tools use this. Changing this will break them. */ file_inode(file)->i_ino = shp->shm_perm.id; ns->shm_tot += numpages; error = shp->shm_perm.id; ipc_unlock_object(&shp->shm_perm); rcu_read_unlock(); return error; no_id: ipc_update_pid(&shp->shm_cprid, NULL); ipc_update_pid(&shp->shm_lprid, NULL); fput(file); ipc_rcu_putref(&shp->shm_perm, shm_rcu_free); return error; no_file: call_rcu(&shp->shm_perm.rcu, shm_rcu_free); return error; } /* * Called with shm_ids.rwsem and ipcp locked. */ static int shm_more_checks(struct kern_ipc_perm *ipcp, struct ipc_params *params) { struct shmid_kernel *shp; shp = container_of(ipcp, struct shmid_kernel, shm_perm); if (shp->shm_segsz < params->u.size) return -EINVAL; return 0; } long ksys_shmget(key_t key, size_t size, int shmflg) { struct ipc_namespace *ns; static const struct ipc_ops shm_ops = { .getnew = newseg, .associate = security_shm_associate, .more_checks = shm_more_checks, }; struct ipc_params shm_params; ns = current->nsproxy->ipc_ns; shm_params.key = key; shm_params.flg = shmflg; shm_params.u.size = size; return ipcget(ns, &shm_ids(ns), &shm_ops, &shm_params); } SYSCALL_DEFINE3(shmget, key_t, key, size_t, size, int, shmflg) { return ksys_shmget(key, size, shmflg); } static inline unsigned long copy_shmid_to_user(void __user *buf, struct shmid64_ds *in, int version) { switch (version) { case IPC_64: return copy_to_user(buf, in, sizeof(*in)); case IPC_OLD: { struct shmid_ds out; memset(&out, 0, sizeof(out)); ipc64_perm_to_ipc_perm(&in->shm_perm, &out.shm_perm); out.shm_segsz = in->shm_segsz; out.shm_atime = in->shm_atime; out.shm_dtime = in->shm_dtime; out.shm_ctime = in->shm_ctime; out.shm_cpid = in->shm_cpid; out.shm_lpid = in->shm_lpid; out.shm_nattch = in->shm_nattch; return copy_to_user(buf, &out, sizeof(out)); } default: return -EINVAL; } } static inline unsigned long copy_shmid_from_user(struct shmid64_ds *out, void __user *buf, int version) { switch (version) { case IPC_64: if (copy_from_user(out, buf, sizeof(*out))) return -EFAULT; return 0; case IPC_OLD: { struct shmid_ds tbuf_old; if (copy_from_user(&tbuf_old, buf, sizeof(tbuf_old))) return -EFAULT; out->shm_perm.uid = tbuf_old.shm_perm.uid; out->shm_perm.gid = tbuf_old.shm_perm.gid; out->shm_perm.mode = tbuf_old.shm_perm.mode; return 0; } default: return -EINVAL; } } static inline unsigned long copy_shminfo_to_user(void __user *buf, struct shminfo64 *in, int version) { switch (version) { case IPC_64: return copy_to_user(buf, in, sizeof(*in)); case IPC_OLD: { struct shminfo out; if (in->shmmax > INT_MAX) out.shmmax = INT_MAX; else out.shmmax = (int)in->shmmax; out.shmmin = in->shmmin; out.shmmni = in->shmmni; out.shmseg = in->shmseg; out.shmall = in->shmall; return copy_to_user(buf, &out, sizeof(out)); } default: return -EINVAL; } } /* * Calculate and add used RSS and swap pages of a shm. * Called with shm_ids.rwsem held as a reader */ static void shm_add_rss_swap(struct shmid_kernel *shp, unsigned long *rss_add, unsigned long *swp_add) { struct inode *inode; inode = file_inode(shp->shm_file); if (is_file_hugepages(shp->shm_file)) { struct address_space *mapping = inode->i_mapping; struct hstate *h = hstate_file(shp->shm_file); *rss_add += pages_per_huge_page(h) * mapping->nrpages; } else { #ifdef CONFIG_SHMEM struct shmem_inode_info *info = SHMEM_I(inode); spin_lock_irq(&info->lock); *rss_add += inode->i_mapping->nrpages; *swp_add += info->swapped; spin_unlock_irq(&info->lock); #else *rss_add += inode->i_mapping->nrpages; #endif } } /* * Called with shm_ids.rwsem held as a reader */ static void shm_get_stat(struct ipc_namespace *ns, unsigned long *rss, unsigned long *swp) { int next_id; int total, in_use; *rss = 0; *swp = 0; in_use = shm_ids(ns).in_use; for (total = 0, next_id = 0; total < in_use; next_id++) { struct kern_ipc_perm *ipc; struct shmid_kernel *shp; ipc = idr_find(&shm_ids(ns).ipcs_idr, next_id); if (ipc == NULL) continue; shp = container_of(ipc, struct shmid_kernel, shm_perm); shm_add_rss_swap(shp, rss, swp); total++; } } /* * This function handles some shmctl commands which require the rwsem * to be held in write mode. * NOTE: no locks must be held, the rwsem is taken inside this function. */ static int shmctl_down(struct ipc_namespace *ns, int shmid, int cmd, struct shmid64_ds *shmid64) { struct kern_ipc_perm *ipcp; struct shmid_kernel *shp; int err; down_write(&shm_ids(ns).rwsem); rcu_read_lock(); ipcp = ipcctl_obtain_check(ns, &shm_ids(ns), shmid, cmd, &shmid64->shm_perm, 0); if (IS_ERR(ipcp)) { err = PTR_ERR(ipcp); goto out_unlock1; } shp = container_of(ipcp, struct shmid_kernel, shm_perm); err = security_shm_shmctl(&shp->shm_perm, cmd); if (err) goto out_unlock1; switch (cmd) { case IPC_RMID: ipc_lock_object(&shp->shm_perm); /* do_shm_rmid unlocks the ipc object and rcu */ do_shm_rmid(ns, ipcp); goto out_up; case IPC_SET: ipc_lock_object(&shp->shm_perm); err = ipc_update_perm(&shmid64->shm_perm, ipcp); if (err) goto out_unlock0; shp->shm_ctim = ktime_get_real_seconds(); break; default: err = -EINVAL; goto out_unlock1; } out_unlock0: ipc_unlock_object(&shp->shm_perm); out_unlock1: rcu_read_unlock(); out_up: up_write(&shm_ids(ns).rwsem); return err; } static int shmctl_ipc_info(struct ipc_namespace *ns, struct shminfo64 *shminfo) { int err = security_shm_shmctl(NULL, IPC_INFO); if (!err) { memset(shminfo, 0, sizeof(*shminfo)); shminfo->shmmni = shminfo->shmseg = ns->shm_ctlmni; shminfo->shmmax = ns->shm_ctlmax; shminfo->shmall = ns->shm_ctlall; shminfo->shmmin = SHMMIN; down_read(&shm_ids(ns).rwsem); err = ipc_get_maxidx(&shm_ids(ns)); up_read(&shm_ids(ns).rwsem); if (err < 0) err = 0; } return err; } static int shmctl_shm_info(struct ipc_namespace *ns, struct shm_info *shm_info) { int err = security_shm_shmctl(NULL, SHM_INFO); if (!err) { memset(shm_info, 0, sizeof(*shm_info)); down_read(&shm_ids(ns).rwsem); shm_info->used_ids = shm_ids(ns).in_use; shm_get_stat(ns, &shm_info->shm_rss, &shm_info->shm_swp); shm_info->shm_tot = ns->shm_tot; shm_info->swap_attempts = 0; shm_info->swap_successes = 0; err = ipc_get_maxidx(&shm_ids(ns)); up_read(&shm_ids(ns).rwsem); if (err < 0) err = 0; } return err; } static int shmctl_stat(struct ipc_namespace *ns, int shmid, int cmd, struct shmid64_ds *tbuf) { struct shmid_kernel *shp; int err; memset(tbuf, 0, sizeof(*tbuf)); rcu_read_lock(); if (cmd == SHM_STAT || cmd == SHM_STAT_ANY) { shp = shm_obtain_object(ns, shmid); if (IS_ERR(shp)) { err = PTR_ERR(shp); goto out_unlock; } } else { /* IPC_STAT */ shp = shm_obtain_object_check(ns, shmid); if (IS_ERR(shp)) { err = PTR_ERR(shp); goto out_unlock; } } /* * Semantically SHM_STAT_ANY ought to be identical to * that functionality provided by the /proc/sysvipc/ * interface. As such, only audit these calls and * do not do traditional S_IRUGO permission checks on * the ipc object. */ if (cmd == SHM_STAT_ANY) audit_ipc_obj(&shp->shm_perm); else { err = -EACCES; if (ipcperms(ns, &shp->shm_perm, S_IRUGO)) goto out_unlock; } err = security_shm_shmctl(&shp->shm_perm, cmd); if (err) goto out_unlock; ipc_lock_object(&shp->shm_perm); if (!ipc_valid_object(&shp->shm_perm)) { ipc_unlock_object(&shp->shm_perm); err = -EIDRM; goto out_unlock; } kernel_to_ipc64_perm(&shp->shm_perm, &tbuf->shm_perm); tbuf->shm_segsz = shp->shm_segsz; tbuf->shm_atime = shp->shm_atim; tbuf->shm_dtime = shp->shm_dtim; tbuf->shm_ctime = shp->shm_ctim; #ifndef CONFIG_64BIT tbuf->shm_atime_high = shp->shm_atim >> 32; tbuf->shm_dtime_high = shp->shm_dtim >> 32; tbuf->shm_ctime_high = shp->shm_ctim >> 32; #endif tbuf->shm_cpid = pid_vnr(shp->shm_cprid); tbuf->shm_lpid = pid_vnr(shp->shm_lprid); tbuf->shm_nattch = shp->shm_nattch; if (cmd == IPC_STAT) { /* * As defined in SUS: * Return 0 on success */ err = 0; } else { /* * SHM_STAT and SHM_STAT_ANY (both Linux specific) * Return the full id, including the sequence number */ err = shp->shm_perm.id; } ipc_unlock_object(&shp->shm_perm); out_unlock: rcu_read_unlock(); return err; } static int shmctl_do_lock(struct ipc_namespace *ns, int shmid, int cmd) { struct shmid_kernel *shp; struct file *shm_file; int err; rcu_read_lock(); shp = shm_obtain_object_check(ns, shmid); if (IS_ERR(shp)) { err = PTR_ERR(shp); goto out_unlock1; } audit_ipc_obj(&(shp->shm_perm)); err = security_shm_shmctl(&shp->shm_perm, cmd); if (err) goto out_unlock1; ipc_lock_object(&shp->shm_perm); /* check if shm_destroy() is tearing down shp */ if (!ipc_valid_object(&shp->shm_perm)) { err = -EIDRM; goto out_unlock0; } if (!ns_capable(ns->user_ns, CAP_IPC_LOCK)) { kuid_t euid = current_euid(); if (!uid_eq(euid, shp->shm_perm.uid) && !uid_eq(euid, shp->shm_perm.cuid)) { err = -EPERM; goto out_unlock0; } if (cmd == SHM_LOCK && !rlimit(RLIMIT_MEMLOCK)) { err = -EPERM; goto out_unlock0; } } shm_file = shp->shm_file; if (is_file_hugepages(shm_file)) goto out_unlock0; if (cmd == SHM_LOCK) { struct ucounts *ucounts = current_ucounts(); err = shmem_lock(shm_file, 1, ucounts); if (!err && !(shp->shm_perm.mode & SHM_LOCKED)) { shp->shm_perm.mode |= SHM_LOCKED; shp->mlock_ucounts = ucounts; } goto out_unlock0; } /* SHM_UNLOCK */ if (!(shp->shm_perm.mode & SHM_LOCKED)) goto out_unlock0; shmem_lock(shm_file, 0, shp->mlock_ucounts); shp->shm_perm.mode &= ~SHM_LOCKED; shp->mlock_ucounts = NULL; get_file(shm_file); ipc_unlock_object(&shp->shm_perm); rcu_read_unlock(); shmem_unlock_mapping(shm_file->f_mapping); fput(shm_file); return err; out_unlock0: ipc_unlock_object(&shp->shm_perm); out_unlock1: rcu_read_unlock(); return err; } static long ksys_shmctl(int shmid, int cmd, struct shmid_ds __user *buf, int version) { int err; struct ipc_namespace *ns; struct shmid64_ds sem64; if (cmd < 0 || shmid < 0) return -EINVAL; ns = current->nsproxy->ipc_ns; switch (cmd) { case IPC_INFO: { struct shminfo64 shminfo; err = shmctl_ipc_info(ns, &shminfo); if (err < 0) return err; if (copy_shminfo_to_user(buf, &shminfo, version)) err = -EFAULT; return err; } case SHM_INFO: { struct shm_info shm_info; err = shmctl_shm_info(ns, &shm_info); if (err < 0) return err; if (copy_to_user(buf, &shm_info, sizeof(shm_info))) err = -EFAULT; return err; } case SHM_STAT: case SHM_STAT_ANY: case IPC_STAT: { err = shmctl_stat(ns, shmid, cmd, &sem64); if (err < 0) return err; if (copy_shmid_to_user(buf, &sem64, version)) err = -EFAULT; return err; } case IPC_SET: if (copy_shmid_from_user(&sem64, buf, version)) return -EFAULT; fallthrough; case IPC_RMID: return shmctl_down(ns, shmid, cmd, &sem64); case SHM_LOCK: case SHM_UNLOCK: return shmctl_do_lock(ns, shmid, cmd); default: return -EINVAL; } } SYSCALL_DEFINE3(shmctl, int, shmid, int, cmd, struct shmid_ds __user *, buf) { return ksys_shmctl(shmid, cmd, buf, IPC_64); } #ifdef CONFIG_ARCH_WANT_IPC_PARSE_VERSION long ksys_old_shmctl(int shmid, int cmd, struct shmid_ds __user *buf) { int version = ipc_parse_version(&cmd); return ksys_shmctl(shmid, cmd, buf, version); } SYSCALL_DEFINE3(old_shmctl, int, shmid, int, cmd, struct shmid_ds __user *, buf) { return ksys_old_shmctl(shmid, cmd, buf); } #endif #ifdef CONFIG_COMPAT struct compat_shmid_ds { struct compat_ipc_perm shm_perm; int shm_segsz; old_time32_t shm_atime; old_time32_t shm_dtime; old_time32_t shm_ctime; compat_ipc_pid_t shm_cpid; compat_ipc_pid_t shm_lpid; unsigned short shm_nattch; unsigned short shm_unused; compat_uptr_t shm_unused2; compat_uptr_t shm_unused3; }; struct compat_shminfo64 { compat_ulong_t shmmax; compat_ulong_t shmmin; compat_ulong_t shmmni; compat_ulong_t shmseg; compat_ulong_t shmall; compat_ulong_t __unused1; compat_ulong_t __unused2; compat_ulong_t __unused3; compat_ulong_t __unused4; }; struct compat_shm_info { compat_int_t used_ids; compat_ulong_t shm_tot, shm_rss, shm_swp; compat_ulong_t swap_attempts, swap_successes; }; static int copy_compat_shminfo_to_user(void __user *buf, struct shminfo64 *in, int version) { if (in->shmmax > INT_MAX) in->shmmax = INT_MAX; if (version == IPC_64) { struct compat_shminfo64 info; memset(&info, 0, sizeof(info)); info.shmmax = in->shmmax; info.shmmin = in->shmmin; info.shmmni = in->shmmni; info.shmseg = in->shmseg; info.shmall = in->shmall; return copy_to_user(buf, &info, sizeof(info)); } else { struct shminfo info; memset(&info, 0, sizeof(info)); info.shmmax = in->shmmax; info.shmmin = in->shmmin; info.shmmni = in->shmmni; info.shmseg = in->shmseg; info.shmall = in->shmall; return copy_to_user(buf, &info, sizeof(info)); } } static int put_compat_shm_info(struct shm_info *ip, struct compat_shm_info __user *uip) { struct compat_shm_info info; memset(&info, 0, sizeof(info)); info.used_ids = ip->used_ids; info.shm_tot = ip->shm_tot; info.shm_rss = ip->shm_rss; info.shm_swp = ip->shm_swp; info.swap_attempts = ip->swap_attempts; info.swap_successes = ip->swap_successes; return copy_to_user(uip, &info, sizeof(info)); } static int copy_compat_shmid_to_user(void __user *buf, struct shmid64_ds *in, int version) { if (version == IPC_64) { struct compat_shmid64_ds v; memset(&v, 0, sizeof(v)); to_compat_ipc64_perm(&v.shm_perm, &in->shm_perm); v.shm_atime = lower_32_bits(in->shm_atime); v.shm_atime_high = upper_32_bits(in->shm_atime); v.shm_dtime = lower_32_bits(in->shm_dtime); v.shm_dtime_high = upper_32_bits(in->shm_dtime); v.shm_ctime = lower_32_bits(in->shm_ctime); v.shm_ctime_high = upper_32_bits(in->shm_ctime); v.shm_segsz = in->shm_segsz; v.shm_nattch = in->shm_nattch; v.shm_cpid = in->shm_cpid; v.shm_lpid = in->shm_lpid; return copy_to_user(buf, &v, sizeof(v)); } else { struct compat_shmid_ds v; memset(&v, 0, sizeof(v)); to_compat_ipc_perm(&v.shm_perm, &in->shm_perm); v.shm_perm.key = in->shm_perm.key; v.shm_atime = in->shm_atime; v.shm_dtime = in->shm_dtime; v.shm_ctime = in->shm_ctime; v.shm_segsz = in->shm_segsz; v.shm_nattch = in->shm_nattch; v.shm_cpid = in->shm_cpid; v.shm_lpid = in->shm_lpid; return copy_to_user(buf, &v, sizeof(v)); } } static int copy_compat_shmid_from_user(struct shmid64_ds *out, void __user *buf, int version) { memset(out, 0, sizeof(*out)); if (version == IPC_64) { struct compat_shmid64_ds __user *p = buf; return get_compat_ipc64_perm(&out->shm_perm, &p->shm_perm); } else { struct compat_shmid_ds __user *p = buf; return get_compat_ipc_perm(&out->shm_perm, &p->shm_perm); } } static long compat_ksys_shmctl(int shmid, int cmd, void __user *uptr, int version) { struct ipc_namespace *ns; struct shmid64_ds sem64; int err; ns = current->nsproxy->ipc_ns; if (cmd < 0 || shmid < 0) return -EINVAL; switch (cmd) { case IPC_INFO: { struct shminfo64 shminfo; err = shmctl_ipc_info(ns, &shminfo); if (err < 0) return err; if (copy_compat_shminfo_to_user(uptr, &shminfo, version)) err = -EFAULT; return err; } case SHM_INFO: { struct shm_info shm_info; err = shmctl_shm_info(ns, &shm_info); if (err < 0) return err; if (put_compat_shm_info(&shm_info, uptr)) err = -EFAULT; return err; } case IPC_STAT: case SHM_STAT_ANY: case SHM_STAT: err = shmctl_stat(ns, shmid, cmd, &sem64); if (err < 0) return err; if (copy_compat_shmid_to_user(uptr, &sem64, version)) err = -EFAULT; return err; case IPC_SET: if (copy_compat_shmid_from_user(&sem64, uptr, version)) return -EFAULT; fallthrough; case IPC_RMID: return shmctl_down(ns, shmid, cmd, &sem64); case SHM_LOCK: case SHM_UNLOCK: return shmctl_do_lock(ns, shmid, cmd); default: return -EINVAL; } return err; } COMPAT_SYSCALL_DEFINE3(shmctl, int, shmid, int, cmd, void __user *, uptr) { return compat_ksys_shmctl(shmid, cmd, uptr, IPC_64); } #ifdef CONFIG_ARCH_WANT_COMPAT_IPC_PARSE_VERSION long compat_ksys_old_shmctl(int shmid, int cmd, void __user *uptr) { int version = compat_ipc_parse_version(&cmd); return compat_ksys_shmctl(shmid, cmd, uptr, version); } COMPAT_SYSCALL_DEFINE3(old_shmctl, int, shmid, int, cmd, void __user *, uptr) { return compat_ksys_old_shmctl(shmid, cmd, uptr); } #endif #endif /* * Fix shmaddr, allocate descriptor, map shm, add attach descriptor to lists. * * NOTE! Despite the name, this is NOT a direct system call entrypoint. The * "raddr" thing points to kernel space, and there has to be a wrapper around * this. */ long do_shmat(int shmid, char __user *shmaddr, int shmflg, ulong *raddr, unsigned long shmlba) { struct shmid_kernel *shp; unsigned long addr = (unsigned long)shmaddr; unsigned long size; struct file *file, *base; int err; unsigned long flags = MAP_SHARED; unsigned long prot; int acc_mode; struct ipc_namespace *ns; struct shm_file_data *sfd; int f_flags; unsigned long populate = 0; err = -EINVAL; if (shmid < 0) goto out; if (addr) { if (addr & (shmlba - 1)) { if (shmflg & SHM_RND) { addr &= ~(shmlba - 1); /* round down */ /* * Ensure that the round-down is non-nil * when remapping. This can happen for * cases when addr < shmlba. */ if (!addr && (shmflg & SHM_REMAP)) goto out; } else #ifndef __ARCH_FORCE_SHMLBA if (addr & ~PAGE_MASK) #endif goto out; } flags |= MAP_FIXED; } else if ((shmflg & SHM_REMAP)) goto out; if (shmflg & SHM_RDONLY) { prot = PROT_READ; acc_mode = S_IRUGO; f_flags = O_RDONLY; } else { prot = PROT_READ | PROT_WRITE; acc_mode = S_IRUGO | S_IWUGO; f_flags = O_RDWR; } if (shmflg & SHM_EXEC) { prot |= PROT_EXEC; acc_mode |= S_IXUGO; } /* * We cannot rely on the fs check since SYSV IPC does have an * additional creator id... */ ns = current->nsproxy->ipc_ns; rcu_read_lock(); shp = shm_obtain_object_check(ns, shmid); if (IS_ERR(shp)) { err = PTR_ERR(shp); goto out_unlock; } err = -EACCES; if (ipcperms(ns, &shp->shm_perm, acc_mode)) goto out_unlock; err = security_shm_shmat(&shp->shm_perm, shmaddr, shmflg); if (err) goto out_unlock; ipc_lock_object(&shp->shm_perm); /* check if shm_destroy() is tearing down shp */ if (!ipc_valid_object(&shp->shm_perm)) { ipc_unlock_object(&shp->shm_perm); err = -EIDRM; goto out_unlock; } /* * We need to take a reference to the real shm file to prevent the * pointer from becoming stale in cases where the lifetime of the outer * file extends beyond that of the shm segment. It's not usually * possible, but it can happen during remap_file_pages() emulation as * that unmaps the memory, then does ->mmap() via file reference only. * We'll deny the ->mmap() if the shm segment was since removed, but to * detect shm ID reuse we need to compare the file pointers. */ base = get_file(shp->shm_file); shp->shm_nattch++; size = i_size_read(file_inode(base)); ipc_unlock_object(&shp->shm_perm); rcu_read_unlock(); err = -ENOMEM; sfd = kzalloc(sizeof(*sfd), GFP_KERNEL); if (!sfd) { fput(base); goto out_nattch; } file = alloc_file_clone(base, f_flags, is_file_hugepages(base) ? &shm_file_operations_huge : &shm_file_operations); err = PTR_ERR(file); if (IS_ERR(file)) { kfree(sfd); fput(base); goto out_nattch; } sfd->id = shp->shm_perm.id; sfd->ns = get_ipc_ns(ns); sfd->file = base; sfd->vm_ops = NULL; file->private_data = sfd; err = security_mmap_file(file, prot, flags); if (err) goto out_fput; if (mmap_write_lock_killable(current->mm)) { err = -EINTR; goto out_fput; } if (addr && !(shmflg & SHM_REMAP)) { err = -EINVAL; if (addr + size < addr) goto invalid; if (find_vma_intersection(current->mm, addr, addr + size)) goto invalid; } addr = do_mmap(file, addr, size, prot, flags, 0, 0, &populate, NULL); *raddr = addr; err = 0; if (IS_ERR_VALUE(addr)) err = (long)addr; invalid: mmap_write_unlock(current->mm); if (populate) mm_populate(addr, populate); out_fput: fput(file); out_nattch: down_write(&shm_ids(ns).rwsem); shp = shm_lock(ns, shmid); shp->shm_nattch--; if (shm_may_destroy(shp)) shm_destroy(ns, shp); else shm_unlock(shp); up_write(&shm_ids(ns).rwsem); return err; out_unlock: rcu_read_unlock(); out: return err; } SYSCALL_DEFINE3(shmat, int, shmid, char __user *, shmaddr, int, shmflg) { unsigned long ret; long err; err = do_shmat(shmid, shmaddr, shmflg, &ret, SHMLBA); if (err) return err; force_successful_syscall_return(); return (long)ret; } #ifdef CONFIG_COMPAT #ifndef COMPAT_SHMLBA #define COMPAT_SHMLBA SHMLBA #endif COMPAT_SYSCALL_DEFINE3(shmat, int, shmid, compat_uptr_t, shmaddr, int, shmflg) { unsigned long ret; long err; err = do_shmat(shmid, compat_ptr(shmaddr), shmflg, &ret, COMPAT_SHMLBA); if (err) return err; force_successful_syscall_return(); return (long)ret; } #endif /* * detach and kill segment if marked destroyed. * The work is done in shm_close. */ long ksys_shmdt(char __user *shmaddr) { struct mm_struct *mm = current->mm; struct vm_area_struct *vma; unsigned long addr = (unsigned long)shmaddr; int retval = -EINVAL; #ifdef CONFIG_MMU loff_t size = 0; struct file *file; VMA_ITERATOR(vmi, mm, addr); #endif if (addr & ~PAGE_MASK) return retval; if (mmap_write_lock_killable(mm)) return -EINTR; /* * This function tries to be smart and unmap shm segments that * were modified by partial mlock or munmap calls: * - It first determines the size of the shm segment that should be * unmapped: It searches for a vma that is backed by shm and that * started at address shmaddr. It records it's size and then unmaps * it. * - Then it unmaps all shm vmas that started at shmaddr and that * are within the initially determined size and that are from the * same shm segment from which we determined the size. * Errors from do_munmap are ignored: the function only fails if * it's called with invalid parameters or if it's called to unmap * a part of a vma. Both calls in this function are for full vmas, * the parameters are directly copied from the vma itself and always * valid - therefore do_munmap cannot fail. (famous last words?) */ /* * If it had been mremap()'d, the starting address would not * match the usual checks anyway. So assume all vma's are * above the starting address given. */ #ifdef CONFIG_MMU for_each_vma(vmi, vma) { /* * Check if the starting address would match, i.e. it's * a fragment created by mprotect() and/or munmap(), or it * otherwise it starts at this address with no hassles. */ if ((vma->vm_ops == &shm_vm_ops) && (vma->vm_start - addr)/PAGE_SIZE == vma->vm_pgoff) { /* * Record the file of the shm segment being * unmapped. With mremap(), someone could place * page from another segment but with equal offsets * in the range we are unmapping. */ file = vma->vm_file; size = i_size_read(file_inode(vma->vm_file)); do_vmi_align_munmap(&vmi, vma, mm, vma->vm_start, vma->vm_end, NULL, false); /* * We discovered the size of the shm segment, so * break out of here and fall through to the next * loop that uses the size information to stop * searching for matching vma's. */ retval = 0; vma = vma_next(&vmi); break; } } /* * We need look no further than the maximum address a fragment * could possibly have landed at. Also cast things to loff_t to * prevent overflows and make comparisons vs. equal-width types. */ size = PAGE_ALIGN(size); while (vma && (loff_t)(vma->vm_end - addr) <= size) { /* finding a matching vma now does not alter retval */ if ((vma->vm_ops == &shm_vm_ops) && ((vma->vm_start - addr)/PAGE_SIZE == vma->vm_pgoff) && (vma->vm_file == file)) { do_vmi_align_munmap(&vmi, vma, mm, vma->vm_start, vma->vm_end, NULL, false); } vma = vma_next(&vmi); } #else /* CONFIG_MMU */ vma = vma_lookup(mm, addr); /* under NOMMU conditions, the exact address to be destroyed must be * given */ if (vma && vma->vm_start == addr && vma->vm_ops == &shm_vm_ops) { do_munmap(mm, vma->vm_start, vma->vm_end - vma->vm_start, NULL); retval = 0; } #endif mmap_write_unlock(mm); return retval; } SYSCALL_DEFINE1(shmdt, char __user *, shmaddr) { return ksys_shmdt(shmaddr); } #ifdef CONFIG_PROC_FS static int sysvipc_shm_proc_show(struct seq_file *s, void *it) { struct pid_namespace *pid_ns = ipc_seq_pid_ns(s); struct user_namespace *user_ns = seq_user_ns(s); struct kern_ipc_perm *ipcp = it; struct shmid_kernel *shp; unsigned long rss = 0, swp = 0; shp = container_of(ipcp, struct shmid_kernel, shm_perm); shm_add_rss_swap(shp, &rss, &swp); #if BITS_PER_LONG <= 32 #define SIZE_SPEC "%10lu" #else #define SIZE_SPEC "%21lu" #endif seq_printf(s, "%10d %10d %4o " SIZE_SPEC " %5u %5u " "%5lu %5u %5u %5u %5u %10llu %10llu %10llu " SIZE_SPEC " " SIZE_SPEC "\n", shp->shm_perm.key, shp->shm_perm.id, shp->shm_perm.mode, shp->shm_segsz, pid_nr_ns(shp->shm_cprid, pid_ns), pid_nr_ns(shp->shm_lprid, pid_ns), shp->shm_nattch, from_kuid_munged(user_ns, shp->shm_perm.uid), from_kgid_munged(user_ns, shp->shm_perm.gid), from_kuid_munged(user_ns, shp->shm_perm.cuid), from_kgid_munged(user_ns, shp->shm_perm.cgid), shp->shm_atim, shp->shm_dtim, shp->shm_ctim, rss * PAGE_SIZE, swp * PAGE_SIZE); return 0; } #endif |
| 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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 | // SPDX-License-Identifier: GPL-2.0 /* * Shared Memory Communications over RDMA (SMC-R) and RoCE * * Manage send buffer. * Producer: * Copy user space data into send buffer, if send buffer space available. * Consumer: * Trigger RDMA write into RMBE of peer and send CDC, if RMBE space available. * * Copyright IBM Corp. 2016 * * Author(s): Ursula Braun <ubraun@linux.vnet.ibm.com> */ #include <linux/net.h> #include <linux/rcupdate.h> #include <linux/workqueue.h> #include <linux/sched/signal.h> #include <net/sock.h> #include <net/tcp.h> #include "smc.h" #include "smc_wr.h" #include "smc_cdc.h" #include "smc_close.h" #include "smc_ism.h" #include "smc_tx.h" #include "smc_stats.h" #include "smc_tracepoint.h" #define SMC_TX_WORK_DELAY 0 /***************************** sndbuf producer *******************************/ /* callback implementation for sk.sk_write_space() * to wakeup sndbuf producers that blocked with smc_tx_wait(). * called under sk_socket lock. */ static void smc_tx_write_space(struct sock *sk) { struct socket *sock = sk->sk_socket; struct smc_sock *smc = smc_sk(sk); struct socket_wq *wq; /* similar to sk_stream_write_space */ if (atomic_read(&smc->conn.sndbuf_space) && sock) { if (test_bit(SOCK_NOSPACE, &sock->flags)) SMC_STAT_RMB_TX_FULL(smc, !smc->conn.lnk); clear_bit(SOCK_NOSPACE, &sock->flags); rcu_read_lock(); wq = rcu_dereference(sk->sk_wq); if (skwq_has_sleeper(wq)) wake_up_interruptible_poll(&wq->wait, EPOLLOUT | EPOLLWRNORM | EPOLLWRBAND); if (wq && wq->fasync_list && !(sk->sk_shutdown & SEND_SHUTDOWN)) sock_wake_async(wq, SOCK_WAKE_SPACE, POLL_OUT); rcu_read_unlock(); } } /* Wakeup sndbuf producers that blocked with smc_tx_wait(). * Cf. tcp_data_snd_check()=>tcp_check_space()=>tcp_new_space(). */ void smc_tx_sndbuf_nonfull(struct smc_sock *smc) { if (smc->sk.sk_socket && test_bit(SOCK_NOSPACE, &smc->sk.sk_socket->flags)) smc->sk.sk_write_space(&smc->sk); } /* blocks sndbuf producer until at least one byte of free space available * or urgent Byte was consumed */ static int smc_tx_wait(struct smc_sock *smc, int flags) { DEFINE_WAIT_FUNC(wait, woken_wake_function); struct smc_connection *conn = &smc->conn; struct sock *sk = &smc->sk; long timeo; int rc = 0; /* similar to sk_stream_wait_memory */ timeo = sock_sndtimeo(sk, flags & MSG_DONTWAIT); add_wait_queue(sk_sleep(sk), &wait); while (1) { sk_set_bit(SOCKWQ_ASYNC_NOSPACE, sk); if (sk->sk_err || (sk->sk_shutdown & SEND_SHUTDOWN) || conn->killed || conn->local_tx_ctrl.conn_state_flags.peer_done_writing) { rc = -EPIPE; break; } if (smc_cdc_rxed_any_close(conn)) { rc = -ECONNRESET; break; } if (!timeo) { /* ensure EPOLLOUT is subsequently generated */ set_bit(SOCK_NOSPACE, &sk->sk_socket->flags); rc = -EAGAIN; break; } if (signal_pending(current)) { rc = sock_intr_errno(timeo); break; } sk_clear_bit(SOCKWQ_ASYNC_NOSPACE, sk); if (atomic_read(&conn->sndbuf_space) && !conn->urg_tx_pend) break; /* at least 1 byte of free & no urgent data */ set_bit(SOCK_NOSPACE, &sk->sk_socket->flags); sk_wait_event(sk, &timeo, READ_ONCE(sk->sk_err) || (READ_ONCE(sk->sk_shutdown) & SEND_SHUTDOWN) || smc_cdc_rxed_any_close(conn) || (atomic_read(&conn->sndbuf_space) && !conn->urg_tx_pend), &wait); } remove_wait_queue(sk_sleep(sk), &wait); return rc; } static bool smc_tx_is_corked(struct smc_sock *smc) { struct tcp_sock *tp = tcp_sk(smc->clcsock->sk); return (tp->nonagle & TCP_NAGLE_CORK) ? true : false; } /* If we have pending CDC messages, do not send: * Because CQE of this CDC message will happen shortly, it gives * a chance to coalesce future sendmsg() payload in to one RDMA Write, * without need for a timer, and with no latency trade off. * Algorithm here: * 1. First message should never cork * 2. If we have pending Tx CDC messages, wait for the first CDC * message's completion * 3. Don't cork to much data in a single RDMA Write to prevent burst * traffic, total corked message should not exceed sendbuf/2 */ static bool smc_should_autocork(struct smc_sock *smc) { struct smc_connection *conn = &smc->conn; int corking_size; corking_size = min_t(unsigned int, conn->sndbuf_desc->len >> 1, sock_net(&smc->sk)->smc.sysctl_autocorking_size); if (atomic_read(&conn->cdc_pend_tx_wr) == 0 || smc_tx_prepared_sends(conn) > corking_size) return false; return true; } static bool smc_tx_should_cork(struct smc_sock *smc, struct msghdr *msg) { struct smc_connection *conn = &smc->conn; if (smc_should_autocork(smc)) return true; /* for a corked socket defer the RDMA writes if * sndbuf_space is still available. The applications * should known how/when to uncork it. */ if ((msg->msg_flags & MSG_MORE || smc_tx_is_corked(smc)) && atomic_read(&conn->sndbuf_space)) return true; return false; } /* sndbuf producer: main API called by socket layer. * called under sock lock. */ int smc_tx_sendmsg(struct smc_sock *smc, struct msghdr *msg, size_t len) { size_t copylen, send_done = 0, send_remaining = len; size_t chunk_len, chunk_off, chunk_len_sum; struct smc_connection *conn = &smc->conn; union smc_host_cursor prep; struct sock *sk = &smc->sk; char *sndbuf_base; int tx_cnt_prep; int writespace; int rc, chunk; /* This should be in poll */ sk_clear_bit(SOCKWQ_ASYNC_NOSPACE, sk); if (sk->sk_err || (sk->sk_shutdown & SEND_SHUTDOWN)) { rc = -EPIPE; goto out_err; } if (sk->sk_state == SMC_INIT) return -ENOTCONN; if (len > conn->sndbuf_desc->len) SMC_STAT_RMB_TX_SIZE_SMALL(smc, !conn->lnk); if (len > conn->peer_rmbe_size) SMC_STAT_RMB_TX_PEER_SIZE_SMALL(smc, !conn->lnk); if (msg->msg_flags & MSG_OOB) SMC_STAT_INC(smc, urg_data_cnt); while (msg_data_left(msg)) { if (smc->sk.sk_shutdown & SEND_SHUTDOWN || (smc->sk.sk_err == ECONNABORTED) || conn->killed) return -EPIPE; if (smc_cdc_rxed_any_close(conn)) return send_done ?: -ECONNRESET; if (msg->msg_flags & MSG_OOB) conn->local_tx_ctrl.prod_flags.urg_data_pending = 1; if (!atomic_read(&conn->sndbuf_space) || conn->urg_tx_pend) { if (send_done) return send_done; rc = smc_tx_wait(smc, msg->msg_flags); if (rc) goto out_err; continue; } /* initialize variables for 1st iteration of subsequent loop */ /* could be just 1 byte, even after smc_tx_wait above */ writespace = atomic_read(&conn->sndbuf_space); /* not more than what user space asked for */ copylen = min_t(size_t, send_remaining, writespace); /* determine start of sndbuf */ sndbuf_base = conn->sndbuf_desc->cpu_addr; smc_curs_copy(&prep, &conn->tx_curs_prep, conn); tx_cnt_prep = prep.count; /* determine chunks where to write into sndbuf */ /* either unwrapped case, or 1st chunk of wrapped case */ chunk_len = min_t(size_t, copylen, conn->sndbuf_desc->len - tx_cnt_prep); chunk_len_sum = chunk_len; chunk_off = tx_cnt_prep; for (chunk = 0; chunk < 2; chunk++) { rc = memcpy_from_msg(sndbuf_base + chunk_off, msg, chunk_len); if (rc) { smc_sndbuf_sync_sg_for_device(conn); if (send_done) return send_done; goto out_err; } send_done += chunk_len; send_remaining -= chunk_len; if (chunk_len_sum == copylen) break; /* either on 1st or 2nd iteration */ /* prepare next (== 2nd) iteration */ chunk_len = copylen - chunk_len; /* remainder */ chunk_len_sum += chunk_len; chunk_off = 0; /* modulo offset in send ring buffer */ } smc_sndbuf_sync_sg_for_device(conn); /* update cursors */ smc_curs_add(conn->sndbuf_desc->len, &prep, copylen); smc_curs_copy(&conn->tx_curs_prep, &prep, conn); /* increased in send tasklet smc_cdc_tx_handler() */ smp_mb__before_atomic(); atomic_sub(copylen, &conn->sndbuf_space); /* guarantee 0 <= sndbuf_space <= sndbuf_desc->len */ smp_mb__after_atomic(); /* since we just produced more new data into sndbuf, * trigger sndbuf consumer: RDMA write into peer RMBE and CDC */ if ((msg->msg_flags & MSG_OOB) && !send_remaining) conn->urg_tx_pend = true; /* If we need to cork, do nothing and wait for the next * sendmsg() call or push on tx completion */ if (!smc_tx_should_cork(smc, msg)) smc_tx_sndbuf_nonempty(conn); trace_smc_tx_sendmsg(smc, copylen); } /* while (msg_data_left(msg)) */ return send_done; out_err: rc = sk_stream_error(sk, msg->msg_flags, rc); /* make sure we wake any epoll edge trigger waiter */ if (unlikely(rc == -EAGAIN)) sk->sk_write_space(sk); return rc; } /***************************** sndbuf consumer *******************************/ /* sndbuf consumer: actual data transfer of one target chunk with ISM write */ int smcd_tx_ism_write(struct smc_connection *conn, void *data, size_t len, u32 offset, int signal) { int rc; rc = smc_ism_write(conn->lgr->smcd, conn->peer_token, conn->peer_rmbe_idx, signal, conn->tx_off + offset, data, len); if (rc) conn->local_tx_ctrl.conn_state_flags.peer_conn_abort = 1; return rc; } /* sndbuf consumer: actual data transfer of one target chunk with RDMA write */ static int smc_tx_rdma_write(struct smc_connection *conn, int peer_rmbe_offset, int num_sges, struct ib_rdma_wr *rdma_wr) { struct smc_link_group *lgr = conn->lgr; struct smc_link *link = conn->lnk; int rc; rdma_wr->wr.wr_id = smc_wr_tx_get_next_wr_id(link); rdma_wr->wr.num_sge = num_sges; rdma_wr->remote_addr = lgr->rtokens[conn->rtoken_idx][link->link_idx].dma_addr + /* RMBE within RMB */ conn->tx_off + /* offset within RMBE */ peer_rmbe_offset; rdma_wr->rkey = lgr->rtokens[conn->rtoken_idx][link->link_idx].rkey; rc = ib_post_send(link->roce_qp, &rdma_wr->wr, NULL); if (rc) smcr_link_down_cond_sched(link); return rc; } /* sndbuf consumer */ static inline void smc_tx_advance_cursors(struct smc_connection *conn, union smc_host_cursor *prod, union smc_host_cursor *sent, size_t len) { smc_curs_add(conn->peer_rmbe_size, prod, len); /* increased in recv tasklet smc_cdc_msg_rcv() */ smp_mb__before_atomic(); /* data in flight reduces usable snd_wnd */ atomic_sub(len, &conn->peer_rmbe_space); /* guarantee 0 <= peer_rmbe_space <= peer_rmbe_size */ smp_mb__after_atomic(); smc_curs_add(conn->sndbuf_desc->len, sent, len); } /* SMC-R helper for smc_tx_rdma_writes() */ static int smcr_tx_rdma_writes(struct smc_connection *conn, size_t len, size_t src_off, size_t src_len, size_t dst_off, size_t dst_len, struct smc_rdma_wr *wr_rdma_buf) { struct smc_link *link = conn->lnk; dma_addr_t dma_addr = sg_dma_address(conn->sndbuf_desc->sgt[link->link_idx].sgl); u64 virt_addr = (uintptr_t)conn->sndbuf_desc->cpu_addr; int src_len_sum = src_len, dst_len_sum = dst_len; int sent_count = src_off; int srcchunk, dstchunk; int num_sges; int rc; for (dstchunk = 0; dstchunk < 2; dstchunk++) { struct ib_rdma_wr *wr = &wr_rdma_buf->wr_tx_rdma[dstchunk]; struct ib_sge *sge = wr->wr.sg_list; u64 base_addr = dma_addr; if (dst_len < link->qp_attr.cap.max_inline_data) { base_addr = virt_addr; wr->wr.send_flags |= IB_SEND_INLINE; } else { wr->wr.send_flags &= ~IB_SEND_INLINE; } num_sges = 0; for (srcchunk = 0; srcchunk < 2; srcchunk++) { sge[srcchunk].addr = conn->sndbuf_desc->is_vm ? (virt_addr + src_off) : (base_addr + src_off); sge[srcchunk].length = src_len; if (conn->sndbuf_desc->is_vm) sge[srcchunk].lkey = conn->sndbuf_desc->mr[link->link_idx]->lkey; num_sges++; src_off += src_len; if (src_off >= conn->sndbuf_desc->len) src_off -= conn->sndbuf_desc->len; /* modulo in send ring */ if (src_len_sum == dst_len) break; /* either on 1st or 2nd iteration */ /* prepare next (== 2nd) iteration */ src_len = dst_len - src_len; /* remainder */ src_len_sum += src_len; } rc = smc_tx_rdma_write(conn, dst_off, num_sges, wr); if (rc) return rc; if (dst_len_sum == len) break; /* either on 1st or 2nd iteration */ /* prepare next (== 2nd) iteration */ dst_off = 0; /* modulo offset in RMBE ring buffer */ dst_len = len - dst_len; /* remainder */ dst_len_sum += dst_len; src_len = min_t(int, dst_len, conn->sndbuf_desc->len - sent_count); src_len_sum = src_len; } return 0; } /* SMC-D helper for smc_tx_rdma_writes() */ static int smcd_tx_rdma_writes(struct smc_connection *conn, size_t len, size_t src_off, size_t src_len, size_t dst_off, size_t dst_len) { int src_len_sum = src_len, dst_len_sum = dst_len; int srcchunk, dstchunk; int rc; for (dstchunk = 0; dstchunk < 2; dstchunk++) { for (srcchunk = 0; srcchunk < 2; srcchunk++) { void *data = conn->sndbuf_desc->cpu_addr + src_off; rc = smcd_tx_ism_write(conn, data, src_len, dst_off + sizeof(struct smcd_cdc_msg), 0); if (rc) return rc; dst_off += src_len; src_off += src_len; if (src_off >= conn->sndbuf_desc->len) src_off -= conn->sndbuf_desc->len; /* modulo in send ring */ if (src_len_sum == dst_len) break; /* either on 1st or 2nd iteration */ /* prepare next (== 2nd) iteration */ src_len = dst_len - src_len; /* remainder */ src_len_sum += src_len; } if (dst_len_sum == len) break; /* either on 1st or 2nd iteration */ /* prepare next (== 2nd) iteration */ dst_off = 0; /* modulo offset in RMBE ring buffer */ dst_len = len - dst_len; /* remainder */ dst_len_sum += dst_len; src_len = min_t(int, dst_len, conn->sndbuf_desc->len - src_off); src_len_sum = src_len; } return 0; } /* sndbuf consumer: prepare all necessary (src&dst) chunks of data transmit; * usable snd_wnd as max transmit */ static int smc_tx_rdma_writes(struct smc_connection *conn, struct smc_rdma_wr *wr_rdma_buf) { size_t len, src_len, dst_off, dst_len; /* current chunk values */ union smc_host_cursor sent, prep, prod, cons; struct smc_cdc_producer_flags *pflags; int to_send, rmbespace; int rc; /* source: sndbuf */ smc_curs_copy(&sent, &conn->tx_curs_sent, conn); smc_curs_copy(&prep, &conn->tx_curs_prep, conn); /* cf. wmem_alloc - (snd_max - snd_una) */ to_send = smc_curs_diff(conn->sndbuf_desc->len, &sent, &prep); if (to_send <= 0) return 0; /* destination: RMBE */ /* cf. snd_wnd */ rmbespace = atomic_read(&conn->peer_rmbe_space); if (rmbespace <= 0) { struct smc_sock *smc = container_of(conn, struct smc_sock, conn); SMC_STAT_RMB_TX_PEER_FULL(smc, !conn->lnk); return 0; } smc_curs_copy(&prod, &conn->local_tx_ctrl.prod, conn); smc_curs_copy(&cons, &conn->local_rx_ctrl.cons, conn); /* if usable snd_wnd closes ask peer to advertise once it opens again */ pflags = &conn->local_tx_ctrl.prod_flags; pflags->write_blocked = (to_send >= rmbespace); /* cf. usable snd_wnd */ len = min(to_send, rmbespace); /* initialize variables for first iteration of subsequent nested loop */ dst_off = prod.count; if (prod.wrap == cons.wrap) { /* the filled destination area is unwrapped, * hence the available free destination space is wrapped * and we need 2 destination chunks of sum len; start with 1st * which is limited by what's available in sndbuf */ dst_len = min_t(size_t, conn->peer_rmbe_size - prod.count, len); } else { /* the filled destination area is wrapped, * hence the available free destination space is unwrapped * and we need a single destination chunk of entire len */ dst_len = len; } /* dst_len determines the maximum src_len */ if (sent.count + dst_len <= conn->sndbuf_desc->len) { /* unwrapped src case: single chunk of entire dst_len */ src_len = dst_len; } else { /* wrapped src case: 2 chunks of sum dst_len; start with 1st: */ src_len = conn->sndbuf_desc->len - sent.count; } if (conn->lgr->is_smcd) rc = smcd_tx_rdma_writes(conn, len, sent.count, src_len, dst_off, dst_len); else rc = smcr_tx_rdma_writes(conn, len, sent.count, src_len, dst_off, dst_len, wr_rdma_buf); if (rc) return rc; if (conn->urg_tx_pend && len == to_send) pflags->urg_data_present = 1; smc_tx_advance_cursors(conn, &prod, &sent, len); /* update connection's cursors with advanced local cursors */ smc_curs_copy(&conn->local_tx_ctrl.prod, &prod, conn); /* dst: peer RMBE */ smc_curs_copy(&conn->tx_curs_sent, &sent, conn);/* src: local sndbuf */ return 0; } /* Wakeup sndbuf consumers from any context (IRQ or process) * since there is more data to transmit; usable snd_wnd as max transmit */ static int smcr_tx_sndbuf_nonempty(struct smc_connection *conn) { struct smc_cdc_producer_flags *pflags = &conn->local_tx_ctrl.prod_flags; struct smc_link *link = conn->lnk; struct smc_rdma_wr *wr_rdma_buf; struct smc_cdc_tx_pend *pend; struct smc_wr_buf *wr_buf; int rc; if (!link || !smc_wr_tx_link_hold(link)) return -ENOLINK; rc = smc_cdc_get_free_slot(conn, link, &wr_buf, &wr_rdma_buf, &pend); if (rc < 0) { smc_wr_tx_link_put(link); if (rc == -EBUSY) { struct smc_sock *smc = container_of(conn, struct smc_sock, conn); if (smc->sk.sk_err == ECONNABORTED) return sock_error(&smc->sk); if (conn->killed) return -EPIPE; rc = 0; mod_delayed_work(conn->lgr->tx_wq, &conn->tx_work, SMC_TX_WORK_DELAY); } return rc; } spin_lock_bh(&conn->send_lock); if (link != conn->lnk) { /* link of connection changed, tx_work will restart */ smc_wr_tx_put_slot(link, (struct smc_wr_tx_pend_priv *)pend); rc = -ENOLINK; goto out_unlock; } if (!pflags->urg_data_present) { rc = smc_tx_rdma_writes(conn, wr_rdma_buf); if (rc) { smc_wr_tx_put_slot(link, (struct smc_wr_tx_pend_priv *)pend); goto out_unlock; } } rc = smc_cdc_msg_send(conn, wr_buf, pend); if (!rc && pflags->urg_data_present) { pflags->urg_data_pending = 0; pflags->urg_data_present = 0; } out_unlock: spin_unlock_bh(&conn->send_lock); smc_wr_tx_link_put(link); return rc; } static int smcd_tx_sndbuf_nonempty(struct smc_connection *conn) { struct smc_cdc_producer_flags *pflags = &conn->local_tx_ctrl.prod_flags; int rc = 0; spin_lock_bh(&conn->send_lock); if (!pflags->urg_data_present) rc = smc_tx_rdma_writes(conn, NULL); if (!rc) rc = smcd_cdc_msg_send(conn); if (!rc && pflags->urg_data_present) { pflags->urg_data_pending = 0; pflags->urg_data_present = 0; } spin_unlock_bh(&conn->send_lock); return rc; } int smc_tx_sndbuf_nonempty(struct smc_connection *conn) { struct smc_sock *smc = container_of(conn, struct smc_sock, conn); int rc = 0; /* No data in the send queue */ if (unlikely(smc_tx_prepared_sends(conn) <= 0)) goto out; /* Peer don't have RMBE space */ if (unlikely(atomic_read(&conn->peer_rmbe_space) <= 0)) { SMC_STAT_RMB_TX_PEER_FULL(smc, !conn->lnk); goto out; } if (conn->killed || conn->local_rx_ctrl.conn_state_flags.peer_conn_abort) { rc = -EPIPE; /* connection being aborted */ goto out; } if (conn->lgr->is_smcd) rc = smcd_tx_sndbuf_nonempty(conn); else rc = smcr_tx_sndbuf_nonempty(conn); if (!rc) { /* trigger socket release if connection is closing */ smc_close_wake_tx_prepared(smc); } out: return rc; } /* Wakeup sndbuf consumers from process context * since there is more data to transmit. The caller * must hold sock lock. */ void smc_tx_pending(struct smc_connection *conn) { struct smc_sock *smc = container_of(conn, struct smc_sock, conn); int rc; if (smc->sk.sk_err) return; rc = smc_tx_sndbuf_nonempty(conn); if (!rc && conn->local_rx_ctrl.prod_flags.write_blocked && !atomic_read(&conn->bytes_to_rcv)) conn->local_rx_ctrl.prod_flags.write_blocked = 0; } /* Wakeup sndbuf consumers from process context * since there is more data to transmit in locked * sock. */ void smc_tx_work(struct work_struct *work) { struct smc_connection *conn = container_of(to_delayed_work(work), struct smc_connection, tx_work); struct smc_sock *smc = container_of(conn, struct smc_sock, conn); lock_sock(&smc->sk); smc_tx_pending(conn); release_sock(&smc->sk); } void smc_tx_consumer_update(struct smc_connection *conn, bool force) { union smc_host_cursor cfed, cons, prod; int sender_free = conn->rmb_desc->len; int to_confirm; smc_curs_copy(&cons, &conn->local_tx_ctrl.cons, conn); smc_curs_copy(&cfed, &conn->rx_curs_confirmed, conn); to_confirm = smc_curs_diff(conn->rmb_desc->len, &cfed, &cons); if (to_confirm > conn->rmbe_update_limit) { smc_curs_copy(&prod, &conn->local_rx_ctrl.prod, conn); sender_free = conn->rmb_desc->len - smc_curs_diff_large(conn->rmb_desc->len, &cfed, &prod); } if (conn->local_rx_ctrl.prod_flags.cons_curs_upd_req || force || ((to_confirm > conn->rmbe_update_limit) && ((sender_free <= (conn->rmb_desc->len / 2)) || conn->local_rx_ctrl.prod_flags.write_blocked))) { if (conn->killed || conn->local_rx_ctrl.conn_state_flags.peer_conn_abort) return; if ((smc_cdc_get_slot_and_msg_send(conn) < 0) && !conn->killed) { queue_delayed_work(conn->lgr->tx_wq, &conn->tx_work, SMC_TX_WORK_DELAY); return; } } if (conn->local_rx_ctrl.prod_flags.write_blocked && !atomic_read(&conn->bytes_to_rcv)) conn->local_rx_ctrl.prod_flags.write_blocked = 0; } /***************************** send initialize *******************************/ /* Initialize send properties on connection establishment. NB: not __init! */ void smc_tx_init(struct smc_sock *smc) { smc->sk.sk_write_space = smc_tx_write_space; } |
| 11 11 17 | 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 | /* SPDX-License-Identifier: GPL-2.0-or-later */ #ifndef _NET_GSO_H #define _NET_GSO_H #include <linux/skbuff.h> /* Keeps track of mac header offset relative to skb->head. * It is useful for TSO of Tunneling protocol. e.g. GRE. * For non-tunnel skb it points to skb_mac_header() and for * tunnel skb it points to outer mac header. * Keeps track of level of encapsulation of network headers. */ struct skb_gso_cb { union { int mac_offset; int data_offset; }; int encap_level; __wsum csum; __u16 csum_start; }; #define SKB_GSO_CB_OFFSET 32 #define SKB_GSO_CB(skb) ((struct skb_gso_cb *)((skb)->cb + SKB_GSO_CB_OFFSET)) static inline int skb_tnl_header_len(const struct sk_buff *inner_skb) { return (skb_mac_header(inner_skb) - inner_skb->head) - SKB_GSO_CB(inner_skb)->mac_offset; } static inline int gso_pskb_expand_head(struct sk_buff *skb, int extra) { int new_headroom, headroom; int ret; headroom = skb_headroom(skb); ret = pskb_expand_head(skb, extra, 0, GFP_ATOMIC); if (ret) return ret; new_headroom = skb_headroom(skb); SKB_GSO_CB(skb)->mac_offset += (new_headroom - headroom); return 0; } static inline void gso_reset_checksum(struct sk_buff *skb, __wsum res) { /* Do not update partial checksums if remote checksum is enabled. */ if (skb->remcsum_offload) return; SKB_GSO_CB(skb)->csum = res; SKB_GSO_CB(skb)->csum_start = skb_checksum_start(skb) - skb->head; } /* Compute the checksum for a gso segment. First compute the checksum value * from the start of transport header to SKB_GSO_CB(skb)->csum_start, and * then add in skb->csum (checksum from csum_start to end of packet). * skb->csum and csum_start are then updated to reflect the checksum of the * resultant packet starting from the transport header-- the resultant checksum * is in the res argument (i.e. normally zero or ~ of checksum of a pseudo * header. */ static inline __sum16 gso_make_checksum(struct sk_buff *skb, __wsum res) { unsigned char *csum_start = skb_transport_header(skb); int plen = (skb->head + SKB_GSO_CB(skb)->csum_start) - csum_start; __wsum partial = SKB_GSO_CB(skb)->csum; SKB_GSO_CB(skb)->csum = res; SKB_GSO_CB(skb)->csum_start = csum_start - skb->head; return csum_fold(csum_partial(csum_start, plen, partial)); } struct sk_buff *__skb_gso_segment(struct sk_buff *skb, netdev_features_t features, bool tx_path); static inline struct sk_buff *skb_gso_segment(struct sk_buff *skb, netdev_features_t features) { return __skb_gso_segment(skb, features, true); } struct sk_buff *skb_eth_gso_segment(struct sk_buff *skb, netdev_features_t features, __be16 type); struct sk_buff *skb_mac_gso_segment(struct sk_buff *skb, netdev_features_t features); bool skb_gso_validate_network_len(const struct sk_buff *skb, unsigned int mtu); bool skb_gso_validate_mac_len(const struct sk_buff *skb, unsigned int len); static inline void skb_gso_error_unwind(struct sk_buff *skb, __be16 protocol, int pulled_hlen, u16 mac_offset, int mac_len) { skb->protocol = protocol; skb->encapsulation = 1; skb_push(skb, pulled_hlen); skb_reset_transport_header(skb); skb->mac_header = mac_offset; skb->network_header = skb->mac_header + mac_len; skb->mac_len = mac_len; } #endif /* _NET_GSO_H */ |
| 146 131 15 15 15 15 6 12 146 | 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 | // SPDX-License-Identifier: GPL-2.0-only /* * linux/kernel/ptrace.c * * (C) Copyright 1999 Linus Torvalds * * Common interfaces for "ptrace()" which we do not want * to continually duplicate across every architecture. */ #include <linux/capability.h> #include <linux/export.h> #include <linux/sched.h> #include <linux/sched/mm.h> #include <linux/sched/coredump.h> #include <linux/sched/task.h> #include <linux/errno.h> #include <linux/mm.h> #include <linux/highmem.h> #include <linux/pagemap.h> #include <linux/ptrace.h> #include <linux/security.h> #include <linux/signal.h> #include <linux/uio.h> #include <linux/audit.h> #include <linux/pid_namespace.h> #include <linux/syscalls.h> #include <linux/uaccess.h> #include <linux/regset.h> #include <linux/hw_breakpoint.h> #include <linux/cn_proc.h> #include <linux/compat.h> #include <linux/sched/signal.h> #include <linux/minmax.h> #include <linux/syscall_user_dispatch.h> #include <asm/syscall.h> /* for syscall_get_* */ /* * Access another process' address space via ptrace. * Source/target buffer must be kernel space, * Do not walk the page table directly, use get_user_pages */ int ptrace_access_vm(struct task_struct *tsk, unsigned long addr, void *buf, int len, unsigned int gup_flags) { struct mm_struct *mm; int ret; mm = get_task_mm(tsk); if (!mm) return 0; if (!tsk->ptrace || (current != tsk->parent) || ((get_dumpable(mm) != SUID_DUMP_USER) && !ptracer_capable(tsk, mm->user_ns))) { mmput(mm); return 0; } ret = access_remote_vm(mm, addr, buf, len, gup_flags); mmput(mm); return ret; } void __ptrace_link(struct task_struct *child, struct task_struct *new_parent, const struct cred *ptracer_cred) { BUG_ON(!list_empty(&child->ptrace_entry)); list_add(&child->ptrace_entry, &new_parent->ptraced); child->parent = new_parent; child->ptracer_cred = get_cred(ptracer_cred); } /* * ptrace a task: make the debugger its new parent and * move it to the ptrace list. * * Must be called with the tasklist lock write-held. */ static void ptrace_link(struct task_struct *child, struct task_struct *new_parent) { __ptrace_link(child, new_parent, current_cred()); } /** * __ptrace_unlink - unlink ptracee and restore its execution state * @child: ptracee to be unlinked * * Remove @child from the ptrace list, move it back to the original parent, * and restore the execution state so that it conforms to the group stop * state. * * Unlinking can happen via two paths - explicit PTRACE_DETACH or ptracer * exiting. For PTRACE_DETACH, unless the ptracee has been killed between * ptrace_check_attach() and here, it's guaranteed to be in TASK_TRACED. * If the ptracer is exiting, the ptracee can be in any state. * * After detach, the ptracee should be in a state which conforms to the * group stop. If the group is stopped or in the process of stopping, the * ptracee should be put into TASK_STOPPED; otherwise, it should be woken * up from TASK_TRACED. * * If the ptracee is in TASK_TRACED and needs to be moved to TASK_STOPPED, * it goes through TRACED -> RUNNING -> STOPPED transition which is similar * to but in the opposite direction of what happens while attaching to a * stopped task. However, in this direction, the intermediate RUNNING * state is not hidden even from the current ptracer and if it immediately * re-attaches and performs a WNOHANG wait(2), it may fail. * * CONTEXT: * write_lock_irq(tasklist_lock) */ void __ptrace_unlink(struct task_struct *child) { const struct cred *old_cred; BUG_ON(!child->ptrace); clear_task_syscall_work(child, SYSCALL_TRACE); #if defined(CONFIG_GENERIC_ENTRY) || defined(TIF_SYSCALL_EMU) clear_task_syscall_work(child, SYSCALL_EMU); #endif child->parent = child->real_parent; list_del_init(&child->ptrace_entry); old_cred = child->ptracer_cred; child->ptracer_cred = NULL; put_cred(old_cred); spin_lock(&child->sighand->siglock); child->ptrace = 0; /* * Clear all pending traps and TRAPPING. TRAPPING should be * cleared regardless of JOBCTL_STOP_PENDING. Do it explicitly. */ task_clear_jobctl_pending(child, JOBCTL_TRAP_MASK); task_clear_jobctl_trapping(child); /* * Reinstate JOBCTL_STOP_PENDING if group stop is in effect and * @child isn't dead. */ if (!(child->flags & PF_EXITING) && (child->signal->flags & SIGNAL_STOP_STOPPED || child->signal->group_stop_count)) child->jobctl |= JOBCTL_STOP_PENDING; /* * If transition to TASK_STOPPED is pending or in TASK_TRACED, kick * @child in the butt. Note that @resume should be used iff @child * is in TASK_TRACED; otherwise, we might unduly disrupt * TASK_KILLABLE sleeps. */ if (child->jobctl & JOBCTL_STOP_PENDING || task_is_traced(child)) ptrace_signal_wake_up(child, true); spin_unlock(&child->sighand->siglock); } static bool looks_like_a_spurious_pid(struct task_struct *task) { if (task->exit_code != ((PTRACE_EVENT_EXEC << 8) | SIGTRAP)) return false; if (task_pid_vnr(task) == task->ptrace_message) return false; /* * The tracee changed its pid but the PTRACE_EVENT_EXEC event * was not wait()'ed, most probably debugger targets the old * leader which was destroyed in de_thread(). */ return true; } /* * Ensure that nothing can wake it up, even SIGKILL * * A task is switched to this state while a ptrace operation is in progress; * such that the ptrace operation is uninterruptible. */ static bool ptrace_freeze_traced(struct task_struct *task) { bool ret = false; /* Lockless, nobody but us can set this flag */ if (task->jobctl & JOBCTL_LISTENING) return ret; spin_lock_irq(&task->sighand->siglock); if (task_is_traced(task) && !looks_like_a_spurious_pid(task) && !__fatal_signal_pending(task)) { task->jobctl |= JOBCTL_PTRACE_FROZEN; ret = true; } spin_unlock_irq(&task->sighand->siglock); return ret; } static void ptrace_unfreeze_traced(struct task_struct *task) { unsigned long flags; /* * The child may be awake and may have cleared * JOBCTL_PTRACE_FROZEN (see ptrace_resume). The child will * not set JOBCTL_PTRACE_FROZEN or enter __TASK_TRACED anew. */ if (lock_task_sighand(task, &flags)) { task->jobctl &= ~JOBCTL_PTRACE_FROZEN; if (__fatal_signal_pending(task)) { task->jobctl &= ~JOBCTL_TRACED; wake_up_state(task, __TASK_TRACED); } unlock_task_sighand(task, &flags); } } /** * ptrace_check_attach - check whether ptracee is ready for ptrace operation * @child: ptracee to check for * @ignore_state: don't check whether @child is currently %TASK_TRACED * * Check whether @child is being ptraced by %current and ready for further * ptrace operations. If @ignore_state is %false, @child also should be in * %TASK_TRACED state and on return the child is guaranteed to be traced * and not executing. If @ignore_state is %true, @child can be in any * state. * * CONTEXT: * Grabs and releases tasklist_lock and @child->sighand->siglock. * * RETURNS: * 0 on success, -ESRCH if %child is not ready. */ static int ptrace_check_attach(struct task_struct *child, bool ignore_state) { int ret = -ESRCH; /* * We take the read lock around doing both checks to close a * possible race where someone else was tracing our child and * detached between these two checks. After this locked check, * we are sure that this is our traced child and that can only * be changed by us so it's not changing right after this. */ read_lock(&tasklist_lock); if (child->ptrace && child->parent == current) { /* * child->sighand can't be NULL, release_task() * does ptrace_unlink() before __exit_signal(). */ if (ignore_state || ptrace_freeze_traced(child)) ret = 0; } read_unlock(&tasklist_lock); if (!ret && !ignore_state && WARN_ON_ONCE(!wait_task_inactive(child, __TASK_TRACED|TASK_FROZEN))) ret = -ESRCH; return ret; } static bool ptrace_has_cap(struct user_namespace *ns, unsigned int mode) { if (mode & PTRACE_MODE_NOAUDIT) return ns_capable_noaudit(ns, CAP_SYS_PTRACE); return ns_capable(ns, CAP_SYS_PTRACE); } /* Returns 0 on success, -errno on denial. */ static int __ptrace_may_access(struct task_struct *task, unsigned int mode) { const struct cred *cred = current_cred(), *tcred; struct mm_struct *mm; kuid_t caller_uid; kgid_t caller_gid; if (!(mode & PTRACE_MODE_FSCREDS) == !(mode & PTRACE_MODE_REALCREDS)) { WARN(1, "denying ptrace access check without PTRACE_MODE_*CREDS\n"); return -EPERM; } /* May we inspect the given task? * This check is used both for attaching with ptrace * and for allowing access to sensitive information in /proc. * * ptrace_attach denies several cases that /proc allows * because setting up the necessary parent/child relationship * or halting the specified task is impossible. */ /* Don't let security modules deny introspection */ if (same_thread_group(task, current)) return 0; rcu_read_lock(); if (mode & PTRACE_MODE_FSCREDS) { caller_uid = cred->fsuid; caller_gid = cred->fsgid; } else { /* * Using the euid would make more sense here, but something * in userland might rely on the old behavior, and this * shouldn't be a security problem since * PTRACE_MODE_REALCREDS implies that the caller explicitly * used a syscall that requests access to another process * (and not a filesystem syscall to procfs). */ caller_uid = cred->uid; caller_gid = cred->gid; } tcred = __task_cred(task); if (uid_eq(caller_uid, tcred->euid) && uid_eq(caller_uid, tcred->suid) && uid_eq(caller_uid, tcred->uid) && gid_eq(caller_gid, tcred->egid) && gid_eq(caller_gid, tcred->sgid) && gid_eq(caller_gid, tcred->gid)) goto ok; if (ptrace_has_cap(tcred->user_ns, mode)) goto ok; rcu_read_unlock(); return -EPERM; ok: rcu_read_unlock(); /* * If a task drops privileges and becomes nondumpable (through a syscall * like setresuid()) while we are trying to access it, we must ensure * that the dumpability is read after the credentials; otherwise, * we may be able to attach to a task that we shouldn't be able to * attach to (as if the task had dropped privileges without becoming * nondumpable). * Pairs with a write barrier in commit_creds(). */ smp_rmb(); mm = task->mm; if (mm && ((get_dumpable(mm) != SUID_DUMP_USER) && !ptrace_has_cap(mm->user_ns, mode))) return -EPERM; return security_ptrace_access_check(task, mode); } bool ptrace_may_access(struct task_struct *task, unsigned int mode) { int err; task_lock(task); err = __ptrace_may_access(task, mode); task_unlock(task); return !err; } static int check_ptrace_options(unsigned long data) { if (data & ~(unsigned long)PTRACE_O_MASK) return -EINVAL; if (unlikely(data & PTRACE_O_SUSPEND_SECCOMP)) { if (!IS_ENABLED(CONFIG_CHECKPOINT_RESTORE) || !IS_ENABLED(CONFIG_SECCOMP)) return -EINVAL; if (!capable(CAP_SYS_ADMIN)) return -EPERM; if (seccomp_mode(¤t->seccomp) != SECCOMP_MODE_DISABLED || current->ptrace & PT_SUSPEND_SECCOMP) return -EPERM; } return 0; } static inline void ptrace_set_stopped(struct task_struct *task, bool seize) { guard(spinlock)(&task->sighand->siglock); /* SEIZE doesn't trap tracee on attach */ if (!seize) send_signal_locked(SIGSTOP, SEND_SIG_PRIV, task, PIDTYPE_PID); /* * If the task is already STOPPED, set JOBCTL_TRAP_STOP and * TRAPPING, and kick it so that it transits to TRACED. TRAPPING * will be cleared if the child completes the transition or any * event which clears the group stop states happens. We'll wait * for the transition to complete before returning from this * function. * * This hides STOPPED -> RUNNING -> TRACED transition from the * attaching thread but a different thread in the same group can * still observe the transient RUNNING state. IOW, if another * thread's WNOHANG wait(2) on the stopped tracee races against * ATTACH, the wait(2) may fail due to the transient RUNNING. * * The following task_is_stopped() test is safe as both transitions * in and out of STOPPED are protected by siglock. */ if (task_is_stopped(task) && task_set_jobctl_pending(task, JOBCTL_TRAP_STOP | JOBCTL_TRAPPING)) { task->jobctl &= ~JOBCTL_STOPPED; signal_wake_up_state(task, __TASK_STOPPED); } } static int ptrace_attach(struct task_struct *task, long request, unsigned long addr, unsigned long flags) { bool seize = (request == PTRACE_SEIZE); int retval; if (seize) { if (addr != 0) return -EIO; /* * This duplicates the check in check_ptrace_options() because * ptrace_attach() and ptrace_setoptions() have historically * used different error codes for unknown ptrace options. */ if (flags & ~(unsigned long)PTRACE_O_MASK) return -EIO; retval = check_ptrace_options(flags); if (retval) return retval; flags = PT_PTRACED | PT_SEIZED | (flags << PT_OPT_FLAG_SHIFT); } else { flags = PT_PTRACED; } audit_ptrace(task); if (unlikely(task->flags & PF_KTHREAD)) return -EPERM; if (same_thread_group(task, current)) return -EPERM; /* * Protect exec's credential calculations against our interference; * SUID, SGID and LSM creds get determined differently * under ptrace. */ scoped_cond_guard (mutex_intr, return -ERESTARTNOINTR, &task->signal->cred_guard_mutex) { scoped_guard (task_lock, task) { retval = __ptrace_may_access(task, PTRACE_MODE_ATTACH_REALCREDS); if (retval) return retval; } scoped_guard (write_lock_irq, &tasklist_lock) { if (unlikely(task->exit_state)) return -EPERM; if (task->ptrace) return -EPERM; task->ptrace = flags; ptrace_link(task, current); ptrace_set_stopped(task, seize); } } /* * We do not bother to change retval or clear JOBCTL_TRAPPING * if wait_on_bit() was interrupted by SIGKILL. The tracer will * not return to user-mode, it will exit and clear this bit in * __ptrace_unlink() if it wasn't already cleared by the tracee; * and until then nobody can ptrace this task. */ wait_on_bit(&task->jobctl, JOBCTL_TRAPPING_BIT, TASK_KILLABLE); proc_ptrace_connector(task, PTRACE_ATTACH); return 0; } /** * ptrace_traceme -- helper for PTRACE_TRACEME * * Performs checks and sets PT_PTRACED. * Should be used by all ptrace implementations for PTRACE_TRACEME. */ static int ptrace_traceme(void) { int ret = -EPERM; write_lock_irq(&tasklist_lock); /* Are we already being traced? */ if (!current->ptrace) { ret = security_ptrace_traceme(current->parent); /* * Check PF_EXITING to ensure ->real_parent has not passed * exit_ptrace(). Otherwise we don't report the error but * pretend ->real_parent untraces us right after return. */ if (!ret && !(current->real_parent->flags & PF_EXITING)) { current->ptrace = PT_PTRACED; ptrace_link(current, current->real_parent); } } write_unlock_irq(&tasklist_lock); return ret; } /* * Called with irqs disabled, returns true if childs should reap themselves. */ static int ignoring_children(struct sighand_struct *sigh) { int ret; spin_lock(&sigh->siglock); ret = (sigh->action[SIGCHLD-1].sa.sa_handler == SIG_IGN) || (sigh->action[SIGCHLD-1].sa.sa_flags & SA_NOCLDWAIT); spin_unlock(&sigh->siglock); return ret; } /* * Called with tasklist_lock held for writing. * Unlink a traced task, and clean it up if it was a traced zombie. * Return true if it needs to be reaped with release_task(). * (We can't call release_task() here because we already hold tasklist_lock.) * * If it's a zombie, our attachedness prevented normal parent notification * or self-reaping. Do notification now if it would have happened earlier. * If it should reap itself, return true. * * If it's our own child, there is no notification to do. But if our normal * children self-reap, then this child was prevented by ptrace and we must * reap it now, in that case we must also wake up sub-threads sleeping in * do_wait(). */ static bool __ptrace_detach(struct task_struct *tracer, struct task_struct *p) { bool dead; __ptrace_unlink(p); if (p->exit_state != EXIT_ZOMBIE) return false; dead = !thread_group_leader(p); if (!dead && thread_group_empty(p)) { if (!same_thread_group(p->real_parent, tracer)) dead = do_notify_parent(p, p->exit_signal); else if (ignoring_children(tracer->sighand)) { __wake_up_parent(p, tracer); dead = true; } } /* Mark it as in the process of being reaped. */ if (dead) p->exit_state = EXIT_DEAD; return dead; } static int ptrace_detach(struct task_struct *child, unsigned int data) { if (!valid_signal(data)) return -EIO; /* Architecture-specific hardware disable .. */ ptrace_disable(child); write_lock_irq(&tasklist_lock); /* * We rely on ptrace_freeze_traced(). It can't be killed and * untraced by another thread, it can't be a zombie. */ WARN_ON(!child->ptrace || child->exit_state); /* * tasklist_lock avoids the race with wait_task_stopped(), see * the comment in ptrace_resume(). */ child->exit_code = data; __ptrace_detach(current, child); write_unlock_irq(&tasklist_lock); proc_ptrace_connector(child, PTRACE_DETACH); return 0; } /* * Detach all tasks we were using ptrace on. Called with tasklist held * for writing. */ void exit_ptrace(struct task_struct *tracer, struct list_head *dead) { struct task_struct *p, *n; list_for_each_entry_safe(p, n, &tracer->ptraced, ptrace_entry) { if (unlikely(p->ptrace & PT_EXITKILL)) send_sig_info(SIGKILL, SEND_SIG_PRIV, p); if (__ptrace_detach(tracer, p)) list_add(&p->ptrace_entry, dead); } } int ptrace_readdata(struct task_struct *tsk, unsigned long src, char __user *dst, int len) { int copied = 0; while (len > 0) { char buf[128]; int this_len, retval; this_len = (len > sizeof(buf)) ? sizeof(buf) : len; retval = ptrace_access_vm(tsk, src, buf, this_len, FOLL_FORCE); if (!retval) { if (copied) break; return -EIO; } if (copy_to_user(dst, buf, retval)) return -EFAULT; copied += retval; src += retval; dst += retval; len -= retval; } return copied; } int ptrace_writedata(struct task_struct *tsk, char __user *src, unsigned long dst, int len) { int copied = 0; while (len > 0) { char buf[128]; int this_len, retval; this_len = (len > sizeof(buf)) ? sizeof(buf) : len; if (copy_from_user(buf, src, this_len)) return -EFAULT; retval = ptrace_access_vm(tsk, dst, buf, this_len, FOLL_FORCE | FOLL_WRITE); if (!retval) { if (copied) break; return -EIO; } copied += retval; src += retval; dst += retval; len -= retval; } return copied; } static int ptrace_setoptions(struct task_struct *child, unsigned long data) { unsigned flags; int ret; ret = check_ptrace_options(data); if (ret) return ret; /* Avoid intermediate state when all opts are cleared */ flags = child->ptrace; flags &= ~(PTRACE_O_MASK << PT_OPT_FLAG_SHIFT); flags |= (data << PT_OPT_FLAG_SHIFT); child->ptrace = flags; return 0; } static int ptrace_getsiginfo(struct task_struct *child, kernel_siginfo_t *info) { unsigned long flags; int error = -ESRCH; if (lock_task_sighand(child, &flags)) { error = -EINVAL; if (likely(child->last_siginfo != NULL)) { copy_siginfo(info, child->last_siginfo); error = 0; } unlock_task_sighand(child, &flags); } return error; } static int ptrace_setsiginfo(struct task_struct *child, const kernel_siginfo_t *info) { unsigned long flags; int error = -ESRCH; if (lock_task_sighand(child, &flags)) { error = -EINVAL; if (likely(child->last_siginfo != NULL)) { copy_siginfo(child->last_siginfo, info); error = 0; } unlock_task_sighand(child, &flags); } return error; } static int ptrace_peek_siginfo(struct task_struct *child, unsigned long addr, unsigned long data) { struct ptrace_peeksiginfo_args arg; struct sigpending *pending; struct sigqueue *q; int ret, i; ret = copy_from_user(&arg, (void __user *) addr, sizeof(struct ptrace_peeksiginfo_args)); if (ret) return -EFAULT; if (arg.flags & ~PTRACE_PEEKSIGINFO_SHARED) return -EINVAL; /* unknown flags */ if (arg.nr < 0) return -EINVAL; /* Ensure arg.off fits in an unsigned long */ if (arg.off > ULONG_MAX) return 0; if (arg.flags & PTRACE_PEEKSIGINFO_SHARED) pending = &child->signal->shared_pending; else pending = &child->pending; for (i = 0; i < arg.nr; ) { kernel_siginfo_t info; unsigned long off = arg.off + i; bool found = false; spin_lock_irq(&child->sighand->siglock); list_for_each_entry(q, &pending->list, list) { if (!off--) { found = true; copy_siginfo(&info, &q->info); break; } } spin_unlock_irq(&child->sighand->siglock); if (!found) /* beyond the end of the list */ break; #ifdef CONFIG_COMPAT if (unlikely(in_compat_syscall())) { compat_siginfo_t __user *uinfo = compat_ptr(data); if (copy_siginfo_to_user32(uinfo, &info)) { ret = -EFAULT; break; } } else #endif { siginfo_t __user *uinfo = (siginfo_t __user *) data; if (copy_siginfo_to_user(uinfo, &info)) { ret = -EFAULT; break; } } data += sizeof(siginfo_t); i++; if (signal_pending(current)) break; cond_resched(); } if (i > 0) return i; return ret; } #ifdef CONFIG_RSEQ static long ptrace_get_rseq_configuration(struct task_struct *task, unsigned long size, void __user *data) { struct ptrace_rseq_configuration conf = { .rseq_abi_pointer = (u64)(uintptr_t)task->rseq, .rseq_abi_size = task->rseq_len, .signature = task->rseq_sig, .flags = 0, }; size = min_t(unsigned long, size, sizeof(conf)); if (copy_to_user(data, &conf, size)) return -EFAULT; return sizeof(conf); } #endif #define is_singlestep(request) ((request) == PTRACE_SINGLESTEP) #ifdef PTRACE_SINGLEBLOCK #define is_singleblock(request) ((request) == PTRACE_SINGLEBLOCK) #else #define is_singleblock(request) 0 #endif #ifdef PTRACE_SYSEMU #define is_sysemu_singlestep(request) ((request) == PTRACE_SYSEMU_SINGLESTEP) #else #define is_sysemu_singlestep(request) 0 #endif static int ptrace_resume(struct task_struct *child, long request, unsigned long data) { if (!valid_signal(data)) return -EIO; if (request == PTRACE_SYSCALL) set_task_syscall_work(child, SYSCALL_TRACE); else clear_task_syscall_work(child, SYSCALL_TRACE); #if defined(CONFIG_GENERIC_ENTRY) || defined(TIF_SYSCALL_EMU) if (request == PTRACE_SYSEMU || request == PTRACE_SYSEMU_SINGLESTEP) set_task_syscall_work(child, SYSCALL_EMU); else clear_task_syscall_work(child, SYSCALL_EMU); #endif if (is_singleblock(request)) { if (unlikely(!arch_has_block_step())) return -EIO; user_enable_block_step(child); } else if (is_singlestep(request) || is_sysemu_singlestep(request)) { if (unlikely(!arch_has_single_step())) return -EIO; user_enable_single_step(child); } else { user_disable_single_step(child); } /* * Change ->exit_code and ->state under siglock to avoid the race * with wait_task_stopped() in between; a non-zero ->exit_code will * wrongly look like another report from tracee. * * Note that we need siglock even if ->exit_code == data and/or this * status was not reported yet, the new status must not be cleared by * wait_task_stopped() after resume. */ spin_lock_irq(&child->sighand->siglock); child->exit_code = data; child->jobctl &= ~JOBCTL_TRACED; wake_up_state(child, __TASK_TRACED); spin_unlock_irq(&child->sighand->siglock); return 0; } #ifdef CONFIG_HAVE_ARCH_TRACEHOOK static const struct user_regset * find_regset(const struct user_regset_view *view, unsigned int type) { const struct user_regset *regset; int n; for (n = 0; n < view->n; ++n) { regset = view->regsets + n; if (regset->core_note_type == type) return regset; } return NULL; } static int ptrace_regset(struct task_struct *task, int req, unsigned int type, struct iovec *kiov) { const struct user_regset_view *view = task_user_regset_view(task); const struct user_regset *regset = find_regset(view, type); int regset_no; if (!regset || (kiov->iov_len % regset->size) != 0) return -EINVAL; regset_no = regset - view->regsets; kiov->iov_len = min(kiov->iov_len, (__kernel_size_t) (regset->n * regset->size)); if (req == PTRACE_GETREGSET) return copy_regset_to_user(task, view, regset_no, 0, kiov->iov_len, kiov->iov_base); else return copy_regset_from_user(task, view, regset_no, 0, kiov->iov_len, kiov->iov_base); } /* * This is declared in linux/regset.h and defined in machine-dependent * code. We put the export here, near the primary machine-neutral use, * to ensure no machine forgets it. */ EXPORT_SYMBOL_GPL(task_user_regset_view); static unsigned long ptrace_get_syscall_info_entry(struct task_struct *child, struct pt_regs *regs, struct ptrace_syscall_info *info) { unsigned long args[ARRAY_SIZE(info->entry.args)]; int i; info->op = PTRACE_SYSCALL_INFO_ENTRY; info->entry.nr = syscall_get_nr(child, regs); syscall_get_arguments(child, regs, args); for (i = 0; i < ARRAY_SIZE(args); i++) info->entry.args[i] = args[i]; /* args is the last field in struct ptrace_syscall_info.entry */ return offsetofend(struct ptrace_syscall_info, entry.args); } static unsigned long ptrace_get_syscall_info_seccomp(struct task_struct *child, struct pt_regs *regs, struct ptrace_syscall_info *info) { /* * As struct ptrace_syscall_info.entry is currently a subset * of struct ptrace_syscall_info.seccomp, it makes sense to * initialize that subset using ptrace_get_syscall_info_entry(). * This can be reconsidered in the future if these structures * diverge significantly enough. */ ptrace_get_syscall_info_entry(child, regs, info); info->op = PTRACE_SYSCALL_INFO_SECCOMP; info->seccomp.ret_data = child->ptrace_message; /* ret_data is the last field in struct ptrace_syscall_info.seccomp */ return offsetofend(struct ptrace_syscall_info, seccomp.ret_data); } static unsigned long ptrace_get_syscall_info_exit(struct task_struct *child, struct pt_regs *regs, struct ptrace_syscall_info *info) { info->op = PTRACE_SYSCALL_INFO_EXIT; info->exit.rval = syscall_get_error(child, regs); info->exit.is_error = !!info->exit.rval; if (!info->exit.is_error) info->exit.rval = syscall_get_return_value(child, regs); /* is_error is the last field in struct ptrace_syscall_info.exit */ return offsetofend(struct ptrace_syscall_info, exit.is_error); } static int ptrace_get_syscall_info(struct task_struct *child, unsigned long user_size, void __user *datavp) { struct pt_regs *regs = task_pt_regs(child); struct ptrace_syscall_info info = { .op = PTRACE_SYSCALL_INFO_NONE, .arch = syscall_get_arch(child), .instruction_pointer = instruction_pointer(regs), .stack_pointer = user_stack_pointer(regs), }; unsigned long actual_size = offsetof(struct ptrace_syscall_info, entry); unsigned long write_size; /* * This does not need lock_task_sighand() to access * child->last_siginfo because ptrace_freeze_traced() * called earlier by ptrace_check_attach() ensures that * the tracee cannot go away and clear its last_siginfo. */ switch (child->last_siginfo ? child->last_siginfo->si_code : 0) { case SIGTRAP | 0x80: switch (child->ptrace_message) { case PTRACE_EVENTMSG_SYSCALL_ENTRY: actual_size = ptrace_get_syscall_info_entry(child, regs, &info); break; case PTRACE_EVENTMSG_SYSCALL_EXIT: actual_size = ptrace_get_syscall_info_exit(child, regs, &info); break; } break; case SIGTRAP | (PTRACE_EVENT_SECCOMP << 8): actual_size = ptrace_get_syscall_info_seccomp(child, regs, &info); break; } write_size = min(actual_size, user_size); return copy_to_user(datavp, &info, write_size) ? -EFAULT : actual_size; } #endif /* CONFIG_HAVE_ARCH_TRACEHOOK */ int ptrace_request(struct task_struct *child, long request, unsigned long addr, unsigned long data) { bool seized = child->ptrace & PT_SEIZED; int ret = -EIO; kernel_siginfo_t siginfo, *si; void __user *datavp = (void __user *) data; unsigned long __user *datalp = datavp; unsigned long flags; switch (request) { case PTRACE_PEEKTEXT: case PTRACE_PEEKDATA: return generic_ptrace_peekdata(child, addr, data); case PTRACE_POKETEXT: case PTRACE_POKEDATA: return generic_ptrace_pokedata(child, addr, data); #ifdef PTRACE_OLDSETOPTIONS case PTRACE_OLDSETOPTIONS: #endif case PTRACE_SETOPTIONS: ret = ptrace_setoptions(child, data); break; case PTRACE_GETEVENTMSG: ret = put_user(child->ptrace_message, datalp); break; case PTRACE_PEEKSIGINFO: ret = ptrace_peek_siginfo(child, addr, data); break; case PTRACE_GETSIGINFO: ret = ptrace_getsiginfo(child, &siginfo); if (!ret) ret = copy_siginfo_to_user(datavp, &siginfo); break; case PTRACE_SETSIGINFO: ret = copy_siginfo_from_user(&siginfo, datavp); if (!ret) ret = ptrace_setsiginfo(child, &siginfo); break; case PTRACE_GETSIGMASK: { sigset_t *mask; if (addr != sizeof(sigset_t)) { ret = -EINVAL; break; } if (test_tsk_restore_sigmask(child)) mask = &child->saved_sigmask; else mask = &child->blocked; if (copy_to_user(datavp, mask, sizeof(sigset_t))) ret = -EFAULT; else ret = 0; break; } case PTRACE_SETSIGMASK: { sigset_t new_set; if (addr != sizeof(sigset_t)) { ret = -EINVAL; break; } if (copy_from_user(&new_set, datavp, sizeof(sigset_t))) { ret = -EFAULT; break; } sigdelsetmask(&new_set, sigmask(SIGKILL)|sigmask(SIGSTOP)); /* * Every thread does recalc_sigpending() after resume, so * retarget_shared_pending() and recalc_sigpending() are not * called here. */ spin_lock_irq(&child->sighand->siglock); child->blocked = new_set; spin_unlock_irq(&child->sighand->siglock); clear_tsk_restore_sigmask(child); ret = 0; break; } case PTRACE_INTERRUPT: /* * Stop tracee without any side-effect on signal or job * control. At least one trap is guaranteed to happen * after this request. If @child is already trapped, the * current trap is not disturbed and another trap will * happen after the current trap is ended with PTRACE_CONT. * * The actual trap might not be PTRACE_EVENT_STOP trap but * the pending condition is cleared regardless. */ if (unlikely(!seized || !lock_task_sighand(child, &flags))) break; /* * INTERRUPT doesn't disturb existing trap sans one * exception. If ptracer issued LISTEN for the current * STOP, this INTERRUPT should clear LISTEN and re-trap * tracee into STOP. */ if (likely(task_set_jobctl_pending(child, JOBCTL_TRAP_STOP))) ptrace_signal_wake_up(child, child->jobctl & JOBCTL_LISTENING); unlock_task_sighand(child, &flags); ret = 0; break; case PTRACE_LISTEN: /* * Listen for events. Tracee must be in STOP. It's not * resumed per-se but is not considered to be in TRACED by * wait(2) or ptrace(2). If an async event (e.g. group * stop state change) happens, tracee will enter STOP trap * again. Alternatively, ptracer can issue INTERRUPT to * finish listening and re-trap tracee into STOP. */ if (unlikely(!seized || !lock_task_sighand(child, &flags))) break; si = child->last_siginfo; if (likely(si && (si->si_code >> 8) == PTRACE_EVENT_STOP)) { child->jobctl |= JOBCTL_LISTENING; /* * If NOTIFY is set, it means event happened between * start of this trap and now. Trigger re-trap. */ if (child->jobctl & JOBCTL_TRAP_NOTIFY) ptrace_signal_wake_up(child, true); ret = 0; } unlock_task_sighand(child, &flags); break; case PTRACE_DETACH: /* detach a process that was attached. */ ret = ptrace_detach(child, data); break; #ifdef CONFIG_BINFMT_ELF_FDPIC case PTRACE_GETFDPIC: { struct mm_struct *mm = get_task_mm(child); unsigned long tmp = 0; ret = -ESRCH; if (!mm) break; switch (addr) { case PTRACE_GETFDPIC_EXEC: tmp = mm->context.exec_fdpic_loadmap; break; case PTRACE_GETFDPIC_INTERP: tmp = mm->context.interp_fdpic_loadmap; break; default: break; } mmput(mm); ret = put_user(tmp, datalp); break; } #endif case PTRACE_SINGLESTEP: #ifdef PTRACE_SINGLEBLOCK case PTRACE_SINGLEBLOCK: #endif #ifdef PTRACE_SYSEMU case PTRACE_SYSEMU: case PTRACE_SYSEMU_SINGLESTEP: #endif case PTRACE_SYSCALL: case PTRACE_CONT: return ptrace_resume(child, request, data); case PTRACE_KILL: send_sig_info(SIGKILL, SEND_SIG_NOINFO, child); return 0; #ifdef CONFIG_HAVE_ARCH_TRACEHOOK case PTRACE_GETREGSET: case PTRACE_SETREGSET: { struct iovec kiov; struct iovec __user *uiov = datavp; if (!access_ok(uiov, sizeof(*uiov))) return -EFAULT; if (__get_user(kiov.iov_base, &uiov->iov_base) || __get_user(kiov.iov_len, &uiov->iov_len)) return -EFAULT; ret = ptrace_regset(child, request, addr, &kiov); if (!ret) ret = __put_user(kiov.iov_len, &uiov->iov_len); break; } case PTRACE_GET_SYSCALL_INFO: ret = ptrace_get_syscall_info(child, addr, datavp); break; #endif case PTRACE_SECCOMP_GET_FILTER: ret = seccomp_get_filter(child, addr, datavp); break; case PTRACE_SECCOMP_GET_METADATA: ret = seccomp_get_metadata(child, addr, datavp); break; #ifdef CONFIG_RSEQ case PTRACE_GET_RSEQ_CONFIGURATION: ret = ptrace_get_rseq_configuration(child, addr, datavp); break; #endif case PTRACE_SET_SYSCALL_USER_DISPATCH_CONFIG: ret = syscall_user_dispatch_set_config(child, addr, datavp); break; case PTRACE_GET_SYSCALL_USER_DISPATCH_CONFIG: ret = syscall_user_dispatch_get_config(child, addr, datavp); break; default: break; } return ret; } SYSCALL_DEFINE4(ptrace, long, request, long, pid, unsigned long, addr, unsigned long, data) { struct task_struct *child; long ret; if (request == PTRACE_TRACEME) { ret = ptrace_traceme(); goto out; } child = find_get_task_by_vpid(pid); if (!child) { ret = -ESRCH; goto out; } if (request == PTRACE_ATTACH || request == PTRACE_SEIZE) { ret = ptrace_attach(child, request, addr, data); goto out_put_task_struct; } ret = ptrace_check_attach(child, request == PTRACE_KILL || request == PTRACE_INTERRUPT); if (ret < 0) goto out_put_task_struct; ret = arch_ptrace(child, request, addr, data); if (ret || request != PTRACE_DETACH) ptrace_unfreeze_traced(child); out_put_task_struct: put_task_struct(child); out: return ret; } int generic_ptrace_peekdata(struct task_struct *tsk, unsigned long addr, unsigned long data) { unsigned long tmp; int copied; copied = ptrace_access_vm(tsk, addr, &tmp, sizeof(tmp), FOLL_FORCE); if (copied != sizeof(tmp)) return -EIO; return put_user(tmp, (unsigned long __user *)data); } int generic_ptrace_pokedata(struct task_struct *tsk, unsigned long addr, unsigned long data) { int copied; copied = ptrace_access_vm(tsk, addr, &data, sizeof(data), FOLL_FORCE | FOLL_WRITE); return (copied == sizeof(data)) ? 0 : -EIO; } #if defined CONFIG_COMPAT int compat_ptrace_request(struct task_struct *child, compat_long_t request, compat_ulong_t addr, compat_ulong_t data) { compat_ulong_t __user *datap = compat_ptr(data); compat_ulong_t word; kernel_siginfo_t siginfo; int ret; switch (request) { case PTRACE_PEEKTEXT: case PTRACE_PEEKDATA: ret = ptrace_access_vm(child, addr, &word, sizeof(word), FOLL_FORCE); if (ret != sizeof(word)) ret = -EIO; else ret = put_user(word, datap); break; case PTRACE_POKETEXT: case PTRACE_POKEDATA: ret = ptrace_access_vm(child, addr, &data, sizeof(data), FOLL_FORCE | FOLL_WRITE); ret = (ret != sizeof(data) ? -EIO : 0); break; case PTRACE_GETEVENTMSG: ret = put_user((compat_ulong_t) child->ptrace_message, datap); break; case PTRACE_GETSIGINFO: ret = ptrace_getsiginfo(child, &siginfo); if (!ret) ret = copy_siginfo_to_user32( (struct compat_siginfo __user *) datap, &siginfo); break; case PTRACE_SETSIGINFO: ret = copy_siginfo_from_user32( &siginfo, (struct compat_siginfo __user *) datap); if (!ret) ret = ptrace_setsiginfo(child, &siginfo); break; #ifdef CONFIG_HAVE_ARCH_TRACEHOOK case PTRACE_GETREGSET: case PTRACE_SETREGSET: { struct iovec kiov; struct compat_iovec __user *uiov = (struct compat_iovec __user *) datap; compat_uptr_t ptr; compat_size_t len; if (!access_ok(uiov, sizeof(*uiov))) return -EFAULT; if (__get_user(ptr, &uiov->iov_base) || __get_user(len, &uiov->iov_len)) return -EFAULT; kiov.iov_base = compat_ptr(ptr); kiov.iov_len = len; ret = ptrace_regset(child, request, addr, &kiov); if (!ret) ret = __put_user(kiov.iov_len, &uiov->iov_len); break; } #endif default: ret = ptrace_request(child, request, addr, data); } return ret; } COMPAT_SYSCALL_DEFINE4(ptrace, compat_long_t, request, compat_long_t, pid, compat_long_t, addr, compat_long_t, data) { struct task_struct *child; long ret; if (request == PTRACE_TRACEME) { ret = ptrace_traceme(); goto out; } child = find_get_task_by_vpid(pid); if (!child) { ret = -ESRCH; goto out; } if (request == PTRACE_ATTACH || request == PTRACE_SEIZE) { ret = ptrace_attach(child, request, addr, data); goto out_put_task_struct; } ret = ptrace_check_attach(child, request == PTRACE_KILL || request == PTRACE_INTERRUPT); if (!ret) { ret = compat_arch_ptrace(child, request, addr, data); if (ret || request != PTRACE_DETACH) ptrace_unfreeze_traced(child); } out_put_task_struct: put_task_struct(child); out: return ret; } #endif /* CONFIG_COMPAT */ |
| 242 276 479 | 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 | /* SPDX-License-Identifier: GPL-2.0 */ #undef TRACE_SYSTEM #define TRACE_SYSTEM page_pool #if !defined(_TRACE_PAGE_POOL_H) || defined(TRACE_HEADER_MULTI_READ) #define _TRACE_PAGE_POOL_H #include <linux/types.h> #include <linux/tracepoint.h> #include <trace/events/mmflags.h> #include <net/page_pool/types.h> TRACE_EVENT(page_pool_release, TP_PROTO(const struct page_pool *pool, s32 inflight, u32 hold, u32 release), TP_ARGS(pool, inflight, hold, release), TP_STRUCT__entry( __field(const struct page_pool *, pool) __field(s32, inflight) __field(u32, hold) __field(u32, release) __field(u64, cnt) ), TP_fast_assign( __entry->pool = pool; __entry->inflight = inflight; __entry->hold = hold; __entry->release = release; __entry->cnt = pool->destroy_cnt; ), TP_printk("page_pool=%p inflight=%d hold=%u release=%u cnt=%llu", __entry->pool, __entry->inflight, __entry->hold, __entry->release, __entry->cnt) ); TRACE_EVENT(page_pool_state_release, TP_PROTO(const struct page_pool *pool, netmem_ref netmem, u32 release), TP_ARGS(pool, netmem, release), TP_STRUCT__entry( __field(const struct page_pool *, pool) __field(unsigned long, netmem) __field(u32, release) __field(unsigned long, pfn) ), TP_fast_assign( __entry->pool = pool; __entry->netmem = (__force unsigned long)netmem; __entry->release = release; __entry->pfn = netmem_pfn_trace(netmem); ), TP_printk("page_pool=%p netmem=%p is_net_iov=%lu pfn=0x%lx release=%u", __entry->pool, (void *)__entry->netmem, __entry->netmem & NET_IOV, __entry->pfn, __entry->release) ); TRACE_EVENT(page_pool_state_hold, TP_PROTO(const struct page_pool *pool, netmem_ref netmem, u32 hold), TP_ARGS(pool, netmem, hold), TP_STRUCT__entry( __field(const struct page_pool *, pool) __field(unsigned long, netmem) __field(u32, hold) __field(unsigned long, pfn) ), TP_fast_assign( __entry->pool = pool; __entry->netmem = (__force unsigned long)netmem; __entry->hold = hold; __entry->pfn = netmem_pfn_trace(netmem); ), TP_printk("page_pool=%p netmem=%p is_net_iov=%lu, pfn=0x%lx hold=%u", __entry->pool, (void *)__entry->netmem, __entry->netmem & NET_IOV, __entry->pfn, __entry->hold) ); TRACE_EVENT(page_pool_update_nid, TP_PROTO(const struct page_pool *pool, int new_nid), TP_ARGS(pool, new_nid), TP_STRUCT__entry( __field(const struct page_pool *, pool) __field(int, pool_nid) __field(int, new_nid) ), TP_fast_assign( __entry->pool = pool; __entry->pool_nid = pool->p.nid; __entry->new_nid = new_nid; ), TP_printk("page_pool=%p pool_nid=%d new_nid=%d", __entry->pool, __entry->pool_nid, __entry->new_nid) ); #endif /* _TRACE_PAGE_POOL_H */ /* This part must be outside protection */ #include <trace/define_trace.h> |
| 109 10 9554 70 49 229 527 423 32 84 85 199 199 563 5 152 22 136 8 12 16 14 197 153 83 175 3 43 13 11 2 3 5 96 45 50 31 18 47 96 628 134 582 625 629 2 2 181 612 610 421 422 422 9 9 46 422 422 399 153 247 145 146 146 146 7 7 7 7 14 14 14 14 14 270 270 270 272 10 10 161 161 15 23 23 19 19 166 165 162 14 28 22 370 327 46 46 2 44 12 63 51 38 13 51 1 422 420 28 4596 4591 51 4582 3 44 22 22 13 24 10 14 120 825 826 2 15 2 813 817 3 799 3 7 8 235 566 717 3 717 717 246 102 122 11 565 118 44 416 5 874 10 13 12 18 30 24 6 25 1 36 38 147 1 2 8 1 139 1 26 111 135 1 17 84 33 146 437 2 15 1 423 1 34 393 417 5 171 259 429 118 1 12 1 4 104 2 13 87 51 39 116 179 1 13 1 33 1 140 3 164 167 75 100 177 16 1 15 2 1 7 12 12 166 2 163 1 165 4 151 58 52 1 50 1 50 3 46 30 45 46 3 9 2 30 12 26 5 50 2 5 6 2 34 1 1 10 25 30 30 1 12 11 11 43 17 2 6 1 1 8 15 4194 2 4184 3 2089 2119 2089 2091 2090 39 2109 2111 10 40 2066 39 39 39 2178 39 2194 2198 32 346 346 116 2089 2088 598 34 37 17 290 55 2962 17 154 3154 193 3045 116 241 4118 54 67 3 72 4266 4262 2 9 4268 3430 114 1 263 1 237 49 110 74 37 151 3808 2584 4306 3 4300 4291 7 504 3808 3485 16 1 4260 9 5 14 28 93 4172 38 1 4 4186 5 3 2065 9 2089 143 33 4 29 40 9 31 105 106 105 51 76 41 51 47 11 59 76 76 51 25 17 59 8 8 36 73 77 74 380 5 376 331 18 27 24 38 60 14 13 4 3 6 16 1 2 13 1 8 1 1 1 1 1 18 1 4 1 7 6 274 275 3 269 3 266 3 263 292 4 288 9 262 12 545 395 9 7 14 9 20 11 7 7 44 9 17 290 51 28 42 2 2 1 1 1 8 58 94 216 2 4 27 30 154 118 7 2 64 6 1 21 88 204 1 2 10 22 17 65 34 65 9 2 21 10 14 117 120 1 2 118 2385 4 2379 2378 2383 8 1 2353 34 7 15 20 8 6 8 3 15 1 9 6 16 5 1 5 6 19 6 5 3 23 23 16 1 16 23 19 126 119 117 135 1 118 8 4 126 116 116 93 23 23 4 32 72 85 4 3 8 8 78 7 2 10 71 9 3 9 63 23 86 79 74 3 7 3 52 6 6 13 68 21 14 2 16 13 3 3 13 28 32 1 28 28 16 224 1 22 136 22 28 8 32 222 710 2 1 698 6 696 20 2 18 22 22 6 7 3 12 52 3 2 47 47 18 29 11 1 3 7 266 2 22 204 2 65 25 169 20 64 172 232 212 2 6 206 5 56 62 37 1 34 1 5 2 197 30 1 1 28 5 24 1 12 2 7 19 6 13 19 24 20 1 19 5 1 11 12 4 7 13 7 1 4 17 3 13 3 3 2 26 32 3 1 28 16 3 2 11 5 1 22 1 2 19 1 14 1 9 5 5 3 8 21 2 2 17 9584 9576 9562 2 825 147 437 118 179 17 4302 33 40 217 202 119 2389 22 1 6 15 16 225 291 707 20 52 48 69 28 170 22 213 29 17 5 32 16 20 22 20 9582 3 1 2 18 18 56 18 14 1 3 121 3 7 14 5 112 | 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 | // SPDX-License-Identifier: GPL-2.0-only /* Copyright (c) 2011-2014 PLUMgrid, http://plumgrid.com */ #include <linux/bpf.h> #include <linux/bpf-cgroup.h> #include <linux/bpf_trace.h> #include <linux/bpf_lirc.h> #include <linux/bpf_verifier.h> #include <linux/bsearch.h> #include <linux/btf.h> #include <linux/syscalls.h> #include <linux/slab.h> #include <linux/sched/signal.h> #include <linux/vmalloc.h> #include <linux/mmzone.h> #include <linux/anon_inodes.h> #include <linux/fdtable.h> #include <linux/file.h> #include <linux/fs.h> #include <linux/license.h> #include <linux/filter.h> #include <linux/kernel.h> #include <linux/idr.h> #include <linux/cred.h> #include <linux/timekeeping.h> #include <linux/ctype.h> #include <linux/nospec.h> #include <linux/audit.h> #include <uapi/linux/btf.h> #include <linux/pgtable.h> #include <linux/bpf_lsm.h> #include <linux/poll.h> #include <linux/sort.h> #include <linux/bpf-netns.h> #include <linux/rcupdate_trace.h> #include <linux/memcontrol.h> #include <linux/trace_events.h> #include <linux/tracepoint.h> #include <net/netfilter/nf_bpf_link.h> #include <net/netkit.h> #include <net/tcx.h> #define IS_FD_ARRAY(map) ((map)->map_type == BPF_MAP_TYPE_PERF_EVENT_ARRAY || \ (map)->map_type == BPF_MAP_TYPE_CGROUP_ARRAY || \ (map)->map_type == BPF_MAP_TYPE_ARRAY_OF_MAPS) #define IS_FD_PROG_ARRAY(map) ((map)->map_type == BPF_MAP_TYPE_PROG_ARRAY) #define IS_FD_HASH(map) ((map)->map_type == BPF_MAP_TYPE_HASH_OF_MAPS) #define IS_FD_MAP(map) (IS_FD_ARRAY(map) || IS_FD_PROG_ARRAY(map) || \ IS_FD_HASH(map)) #define BPF_OBJ_FLAG_MASK (BPF_F_RDONLY | BPF_F_WRONLY) DEFINE_PER_CPU(int, bpf_prog_active); static DEFINE_IDR(prog_idr); static DEFINE_SPINLOCK(prog_idr_lock); static DEFINE_IDR(map_idr); static DEFINE_SPINLOCK(map_idr_lock); static DEFINE_IDR(link_idr); static DEFINE_SPINLOCK(link_idr_lock); int sysctl_unprivileged_bpf_disabled __read_mostly = IS_BUILTIN(CONFIG_BPF_UNPRIV_DEFAULT_OFF) ? 2 : 0; static const struct bpf_map_ops * const bpf_map_types[] = { #define BPF_PROG_TYPE(_id, _name, prog_ctx_type, kern_ctx_type) #define BPF_MAP_TYPE(_id, _ops) \ [_id] = &_ops, #define BPF_LINK_TYPE(_id, _name) #include <linux/bpf_types.h> #undef BPF_PROG_TYPE #undef BPF_MAP_TYPE #undef BPF_LINK_TYPE }; /* * If we're handed a bigger struct than we know of, ensure all the unknown bits * are 0 - i.e. new user-space does not rely on any kernel feature extensions * we don't know about yet. * * There is a ToCToU between this function call and the following * copy_from_user() call. However, this is not a concern since this function is * meant to be a future-proofing of bits. */ int bpf_check_uarg_tail_zero(bpfptr_t uaddr, size_t expected_size, size_t actual_size) { int res; if (unlikely(actual_size > PAGE_SIZE)) /* silly large */ return -E2BIG; if (actual_size <= expected_size) return 0; if (uaddr.is_kernel) res = memchr_inv(uaddr.kernel + expected_size, 0, actual_size - expected_size) == NULL; else res = check_zeroed_user(uaddr.user + expected_size, actual_size - expected_size); if (res < 0) return res; return res ? 0 : -E2BIG; } const struct bpf_map_ops bpf_map_offload_ops = { .map_meta_equal = bpf_map_meta_equal, .map_alloc = bpf_map_offload_map_alloc, .map_free = bpf_map_offload_map_free, .map_check_btf = map_check_no_btf, .map_mem_usage = bpf_map_offload_map_mem_usage, }; static void bpf_map_write_active_inc(struct bpf_map *map) { atomic64_inc(&map->writecnt); } static void bpf_map_write_active_dec(struct bpf_map *map) { atomic64_dec(&map->writecnt); } bool bpf_map_write_active(const struct bpf_map *map) { return atomic64_read(&map->writecnt) != 0; } static u32 bpf_map_value_size(const struct bpf_map *map) { if (map->map_type == BPF_MAP_TYPE_PERCPU_HASH || map->map_type == BPF_MAP_TYPE_LRU_PERCPU_HASH || map->map_type == BPF_MAP_TYPE_PERCPU_ARRAY || map->map_type == BPF_MAP_TYPE_PERCPU_CGROUP_STORAGE) return round_up(map->value_size, 8) * num_possible_cpus(); else if (IS_FD_MAP(map)) return sizeof(u32); else return map->value_size; } static void maybe_wait_bpf_programs(struct bpf_map *map) { /* Wait for any running non-sleepable BPF programs to complete so that * userspace, when we return to it, knows that all non-sleepable * programs that could be running use the new map value. For sleepable * BPF programs, synchronize_rcu_tasks_trace() should be used to wait * for the completions of these programs, but considering the waiting * time can be very long and userspace may think it will hang forever, * so don't handle sleepable BPF programs now. */ if (map->map_type == BPF_MAP_TYPE_HASH_OF_MAPS || map->map_type == BPF_MAP_TYPE_ARRAY_OF_MAPS) synchronize_rcu(); } static void unpin_uptr_kaddr(void *kaddr) { if (kaddr) unpin_user_page(virt_to_page(kaddr)); } static void __bpf_obj_unpin_uptrs(struct btf_record *rec, u32 cnt, void *obj) { const struct btf_field *field; void **uptr_addr; int i; for (i = 0, field = rec->fields; i < cnt; i++, field++) { if (field->type != BPF_UPTR) continue; uptr_addr = obj + field->offset; unpin_uptr_kaddr(*uptr_addr); } } static void bpf_obj_unpin_uptrs(struct btf_record *rec, void *obj) { if (!btf_record_has_field(rec, BPF_UPTR)) return; __bpf_obj_unpin_uptrs(rec, rec->cnt, obj); } static int bpf_obj_pin_uptrs(struct btf_record *rec, void *obj) { const struct btf_field *field; const struct btf_type *t; unsigned long start, end; struct page *page; void **uptr_addr; int i, err; if (!btf_record_has_field(rec, BPF_UPTR)) return 0; for (i = 0, field = rec->fields; i < rec->cnt; i++, field++) { if (field->type != BPF_UPTR) continue; uptr_addr = obj + field->offset; start = *(unsigned long *)uptr_addr; if (!start) continue; t = btf_type_by_id(field->kptr.btf, field->kptr.btf_id); /* t->size was checked for zero before */ if (check_add_overflow(start, t->size - 1, &end)) { err = -EFAULT; goto unpin_all; } /* The uptr's struct cannot span across two pages */ if ((start & PAGE_MASK) != (end & PAGE_MASK)) { err = -EOPNOTSUPP; goto unpin_all; } err = pin_user_pages_fast(start, 1, FOLL_LONGTERM | FOLL_WRITE, &page); if (err != 1) goto unpin_all; if (PageHighMem(page)) { err = -EOPNOTSUPP; unpin_user_page(page); goto unpin_all; } *uptr_addr = page_address(page) + offset_in_page(start); } return 0; unpin_all: __bpf_obj_unpin_uptrs(rec, i, obj); return err; } static int bpf_map_update_value(struct bpf_map *map, struct file *map_file, void *key, void *value, __u64 flags) { int err; /* Need to create a kthread, thus must support schedule */ if (bpf_map_is_offloaded(map)) { return bpf_map_offload_update_elem(map, key, value, flags); } else if (map->map_type == BPF_MAP_TYPE_CPUMAP || map->map_type == BPF_MAP_TYPE_ARENA || map->map_type == BPF_MAP_TYPE_STRUCT_OPS) { return map->ops->map_update_elem(map, key, value, flags); } else if (map->map_type == BPF_MAP_TYPE_SOCKHASH || map->map_type == BPF_MAP_TYPE_SOCKMAP) { return sock_map_update_elem_sys(map, key, value, flags); } else if (IS_FD_PROG_ARRAY(map)) { return bpf_fd_array_map_update_elem(map, map_file, key, value, flags); } bpf_disable_instrumentation(); if (map->map_type == BPF_MAP_TYPE_PERCPU_HASH || map->map_type == BPF_MAP_TYPE_LRU_PERCPU_HASH) { err = bpf_percpu_hash_update(map, key, value, flags); } else if (map->map_type == BPF_MAP_TYPE_PERCPU_ARRAY) { err = bpf_percpu_array_update(map, key, value, flags); } else if (map->map_type == BPF_MAP_TYPE_PERCPU_CGROUP_STORAGE) { err = bpf_percpu_cgroup_storage_update(map, key, value, flags); } else if (IS_FD_ARRAY(map)) { err = bpf_fd_array_map_update_elem(map, map_file, key, value, flags); } else if (map->map_type == BPF_MAP_TYPE_HASH_OF_MAPS) { err = bpf_fd_htab_map_update_elem(map, map_file, key, value, flags); } else if (map->map_type == BPF_MAP_TYPE_REUSEPORT_SOCKARRAY) { /* rcu_read_lock() is not needed */ err = bpf_fd_reuseport_array_update_elem(map, key, value, flags); } else if (map->map_type == BPF_MAP_TYPE_QUEUE || map->map_type == BPF_MAP_TYPE_STACK || map->map_type == BPF_MAP_TYPE_BLOOM_FILTER) { err = map->ops->map_push_elem(map, value, flags); } else { err = bpf_obj_pin_uptrs(map->record, value); if (!err) { rcu_read_lock(); err = map->ops->map_update_elem(map, key, value, flags); rcu_read_unlock(); if (err) bpf_obj_unpin_uptrs(map->record, value); } } bpf_enable_instrumentation(); return err; } static int bpf_map_copy_value(struct bpf_map *map, void *key, void *value, __u64 flags) { void *ptr; int err; if (bpf_map_is_offloaded(map)) return bpf_map_offload_lookup_elem(map, key, value); bpf_disable_instrumentation(); if (map->map_type == BPF_MAP_TYPE_PERCPU_HASH || map->map_type == BPF_MAP_TYPE_LRU_PERCPU_HASH) { err = bpf_percpu_hash_copy(map, key, value); } else if (map->map_type == BPF_MAP_TYPE_PERCPU_ARRAY) { err = bpf_percpu_array_copy(map, key, value); } else if (map->map_type == BPF_MAP_TYPE_PERCPU_CGROUP_STORAGE) { err = bpf_percpu_cgroup_storage_copy(map, key, value); } else if (map->map_type == BPF_MAP_TYPE_STACK_TRACE) { err = bpf_stackmap_copy(map, key, value); } else if (IS_FD_ARRAY(map) || IS_FD_PROG_ARRAY(map)) { err = bpf_fd_array_map_lookup_elem(map, key, value); } else if (IS_FD_HASH(map)) { err = bpf_fd_htab_map_lookup_elem(map, key, value); } else if (map->map_type == BPF_MAP_TYPE_REUSEPORT_SOCKARRAY) { err = bpf_fd_reuseport_array_lookup_elem(map, key, value); } else if (map->map_type == BPF_MAP_TYPE_QUEUE || map->map_type == BPF_MAP_TYPE_STACK || map->map_type == BPF_MAP_TYPE_BLOOM_FILTER) { err = map->ops->map_peek_elem(map, value); } else if (map->map_type == BPF_MAP_TYPE_STRUCT_OPS) { /* struct_ops map requires directly updating "value" */ err = bpf_struct_ops_map_sys_lookup_elem(map, key, value); } else { rcu_read_lock(); if (map->ops->map_lookup_elem_sys_only) ptr = map->ops->map_lookup_elem_sys_only(map, key); else ptr = map->ops->map_lookup_elem(map, key); if (IS_ERR(ptr)) { err = PTR_ERR(ptr); } else if (!ptr) { err = -ENOENT; } else { err = 0; if (flags & BPF_F_LOCK) /* lock 'ptr' and copy everything but lock */ copy_map_value_locked(map, value, ptr, true); else copy_map_value(map, value, ptr); /* mask lock and timer, since value wasn't zero inited */ check_and_init_map_value(map, value); } rcu_read_unlock(); } bpf_enable_instrumentation(); return err; } /* Please, do not use this function outside from the map creation path * (e.g. in map update path) without taking care of setting the active * memory cgroup (see at bpf_map_kmalloc_node() for example). */ static void *__bpf_map_area_alloc(u64 size, int numa_node, bool mmapable) { /* We really just want to fail instead of triggering OOM killer * under memory pressure, therefore we set __GFP_NORETRY to kmalloc, * which is used for lower order allocation requests. * * It has been observed that higher order allocation requests done by * vmalloc with __GFP_NORETRY being set might fail due to not trying * to reclaim memory from the page cache, thus we set * __GFP_RETRY_MAYFAIL to avoid such situations. */ gfp_t gfp = bpf_memcg_flags(__GFP_NOWARN | __GFP_ZERO); unsigned int flags = 0; unsigned long align = 1; void *area; if (size >= SIZE_MAX) return NULL; /* kmalloc()'ed memory can't be mmap()'ed */ if (mmapable) { BUG_ON(!PAGE_ALIGNED(size)); align = SHMLBA; flags = VM_USERMAP; } else if (size <= (PAGE_SIZE << PAGE_ALLOC_COSTLY_ORDER)) { area = kmalloc_node(size, gfp | GFP_USER | __GFP_NORETRY, numa_node); if (area != NULL) return area; } return __vmalloc_node_range(size, align, VMALLOC_START, VMALLOC_END, gfp | GFP_KERNEL | __GFP_RETRY_MAYFAIL, PAGE_KERNEL, flags, numa_node, __builtin_return_address(0)); } void *bpf_map_area_alloc(u64 size, int numa_node) { return __bpf_map_area_alloc(size, numa_node, false); } void *bpf_map_area_mmapable_alloc(u64 size, int numa_node) { return __bpf_map_area_alloc(size, numa_node, true); } void bpf_map_area_free(void *area) { kvfree(area); } static u32 bpf_map_flags_retain_permanent(u32 flags) { /* Some map creation flags are not tied to the map object but * rather to the map fd instead, so they have no meaning upon * map object inspection since multiple file descriptors with * different (access) properties can exist here. Thus, given * this has zero meaning for the map itself, lets clear these * from here. */ return flags & ~(BPF_F_RDONLY | BPF_F_WRONLY); } void bpf_map_init_from_attr(struct bpf_map *map, union bpf_attr *attr) { map->map_type = attr->map_type; map->key_size = attr->key_size; map->value_size = attr->value_size; map->max_entries = attr->max_entries; map->map_flags = bpf_map_flags_retain_permanent(attr->map_flags); map->numa_node = bpf_map_attr_numa_node(attr); map->map_extra = attr->map_extra; } static int bpf_map_alloc_id(struct bpf_map *map) { int id; idr_preload(GFP_KERNEL); spin_lock_bh(&map_idr_lock); id = idr_alloc_cyclic(&map_idr, map, 1, INT_MAX, GFP_ATOMIC); if (id > 0) map->id = id; spin_unlock_bh(&map_idr_lock); idr_preload_end(); if (WARN_ON_ONCE(!id)) return -ENOSPC; return id > 0 ? 0 : id; } void bpf_map_free_id(struct bpf_map *map) { unsigned long flags; /* Offloaded maps are removed from the IDR store when their device * disappears - even if someone holds an fd to them they are unusable, * the memory is gone, all ops will fail; they are simply waiting for * refcnt to drop to be freed. */ if (!map->id) return; spin_lock_irqsave(&map_idr_lock, flags); idr_remove(&map_idr, map->id); map->id = 0; spin_unlock_irqrestore(&map_idr_lock, flags); } #ifdef CONFIG_MEMCG static void bpf_map_save_memcg(struct bpf_map *map) { /* Currently if a map is created by a process belonging to the root * memory cgroup, get_obj_cgroup_from_current() will return NULL. * So we have to check map->objcg for being NULL each time it's * being used. */ if (memcg_bpf_enabled()) map->objcg = get_obj_cgroup_from_current(); } static void bpf_map_release_memcg(struct bpf_map *map) { if (map->objcg) obj_cgroup_put(map->objcg); } static struct mem_cgroup *bpf_map_get_memcg(const struct bpf_map *map) { if (map->objcg) return get_mem_cgroup_from_objcg(map->objcg); return root_mem_cgroup; } void *bpf_map_kmalloc_node(const struct bpf_map *map, size_t size, gfp_t flags, int node) { struct mem_cgroup *memcg, *old_memcg; void *ptr; memcg = bpf_map_get_memcg(map); old_memcg = set_active_memcg(memcg); ptr = kmalloc_node(size, flags | __GFP_ACCOUNT, node); set_active_memcg(old_memcg); mem_cgroup_put(memcg); return ptr; } void *bpf_map_kzalloc(const struct bpf_map *map, size_t size, gfp_t flags) { struct mem_cgroup *memcg, *old_memcg; void *ptr; memcg = bpf_map_get_memcg(map); old_memcg = set_active_memcg(memcg); ptr = kzalloc(size, flags | __GFP_ACCOUNT); set_active_memcg(old_memcg); mem_cgroup_put(memcg); return ptr; } void *bpf_map_kvcalloc(struct bpf_map *map, size_t n, size_t size, gfp_t flags) { struct mem_cgroup *memcg, *old_memcg; void *ptr; memcg = bpf_map_get_memcg(map); old_memcg = set_active_memcg(memcg); ptr = kvcalloc(n, size, flags | __GFP_ACCOUNT); set_active_memcg(old_memcg); mem_cgroup_put(memcg); return ptr; } void __percpu *bpf_map_alloc_percpu(const struct bpf_map *map, size_t size, size_t align, gfp_t flags) { struct mem_cgroup *memcg, *old_memcg; void __percpu *ptr; memcg = bpf_map_get_memcg(map); old_memcg = set_active_memcg(memcg); ptr = __alloc_percpu_gfp(size, align, flags | __GFP_ACCOUNT); set_active_memcg(old_memcg); mem_cgroup_put(memcg); return ptr; } #else static void bpf_map_save_memcg(struct bpf_map *map) { } static void bpf_map_release_memcg(struct bpf_map *map) { } #endif int bpf_map_alloc_pages(const struct bpf_map *map, gfp_t gfp, int nid, unsigned long nr_pages, struct page **pages) { unsigned long i, j; struct page *pg; int ret = 0; #ifdef CONFIG_MEMCG struct mem_cgroup *memcg, *old_memcg; memcg = bpf_map_get_memcg(map); old_memcg = set_active_memcg(memcg); #endif for (i = 0; i < nr_pages; i++) { pg = alloc_pages_node(nid, gfp | __GFP_ACCOUNT, 0); if (pg) { pages[i] = pg; continue; } for (j = 0; j < i; j++) __free_page(pages[j]); ret = -ENOMEM; break; } #ifdef CONFIG_MEMCG set_active_memcg(old_memcg); mem_cgroup_put(memcg); #endif return ret; } static int btf_field_cmp(const void *a, const void *b) { const struct btf_field *f1 = a, *f2 = b; if (f1->offset < f2->offset) return -1; else if (f1->offset > f2->offset) return 1; return 0; } struct btf_field *btf_record_find(const struct btf_record *rec, u32 offset, u32 field_mask) { struct btf_field *field; if (IS_ERR_OR_NULL(rec) || !(rec->field_mask & field_mask)) return NULL; field = bsearch(&offset, rec->fields, rec->cnt, sizeof(rec->fields[0]), btf_field_cmp); if (!field || !(field->type & field_mask)) return NULL; return field; } void btf_record_free(struct btf_record *rec) { int i; if (IS_ERR_OR_NULL(rec)) return; for (i = 0; i < rec->cnt; i++) { switch (rec->fields[i].type) { case BPF_KPTR_UNREF: case BPF_KPTR_REF: case BPF_KPTR_PERCPU: case BPF_UPTR: if (rec->fields[i].kptr.module) module_put(rec->fields[i].kptr.module); if (btf_is_kernel(rec->fields[i].kptr.btf)) btf_put(rec->fields[i].kptr.btf); break; case BPF_LIST_HEAD: case BPF_LIST_NODE: case BPF_RB_ROOT: case BPF_RB_NODE: case BPF_SPIN_LOCK: case BPF_TIMER: case BPF_REFCOUNT: case BPF_WORKQUEUE: /* Nothing to release */ break; default: WARN_ON_ONCE(1); continue; } } kfree(rec); } void bpf_map_free_record(struct bpf_map *map) { btf_record_free(map->record); map->record = NULL; } struct btf_record *btf_record_dup(const struct btf_record *rec) { const struct btf_field *fields; struct btf_record *new_rec; int ret, size, i; if (IS_ERR_OR_NULL(rec)) return NULL; size = offsetof(struct btf_record, fields[rec->cnt]); new_rec = kmemdup(rec, size, GFP_KERNEL | __GFP_NOWARN); if (!new_rec) return ERR_PTR(-ENOMEM); /* Do a deep copy of the btf_record */ fields = rec->fields; new_rec->cnt = 0; for (i = 0; i < rec->cnt; i++) { switch (fields[i].type) { case BPF_KPTR_UNREF: case BPF_KPTR_REF: case BPF_KPTR_PERCPU: case BPF_UPTR: if (btf_is_kernel(fields[i].kptr.btf)) btf_get(fields[i].kptr.btf); if (fields[i].kptr.module && !try_module_get(fields[i].kptr.module)) { ret = -ENXIO; goto free; } break; case BPF_LIST_HEAD: case BPF_LIST_NODE: case BPF_RB_ROOT: case BPF_RB_NODE: case BPF_SPIN_LOCK: case BPF_TIMER: case BPF_REFCOUNT: case BPF_WORKQUEUE: /* Nothing to acquire */ break; default: ret = -EFAULT; WARN_ON_ONCE(1); goto free; } new_rec->cnt++; } return new_rec; free: btf_record_free(new_rec); return ERR_PTR(ret); } bool btf_record_equal(const struct btf_record *rec_a, const struct btf_record *rec_b) { bool a_has_fields = !IS_ERR_OR_NULL(rec_a), b_has_fields = !IS_ERR_OR_NULL(rec_b); int size; if (!a_has_fields && !b_has_fields) return true; if (a_has_fields != b_has_fields) return false; if (rec_a->cnt != rec_b->cnt) return false; size = offsetof(struct btf_record, fields[rec_a->cnt]); /* btf_parse_fields uses kzalloc to allocate a btf_record, so unused * members are zeroed out. So memcmp is safe to do without worrying * about padding/unused fields. * * While spin_lock, timer, and kptr have no relation to map BTF, * list_head metadata is specific to map BTF, the btf and value_rec * members in particular. btf is the map BTF, while value_rec points to * btf_record in that map BTF. * * So while by default, we don't rely on the map BTF (which the records * were parsed from) matching for both records, which is not backwards * compatible, in case list_head is part of it, we implicitly rely on * that by way of depending on memcmp succeeding for it. */ return !memcmp(rec_a, rec_b, size); } void bpf_obj_free_timer(const struct btf_record *rec, void *obj) { if (WARN_ON_ONCE(!btf_record_has_field(rec, BPF_TIMER))) return; bpf_timer_cancel_and_free(obj + rec->timer_off); } void bpf_obj_free_workqueue(const struct btf_record *rec, void *obj) { if (WARN_ON_ONCE(!btf_record_has_field(rec, BPF_WORKQUEUE))) return; bpf_wq_cancel_and_free(obj + rec->wq_off); } void bpf_obj_free_fields(const struct btf_record *rec, void *obj) { const struct btf_field *fields; int i; if (IS_ERR_OR_NULL(rec)) return; fields = rec->fields; for (i = 0; i < rec->cnt; i++) { struct btf_struct_meta *pointee_struct_meta; const struct btf_field *field = &fields[i]; void *field_ptr = obj + field->offset; void *xchgd_field; switch (fields[i].type) { case BPF_SPIN_LOCK: break; case BPF_TIMER: bpf_timer_cancel_and_free(field_ptr); break; case BPF_WORKQUEUE: bpf_wq_cancel_and_free(field_ptr); break; case BPF_KPTR_UNREF: WRITE_ONCE(*(u64 *)field_ptr, 0); break; case BPF_KPTR_REF: case BPF_KPTR_PERCPU: xchgd_field = (void *)xchg((unsigned long *)field_ptr, 0); if (!xchgd_field) break; if (!btf_is_kernel(field->kptr.btf)) { pointee_struct_meta = btf_find_struct_meta(field->kptr.btf, field->kptr.btf_id); __bpf_obj_drop_impl(xchgd_field, pointee_struct_meta ? pointee_struct_meta->record : NULL, fields[i].type == BPF_KPTR_PERCPU); } else { field->kptr.dtor(xchgd_field); } break; case BPF_UPTR: /* The caller ensured that no one is using the uptr */ unpin_uptr_kaddr(*(void **)field_ptr); break; case BPF_LIST_HEAD: if (WARN_ON_ONCE(rec->spin_lock_off < 0)) continue; bpf_list_head_free(field, field_ptr, obj + rec->spin_lock_off); break; case BPF_RB_ROOT: if (WARN_ON_ONCE(rec->spin_lock_off < 0)) continue; bpf_rb_root_free(field, field_ptr, obj + rec->spin_lock_off); break; case BPF_LIST_NODE: case BPF_RB_NODE: case BPF_REFCOUNT: break; default: WARN_ON_ONCE(1); continue; } } } static void bpf_map_free(struct bpf_map *map) { struct btf_record *rec = map->record; struct btf *btf = map->btf; /* implementation dependent freeing. Disabling migration to simplify * the free of values or special fields allocated from bpf memory * allocator. */ migrate_disable(); map->ops->map_free(map); migrate_enable(); /* Delay freeing of btf_record for maps, as map_free * callback usually needs access to them. It is better to do it here * than require each callback to do the free itself manually. * * Note that the btf_record stashed in map->inner_map_meta->record was * already freed using the map_free callback for map in map case which * eventually calls bpf_map_free_meta, since inner_map_meta is only a * template bpf_map struct used during verification. */ btf_record_free(rec); /* Delay freeing of btf for maps, as map_free callback may need * struct_meta info which will be freed with btf_put(). */ btf_put(btf); } /* called from workqueue */ static void bpf_map_free_deferred(struct work_struct *work) { struct bpf_map *map = container_of(work, struct bpf_map, work); security_bpf_map_free(map); bpf_map_release_memcg(map); bpf_map_free(map); } static void bpf_map_put_uref(struct bpf_map *map) { if (atomic64_dec_and_test(&map->usercnt)) { if (map->ops->map_release_uref) map->ops->map_release_uref(map); } } static void bpf_map_free_in_work(struct bpf_map *map) { INIT_WORK(&map->work, bpf_map_free_deferred); /* Avoid spawning kworkers, since they all might contend * for the same mutex like slab_mutex. */ queue_work(system_unbound_wq, &map->work); } static void bpf_map_free_rcu_gp(struct rcu_head *rcu) { bpf_map_free_in_work(container_of(rcu, struct bpf_map, rcu)); } static void bpf_map_free_mult_rcu_gp(struct rcu_head *rcu) { if (rcu_trace_implies_rcu_gp()) bpf_map_free_rcu_gp(rcu); else call_rcu(rcu, bpf_map_free_rcu_gp); } /* decrement map refcnt and schedule it for freeing via workqueue * (underlying map implementation ops->map_free() might sleep) */ void bpf_map_put(struct bpf_map *map) { if (atomic64_dec_and_test(&map->refcnt)) { /* bpf_map_free_id() must be called first */ bpf_map_free_id(map); WARN_ON_ONCE(atomic64_read(&map->sleepable_refcnt)); if (READ_ONCE(map->free_after_mult_rcu_gp)) call_rcu_tasks_trace(&map->rcu, bpf_map_free_mult_rcu_gp); else if (READ_ONCE(map->free_after_rcu_gp)) call_rcu(&map->rcu, bpf_map_free_rcu_gp); else bpf_map_free_in_work(map); } } EXPORT_SYMBOL_GPL(bpf_map_put); void bpf_map_put_with_uref(struct bpf_map *map) { bpf_map_put_uref(map); bpf_map_put(map); } static int bpf_map_release(struct inode *inode, struct file *filp) { struct bpf_map *map = filp->private_data; if (map->ops->map_release) map->ops->map_release(map, filp); bpf_map_put_with_uref(map); return 0; } static fmode_t map_get_sys_perms(struct bpf_map *map, struct fd f) { fmode_t mode = fd_file(f)->f_mode; /* Our file permissions may have been overridden by global * map permissions facing syscall side. */ if (READ_ONCE(map->frozen)) mode &= ~FMODE_CAN_WRITE; return mode; } #ifdef CONFIG_PROC_FS /* Show the memory usage of a bpf map */ static u64 bpf_map_memory_usage(const struct bpf_map *map) { return map->ops->map_mem_usage(map); } static void bpf_map_show_fdinfo(struct seq_file *m, struct file *filp) { struct bpf_map *map = filp->private_data; u32 type = 0, jited = 0; if (map_type_contains_progs(map)) { spin_lock(&map->owner.lock); type = map->owner.type; jited = map->owner.jited; spin_unlock(&map->owner.lock); } seq_printf(m, "map_type:\t%u\n" "key_size:\t%u\n" "value_size:\t%u\n" "max_entries:\t%u\n" "map_flags:\t%#x\n" "map_extra:\t%#llx\n" "memlock:\t%llu\n" "map_id:\t%u\n" "frozen:\t%u\n", map->map_type, map->key_size, map->value_size, map->max_entries, map->map_flags, (unsigned long long)map->map_extra, bpf_map_memory_usage(map), map->id, READ_ONCE(map->frozen)); if (type) { seq_printf(m, "owner_prog_type:\t%u\n", type); seq_printf(m, "owner_jited:\t%u\n", jited); } } #endif static ssize_t bpf_dummy_read(struct file *filp, char __user *buf, size_t siz, loff_t *ppos) { /* We need this handler such that alloc_file() enables * f_mode with FMODE_CAN_READ. */ return -EINVAL; } static ssize_t bpf_dummy_write(struct file *filp, const char __user *buf, size_t siz, loff_t *ppos) { /* We need this handler such that alloc_file() enables * f_mode with FMODE_CAN_WRITE. */ return -EINVAL; } /* called for any extra memory-mapped regions (except initial) */ static void bpf_map_mmap_open(struct vm_area_struct *vma) { struct bpf_map *map = vma->vm_file->private_data; if (vma->vm_flags & VM_MAYWRITE) bpf_map_write_active_inc(map); } /* called for all unmapped memory region (including initial) */ static void bpf_map_mmap_close(struct vm_area_struct *vma) { struct bpf_map *map = vma->vm_file->private_data; if (vma->vm_flags & VM_MAYWRITE) bpf_map_write_active_dec(map); } static const struct vm_operations_struct bpf_map_default_vmops = { .open = bpf_map_mmap_open, .close = bpf_map_mmap_close, }; static int bpf_map_mmap(struct file *filp, struct vm_area_struct *vma) { struct bpf_map *map = filp->private_data; int err; if (!map->ops->map_mmap || !IS_ERR_OR_NULL(map->record)) return -ENOTSUPP; if (!(vma->vm_flags & VM_SHARED)) return -EINVAL; mutex_lock(&map->freeze_mutex); if (vma->vm_flags & VM_WRITE) { if (map->frozen) { err = -EPERM; goto out; } /* map is meant to be read-only, so do not allow mapping as * writable, because it's possible to leak a writable page * reference and allows user-space to still modify it after * freezing, while verifier will assume contents do not change */ if (map->map_flags & BPF_F_RDONLY_PROG) { err = -EACCES; goto out; } } /* set default open/close callbacks */ vma->vm_ops = &bpf_map_default_vmops; vma->vm_private_data = map; vm_flags_clear(vma, VM_MAYEXEC); if (!(vma->vm_flags & VM_WRITE)) /* disallow re-mapping with PROT_WRITE */ vm_flags_clear(vma, VM_MAYWRITE); err = map->ops->map_mmap(map, vma); if (err) goto out; if (vma->vm_flags & VM_MAYWRITE) bpf_map_write_active_inc(map); out: mutex_unlock(&map->freeze_mutex); return err; } static __poll_t bpf_map_poll(struct file *filp, struct poll_table_struct *pts) { struct bpf_map *map = filp->private_data; if (map->ops->map_poll) return map->ops->map_poll(map, filp, pts); return EPOLLERR; } static unsigned long bpf_get_unmapped_area(struct file *filp, unsigned long addr, unsigned long len, unsigned long pgoff, unsigned long flags) { struct bpf_map *map = filp->private_data; if (map->ops->map_get_unmapped_area) return map->ops->map_get_unmapped_area(filp, addr, len, pgoff, flags); #ifdef CONFIG_MMU return mm_get_unmapped_area(current->mm, filp, addr, len, pgoff, flags); #else return addr; #endif } const struct file_operations bpf_map_fops = { #ifdef CONFIG_PROC_FS .show_fdinfo = bpf_map_show_fdinfo, #endif .release = bpf_map_release, .read = bpf_dummy_read, .write = bpf_dummy_write, .mmap = bpf_map_mmap, .poll = bpf_map_poll, .get_unmapped_area = bpf_get_unmapped_area, }; int bpf_map_new_fd(struct bpf_map *map, int flags) { int ret; ret = security_bpf_map(map, OPEN_FMODE(flags)); if (ret < 0) return ret; return anon_inode_getfd("bpf-map", &bpf_map_fops, map, flags | O_CLOEXEC); } int bpf_get_file_flag(int flags) { if ((flags & BPF_F_RDONLY) && (flags & BPF_F_WRONLY)) return -EINVAL; if (flags & BPF_F_RDONLY) return O_RDONLY; if (flags & BPF_F_WRONLY) return O_WRONLY; return O_RDWR; } /* helper macro to check that unused fields 'union bpf_attr' are zero */ #define CHECK_ATTR(CMD) \ memchr_inv((void *) &attr->CMD##_LAST_FIELD + \ sizeof(attr->CMD##_LAST_FIELD), 0, \ sizeof(*attr) - \ offsetof(union bpf_attr, CMD##_LAST_FIELD) - \ sizeof(attr->CMD##_LAST_FIELD)) != NULL /* dst and src must have at least "size" number of bytes. * Return strlen on success and < 0 on error. */ int bpf_obj_name_cpy(char *dst, const char *src, unsigned int size) { const char *end = src + size; const char *orig_src = src; memset(dst, 0, size); /* Copy all isalnum(), '_' and '.' chars. */ while (src < end && *src) { if (!isalnum(*src) && *src != '_' && *src != '.') return -EINVAL; *dst++ = *src++; } /* No '\0' found in "size" number of bytes */ if (src == end) return -EINVAL; return src - orig_src; } int map_check_no_btf(const struct bpf_map *map, const struct btf *btf, const struct btf_type *key_type, const struct btf_type *value_type) { return -ENOTSUPP; } static int map_check_btf(struct bpf_map *map, struct bpf_token *token, const struct btf *btf, u32 btf_key_id, u32 btf_value_id) { const struct btf_type *key_type, *value_type; u32 key_size, value_size; int ret = 0; /* Some maps allow key to be unspecified. */ if (btf_key_id) { key_type = btf_type_id_size(btf, &btf_key_id, &key_size); if (!key_type || key_size != map->key_size) return -EINVAL; } else { key_type = btf_type_by_id(btf, 0); if (!map->ops->map_check_btf) return -EINVAL; } value_type = btf_type_id_size(btf, &btf_value_id, &value_size); if (!value_type || value_size != map->value_size) return -EINVAL; map->record = btf_parse_fields(btf, value_type, BPF_SPIN_LOCK | BPF_TIMER | BPF_KPTR | BPF_LIST_HEAD | BPF_RB_ROOT | BPF_REFCOUNT | BPF_WORKQUEUE | BPF_UPTR, map->value_size); if (!IS_ERR_OR_NULL(map->record)) { int i; if (!bpf_token_capable(token, CAP_BPF)) { ret = -EPERM; goto free_map_tab; } if (map->map_flags & (BPF_F_RDONLY_PROG | BPF_F_WRONLY_PROG)) { ret = -EACCES; goto free_map_tab; } for (i = 0; i < sizeof(map->record->field_mask) * 8; i++) { switch (map->record->field_mask & (1 << i)) { case 0: continue; case BPF_SPIN_LOCK: if (map->map_type != BPF_MAP_TYPE_HASH && map->map_type != BPF_MAP_TYPE_ARRAY && map->map_type != BPF_MAP_TYPE_CGROUP_STORAGE && map->map_type != BPF_MAP_TYPE_SK_STORAGE && map->map_type != BPF_MAP_TYPE_INODE_STORAGE && map->map_type != BPF_MAP_TYPE_TASK_STORAGE && map->map_type != BPF_MAP_TYPE_CGRP_STORAGE) { ret = -EOPNOTSUPP; goto free_map_tab; } break; case BPF_TIMER: case BPF_WORKQUEUE: if (map->map_type != BPF_MAP_TYPE_HASH && map->map_type != BPF_MAP_TYPE_LRU_HASH && map->map_type != BPF_MAP_TYPE_ARRAY) { ret = -EOPNOTSUPP; goto free_map_tab; } break; case BPF_KPTR_UNREF: case BPF_KPTR_REF: case BPF_KPTR_PERCPU: case BPF_REFCOUNT: if (map->map_type != BPF_MAP_TYPE_HASH && map->map_type != BPF_MAP_TYPE_PERCPU_HASH && map->map_type != BPF_MAP_TYPE_LRU_HASH && map->map_type != BPF_MAP_TYPE_LRU_PERCPU_HASH && map->map_type != BPF_MAP_TYPE_ARRAY && map->map_type != BPF_MAP_TYPE_PERCPU_ARRAY && map->map_type != BPF_MAP_TYPE_SK_STORAGE && map->map_type != BPF_MAP_TYPE_INODE_STORAGE && map->map_type != BPF_MAP_TYPE_TASK_STORAGE && map->map_type != BPF_MAP_TYPE_CGRP_STORAGE) { ret = -EOPNOTSUPP; goto free_map_tab; } break; case BPF_UPTR: if (map->map_type != BPF_MAP_TYPE_TASK_STORAGE) { ret = -EOPNOTSUPP; goto free_map_tab; } break; case BPF_LIST_HEAD: case BPF_RB_ROOT: if (map->map_type != BPF_MAP_TYPE_HASH && map->map_type != BPF_MAP_TYPE_LRU_HASH && map->map_type != BPF_MAP_TYPE_ARRAY) { ret = -EOPNOTSUPP; goto free_map_tab; } break; default: /* Fail if map_type checks are missing for a field type */ ret = -EOPNOTSUPP; goto free_map_tab; } } } ret = btf_check_and_fixup_fields(btf, map->record); if (ret < 0) goto free_map_tab; if (map->ops->map_check_btf) { ret = map->ops->map_check_btf(map, btf, key_type, value_type); if (ret < 0) goto free_map_tab; } return ret; free_map_tab: bpf_map_free_record(map); return ret; } static bool bpf_net_capable(void) { return capable(CAP_NET_ADMIN) || capable(CAP_SYS_ADMIN); } #define BPF_MAP_CREATE_LAST_FIELD map_token_fd /* called via syscall */ static int map_create(union bpf_attr *attr) { const struct bpf_map_ops *ops; struct bpf_token *token = NULL; int numa_node = bpf_map_attr_numa_node(attr); u32 map_type = attr->map_type; struct bpf_map *map; bool token_flag; int f_flags; int err; err = CHECK_ATTR(BPF_MAP_CREATE); if (err) return -EINVAL; /* check BPF_F_TOKEN_FD flag, remember if it's set, and then clear it * to avoid per-map type checks tripping on unknown flag */ token_flag = attr->map_flags & BPF_F_TOKEN_FD; attr->map_flags &= ~BPF_F_TOKEN_FD; if (attr->btf_vmlinux_value_type_id) { if (attr->map_type != BPF_MAP_TYPE_STRUCT_OPS || attr->btf_key_type_id || attr->btf_value_type_id) return -EINVAL; } else if (attr->btf_key_type_id && !attr->btf_value_type_id) { return -EINVAL; } if (attr->map_type != BPF_MAP_TYPE_BLOOM_FILTER && attr->map_type != BPF_MAP_TYPE_ARENA && attr->map_extra != 0) return -EINVAL; f_flags = bpf_get_file_flag(attr->map_flags); if (f_flags < 0) return f_flags; if (numa_node != NUMA_NO_NODE && ((unsigned int)numa_node >= nr_node_ids || !node_online(numa_node))) return -EINVAL; /* find map type and init map: hashtable vs rbtree vs bloom vs ... */ map_type = attr->map_type; if (map_type >= ARRAY_SIZE(bpf_map_types)) return -EINVAL; map_type = array_index_nospec(map_type, ARRAY_SIZE(bpf_map_types)); ops = bpf_map_types[map_type]; if (!ops) return -EINVAL; if (ops->map_alloc_check) { err = ops->map_alloc_check(attr); if (err) return err; } if (attr->map_ifindex) ops = &bpf_map_offload_ops; if (!ops->map_mem_usage) return -EINVAL; if (token_flag) { token = bpf_token_get_from_fd(attr->map_token_fd); if (IS_ERR(token)) return PTR_ERR(token); /* if current token doesn't grant map creation permissions, * then we can't use this token, so ignore it and rely on * system-wide capabilities checks */ if (!bpf_token_allow_cmd(token, BPF_MAP_CREATE) || !bpf_token_allow_map_type(token, attr->map_type)) { bpf_token_put(token); token = NULL; } } err = -EPERM; /* Intent here is for unprivileged_bpf_disabled to block BPF map * creation for unprivileged users; other actions depend * on fd availability and access to bpffs, so are dependent on * object creation success. Even with unprivileged BPF disabled, * capability checks are still carried out. */ if (sysctl_unprivileged_bpf_disabled && !bpf_token_capable(token, CAP_BPF)) goto put_token; /* check privileged map type permissions */ switch (map_type) { case BPF_MAP_TYPE_ARRAY: case BPF_MAP_TYPE_PERCPU_ARRAY: case BPF_MAP_TYPE_PROG_ARRAY: case BPF_MAP_TYPE_PERF_EVENT_ARRAY: case BPF_MAP_TYPE_CGROUP_ARRAY: case BPF_MAP_TYPE_ARRAY_OF_MAPS: case BPF_MAP_TYPE_HASH: case BPF_MAP_TYPE_PERCPU_HASH: case BPF_MAP_TYPE_HASH_OF_MAPS: case BPF_MAP_TYPE_RINGBUF: case BPF_MAP_TYPE_USER_RINGBUF: case BPF_MAP_TYPE_CGROUP_STORAGE: case BPF_MAP_TYPE_PERCPU_CGROUP_STORAGE: /* unprivileged */ break; case BPF_MAP_TYPE_SK_STORAGE: case BPF_MAP_TYPE_INODE_STORAGE: case BPF_MAP_TYPE_TASK_STORAGE: case BPF_MAP_TYPE_CGRP_STORAGE: case BPF_MAP_TYPE_BLOOM_FILTER: case BPF_MAP_TYPE_LPM_TRIE: case BPF_MAP_TYPE_REUSEPORT_SOCKARRAY: case BPF_MAP_TYPE_STACK_TRACE: case BPF_MAP_TYPE_QUEUE: case BPF_MAP_TYPE_STACK: case BPF_MAP_TYPE_LRU_HASH: case BPF_MAP_TYPE_LRU_PERCPU_HASH: case BPF_MAP_TYPE_STRUCT_OPS: case BPF_MAP_TYPE_CPUMAP: case BPF_MAP_TYPE_ARENA: if (!bpf_token_capable(token, CAP_BPF)) goto put_token; break; case BPF_MAP_TYPE_SOCKMAP: case BPF_MAP_TYPE_SOCKHASH: case BPF_MAP_TYPE_DEVMAP: case BPF_MAP_TYPE_DEVMAP_HASH: case BPF_MAP_TYPE_XSKMAP: if (!bpf_token_capable(token, CAP_NET_ADMIN)) goto put_token; break; default: WARN(1, "unsupported map type %d", map_type); goto put_token; } map = ops->map_alloc(attr); if (IS_ERR(map)) { err = PTR_ERR(map); goto put_token; } map->ops = ops; map->map_type = map_type; err = bpf_obj_name_cpy(map->name, attr->map_name, sizeof(attr->map_name)); if (err < 0) goto free_map; atomic64_set(&map->refcnt, 1); atomic64_set(&map->usercnt, 1); mutex_init(&map->freeze_mutex); spin_lock_init(&map->owner.lock); if (attr->btf_key_type_id || attr->btf_value_type_id || /* Even the map's value is a kernel's struct, * the bpf_prog.o must have BTF to begin with * to figure out the corresponding kernel's * counter part. Thus, attr->btf_fd has * to be valid also. */ attr->btf_vmlinux_value_type_id) { struct btf *btf; btf = btf_get_by_fd(attr->btf_fd); if (IS_ERR(btf)) { err = PTR_ERR(btf); goto free_map; } if (btf_is_kernel(btf)) { btf_put(btf); err = -EACCES; goto free_map; } map->btf = btf; if (attr->btf_value_type_id) { err = map_check_btf(map, token, btf, attr->btf_key_type_id, attr->btf_value_type_id); if (err) goto free_map; } map->btf_key_type_id = attr->btf_key_type_id; map->btf_value_type_id = attr->btf_value_type_id; map->btf_vmlinux_value_type_id = attr->btf_vmlinux_value_type_id; } err = security_bpf_map_create(map, attr, token); if (err) goto free_map_sec; err = bpf_map_alloc_id(map); if (err) goto free_map_sec; bpf_map_save_memcg(map); bpf_token_put(token); err = bpf_map_new_fd(map, f_flags); if (err < 0) { /* failed to allocate fd. * bpf_map_put_with_uref() is needed because the above * bpf_map_alloc_id() has published the map * to the userspace and the userspace may * have refcnt-ed it through BPF_MAP_GET_FD_BY_ID. */ bpf_map_put_with_uref(map); return err; } return err; free_map_sec: security_bpf_map_free(map); free_map: bpf_map_free(map); put_token: bpf_token_put(token); return err; } void bpf_map_inc(struct bpf_map *map) { atomic64_inc(&map->refcnt); } EXPORT_SYMBOL_GPL(bpf_map_inc); void bpf_map_inc_with_uref(struct bpf_map *map) { atomic64_inc(&map->refcnt); atomic64_inc(&map->usercnt); } EXPORT_SYMBOL_GPL(bpf_map_inc_with_uref); struct bpf_map *bpf_map_get(u32 ufd) { CLASS(fd, f)(ufd); struct bpf_map *map = __bpf_map_get(f); if (!IS_ERR(map)) bpf_map_inc(map); return map; } EXPORT_SYMBOL(bpf_map_get); struct bpf_map *bpf_map_get_with_uref(u32 ufd) { CLASS(fd, f)(ufd); struct bpf_map *map = __bpf_map_get(f); if (!IS_ERR(map)) bpf_map_inc_with_uref(map); return map; } /* map_idr_lock should have been held or the map should have been * protected by rcu read lock. */ struct bpf_map *__bpf_map_inc_not_zero(struct bpf_map *map, bool uref) { int refold; refold = atomic64_fetch_add_unless(&map->refcnt, 1, 0); if (!refold) return ERR_PTR(-ENOENT); if (uref) atomic64_inc(&map->usercnt); return map; } struct bpf_map *bpf_map_inc_not_zero(struct bpf_map *map) { spin_lock_bh(&map_idr_lock); map = __bpf_map_inc_not_zero(map, false); spin_unlock_bh(&map_idr_lock); return map; } EXPORT_SYMBOL_GPL(bpf_map_inc_not_zero); int __weak bpf_stackmap_copy(struct bpf_map *map, void *key, void *value) { return -ENOTSUPP; } static void *__bpf_copy_key(void __user *ukey, u64 key_size) { if (key_size) return vmemdup_user(ukey, key_size); if (ukey) return ERR_PTR(-EINVAL); return NULL; } static void *___bpf_copy_key(bpfptr_t ukey, u64 key_size) { if (key_size) return kvmemdup_bpfptr(ukey, key_size); if (!bpfptr_is_null(ukey)) return ERR_PTR(-EINVAL); return NULL; } /* last field in 'union bpf_attr' used by this command */ #define BPF_MAP_LOOKUP_ELEM_LAST_FIELD flags static int map_lookup_elem(union bpf_attr *attr) { void __user *ukey = u64_to_user_ptr(attr->key); void __user *uvalue = u64_to_user_ptr(attr->value); struct bpf_map *map; void *key, *value; u32 value_size; int err; if (CHECK_ATTR(BPF_MAP_LOOKUP_ELEM)) return -EINVAL; if (attr->flags & ~BPF_F_LOCK) return -EINVAL; CLASS(fd, f)(attr->map_fd); map = __bpf_map_get(f); if (IS_ERR(map)) return PTR_ERR(map); if (!(map_get_sys_perms(map, f) & FMODE_CAN_READ)) return -EPERM; if ((attr->flags & BPF_F_LOCK) && !btf_record_has_field(map->record, BPF_SPIN_LOCK)) return -EINVAL; key = __bpf_copy_key(ukey, map->key_size); if (IS_ERR(key)) return PTR_ERR(key); value_size = bpf_map_value_size(map); err = -ENOMEM; value = kvmalloc(value_size, GFP_USER | __GFP_NOWARN); if (!value) goto free_key; if (map->map_type == BPF_MAP_TYPE_BLOOM_FILTER) { if (copy_from_user(value, uvalue, value_size)) err = -EFAULT; else err = bpf_map_copy_value(map, key, value, attr->flags); goto free_value; } err = bpf_map_copy_value(map, key, value, attr->flags); if (err) goto free_value; err = -EFAULT; if (copy_to_user(uvalue, value, value_size) != 0) goto free_value; err = 0; free_value: kvfree(value); free_key: kvfree(key); return err; } #define BPF_MAP_UPDATE_ELEM_LAST_FIELD flags static int map_update_elem(union bpf_attr *attr, bpfptr_t uattr) { bpfptr_t ukey = make_bpfptr(attr->key, uattr.is_kernel); bpfptr_t uvalue = make_bpfptr(attr->value, uattr.is_kernel); struct bpf_map *map; void *key, *value; u32 value_size; int err; if (CHECK_ATTR(BPF_MAP_UPDATE_ELEM)) return -EINVAL; CLASS(fd, f)(attr->map_fd); map = __bpf_map_get(f); if (IS_ERR(map)) return PTR_ERR(map); bpf_map_write_active_inc(map); if (!(map_get_sys_perms(map, f) & FMODE_CAN_WRITE)) { err = -EPERM; goto err_put; } if ((attr->flags & BPF_F_LOCK) && !btf_record_has_field(map->record, BPF_SPIN_LOCK)) { err = -EINVAL; goto err_put; } key = ___bpf_copy_key(ukey, map->key_size); if (IS_ERR(key)) { err = PTR_ERR(key); goto err_put; } value_size = bpf_map_value_size(map); value = kvmemdup_bpfptr(uvalue, value_size); if (IS_ERR(value)) { err = PTR_ERR(value); goto free_key; } err = bpf_map_update_value(map, fd_file(f), key, value, attr->flags); if (!err) maybe_wait_bpf_programs(map); kvfree(value); free_key: kvfree(key); err_put: bpf_map_write_active_dec(map); return err; } #define BPF_MAP_DELETE_ELEM_LAST_FIELD key static int map_delete_elem(union bpf_attr *attr, bpfptr_t uattr) { bpfptr_t ukey = make_bpfptr(attr->key, uattr.is_kernel); struct bpf_map *map; void *key; int err; if (CHECK_ATTR(BPF_MAP_DELETE_ELEM)) return -EINVAL; CLASS(fd, f)(attr->map_fd); map = __bpf_map_get(f); if (IS_ERR(map)) return PTR_ERR(map); bpf_map_write_active_inc(map); if (!(map_get_sys_perms(map, f) & FMODE_CAN_WRITE)) { err = -EPERM; goto err_put; } key = ___bpf_copy_key(ukey, map->key_size); if (IS_ERR(key)) { err = PTR_ERR(key); goto err_put; } if (bpf_map_is_offloaded(map)) { err = bpf_map_offload_delete_elem(map, key); goto out; } else if (IS_FD_PROG_ARRAY(map) || map->map_type == BPF_MAP_TYPE_STRUCT_OPS) { /* These maps require sleepable context */ err = map->ops->map_delete_elem(map, key); goto out; } bpf_disable_instrumentation(); rcu_read_lock(); err = map->ops->map_delete_elem(map, key); rcu_read_unlock(); bpf_enable_instrumentation(); if (!err) maybe_wait_bpf_programs(map); out: kvfree(key); err_put: bpf_map_write_active_dec(map); return err; } /* last field in 'union bpf_attr' used by this command */ #define BPF_MAP_GET_NEXT_KEY_LAST_FIELD next_key static int map_get_next_key(union bpf_attr *attr) { void __user *ukey = u64_to_user_ptr(attr->key); void __user *unext_key = u64_to_user_ptr(attr->next_key); struct bpf_map *map; void *key, *next_key; int err; if (CHECK_ATTR(BPF_MAP_GET_NEXT_KEY)) return -EINVAL; CLASS(fd, f)(attr->map_fd); map = __bpf_map_get(f); if (IS_ERR(map)) return PTR_ERR(map); if (!(map_get_sys_perms(map, f) & FMODE_CAN_READ)) return -EPERM; if (ukey) { key = __bpf_copy_key(ukey, map->key_size); if (IS_ERR(key)) return PTR_ERR(key); } else { key = NULL; } err = -ENOMEM; next_key = kvmalloc(map->key_size, GFP_USER); if (!next_key) goto free_key; if (bpf_map_is_offloaded(map)) { err = bpf_map_offload_get_next_key(map, key, next_key); goto out; } rcu_read_lock(); err = map->ops->map_get_next_key(map, key, next_key); rcu_read_unlock(); out: if (err) goto free_next_key; err = -EFAULT; if (copy_to_user(unext_key, next_key, map->key_size) != 0) goto free_next_key; err = 0; free_next_key: kvfree(next_key); free_key: kvfree(key); return err; } int generic_map_delete_batch(struct bpf_map *map, const union bpf_attr *attr, union bpf_attr __user *uattr) { void __user *keys = u64_to_user_ptr(attr->batch.keys); u32 cp, max_count; int err = 0; void *key; if (attr->batch.elem_flags & ~BPF_F_LOCK) return -EINVAL; if ((attr->batch.elem_flags & BPF_F_LOCK) && !btf_record_has_field(map->record, BPF_SPIN_LOCK)) { return -EINVAL; } max_count = attr->batch.count; if (!max_count) return 0; if (put_user(0, &uattr->batch.count)) return -EFAULT; key = kvmalloc(map->key_size, GFP_USER | __GFP_NOWARN); if (!key) return -ENOMEM; for (cp = 0; cp < max_count; cp++) { err = -EFAULT; if (copy_from_user(key, keys + cp * map->key_size, map->key_size)) break; if (bpf_map_is_offloaded(map)) { err = bpf_map_offload_delete_elem(map, key); break; } bpf_disable_instrumentation(); rcu_read_lock(); err = map->ops->map_delete_elem(map, key); rcu_read_unlock(); bpf_enable_instrumentation(); if (err) break; cond_resched(); } if (copy_to_user(&uattr->batch.count, &cp, sizeof(cp))) err = -EFAULT; kvfree(key); return err; } int generic_map_update_batch(struct bpf_map *map, struct file *map_file, const union bpf_attr *attr, union bpf_attr __user *uattr) { void __user *values = u64_to_user_ptr(attr->batch.values); void __user *keys = u64_to_user_ptr(attr->batch.keys); u32 value_size, cp, max_count; void *key, *value; int err = 0; if (attr->batch.elem_flags & ~BPF_F_LOCK) return -EINVAL; if ((attr->batch.elem_flags & BPF_F_LOCK) && !btf_record_has_field(map->record, BPF_SPIN_LOCK)) { return -EINVAL; } value_size = bpf_map_value_size(map); max_count = attr->batch.count; if (!max_count) return 0; if (put_user(0, &uattr->batch.count)) return -EFAULT; key = kvmalloc(map->key_size, GFP_USER | __GFP_NOWARN); if (!key) return -ENOMEM; value = kvmalloc(value_size, GFP_USER | __GFP_NOWARN); if (!value) { kvfree(key); return -ENOMEM; } for (cp = 0; cp < max_count; cp++) { err = -EFAULT; if (copy_from_user(key, keys + cp * map->key_size, map->key_size) || copy_from_user(value, values + cp * value_size, value_size)) break; err = bpf_map_update_value(map, map_file, key, value, attr->batch.elem_flags); if (err) break; cond_resched(); } if (copy_to_user(&uattr->batch.count, &cp, sizeof(cp))) err = -EFAULT; kvfree(value); kvfree(key); return err; } #define MAP_LOOKUP_RETRIES 3 int generic_map_lookup_batch(struct bpf_map *map, const union bpf_attr *attr, union bpf_attr __user *uattr) { void __user *uobatch = u64_to_user_ptr(attr->batch.out_batch); void __user *ubatch = u64_to_user_ptr(attr->batch.in_batch); void __user *values = u64_to_user_ptr(attr->batch.values); void __user *keys = u64_to_user_ptr(attr->batch.keys); void *buf, *buf_prevkey, *prev_key, *key, *value; int err, retry = MAP_LOOKUP_RETRIES; u32 value_size, cp, max_count; if (attr->batch.elem_flags & ~BPF_F_LOCK) return -EINVAL; if ((attr->batch.elem_flags & BPF_F_LOCK) && !btf_record_has_field(map->record, BPF_SPIN_LOCK)) return -EINVAL; value_size = bpf_map_value_size(map); max_count = attr->batch.count; if (!max_count) return 0; if (put_user(0, &uattr->batch.count)) return -EFAULT; buf_prevkey = kvmalloc(map->key_size, GFP_USER | __GFP_NOWARN); if (!buf_prevkey) return -ENOMEM; buf = kvmalloc(map->key_size + value_size, GFP_USER | __GFP_NOWARN); if (!buf) { kvfree(buf_prevkey); return -ENOMEM; } err = -EFAULT; prev_key = NULL; if (ubatch && copy_from_user(buf_prevkey, ubatch, map->key_size)) goto free_buf; key = buf; value = key + map->key_size; if (ubatch) prev_key = buf_prevkey; for (cp = 0; cp < max_count;) { rcu_read_lock(); err = map->ops->map_get_next_key(map, prev_key, key); rcu_read_unlock(); if (err) break; err = bpf_map_copy_value(map, key, value, attr->batch.elem_flags); if (err == -ENOENT) { if (retry) { retry--; continue; } err = -EINTR; break; } if (err) goto free_buf; if (copy_to_user(keys + cp * map->key_size, key, map->key_size)) { err = -EFAULT; goto free_buf; } if (copy_to_user(values + cp * value_size, value, value_size)) { err = -EFAULT; goto free_buf; } if (!prev_key) prev_key = buf_prevkey; swap(prev_key, key); retry = MAP_LOOKUP_RETRIES; cp++; cond_resched(); } if (err == -EFAULT) goto free_buf; if ((copy_to_user(&uattr->batch.count, &cp, sizeof(cp)) || (cp && copy_to_user(uobatch, prev_key, map->key_size)))) err = -EFAULT; free_buf: kvfree(buf_prevkey); kvfree(buf); return err; } #define BPF_MAP_LOOKUP_AND_DELETE_ELEM_LAST_FIELD flags static int map_lookup_and_delete_elem(union bpf_attr *attr) { void __user *ukey = u64_to_user_ptr(attr->key); void __user *uvalue = u64_to_user_ptr(attr->value); struct bpf_map *map; void *key, *value; u32 value_size; int err; if (CHECK_ATTR(BPF_MAP_LOOKUP_AND_DELETE_ELEM)) return -EINVAL; if (attr->flags & ~BPF_F_LOCK) return -EINVAL; CLASS(fd, f)(attr->map_fd); map = __bpf_map_get(f); if (IS_ERR(map)) return PTR_ERR(map); bpf_map_write_active_inc(map); if (!(map_get_sys_perms(map, f) & FMODE_CAN_READ) || !(map_get_sys_perms(map, f) & FMODE_CAN_WRITE)) { err = -EPERM; goto err_put; } if (attr->flags && (map->map_type == BPF_MAP_TYPE_QUEUE || map->map_type == BPF_MAP_TYPE_STACK)) { err = -EINVAL; goto err_put; } if ((attr->flags & BPF_F_LOCK) && !btf_record_has_field(map->record, BPF_SPIN_LOCK)) { err = -EINVAL; goto err_put; } key = __bpf_copy_key(ukey, map->key_size); if (IS_ERR(key)) { err = PTR_ERR(key); goto err_put; } value_size = bpf_map_value_size(map); err = -ENOMEM; value = kvmalloc(value_size, GFP_USER | __GFP_NOWARN); if (!value) goto free_key; err = -ENOTSUPP; if (map->map_type == BPF_MAP_TYPE_QUEUE || map->map_type == BPF_MAP_TYPE_STACK) { err = map->ops->map_pop_elem(map, value); } else if (map->map_type == BPF_MAP_TYPE_HASH || map->map_type == BPF_MAP_TYPE_PERCPU_HASH || map->map_type == BPF_MAP_TYPE_LRU_HASH || map->map_type == BPF_MAP_TYPE_LRU_PERCPU_HASH) { if (!bpf_map_is_offloaded(map)) { bpf_disable_instrumentation(); rcu_read_lock(); err = map->ops->map_lookup_and_delete_elem(map, key, value, attr->flags); rcu_read_unlock(); bpf_enable_instrumentation(); } } if (err) goto free_value; if (copy_to_user(uvalue, value, value_size) != 0) { err = -EFAULT; goto free_value; } err = 0; free_value: kvfree(value); free_key: kvfree(key); err_put: bpf_map_write_active_dec(map); return err; } #define BPF_MAP_FREEZE_LAST_FIELD map_fd static int map_freeze(const union bpf_attr *attr) { int err = 0; struct bpf_map *map; if (CHECK_ATTR(BPF_MAP_FREEZE)) return -EINVAL; CLASS(fd, f)(attr->map_fd); map = __bpf_map_get(f); if (IS_ERR(map)) return PTR_ERR(map); if (map->map_type == BPF_MAP_TYPE_STRUCT_OPS || !IS_ERR_OR_NULL(map->record)) return -ENOTSUPP; if (!(map_get_sys_perms(map, f) & FMODE_CAN_WRITE)) return -EPERM; mutex_lock(&map->freeze_mutex); if (bpf_map_write_active(map)) { err = -EBUSY; goto err_put; } if (READ_ONCE(map->frozen)) { err = -EBUSY; goto err_put; } WRITE_ONCE(map->frozen, true); err_put: mutex_unlock(&map->freeze_mutex); return err; } static const struct bpf_prog_ops * const bpf_prog_types[] = { #define BPF_PROG_TYPE(_id, _name, prog_ctx_type, kern_ctx_type) \ [_id] = & _name ## _prog_ops, #define BPF_MAP_TYPE(_id, _ops) #define BPF_LINK_TYPE(_id, _name) #include <linux/bpf_types.h> #undef BPF_PROG_TYPE #undef BPF_MAP_TYPE #undef BPF_LINK_TYPE }; static int find_prog_type(enum bpf_prog_type type, struct bpf_prog *prog) { const struct bpf_prog_ops *ops; if (type >= ARRAY_SIZE(bpf_prog_types)) return -EINVAL; type = array_index_nospec(type, ARRAY_SIZE(bpf_prog_types)); ops = bpf_prog_types[type]; if (!ops) return -EINVAL; if (!bpf_prog_is_offloaded(prog->aux)) prog->aux->ops = ops; else prog->aux->ops = &bpf_offload_prog_ops; prog->type = type; return 0; } enum bpf_audit { BPF_AUDIT_LOAD, BPF_AUDIT_UNLOAD, BPF_AUDIT_MAX, }; static const char * const bpf_audit_str[BPF_AUDIT_MAX] = { [BPF_AUDIT_LOAD] = "LOAD", [BPF_AUDIT_UNLOAD] = "UNLOAD", }; static void bpf_audit_prog(const struct bpf_prog *prog, unsigned int op) { struct audit_context *ctx = NULL; struct audit_buffer *ab; if (WARN_ON_ONCE(op >= BPF_AUDIT_MAX)) return; if (audit_enabled == AUDIT_OFF) return; if (!in_irq() && !irqs_disabled()) ctx = audit_context(); ab = audit_log_start(ctx, GFP_ATOMIC, AUDIT_BPF); if (unlikely(!ab)) return; audit_log_format(ab, "prog-id=%u op=%s", prog->aux->id, bpf_audit_str[op]); audit_log_end(ab); } static int bpf_prog_alloc_id(struct bpf_prog *prog) { int id; idr_preload(GFP_KERNEL); spin_lock_bh(&prog_idr_lock); id = idr_alloc_cyclic(&prog_idr, prog, 1, INT_MAX, GFP_ATOMIC); if (id > 0) prog->aux->id = id; spin_unlock_bh(&prog_idr_lock); idr_preload_end(); /* id is in [1, INT_MAX) */ if (WARN_ON_ONCE(!id)) return -ENOSPC; return id > 0 ? 0 : id; } void bpf_prog_free_id(struct bpf_prog *prog) { unsigned long flags; /* cBPF to eBPF migrations are currently not in the idr store. * Offloaded programs are removed from the store when their device * disappears - even if someone grabs an fd to them they are unusable, * simply waiting for refcnt to drop to be freed. */ if (!prog->aux->id) return; spin_lock_irqsave(&prog_idr_lock, flags); idr_remove(&prog_idr, prog->aux->id); prog->aux->id = 0; spin_unlock_irqrestore(&prog_idr_lock, flags); } static void __bpf_prog_put_rcu(struct rcu_head *rcu) { struct bpf_prog_aux *aux = container_of(rcu, struct bpf_prog_aux, rcu); kvfree(aux->func_info); kfree(aux->func_info_aux); free_uid(aux->user); security_bpf_prog_free(aux->prog); bpf_prog_free(aux->prog); } static void __bpf_prog_put_noref(struct bpf_prog *prog, bool deferred) { bpf_prog_kallsyms_del_all(prog); btf_put(prog->aux->btf); module_put(prog->aux->mod); kvfree(prog->aux->jited_linfo); kvfree(prog->aux->linfo); kfree(prog->aux->kfunc_tab); if (prog->aux->attach_btf) btf_put(prog->aux->attach_btf); if (deferred) { if (prog->sleepable) call_rcu_tasks_trace(&prog->aux->rcu, __bpf_prog_put_rcu); else call_rcu(&prog->aux->rcu, __bpf_prog_put_rcu); } else { __bpf_prog_put_rcu(&prog->aux->rcu); } } static void bpf_prog_put_deferred(struct work_struct *work) { struct bpf_prog_aux *aux; struct bpf_prog *prog; aux = container_of(work, struct bpf_prog_aux, work); prog = aux->prog; perf_event_bpf_event(prog, PERF_BPF_EVENT_PROG_UNLOAD, 0); bpf_audit_prog(prog, BPF_AUDIT_UNLOAD); bpf_prog_free_id(prog); __bpf_prog_put_noref(prog, true); } static void __bpf_prog_put(struct bpf_prog *prog) { struct bpf_prog_aux *aux = prog->aux; if (atomic64_dec_and_test(&aux->refcnt)) { if (in_irq() || irqs_disabled()) { INIT_WORK(&aux->work, bpf_prog_put_deferred); schedule_work(&aux->work); } else { bpf_prog_put_deferred(&aux->work); } } } void bpf_prog_put(struct bpf_prog *prog) { __bpf_prog_put(prog); } EXPORT_SYMBOL_GPL(bpf_prog_put); static int bpf_prog_release(struct inode *inode, struct file *filp) { struct bpf_prog *prog = filp->private_data; bpf_prog_put(prog); return 0; } struct bpf_prog_kstats { u64 nsecs; u64 cnt; u64 misses; }; void notrace bpf_prog_inc_misses_counter(struct bpf_prog *prog) { struct bpf_prog_stats *stats; unsigned int flags; stats = this_cpu_ptr(prog->stats); flags = u64_stats_update_begin_irqsave(&stats->syncp); u64_stats_inc(&stats->misses); u64_stats_update_end_irqrestore(&stats->syncp, flags); } static void bpf_prog_get_stats(const struct bpf_prog *prog, struct bpf_prog_kstats *stats) { u64 nsecs = 0, cnt = 0, misses = 0; int cpu; for_each_possible_cpu(cpu) { const struct bpf_prog_stats *st; unsigned int start; u64 tnsecs, tcnt, tmisses; st = per_cpu_ptr(prog->stats, cpu); do { start = u64_stats_fetch_begin(&st->syncp); tnsecs = u64_stats_read(&st->nsecs); tcnt = u64_stats_read(&st->cnt); tmisses = u64_stats_read(&st->misses); } while (u64_stats_fetch_retry(&st->syncp, start)); nsecs += tnsecs; cnt += tcnt; misses += tmisses; } stats->nsecs = nsecs; stats->cnt = cnt; stats->misses = misses; } #ifdef CONFIG_PROC_FS static void bpf_prog_show_fdinfo(struct seq_file *m, struct file *filp) { const struct bpf_prog *prog = filp->private_data; char prog_tag[sizeof(prog->tag) * 2 + 1] = { }; struct bpf_prog_kstats stats; bpf_prog_get_stats(prog, &stats); bin2hex(prog_tag, prog->tag, sizeof(prog->tag)); seq_printf(m, "prog_type:\t%u\n" "prog_jited:\t%u\n" "prog_tag:\t%s\n" "memlock:\t%llu\n" "prog_id:\t%u\n" "run_time_ns:\t%llu\n" "run_cnt:\t%llu\n" "recursion_misses:\t%llu\n" "verified_insns:\t%u\n", prog->type, prog->jited, prog_tag, prog->pages * 1ULL << PAGE_SHIFT, prog->aux->id, stats.nsecs, stats.cnt, stats.misses, prog->aux->verified_insns); } #endif const struct file_operations bpf_prog_fops = { #ifdef CONFIG_PROC_FS .show_fdinfo = bpf_prog_show_fdinfo, #endif .release = bpf_prog_release, .read = bpf_dummy_read, .write = bpf_dummy_write, }; int bpf_prog_new_fd(struct bpf_prog *prog) { int ret; ret = security_bpf_prog(prog); if (ret < 0) return ret; return anon_inode_getfd("bpf-prog", &bpf_prog_fops, prog, O_RDWR | O_CLOEXEC); } void bpf_prog_add(struct bpf_prog *prog, int i) { atomic64_add(i, &prog->aux->refcnt); } EXPORT_SYMBOL_GPL(bpf_prog_add); void bpf_prog_sub(struct bpf_prog *prog, int i) { /* Only to be used for undoing previous bpf_prog_add() in some * error path. We still know that another entity in our call * path holds a reference to the program, thus atomic_sub() can * be safely used in such cases! */ WARN_ON(atomic64_sub_return(i, &prog->aux->refcnt) == 0); } EXPORT_SYMBOL_GPL(bpf_prog_sub); void bpf_prog_inc(struct bpf_prog *prog) { atomic64_inc(&prog->aux->refcnt); } EXPORT_SYMBOL_GPL(bpf_prog_inc); /* prog_idr_lock should have been held */ struct bpf_prog *bpf_prog_inc_not_zero(struct bpf_prog *prog) { int refold; refold = atomic64_fetch_add_unless(&prog->aux->refcnt, 1, 0); if (!refold) return ERR_PTR(-ENOENT); return prog; } EXPORT_SYMBOL_GPL(bpf_prog_inc_not_zero); bool bpf_prog_get_ok(struct bpf_prog *prog, enum bpf_prog_type *attach_type, bool attach_drv) { /* not an attachment, just a refcount inc, always allow */ if (!attach_type) return true; if (prog->type != *attach_type) return false; if (bpf_prog_is_offloaded(prog->aux) && !attach_drv) return false; return true; } static struct bpf_prog *__bpf_prog_get(u32 ufd, enum bpf_prog_type *attach_type, bool attach_drv) { CLASS(fd, f)(ufd); struct bpf_prog *prog; if (fd_empty(f)) return ERR_PTR(-EBADF); if (fd_file(f)->f_op != &bpf_prog_fops) return ERR_PTR(-EINVAL); prog = fd_file(f)->private_data; if (!bpf_prog_get_ok(prog, attach_type, attach_drv)) return ERR_PTR(-EINVAL); bpf_prog_inc(prog); return prog; } struct bpf_prog *bpf_prog_get(u32 ufd) { return __bpf_prog_get(ufd, NULL, false); } struct bpf_prog *bpf_prog_get_type_dev(u32 ufd, enum bpf_prog_type type, bool attach_drv) { return __bpf_prog_get(ufd, &type, attach_drv); } EXPORT_SYMBOL_GPL(bpf_prog_get_type_dev); /* Initially all BPF programs could be loaded w/o specifying * expected_attach_type. Later for some of them specifying expected_attach_type * at load time became required so that program could be validated properly. * Programs of types that are allowed to be loaded both w/ and w/o (for * backward compatibility) expected_attach_type, should have the default attach * type assigned to expected_attach_type for the latter case, so that it can be * validated later at attach time. * * bpf_prog_load_fixup_attach_type() sets expected_attach_type in @attr if * prog type requires it but has some attach types that have to be backward * compatible. */ static void bpf_prog_load_fixup_attach_type(union bpf_attr *attr) { switch (attr->prog_type) { case BPF_PROG_TYPE_CGROUP_SOCK: /* Unfortunately BPF_ATTACH_TYPE_UNSPEC enumeration doesn't * exist so checking for non-zero is the way to go here. */ if (!attr->expected_attach_type) attr->expected_attach_type = BPF_CGROUP_INET_SOCK_CREATE; break; case BPF_PROG_TYPE_SK_REUSEPORT: if (!attr->expected_attach_type) attr->expected_attach_type = BPF_SK_REUSEPORT_SELECT; break; } } static int bpf_prog_load_check_attach(enum bpf_prog_type prog_type, enum bpf_attach_type expected_attach_type, struct btf *attach_btf, u32 btf_id, struct bpf_prog *dst_prog) { if (btf_id) { if (btf_id > BTF_MAX_TYPE) return -EINVAL; if (!attach_btf && !dst_prog) return -EINVAL; switch (prog_type) { case BPF_PROG_TYPE_TRACING: case BPF_PROG_TYPE_LSM: case BPF_PROG_TYPE_STRUCT_OPS: case BPF_PROG_TYPE_EXT: break; default: return -EINVAL; } } if (attach_btf && (!btf_id || dst_prog)) return -EINVAL; if (dst_prog && prog_type != BPF_PROG_TYPE_TRACING && prog_type != BPF_PROG_TYPE_EXT) return -EINVAL; switch (prog_type) { case BPF_PROG_TYPE_CGROUP_SOCK: switch (expected_attach_type) { case BPF_CGROUP_INET_SOCK_CREATE: case BPF_CGROUP_INET_SOCK_RELEASE: case BPF_CGROUP_INET4_POST_BIND: case BPF_CGROUP_INET6_POST_BIND: return 0; default: return -EINVAL; } case BPF_PROG_TYPE_CGROUP_SOCK_ADDR: switch (expected_attach_type) { case BPF_CGROUP_INET4_BIND: case BPF_CGROUP_INET6_BIND: case BPF_CGROUP_INET4_CONNECT: case BPF_CGROUP_INET6_CONNECT: case BPF_CGROUP_UNIX_CONNECT: case BPF_CGROUP_INET4_GETPEERNAME: case BPF_CGROUP_INET6_GETPEERNAME: case BPF_CGROUP_UNIX_GETPEERNAME: case BPF_CGROUP_INET4_GETSOCKNAME: case BPF_CGROUP_INET6_GETSOCKNAME: case BPF_CGROUP_UNIX_GETSOCKNAME: case BPF_CGROUP_UDP4_SENDMSG: case BPF_CGROUP_UDP6_SENDMSG: case BPF_CGROUP_UNIX_SENDMSG: case BPF_CGROUP_UDP4_RECVMSG: case BPF_CGROUP_UDP6_RECVMSG: case BPF_CGROUP_UNIX_RECVMSG: return 0; default: return -EINVAL; } case BPF_PROG_TYPE_CGROUP_SKB: switch (expected_attach_type) { case BPF_CGROUP_INET_INGRESS: case BPF_CGROUP_INET_EGRESS: return 0; default: return -EINVAL; } case BPF_PROG_TYPE_CGROUP_SOCKOPT: switch (expected_attach_type) { case BPF_CGROUP_SETSOCKOPT: case BPF_CGROUP_GETSOCKOPT: return 0; default: return -EINVAL; } case BPF_PROG_TYPE_SK_LOOKUP: if (expected_attach_type == BPF_SK_LOOKUP) return 0; return -EINVAL; case BPF_PROG_TYPE_SK_REUSEPORT: switch (expected_attach_type) { case BPF_SK_REUSEPORT_SELECT: case BPF_SK_REUSEPORT_SELECT_OR_MIGRATE: return 0; default: return -EINVAL; } case BPF_PROG_TYPE_NETFILTER: if (expected_attach_type == BPF_NETFILTER) return 0; return -EINVAL; case BPF_PROG_TYPE_SYSCALL: case BPF_PROG_TYPE_EXT: if (expected_attach_type) return -EINVAL; fallthrough; default: return 0; } } static bool is_net_admin_prog_type(enum bpf_prog_type prog_type) { switch (prog_type) { case BPF_PROG_TYPE_SCHED_CLS: case BPF_PROG_TYPE_SCHED_ACT: case BPF_PROG_TYPE_XDP: case BPF_PROG_TYPE_LWT_IN: case BPF_PROG_TYPE_LWT_OUT: case BPF_PROG_TYPE_LWT_XMIT: case BPF_PROG_TYPE_LWT_SEG6LOCAL: case BPF_PROG_TYPE_SK_SKB: case BPF_PROG_TYPE_SK_MSG: case BPF_PROG_TYPE_FLOW_DISSECTOR: case BPF_PROG_TYPE_CGROUP_DEVICE: case BPF_PROG_TYPE_CGROUP_SOCK: case BPF_PROG_TYPE_CGROUP_SOCK_ADDR: case BPF_PROG_TYPE_CGROUP_SOCKOPT: case BPF_PROG_TYPE_CGROUP_SYSCTL: case BPF_PROG_TYPE_SOCK_OPS: case BPF_PROG_TYPE_EXT: /* extends any prog */ case BPF_PROG_TYPE_NETFILTER: return true; case BPF_PROG_TYPE_CGROUP_SKB: /* always unpriv */ case BPF_PROG_TYPE_SK_REUSEPORT: /* equivalent to SOCKET_FILTER. need CAP_BPF only */ default: return false; } } static bool is_perfmon_prog_type(enum bpf_prog_type prog_type) { switch (prog_type) { case BPF_PROG_TYPE_KPROBE: case BPF_PROG_TYPE_TRACEPOINT: case BPF_PROG_TYPE_PERF_EVENT: case BPF_PROG_TYPE_RAW_TRACEPOINT: case BPF_PROG_TYPE_RAW_TRACEPOINT_WRITABLE: case BPF_PROG_TYPE_TRACING: case BPF_PROG_TYPE_LSM: case BPF_PROG_TYPE_STRUCT_OPS: /* has access to struct sock */ case BPF_PROG_TYPE_EXT: /* extends any prog */ return true; default: return false; } } /* last field in 'union bpf_attr' used by this command */ #define BPF_PROG_LOAD_LAST_FIELD fd_array_cnt static int bpf_prog_load(union bpf_attr *attr, bpfptr_t uattr, u32 uattr_size) { enum bpf_prog_type type = attr->prog_type; struct bpf_prog *prog, *dst_prog = NULL; struct btf *attach_btf = NULL; struct bpf_token *token = NULL; bool bpf_cap; int err; char license[128]; if (CHECK_ATTR(BPF_PROG_LOAD)) return -EINVAL; if (attr->prog_flags & ~(BPF_F_STRICT_ALIGNMENT | BPF_F_ANY_ALIGNMENT | BPF_F_TEST_STATE_FREQ | BPF_F_SLEEPABLE | BPF_F_TEST_RND_HI32 | BPF_F_XDP_HAS_FRAGS | BPF_F_XDP_DEV_BOUND_ONLY | BPF_F_TEST_REG_INVARIANTS | BPF_F_TOKEN_FD)) return -EINVAL; bpf_prog_load_fixup_attach_type(attr); if (attr->prog_flags & BPF_F_TOKEN_FD) { token = bpf_token_get_from_fd(attr->prog_token_fd); if (IS_ERR(token)) return PTR_ERR(token); /* if current token doesn't grant prog loading permissions, * then we can't use this token, so ignore it and rely on * system-wide capabilities checks */ if (!bpf_token_allow_cmd(token, BPF_PROG_LOAD) || !bpf_token_allow_prog_type(token, attr->prog_type, attr->expected_attach_type)) { bpf_token_put(token); token = NULL; } } bpf_cap = bpf_token_capable(token, CAP_BPF); err = -EPERM; if (!IS_ENABLED(CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS) && (attr->prog_flags & BPF_F_ANY_ALIGNMENT) && !bpf_cap) goto put_token; /* Intent here is for unprivileged_bpf_disabled to block BPF program * creation for unprivileged users; other actions depend * on fd availability and access to bpffs, so are dependent on * object creation success. Even with unprivileged BPF disabled, * capability checks are still carried out for these * and other operations. */ if (sysctl_unprivileged_bpf_disabled && !bpf_cap) goto put_token; if (attr->insn_cnt == 0 || attr->insn_cnt > (bpf_cap ? BPF_COMPLEXITY_LIMIT_INSNS : BPF_MAXINSNS)) { err = -E2BIG; goto put_token; } if (type != BPF_PROG_TYPE_SOCKET_FILTER && type != BPF_PROG_TYPE_CGROUP_SKB && !bpf_cap) goto put_token; if (is_net_admin_prog_type(type) && !bpf_token_capable(token, CAP_NET_ADMIN)) goto put_token; if (is_perfmon_prog_type(type) && !bpf_token_capable(token, CAP_PERFMON)) goto put_token; /* attach_prog_fd/attach_btf_obj_fd can specify fd of either bpf_prog * or btf, we need to check which one it is */ if (attr->attach_prog_fd) { dst_prog = bpf_prog_get(attr->attach_prog_fd); if (IS_ERR(dst_prog)) { dst_prog = NULL; attach_btf = btf_get_by_fd(attr->attach_btf_obj_fd); if (IS_ERR(attach_btf)) { err = -EINVAL; goto put_token; } if (!btf_is_kernel(attach_btf)) { /* attaching through specifying bpf_prog's BTF * objects directly might be supported eventually */ btf_put(attach_btf); err = -ENOTSUPP; goto put_token; } } } else if (attr->attach_btf_id) { /* fall back to vmlinux BTF, if BTF type ID is specified */ attach_btf = bpf_get_btf_vmlinux(); if (IS_ERR(attach_btf)) { err = PTR_ERR(attach_btf); goto put_token; } if (!attach_btf) { err = -EINVAL; goto put_token; } btf_get(attach_btf); } if (bpf_prog_load_check_attach(type, attr->expected_attach_type, attach_btf, attr->attach_btf_id, dst_prog)) { if (dst_prog) bpf_prog_put(dst_prog); if (attach_btf) btf_put(attach_btf); err = -EINVAL; goto put_token; } /* plain bpf_prog allocation */ prog = bpf_prog_alloc(bpf_prog_size(attr->insn_cnt), GFP_USER); if (!prog) { if (dst_prog) bpf_prog_put(dst_prog); if (attach_btf) btf_put(attach_btf); err = -EINVAL; goto put_token; } prog->expected_attach_type = attr->expected_attach_type; prog->sleepable = !!(attr->prog_flags & BPF_F_SLEEPABLE); prog->aux->attach_btf = attach_btf; prog->aux->attach_btf_id = attr->attach_btf_id; prog->aux->dst_prog = dst_prog; prog->aux->dev_bound = !!attr->prog_ifindex; prog->aux->xdp_has_frags = attr->prog_flags & BPF_F_XDP_HAS_FRAGS; /* move token into prog->aux, reuse taken refcnt */ prog->aux->token = token; token = NULL; prog->aux->user = get_current_user(); prog->len = attr->insn_cnt; err = -EFAULT; if (copy_from_bpfptr(prog->insns, make_bpfptr(attr->insns, uattr.is_kernel), bpf_prog_insn_size(prog)) != 0) goto free_prog; /* copy eBPF program license from user space */ if (strncpy_from_bpfptr(license, make_bpfptr(attr->license, uattr.is_kernel), sizeof(license) - 1) < 0) goto free_prog; license[sizeof(license) - 1] = 0; /* eBPF programs must be GPL compatible to use GPL-ed functions */ prog->gpl_compatible = license_is_gpl_compatible(license) ? 1 : 0; prog->orig_prog = NULL; prog->jited = 0; atomic64_set(&prog->aux->refcnt, 1); if (bpf_prog_is_dev_bound(prog->aux)) { err = bpf_prog_dev_bound_init(prog, attr); if (err) goto free_prog; } if (type == BPF_PROG_TYPE_EXT && dst_prog && bpf_prog_is_dev_bound(dst_prog->aux)) { err = bpf_prog_dev_bound_inherit(prog, dst_prog); if (err) goto free_prog; } /* * Bookkeeping for managing the program attachment chain. * * It might be tempting to set attach_tracing_prog flag at the attachment * time, but this will not prevent from loading bunch of tracing prog * first, then attach them one to another. * * The flag attach_tracing_prog is set for the whole program lifecycle, and * doesn't have to be cleared in bpf_tracing_link_release, since tracing * programs cannot change attachment target. */ if (type == BPF_PROG_TYPE_TRACING && dst_prog && dst_prog->type == BPF_PROG_TYPE_TRACING) { prog->aux->attach_tracing_prog = true; } /* find program type: socket_filter vs tracing_filter */ err = find_prog_type(type, prog); if (err < 0) goto free_prog; prog->aux->load_time = ktime_get_boottime_ns(); err = bpf_obj_name_cpy(prog->aux->name, attr->prog_name, sizeof(attr->prog_name)); if (err < 0) goto free_prog; err = security_bpf_prog_load(prog, attr, token); if (err) goto free_prog_sec; /* run eBPF verifier */ err = bpf_check(&prog, attr, uattr, uattr_size); if (err < 0) goto free_used_maps; prog = bpf_prog_select_runtime(prog, &err); if (err < 0) goto free_used_maps; err = bpf_prog_alloc_id(prog); if (err) goto free_used_maps; /* Upon success of bpf_prog_alloc_id(), the BPF prog is * effectively publicly exposed. However, retrieving via * bpf_prog_get_fd_by_id() will take another reference, * therefore it cannot be gone underneath us. * * Only for the time /after/ successful bpf_prog_new_fd() * and before returning to userspace, we might just hold * one reference and any parallel close on that fd could * rip everything out. Hence, below notifications must * happen before bpf_prog_new_fd(). * * Also, any failure handling from this point onwards must * be using bpf_prog_put() given the program is exposed. */ bpf_prog_kallsyms_add(prog); perf_event_bpf_event(prog, PERF_BPF_EVENT_PROG_LOAD, 0); bpf_audit_prog(prog, BPF_AUDIT_LOAD); err = bpf_prog_new_fd(prog); if (err < 0) bpf_prog_put(prog); return err; free_used_maps: /* In case we have subprogs, we need to wait for a grace * period before we can tear down JIT memory since symbols * are already exposed under kallsyms. */ __bpf_prog_put_noref(prog, prog->aux->real_func_cnt); return err; free_prog_sec: security_bpf_prog_free(prog); free_prog: free_uid(prog->aux->user); if (prog->aux->attach_btf) btf_put(prog->aux->attach_btf); bpf_prog_free(prog); put_token: bpf_token_put(token); return err; } #define BPF_OBJ_LAST_FIELD path_fd static int bpf_obj_pin(const union bpf_attr *attr) { int path_fd; if (CHECK_ATTR(BPF_OBJ) || attr->file_flags & ~BPF_F_PATH_FD) return -EINVAL; /* path_fd has to be accompanied by BPF_F_PATH_FD flag */ if (!(attr->file_flags & BPF_F_PATH_FD) && attr->path_fd) return -EINVAL; path_fd = attr->file_flags & BPF_F_PATH_FD ? attr->path_fd : AT_FDCWD; return bpf_obj_pin_user(attr->bpf_fd, path_fd, u64_to_user_ptr(attr->pathname)); } static int bpf_obj_get(const union bpf_attr *attr) { int path_fd; if (CHECK_ATTR(BPF_OBJ) || attr->bpf_fd != 0 || attr->file_flags & ~(BPF_OBJ_FLAG_MASK | BPF_F_PATH_FD)) return -EINVAL; /* path_fd has to be accompanied by BPF_F_PATH_FD flag */ if (!(attr->file_flags & BPF_F_PATH_FD) && attr->path_fd) return -EINVAL; path_fd = attr->file_flags & BPF_F_PATH_FD ? attr->path_fd : AT_FDCWD; return bpf_obj_get_user(path_fd, u64_to_user_ptr(attr->pathname), attr->file_flags); } /* bpf_link_init_sleepable() allows to specify whether BPF link itself has * "sleepable" semantics, which normally would mean that BPF link's attach * hook can dereference link or link's underlying program for some time after * detachment due to RCU Tasks Trace-based lifetime protection scheme. * BPF program itself can be non-sleepable, yet, because it's transitively * reachable through BPF link, its freeing has to be delayed until after RCU * Tasks Trace GP. */ void bpf_link_init_sleepable(struct bpf_link *link, enum bpf_link_type type, const struct bpf_link_ops *ops, struct bpf_prog *prog, bool sleepable) { WARN_ON(ops->dealloc && ops->dealloc_deferred); atomic64_set(&link->refcnt, 1); link->type = type; link->sleepable = sleepable; link->id = 0; link->ops = ops; link->prog = prog; } void bpf_link_init(struct bpf_link *link, enum bpf_link_type type, const struct bpf_link_ops *ops, struct bpf_prog *prog) { bpf_link_init_sleepable(link, type, ops, prog, false); } static void bpf_link_free_id(int id) { if (!id) return; spin_lock_bh(&link_idr_lock); idr_remove(&link_idr, id); spin_unlock_bh(&link_idr_lock); } /* Clean up bpf_link and corresponding anon_inode file and FD. After * anon_inode is created, bpf_link can't be just kfree()'d due to deferred * anon_inode's release() call. This helper marks bpf_link as * defunct, releases anon_inode file and puts reserved FD. bpf_prog's refcnt * is not decremented, it's the responsibility of a calling code that failed * to complete bpf_link initialization. * This helper eventually calls link's dealloc callback, but does not call * link's release callback. */ void bpf_link_cleanup(struct bpf_link_primer *primer) { primer->link->prog = NULL; bpf_link_free_id(primer->id); fput(primer->file); put_unused_fd(primer->fd); } void bpf_link_inc(struct bpf_link *link) { atomic64_inc(&link->refcnt); } static void bpf_link_dealloc(struct bpf_link *link) { /* now that we know that bpf_link itself can't be reached, put underlying BPF program */ if (link->prog) bpf_prog_put(link->prog); /* free bpf_link and its containing memory */ if (link->ops->dealloc_deferred) link->ops->dealloc_deferred(link); else link->ops->dealloc(link); } static void bpf_link_defer_dealloc_rcu_gp(struct rcu_head *rcu) { struct bpf_link *link = container_of(rcu, struct bpf_link, rcu); bpf_link_dealloc(link); } static void bpf_link_defer_dealloc_mult_rcu_gp(struct rcu_head *rcu) { if (rcu_trace_implies_rcu_gp()) bpf_link_defer_dealloc_rcu_gp(rcu); else call_rcu(rcu, bpf_link_defer_dealloc_rcu_gp); } /* bpf_link_free is guaranteed to be called from process context */ static void bpf_link_free(struct bpf_link *link) { const struct bpf_link_ops *ops = link->ops; bpf_link_free_id(link->id); /* detach BPF program, clean up used resources */ if (link->prog) ops->release(link); if (ops->dealloc_deferred) { /* Schedule BPF link deallocation, which will only then * trigger putting BPF program refcount. * If underlying BPF program is sleepable or BPF link's target * attach hookpoint is sleepable or otherwise requires RCU GPs * to ensure link and its underlying BPF program is not * reachable anymore, we need to first wait for RCU tasks * trace sync, and then go through "classic" RCU grace period */ if (link->sleepable || (link->prog && link->prog->sleepable)) call_rcu_tasks_trace(&link->rcu, bpf_link_defer_dealloc_mult_rcu_gp); else call_rcu(&link->rcu, bpf_link_defer_dealloc_rcu_gp); } else if (ops->dealloc) { bpf_link_dealloc(link); } } static void bpf_link_put_deferred(struct work_struct *work) { struct bpf_link *link = container_of(work, struct bpf_link, work); bpf_link_free(link); } /* bpf_link_put might be called from atomic context. It needs to be called * from sleepable context in order to acquire sleeping locks during the process. */ void bpf_link_put(struct bpf_link *link) { if (!atomic64_dec_and_test(&link->refcnt)) return; INIT_WORK(&link->work, bpf_link_put_deferred); schedule_work(&link->work); } EXPORT_SYMBOL(bpf_link_put); static void bpf_link_put_direct(struct bpf_link *link) { if (!atomic64_dec_and_test(&link->refcnt)) return; bpf_link_free(link); } static int bpf_link_release(struct inode *inode, struct file *filp) { struct bpf_link *link = filp->private_data; bpf_link_put_direct(link); return 0; } #ifdef CONFIG_PROC_FS #define BPF_PROG_TYPE(_id, _name, prog_ctx_type, kern_ctx_type) #define BPF_MAP_TYPE(_id, _ops) #define BPF_LINK_TYPE(_id, _name) [_id] = #_name, static const char *bpf_link_type_strs[] = { [BPF_LINK_TYPE_UNSPEC] = "<invalid>", #include <linux/bpf_types.h> }; #undef BPF_PROG_TYPE #undef BPF_MAP_TYPE #undef BPF_LINK_TYPE static void bpf_link_show_fdinfo(struct seq_file *m, struct file *filp) { const struct bpf_link *link = filp->private_data; const struct bpf_prog *prog = link->prog; enum bpf_link_type type = link->type; char prog_tag[sizeof(prog->tag) * 2 + 1] = { }; if (type < ARRAY_SIZE(bpf_link_type_strs) && bpf_link_type_strs[type]) { seq_printf(m, "link_type:\t%s\n", bpf_link_type_strs[type]); } else { WARN_ONCE(1, "missing BPF_LINK_TYPE(...) for link type %u\n", type); seq_printf(m, "link_type:\t<%u>\n", type); } seq_printf(m, "link_id:\t%u\n", link->id); if (prog) { bin2hex(prog_tag, prog->tag, sizeof(prog->tag)); seq_printf(m, "prog_tag:\t%s\n" "prog_id:\t%u\n", prog_tag, prog->aux->id); } if (link->ops->show_fdinfo) link->ops->show_fdinfo(link, m); } #endif static __poll_t bpf_link_poll(struct file *file, struct poll_table_struct *pts) { struct bpf_link *link = file->private_data; return link->ops->poll(file, pts); } static const struct file_operations bpf_link_fops = { #ifdef CONFIG_PROC_FS .show_fdinfo = bpf_link_show_fdinfo, #endif .release = bpf_link_release, .read = bpf_dummy_read, .write = bpf_dummy_write, }; static const struct file_operations bpf_link_fops_poll = { #ifdef CONFIG_PROC_FS .show_fdinfo = bpf_link_show_fdinfo, #endif .release = bpf_link_release, .read = bpf_dummy_read, .write = bpf_dummy_write, .poll = bpf_link_poll, }; static int bpf_link_alloc_id(struct bpf_link *link) { int id; idr_preload(GFP_KERNEL); spin_lock_bh(&link_idr_lock); id = idr_alloc_cyclic(&link_idr, link, 1, INT_MAX, GFP_ATOMIC); spin_unlock_bh(&link_idr_lock); idr_preload_end(); return id; } /* Prepare bpf_link to be exposed to user-space by allocating anon_inode file, * reserving unused FD and allocating ID from link_idr. This is to be paired * with bpf_link_settle() to install FD and ID and expose bpf_link to * user-space, if bpf_link is successfully attached. If not, bpf_link and * pre-allocated resources are to be freed with bpf_cleanup() call. All the * transient state is passed around in struct bpf_link_primer. * This is preferred way to create and initialize bpf_link, especially when * there are complicated and expensive operations in between creating bpf_link * itself and attaching it to BPF hook. By using bpf_link_prime() and * bpf_link_settle() kernel code using bpf_link doesn't have to perform * expensive (and potentially failing) roll back operations in a rare case * that file, FD, or ID can't be allocated. */ int bpf_link_prime(struct bpf_link *link, struct bpf_link_primer *primer) { struct file *file; int fd, id; fd = get_unused_fd_flags(O_CLOEXEC); if (fd < 0) return fd; id = bpf_link_alloc_id(link); if (id < 0) { put_unused_fd(fd); return id; } file = anon_inode_getfile("bpf_link", link->ops->poll ? &bpf_link_fops_poll : &bpf_link_fops, link, O_CLOEXEC); if (IS_ERR(file)) { bpf_link_free_id(id); put_unused_fd(fd); return PTR_ERR(file); } primer->link = link; primer->file = file; primer->fd = fd; primer->id = id; return 0; } int bpf_link_settle(struct bpf_link_primer *primer) { /* make bpf_link fetchable by ID */ spin_lock_bh(&link_idr_lock); primer->link->id = primer->id; spin_unlock_bh(&link_idr_lock); /* make bpf_link fetchable by FD */ fd_install(primer->fd, primer->file); /* pass through installed FD */ return primer->fd; } int bpf_link_new_fd(struct bpf_link *link) { return anon_inode_getfd("bpf-link", link->ops->poll ? &bpf_link_fops_poll : &bpf_link_fops, link, O_CLOEXEC); } struct bpf_link *bpf_link_get_from_fd(u32 ufd) { CLASS(fd, f)(ufd); struct bpf_link *link; if (fd_empty(f)) return ERR_PTR(-EBADF); if (fd_file(f)->f_op != &bpf_link_fops && fd_file(f)->f_op != &bpf_link_fops_poll) return ERR_PTR(-EINVAL); link = fd_file(f)->private_data; bpf_link_inc(link); return link; } EXPORT_SYMBOL(bpf_link_get_from_fd); static void bpf_tracing_link_release(struct bpf_link *link) { struct bpf_tracing_link *tr_link = container_of(link, struct bpf_tracing_link, link.link); WARN_ON_ONCE(bpf_trampoline_unlink_prog(&tr_link->link, tr_link->trampoline, tr_link->tgt_prog)); bpf_trampoline_put(tr_link->trampoline); /* tgt_prog is NULL if target is a kernel function */ if (tr_link->tgt_prog) bpf_prog_put(tr_link->tgt_prog); } static void bpf_tracing_link_dealloc(struct bpf_link *link) { struct bpf_tracing_link *tr_link = container_of(link, struct bpf_tracing_link, link.link); kfree(tr_link); } static void bpf_tracing_link_show_fdinfo(const struct bpf_link *link, struct seq_file *seq) { struct bpf_tracing_link *tr_link = container_of(link, struct bpf_tracing_link, link.link); u32 target_btf_id, target_obj_id; bpf_trampoline_unpack_key(tr_link->trampoline->key, &target_obj_id, &target_btf_id); seq_printf(seq, "attach_type:\t%d\n" "target_obj_id:\t%u\n" "target_btf_id:\t%u\n", tr_link->attach_type, target_obj_id, target_btf_id); } static int bpf_tracing_link_fill_link_info(const struct bpf_link *link, struct bpf_link_info *info) { struct bpf_tracing_link *tr_link = container_of(link, struct bpf_tracing_link, link.link); info->tracing.attach_type = tr_link->attach_type; bpf_trampoline_unpack_key(tr_link->trampoline->key, &info->tracing.target_obj_id, &info->tracing.target_btf_id); return 0; } static const struct bpf_link_ops bpf_tracing_link_lops = { .release = bpf_tracing_link_release, .dealloc = bpf_tracing_link_dealloc, .show_fdinfo = bpf_tracing_link_show_fdinfo, .fill_link_info = bpf_tracing_link_fill_link_info, }; static int bpf_tracing_prog_attach(struct bpf_prog *prog, int tgt_prog_fd, u32 btf_id, u64 bpf_cookie) { struct bpf_link_primer link_primer; struct bpf_prog *tgt_prog = NULL; struct bpf_trampoline *tr = NULL; struct bpf_tracing_link *link; u64 key = 0; int err; switch (prog->type) { case BPF_PROG_TYPE_TRACING: if (prog->expected_attach_type != BPF_TRACE_FENTRY && prog->expected_attach_type != BPF_TRACE_FEXIT && prog->expected_attach_type != BPF_MODIFY_RETURN) { err = -EINVAL; goto out_put_prog; } break; case BPF_PROG_TYPE_EXT: if (prog->expected_attach_type != 0) { err = -EINVAL; goto out_put_prog; } break; case BPF_PROG_TYPE_LSM: if (prog->expected_attach_type != BPF_LSM_MAC) { err = -EINVAL; goto out_put_prog; } break; default: err = -EINVAL; goto out_put_prog; } if (!!tgt_prog_fd != !!btf_id) { err = -EINVAL; goto out_put_prog; } if (tgt_prog_fd) { /* * For now we only allow new targets for BPF_PROG_TYPE_EXT. If this * part would be changed to implement the same for * BPF_PROG_TYPE_TRACING, do not forget to update the way how * attach_tracing_prog flag is set. */ if (prog->type != BPF_PROG_TYPE_EXT) { err = -EINVAL; goto out_put_prog; } tgt_prog = bpf_prog_get(tgt_prog_fd); if (IS_ERR(tgt_prog)) { err = PTR_ERR(tgt_prog); tgt_prog = NULL; goto out_put_prog; } key = bpf_trampoline_compute_key(tgt_prog, NULL, btf_id); } link = kzalloc(sizeof(*link), GFP_USER); if (!link) { err = -ENOMEM; goto out_put_prog; } bpf_link_init(&link->link.link, BPF_LINK_TYPE_TRACING, &bpf_tracing_link_lops, prog); link->attach_type = prog->expected_attach_type; link->link.cookie = bpf_cookie; mutex_lock(&prog->aux->dst_mutex); /* There are a few possible cases here: * * - if prog->aux->dst_trampoline is set, the program was just loaded * and not yet attached to anything, so we can use the values stored * in prog->aux * * - if prog->aux->dst_trampoline is NULL, the program has already been * attached to a target and its initial target was cleared (below) * * - if tgt_prog != NULL, the caller specified tgt_prog_fd + * target_btf_id using the link_create API. * * - if tgt_prog == NULL when this function was called using the old * raw_tracepoint_open API, and we need a target from prog->aux * * - if prog->aux->dst_trampoline and tgt_prog is NULL, the program * was detached and is going for re-attachment. * * - if prog->aux->dst_trampoline is NULL and tgt_prog and prog->aux->attach_btf * are NULL, then program was already attached and user did not provide * tgt_prog_fd so we have no way to find out or create trampoline */ if (!prog->aux->dst_trampoline && !tgt_prog) { /* * Allow re-attach for TRACING and LSM programs. If it's * currently linked, bpf_trampoline_link_prog will fail. * EXT programs need to specify tgt_prog_fd, so they * re-attach in separate code path. */ if (prog->type != BPF_PROG_TYPE_TRACING && prog->type != BPF_PROG_TYPE_LSM) { err = -EINVAL; goto out_unlock; } /* We can allow re-attach only if we have valid attach_btf. */ if (!prog->aux->attach_btf) { err = -EINVAL; goto out_unlock; } btf_id = prog->aux->attach_btf_id; key = bpf_trampoline_compute_key(NULL, prog->aux->attach_btf, btf_id); } if (!prog->aux->dst_trampoline || (key && key != prog->aux->dst_trampoline->key)) { /* If there is no saved target, or the specified target is * different from the destination specified at load time, we * need a new trampoline and a check for compatibility */ struct bpf_attach_target_info tgt_info = {}; err = bpf_check_attach_target(NULL, prog, tgt_prog, btf_id, &tgt_info); if (err) goto out_unlock; if (tgt_info.tgt_mod) { module_put(prog->aux->mod); prog->aux->mod = tgt_info.tgt_mod; } tr = bpf_trampoline_get(key, &tgt_info); if (!tr) { err = -ENOMEM; goto out_unlock; } } else { /* The caller didn't specify a target, or the target was the * same as the destination supplied during program load. This * means we can reuse the trampoline and reference from program * load time, and there is no need to allocate a new one. This * can only happen once for any program, as the saved values in * prog->aux are cleared below. */ tr = prog->aux->dst_trampoline; tgt_prog = prog->aux->dst_prog; } err = bpf_link_prime(&link->link.link, &link_primer); if (err) goto out_unlock; err = bpf_trampoline_link_prog(&link->link, tr, tgt_prog); if (err) { bpf_link_cleanup(&link_primer); link = NULL; goto out_unlock; } link->tgt_prog = tgt_prog; link->trampoline = tr; /* Always clear the trampoline and target prog from prog->aux to make * sure the original attach destination is not kept alive after a * program is (re-)attached to another target. */ if (prog->aux->dst_prog && (tgt_prog_fd || tr != prog->aux->dst_trampoline)) /* got extra prog ref from syscall, or attaching to different prog */ bpf_prog_put(prog->aux->dst_prog); if (prog->aux->dst_trampoline && tr != prog->aux->dst_trampoline) /* we allocated a new trampoline, so free the old one */ bpf_trampoline_put(prog->aux->dst_trampoline); prog->aux->dst_prog = NULL; prog->aux->dst_trampoline = NULL; mutex_unlock(&prog->aux->dst_mutex); return bpf_link_settle(&link_primer); out_unlock: if (tr && tr != prog->aux->dst_trampoline) bpf_trampoline_put(tr); mutex_unlock(&prog->aux->dst_mutex); kfree(link); out_put_prog: if (tgt_prog_fd && tgt_prog) bpf_prog_put(tgt_prog); return err; } static void bpf_raw_tp_link_release(struct bpf_link *link) { struct bpf_raw_tp_link *raw_tp = container_of(link, struct bpf_raw_tp_link, link); bpf_probe_unregister(raw_tp->btp, raw_tp); bpf_put_raw_tracepoint(raw_tp->btp); } static void bpf_raw_tp_link_dealloc(struct bpf_link *link) { struct bpf_raw_tp_link *raw_tp = container_of(link, struct bpf_raw_tp_link, link); kfree(raw_tp); } static void bpf_raw_tp_link_show_fdinfo(const struct bpf_link *link, struct seq_file *seq) { struct bpf_raw_tp_link *raw_tp_link = container_of(link, struct bpf_raw_tp_link, link); seq_printf(seq, "tp_name:\t%s\n", raw_tp_link->btp->tp->name); } static int bpf_copy_to_user(char __user *ubuf, const char *buf, u32 ulen, u32 len) { if (ulen >= len + 1) { if (copy_to_user(ubuf, buf, len + 1)) return -EFAULT; } else { char zero = '\0'; if (copy_to_user(ubuf, buf, ulen - 1)) return -EFAULT; if (put_user(zero, ubuf + ulen - 1)) return -EFAULT; return -ENOSPC; } return 0; } static int bpf_raw_tp_link_fill_link_info(const struct bpf_link *link, struct bpf_link_info *info) { struct bpf_raw_tp_link *raw_tp_link = container_of(link, struct bpf_raw_tp_link, link); char __user *ubuf = u64_to_user_ptr(info->raw_tracepoint.tp_name); const char *tp_name = raw_tp_link->btp->tp->name; u32 ulen = info->raw_tracepoint.tp_name_len; size_t tp_len = strlen(tp_name); if (!ulen ^ !ubuf) return -EINVAL; info->raw_tracepoint.tp_name_len = tp_len + 1; if (!ubuf) return 0; return bpf_copy_to_user(ubuf, tp_name, ulen, tp_len); } static const struct bpf_link_ops bpf_raw_tp_link_lops = { .release = bpf_raw_tp_link_release, .dealloc_deferred = bpf_raw_tp_link_dealloc, .show_fdinfo = bpf_raw_tp_link_show_fdinfo, .fill_link_info = bpf_raw_tp_link_fill_link_info, }; #ifdef CONFIG_PERF_EVENTS struct bpf_perf_link { struct bpf_link link; struct file *perf_file; }; static void bpf_perf_link_release(struct bpf_link *link) { struct bpf_perf_link *perf_link = container_of(link, struct bpf_perf_link, link); struct perf_event *event = perf_link->perf_file->private_data; perf_event_free_bpf_prog(event); fput(perf_link->perf_file); } static void bpf_perf_link_dealloc(struct bpf_link *link) { struct bpf_perf_link *perf_link = container_of(link, struct bpf_perf_link, link); kfree(perf_link); } static int bpf_perf_link_fill_common(const struct perf_event *event, char __user *uname, u32 *ulenp, u64 *probe_offset, u64 *probe_addr, u32 *fd_type, unsigned long *missed) { const char *buf; u32 prog_id, ulen; size_t len; int err; ulen = *ulenp; if (!ulen ^ !uname) return -EINVAL; err = bpf_get_perf_event_info(event, &prog_id, fd_type, &buf, probe_offset, probe_addr, missed); if (err) return err; if (buf) { len = strlen(buf); *ulenp = len + 1; } else { *ulenp = 1; } if (!uname) return 0; if (buf) { err = bpf_copy_to_user(uname, buf, ulen, len); if (err) return err; } else { char zero = '\0'; if (put_user(zero, uname)) return -EFAULT; } return 0; } #ifdef CONFIG_KPROBE_EVENTS static int bpf_perf_link_fill_kprobe(const struct perf_event *event, struct bpf_link_info *info) { unsigned long missed; char __user *uname; u64 addr, offset; u32 ulen, type; int err; uname = u64_to_user_ptr(info->perf_event.kprobe.func_name); ulen = info->perf_event.kprobe.name_len; err = bpf_perf_link_fill_common(event, uname, &ulen, &offset, &addr, &type, &missed); if (err) return err; if (type == BPF_FD_TYPE_KRETPROBE) info->perf_event.type = BPF_PERF_EVENT_KRETPROBE; else info->perf_event.type = BPF_PERF_EVENT_KPROBE; info->perf_event.kprobe.name_len = ulen; info->perf_event.kprobe.offset = offset; info->perf_event.kprobe.missed = missed; if (!kallsyms_show_value(current_cred())) addr = 0; info->perf_event.kprobe.addr = addr; info->perf_event.kprobe.cookie = event->bpf_cookie; return 0; } #endif #ifdef CONFIG_UPROBE_EVENTS static int bpf_perf_link_fill_uprobe(const struct perf_event *event, struct bpf_link_info *info) { char __user *uname; u64 addr, offset; u32 ulen, type; int err; uname = u64_to_user_ptr(info->perf_event.uprobe.file_name); ulen = info->perf_event.uprobe.name_len; err = bpf_perf_link_fill_common(event, uname, &ulen, &offset, &addr, &type, NULL); if (err) return err; if (type == BPF_FD_TYPE_URETPROBE) info->perf_event.type = BPF_PERF_EVENT_URETPROBE; else info->perf_event.type = BPF_PERF_EVENT_UPROBE; info->perf_event.uprobe.name_len = ulen; info->perf_event.uprobe.offset = offset; info->perf_event.uprobe.cookie = event->bpf_cookie; return 0; } #endif static int bpf_perf_link_fill_probe(const struct perf_event *event, struct bpf_link_info *info) { #ifdef CONFIG_KPROBE_EVENTS if (event->tp_event->flags & TRACE_EVENT_FL_KPROBE) return bpf_perf_link_fill_kprobe(event, info); #endif #ifdef CONFIG_UPROBE_EVENTS if (event->tp_event->flags & TRACE_EVENT_FL_UPROBE) return bpf_perf_link_fill_uprobe(event, info); #endif return -EOPNOTSUPP; } static int bpf_perf_link_fill_tracepoint(const struct perf_event *event, struct bpf_link_info *info) { char __user *uname; u32 ulen; int err; uname = u64_to_user_ptr(info->perf_event.tracepoint.tp_name); ulen = info->perf_event.tracepoint.name_len; err = bpf_perf_link_fill_common(event, uname, &ulen, NULL, NULL, NULL, NULL); if (err) return err; info->perf_event.type = BPF_PERF_EVENT_TRACEPOINT; info->perf_event.tracepoint.name_len = ulen; info->perf_event.tracepoint.cookie = event->bpf_cookie; return 0; } static int bpf_perf_link_fill_perf_event(const struct perf_event *event, struct bpf_link_info *info) { info->perf_event.event.type = event->attr.type; info->perf_event.event.config = event->attr.config; info->perf_event.event.cookie = event->bpf_cookie; info->perf_event.type = BPF_PERF_EVENT_EVENT; return 0; } static int bpf_perf_link_fill_link_info(const struct bpf_link *link, struct bpf_link_info *info) { struct bpf_perf_link *perf_link; const struct perf_event *event; perf_link = container_of(link, struct bpf_perf_link, link); event = perf_get_event(perf_link->perf_file); if (IS_ERR(event)) return PTR_ERR(event); switch (event->prog->type) { case BPF_PROG_TYPE_PERF_EVENT: return bpf_perf_link_fill_perf_event(event, info); case BPF_PROG_TYPE_TRACEPOINT: return bpf_perf_link_fill_tracepoint(event, info); case BPF_PROG_TYPE_KPROBE: return bpf_perf_link_fill_probe(event, info); default: return -EOPNOTSUPP; } } static const struct bpf_link_ops bpf_perf_link_lops = { .release = bpf_perf_link_release, .dealloc = bpf_perf_link_dealloc, .fill_link_info = bpf_perf_link_fill_link_info, }; static int bpf_perf_link_attach(const union bpf_attr *attr, struct bpf_prog *prog) { struct bpf_link_primer link_primer; struct bpf_perf_link *link; struct perf_event *event; struct file *perf_file; int err; if (attr->link_create.flags) return -EINVAL; perf_file = perf_event_get(attr->link_create.target_fd); if (IS_ERR(perf_file)) return PTR_ERR(perf_file); link = kzalloc(sizeof(*link), GFP_USER); if (!link) { err = -ENOMEM; goto out_put_file; } bpf_link_init(&link->link, BPF_LINK_TYPE_PERF_EVENT, &bpf_perf_link_lops, prog); link->perf_file = perf_file; err = bpf_link_prime(&link->link, &link_primer); if (err) { kfree(link); goto out_put_file; } event = perf_file->private_data; err = perf_event_set_bpf_prog(event, prog, attr->link_create.perf_event.bpf_cookie); if (err) { bpf_link_cleanup(&link_primer); goto out_put_file; } /* perf_event_set_bpf_prog() doesn't take its own refcnt on prog */ bpf_prog_inc(prog); return bpf_link_settle(&link_primer); out_put_file: fput(perf_file); return err; } #else static int bpf_perf_link_attach(const union bpf_attr *attr, struct bpf_prog *prog) { return -EOPNOTSUPP; } #endif /* CONFIG_PERF_EVENTS */ static int bpf_raw_tp_link_attach(struct bpf_prog *prog, const char __user *user_tp_name, u64 cookie) { struct bpf_link_primer link_primer; struct bpf_raw_tp_link *link; struct bpf_raw_event_map *btp; const char *tp_name; char buf[128]; int err; switch (prog->type) { case BPF_PROG_TYPE_TRACING: case BPF_PROG_TYPE_EXT: case BPF_PROG_TYPE_LSM: if (user_tp_name) /* The attach point for this category of programs * should be specified via btf_id during program load. */ return -EINVAL; if (prog->type == BPF_PROG_TYPE_TRACING && prog->expected_attach_type == BPF_TRACE_RAW_TP) { tp_name = prog->aux->attach_func_name; break; } return bpf_tracing_prog_attach(prog, 0, 0, 0); case BPF_PROG_TYPE_RAW_TRACEPOINT: case BPF_PROG_TYPE_RAW_TRACEPOINT_WRITABLE: if (strncpy_from_user(buf, user_tp_name, sizeof(buf) - 1) < 0) return -EFAULT; buf[sizeof(buf) - 1] = 0; tp_name = buf; break; default: return -EINVAL; } btp = bpf_get_raw_tracepoint(tp_name); if (!btp) return -ENOENT; link = kzalloc(sizeof(*link), GFP_USER); if (!link) { err = -ENOMEM; goto out_put_btp; } bpf_link_init_sleepable(&link->link, BPF_LINK_TYPE_RAW_TRACEPOINT, &bpf_raw_tp_link_lops, prog, tracepoint_is_faultable(btp->tp)); link->btp = btp; link->cookie = cookie; err = bpf_link_prime(&link->link, &link_primer); if (err) { kfree(link); goto out_put_btp; } err = bpf_probe_register(link->btp, link); if (err) { bpf_link_cleanup(&link_primer); goto out_put_btp; } return bpf_link_settle(&link_primer); out_put_btp: bpf_put_raw_tracepoint(btp); return err; } #define BPF_RAW_TRACEPOINT_OPEN_LAST_FIELD raw_tracepoint.cookie static int bpf_raw_tracepoint_open(const union bpf_attr *attr) { struct bpf_prog *prog; void __user *tp_name; __u64 cookie; int fd; if (CHECK_ATTR(BPF_RAW_TRACEPOINT_OPEN)) return -EINVAL; prog = bpf_prog_get(attr->raw_tracepoint.prog_fd); if (IS_ERR(prog)) return PTR_ERR(prog); tp_name = u64_to_user_ptr(attr->raw_tracepoint.name); cookie = attr->raw_tracepoint.cookie; fd = bpf_raw_tp_link_attach(prog, tp_name, cookie); if (fd < 0) bpf_prog_put(prog); return fd; } static enum bpf_prog_type attach_type_to_prog_type(enum bpf_attach_type attach_type) { switch (attach_type) { case BPF_CGROUP_INET_INGRESS: case BPF_CGROUP_INET_EGRESS: return BPF_PROG_TYPE_CGROUP_SKB; case BPF_CGROUP_INET_SOCK_CREATE: case BPF_CGROUP_INET_SOCK_RELEASE: case BPF_CGROUP_INET4_POST_BIND: case BPF_CGROUP_INET6_POST_BIND: return BPF_PROG_TYPE_CGROUP_SOCK; case BPF_CGROUP_INET4_BIND: case BPF_CGROUP_INET6_BIND: case BPF_CGROUP_INET4_CONNECT: case BPF_CGROUP_INET6_CONNECT: case BPF_CGROUP_UNIX_CONNECT: case BPF_CGROUP_INET4_GETPEERNAME: case BPF_CGROUP_INET6_GETPEERNAME: case BPF_CGROUP_UNIX_GETPEERNAME: case BPF_CGROUP_INET4_GETSOCKNAME: case BPF_CGROUP_INET6_GETSOCKNAME: case BPF_CGROUP_UNIX_GETSOCKNAME: case BPF_CGROUP_UDP4_SENDMSG: case BPF_CGROUP_UDP6_SENDMSG: case BPF_CGROUP_UNIX_SENDMSG: case BPF_CGROUP_UDP4_RECVMSG: case BPF_CGROUP_UDP6_RECVMSG: case BPF_CGROUP_UNIX_RECVMSG: return BPF_PROG_TYPE_CGROUP_SOCK_ADDR; case BPF_CGROUP_SOCK_OPS: return BPF_PROG_TYPE_SOCK_OPS; case BPF_CGROUP_DEVICE: return BPF_PROG_TYPE_CGROUP_DEVICE; case BPF_SK_MSG_VERDICT: return BPF_PROG_TYPE_SK_MSG; case BPF_SK_SKB_STREAM_PARSER: case BPF_SK_SKB_STREAM_VERDICT: case BPF_SK_SKB_VERDICT: return BPF_PROG_TYPE_SK_SKB; case BPF_LIRC_MODE2: return BPF_PROG_TYPE_LIRC_MODE2; case BPF_FLOW_DISSECTOR: return BPF_PROG_TYPE_FLOW_DISSECTOR; case BPF_CGROUP_SYSCTL: return BPF_PROG_TYPE_CGROUP_SYSCTL; case BPF_CGROUP_GETSOCKOPT: case BPF_CGROUP_SETSOCKOPT: return BPF_PROG_TYPE_CGROUP_SOCKOPT; case BPF_TRACE_ITER: case BPF_TRACE_RAW_TP: case BPF_TRACE_FENTRY: case BPF_TRACE_FEXIT: case BPF_MODIFY_RETURN: return BPF_PROG_TYPE_TRACING; case BPF_LSM_MAC: return BPF_PROG_TYPE_LSM; case BPF_SK_LOOKUP: return BPF_PROG_TYPE_SK_LOOKUP; case BPF_XDP: return BPF_PROG_TYPE_XDP; case BPF_LSM_CGROUP: return BPF_PROG_TYPE_LSM; case BPF_TCX_INGRESS: case BPF_TCX_EGRESS: case BPF_NETKIT_PRIMARY: case BPF_NETKIT_PEER: return BPF_PROG_TYPE_SCHED_CLS; default: return BPF_PROG_TYPE_UNSPEC; } } static int bpf_prog_attach_check_attach_type(const struct bpf_prog *prog, enum bpf_attach_type attach_type) { enum bpf_prog_type ptype; switch (prog->type) { case BPF_PROG_TYPE_CGROUP_SOCK: case BPF_PROG_TYPE_CGROUP_SOCK_ADDR: case BPF_PROG_TYPE_CGROUP_SOCKOPT: case BPF_PROG_TYPE_SK_LOOKUP: return attach_type == prog->expected_attach_type ? 0 : -EINVAL; case BPF_PROG_TYPE_CGROUP_SKB: if (!bpf_token_capable(prog->aux->token, CAP_NET_ADMIN)) /* cg-skb progs can be loaded by unpriv user. * check permissions at attach time. */ return -EPERM; ptype = attach_type_to_prog_type(attach_type); if (prog->type != ptype) return -EINVAL; return prog->enforce_expected_attach_type && prog->expected_attach_type != attach_type ? -EINVAL : 0; case BPF_PROG_TYPE_EXT: return 0; case BPF_PROG_TYPE_NETFILTER: if (attach_type != BPF_NETFILTER) return -EINVAL; return 0; case BPF_PROG_TYPE_PERF_EVENT: case BPF_PROG_TYPE_TRACEPOINT: if (attach_type != BPF_PERF_EVENT) return -EINVAL; return 0; case BPF_PROG_TYPE_KPROBE: if (prog->expected_attach_type == BPF_TRACE_KPROBE_MULTI && attach_type != BPF_TRACE_KPROBE_MULTI) return -EINVAL; if (prog->expected_attach_type == BPF_TRACE_KPROBE_SESSION && attach_type != BPF_TRACE_KPROBE_SESSION) return -EINVAL; if (prog->expected_attach_type == BPF_TRACE_UPROBE_MULTI && attach_type != BPF_TRACE_UPROBE_MULTI) return -EINVAL; if (prog->expected_attach_type == BPF_TRACE_UPROBE_SESSION && attach_type != BPF_TRACE_UPROBE_SESSION) return -EINVAL; if (attach_type != BPF_PERF_EVENT && attach_type != BPF_TRACE_KPROBE_MULTI && attach_type != BPF_TRACE_KPROBE_SESSION && attach_type != BPF_TRACE_UPROBE_MULTI && attach_type != BPF_TRACE_UPROBE_SESSION) return -EINVAL; return 0; case BPF_PROG_TYPE_SCHED_CLS: if (attach_type != BPF_TCX_INGRESS && attach_type != BPF_TCX_EGRESS && attach_type != BPF_NETKIT_PRIMARY && attach_type != BPF_NETKIT_PEER) return -EINVAL; return 0; default: ptype = attach_type_to_prog_type(attach_type); if (ptype == BPF_PROG_TYPE_UNSPEC || ptype != prog->type) return -EINVAL; return 0; } } #define BPF_PROG_ATTACH_LAST_FIELD expected_revision #define BPF_F_ATTACH_MASK_BASE \ (BPF_F_ALLOW_OVERRIDE | \ BPF_F_ALLOW_MULTI | \ BPF_F_REPLACE) #define BPF_F_ATTACH_MASK_MPROG \ (BPF_F_REPLACE | \ BPF_F_BEFORE | \ BPF_F_AFTER | \ BPF_F_ID | \ BPF_F_LINK) static int bpf_prog_attach(const union bpf_attr *attr) { enum bpf_prog_type ptype; struct bpf_prog *prog; int ret; if (CHECK_ATTR(BPF_PROG_ATTACH)) return -EINVAL; ptype = attach_type_to_prog_type(attr->attach_type); if (ptype == BPF_PROG_TYPE_UNSPEC) return -EINVAL; if (bpf_mprog_supported(ptype)) { if (attr->attach_flags & ~BPF_F_ATTACH_MASK_MPROG) return -EINVAL; } else { if (attr->attach_flags & ~BPF_F_ATTACH_MASK_BASE) return -EINVAL; if (attr->relative_fd || attr->expected_revision) return -EINVAL; } prog = bpf_prog_get_type(attr->attach_bpf_fd, ptype); if (IS_ERR(prog)) return PTR_ERR(prog); if (bpf_prog_attach_check_attach_type(prog, attr->attach_type)) { bpf_prog_put(prog); return -EINVAL; } switch (ptype) { case BPF_PROG_TYPE_SK_SKB: case BPF_PROG_TYPE_SK_MSG: ret = sock_map_get_from_fd(attr, prog); break; case BPF_PROG_TYPE_LIRC_MODE2: ret = lirc_prog_attach(attr, prog); break; case BPF_PROG_TYPE_FLOW_DISSECTOR: ret = netns_bpf_prog_attach(attr, prog); break; case BPF_PROG_TYPE_CGROUP_DEVICE: case BPF_PROG_TYPE_CGROUP_SKB: case BPF_PROG_TYPE_CGROUP_SOCK: case BPF_PROG_TYPE_CGROUP_SOCK_ADDR: case BPF_PROG_TYPE_CGROUP_SOCKOPT: case BPF_PROG_TYPE_CGROUP_SYSCTL: case BPF_PROG_TYPE_SOCK_OPS: case BPF_PROG_TYPE_LSM: if (ptype == BPF_PROG_TYPE_LSM && prog->expected_attach_type != BPF_LSM_CGROUP) ret = -EINVAL; else ret = cgroup_bpf_prog_attach(attr, ptype, prog); break; case BPF_PROG_TYPE_SCHED_CLS: if (attr->attach_type == BPF_TCX_INGRESS || attr->attach_type == BPF_TCX_EGRESS) ret = tcx_prog_attach(attr, prog); else ret = netkit_prog_attach(attr, prog); break; default: ret = -EINVAL; } if (ret) bpf_prog_put(prog); return ret; } #define BPF_PROG_DETACH_LAST_FIELD expected_revision static int bpf_prog_detach(const union bpf_attr *attr) { struct bpf_prog *prog = NULL; enum bpf_prog_type ptype; int ret; if (CHECK_ATTR(BPF_PROG_DETACH)) return -EINVAL; ptype = attach_type_to_prog_type(attr->attach_type); if (bpf_mprog_supported(ptype)) { if (ptype == BPF_PROG_TYPE_UNSPEC) return -EINVAL; if (attr->attach_flags & ~BPF_F_ATTACH_MASK_MPROG) return -EINVAL; if (attr->attach_bpf_fd) { prog = bpf_prog_get_type(attr->attach_bpf_fd, ptype); if (IS_ERR(prog)) return PTR_ERR(prog); } } else if (attr->attach_flags || attr->relative_fd || attr->expected_revision) { return -EINVAL; } switch (ptype) { case BPF_PROG_TYPE_SK_MSG: case BPF_PROG_TYPE_SK_SKB: ret = sock_map_prog_detach(attr, ptype); break; case BPF_PROG_TYPE_LIRC_MODE2: ret = lirc_prog_detach(attr); break; case BPF_PROG_TYPE_FLOW_DISSECTOR: ret = netns_bpf_prog_detach(attr, ptype); break; case BPF_PROG_TYPE_CGROUP_DEVICE: case BPF_PROG_TYPE_CGROUP_SKB: case BPF_PROG_TYPE_CGROUP_SOCK: case BPF_PROG_TYPE_CGROUP_SOCK_ADDR: case BPF_PROG_TYPE_CGROUP_SOCKOPT: case BPF_PROG_TYPE_CGROUP_SYSCTL: case BPF_PROG_TYPE_SOCK_OPS: case BPF_PROG_TYPE_LSM: ret = cgroup_bpf_prog_detach(attr, ptype); break; case BPF_PROG_TYPE_SCHED_CLS: if (attr->attach_type == BPF_TCX_INGRESS || attr->attach_type == BPF_TCX_EGRESS) ret = tcx_prog_detach(attr, prog); else ret = netkit_prog_detach(attr, prog); break; default: ret = -EINVAL; } if (prog) bpf_prog_put(prog); return ret; } #define BPF_PROG_QUERY_LAST_FIELD query.revision static int bpf_prog_query(const union bpf_attr *attr, union bpf_attr __user *uattr) { if (!bpf_net_capable()) return -EPERM; if (CHECK_ATTR(BPF_PROG_QUERY)) return -EINVAL; if (attr->query.query_flags & ~BPF_F_QUERY_EFFECTIVE) return -EINVAL; switch (attr->query.attach_type) { case BPF_CGROUP_INET_INGRESS: case BPF_CGROUP_INET_EGRESS: case BPF_CGROUP_INET_SOCK_CREATE: case BPF_CGROUP_INET_SOCK_RELEASE: case BPF_CGROUP_INET4_BIND: case BPF_CGROUP_INET6_BIND: case BPF_CGROUP_INET4_POST_BIND: case BPF_CGROUP_INET6_POST_BIND: case BPF_CGROUP_INET4_CONNECT: case BPF_CGROUP_INET6_CONNECT: case BPF_CGROUP_UNIX_CONNECT: case BPF_CGROUP_INET4_GETPEERNAME: case BPF_CGROUP_INET6_GETPEERNAME: case BPF_CGROUP_UNIX_GETPEERNAME: case BPF_CGROUP_INET4_GETSOCKNAME: case BPF_CGROUP_INET6_GETSOCKNAME: case BPF_CGROUP_UNIX_GETSOCKNAME: case BPF_CGROUP_UDP4_SENDMSG: case BPF_CGROUP_UDP6_SENDMSG: case BPF_CGROUP_UNIX_SENDMSG: case BPF_CGROUP_UDP4_RECVMSG: case BPF_CGROUP_UDP6_RECVMSG: case BPF_CGROUP_UNIX_RECVMSG: case BPF_CGROUP_SOCK_OPS: case BPF_CGROUP_DEVICE: case BPF_CGROUP_SYSCTL: case BPF_CGROUP_GETSOCKOPT: case BPF_CGROUP_SETSOCKOPT: case BPF_LSM_CGROUP: return cgroup_bpf_prog_query(attr, uattr); case BPF_LIRC_MODE2: return lirc_prog_query(attr, uattr); case BPF_FLOW_DISSECTOR: case BPF_SK_LOOKUP: return netns_bpf_prog_query(attr, uattr); case BPF_SK_SKB_STREAM_PARSER: case BPF_SK_SKB_STREAM_VERDICT: case BPF_SK_MSG_VERDICT: case BPF_SK_SKB_VERDICT: return sock_map_bpf_prog_query(attr, uattr); case BPF_TCX_INGRESS: case BPF_TCX_EGRESS: return tcx_prog_query(attr, uattr); case BPF_NETKIT_PRIMARY: case BPF_NETKIT_PEER: return netkit_prog_query(attr, uattr); default: return -EINVAL; } } #define BPF_PROG_TEST_RUN_LAST_FIELD test.batch_size static int bpf_prog_test_run(const union bpf_attr *attr, union bpf_attr __user *uattr) { struct bpf_prog *prog; int ret = -ENOTSUPP; if (CHECK_ATTR(BPF_PROG_TEST_RUN)) return -EINVAL; if ((attr->test.ctx_size_in && !attr->test.ctx_in) || (!attr->test.ctx_size_in && attr->test.ctx_in)) return -EINVAL; if ((attr->test.ctx_size_out && !attr->test.ctx_out) || (!attr->test.ctx_size_out && attr->test.ctx_out)) return -EINVAL; prog = bpf_prog_get(attr->test.prog_fd); if (IS_ERR(prog)) return PTR_ERR(prog); if (prog->aux->ops->test_run) ret = prog->aux->ops->test_run(prog, attr, uattr); bpf_prog_put(prog); return ret; } #define BPF_OBJ_GET_NEXT_ID_LAST_FIELD next_id static int bpf_obj_get_next_id(const union bpf_attr *attr, union bpf_attr __user *uattr, struct idr *idr, spinlock_t *lock) { u32 next_id = attr->start_id; int err = 0; if (CHECK_ATTR(BPF_OBJ_GET_NEXT_ID) || next_id >= INT_MAX) return -EINVAL; if (!capable(CAP_SYS_ADMIN)) return -EPERM; next_id++; spin_lock_bh(lock); if (!idr_get_next(idr, &next_id)) err = -ENOENT; spin_unlock_bh(lock); if (!err) err = put_user(next_id, &uattr->next_id); return err; } struct bpf_map *bpf_map_get_curr_or_next(u32 *id) { struct bpf_map *map; spin_lock_bh(&map_idr_lock); again: map = idr_get_next(&map_idr, id); if (map) { map = __bpf_map_inc_not_zero(map, false); if (IS_ERR(map)) { (*id)++; goto again; } } spin_unlock_bh(&map_idr_lock); return map; } struct bpf_prog *bpf_prog_get_curr_or_next(u32 *id) { struct bpf_prog *prog; spin_lock_bh(&prog_idr_lock); again: prog = idr_get_next(&prog_idr, id); if (prog) { prog = bpf_prog_inc_not_zero(prog); if (IS_ERR(prog)) { (*id)++; goto again; } } spin_unlock_bh(&prog_idr_lock); return prog; } #define BPF_PROG_GET_FD_BY_ID_LAST_FIELD prog_id struct bpf_prog *bpf_prog_by_id(u32 id) { struct bpf_prog *prog; if (!id) return ERR_PTR(-ENOENT); spin_lock_bh(&prog_idr_lock); prog = idr_find(&prog_idr, id); if (prog) prog = bpf_prog_inc_not_zero(prog); else prog = ERR_PTR(-ENOENT); spin_unlock_bh(&prog_idr_lock); return prog; } static int bpf_prog_get_fd_by_id(const union bpf_attr *attr) { struct bpf_prog *prog; u32 id = attr->prog_id; int fd; if (CHECK_ATTR(BPF_PROG_GET_FD_BY_ID)) return -EINVAL; if (!capable(CAP_SYS_ADMIN)) return -EPERM; prog = bpf_prog_by_id(id); if (IS_ERR(prog)) return PTR_ERR(prog); fd = bpf_prog_new_fd(prog); if (fd < 0) bpf_prog_put(prog); return fd; } #define BPF_MAP_GET_FD_BY_ID_LAST_FIELD open_flags static int bpf_map_get_fd_by_id(const union bpf_attr *attr) { struct bpf_map *map; u32 id = attr->map_id; int f_flags; int fd; if (CHECK_ATTR(BPF_MAP_GET_FD_BY_ID) || attr->open_flags & ~BPF_OBJ_FLAG_MASK) return -EINVAL; if (!capable(CAP_SYS_ADMIN)) return -EPERM; f_flags = bpf_get_file_flag(attr->open_flags); if (f_flags < 0) return f_flags; spin_lock_bh(&map_idr_lock); map = idr_find(&map_idr, id); if (map) map = __bpf_map_inc_not_zero(map, true); else map = ERR_PTR(-ENOENT); spin_unlock_bh(&map_idr_lock); if (IS_ERR(map)) return PTR_ERR(map); fd = bpf_map_new_fd(map, f_flags); if (fd < 0) bpf_map_put_with_uref(map); return fd; } static const struct bpf_map *bpf_map_from_imm(const struct bpf_prog *prog, unsigned long addr, u32 *off, u32 *type) { const struct bpf_map *map; int i; mutex_lock(&prog->aux->used_maps_mutex); for (i = 0, *off = 0; i < prog->aux->used_map_cnt; i++) { map = prog->aux->used_maps[i]; if (map == (void *)addr) { *type = BPF_PSEUDO_MAP_FD; goto out; } if (!map->ops->map_direct_value_meta) continue; if (!map->ops->map_direct_value_meta(map, addr, off)) { *type = BPF_PSEUDO_MAP_VALUE; goto out; } } map = NULL; out: mutex_unlock(&prog->aux->used_maps_mutex); return map; } static struct bpf_insn *bpf_insn_prepare_dump(const struct bpf_prog *prog, const struct cred *f_cred) { const struct bpf_map *map; struct bpf_insn *insns; u32 off, type; u64 imm; u8 code; int i; insns = kmemdup(prog->insnsi, bpf_prog_insn_size(prog), GFP_USER); if (!insns) return insns; for (i = 0; i < prog->len; i++) { code = insns[i].code; if (code == (BPF_JMP | BPF_TAIL_CALL)) { insns[i].code = BPF_JMP | BPF_CALL; insns[i].imm = BPF_FUNC_tail_call; /* fall-through */ } if (code == (BPF_JMP | BPF_CALL) || code == (BPF_JMP | BPF_CALL_ARGS)) { if (code == (BPF_JMP | BPF_CALL_ARGS)) insns[i].code = BPF_JMP | BPF_CALL; if (!bpf_dump_raw_ok(f_cred)) insns[i].imm = 0; continue; } if (BPF_CLASS(code) == BPF_LDX && BPF_MODE(code) == BPF_PROBE_MEM) { insns[i].code = BPF_LDX | BPF_SIZE(code) | BPF_MEM; continue; } if ((BPF_CLASS(code) == BPF_LDX || BPF_CLASS(code) == BPF_STX || BPF_CLASS(code) == BPF_ST) && BPF_MODE(code) == BPF_PROBE_MEM32) { insns[i].code = BPF_CLASS(code) | BPF_SIZE(code) | BPF_MEM; continue; } if (code != (BPF_LD | BPF_IMM | BPF_DW)) continue; imm = ((u64)insns[i + 1].imm << 32) | (u32)insns[i].imm; map = bpf_map_from_imm(prog, imm, &off, &type); if (map) { insns[i].src_reg = type; insns[i].imm = map->id; insns[i + 1].imm = off; continue; } } return insns; } static int set_info_rec_size(struct bpf_prog_info *info) { /* * Ensure info.*_rec_size is the same as kernel expected size * * or * * Only allow zero *_rec_size if both _rec_size and _cnt are * zero. In this case, the kernel will set the expected * _rec_size back to the info. */ if ((info->nr_func_info || info->func_info_rec_size) && info->func_info_rec_size != sizeof(struct bpf_func_info)) return -EINVAL; if ((info->nr_line_info || info->line_info_rec_size) && info->line_info_rec_size != sizeof(struct bpf_line_info)) return -EINVAL; if ((info->nr_jited_line_info || info->jited_line_info_rec_size) && info->jited_line_info_rec_size != sizeof(__u64)) return -EINVAL; info->func_info_rec_size = sizeof(struct bpf_func_info); info->line_info_rec_size = sizeof(struct bpf_line_info); info->jited_line_info_rec_size = sizeof(__u64); return 0; } static int bpf_prog_get_info_by_fd(struct file *file, struct bpf_prog *prog, const union bpf_attr *attr, union bpf_attr __user *uattr) { struct bpf_prog_info __user *uinfo = u64_to_user_ptr(attr->info.info); struct btf *attach_btf = bpf_prog_get_target_btf(prog); struct bpf_prog_info info; u32 info_len = attr->info.info_len; struct bpf_prog_kstats stats; char __user *uinsns; u32 ulen; int err; err = bpf_check_uarg_tail_zero(USER_BPFPTR(uinfo), sizeof(info), info_len); if (err) return err; info_len = min_t(u32, sizeof(info), info_len); memset(&info, 0, sizeof(info)); if (copy_from_user(&info, uinfo, info_len)) return -EFAULT; info.type = prog->type; info.id = prog->aux->id; info.load_time = prog->aux->load_time; info.created_by_uid = from_kuid_munged(current_user_ns(), prog->aux->user->uid); info.gpl_compatible = prog->gpl_compatible; memcpy(info.tag, prog->tag, sizeof(prog->tag)); memcpy(info.name, prog->aux->name, sizeof(prog->aux->name)); mutex_lock(&prog->aux->used_maps_mutex); ulen = info.nr_map_ids; info.nr_map_ids = prog->aux->used_map_cnt; ulen = min_t(u32, info.nr_map_ids, ulen); if (ulen) { u32 __user *user_map_ids = u64_to_user_ptr(info.map_ids); u32 i; for (i = 0; i < ulen; i++) if (put_user(prog->aux->used_maps[i]->id, &user_map_ids[i])) { mutex_unlock(&prog->aux->used_maps_mutex); return -EFAULT; } } mutex_unlock(&prog->aux->used_maps_mutex); err = set_info_rec_size(&info); if (err) return err; bpf_prog_get_stats(prog, &stats); info.run_time_ns = stats.nsecs; info.run_cnt = stats.cnt; info.recursion_misses = stats.misses; info.verified_insns = prog->aux->verified_insns; if (!bpf_capable()) { info.jited_prog_len = 0; info.xlated_prog_len = 0; info.nr_jited_ksyms = 0; info.nr_jited_func_lens = 0; info.nr_func_info = 0; info.nr_line_info = 0; info.nr_jited_line_info = 0; goto done; } ulen = info.xlated_prog_len; info.xlated_prog_len = bpf_prog_insn_size(prog); if (info.xlated_prog_len && ulen) { struct bpf_insn *insns_sanitized; bool fault; if (prog->blinded && !bpf_dump_raw_ok(file->f_cred)) { info.xlated_prog_insns = 0; goto done; } insns_sanitized = bpf_insn_prepare_dump(prog, file->f_cred); if (!insns_sanitized) return -ENOMEM; uinsns = u64_to_user_ptr(info.xlated_prog_insns); ulen = min_t(u32, info.xlated_prog_len, ulen); fault = copy_to_user(uinsns, insns_sanitized, ulen); kfree(insns_sanitized); if (fault) return -EFAULT; } if (bpf_prog_is_offloaded(prog->aux)) { err = bpf_prog_offload_info_fill(&info, prog); if (err) return err; goto done; } /* NOTE: the following code is supposed to be skipped for offload. * bpf_prog_offload_info_fill() is the place to fill similar fields * for offload. */ ulen = info.jited_prog_len; if (prog->aux->func_cnt) { u32 i; info.jited_prog_len = 0; for (i = 0; i < prog->aux->func_cnt; i++) info.jited_prog_len += prog->aux->func[i]->jited_len; } else { info.jited_prog_len = prog->jited_len; } if (info.jited_prog_len && ulen) { if (bpf_dump_raw_ok(file->f_cred)) { uinsns = u64_to_user_ptr(info.jited_prog_insns); ulen = min_t(u32, info.jited_prog_len, ulen); /* for multi-function programs, copy the JITed * instructions for all the functions */ if (prog->aux->func_cnt) { u32 len, free, i; u8 *img; free = ulen; for (i = 0; i < prog->aux->func_cnt; i++) { len = prog->aux->func[i]->jited_len; len = min_t(u32, len, free); img = (u8 *) prog->aux->func[i]->bpf_func; if (copy_to_user(uinsns, img, len)) return -EFAULT; uinsns += len; free -= len; if (!free) break; } } else { if (copy_to_user(uinsns, prog->bpf_func, ulen)) return -EFAULT; } } else { info.jited_prog_insns = 0; } } ulen = info.nr_jited_ksyms; info.nr_jited_ksyms = prog->aux->func_cnt ? : 1; if (ulen) { if (bpf_dump_raw_ok(file->f_cred)) { unsigned long ksym_addr; u64 __user *user_ksyms; u32 i; /* copy the address of the kernel symbol * corresponding to each function */ ulen = min_t(u32, info.nr_jited_ksyms, ulen); user_ksyms = u64_to_user_ptr(info.jited_ksyms); if (prog->aux->func_cnt) { for (i = 0; i < ulen; i++) { ksym_addr = (unsigned long) prog->aux->func[i]->bpf_func; if (put_user((u64) ksym_addr, &user_ksyms[i])) return -EFAULT; } } else { ksym_addr = (unsigned long) prog->bpf_func; if (put_user((u64) ksym_addr, &user_ksyms[0])) return -EFAULT; } } else { info.jited_ksyms = 0; } } ulen = info.nr_jited_func_lens; info.nr_jited_func_lens = prog->aux->func_cnt ? : 1; if (ulen) { if (bpf_dump_raw_ok(file->f_cred)) { u32 __user *user_lens; u32 func_len, i; /* copy the JITed image lengths for each function */ ulen = min_t(u32, info.nr_jited_func_lens, ulen); user_lens = u64_to_user_ptr(info.jited_func_lens); if (prog->aux->func_cnt) { for (i = 0; i < ulen; i++) { func_len = prog->aux->func[i]->jited_len; if (put_user(func_len, &user_lens[i])) return -EFAULT; } } else { func_len = prog->jited_len; if (put_user(func_len, &user_lens[0])) return -EFAULT; } } else { info.jited_func_lens = 0; } } if (prog->aux->btf) info.btf_id = btf_obj_id(prog->aux->btf); info.attach_btf_id = prog->aux->attach_btf_id; if (attach_btf) info.attach_btf_obj_id = btf_obj_id(attach_btf); ulen = info.nr_func_info; info.nr_func_info = prog->aux->func_info_cnt; if (info.nr_func_info && ulen) { char __user *user_finfo; user_finfo = u64_to_user_ptr(info.func_info); ulen = min_t(u32, info.nr_func_info, ulen); if (copy_to_user(user_finfo, prog->aux->func_info, info.func_info_rec_size * ulen)) return -EFAULT; } ulen = info.nr_line_info; info.nr_line_info = prog->aux->nr_linfo; if (info.nr_line_info && ulen) { __u8 __user *user_linfo; user_linfo = u64_to_user_ptr(info.line_info); ulen = min_t(u32, info.nr_line_info, ulen); if (copy_to_user(user_linfo, prog->aux->linfo, info.line_info_rec_size * ulen)) return -EFAULT; } ulen = info.nr_jited_line_info; if (prog->aux->jited_linfo) info.nr_jited_line_info = prog->aux->nr_linfo; else info.nr_jited_line_info = 0; if (info.nr_jited_line_info && ulen) { if (bpf_dump_raw_ok(file->f_cred)) { unsigned long line_addr; __u64 __user *user_linfo; u32 i; user_linfo = u64_to_user_ptr(info.jited_line_info); ulen = min_t(u32, info.nr_jited_line_info, ulen); for (i = 0; i < ulen; i++) { line_addr = (unsigned long)prog->aux->jited_linfo[i]; if (put_user((__u64)line_addr, &user_linfo[i])) return -EFAULT; } } else { info.jited_line_info = 0; } } ulen = info.nr_prog_tags; info.nr_prog_tags = prog->aux->func_cnt ? : 1; if (ulen) { __u8 __user (*user_prog_tags)[BPF_TAG_SIZE]; u32 i; user_prog_tags = u64_to_user_ptr(info.prog_tags); ulen = min_t(u32, info.nr_prog_tags, ulen); if (prog->aux->func_cnt) { for (i = 0; i < ulen; i++) { if (copy_to_user(user_prog_tags[i], prog->aux->func[i]->tag, BPF_TAG_SIZE)) return -EFAULT; } } else { if (copy_to_user(user_prog_tags[0], prog->tag, BPF_TAG_SIZE)) return -EFAULT; } } done: if (copy_to_user(uinfo, &info, info_len) || put_user(info_len, &uattr->info.info_len)) return -EFAULT; return 0; } static int bpf_map_get_info_by_fd(struct file *file, struct bpf_map *map, const union bpf_attr *attr, union bpf_attr __user *uattr) { struct bpf_map_info __user *uinfo = u64_to_user_ptr(attr->info.info); struct bpf_map_info info; u32 info_len = attr->info.info_len; int err; err = bpf_check_uarg_tail_zero(USER_BPFPTR(uinfo), sizeof(info), info_len); if (err) return err; info_len = min_t(u32, sizeof(info), info_len); memset(&info, 0, sizeof(info)); info.type = map->map_type; info.id = map->id; info.key_size = map->key_size; info.value_size = map->value_size; info.max_entries = map->max_entries; info.map_flags = map->map_flags; info.map_extra = map->map_extra; memcpy(info.name, map->name, sizeof(map->name)); if (map->btf) { info.btf_id = btf_obj_id(map->btf); info.btf_key_type_id = map->btf_key_type_id; info.btf_value_type_id = map->btf_value_type_id; } info.btf_vmlinux_value_type_id = map->btf_vmlinux_value_type_id; if (map->map_type == BPF_MAP_TYPE_STRUCT_OPS) bpf_map_struct_ops_info_fill(&info, map); if (bpf_map_is_offloaded(map)) { err = bpf_map_offload_info_fill(&info, map); if (err) return err; } if (copy_to_user(uinfo, &info, info_len) || put_user(info_len, &uattr->info.info_len)) return -EFAULT; return 0; } static int bpf_btf_get_info_by_fd(struct file *file, struct btf *btf, const union bpf_attr *attr, union bpf_attr __user *uattr) { struct bpf_btf_info __user *uinfo = u64_to_user_ptr(attr->info.info); u32 info_len = attr->info.info_len; int err; err = bpf_check_uarg_tail_zero(USER_BPFPTR(uinfo), sizeof(*uinfo), info_len); if (err) return err; return btf_get_info_by_fd(btf, attr, uattr); } static int bpf_link_get_info_by_fd(struct file *file, struct bpf_link *link, const union bpf_attr *attr, union bpf_attr __user *uattr) { struct bpf_link_info __user *uinfo = u64_to_user_ptr(attr->info.info); struct bpf_link_info info; u32 info_len = attr->info.info_len; int err; err = bpf_check_uarg_tail_zero(USER_BPFPTR(uinfo), sizeof(info), info_len); if (err) return err; info_len = min_t(u32, sizeof(info), info_len); memset(&info, 0, sizeof(info)); if (copy_from_user(&info, uinfo, info_len)) return -EFAULT; info.type = link->type; info.id = link->id; if (link->prog) info.prog_id = link->prog->aux->id; if (link->ops->fill_link_info) { err = link->ops->fill_link_info(link, &info); if (err) return err; } if (copy_to_user(uinfo, &info, info_len) || put_user(info_len, &uattr->info.info_len)) return -EFAULT; return 0; } #define BPF_OBJ_GET_INFO_BY_FD_LAST_FIELD info.info static int bpf_obj_get_info_by_fd(const union bpf_attr *attr, union bpf_attr __user *uattr) { if (CHECK_ATTR(BPF_OBJ_GET_INFO_BY_FD)) return -EINVAL; CLASS(fd, f)(attr->info.bpf_fd); if (fd_empty(f)) return -EBADFD; if (fd_file(f)->f_op == &bpf_prog_fops) return bpf_prog_get_info_by_fd(fd_file(f), fd_file(f)->private_data, attr, uattr); else if (fd_file(f)->f_op == &bpf_map_fops) return bpf_map_get_info_by_fd(fd_file(f), fd_file(f)->private_data, attr, uattr); else if (fd_file(f)->f_op == &btf_fops) return bpf_btf_get_info_by_fd(fd_file(f), fd_file(f)->private_data, attr, uattr); else if (fd_file(f)->f_op == &bpf_link_fops || fd_file(f)->f_op == &bpf_link_fops_poll) return bpf_link_get_info_by_fd(fd_file(f), fd_file(f)->private_data, attr, uattr); return -EINVAL; } #define BPF_BTF_LOAD_LAST_FIELD btf_token_fd static int bpf_btf_load(const union bpf_attr *attr, bpfptr_t uattr, __u32 uattr_size) { struct bpf_token *token = NULL; if (CHECK_ATTR(BPF_BTF_LOAD)) return -EINVAL; if (attr->btf_flags & ~BPF_F_TOKEN_FD) return -EINVAL; if (attr->btf_flags & BPF_F_TOKEN_FD) { token = bpf_token_get_from_fd(attr->btf_token_fd); if (IS_ERR(token)) return PTR_ERR(token); if (!bpf_token_allow_cmd(token, BPF_BTF_LOAD)) { bpf_token_put(token); token = NULL; } } if (!bpf_token_capable(token, CAP_BPF)) { bpf_token_put(token); return -EPERM; } bpf_token_put(token); return btf_new_fd(attr, uattr, uattr_size); } #define BPF_BTF_GET_FD_BY_ID_LAST_FIELD btf_id static int bpf_btf_get_fd_by_id(const union bpf_attr *attr) { if (CHECK_ATTR(BPF_BTF_GET_FD_BY_ID)) return -EINVAL; if (!capable(CAP_SYS_ADMIN)) return -EPERM; return btf_get_fd_by_id(attr->btf_id); } static int bpf_task_fd_query_copy(const union bpf_attr *attr, union bpf_attr __user *uattr, u32 prog_id, u32 fd_type, const char *buf, u64 probe_offset, u64 probe_addr) { char __user *ubuf = u64_to_user_ptr(attr->task_fd_query.buf); u32 len = buf ? strlen(buf) : 0, input_len; int err = 0; if (put_user(len, &uattr->task_fd_query.buf_len)) return -EFAULT; input_len = attr->task_fd_query.buf_len; if (input_len && ubuf) { if (!len) { /* nothing to copy, just make ubuf NULL terminated */ char zero = '\0'; if (put_user(zero, ubuf)) return -EFAULT; } else if (input_len >= len + 1) { /* ubuf can hold the string with NULL terminator */ if (copy_to_user(ubuf, buf, len + 1)) return -EFAULT; } else { /* ubuf cannot hold the string with NULL terminator, * do a partial copy with NULL terminator. */ char zero = '\0'; err = -ENOSPC; if (copy_to_user(ubuf, buf, input_len - 1)) return -EFAULT; if (put_user(zero, ubuf + input_len - 1)) return -EFAULT; } } if (put_user(prog_id, &uattr->task_fd_query.prog_id) || put_user(fd_type, &uattr->task_fd_query.fd_type) || put_user(probe_offset, &uattr->task_fd_query.probe_offset) || put_user(probe_addr, &uattr->task_fd_query.probe_addr)) return -EFAULT; return err; } #define BPF_TASK_FD_QUERY_LAST_FIELD task_fd_query.probe_addr static int bpf_task_fd_query(const union bpf_attr *attr, union bpf_attr __user *uattr) { pid_t pid = attr->task_fd_query.pid; u32 fd = attr->task_fd_query.fd; const struct perf_event *event; struct task_struct *task; struct file *file; int err; if (CHECK_ATTR(BPF_TASK_FD_QUERY)) return -EINVAL; if (!capable(CAP_SYS_ADMIN)) return -EPERM; if (attr->task_fd_query.flags != 0) return -EINVAL; rcu_read_lock(); task = get_pid_task(find_vpid(pid), PIDTYPE_PID); rcu_read_unlock(); if (!task) return -ENOENT; err = 0; file = fget_task(task, fd); put_task_struct(task); if (!file) return -EBADF; if (file->f_op == &bpf_link_fops || file->f_op == &bpf_link_fops_poll) { struct bpf_link *link = file->private_data; if (link->ops == &bpf_raw_tp_link_lops) { struct bpf_raw_tp_link *raw_tp = container_of(link, struct bpf_raw_tp_link, link); struct bpf_raw_event_map *btp = raw_tp->btp; err = bpf_task_fd_query_copy(attr, uattr, raw_tp->link.prog->aux->id, BPF_FD_TYPE_RAW_TRACEPOINT, btp->tp->name, 0, 0); goto put_file; } goto out_not_supp; } event = perf_get_event(file); if (!IS_ERR(event)) { u64 probe_offset, probe_addr; u32 prog_id, fd_type; const char *buf; err = bpf_get_perf_event_info(event, &prog_id, &fd_type, &buf, &probe_offset, &probe_addr, NULL); if (!err) err = bpf_task_fd_query_copy(attr, uattr, prog_id, fd_type, buf, probe_offset, probe_addr); goto put_file; } out_not_supp: err = -ENOTSUPP; put_file: fput(file); return err; } #define BPF_MAP_BATCH_LAST_FIELD batch.flags #define BPF_DO_BATCH(fn, ...) \ do { \ if (!fn) { \ err = -ENOTSUPP; \ goto err_put; \ } \ err = fn(__VA_ARGS__); \ } while (0) static int bpf_map_do_batch(const union bpf_attr *attr, union bpf_attr __user *uattr, int cmd) { bool has_read = cmd == BPF_MAP_LOOKUP_BATCH || cmd == BPF_MAP_LOOKUP_AND_DELETE_BATCH; bool has_write = cmd != BPF_MAP_LOOKUP_BATCH; struct bpf_map *map; int err; if (CHECK_ATTR(BPF_MAP_BATCH)) return -EINVAL; CLASS(fd, f)(attr->batch.map_fd); map = __bpf_map_get(f); if (IS_ERR(map)) return PTR_ERR(map); if (has_write) bpf_map_write_active_inc(map); if (has_read && !(map_get_sys_perms(map, f) & FMODE_CAN_READ)) { err = -EPERM; goto err_put; } if (has_write && !(map_get_sys_perms(map, f) & FMODE_CAN_WRITE)) { err = -EPERM; goto err_put; } if (cmd == BPF_MAP_LOOKUP_BATCH) BPF_DO_BATCH(map->ops->map_lookup_batch, map, attr, uattr); else if (cmd == BPF_MAP_LOOKUP_AND_DELETE_BATCH) BPF_DO_BATCH(map->ops->map_lookup_and_delete_batch, map, attr, uattr); else if (cmd == BPF_MAP_UPDATE_BATCH) BPF_DO_BATCH(map->ops->map_update_batch, map, fd_file(f), attr, uattr); else BPF_DO_BATCH(map->ops->map_delete_batch, map, attr, uattr); err_put: if (has_write) { maybe_wait_bpf_programs(map); bpf_map_write_active_dec(map); } return err; } #define BPF_LINK_CREATE_LAST_FIELD link_create.uprobe_multi.pid static int link_create(union bpf_attr *attr, bpfptr_t uattr) { struct bpf_prog *prog; int ret; if (CHECK_ATTR(BPF_LINK_CREATE)) return -EINVAL; if (attr->link_create.attach_type == BPF_STRUCT_OPS) return bpf_struct_ops_link_create(attr); prog = bpf_prog_get(attr->link_create.prog_fd); if (IS_ERR(prog)) return PTR_ERR(prog); ret = bpf_prog_attach_check_attach_type(prog, attr->link_create.attach_type); if (ret) goto out; switch (prog->type) { case BPF_PROG_TYPE_CGROUP_SKB: case BPF_PROG_TYPE_CGROUP_SOCK: case BPF_PROG_TYPE_CGROUP_SOCK_ADDR: case BPF_PROG_TYPE_SOCK_OPS: case BPF_PROG_TYPE_CGROUP_DEVICE: case BPF_PROG_TYPE_CGROUP_SYSCTL: case BPF_PROG_TYPE_CGROUP_SOCKOPT: ret = cgroup_bpf_link_attach(attr, prog); break; case BPF_PROG_TYPE_EXT: ret = bpf_tracing_prog_attach(prog, attr->link_create.target_fd, attr->link_create.target_btf_id, attr->link_create.tracing.cookie); break; case BPF_PROG_TYPE_LSM: case BPF_PROG_TYPE_TRACING: if (attr->link_create.attach_type != prog->expected_attach_type) { ret = -EINVAL; goto out; } if (prog->expected_attach_type == BPF_TRACE_RAW_TP) ret = bpf_raw_tp_link_attach(prog, NULL, attr->link_create.tracing.cookie); else if (prog->expected_attach_type == BPF_TRACE_ITER) ret = bpf_iter_link_attach(attr, uattr, prog); else if (prog->expected_attach_type == BPF_LSM_CGROUP) ret = cgroup_bpf_link_attach(attr, prog); else ret = bpf_tracing_prog_attach(prog, attr->link_create.target_fd, attr->link_create.target_btf_id, attr->link_create.tracing.cookie); break; case BPF_PROG_TYPE_FLOW_DISSECTOR: case BPF_PROG_TYPE_SK_LOOKUP: ret = netns_bpf_link_create(attr, prog); break; case BPF_PROG_TYPE_SK_MSG: case BPF_PROG_TYPE_SK_SKB: ret = sock_map_link_create(attr, prog); break; #ifdef CONFIG_NET case BPF_PROG_TYPE_XDP: ret = bpf_xdp_link_attach(attr, prog); break; case BPF_PROG_TYPE_SCHED_CLS: if (attr->link_create.attach_type == BPF_TCX_INGRESS || attr->link_create.attach_type == BPF_TCX_EGRESS) ret = tcx_link_attach(attr, prog); else ret = netkit_link_attach(attr, prog); break; case BPF_PROG_TYPE_NETFILTER: ret = bpf_nf_link_attach(attr, prog); break; #endif case BPF_PROG_TYPE_PERF_EVENT: case BPF_PROG_TYPE_TRACEPOINT: ret = bpf_perf_link_attach(attr, prog); break; case BPF_PROG_TYPE_KPROBE: if (attr->link_create.attach_type == BPF_PERF_EVENT) ret = bpf_perf_link_attach(attr, prog); else if (attr->link_create.attach_type == BPF_TRACE_KPROBE_MULTI || attr->link_create.attach_type == BPF_TRACE_KPROBE_SESSION) ret = bpf_kprobe_multi_link_attach(attr, prog); else if (attr->link_create.attach_type == BPF_TRACE_UPROBE_MULTI || attr->link_create.attach_type == BPF_TRACE_UPROBE_SESSION) ret = bpf_uprobe_multi_link_attach(attr, prog); break; default: ret = -EINVAL; } out: if (ret < 0) bpf_prog_put(prog); return ret; } static int link_update_map(struct bpf_link *link, union bpf_attr *attr) { struct bpf_map *new_map, *old_map = NULL; int ret; new_map = bpf_map_get(attr->link_update.new_map_fd); if (IS_ERR(new_map)) return PTR_ERR(new_map); if (attr->link_update.flags & BPF_F_REPLACE) { old_map = bpf_map_get(attr->link_update.old_map_fd); if (IS_ERR(old_map)) { ret = PTR_ERR(old_map); goto out_put; } } else if (attr->link_update.old_map_fd) { ret = -EINVAL; goto out_put; } ret = link->ops->update_map(link, new_map, old_map); if (old_map) bpf_map_put(old_map); out_put: bpf_map_put(new_map); return ret; } #define BPF_LINK_UPDATE_LAST_FIELD link_update.old_prog_fd static int link_update(union bpf_attr *attr) { struct bpf_prog *old_prog = NULL, *new_prog; struct bpf_link *link; u32 flags; int ret; if (CHECK_ATTR(BPF_LINK_UPDATE)) return -EINVAL; flags = attr->link_update.flags; if (flags & ~BPF_F_REPLACE) return -EINVAL; link = bpf_link_get_from_fd(attr->link_update.link_fd); if (IS_ERR(link)) return PTR_ERR(link); if (link->ops->update_map) { ret = link_update_map(link, attr); goto out_put_link; } new_prog = bpf_prog_get(attr->link_update.new_prog_fd); if (IS_ERR(new_prog)) { ret = PTR_ERR(new_prog); goto out_put_link; } if (flags & BPF_F_REPLACE) { old_prog = bpf_prog_get(attr->link_update.old_prog_fd); if (IS_ERR(old_prog)) { ret = PTR_ERR(old_prog); old_prog = NULL; goto out_put_progs; } } else if (attr->link_update.old_prog_fd) { ret = -EINVAL; goto out_put_progs; } if (link->ops->update_prog) ret = link->ops->update_prog(link, new_prog, old_prog); else ret = -EINVAL; out_put_progs: if (old_prog) bpf_prog_put(old_prog); if (ret) bpf_prog_put(new_prog); out_put_link: bpf_link_put_direct(link); return ret; } #define BPF_LINK_DETACH_LAST_FIELD link_detach.link_fd static int link_detach(union bpf_attr *attr) { struct bpf_link *link; int ret; if (CHECK_ATTR(BPF_LINK_DETACH)) return -EINVAL; link = bpf_link_get_from_fd(attr->link_detach.link_fd); if (IS_ERR(link)) return PTR_ERR(link); if (link->ops->detach) ret = link->ops->detach(link); else ret = -EOPNOTSUPP; bpf_link_put_direct(link); return ret; } struct bpf_link *bpf_link_inc_not_zero(struct bpf_link *link) { return atomic64_fetch_add_unless(&link->refcnt, 1, 0) ? link : ERR_PTR(-ENOENT); } EXPORT_SYMBOL(bpf_link_inc_not_zero); struct bpf_link *bpf_link_by_id(u32 id) { struct bpf_link *link; if (!id) return ERR_PTR(-ENOENT); spin_lock_bh(&link_idr_lock); /* before link is "settled", ID is 0, pretend it doesn't exist yet */ link = idr_find(&link_idr, id); if (link) { if (link->id) link = bpf_link_inc_not_zero(link); else link = ERR_PTR(-EAGAIN); } else { link = ERR_PTR(-ENOENT); } spin_unlock_bh(&link_idr_lock); return link; } struct bpf_link *bpf_link_get_curr_or_next(u32 *id) { struct bpf_link *link; spin_lock_bh(&link_idr_lock); again: link = idr_get_next(&link_idr, id); if (link) { link = bpf_link_inc_not_zero(link); if (IS_ERR(link)) { (*id)++; goto again; } } spin_unlock_bh(&link_idr_lock); return link; } #define BPF_LINK_GET_FD_BY_ID_LAST_FIELD link_id static int bpf_link_get_fd_by_id(const union bpf_attr *attr) { struct bpf_link *link; u32 id = attr->link_id; int fd; if (CHECK_ATTR(BPF_LINK_GET_FD_BY_ID)) return -EINVAL; if (!capable(CAP_SYS_ADMIN)) return -EPERM; link = bpf_link_by_id(id); if (IS_ERR(link)) return PTR_ERR(link); fd = bpf_link_new_fd(link); if (fd < 0) bpf_link_put_direct(link); return fd; } DEFINE_MUTEX(bpf_stats_enabled_mutex); static int bpf_stats_release(struct inode *inode, struct file *file) { mutex_lock(&bpf_stats_enabled_mutex); static_key_slow_dec(&bpf_stats_enabled_key.key); mutex_unlock(&bpf_stats_enabled_mutex); return 0; } static const struct file_operations bpf_stats_fops = { .release = bpf_stats_release, }; static int bpf_enable_runtime_stats(void) { int fd; mutex_lock(&bpf_stats_enabled_mutex); /* Set a very high limit to avoid overflow */ if (static_key_count(&bpf_stats_enabled_key.key) > INT_MAX / 2) { mutex_unlock(&bpf_stats_enabled_mutex); return -EBUSY; } fd = anon_inode_getfd("bpf-stats", &bpf_stats_fops, NULL, O_CLOEXEC); if (fd >= 0) static_key_slow_inc(&bpf_stats_enabled_key.key); mutex_unlock(&bpf_stats_enabled_mutex); return fd; } #define BPF_ENABLE_STATS_LAST_FIELD enable_stats.type static int bpf_enable_stats(union bpf_attr *attr) { if (CHECK_ATTR(BPF_ENABLE_STATS)) return -EINVAL; if (!capable(CAP_SYS_ADMIN)) return -EPERM; switch (attr->enable_stats.type) { case BPF_STATS_RUN_TIME: return bpf_enable_runtime_stats(); default: break; } return -EINVAL; } #define BPF_ITER_CREATE_LAST_FIELD iter_create.flags static int bpf_iter_create(union bpf_attr *attr) { struct bpf_link *link; int err; if (CHECK_ATTR(BPF_ITER_CREATE)) return -EINVAL; if (attr->iter_create.flags) return -EINVAL; link = bpf_link_get_from_fd(attr->iter_create.link_fd); if (IS_ERR(link)) return PTR_ERR(link); err = bpf_iter_new_fd(link); bpf_link_put_direct(link); return err; } #define BPF_PROG_BIND_MAP_LAST_FIELD prog_bind_map.flags static int bpf_prog_bind_map(union bpf_attr *attr) { struct bpf_prog *prog; struct bpf_map *map; struct bpf_map **used_maps_old, **used_maps_new; int i, ret = 0; if (CHECK_ATTR(BPF_PROG_BIND_MAP)) return -EINVAL; if (attr->prog_bind_map.flags) return -EINVAL; prog = bpf_prog_get(attr->prog_bind_map.prog_fd); if (IS_ERR(prog)) return PTR_ERR(prog); map = bpf_map_get(attr->prog_bind_map.map_fd); if (IS_ERR(map)) { ret = PTR_ERR(map); goto out_prog_put; } mutex_lock(&prog->aux->used_maps_mutex); used_maps_old = prog->aux->used_maps; for (i = 0; i < prog->aux->used_map_cnt; i++) if (used_maps_old[i] == map) { bpf_map_put(map); goto out_unlock; } used_maps_new = kmalloc_array(prog->aux->used_map_cnt + 1, sizeof(used_maps_new[0]), GFP_KERNEL); if (!used_maps_new) { ret = -ENOMEM; goto out_unlock; } /* The bpf program will not access the bpf map, but for the sake of * simplicity, increase sleepable_refcnt for sleepable program as well. */ if (prog->sleepable) atomic64_inc(&map->sleepable_refcnt); memcpy(used_maps_new, used_maps_old, sizeof(used_maps_old[0]) * prog->aux->used_map_cnt); used_maps_new[prog->aux->used_map_cnt] = map; prog->aux->used_map_cnt++; prog->aux->used_maps = used_maps_new; kfree(used_maps_old); out_unlock: mutex_unlock(&prog->aux->used_maps_mutex); if (ret) bpf_map_put(map); out_prog_put: bpf_prog_put(prog); return ret; } #define BPF_TOKEN_CREATE_LAST_FIELD token_create.bpffs_fd static int token_create(union bpf_attr *attr) { if (CHECK_ATTR(BPF_TOKEN_CREATE)) return -EINVAL; /* no flags are supported yet */ if (attr->token_create.flags) return -EINVAL; return bpf_token_create(attr); } static int __sys_bpf(enum bpf_cmd cmd, bpfptr_t uattr, unsigned int size) { union bpf_attr attr; int err; err = bpf_check_uarg_tail_zero(uattr, sizeof(attr), size); if (err) return err; size = min_t(u32, size, sizeof(attr)); /* copy attributes from user space, may be less than sizeof(bpf_attr) */ memset(&attr, 0, sizeof(attr)); if (copy_from_bpfptr(&attr, uattr, size) != 0) return -EFAULT; err = security_bpf(cmd, &attr, size); if (err < 0) return err; switch (cmd) { case BPF_MAP_CREATE: err = map_create(&attr); break; case BPF_MAP_LOOKUP_ELEM: err = map_lookup_elem(&attr); break; case BPF_MAP_UPDATE_ELEM: err = map_update_elem(&attr, uattr); break; case BPF_MAP_DELETE_ELEM: err = map_delete_elem(&attr, uattr); break; case BPF_MAP_GET_NEXT_KEY: err = map_get_next_key(&attr); break; case BPF_MAP_FREEZE: err = map_freeze(&attr); break; case BPF_PROG_LOAD: err = bpf_prog_load(&attr, uattr, size); break; case BPF_OBJ_PIN: err = bpf_obj_pin(&attr); break; case BPF_OBJ_GET: err = bpf_obj_get(&attr); break; case BPF_PROG_ATTACH: err = bpf_prog_attach(&attr); break; case BPF_PROG_DETACH: err = bpf_prog_detach(&attr); break; case BPF_PROG_QUERY: err = bpf_prog_query(&attr, uattr.user); break; case BPF_PROG_TEST_RUN: err = bpf_prog_test_run(&attr, uattr.user); break; case BPF_PROG_GET_NEXT_ID: err = bpf_obj_get_next_id(&attr, uattr.user, &prog_idr, &prog_idr_lock); break; case BPF_MAP_GET_NEXT_ID: err = bpf_obj_get_next_id(&attr, uattr.user, &map_idr, &map_idr_lock); break; case BPF_BTF_GET_NEXT_ID: err = bpf_obj_get_next_id(&attr, uattr.user, &btf_idr, &btf_idr_lock); break; case BPF_PROG_GET_FD_BY_ID: err = bpf_prog_get_fd_by_id(&attr); break; case BPF_MAP_GET_FD_BY_ID: err = bpf_map_get_fd_by_id(&attr); break; case BPF_OBJ_GET_INFO_BY_FD: err = bpf_obj_get_info_by_fd(&attr, uattr.user); break; case BPF_RAW_TRACEPOINT_OPEN: err = bpf_raw_tracepoint_open(&attr); break; case BPF_BTF_LOAD: err = bpf_btf_load(&attr, uattr, size); break; case BPF_BTF_GET_FD_BY_ID: err = bpf_btf_get_fd_by_id(&attr); break; case BPF_TASK_FD_QUERY: err = bpf_task_fd_query(&attr, uattr.user); break; case BPF_MAP_LOOKUP_AND_DELETE_ELEM: err = map_lookup_and_delete_elem(&attr); break; case BPF_MAP_LOOKUP_BATCH: err = bpf_map_do_batch(&attr, uattr.user, BPF_MAP_LOOKUP_BATCH); break; case BPF_MAP_LOOKUP_AND_DELETE_BATCH: err = bpf_map_do_batch(&attr, uattr.user, BPF_MAP_LOOKUP_AND_DELETE_BATCH); break; case BPF_MAP_UPDATE_BATCH: err = bpf_map_do_batch(&attr, uattr.user, BPF_MAP_UPDATE_BATCH); break; case BPF_MAP_DELETE_BATCH: err = bpf_map_do_batch(&attr, uattr.user, BPF_MAP_DELETE_BATCH); break; case BPF_LINK_CREATE: err = link_create(&attr, uattr); break; case BPF_LINK_UPDATE: err = link_update(&attr); break; case BPF_LINK_GET_FD_BY_ID: err = bpf_link_get_fd_by_id(&attr); break; case BPF_LINK_GET_NEXT_ID: err = bpf_obj_get_next_id(&attr, uattr.user, &link_idr, &link_idr_lock); break; case BPF_ENABLE_STATS: err = bpf_enable_stats(&attr); break; case BPF_ITER_CREATE: err = bpf_iter_create(&attr); break; case BPF_LINK_DETACH: err = link_detach(&attr); break; case BPF_PROG_BIND_MAP: err = bpf_prog_bind_map(&attr); break; case BPF_TOKEN_CREATE: err = token_create(&attr); break; default: err = -EINVAL; break; } return err; } SYSCALL_DEFINE3(bpf, int, cmd, union bpf_attr __user *, uattr, unsigned int, size) { return __sys_bpf(cmd, USER_BPFPTR(uattr), size); } static bool syscall_prog_is_valid_access(int off, int size, enum bpf_access_type type, const struct bpf_prog *prog, struct bpf_insn_access_aux *info) { if (off < 0 || off >= U16_MAX) return false; if (off % size != 0) return false; return true; } BPF_CALL_3(bpf_sys_bpf, int, cmd, union bpf_attr *, attr, u32, attr_size) { switch (cmd) { case BPF_MAP_CREATE: case BPF_MAP_DELETE_ELEM: case BPF_MAP_UPDATE_ELEM: case BPF_MAP_FREEZE: case BPF_MAP_GET_FD_BY_ID: case BPF_PROG_LOAD: case BPF_BTF_LOAD: case BPF_LINK_CREATE: case BPF_RAW_TRACEPOINT_OPEN: break; default: return -EINVAL; } return __sys_bpf(cmd, KERNEL_BPFPTR(attr), attr_size); } /* To shut up -Wmissing-prototypes. * This function is used by the kernel light skeleton * to load bpf programs when modules are loaded or during kernel boot. * See tools/lib/bpf/skel_internal.h */ int kern_sys_bpf(int cmd, union bpf_attr *attr, unsigned int size); int kern_sys_bpf(int cmd, union bpf_attr *attr, unsigned int size) { struct bpf_prog * __maybe_unused prog; struct bpf_tramp_run_ctx __maybe_unused run_ctx; switch (cmd) { #ifdef CONFIG_BPF_JIT /* __bpf_prog_enter_sleepable used by trampoline and JIT */ case BPF_PROG_TEST_RUN: if (attr->test.data_in || attr->test.data_out || attr->test.ctx_out || attr->test.duration || attr->test.repeat || attr->test.flags) return -EINVAL; prog = bpf_prog_get_type(attr->test.prog_fd, BPF_PROG_TYPE_SYSCALL); if (IS_ERR(prog)) return PTR_ERR(prog); if (attr->test.ctx_size_in < prog->aux->max_ctx_offset || attr->test.ctx_size_in > U16_MAX) { bpf_prog_put(prog); return -EINVAL; } run_ctx.bpf_cookie = 0; if (!__bpf_prog_enter_sleepable_recur(prog, &run_ctx)) { /* recursion detected */ __bpf_prog_exit_sleepable_recur(prog, 0, &run_ctx); bpf_prog_put(prog); return -EBUSY; } attr->test.retval = bpf_prog_run(prog, (void *) (long) attr->test.ctx_in); __bpf_prog_exit_sleepable_recur(prog, 0 /* bpf_prog_run does runtime stats */, &run_ctx); bpf_prog_put(prog); return 0; #endif default: return ____bpf_sys_bpf(cmd, attr, size); } } EXPORT_SYMBOL(kern_sys_bpf); static const struct bpf_func_proto bpf_sys_bpf_proto = { .func = bpf_sys_bpf, .gpl_only = false, .ret_type = RET_INTEGER, .arg1_type = ARG_ANYTHING, .arg2_type = ARG_PTR_TO_MEM | MEM_RDONLY, .arg3_type = ARG_CONST_SIZE, }; const struct bpf_func_proto * __weak tracing_prog_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) { return bpf_base_func_proto(func_id, prog); } BPF_CALL_1(bpf_sys_close, u32, fd) { /* When bpf program calls this helper there should not be * an fdget() without matching completed fdput(). * This helper is allowed in the following callchain only: * sys_bpf->prog_test_run->bpf_prog->bpf_sys_close */ return close_fd(fd); } static const struct bpf_func_proto bpf_sys_close_proto = { .func = bpf_sys_close, .gpl_only = false, .ret_type = RET_INTEGER, .arg1_type = ARG_ANYTHING, }; BPF_CALL_4(bpf_kallsyms_lookup_name, const char *, name, int, name_sz, int, flags, u64 *, res) { *res = 0; if (flags) return -EINVAL; if (name_sz <= 1 || name[name_sz - 1]) return -EINVAL; if (!bpf_dump_raw_ok(current_cred())) return -EPERM; *res = kallsyms_lookup_name(name); return *res ? 0 : -ENOENT; } static const struct bpf_func_proto bpf_kallsyms_lookup_name_proto = { .func = bpf_kallsyms_lookup_name, .gpl_only = false, .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_MEM, .arg2_type = ARG_CONST_SIZE_OR_ZERO, .arg3_type = ARG_ANYTHING, .arg4_type = ARG_PTR_TO_FIXED_SIZE_MEM | MEM_UNINIT | MEM_WRITE | MEM_ALIGNED, .arg4_size = sizeof(u64), }; static const struct bpf_func_proto * syscall_prog_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) { switch (func_id) { case BPF_FUNC_sys_bpf: return !bpf_token_capable(prog->aux->token, CAP_PERFMON) ? NULL : &bpf_sys_bpf_proto; case BPF_FUNC_btf_find_by_name_kind: return &bpf_btf_find_by_name_kind_proto; case BPF_FUNC_sys_close: return &bpf_sys_close_proto; case BPF_FUNC_kallsyms_lookup_name: return &bpf_kallsyms_lookup_name_proto; default: return tracing_prog_func_proto(func_id, prog); } } const struct bpf_verifier_ops bpf_syscall_verifier_ops = { .get_func_proto = syscall_prog_func_proto, .is_valid_access = syscall_prog_is_valid_access, }; const struct bpf_prog_ops bpf_syscall_prog_ops = { .test_run = bpf_prog_test_run_syscall, }; #ifdef CONFIG_SYSCTL static int bpf_stats_handler(const struct ctl_table *table, int write, void *buffer, size_t *lenp, loff_t *ppos) { struct static_key *key = (struct static_key *)table->data; static int saved_val; int val, ret; struct ctl_table tmp = { .data = &val, .maxlen = sizeof(val), .mode = table->mode, .extra1 = SYSCTL_ZERO, .extra2 = SYSCTL_ONE, }; if (write && !capable(CAP_SYS_ADMIN)) return -EPERM; mutex_lock(&bpf_stats_enabled_mutex); val = saved_val; ret = proc_dointvec_minmax(&tmp, write, buffer, lenp, ppos); if (write && !ret && val != saved_val) { if (val) static_key_slow_inc(key); else static_key_slow_dec(key); saved_val = val; } mutex_unlock(&bpf_stats_enabled_mutex); return ret; } void __weak unpriv_ebpf_notify(int new_state) { } static int bpf_unpriv_handler(const struct ctl_table *table, int write, void *buffer, size_t *lenp, loff_t *ppos) { int ret, unpriv_enable = *(int *)table->data; bool locked_state = unpriv_enable == 1; struct ctl_table tmp = *table; if (write && !capable(CAP_SYS_ADMIN)) return -EPERM; tmp.data = &unpriv_enable; ret = proc_dointvec_minmax(&tmp, write, buffer, lenp, ppos); if (write && !ret) { if (locked_state && unpriv_enable != 1) return -EPERM; *(int *)table->data = unpriv_enable; } if (write) unpriv_ebpf_notify(unpriv_enable); return ret; } static const struct ctl_table bpf_syscall_table[] = { { .procname = "unprivileged_bpf_disabled", .data = &sysctl_unprivileged_bpf_disabled, .maxlen = sizeof(sysctl_unprivileged_bpf_disabled), .mode = 0644, .proc_handler = bpf_unpriv_handler, .extra1 = SYSCTL_ZERO, .extra2 = SYSCTL_TWO, }, { .procname = "bpf_stats_enabled", .data = &bpf_stats_enabled_key.key, .mode = 0644, .proc_handler = bpf_stats_handler, }, }; static int __init bpf_syscall_sysctl_init(void) { register_sysctl_init("kernel", bpf_syscall_table); return 0; } late_initcall(bpf_syscall_sysctl_init); #endif /* CONFIG_SYSCTL */ |
| 17 17 17 17 14 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 | // SPDX-License-Identifier: GPL-2.0-or-later /* RxRPC virtual connection handler, common bits. * * Copyright (C) 2007, 2016 Red Hat, Inc. All Rights Reserved. * Written by David Howells (dhowells@redhat.com) */ #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt #include <linux/module.h> #include <linux/slab.h> #include <linux/net.h> #include <linux/skbuff.h> #include "ar-internal.h" /* * Time till a connection expires after last use (in seconds). */ unsigned int __read_mostly rxrpc_connection_expiry = 10 * 60; unsigned int __read_mostly rxrpc_closed_conn_expiry = 10; static void rxrpc_clean_up_connection(struct work_struct *work); static void rxrpc_set_service_reap_timer(struct rxrpc_net *rxnet, unsigned long reap_at); void rxrpc_poke_conn(struct rxrpc_connection *conn, enum rxrpc_conn_trace why) { struct rxrpc_local *local = conn->local; bool busy; if (WARN_ON_ONCE(!local)) return; spin_lock_irq(&local->lock); busy = !list_empty(&conn->attend_link); if (!busy) { rxrpc_get_connection(conn, why); list_add_tail(&conn->attend_link, &local->conn_attend_q); } spin_unlock_irq(&local->lock); rxrpc_wake_up_io_thread(local); } static void rxrpc_connection_timer(struct timer_list *timer) { struct rxrpc_connection *conn = container_of(timer, struct rxrpc_connection, timer); rxrpc_poke_conn(conn, rxrpc_conn_get_poke_timer); } /* * allocate a new connection */ struct rxrpc_connection *rxrpc_alloc_connection(struct rxrpc_net *rxnet, gfp_t gfp) { struct rxrpc_connection *conn; _enter(""); conn = kzalloc(sizeof(struct rxrpc_connection), gfp); if (conn) { INIT_LIST_HEAD(&conn->cache_link); timer_setup(&conn->timer, &rxrpc_connection_timer, 0); INIT_WORK(&conn->processor, rxrpc_process_connection); INIT_WORK(&conn->destructor, rxrpc_clean_up_connection); INIT_LIST_HEAD(&conn->proc_link); INIT_LIST_HEAD(&conn->link); mutex_init(&conn->security_lock); mutex_init(&conn->tx_data_alloc_lock); skb_queue_head_init(&conn->rx_queue); conn->rxnet = rxnet; conn->security = &rxrpc_no_security; spin_lock_init(&conn->state_lock); conn->debug_id = atomic_inc_return(&rxrpc_debug_id); conn->idle_timestamp = jiffies; } _leave(" = %p{%d}", conn, conn ? conn->debug_id : 0); return conn; } /* * Look up a connection in the cache by protocol parameters. * * If successful, a pointer to the connection is returned, but no ref is taken. * NULL is returned if there is no match. * * When searching for a service call, if we find a peer but no connection, we * return that through *_peer in case we need to create a new service call. * * The caller must be holding the RCU read lock. */ struct rxrpc_connection *rxrpc_find_client_connection_rcu(struct rxrpc_local *local, struct sockaddr_rxrpc *srx, struct sk_buff *skb) { struct rxrpc_connection *conn; struct rxrpc_skb_priv *sp = rxrpc_skb(skb); struct rxrpc_peer *peer; _enter(",%x", sp->hdr.cid & RXRPC_CIDMASK); /* Look up client connections by connection ID alone as their * IDs are unique for this machine. */ conn = idr_find(&local->conn_ids, sp->hdr.cid >> RXRPC_CIDSHIFT); if (!conn || refcount_read(&conn->ref) == 0) { _debug("no conn"); goto not_found; } if (conn->proto.epoch != sp->hdr.epoch || conn->local != local) goto not_found; peer = conn->peer; switch (srx->transport.family) { case AF_INET: if (peer->srx.transport.sin.sin_port != srx->transport.sin.sin_port) goto not_found; break; #ifdef CONFIG_AF_RXRPC_IPV6 case AF_INET6: if (peer->srx.transport.sin6.sin6_port != srx->transport.sin6.sin6_port) goto not_found; break; #endif default: BUG(); } _leave(" = %p", conn); return conn; not_found: _leave(" = NULL"); return NULL; } /* * Disconnect a call and clear any channel it occupies when that call * terminates. The caller must hold the channel_lock and must release the * call's ref on the connection. */ void __rxrpc_disconnect_call(struct rxrpc_connection *conn, struct rxrpc_call *call) { struct rxrpc_channel *chan = &conn->channels[call->cid & RXRPC_CHANNELMASK]; _enter("%d,%x", conn->debug_id, call->cid); if (chan->call == call) { /* Save the result of the call so that we can repeat it if necessary * through the channel, whilst disposing of the actual call record. */ trace_rxrpc_disconnect_call(call); switch (call->completion) { case RXRPC_CALL_SUCCEEDED: chan->last_seq = call->rx_highest_seq; chan->last_type = RXRPC_PACKET_TYPE_ACK; break; case RXRPC_CALL_LOCALLY_ABORTED: chan->last_abort = call->abort_code; chan->last_type = RXRPC_PACKET_TYPE_ABORT; break; default: chan->last_abort = RX_CALL_DEAD; chan->last_type = RXRPC_PACKET_TYPE_ABORT; break; } chan->last_call = chan->call_id; chan->call_id = chan->call_counter; chan->call = NULL; } _leave(""); } /* * Disconnect a call and clear any channel it occupies when that call * terminates. */ void rxrpc_disconnect_call(struct rxrpc_call *call) { struct rxrpc_connection *conn = call->conn; set_bit(RXRPC_CALL_DISCONNECTED, &call->flags); rxrpc_see_call(call, rxrpc_call_see_disconnected); call->peer->cong_ssthresh = call->cong_ssthresh; if (!hlist_unhashed(&call->error_link)) { spin_lock_irq(&call->peer->lock); hlist_del_init(&call->error_link); spin_unlock_irq(&call->peer->lock); } if (rxrpc_is_client_call(call)) { rxrpc_disconnect_client_call(call->bundle, call); } else { __rxrpc_disconnect_call(conn, call); conn->idle_timestamp = jiffies; if (atomic_dec_and_test(&conn->active)) rxrpc_set_service_reap_timer(conn->rxnet, jiffies + rxrpc_connection_expiry * HZ); } rxrpc_put_call(call, rxrpc_call_put_io_thread); } /* * Queue a connection's work processor, getting a ref to pass to the work * queue. */ void rxrpc_queue_conn(struct rxrpc_connection *conn, enum rxrpc_conn_trace why) { if (atomic_read(&conn->active) >= 0 && rxrpc_queue_work(&conn->processor)) rxrpc_see_connection(conn, why); } /* * Note the re-emergence of a connection. */ void rxrpc_see_connection(struct rxrpc_connection *conn, enum rxrpc_conn_trace why) { if (conn) { int r = refcount_read(&conn->ref); trace_rxrpc_conn(conn->debug_id, r, why); } } /* * Get a ref on a connection. */ struct rxrpc_connection *rxrpc_get_connection(struct rxrpc_connection *conn, enum rxrpc_conn_trace why) { int r; __refcount_inc(&conn->ref, &r); trace_rxrpc_conn(conn->debug_id, r + 1, why); return conn; } /* * Try to get a ref on a connection. */ struct rxrpc_connection * rxrpc_get_connection_maybe(struct rxrpc_connection *conn, enum rxrpc_conn_trace why) { int r; if (conn) { if (__refcount_inc_not_zero(&conn->ref, &r)) trace_rxrpc_conn(conn->debug_id, r + 1, why); else conn = NULL; } return conn; } /* * Set the service connection reap timer. */ static void rxrpc_set_service_reap_timer(struct rxrpc_net *rxnet, unsigned long reap_at) { if (rxnet->live) timer_reduce(&rxnet->service_conn_reap_timer, reap_at); } /* * destroy a virtual connection */ static void rxrpc_rcu_free_connection(struct rcu_head *rcu) { struct rxrpc_connection *conn = container_of(rcu, struct rxrpc_connection, rcu); struct rxrpc_net *rxnet = conn->rxnet; _enter("{%d,u=%d}", conn->debug_id, refcount_read(&conn->ref)); trace_rxrpc_conn(conn->debug_id, refcount_read(&conn->ref), rxrpc_conn_free); kfree(conn); if (atomic_dec_and_test(&rxnet->nr_conns)) wake_up_var(&rxnet->nr_conns); } /* * Clean up a dead connection. */ static void rxrpc_clean_up_connection(struct work_struct *work) { struct rxrpc_connection *conn = container_of(work, struct rxrpc_connection, destructor); struct rxrpc_net *rxnet = conn->rxnet; ASSERT(!conn->channels[0].call && !conn->channels[1].call && !conn->channels[2].call && !conn->channels[3].call); ASSERT(list_empty(&conn->cache_link)); del_timer_sync(&conn->timer); cancel_work_sync(&conn->processor); /* Processing may restart the timer */ del_timer_sync(&conn->timer); write_lock(&rxnet->conn_lock); list_del_init(&conn->proc_link); write_unlock(&rxnet->conn_lock); if (conn->pmtud_probe) { trace_rxrpc_pmtud_lost(conn, 0); conn->peer->pmtud_probing = false; conn->peer->pmtud_pending = true; } rxrpc_purge_queue(&conn->rx_queue); rxrpc_kill_client_conn(conn); conn->security->clear(conn); key_put(conn->key); rxrpc_put_bundle(conn->bundle, rxrpc_bundle_put_conn); rxrpc_put_peer(conn->peer, rxrpc_peer_put_conn); rxrpc_put_local(conn->local, rxrpc_local_put_kill_conn); /* Drain the Rx queue. Note that even though we've unpublished, an * incoming packet could still be being added to our Rx queue, so we * will need to drain it again in the RCU cleanup handler. */ rxrpc_purge_queue(&conn->rx_queue); page_frag_cache_drain(&conn->tx_data_alloc); call_rcu(&conn->rcu, rxrpc_rcu_free_connection); } /* * Drop a ref on a connection. */ void rxrpc_put_connection(struct rxrpc_connection *conn, enum rxrpc_conn_trace why) { unsigned int debug_id; bool dead; int r; if (!conn) return; debug_id = conn->debug_id; dead = __refcount_dec_and_test(&conn->ref, &r); trace_rxrpc_conn(debug_id, r - 1, why); if (dead) { del_timer(&conn->timer); cancel_work(&conn->processor); if (in_softirq() || work_busy(&conn->processor) || timer_pending(&conn->timer)) /* Can't use the rxrpc workqueue as we need to cancel/flush * something that may be running/waiting there. */ schedule_work(&conn->destructor); else rxrpc_clean_up_connection(&conn->destructor); } } /* * reap dead service connections */ void rxrpc_service_connection_reaper(struct work_struct *work) { struct rxrpc_connection *conn, *_p; struct rxrpc_net *rxnet = container_of(work, struct rxrpc_net, service_conn_reaper); unsigned long expire_at, earliest, idle_timestamp, now; int active; LIST_HEAD(graveyard); _enter(""); now = jiffies; earliest = now + MAX_JIFFY_OFFSET; write_lock(&rxnet->conn_lock); list_for_each_entry_safe(conn, _p, &rxnet->service_conns, link) { ASSERTCMP(atomic_read(&conn->active), >=, 0); if (likely(atomic_read(&conn->active) > 0)) continue; if (conn->state == RXRPC_CONN_SERVICE_PREALLOC) continue; if (rxnet->live && !conn->local->dead) { idle_timestamp = READ_ONCE(conn->idle_timestamp); expire_at = idle_timestamp + rxrpc_connection_expiry * HZ; if (conn->local->service_closed) expire_at = idle_timestamp + rxrpc_closed_conn_expiry * HZ; _debug("reap CONN %d { a=%d,t=%ld }", conn->debug_id, atomic_read(&conn->active), (long)expire_at - (long)now); if (time_before(now, expire_at)) { if (time_before(expire_at, earliest)) earliest = expire_at; continue; } } /* The activity count sits at 0 whilst the conn is unused on * the list; we reduce that to -1 to make the conn unavailable. */ active = 0; if (!atomic_try_cmpxchg(&conn->active, &active, -1)) continue; rxrpc_see_connection(conn, rxrpc_conn_see_reap_service); if (rxrpc_conn_is_client(conn)) BUG(); else rxrpc_unpublish_service_conn(conn); list_move_tail(&conn->link, &graveyard); } write_unlock(&rxnet->conn_lock); if (earliest != now + MAX_JIFFY_OFFSET) { _debug("reschedule reaper %ld", (long)earliest - (long)now); ASSERT(time_after(earliest, now)); rxrpc_set_service_reap_timer(rxnet, earliest); } while (!list_empty(&graveyard)) { conn = list_entry(graveyard.next, struct rxrpc_connection, link); list_del_init(&conn->link); ASSERTCMP(atomic_read(&conn->active), ==, -1); rxrpc_put_connection(conn, rxrpc_conn_put_service_reaped); } _leave(""); } /* * preemptively destroy all the service connection records rather than * waiting for them to time out */ void rxrpc_destroy_all_connections(struct rxrpc_net *rxnet) { struct rxrpc_connection *conn, *_p; bool leak = false; _enter(""); atomic_dec(&rxnet->nr_conns); del_timer_sync(&rxnet->service_conn_reap_timer); rxrpc_queue_work(&rxnet->service_conn_reaper); flush_workqueue(rxrpc_workqueue); write_lock(&rxnet->conn_lock); list_for_each_entry_safe(conn, _p, &rxnet->service_conns, link) { pr_err("AF_RXRPC: Leaked conn %p {%d}\n", conn, refcount_read(&conn->ref)); leak = true; } write_unlock(&rxnet->conn_lock); BUG_ON(leak); ASSERT(list_empty(&rxnet->conn_proc_list)); /* We need to wait for the connections to be destroyed by RCU as they * pin things that we still need to get rid of. */ wait_var_event(&rxnet->nr_conns, !atomic_read(&rxnet->nr_conns)); _leave(""); } |
| 23 23 64 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 | /* 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> |
| 10 3 7 5 5 5 5 5 5 5 5 5 5 1 4 5 7 7 7 7 1 1 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 | // SPDX-License-Identifier: GPL-2.0-or-later /* * IPV4 GSO/GRO offload support * Linux INET implementation * * UDPv4 GSO support */ #include <linux/skbuff.h> #include <net/gro.h> #include <net/gso.h> #include <net/udp.h> #include <net/protocol.h> #include <net/inet_common.h> static struct sk_buff *__skb_udp_tunnel_segment(struct sk_buff *skb, netdev_features_t features, struct sk_buff *(*gso_inner_segment)(struct sk_buff *skb, netdev_features_t features), __be16 new_protocol, bool is_ipv6) { int tnl_hlen = skb_inner_mac_header(skb) - skb_transport_header(skb); bool remcsum, need_csum, offload_csum, gso_partial; struct sk_buff *segs = ERR_PTR(-EINVAL); struct udphdr *uh = udp_hdr(skb); u16 mac_offset = skb->mac_header; __be16 protocol = skb->protocol; u16 mac_len = skb->mac_len; int udp_offset, outer_hlen; __wsum partial; bool need_ipsec; if (unlikely(!pskb_may_pull(skb, tnl_hlen))) goto out; /* Adjust partial header checksum to negate old length. * We cannot rely on the value contained in uh->len as it is * possible that the actual value exceeds the boundaries of the * 16 bit length field due to the header being added outside of an * IP or IPv6 frame that was already limited to 64K - 1. */ if (skb_shinfo(skb)->gso_type & SKB_GSO_PARTIAL) partial = (__force __wsum)uh->len; else partial = (__force __wsum)htonl(skb->len); partial = csum_sub(csum_unfold(uh->check), partial); /* setup inner skb. */ skb->encapsulation = 0; SKB_GSO_CB(skb)->encap_level = 0; __skb_pull(skb, tnl_hlen); skb_reset_mac_header(skb); skb_set_network_header(skb, skb_inner_network_offset(skb)); skb_set_transport_header(skb, skb_inner_transport_offset(skb)); skb->mac_len = skb_inner_network_offset(skb); skb->protocol = new_protocol; need_csum = !!(skb_shinfo(skb)->gso_type & SKB_GSO_UDP_TUNNEL_CSUM); skb->encap_hdr_csum = need_csum; remcsum = !!(skb_shinfo(skb)->gso_type & SKB_GSO_TUNNEL_REMCSUM); skb->remcsum_offload = remcsum; need_ipsec = skb_dst(skb) && dst_xfrm(skb_dst(skb)); /* Try to offload checksum if possible */ offload_csum = !!(need_csum && !need_ipsec && (skb->dev->features & (is_ipv6 ? (NETIF_F_HW_CSUM | NETIF_F_IPV6_CSUM) : (NETIF_F_HW_CSUM | NETIF_F_IP_CSUM)))); features &= skb->dev->hw_enc_features; if (need_csum) features &= ~NETIF_F_SCTP_CRC; /* The only checksum offload we care about from here on out is the * outer one so strip the existing checksum feature flags and * instead set the flag based on our outer checksum offload value. */ if (remcsum) { features &= ~NETIF_F_CSUM_MASK; if (!need_csum || offload_csum) features |= NETIF_F_HW_CSUM; } /* segment inner packet. */ segs = gso_inner_segment(skb, features); if (IS_ERR_OR_NULL(segs)) { skb_gso_error_unwind(skb, protocol, tnl_hlen, mac_offset, mac_len); goto out; } gso_partial = !!(skb_shinfo(segs)->gso_type & SKB_GSO_PARTIAL); outer_hlen = skb_tnl_header_len(skb); udp_offset = outer_hlen - tnl_hlen; skb = segs; do { unsigned int len; if (remcsum) skb->ip_summed = CHECKSUM_NONE; /* Set up inner headers if we are offloading inner checksum */ if (skb->ip_summed == CHECKSUM_PARTIAL) { skb_reset_inner_headers(skb); skb->encapsulation = 1; } skb->mac_len = mac_len; skb->protocol = protocol; __skb_push(skb, outer_hlen); skb_reset_mac_header(skb); skb_set_network_header(skb, mac_len); skb_set_transport_header(skb, udp_offset); len = skb->len - udp_offset; uh = udp_hdr(skb); /* If we are only performing partial GSO the inner header * will be using a length value equal to only one MSS sized * segment instead of the entire frame. */ if (gso_partial && skb_is_gso(skb)) { uh->len = htons(skb_shinfo(skb)->gso_size + SKB_GSO_CB(skb)->data_offset + skb->head - (unsigned char *)uh); } else { uh->len = htons(len); } if (!need_csum) continue; uh->check = ~csum_fold(csum_add(partial, (__force __wsum)htonl(len))); if (skb->encapsulation || !offload_csum) { uh->check = gso_make_checksum(skb, ~uh->check); if (uh->check == 0) uh->check = CSUM_MANGLED_0; } else { skb->ip_summed = CHECKSUM_PARTIAL; skb->csum_start = skb_transport_header(skb) - skb->head; skb->csum_offset = offsetof(struct udphdr, check); } } while ((skb = skb->next)); out: return segs; } struct sk_buff *skb_udp_tunnel_segment(struct sk_buff *skb, netdev_features_t features, bool is_ipv6) { const struct net_offload __rcu **offloads; __be16 protocol = skb->protocol; const struct net_offload *ops; struct sk_buff *segs = ERR_PTR(-EINVAL); struct sk_buff *(*gso_inner_segment)(struct sk_buff *skb, netdev_features_t features); rcu_read_lock(); switch (skb->inner_protocol_type) { case ENCAP_TYPE_ETHER: protocol = skb->inner_protocol; gso_inner_segment = skb_mac_gso_segment; break; case ENCAP_TYPE_IPPROTO: offloads = is_ipv6 ? inet6_offloads : inet_offloads; ops = rcu_dereference(offloads[skb->inner_ipproto]); if (!ops || !ops->callbacks.gso_segment) goto out_unlock; gso_inner_segment = ops->callbacks.gso_segment; break; default: goto out_unlock; } segs = __skb_udp_tunnel_segment(skb, features, gso_inner_segment, protocol, is_ipv6); out_unlock: rcu_read_unlock(); return segs; } EXPORT_SYMBOL(skb_udp_tunnel_segment); static void __udpv4_gso_segment_csum(struct sk_buff *seg, __be32 *oldip, __be32 *newip, __be16 *oldport, __be16 *newport) { struct udphdr *uh; struct iphdr *iph; if (*oldip == *newip && *oldport == *newport) return; uh = udp_hdr(seg); iph = ip_hdr(seg); if (uh->check) { inet_proto_csum_replace4(&uh->check, seg, *oldip, *newip, true); inet_proto_csum_replace2(&uh->check, seg, *oldport, *newport, false); if (!uh->check) uh->check = CSUM_MANGLED_0; } *oldport = *newport; csum_replace4(&iph->check, *oldip, *newip); *oldip = *newip; } static struct sk_buff *__udpv4_gso_segment_list_csum(struct sk_buff *segs) { struct sk_buff *seg; struct udphdr *uh, *uh2; struct iphdr *iph, *iph2; seg = segs; uh = udp_hdr(seg); iph = ip_hdr(seg); if ((udp_hdr(seg)->dest == udp_hdr(seg->next)->dest) && (udp_hdr(seg)->source == udp_hdr(seg->next)->source) && (ip_hdr(seg)->daddr == ip_hdr(seg->next)->daddr) && (ip_hdr(seg)->saddr == ip_hdr(seg->next)->saddr)) return segs; while ((seg = seg->next)) { uh2 = udp_hdr(seg); iph2 = ip_hdr(seg); __udpv4_gso_segment_csum(seg, &iph2->saddr, &iph->saddr, &uh2->source, &uh->source); __udpv4_gso_segment_csum(seg, &iph2->daddr, &iph->daddr, &uh2->dest, &uh->dest); } return segs; } static struct sk_buff *__udp_gso_segment_list(struct sk_buff *skb, netdev_features_t features, bool is_ipv6) { unsigned int mss = skb_shinfo(skb)->gso_size; skb = skb_segment_list(skb, features, skb_mac_header_len(skb)); if (IS_ERR(skb)) return skb; udp_hdr(skb)->len = htons(sizeof(struct udphdr) + mss); return is_ipv6 ? skb : __udpv4_gso_segment_list_csum(skb); } struct sk_buff *__udp_gso_segment(struct sk_buff *gso_skb, netdev_features_t features, bool is_ipv6) { struct sock *sk = gso_skb->sk; unsigned int sum_truesize = 0; struct sk_buff *segs, *seg; struct udphdr *uh; unsigned int mss; bool copy_dtor; __sum16 check; __be16 newlen; mss = skb_shinfo(gso_skb)->gso_size; if (gso_skb->len <= sizeof(*uh) + mss) return ERR_PTR(-EINVAL); if (unlikely(skb_checksum_start(gso_skb) != skb_transport_header(gso_skb) && !(skb_shinfo(gso_skb)->gso_type & SKB_GSO_FRAGLIST))) return ERR_PTR(-EINVAL); /* We don't know if egress device can segment and checksum the packet * when IPv6 extension headers are present. Fall back to software GSO. */ if (gso_skb->ip_summed != CHECKSUM_PARTIAL) features &= ~(NETIF_F_GSO_UDP_L4 | NETIF_F_CSUM_MASK); if (skb_gso_ok(gso_skb, features | NETIF_F_GSO_ROBUST)) { /* Packet is from an untrusted source, reset gso_segs. */ skb_shinfo(gso_skb)->gso_segs = DIV_ROUND_UP(gso_skb->len - sizeof(*uh), mss); return NULL; } if (skb_shinfo(gso_skb)->gso_type & SKB_GSO_FRAGLIST) { /* Detect modified geometry and pass those to skb_segment. */ if (skb_pagelen(gso_skb) - sizeof(*uh) == skb_shinfo(gso_skb)->gso_size) return __udp_gso_segment_list(gso_skb, features, is_ipv6); /* Setup csum, as fraglist skips this in udp4_gro_receive. */ gso_skb->csum_start = skb_transport_header(gso_skb) - gso_skb->head; gso_skb->csum_offset = offsetof(struct udphdr, check); gso_skb->ip_summed = CHECKSUM_PARTIAL; uh = udp_hdr(gso_skb); if (is_ipv6) uh->check = ~udp_v6_check(gso_skb->len, &ipv6_hdr(gso_skb)->saddr, &ipv6_hdr(gso_skb)->daddr, 0); else uh->check = ~udp_v4_check(gso_skb->len, ip_hdr(gso_skb)->saddr, ip_hdr(gso_skb)->daddr, 0); } skb_pull(gso_skb, sizeof(*uh)); /* clear destructor to avoid skb_segment assigning it to tail */ copy_dtor = gso_skb->destructor == sock_wfree; if (copy_dtor) gso_skb->destructor = NULL; segs = skb_segment(gso_skb, features); if (IS_ERR_OR_NULL(segs)) { if (copy_dtor) gso_skb->destructor = sock_wfree; return segs; } /* GSO partial and frag_list segmentation only requires splitting * the frame into an MSS multiple and possibly a remainder, both * cases return a GSO skb. So update the mss now. */ if (skb_is_gso(segs)) mss *= skb_shinfo(segs)->gso_segs; seg = segs; uh = udp_hdr(seg); /* preserve TX timestamp flags and TS key for first segment */ skb_shinfo(seg)->tskey = skb_shinfo(gso_skb)->tskey; skb_shinfo(seg)->tx_flags |= (skb_shinfo(gso_skb)->tx_flags & SKBTX_ANY_TSTAMP); /* compute checksum adjustment based on old length versus new */ newlen = htons(sizeof(*uh) + mss); check = csum16_add(csum16_sub(uh->check, uh->len), newlen); for (;;) { if (copy_dtor) { seg->destructor = sock_wfree; seg->sk = sk; sum_truesize += seg->truesize; } if (!seg->next) break; uh->len = newlen; uh->check = check; if (seg->ip_summed == CHECKSUM_PARTIAL) gso_reset_checksum(seg, ~check); else uh->check = gso_make_checksum(seg, ~check) ? : CSUM_MANGLED_0; seg = seg->next; uh = udp_hdr(seg); } /* last packet can be partial gso_size, account for that in checksum */ newlen = htons(skb_tail_pointer(seg) - skb_transport_header(seg) + seg->data_len); check = csum16_add(csum16_sub(uh->check, uh->len), newlen); uh->len = newlen; uh->check = check; if (seg->ip_summed == CHECKSUM_PARTIAL) gso_reset_checksum(seg, ~check); else uh->check = gso_make_checksum(seg, ~check) ? : CSUM_MANGLED_0; /* On the TX path, CHECKSUM_NONE and CHECKSUM_UNNECESSARY have the same * meaning. However, check for bad offloads in the GSO stack expects the * latter, if the checksum was calculated in software. To vouch for the * segment skbs we actually need to set it on the gso_skb. */ if (gso_skb->ip_summed == CHECKSUM_NONE) gso_skb->ip_summed = CHECKSUM_UNNECESSARY; /* update refcount for the packet */ if (copy_dtor) { int delta = sum_truesize - gso_skb->truesize; /* In some pathological cases, delta can be negative. * We need to either use refcount_add() or refcount_sub_and_test() */ if (likely(delta >= 0)) refcount_add(delta, &sk->sk_wmem_alloc); else WARN_ON_ONCE(refcount_sub_and_test(-delta, &sk->sk_wmem_alloc)); } return segs; } EXPORT_SYMBOL_GPL(__udp_gso_segment); static struct sk_buff *udp4_ufo_fragment(struct sk_buff *skb, netdev_features_t features) { struct sk_buff *segs = ERR_PTR(-EINVAL); unsigned int mss; __wsum csum; struct udphdr *uh; struct iphdr *iph; if (skb->encapsulation && (skb_shinfo(skb)->gso_type & (SKB_GSO_UDP_TUNNEL|SKB_GSO_UDP_TUNNEL_CSUM))) { segs = skb_udp_tunnel_segment(skb, features, false); goto out; } if (!(skb_shinfo(skb)->gso_type & (SKB_GSO_UDP | SKB_GSO_UDP_L4))) goto out; if (!pskb_may_pull(skb, sizeof(struct udphdr))) goto out; if (skb_shinfo(skb)->gso_type & SKB_GSO_UDP_L4) return __udp_gso_segment(skb, features, false); mss = skb_shinfo(skb)->gso_size; if (unlikely(skb->len <= mss)) goto out; /* Do software UFO. Complete and fill in the UDP checksum as * HW cannot do checksum of UDP packets sent as multiple * IP fragments. */ uh = udp_hdr(skb); iph = ip_hdr(skb); uh->check = 0; csum = skb_checksum(skb, 0, skb->len, 0); uh->check = udp_v4_check(skb->len, iph->saddr, iph->daddr, csum); if (uh->check == 0) uh->check = CSUM_MANGLED_0; skb->ip_summed = CHECKSUM_UNNECESSARY; /* If there is no outer header we can fake a checksum offload * due to the fact that we have already done the checksum in * software prior to segmenting the frame. */ if (!skb->encap_hdr_csum) features |= NETIF_F_HW_CSUM; /* Fragment the skb. IP headers of the fragments are updated in * inet_gso_segment() */ segs = skb_segment(skb, features); out: return segs; } #define UDP_GRO_CNT_MAX 64 static struct sk_buff *udp_gro_receive_segment(struct list_head *head, struct sk_buff *skb) { struct udphdr *uh = udp_gro_udphdr(skb); struct sk_buff *pp = NULL; struct udphdr *uh2; struct sk_buff *p; unsigned int ulen; int ret = 0; int flush; /* requires non zero csum, for symmetry with GSO */ if (!uh->check) { NAPI_GRO_CB(skb)->flush = 1; return NULL; } /* Do not deal with padded or malicious packets, sorry ! */ ulen = ntohs(uh->len); if (ulen <= sizeof(*uh) || ulen != skb_gro_len(skb)) { NAPI_GRO_CB(skb)->flush = 1; return NULL; } /* pull encapsulating udp header */ skb_gro_pull(skb, sizeof(struct udphdr)); list_for_each_entry(p, head, list) { if (!NAPI_GRO_CB(p)->same_flow) continue; uh2 = udp_hdr(p); /* Match ports only, as csum is always non zero */ if ((*(u32 *)&uh->source != *(u32 *)&uh2->source)) { NAPI_GRO_CB(p)->same_flow = 0; continue; } if (NAPI_GRO_CB(skb)->is_flist != NAPI_GRO_CB(p)->is_flist) { NAPI_GRO_CB(skb)->flush = 1; return p; } flush = gro_receive_network_flush(uh, uh2, p); /* Terminate the flow on len mismatch or if it grow "too much". * Under small packet flood GRO count could elsewhere grow a lot * leading to excessive truesize values. * On len mismatch merge the first packet shorter than gso_size, * otherwise complete the GRO packet. */ if (ulen > ntohs(uh2->len) || flush) { pp = p; } else { if (NAPI_GRO_CB(skb)->is_flist) { if (!pskb_may_pull(skb, skb_gro_offset(skb))) { NAPI_GRO_CB(skb)->flush = 1; return NULL; } if ((skb->ip_summed != p->ip_summed) || (skb->csum_level != p->csum_level)) { NAPI_GRO_CB(skb)->flush = 1; return NULL; } ret = skb_gro_receive_list(p, skb); } else { skb_gro_postpull_rcsum(skb, uh, sizeof(struct udphdr)); ret = skb_gro_receive(p, skb); } } if (ret || ulen != ntohs(uh2->len) || NAPI_GRO_CB(p)->count >= UDP_GRO_CNT_MAX) pp = p; return pp; } /* mismatch, but we never need to flush */ return NULL; } struct sk_buff *udp_gro_receive(struct list_head *head, struct sk_buff *skb, struct udphdr *uh, struct sock *sk) { struct sk_buff *pp = NULL; struct sk_buff *p; struct udphdr *uh2; unsigned int off = skb_gro_offset(skb); int flush = 1; /* We can do L4 aggregation only if the packet can't land in a tunnel * otherwise we could corrupt the inner stream. Detecting such packets * cannot be foolproof and the aggregation might still happen in some * cases. Such packets should be caught in udp_unexpected_gso later. */ NAPI_GRO_CB(skb)->is_flist = 0; if (!sk || !udp_sk(sk)->gro_receive) { /* If the packet was locally encapsulated in a UDP tunnel that * wasn't detected above, do not GRO. */ if (skb->encapsulation) goto out; if (skb->dev->features & NETIF_F_GRO_FRAGLIST) NAPI_GRO_CB(skb)->is_flist = sk ? !udp_test_bit(GRO_ENABLED, sk) : 1; if ((!sk && (skb->dev->features & NETIF_F_GRO_UDP_FWD)) || (sk && udp_test_bit(GRO_ENABLED, sk)) || NAPI_GRO_CB(skb)->is_flist) return call_gro_receive(udp_gro_receive_segment, head, skb); /* no GRO, be sure flush the current packet */ goto out; } if (NAPI_GRO_CB(skb)->encap_mark || (uh->check && skb->ip_summed != CHECKSUM_PARTIAL && NAPI_GRO_CB(skb)->csum_cnt == 0 && !NAPI_GRO_CB(skb)->csum_valid)) goto out; /* mark that this skb passed once through the tunnel gro layer */ NAPI_GRO_CB(skb)->encap_mark = 1; flush = 0; list_for_each_entry(p, head, list) { if (!NAPI_GRO_CB(p)->same_flow) continue; uh2 = (struct udphdr *)(p->data + off); /* Match ports and either checksums are either both zero * or nonzero. */ if ((*(u32 *)&uh->source != *(u32 *)&uh2->source) || (!uh->check ^ !uh2->check)) { NAPI_GRO_CB(p)->same_flow = 0; continue; } } skb_gro_pull(skb, sizeof(struct udphdr)); /* pull encapsulating udp header */ skb_gro_postpull_rcsum(skb, uh, sizeof(struct udphdr)); pp = call_gro_receive_sk(udp_sk(sk)->gro_receive, sk, head, skb); out: skb_gro_flush_final(skb, pp, flush); return pp; } EXPORT_SYMBOL(udp_gro_receive); static struct sock *udp4_gro_lookup_skb(struct sk_buff *skb, __be16 sport, __be16 dport) { const struct iphdr *iph = skb_gro_network_header(skb); struct net *net = dev_net(skb->dev); int iif, sdif; inet_get_iif_sdif(skb, &iif, &sdif); return __udp4_lib_lookup(net, iph->saddr, sport, iph->daddr, dport, iif, sdif, net->ipv4.udp_table, NULL); } INDIRECT_CALLABLE_SCOPE struct sk_buff *udp4_gro_receive(struct list_head *head, struct sk_buff *skb) { struct udphdr *uh = udp_gro_udphdr(skb); struct sock *sk = NULL; struct sk_buff *pp; if (unlikely(!uh)) goto flush; /* Don't bother verifying checksum if we're going to flush anyway. */ if (NAPI_GRO_CB(skb)->flush) goto skip; if (skb_gro_checksum_validate_zero_check(skb, IPPROTO_UDP, uh->check, inet_gro_compute_pseudo)) goto flush; else if (uh->check) skb_gro_checksum_try_convert(skb, IPPROTO_UDP, inet_gro_compute_pseudo); skip: NAPI_GRO_CB(skb)->is_ipv6 = 0; if (static_branch_unlikely(&udp_encap_needed_key)) sk = udp4_gro_lookup_skb(skb, uh->source, uh->dest); pp = udp_gro_receive(head, skb, uh, sk); return pp; flush: NAPI_GRO_CB(skb)->flush = 1; return NULL; } static int udp_gro_complete_segment(struct sk_buff *skb) { struct udphdr *uh = udp_hdr(skb); skb->csum_start = (unsigned char *)uh - skb->head; skb->csum_offset = offsetof(struct udphdr, check); skb->ip_summed = CHECKSUM_PARTIAL; skb_shinfo(skb)->gso_segs = NAPI_GRO_CB(skb)->count; skb_shinfo(skb)->gso_type |= SKB_GSO_UDP_L4; if (skb->encapsulation) skb->inner_transport_header = skb->transport_header; return 0; } int udp_gro_complete(struct sk_buff *skb, int nhoff, udp_lookup_t lookup) { __be16 newlen = htons(skb->len - nhoff); struct udphdr *uh = (struct udphdr *)(skb->data + nhoff); struct sock *sk; int err; uh->len = newlen; sk = INDIRECT_CALL_INET(lookup, udp6_lib_lookup_skb, udp4_lib_lookup_skb, skb, uh->source, uh->dest); if (sk && udp_sk(sk)->gro_complete) { skb_shinfo(skb)->gso_type = uh->check ? SKB_GSO_UDP_TUNNEL_CSUM : SKB_GSO_UDP_TUNNEL; /* clear the encap mark, so that inner frag_list gro_complete * can take place */ NAPI_GRO_CB(skb)->encap_mark = 0; /* Set encapsulation before calling into inner gro_complete() * functions to make them set up the inner offsets. */ skb->encapsulation = 1; err = udp_sk(sk)->gro_complete(sk, skb, nhoff + sizeof(struct udphdr)); } else { err = udp_gro_complete_segment(skb); } if (skb->remcsum_offload) skb_shinfo(skb)->gso_type |= SKB_GSO_TUNNEL_REMCSUM; return err; } EXPORT_SYMBOL(udp_gro_complete); INDIRECT_CALLABLE_SCOPE int udp4_gro_complete(struct sk_buff *skb, int nhoff) { const u16 offset = NAPI_GRO_CB(skb)->network_offsets[skb->encapsulation]; const struct iphdr *iph = (struct iphdr *)(skb->data + offset); struct udphdr *uh = (struct udphdr *)(skb->data + nhoff); /* do fraglist only if there is no outer UDP encap (or we already processed it) */ if (NAPI_GRO_CB(skb)->is_flist && !NAPI_GRO_CB(skb)->encap_mark) { uh->len = htons(skb->len - nhoff); skb_shinfo(skb)->gso_type |= (SKB_GSO_FRAGLIST|SKB_GSO_UDP_L4); skb_shinfo(skb)->gso_segs = NAPI_GRO_CB(skb)->count; __skb_incr_checksum_unnecessary(skb); return 0; } if (uh->check) uh->check = ~udp_v4_check(skb->len - nhoff, iph->saddr, iph->daddr, 0); return udp_gro_complete(skb, nhoff, udp4_lib_lookup_skb); } int __init udpv4_offload_init(void) { net_hotdata.udpv4_offload = (struct net_offload) { .callbacks = { .gso_segment = udp4_ufo_fragment, .gro_receive = udp4_gro_receive, .gro_complete = udp4_gro_complete, }, }; return inet_add_offload(&net_hotdata.udpv4_offload, IPPROTO_UDP); } |
| 88 3 87 86 62 62 84 87 87 87 69 19 86 1 87 88 88 40 1 1 31 9 40 40 40 40 | 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 | // SPDX-License-Identifier: GPL-2.0-or-later #include <linux/skbuff.h> #include <linux/sctp.h> #include <net/gso.h> #include <net/gro.h> /** * skb_eth_gso_segment - segmentation handler for ethernet protocols. * @skb: buffer to segment * @features: features for the output path (see dev->features) * @type: Ethernet Protocol ID */ struct sk_buff *skb_eth_gso_segment(struct sk_buff *skb, netdev_features_t features, __be16 type) { struct sk_buff *segs = ERR_PTR(-EPROTONOSUPPORT); struct packet_offload *ptype; rcu_read_lock(); list_for_each_entry_rcu(ptype, &net_hotdata.offload_base, list) { if (ptype->type == type && ptype->callbacks.gso_segment) { segs = ptype->callbacks.gso_segment(skb, features); break; } } rcu_read_unlock(); return segs; } EXPORT_SYMBOL(skb_eth_gso_segment); /** * skb_mac_gso_segment - mac layer segmentation handler. * @skb: buffer to segment * @features: features for the output path (see dev->features) */ struct sk_buff *skb_mac_gso_segment(struct sk_buff *skb, netdev_features_t features) { struct sk_buff *segs = ERR_PTR(-EPROTONOSUPPORT); struct packet_offload *ptype; int vlan_depth = skb->mac_len; __be16 type = skb_network_protocol(skb, &vlan_depth); if (unlikely(!type)) return ERR_PTR(-EINVAL); __skb_pull(skb, vlan_depth); rcu_read_lock(); list_for_each_entry_rcu(ptype, &net_hotdata.offload_base, list) { if (ptype->type == type && ptype->callbacks.gso_segment) { segs = ptype->callbacks.gso_segment(skb, features); break; } } rcu_read_unlock(); __skb_push(skb, skb->data - skb_mac_header(skb)); return segs; } EXPORT_SYMBOL(skb_mac_gso_segment); /* openvswitch calls this on rx path, so we need a different check. */ static bool skb_needs_check(const struct sk_buff *skb, bool tx_path) { if (tx_path) return skb->ip_summed != CHECKSUM_PARTIAL && skb->ip_summed != CHECKSUM_UNNECESSARY; return skb->ip_summed == CHECKSUM_NONE; } /** * __skb_gso_segment - Perform segmentation on skb. * @skb: buffer to segment * @features: features for the output path (see dev->features) * @tx_path: whether it is called in TX path * * This function segments the given skb and returns a list of segments. * * It may return NULL if the skb requires no segmentation. This is * only possible when GSO is used for verifying header integrity. * * Segmentation preserves SKB_GSO_CB_OFFSET bytes of previous skb cb. */ struct sk_buff *__skb_gso_segment(struct sk_buff *skb, netdev_features_t features, bool tx_path) { struct sk_buff *segs; if (unlikely(skb_needs_check(skb, tx_path))) { int err; /* We're going to init ->check field in TCP or UDP header */ err = skb_cow_head(skb, 0); if (err < 0) return ERR_PTR(err); } /* Only report GSO partial support if it will enable us to * support segmentation on this frame without needing additional * work. */ if (features & NETIF_F_GSO_PARTIAL) { netdev_features_t partial_features = NETIF_F_GSO_ROBUST; struct net_device *dev = skb->dev; partial_features |= dev->features & dev->gso_partial_features; if (!skb_gso_ok(skb, features | partial_features)) features &= ~NETIF_F_GSO_PARTIAL; } BUILD_BUG_ON(SKB_GSO_CB_OFFSET + sizeof(*SKB_GSO_CB(skb)) > sizeof(skb->cb)); SKB_GSO_CB(skb)->mac_offset = skb_headroom(skb); SKB_GSO_CB(skb)->encap_level = 0; skb_reset_mac_header(skb); skb_reset_mac_len(skb); segs = skb_mac_gso_segment(skb, features); if (segs != skb && unlikely(skb_needs_check(skb, tx_path) && !IS_ERR(segs))) skb_warn_bad_offload(skb); return segs; } EXPORT_SYMBOL(__skb_gso_segment); /** * skb_gso_transport_seglen - Return length of individual segments of a gso packet * * @skb: GSO skb * * skb_gso_transport_seglen is used to determine the real size of the * individual segments, including Layer4 headers (TCP/UDP). * * The MAC/L2 or network (IP, IPv6) headers are not accounted for. */ static unsigned int skb_gso_transport_seglen(const struct sk_buff *skb) { const struct skb_shared_info *shinfo = skb_shinfo(skb); unsigned int thlen = 0; if (skb->encapsulation) { thlen = skb_inner_transport_header(skb) - skb_transport_header(skb); if (likely(shinfo->gso_type & (SKB_GSO_TCPV4 | SKB_GSO_TCPV6))) thlen += inner_tcp_hdrlen(skb); } else if (likely(shinfo->gso_type & (SKB_GSO_TCPV4 | SKB_GSO_TCPV6))) { thlen = tcp_hdrlen(skb); } else if (unlikely(skb_is_gso_sctp(skb))) { thlen = sizeof(struct sctphdr); } else if (shinfo->gso_type & SKB_GSO_UDP_L4) { thlen = sizeof(struct udphdr); } /* UFO sets gso_size to the size of the fragmentation * payload, i.e. the size of the L4 (UDP) header is already * accounted for. */ return thlen + shinfo->gso_size; } /** * skb_gso_network_seglen - Return length of individual segments of a gso packet * * @skb: GSO skb * * skb_gso_network_seglen is used to determine the real size of the * individual segments, including Layer3 (IP, IPv6) and L4 headers (TCP/UDP). * * The MAC/L2 header is not accounted for. */ static unsigned int skb_gso_network_seglen(const struct sk_buff *skb) { unsigned int hdr_len = skb_transport_header(skb) - skb_network_header(skb); return hdr_len + skb_gso_transport_seglen(skb); } /** * skb_gso_mac_seglen - Return length of individual segments of a gso packet * * @skb: GSO skb * * skb_gso_mac_seglen is used to determine the real size of the * individual segments, including MAC/L2, Layer3 (IP, IPv6) and L4 * headers (TCP/UDP). */ static unsigned int skb_gso_mac_seglen(const struct sk_buff *skb) { unsigned int hdr_len = skb_transport_header(skb) - skb_mac_header(skb); return hdr_len + skb_gso_transport_seglen(skb); } /** * skb_gso_size_check - check the skb size, considering GSO_BY_FRAGS * * There are a couple of instances where we have a GSO skb, and we * want to determine what size it would be after it is segmented. * * We might want to check: * - L3+L4+payload size (e.g. IP forwarding) * - L2+L3+L4+payload size (e.g. sanity check before passing to driver) * * This is a helper to do that correctly considering GSO_BY_FRAGS. * * @skb: GSO skb * * @seg_len: The segmented length (from skb_gso_*_seglen). In the * GSO_BY_FRAGS case this will be [header sizes + GSO_BY_FRAGS]. * * @max_len: The maximum permissible length. * * Returns true if the segmented length <= max length. */ static inline bool skb_gso_size_check(const struct sk_buff *skb, unsigned int seg_len, unsigned int max_len) { const struct skb_shared_info *shinfo = skb_shinfo(skb); const struct sk_buff *iter; if (shinfo->gso_size != GSO_BY_FRAGS) return seg_len <= max_len; /* Undo this so we can re-use header sizes */ seg_len -= GSO_BY_FRAGS; skb_walk_frags(skb, iter) { if (seg_len + skb_headlen(iter) > max_len) return false; } return true; } /** * skb_gso_validate_network_len - Will a split GSO skb fit into a given MTU? * * @skb: GSO skb * @mtu: MTU to validate against * * skb_gso_validate_network_len validates if a given skb will fit a * wanted MTU once split. It considers L3 headers, L4 headers, and the * payload. */ bool skb_gso_validate_network_len(const struct sk_buff *skb, unsigned int mtu) { return skb_gso_size_check(skb, skb_gso_network_seglen(skb), mtu); } EXPORT_SYMBOL_GPL(skb_gso_validate_network_len); /** * skb_gso_validate_mac_len - Will a split GSO skb fit in a given length? * * @skb: GSO skb * @len: length to validate against * * skb_gso_validate_mac_len validates if a given skb will fit a wanted * length once split, including L2, L3 and L4 headers and the payload. */ bool skb_gso_validate_mac_len(const struct sk_buff *skb, unsigned int len) { return skb_gso_size_check(skb, skb_gso_mac_seglen(skb), len); } EXPORT_SYMBOL_GPL(skb_gso_validate_mac_len); |
| 3 8 5 1 1 1 3 3 3 3 3 12 11 1 5 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 | /* * llc_station.c - station component of LLC * * Copyright (c) 1997 by Procom Technology, Inc. * 2001-2003 by Arnaldo Carvalho de Melo <acme@conectiva.com.br> * * This program can be redistributed or modified under the terms of the * GNU General Public License as published by the Free Software Foundation. * This program is distributed without any warranty or implied warranty * of merchantability or fitness for a particular purpose. * * See the GNU General Public License for more details. */ #include <linux/init.h> #include <linux/module.h> #include <linux/slab.h> #include <net/llc.h> #include <net/llc_sap.h> #include <net/llc_conn.h> #include <net/llc_c_ac.h> #include <net/llc_s_ac.h> #include <net/llc_c_ev.h> #include <net/llc_c_st.h> #include <net/llc_s_ev.h> #include <net/llc_s_st.h> #include <net/llc_pdu.h> static int llc_stat_ev_rx_null_dsap_xid_c(struct sk_buff *skb) { struct llc_pdu_un *pdu = llc_pdu_un_hdr(skb); return LLC_PDU_IS_CMD(pdu) && /* command PDU */ LLC_PDU_TYPE_IS_U(pdu) && /* U type PDU */ LLC_U_PDU_CMD(pdu) == LLC_1_PDU_CMD_XID && !pdu->dsap; /* NULL DSAP value */ } static int llc_stat_ev_rx_null_dsap_test_c(struct sk_buff *skb) { struct llc_pdu_un *pdu = llc_pdu_un_hdr(skb); return LLC_PDU_IS_CMD(pdu) && /* command PDU */ LLC_PDU_TYPE_IS_U(pdu) && /* U type PDU */ LLC_U_PDU_CMD(pdu) == LLC_1_PDU_CMD_TEST && !pdu->dsap; /* NULL DSAP */ } static int llc_station_ac_send_xid_r(struct sk_buff *skb) { u8 mac_da[ETH_ALEN], dsap; int rc = 1; struct sk_buff *nskb = llc_alloc_frame(NULL, skb->dev, LLC_PDU_TYPE_U, sizeof(struct llc_xid_info)); if (!nskb) goto out; llc_pdu_decode_sa(skb, mac_da); llc_pdu_decode_ssap(skb, &dsap); llc_pdu_header_init(nskb, LLC_PDU_TYPE_U, 0, dsap, LLC_PDU_RSP); llc_pdu_init_as_xid_rsp(nskb, LLC_XID_NULL_CLASS_2, 127); rc = llc_mac_hdr_init(nskb, skb->dev->dev_addr, mac_da); if (unlikely(rc)) goto free; dev_queue_xmit(nskb); out: return rc; free: kfree_skb(nskb); goto out; } static int llc_station_ac_send_test_r(struct sk_buff *skb) { u8 mac_da[ETH_ALEN], dsap; int rc = 1; u32 data_size; struct sk_buff *nskb; if (skb->mac_len < ETH_HLEN) goto out; /* The test request command is type U (llc_len = 3) */ data_size = ntohs(eth_hdr(skb)->h_proto) - 3; nskb = llc_alloc_frame(NULL, skb->dev, LLC_PDU_TYPE_U, data_size); if (!nskb) goto out; llc_pdu_decode_sa(skb, mac_da); llc_pdu_decode_ssap(skb, &dsap); llc_pdu_header_init(nskb, LLC_PDU_TYPE_U, 0, dsap, LLC_PDU_RSP); llc_pdu_init_as_test_rsp(nskb, skb); rc = llc_mac_hdr_init(nskb, skb->dev->dev_addr, mac_da); if (unlikely(rc)) goto free; dev_queue_xmit(nskb); out: return rc; free: kfree_skb(nskb); goto out; } /** * llc_station_rcv - send received pdu to the station state machine * @skb: received frame. * * Sends data unit to station state machine. */ static void llc_station_rcv(struct sk_buff *skb) { if (llc_stat_ev_rx_null_dsap_xid_c(skb)) llc_station_ac_send_xid_r(skb); else if (llc_stat_ev_rx_null_dsap_test_c(skb)) llc_station_ac_send_test_r(skb); kfree_skb(skb); } void __init llc_station_init(void) { llc_set_station_handler(llc_station_rcv); } void llc_station_exit(void) { llc_set_station_handler(NULL); } |
| 33 33 33 33 4 4 4 4 30 | 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 | // SPDX-License-Identifier: GPL-2.0-only /* L2TP core. * * Copyright (c) 2008,2009,2010 Katalix Systems Ltd * * This file contains some code of the original L2TPv2 pppol2tp * driver, which has the following copyright: * * Authors: Martijn van Oosterhout <kleptog@svana.org> * James Chapman (jchapman@katalix.com) * Contributors: * Michal Ostrowski <mostrows@speakeasy.net> * Arnaldo Carvalho de Melo <acme@xconectiva.com.br> * David S. Miller (davem@redhat.com) */ #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt #include <linux/module.h> #include <linux/string.h> #include <linux/list.h> #include <linux/rculist.h> #include <linux/uaccess.h> #include <linux/kernel.h> #include <linux/spinlock.h> #include <linux/kthread.h> #include <linux/sched.h> #include <linux/slab.h> #include <linux/errno.h> #include <linux/jiffies.h> #include <linux/netdevice.h> #include <linux/net.h> #include <linux/inetdevice.h> #include <linux/skbuff.h> #include <linux/init.h> #include <linux/in.h> #include <linux/ip.h> #include <linux/udp.h> #include <linux/l2tp.h> #include <linux/sort.h> #include <linux/file.h> #include <linux/nsproxy.h> #include <net/net_namespace.h> #include <net/netns/generic.h> #include <net/dst.h> #include <net/ip.h> #include <net/udp.h> #include <net/udp_tunnel.h> #include <net/inet_common.h> #include <net/xfrm.h> #include <net/protocol.h> #include <net/inet6_connection_sock.h> #include <net/inet_ecn.h> #include <net/ip6_route.h> #include <net/ip6_checksum.h> #include <asm/byteorder.h> #include <linux/atomic.h> #include "l2tp_core.h" #define CREATE_TRACE_POINTS #include "trace.h" #define L2TP_DRV_VERSION "V2.0" /* L2TP header constants */ #define L2TP_HDRFLAG_T 0x8000 #define L2TP_HDRFLAG_L 0x4000 #define L2TP_HDRFLAG_S 0x0800 #define L2TP_HDRFLAG_O 0x0200 #define L2TP_HDRFLAG_P 0x0100 #define L2TP_HDR_VER_MASK 0x000F #define L2TP_HDR_VER_2 0x0002 #define L2TP_HDR_VER_3 0x0003 /* L2TPv3 default L2-specific sublayer */ #define L2TP_SLFLAG_S 0x40000000 #define L2TP_SL_SEQ_MASK 0x00ffffff #define L2TP_HDR_SIZE_MAX 14 /* Default trace flags */ #define L2TP_DEFAULT_DEBUG_FLAGS 0 #define L2TP_DEPTH_NESTING 2 #if L2TP_DEPTH_NESTING == SINGLE_DEPTH_NESTING #error "L2TP requires its own lockdep subclass" #endif /* Private data stored for received packets in the skb. */ struct l2tp_skb_cb { u32 ns; u16 has_seq; u16 length; unsigned long expires; }; #define L2TP_SKB_CB(skb) ((struct l2tp_skb_cb *)&(skb)->cb[sizeof(struct inet_skb_parm)]) static struct workqueue_struct *l2tp_wq; /* per-net private data for this module */ static unsigned int l2tp_net_id; struct l2tp_net { /* Lock for write access to l2tp_tunnel_idr */ spinlock_t l2tp_tunnel_idr_lock; struct idr l2tp_tunnel_idr; /* Lock for write access to l2tp_v[23]_session_idr/htable */ spinlock_t l2tp_session_idr_lock; struct idr l2tp_v2_session_idr; struct idr l2tp_v3_session_idr; struct hlist_head l2tp_v3_session_htable[16]; }; static u32 l2tp_v2_session_key(u16 tunnel_id, u16 session_id) { return ((u32)tunnel_id) << 16 | session_id; } static unsigned long l2tp_v3_session_hashkey(struct sock *sk, u32 session_id) { return ((unsigned long)sk) + session_id; } #if IS_ENABLED(CONFIG_IPV6) static bool l2tp_sk_is_v6(struct sock *sk) { return sk->sk_family == PF_INET6 && !ipv6_addr_v4mapped(&sk->sk_v6_daddr); } #endif static struct l2tp_net *l2tp_pernet(const struct net *net) { return net_generic(net, l2tp_net_id); } static void l2tp_tunnel_free(struct l2tp_tunnel *tunnel) { struct sock *sk = tunnel->sock; trace_free_tunnel(tunnel); if (sk) { /* Disable udp encapsulation */ switch (tunnel->encap) { case L2TP_ENCAPTYPE_UDP: /* No longer an encapsulation socket. See net/ipv4/udp.c */ WRITE_ONCE(udp_sk(sk)->encap_type, 0); udp_sk(sk)->encap_rcv = NULL; udp_sk(sk)->encap_destroy = NULL; break; case L2TP_ENCAPTYPE_IP: break; } tunnel->sock = NULL; sock_put(sk); } kfree_rcu(tunnel, rcu); } static void l2tp_session_free(struct l2tp_session *session) { trace_free_session(session); if (session->tunnel) l2tp_tunnel_put(session->tunnel); kfree_rcu(session, rcu); } struct l2tp_tunnel *l2tp_sk_to_tunnel(const struct sock *sk) { const struct net *net = sock_net(sk); unsigned long tunnel_id, tmp; struct l2tp_tunnel *tunnel; struct l2tp_net *pn; rcu_read_lock_bh(); pn = l2tp_pernet(net); idr_for_each_entry_ul(&pn->l2tp_tunnel_idr, tunnel, tmp, tunnel_id) { if (tunnel && tunnel->sock == sk && refcount_inc_not_zero(&tunnel->ref_count)) { rcu_read_unlock_bh(); return tunnel; } } rcu_read_unlock_bh(); return NULL; } EXPORT_SYMBOL_GPL(l2tp_sk_to_tunnel); void l2tp_tunnel_put(struct l2tp_tunnel *tunnel) { if (refcount_dec_and_test(&tunnel->ref_count)) l2tp_tunnel_free(tunnel); } EXPORT_SYMBOL_GPL(l2tp_tunnel_put); void l2tp_session_put(struct l2tp_session *session) { if (refcount_dec_and_test(&session->ref_count)) l2tp_session_free(session); } EXPORT_SYMBOL_GPL(l2tp_session_put); /* Lookup a tunnel. A new reference is held on the returned tunnel. */ struct l2tp_tunnel *l2tp_tunnel_get(const struct net *net, u32 tunnel_id) { const struct l2tp_net *pn = l2tp_pernet(net); struct l2tp_tunnel *tunnel; rcu_read_lock_bh(); tunnel = idr_find(&pn->l2tp_tunnel_idr, tunnel_id); if (tunnel && refcount_inc_not_zero(&tunnel->ref_count)) { rcu_read_unlock_bh(); return tunnel; } rcu_read_unlock_bh(); return NULL; } EXPORT_SYMBOL_GPL(l2tp_tunnel_get); struct l2tp_tunnel *l2tp_tunnel_get_next(const struct net *net, unsigned long *key) { struct l2tp_net *pn = l2tp_pernet(net); struct l2tp_tunnel *tunnel = NULL; rcu_read_lock_bh(); again: tunnel = idr_get_next_ul(&pn->l2tp_tunnel_idr, key); if (tunnel) { if (refcount_inc_not_zero(&tunnel->ref_count)) { rcu_read_unlock_bh(); return tunnel; } (*key)++; goto again; } rcu_read_unlock_bh(); return NULL; } EXPORT_SYMBOL_GPL(l2tp_tunnel_get_next); struct l2tp_session *l2tp_v3_session_get(const struct net *net, struct sock *sk, u32 session_id) { const struct l2tp_net *pn = l2tp_pernet(net); struct l2tp_session *session; rcu_read_lock_bh(); session = idr_find(&pn->l2tp_v3_session_idr, session_id); if (session && !hash_hashed(&session->hlist) && refcount_inc_not_zero(&session->ref_count)) { rcu_read_unlock_bh(); return session; } /* If we get here and session is non-NULL, the session_id * collides with one in another tunnel. If sk is non-NULL, * find the session matching sk. */ if (session && sk) { unsigned long key = l2tp_v3_session_hashkey(sk, session->session_id); hash_for_each_possible_rcu(pn->l2tp_v3_session_htable, session, hlist, key) { /* session->tunnel may be NULL if another thread is in * l2tp_session_register and has added an item to * l2tp_v3_session_htable but hasn't yet added the * session to its tunnel's session_list. */ struct l2tp_tunnel *tunnel = READ_ONCE(session->tunnel); if (session->session_id == session_id && tunnel && tunnel->sock == sk && refcount_inc_not_zero(&session->ref_count)) { rcu_read_unlock_bh(); return session; } } } rcu_read_unlock_bh(); return NULL; } EXPORT_SYMBOL_GPL(l2tp_v3_session_get); struct l2tp_session *l2tp_v2_session_get(const struct net *net, u16 tunnel_id, u16 session_id) { u32 session_key = l2tp_v2_session_key(tunnel_id, session_id); const struct l2tp_net *pn = l2tp_pernet(net); struct l2tp_session *session; rcu_read_lock_bh(); session = idr_find(&pn->l2tp_v2_session_idr, session_key); if (session && refcount_inc_not_zero(&session->ref_count)) { rcu_read_unlock_bh(); return session; } rcu_read_unlock_bh(); return NULL; } EXPORT_SYMBOL_GPL(l2tp_v2_session_get); struct l2tp_session *l2tp_session_get(const struct net *net, struct sock *sk, int pver, u32 tunnel_id, u32 session_id) { if (pver == L2TP_HDR_VER_2) return l2tp_v2_session_get(net, tunnel_id, session_id); else return l2tp_v3_session_get(net, sk, session_id); } EXPORT_SYMBOL_GPL(l2tp_session_get); static struct l2tp_session *l2tp_v2_session_get_next(const struct net *net, u16 tid, unsigned long *key) { struct l2tp_net *pn = l2tp_pernet(net); struct l2tp_session *session = NULL; /* Start searching within the range of the tid */ if (*key == 0) *key = l2tp_v2_session_key(tid, 0); rcu_read_lock_bh(); again: session = idr_get_next_ul(&pn->l2tp_v2_session_idr, key); if (session) { struct l2tp_tunnel *tunnel = READ_ONCE(session->tunnel); /* ignore sessions with id 0 as they are internal for pppol2tp */ if (session->session_id == 0) { (*key)++; goto again; } if (tunnel->tunnel_id == tid && refcount_inc_not_zero(&session->ref_count)) { rcu_read_unlock_bh(); return session; } (*key)++; if (tunnel->tunnel_id == tid) goto again; } rcu_read_unlock_bh(); return NULL; } static struct l2tp_session *l2tp_v3_session_get_next(const struct net *net, u32 tid, struct sock *sk, unsigned long *key) { struct l2tp_net *pn = l2tp_pernet(net); struct l2tp_session *session = NULL; rcu_read_lock_bh(); again: session = idr_get_next_ul(&pn->l2tp_v3_session_idr, key); if (session && !hash_hashed(&session->hlist)) { struct l2tp_tunnel *tunnel = READ_ONCE(session->tunnel); if (tunnel && tunnel->tunnel_id == tid && refcount_inc_not_zero(&session->ref_count)) { rcu_read_unlock_bh(); return session; } (*key)++; goto again; } /* If we get here and session is non-NULL, the IDR entry may be one * where the session_id collides with one in another tunnel. Check * session_htable for a match. There can only be one session of a given * ID per tunnel so we can return as soon as a match is found. */ if (session && hash_hashed(&session->hlist)) { unsigned long hkey = l2tp_v3_session_hashkey(sk, session->session_id); u32 sid = session->session_id; hash_for_each_possible_rcu(pn->l2tp_v3_session_htable, session, hlist, hkey) { struct l2tp_tunnel *tunnel = READ_ONCE(session->tunnel); if (session->session_id == sid && tunnel && tunnel->tunnel_id == tid && refcount_inc_not_zero(&session->ref_count)) { rcu_read_unlock_bh(); return session; } } /* If no match found, the colliding session ID isn't in our * tunnel so try the next session ID. */ (*key)++; goto again; } rcu_read_unlock_bh(); return NULL; } struct l2tp_session *l2tp_session_get_next(const struct net *net, struct sock *sk, int pver, u32 tunnel_id, unsigned long *key) { if (pver == L2TP_HDR_VER_2) return l2tp_v2_session_get_next(net, tunnel_id, key); else return l2tp_v3_session_get_next(net, tunnel_id, sk, key); } EXPORT_SYMBOL_GPL(l2tp_session_get_next); /* Lookup a session by interface name. * This is very inefficient but is only used by management interfaces. */ struct l2tp_session *l2tp_session_get_by_ifname(const struct net *net, const char *ifname) { struct l2tp_net *pn = l2tp_pernet(net); unsigned long tunnel_id, tmp; struct l2tp_session *session; struct l2tp_tunnel *tunnel; rcu_read_lock_bh(); idr_for_each_entry_ul(&pn->l2tp_tunnel_idr, tunnel, tmp, tunnel_id) { if (tunnel) { list_for_each_entry_rcu(session, &tunnel->session_list, list) { if (!strcmp(session->ifname, ifname)) { refcount_inc(&session->ref_count); rcu_read_unlock_bh(); return session; } } } } rcu_read_unlock_bh(); return NULL; } EXPORT_SYMBOL_GPL(l2tp_session_get_by_ifname); static void l2tp_session_coll_list_add(struct l2tp_session_coll_list *clist, struct l2tp_session *session) { refcount_inc(&session->ref_count); WARN_ON_ONCE(session->coll_list); session->coll_list = clist; spin_lock(&clist->lock); list_add(&session->clist, &clist->list); spin_unlock(&clist->lock); } static int l2tp_session_collision_add(struct l2tp_net *pn, struct l2tp_session *session1, struct l2tp_session *session2) { struct l2tp_session_coll_list *clist; lockdep_assert_held(&pn->l2tp_session_idr_lock); if (!session2) return -EEXIST; /* If existing session is in IP-encap tunnel, refuse new session */ if (session2->tunnel->encap == L2TP_ENCAPTYPE_IP) return -EEXIST; clist = session2->coll_list; if (!clist) { /* First collision. Allocate list to manage the collided sessions * and add the existing session to the list. */ clist = kmalloc(sizeof(*clist), GFP_ATOMIC); if (!clist) return -ENOMEM; spin_lock_init(&clist->lock); INIT_LIST_HEAD(&clist->list); refcount_set(&clist->ref_count, 1); l2tp_session_coll_list_add(clist, session2); } /* If existing session isn't already in the session hlist, add it. */ if (!hash_hashed(&session2->hlist)) hash_add_rcu(pn->l2tp_v3_session_htable, &session2->hlist, session2->hlist_key); /* Add new session to the hlist and collision list */ hash_add_rcu(pn->l2tp_v3_session_htable, &session1->hlist, session1->hlist_key); refcount_inc(&clist->ref_count); l2tp_session_coll_list_add(clist, session1); return 0; } static void l2tp_session_collision_del(struct l2tp_net *pn, struct l2tp_session *session) { struct l2tp_session_coll_list *clist = session->coll_list; unsigned long session_key = session->session_id; struct l2tp_session *session2; lockdep_assert_held(&pn->l2tp_session_idr_lock); hash_del_rcu(&session->hlist); if (clist) { /* Remove session from its collision list. If there * are other sessions with the same ID, replace this * session's IDR entry with that session, otherwise * remove the IDR entry. If this is the last session, * the collision list data is freed. */ spin_lock(&clist->lock); list_del_init(&session->clist); session2 = list_first_entry_or_null(&clist->list, struct l2tp_session, clist); if (session2) { void *old = idr_replace(&pn->l2tp_v3_session_idr, session2, session_key); WARN_ON_ONCE(IS_ERR_VALUE(old)); } else { void *removed = idr_remove(&pn->l2tp_v3_session_idr, session_key); WARN_ON_ONCE(removed != session); } session->coll_list = NULL; spin_unlock(&clist->lock); if (refcount_dec_and_test(&clist->ref_count)) kfree(clist); l2tp_session_put(session); } } int l2tp_session_register(struct l2tp_session *session, struct l2tp_tunnel *tunnel) { struct l2tp_net *pn = l2tp_pernet(tunnel->l2tp_net); struct l2tp_session *other_session = NULL; void *old = NULL; u32 session_key; int err; spin_lock_bh(&tunnel->list_lock); spin_lock_bh(&pn->l2tp_session_idr_lock); if (!tunnel->acpt_newsess) { err = -ENODEV; goto out; } if (tunnel->version == L2TP_HDR_VER_3) { session_key = session->session_id; err = idr_alloc_u32(&pn->l2tp_v3_session_idr, NULL, &session_key, session_key, GFP_ATOMIC); /* IP encap expects session IDs to be globally unique, while * UDP encap doesn't. This isn't per the RFC, which says that * sessions are identified only by the session ID, but is to * support existing userspace which depends on it. */ if (err == -ENOSPC && tunnel->encap == L2TP_ENCAPTYPE_UDP) { other_session = idr_find(&pn->l2tp_v3_session_idr, session_key); err = l2tp_session_collision_add(pn, session, other_session); } } else { session_key = l2tp_v2_session_key(tunnel->tunnel_id, session->session_id); err = idr_alloc_u32(&pn->l2tp_v2_session_idr, NULL, &session_key, session_key, GFP_ATOMIC); } if (err) { if (err == -ENOSPC) err = -EEXIST; goto out; } refcount_inc(&tunnel->ref_count); WRITE_ONCE(session->tunnel, tunnel); list_add_rcu(&session->list, &tunnel->session_list); /* this makes session available to lockless getters */ if (tunnel->version == L2TP_HDR_VER_3) { if (!other_session) old = idr_replace(&pn->l2tp_v3_session_idr, session, session_key); } else { old = idr_replace(&pn->l2tp_v2_session_idr, session, session_key); } /* old should be NULL, unless something removed or modified * the IDR entry after our idr_alloc_32 above (which shouldn't * happen). */ WARN_ON_ONCE(old); out: spin_unlock_bh(&pn->l2tp_session_idr_lock); spin_unlock_bh(&tunnel->list_lock); if (!err) trace_register_session(session); return err; } EXPORT_SYMBOL_GPL(l2tp_session_register); /***************************************************************************** * Receive data handling *****************************************************************************/ /* Queue a skb in order. We come here only if the skb has an L2TP sequence * number. */ static void l2tp_recv_queue_skb(struct l2tp_session *session, struct sk_buff *skb) { struct sk_buff *skbp; struct sk_buff *tmp; u32 ns = L2TP_SKB_CB(skb)->ns; spin_lock_bh(&session->reorder_q.lock); skb_queue_walk_safe(&session->reorder_q, skbp, tmp) { if (L2TP_SKB_CB(skbp)->ns > ns) { __skb_queue_before(&session->reorder_q, skbp, skb); atomic_long_inc(&session->stats.rx_oos_packets); goto out; } } __skb_queue_tail(&session->reorder_q, skb); out: spin_unlock_bh(&session->reorder_q.lock); } /* Dequeue a single skb. */ static void l2tp_recv_dequeue_skb(struct l2tp_session *session, struct sk_buff *skb) { struct l2tp_tunnel *tunnel = session->tunnel; int length = L2TP_SKB_CB(skb)->length; /* We're about to requeue the skb, so return resources * to its current owner (a socket receive buffer). */ skb_orphan(skb); atomic_long_inc(&tunnel->stats.rx_packets); atomic_long_add(length, &tunnel->stats.rx_bytes); atomic_long_inc(&session->stats.rx_packets); atomic_long_add(length, &session->stats.rx_bytes); if (L2TP_SKB_CB(skb)->has_seq) { /* Bump our Nr */ session->nr++; session->nr &= session->nr_max; trace_session_seqnum_update(session); } /* call private receive handler */ if (session->recv_skb) (*session->recv_skb)(session, skb, L2TP_SKB_CB(skb)->length); else kfree_skb(skb); } /* Dequeue skbs from the session's reorder_q, subject to packet order. * Skbs that have been in the queue for too long are simply discarded. */ static void l2tp_recv_dequeue(struct l2tp_session *session) { struct sk_buff *skb; struct sk_buff *tmp; /* If the pkt at the head of the queue has the nr that we * expect to send up next, dequeue it and any other * in-sequence packets behind it. */ start: spin_lock_bh(&session->reorder_q.lock); skb_queue_walk_safe(&session->reorder_q, skb, tmp) { struct l2tp_skb_cb *cb = L2TP_SKB_CB(skb); /* If the packet has been pending on the queue for too long, discard it */ if (time_after(jiffies, cb->expires)) { atomic_long_inc(&session->stats.rx_seq_discards); atomic_long_inc(&session->stats.rx_errors); trace_session_pkt_expired(session, cb->ns); session->reorder_skip = 1; __skb_unlink(skb, &session->reorder_q); kfree_skb(skb); continue; } if (cb->has_seq) { if (session->reorder_skip) { session->reorder_skip = 0; session->nr = cb->ns; trace_session_seqnum_reset(session); } if (cb->ns != session->nr) goto out; } __skb_unlink(skb, &session->reorder_q); /* Process the skb. We release the queue lock while we * do so to let other contexts process the queue. */ spin_unlock_bh(&session->reorder_q.lock); l2tp_recv_dequeue_skb(session, skb); goto start; } out: spin_unlock_bh(&session->reorder_q.lock); } static int l2tp_seq_check_rx_window(struct l2tp_session *session, u32 nr) { u32 nws; if (nr >= session->nr) nws = nr - session->nr; else nws = (session->nr_max + 1) - (session->nr - nr); return nws < session->nr_window_size; } /* If packet has sequence numbers, queue it if acceptable. Returns 0 if * acceptable, else non-zero. */ static int l2tp_recv_data_seq(struct l2tp_session *session, struct sk_buff *skb) { struct l2tp_skb_cb *cb = L2TP_SKB_CB(skb); if (!l2tp_seq_check_rx_window(session, cb->ns)) { /* Packet sequence number is outside allowed window. * Discard it. */ trace_session_pkt_outside_rx_window(session, cb->ns); goto discard; } if (session->reorder_timeout != 0) { /* Packet reordering enabled. Add skb to session's * reorder queue, in order of ns. */ l2tp_recv_queue_skb(session, skb); goto out; } /* Packet reordering disabled. Discard out-of-sequence packets, while * tracking the number if in-sequence packets after the first OOS packet * is seen. After nr_oos_count_max in-sequence packets, reset the * sequence number to re-enable packet reception. */ if (cb->ns == session->nr) { skb_queue_tail(&session->reorder_q, skb); } else { u32 nr_oos = cb->ns; u32 nr_next = (session->nr_oos + 1) & session->nr_max; if (nr_oos == nr_next) session->nr_oos_count++; else session->nr_oos_count = 0; session->nr_oos = nr_oos; if (session->nr_oos_count > session->nr_oos_count_max) { session->reorder_skip = 1; } if (!session->reorder_skip) { atomic_long_inc(&session->stats.rx_seq_discards); trace_session_pkt_oos(session, cb->ns); goto discard; } skb_queue_tail(&session->reorder_q, skb); } out: return 0; discard: return 1; } /* Do receive processing of L2TP data frames. We handle both L2TPv2 * and L2TPv3 data frames here. * * L2TPv2 Data Message Header * * 0 1 2 3 * 0 1 2 3 4 5 6 7 8 9 0 1 2 3 4 5 6 7 8 9 0 1 2 3 4 5 6 7 8 9 0 1 * +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ * |T|L|x|x|S|x|O|P|x|x|x|x| Ver | Length (opt) | * +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ * | Tunnel ID | Session ID | * +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ * | Ns (opt) | Nr (opt) | * +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ * | Offset Size (opt) | Offset pad... (opt) * +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ * * Data frames are marked by T=0. All other fields are the same as * those in L2TP control frames. * * L2TPv3 Data Message Header * * +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ * | L2TP Session Header | * +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ * | L2-Specific Sublayer | * +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ * | Tunnel Payload ... * +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ * * L2TPv3 Session Header Over IP * * 0 1 2 3 * 0 1 2 3 4 5 6 7 8 9 0 1 2 3 4 5 6 7 8 9 0 1 2 3 4 5 6 7 8 9 0 1 * +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ * | Session ID | * +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ * | Cookie (optional, maximum 64 bits)... * +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ * | * +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ * * L2TPv3 L2-Specific Sublayer Format * * 0 1 2 3 * 0 1 2 3 4 5 6 7 8 9 0 1 2 3 4 5 6 7 8 9 0 1 2 3 4 5 6 7 8 9 0 1 * +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ * |x|S|x|x|x|x|x|x| Sequence Number | * +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ * * Cookie value and sublayer format are negotiated with the peer when * the session is set up. Unlike L2TPv2, we do not need to parse the * packet header to determine if optional fields are present. * * Caller must already have parsed the frame and determined that it is * a data (not control) frame before coming here. Fields up to the * session-id have already been parsed and ptr points to the data * after the session-id. */ void l2tp_recv_common(struct l2tp_session *session, struct sk_buff *skb, unsigned char *ptr, unsigned char *optr, u16 hdrflags, int length) { struct l2tp_tunnel *tunnel = session->tunnel; int offset; /* Parse and check optional cookie */ if (session->peer_cookie_len > 0) { if (memcmp(ptr, &session->peer_cookie[0], session->peer_cookie_len)) { pr_debug_ratelimited("%s: cookie mismatch (%u/%u). Discarding.\n", tunnel->name, tunnel->tunnel_id, session->session_id); atomic_long_inc(&session->stats.rx_cookie_discards); goto discard; } ptr += session->peer_cookie_len; } /* Handle the optional sequence numbers. Sequence numbers are * in different places for L2TPv2 and L2TPv3. * * If we are the LAC, enable/disable sequence numbers under * the control of the LNS. If no sequence numbers present but * we were expecting them, discard frame. */ L2TP_SKB_CB(skb)->has_seq = 0; if (tunnel->version == L2TP_HDR_VER_2) { if (hdrflags & L2TP_HDRFLAG_S) { /* Store L2TP info in the skb */ L2TP_SKB_CB(skb)->ns = ntohs(*(__be16 *)ptr); L2TP_SKB_CB(skb)->has_seq = 1; ptr += 2; /* Skip past nr in the header */ ptr += 2; } } else if (session->l2specific_type == L2TP_L2SPECTYPE_DEFAULT) { u32 l2h = ntohl(*(__be32 *)ptr); if (l2h & 0x40000000) { /* Store L2TP info in the skb */ L2TP_SKB_CB(skb)->ns = l2h & 0x00ffffff; L2TP_SKB_CB(skb)->has_seq = 1; } ptr += 4; } if (L2TP_SKB_CB(skb)->has_seq) { /* Received a packet with sequence numbers. If we're the LAC, * check if we sre sending sequence numbers and if not, * configure it so. */ if (!session->lns_mode && !session->send_seq) { trace_session_seqnum_lns_enable(session); session->send_seq = 1; l2tp_session_set_header_len(session, tunnel->version, tunnel->encap); } } else { /* No sequence numbers. * If user has configured mandatory sequence numbers, discard. */ if (session->recv_seq) { pr_debug_ratelimited("%s: recv data has no seq numbers when required. Discarding.\n", session->name); atomic_long_inc(&session->stats.rx_seq_discards); goto discard; } /* If we're the LAC and we're sending sequence numbers, the * LNS has requested that we no longer send sequence numbers. * If we're the LNS and we're sending sequence numbers, the * LAC is broken. Discard the frame. */ if (!session->lns_mode && session->send_seq) { trace_session_seqnum_lns_disable(session); session->send_seq = 0; l2tp_session_set_header_len(session, tunnel->version, tunnel->encap); } else if (session->send_seq) { pr_debug_ratelimited("%s: recv data has no seq numbers when required. Discarding.\n", session->name); atomic_long_inc(&session->stats.rx_seq_discards); goto discard; } } /* Session data offset is defined only for L2TPv2 and is * indicated by an optional 16-bit value in the header. */ if (tunnel->version == L2TP_HDR_VER_2) { /* If offset bit set, skip it. */ if (hdrflags & L2TP_HDRFLAG_O) { offset = ntohs(*(__be16 *)ptr); ptr += 2 + offset; } } offset = ptr - optr; if (!pskb_may_pull(skb, offset)) goto discard; __skb_pull(skb, offset); /* Prepare skb for adding to the session's reorder_q. Hold * packets for max reorder_timeout or 1 second if not * reordering. */ L2TP_SKB_CB(skb)->length = length; L2TP_SKB_CB(skb)->expires = jiffies + (session->reorder_timeout ? session->reorder_timeout : HZ); /* Add packet to the session's receive queue. Reordering is done here, if * enabled. Saved L2TP protocol info is stored in skb->sb[]. */ if (L2TP_SKB_CB(skb)->has_seq) { if (l2tp_recv_data_seq(session, skb)) goto discard; } else { /* No sequence numbers. Add the skb to the tail of the * reorder queue. This ensures that it will be * delivered after all previous sequenced skbs. */ skb_queue_tail(&session->reorder_q, skb); } /* Try to dequeue as many skbs from reorder_q as we can. */ l2tp_recv_dequeue(session); return; discard: atomic_long_inc(&session->stats.rx_errors); kfree_skb(skb); } EXPORT_SYMBOL_GPL(l2tp_recv_common); /* Drop skbs from the session's reorder_q */ static void l2tp_session_queue_purge(struct l2tp_session *session) { struct sk_buff *skb = NULL; while ((skb = skb_dequeue(&session->reorder_q))) { atomic_long_inc(&session->stats.rx_errors); kfree_skb(skb); } } /* UDP encapsulation receive handler. See net/ipv4/udp.c for details. */ int l2tp_udp_encap_recv(struct sock *sk, struct sk_buff *skb) { struct l2tp_session *session = NULL; struct l2tp_tunnel *tunnel = NULL; struct net *net = sock_net(sk); unsigned char *ptr, *optr; u16 hdrflags; u16 version; int length; /* UDP has verified checksum */ /* UDP always verifies the packet length. */ __skb_pull(skb, sizeof(struct udphdr)); /* Short packet? */ if (!pskb_may_pull(skb, L2TP_HDR_SIZE_MAX)) goto pass; /* Point to L2TP header */ optr = skb->data; ptr = skb->data; /* Get L2TP header flags */ hdrflags = ntohs(*(__be16 *)ptr); /* Get protocol version */ version = hdrflags & L2TP_HDR_VER_MASK; /* Get length of L2TP packet */ length = skb->len; /* If type is control packet, it is handled by userspace. */ if (hdrflags & L2TP_HDRFLAG_T) goto pass; /* Skip flags */ ptr += 2; if (version == L2TP_HDR_VER_2) { u16 tunnel_id, session_id; /* If length is present, skip it */ if (hdrflags & L2TP_HDRFLAG_L) ptr += 2; /* Extract tunnel and session ID */ tunnel_id = ntohs(*(__be16 *)ptr); ptr += 2; session_id = ntohs(*(__be16 *)ptr); ptr += 2; session = l2tp_v2_session_get(net, tunnel_id, session_id); } else { u32 session_id; ptr += 2; /* skip reserved bits */ session_id = ntohl(*(__be32 *)ptr); ptr += 4; session = l2tp_v3_session_get(net, sk, session_id); } if (!session || !session->recv_skb) { if (session) l2tp_session_put(session); /* Not found? Pass to userspace to deal with */ goto pass; } tunnel = session->tunnel; /* Check protocol version */ if (version != tunnel->version) goto invalid; if (version == L2TP_HDR_VER_3 && l2tp_v3_ensure_opt_in_linear(session, skb, &ptr, &optr)) { l2tp_session_put(session); goto invalid; } l2tp_recv_common(session, skb, ptr, optr, hdrflags, length); l2tp_session_put(session); return 0; invalid: atomic_long_inc(&tunnel->stats.rx_invalid); pass: /* Put UDP header back */ __skb_push(skb, sizeof(struct udphdr)); return 1; } EXPORT_SYMBOL_GPL(l2tp_udp_encap_recv); /* UDP encapsulation receive error handler. See net/ipv4/udp.c for details. */ static void l2tp_udp_encap_err_recv(struct sock *sk, struct sk_buff *skb, int err, __be16 port, u32 info, u8 *payload) { sk->sk_err = err; sk_error_report(sk); if (ip_hdr(skb)->version == IPVERSION) { if (inet_test_bit(RECVERR, sk)) return ip_icmp_error(sk, skb, err, port, info, payload); #if IS_ENABLED(CONFIG_IPV6) } else { if (inet6_test_bit(RECVERR6, sk)) return ipv6_icmp_error(sk, skb, err, port, info, payload); #endif } } /************************************************************************ * Transmit handling ***********************************************************************/ /* Build an L2TP header for the session into the buffer provided. */ static int l2tp_build_l2tpv2_header(struct l2tp_session *session, void *buf) { struct l2tp_tunnel *tunnel = session->tunnel; __be16 *bufp = buf; __be16 *optr = buf; u16 flags = L2TP_HDR_VER_2; u32 tunnel_id = tunnel->peer_tunnel_id; u32 session_id = session->peer_session_id; if (session->send_seq) flags |= L2TP_HDRFLAG_S; /* Setup L2TP header. */ *bufp++ = htons(flags); *bufp++ = htons(tunnel_id); *bufp++ = htons(session_id); if (session->send_seq) { *bufp++ = htons(session->ns); *bufp++ = 0; session->ns++; session->ns &= 0xffff; trace_session_seqnum_update(session); } return bufp - optr; } static int l2tp_build_l2tpv3_header(struct l2tp_session *session, void *buf) { struct l2tp_tunnel *tunnel = session->tunnel; char *bufp = buf; char *optr = bufp; /* Setup L2TP header. The header differs slightly for UDP and * IP encapsulations. For UDP, there is 4 bytes of flags. */ if (tunnel->encap == L2TP_ENCAPTYPE_UDP) { u16 flags = L2TP_HDR_VER_3; *((__be16 *)bufp) = htons(flags); bufp += 2; *((__be16 *)bufp) = 0; bufp += 2; } *((__be32 *)bufp) = htonl(session->peer_session_id); bufp += 4; if (session->cookie_len) { memcpy(bufp, &session->cookie[0], session->cookie_len); bufp += session->cookie_len; } if (session->l2specific_type == L2TP_L2SPECTYPE_DEFAULT) { u32 l2h = 0; if (session->send_seq) { l2h = 0x40000000 | session->ns; session->ns++; session->ns &= 0xffffff; trace_session_seqnum_update(session); } *((__be32 *)bufp) = htonl(l2h); bufp += 4; } return bufp - optr; } /* Queue the packet to IP for output: tunnel socket lock must be held */ static int l2tp_xmit_queue(struct l2tp_tunnel *tunnel, struct sk_buff *skb, struct flowi *fl) { int err; skb->ignore_df = 1; skb_dst_drop(skb); #if IS_ENABLED(CONFIG_IPV6) if (l2tp_sk_is_v6(tunnel->sock)) err = inet6_csk_xmit(tunnel->sock, skb, NULL); else #endif err = ip_queue_xmit(tunnel->sock, skb, fl); return err >= 0 ? NET_XMIT_SUCCESS : NET_XMIT_DROP; } static int l2tp_xmit_core(struct l2tp_session *session, struct sk_buff *skb, unsigned int *len) { struct l2tp_tunnel *tunnel = session->tunnel; unsigned int data_len = skb->len; struct sock *sk = tunnel->sock; int headroom, uhlen, udp_len; int ret = NET_XMIT_SUCCESS; struct inet_sock *inet; struct udphdr *uh; /* Check that there's enough headroom in the skb to insert IP, * UDP and L2TP headers. If not enough, expand it to * make room. Adjust truesize. */ uhlen = (tunnel->encap == L2TP_ENCAPTYPE_UDP) ? sizeof(*uh) : 0; headroom = NET_SKB_PAD + sizeof(struct iphdr) + uhlen + session->hdr_len; if (skb_cow_head(skb, headroom)) { kfree_skb(skb); return NET_XMIT_DROP; } /* Setup L2TP header */ if (tunnel->version == L2TP_HDR_VER_2) l2tp_build_l2tpv2_header(session, __skb_push(skb, session->hdr_len)); else l2tp_build_l2tpv3_header(session, __skb_push(skb, session->hdr_len)); /* Reset skb netfilter state */ memset(&(IPCB(skb)->opt), 0, sizeof(IPCB(skb)->opt)); IPCB(skb)->flags &= ~(IPSKB_XFRM_TUNNEL_SIZE | IPSKB_XFRM_TRANSFORMED | IPSKB_REROUTED); nf_reset_ct(skb); /* L2TP uses its own lockdep subclass to avoid lockdep splats caused by * nested socket calls on the same lockdep socket class. This can * happen when data from a user socket is routed over l2tp, which uses * another userspace socket. */ spin_lock_nested(&sk->sk_lock.slock, L2TP_DEPTH_NESTING); if (sock_owned_by_user(sk)) { kfree_skb(skb); ret = NET_XMIT_DROP; goto out_unlock; } /* The user-space may change the connection status for the user-space * provided socket at run time: we must check it under the socket lock */ if (tunnel->fd >= 0 && sk->sk_state != TCP_ESTABLISHED) { kfree_skb(skb); ret = NET_XMIT_DROP; goto out_unlock; } /* Report transmitted length before we add encap header, which keeps * statistics consistent for both UDP and IP encap tx/rx paths. */ *len = skb->len; inet = inet_sk(sk); switch (tunnel->encap) { case L2TP_ENCAPTYPE_UDP: /* Setup UDP header */ __skb_push(skb, sizeof(*uh)); skb_reset_transport_header(skb); uh = udp_hdr(skb); uh->source = inet->inet_sport; uh->dest = inet->inet_dport; udp_len = uhlen + session->hdr_len + data_len; uh->len = htons(udp_len); /* Calculate UDP checksum if configured to do so */ #if IS_ENABLED(CONFIG_IPV6) if (l2tp_sk_is_v6(sk)) udp6_set_csum(udp_get_no_check6_tx(sk), skb, &inet6_sk(sk)->saddr, &sk->sk_v6_daddr, udp_len); else #endif udp_set_csum(sk->sk_no_check_tx, skb, inet->inet_saddr, inet->inet_daddr, udp_len); break; case L2TP_ENCAPTYPE_IP: break; } ret = l2tp_xmit_queue(tunnel, skb, &inet->cork.fl); out_unlock: spin_unlock(&sk->sk_lock.slock); return ret; } /* If caller requires the skb to have a ppp header, the header must be * inserted in the skb data before calling this function. */ int l2tp_xmit_skb(struct l2tp_session *session, struct sk_buff *skb) { unsigned int len = 0; int ret; ret = l2tp_xmit_core(session, skb, &len); if (ret == NET_XMIT_SUCCESS) { atomic_long_inc(&session->tunnel->stats.tx_packets); atomic_long_add(len, &session->tunnel->stats.tx_bytes); atomic_long_inc(&session->stats.tx_packets); atomic_long_add(len, &session->stats.tx_bytes); } else { atomic_long_inc(&session->tunnel->stats.tx_errors); atomic_long_inc(&session->stats.tx_errors); } return ret; } EXPORT_SYMBOL_GPL(l2tp_xmit_skb); /***************************************************************************** * Tinnel and session create/destroy. *****************************************************************************/ /* Remove an l2tp session from l2tp_core's lists. */ static void l2tp_session_unhash(struct l2tp_session *session) { struct l2tp_tunnel *tunnel = session->tunnel; if (tunnel) { struct l2tp_net *pn = l2tp_pernet(tunnel->l2tp_net); struct l2tp_session *removed = session; spin_lock_bh(&tunnel->list_lock); spin_lock_bh(&pn->l2tp_session_idr_lock); /* Remove from the per-tunnel list */ list_del_init(&session->list); /* Remove from per-net IDR */ if (tunnel->version == L2TP_HDR_VER_3) { if (hash_hashed(&session->hlist)) l2tp_session_collision_del(pn, session); else removed = idr_remove(&pn->l2tp_v3_session_idr, session->session_id); } else { u32 session_key = l2tp_v2_session_key(tunnel->tunnel_id, session->session_id); removed = idr_remove(&pn->l2tp_v2_session_idr, session_key); } WARN_ON_ONCE(removed && removed != session); spin_unlock_bh(&pn->l2tp_session_idr_lock); spin_unlock_bh(&tunnel->list_lock); } } /* When the tunnel is closed, all the attached sessions need to go too. */ static void l2tp_tunnel_closeall(struct l2tp_tunnel *tunnel) { struct l2tp_session *session; spin_lock_bh(&tunnel->list_lock); tunnel->acpt_newsess = false; list_for_each_entry(session, &tunnel->session_list, list) l2tp_session_delete(session); spin_unlock_bh(&tunnel->list_lock); } /* Tunnel socket destroy hook for UDP encapsulation */ static void l2tp_udp_encap_destroy(struct sock *sk) { struct l2tp_tunnel *tunnel; tunnel = l2tp_sk_to_tunnel(sk); if (tunnel) { l2tp_tunnel_delete(tunnel); l2tp_tunnel_put(tunnel); } } static void l2tp_tunnel_remove(struct net *net, struct l2tp_tunnel *tunnel) { struct l2tp_net *pn = l2tp_pernet(net); spin_lock_bh(&pn->l2tp_tunnel_idr_lock); idr_remove(&pn->l2tp_tunnel_idr, tunnel->tunnel_id); spin_unlock_bh(&pn->l2tp_tunnel_idr_lock); } /* Workqueue tunnel deletion function */ static void l2tp_tunnel_del_work(struct work_struct *work) { struct l2tp_tunnel *tunnel = container_of(work, struct l2tp_tunnel, del_work); struct sock *sk = tunnel->sock; struct socket *sock = sk->sk_socket; l2tp_tunnel_closeall(tunnel); /* If the tunnel socket was created within the kernel, use * the sk API to release it here. */ if (tunnel->fd < 0) { if (sock) { kernel_sock_shutdown(sock, SHUT_RDWR); sock_release(sock); } } l2tp_tunnel_remove(tunnel->l2tp_net, tunnel); /* drop initial ref */ l2tp_tunnel_put(tunnel); /* drop workqueue ref */ l2tp_tunnel_put(tunnel); } /* Create a socket for the tunnel, if one isn't set up by * userspace. This is used for static tunnels where there is no * managing L2TP daemon. * * Since we don't want these sockets to keep a namespace alive by * themselves, we drop the socket's namespace refcount after creation. * These sockets are freed when the namespace exits using the pernet * exit hook. */ static int l2tp_tunnel_sock_create(struct net *net, u32 tunnel_id, u32 peer_tunnel_id, struct l2tp_tunnel_cfg *cfg, struct socket **sockp) { int err = -EINVAL; struct socket *sock = NULL; struct udp_port_cfg udp_conf; switch (cfg->encap) { case L2TP_ENCAPTYPE_UDP: memset(&udp_conf, 0, sizeof(udp_conf)); #if IS_ENABLED(CONFIG_IPV6) if (cfg->local_ip6 && cfg->peer_ip6) { udp_conf.family = AF_INET6; memcpy(&udp_conf.local_ip6, cfg->local_ip6, sizeof(udp_conf.local_ip6)); memcpy(&udp_conf.peer_ip6, cfg->peer_ip6, sizeof(udp_conf.peer_ip6)); udp_conf.use_udp6_tx_checksums = !cfg->udp6_zero_tx_checksums; udp_conf.use_udp6_rx_checksums = !cfg->udp6_zero_rx_checksums; } else #endif { udp_conf.family = AF_INET; udp_conf.local_ip = cfg->local_ip; udp_conf.peer_ip = cfg->peer_ip; udp_conf.use_udp_checksums = cfg->use_udp_checksums; } udp_conf.local_udp_port = htons(cfg->local_udp_port); udp_conf.peer_udp_port = htons(cfg->peer_udp_port); err = udp_sock_create(net, &udp_conf, &sock); if (err < 0) goto out; break; case L2TP_ENCAPTYPE_IP: #if IS_ENABLED(CONFIG_IPV6) if (cfg->local_ip6 && cfg->peer_ip6) { struct sockaddr_l2tpip6 ip6_addr = {0}; err = sock_create_kern(net, AF_INET6, SOCK_DGRAM, IPPROTO_L2TP, &sock); if (err < 0) goto out; ip6_addr.l2tp_family = AF_INET6; memcpy(&ip6_addr.l2tp_addr, cfg->local_ip6, sizeof(ip6_addr.l2tp_addr)); ip6_addr.l2tp_conn_id = tunnel_id; err = kernel_bind(sock, (struct sockaddr *)&ip6_addr, sizeof(ip6_addr)); if (err < 0) goto out; ip6_addr.l2tp_family = AF_INET6; memcpy(&ip6_addr.l2tp_addr, cfg->peer_ip6, sizeof(ip6_addr.l2tp_addr)); ip6_addr.l2tp_conn_id = peer_tunnel_id; err = kernel_connect(sock, (struct sockaddr *)&ip6_addr, sizeof(ip6_addr), 0); if (err < 0) goto out; } else #endif { struct sockaddr_l2tpip ip_addr = {0}; err = sock_create_kern(net, AF_INET, SOCK_DGRAM, IPPROTO_L2TP, &sock); if (err < 0) goto out; ip_addr.l2tp_family = AF_INET; ip_addr.l2tp_addr = cfg->local_ip; ip_addr.l2tp_conn_id = tunnel_id; err = kernel_bind(sock, (struct sockaddr *)&ip_addr, sizeof(ip_addr)); if (err < 0) goto out; ip_addr.l2tp_family = AF_INET; ip_addr.l2tp_addr = cfg->peer_ip; ip_addr.l2tp_conn_id = peer_tunnel_id; err = kernel_connect(sock, (struct sockaddr *)&ip_addr, sizeof(ip_addr), 0); if (err < 0) goto out; } break; default: goto out; } out: *sockp = sock; if (err < 0 && sock) { kernel_sock_shutdown(sock, SHUT_RDWR); sock_release(sock); *sockp = NULL; } return err; } int l2tp_tunnel_create(int fd, int version, u32 tunnel_id, u32 peer_tunnel_id, struct l2tp_tunnel_cfg *cfg, struct l2tp_tunnel **tunnelp) { struct l2tp_tunnel *tunnel = NULL; int err; enum l2tp_encap_type encap = L2TP_ENCAPTYPE_UDP; if (cfg) encap = cfg->encap; tunnel = kzalloc(sizeof(*tunnel), GFP_KERNEL); if (!tunnel) { err = -ENOMEM; goto err; } tunnel->version = version; tunnel->tunnel_id = tunnel_id; tunnel->peer_tunnel_id = peer_tunnel_id; sprintf(&tunnel->name[0], "tunl %u", tunnel_id); spin_lock_init(&tunnel->list_lock); tunnel->acpt_newsess = true; INIT_LIST_HEAD(&tunnel->session_list); tunnel->encap = encap; refcount_set(&tunnel->ref_count, 1); tunnel->fd = fd; /* Init delete workqueue struct */ INIT_WORK(&tunnel->del_work, l2tp_tunnel_del_work); err = 0; err: if (tunnelp) *tunnelp = tunnel; return err; } EXPORT_SYMBOL_GPL(l2tp_tunnel_create); static int l2tp_validate_socket(const struct sock *sk, const struct net *net, enum l2tp_encap_type encap) { struct l2tp_tunnel *tunnel; if (!net_eq(sock_net(sk), net)) return -EINVAL; if (sk->sk_type != SOCK_DGRAM) return -EPROTONOSUPPORT; if (sk->sk_family != PF_INET && sk->sk_family != PF_INET6) return -EPROTONOSUPPORT; if ((encap == L2TP_ENCAPTYPE_UDP && sk->sk_protocol != IPPROTO_UDP) || (encap == L2TP_ENCAPTYPE_IP && sk->sk_protocol != IPPROTO_L2TP)) return -EPROTONOSUPPORT; if (encap == L2TP_ENCAPTYPE_UDP && sk->sk_user_data) return -EBUSY; tunnel = l2tp_sk_to_tunnel(sk); if (tunnel) { l2tp_tunnel_put(tunnel); return -EBUSY; } return 0; } int l2tp_tunnel_register(struct l2tp_tunnel *tunnel, struct net *net, struct l2tp_tunnel_cfg *cfg) { struct l2tp_net *pn = l2tp_pernet(net); u32 tunnel_id = tunnel->tunnel_id; struct socket *sock; struct sock *sk; int ret; spin_lock_bh(&pn->l2tp_tunnel_idr_lock); ret = idr_alloc_u32(&pn->l2tp_tunnel_idr, NULL, &tunnel_id, tunnel_id, GFP_ATOMIC); spin_unlock_bh(&pn->l2tp_tunnel_idr_lock); if (ret) return ret == -ENOSPC ? -EEXIST : ret; if (tunnel->fd < 0) { ret = l2tp_tunnel_sock_create(net, tunnel->tunnel_id, tunnel->peer_tunnel_id, cfg, &sock); if (ret < 0) goto err; } else { sock = sockfd_lookup(tunnel->fd, &ret); if (!sock) goto err; } sk = sock->sk; lock_sock(sk); write_lock_bh(&sk->sk_callback_lock); ret = l2tp_validate_socket(sk, net, tunnel->encap); if (ret < 0) goto err_inval_sock; write_unlock_bh(&sk->sk_callback_lock); if (tunnel->encap == L2TP_ENCAPTYPE_UDP) { struct udp_tunnel_sock_cfg udp_cfg = { .encap_type = UDP_ENCAP_L2TPINUDP, .encap_rcv = l2tp_udp_encap_recv, .encap_err_rcv = l2tp_udp_encap_err_recv, .encap_destroy = l2tp_udp_encap_destroy, }; setup_udp_tunnel_sock(net, sock, &udp_cfg); } sk->sk_allocation = GFP_ATOMIC; release_sock(sk); sock_hold(sk); tunnel->sock = sk; tunnel->l2tp_net = net; spin_lock_bh(&pn->l2tp_tunnel_idr_lock); idr_replace(&pn->l2tp_tunnel_idr, tunnel, tunnel->tunnel_id); spin_unlock_bh(&pn->l2tp_tunnel_idr_lock); trace_register_tunnel(tunnel); if (tunnel->fd >= 0) sockfd_put(sock); return 0; err_inval_sock: write_unlock_bh(&sk->sk_callback_lock); release_sock(sk); if (tunnel->fd < 0) sock_release(sock); else sockfd_put(sock); err: l2tp_tunnel_remove(net, tunnel); return ret; } EXPORT_SYMBOL_GPL(l2tp_tunnel_register); /* This function is used by the netlink TUNNEL_DELETE command. */ void l2tp_tunnel_delete(struct l2tp_tunnel *tunnel) { if (!test_and_set_bit(0, &tunnel->dead)) { trace_delete_tunnel(tunnel); refcount_inc(&tunnel->ref_count); queue_work(l2tp_wq, &tunnel->del_work); } } EXPORT_SYMBOL_GPL(l2tp_tunnel_delete); void l2tp_session_delete(struct l2tp_session *session) { if (!test_and_set_bit(0, &session->dead)) { trace_delete_session(session); refcount_inc(&session->ref_count); queue_work(l2tp_wq, &session->del_work); } } EXPORT_SYMBOL_GPL(l2tp_session_delete); /* Workqueue session deletion function */ static void l2tp_session_del_work(struct work_struct *work) { struct l2tp_session *session = container_of(work, struct l2tp_session, del_work); l2tp_session_unhash(session); l2tp_session_queue_purge(session); if (session->session_close) (*session->session_close)(session); /* drop initial ref */ l2tp_session_put(session); /* drop workqueue ref */ l2tp_session_put(session); } /* We come here whenever a session's send_seq, cookie_len or * l2specific_type parameters are set. */ void l2tp_session_set_header_len(struct l2tp_session *session, int version, enum l2tp_encap_type encap) { if (version == L2TP_HDR_VER_2) { session->hdr_len = 6; if (session->send_seq) session->hdr_len += 4; } else { session->hdr_len = 4 + session->cookie_len; session->hdr_len += l2tp_get_l2specific_len(session); if (encap == L2TP_ENCAPTYPE_UDP) session->hdr_len += 4; } } EXPORT_SYMBOL_GPL(l2tp_session_set_header_len); struct l2tp_session *l2tp_session_create(int priv_size, struct l2tp_tunnel *tunnel, u32 session_id, u32 peer_session_id, struct l2tp_session_cfg *cfg) { struct l2tp_session *session; session = kzalloc(sizeof(*session) + priv_size, GFP_KERNEL); if (session) { session->magic = L2TP_SESSION_MAGIC; session->session_id = session_id; session->peer_session_id = peer_session_id; session->nr = 0; if (tunnel->version == L2TP_HDR_VER_2) session->nr_max = 0xffff; else session->nr_max = 0xffffff; session->nr_window_size = session->nr_max / 2; session->nr_oos_count_max = 4; /* Use NR of first received packet */ session->reorder_skip = 1; sprintf(&session->name[0], "sess %u/%u", tunnel->tunnel_id, session->session_id); skb_queue_head_init(&session->reorder_q); session->hlist_key = l2tp_v3_session_hashkey(tunnel->sock, session->session_id); INIT_HLIST_NODE(&session->hlist); INIT_LIST_HEAD(&session->clist); INIT_LIST_HEAD(&session->list); INIT_WORK(&session->del_work, l2tp_session_del_work); if (cfg) { session->pwtype = cfg->pw_type; session->send_seq = cfg->send_seq; session->recv_seq = cfg->recv_seq; session->lns_mode = cfg->lns_mode; session->reorder_timeout = cfg->reorder_timeout; session->l2specific_type = cfg->l2specific_type; session->cookie_len = cfg->cookie_len; memcpy(&session->cookie[0], &cfg->cookie[0], cfg->cookie_len); session->peer_cookie_len = cfg->peer_cookie_len; memcpy(&session->peer_cookie[0], &cfg->peer_cookie[0], cfg->peer_cookie_len); } l2tp_session_set_header_len(session, tunnel->version, tunnel->encap); refcount_set(&session->ref_count, 1); return session; } return ERR_PTR(-ENOMEM); } EXPORT_SYMBOL_GPL(l2tp_session_create); /***************************************************************************** * Init and cleanup *****************************************************************************/ static __net_init int l2tp_init_net(struct net *net) { struct l2tp_net *pn = net_generic(net, l2tp_net_id); idr_init(&pn->l2tp_tunnel_idr); spin_lock_init(&pn->l2tp_tunnel_idr_lock); idr_init(&pn->l2tp_v2_session_idr); idr_init(&pn->l2tp_v3_session_idr); spin_lock_init(&pn->l2tp_session_idr_lock); return 0; } static __net_exit void l2tp_pre_exit_net(struct net *net) { struct l2tp_net *pn = l2tp_pernet(net); struct l2tp_tunnel *tunnel = NULL; unsigned long tunnel_id, tmp; rcu_read_lock_bh(); idr_for_each_entry_ul(&pn->l2tp_tunnel_idr, tunnel, tmp, tunnel_id) { if (tunnel) l2tp_tunnel_delete(tunnel); } rcu_read_unlock_bh(); if (l2tp_wq) { /* Run all TUNNEL_DELETE work items just queued. */ __flush_workqueue(l2tp_wq); /* Each TUNNEL_DELETE work item will queue a SESSION_DELETE * work item for each session in the tunnel. Flush the * workqueue again to process these. */ __flush_workqueue(l2tp_wq); } } static int l2tp_idr_item_unexpected(int id, void *p, void *data) { const char *idr_name = data; pr_err("l2tp: %s IDR not empty at net %d exit\n", idr_name, id); WARN_ON_ONCE(1); return 1; } static __net_exit void l2tp_exit_net(struct net *net) { struct l2tp_net *pn = l2tp_pernet(net); /* Our per-net IDRs should be empty. Check that is so, to * help catch cleanup races or refcnt leaks. */ idr_for_each(&pn->l2tp_v2_session_idr, l2tp_idr_item_unexpected, "v2_session"); idr_for_each(&pn->l2tp_v3_session_idr, l2tp_idr_item_unexpected, "v3_session"); idr_for_each(&pn->l2tp_tunnel_idr, l2tp_idr_item_unexpected, "tunnel"); idr_destroy(&pn->l2tp_v2_session_idr); idr_destroy(&pn->l2tp_v3_session_idr); idr_destroy(&pn->l2tp_tunnel_idr); } static struct pernet_operations l2tp_net_ops = { .init = l2tp_init_net, .exit = l2tp_exit_net, .pre_exit = l2tp_pre_exit_net, .id = &l2tp_net_id, .size = sizeof(struct l2tp_net), }; static int __init l2tp_init(void) { int rc = 0; rc = register_pernet_device(&l2tp_net_ops); if (rc) goto out; l2tp_wq = alloc_workqueue("l2tp", WQ_UNBOUND, 0); if (!l2tp_wq) { pr_err("alloc_workqueue failed\n"); unregister_pernet_device(&l2tp_net_ops); rc = -ENOMEM; goto out; } pr_info("L2TP core driver, %s\n", L2TP_DRV_VERSION); out: return rc; } static void __exit l2tp_exit(void) { unregister_pernet_device(&l2tp_net_ops); if (l2tp_wq) { destroy_workqueue(l2tp_wq); l2tp_wq = NULL; } } module_init(l2tp_init); module_exit(l2tp_exit); MODULE_AUTHOR("James Chapman <jchapman@katalix.com>"); MODULE_DESCRIPTION("L2TP core"); MODULE_LICENSE("GPL"); MODULE_VERSION(L2TP_DRV_VERSION); |
| 56 56 | 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 | #include <linux/export.h> #include <linux/kernel.h> #include <linux/mm.h> #include <linux/slab.h> #include <linux/vmalloc.h> /* Allocate an array of spinlocks to be accessed by a hash. Two arguments * indicate the number of elements to allocate in the array. max_size * gives the maximum number of elements to allocate. cpu_mult gives * the number of locks per CPU to allocate. The size is rounded up * to a power of 2 to be suitable as a hash table. */ int __alloc_bucket_spinlocks(spinlock_t **locks, unsigned int *locks_mask, size_t max_size, unsigned int cpu_mult, gfp_t gfp, const char *name, struct lock_class_key *key) { spinlock_t *tlocks = NULL; unsigned int i, size; #if defined(CONFIG_PROVE_LOCKING) unsigned int nr_pcpus = 2; #else unsigned int nr_pcpus = num_possible_cpus(); #endif if (cpu_mult) { nr_pcpus = min_t(unsigned int, nr_pcpus, 64UL); size = min_t(unsigned int, nr_pcpus * cpu_mult, max_size); } else { size = max_size; } if (sizeof(spinlock_t) != 0) { tlocks = kvmalloc_array(size, sizeof(spinlock_t), gfp); if (!tlocks) return -ENOMEM; for (i = 0; i < size; i++) { spin_lock_init(&tlocks[i]); lockdep_init_map(&tlocks[i].dep_map, name, key, 0); } } *locks = tlocks; *locks_mask = size - 1; return 0; } EXPORT_SYMBOL(__alloc_bucket_spinlocks); void free_bucket_spinlocks(spinlock_t *locks) { kvfree(locks); } EXPORT_SYMBOL(free_bucket_spinlocks); |
| 6 | 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 | /* SPDX-License-Identifier: GPL-2.0-or-later */ /* * NET An implementation of the SOCKET network access protocol. * This is the master header file for the Linux NET layer, * or, in plain English: the networking handling part of the * kernel. * * Version: @(#)net.h 1.0.3 05/25/93 * * Authors: Orest Zborowski, <obz@Kodak.COM> * Ross Biro * Fred N. van Kempen, <waltje@uWalt.NL.Mugnet.ORG> */ #ifndef _LINUX_NET_H #define _LINUX_NET_H #include <linux/stringify.h> #include <linux/random.h> #include <linux/wait.h> #include <linux/fcntl.h> /* For O_CLOEXEC and O_NONBLOCK */ #include <linux/rcupdate.h> #include <linux/once.h> #include <linux/fs.h> #include <linux/mm.h> #include <linux/sockptr.h> #include <uapi/linux/net.h> struct poll_table_struct; struct pipe_inode_info; struct inode; struct file; struct net; /* Historically, SOCKWQ_ASYNC_NOSPACE & SOCKWQ_ASYNC_WAITDATA were located * in sock->flags, but moved into sk->sk_wq->flags to be RCU protected. * Eventually all flags will be in sk->sk_wq->flags. */ #define SOCKWQ_ASYNC_NOSPACE 0 #define SOCKWQ_ASYNC_WAITDATA 1 #define SOCK_NOSPACE 2 #define SOCK_PASSCRED 3 #define SOCK_PASSSEC 4 #define SOCK_SUPPORT_ZC 5 #define SOCK_CUSTOM_SOCKOPT 6 #define SOCK_PASSPIDFD 7 #ifndef ARCH_HAS_SOCKET_TYPES /** * enum sock_type - Socket types * @SOCK_STREAM: stream (connection) socket * @SOCK_DGRAM: datagram (conn.less) socket * @SOCK_RAW: raw socket * @SOCK_RDM: reliably-delivered message * @SOCK_SEQPACKET: sequential packet socket * @SOCK_DCCP: Datagram Congestion Control Protocol socket * @SOCK_PACKET: linux specific way of getting packets at the dev level. * For writing rarp and other similar things on the user level. * * When adding some new socket type please * grep ARCH_HAS_SOCKET_TYPE include/asm-* /socket.h, at least MIPS * overrides this enum for binary compat reasons. */ enum sock_type { SOCK_STREAM = 1, SOCK_DGRAM = 2, SOCK_RAW = 3, SOCK_RDM = 4, SOCK_SEQPACKET = 5, SOCK_DCCP = 6, SOCK_PACKET = 10, }; #define SOCK_MAX (SOCK_PACKET + 1) /* Mask which covers at least up to SOCK_MASK-1. The * remaining bits are used as flags. */ #define SOCK_TYPE_MASK 0xf /* Flags for socket, socketpair, accept4 */ #define SOCK_CLOEXEC O_CLOEXEC #ifndef SOCK_NONBLOCK #define SOCK_NONBLOCK O_NONBLOCK #endif #endif /* ARCH_HAS_SOCKET_TYPES */ /** * enum sock_shutdown_cmd - Shutdown types * @SHUT_RD: shutdown receptions * @SHUT_WR: shutdown transmissions * @SHUT_RDWR: shutdown receptions/transmissions */ enum sock_shutdown_cmd { SHUT_RD, SHUT_WR, SHUT_RDWR, }; struct socket_wq { /* Note: wait MUST be first field of socket_wq */ wait_queue_head_t wait; struct fasync_struct *fasync_list; unsigned long flags; /* %SOCKWQ_ASYNC_NOSPACE, etc */ struct rcu_head rcu; } ____cacheline_aligned_in_smp; /** * struct socket - general BSD socket * @state: socket state (%SS_CONNECTED, etc) * @type: socket type (%SOCK_STREAM, etc) * @flags: socket flags (%SOCK_NOSPACE, etc) * @ops: protocol specific socket operations * @file: File back pointer for gc * @sk: internal networking protocol agnostic socket representation * @wq: wait queue for several uses */ struct socket { socket_state state; short type; unsigned long flags; struct file *file; struct sock *sk; const struct proto_ops *ops; /* Might change with IPV6_ADDRFORM or MPTCP. */ struct socket_wq wq; }; /* * "descriptor" for what we're up to with a read. * This allows us to use the same read code yet * have multiple different users of the data that * we read from a file. * * The simplest case just copies the data to user * mode. */ typedef struct { size_t written; size_t count; union { char __user *buf; void *data; } arg; int error; } read_descriptor_t; struct vm_area_struct; struct page; struct sockaddr; struct msghdr; struct module; struct sk_buff; struct proto_accept_arg; typedef int (*sk_read_actor_t)(read_descriptor_t *, struct sk_buff *, unsigned int, size_t); typedef int (*skb_read_actor_t)(struct sock *, struct sk_buff *); struct proto_ops { int family; struct module *owner; int (*release) (struct socket *sock); int (*bind) (struct socket *sock, struct sockaddr *myaddr, int sockaddr_len); int (*connect) (struct socket *sock, struct sockaddr *vaddr, int sockaddr_len, int flags); int (*socketpair)(struct socket *sock1, struct socket *sock2); int (*accept) (struct socket *sock, struct socket *newsock, struct proto_accept_arg *arg); int (*getname) (struct socket *sock, struct sockaddr *addr, int peer); __poll_t (*poll) (struct file *file, struct socket *sock, struct poll_table_struct *wait); int (*ioctl) (struct socket *sock, unsigned int cmd, unsigned long arg); #ifdef CONFIG_COMPAT int (*compat_ioctl) (struct socket *sock, unsigned int cmd, unsigned long arg); #endif int (*gettstamp) (struct socket *sock, void __user *userstamp, bool timeval, bool time32); int (*listen) (struct socket *sock, int len); int (*shutdown) (struct socket *sock, int flags); int (*setsockopt)(struct socket *sock, int level, int optname, sockptr_t optval, unsigned int optlen); int (*getsockopt)(struct socket *sock, int level, int optname, char __user *optval, int __user *optlen); void (*show_fdinfo)(struct seq_file *m, struct socket *sock); int (*sendmsg) (struct socket *sock, struct msghdr *m, size_t total_len); /* Notes for implementing recvmsg: * =============================== * msg->msg_namelen should get updated by the recvmsg handlers * iff msg_name != NULL. It is by default 0 to prevent * returning uninitialized memory to user space. The recvfrom * handlers can assume that msg.msg_name is either NULL or has * a minimum size of sizeof(struct sockaddr_storage). */ int (*recvmsg) (struct socket *sock, struct msghdr *m, size_t total_len, int flags); int (*mmap) (struct file *file, struct socket *sock, struct vm_area_struct * vma); ssize_t (*splice_read)(struct socket *sock, loff_t *ppos, struct pipe_inode_info *pipe, size_t len, unsigned int flags); void (*splice_eof)(struct socket *sock); int (*set_peek_off)(struct sock *sk, int val); int (*peek_len)(struct socket *sock); /* The following functions are called internally by kernel with * sock lock already held. */ int (*read_sock)(struct sock *sk, read_descriptor_t *desc, sk_read_actor_t recv_actor); /* This is different from read_sock(), it reads an entire skb at a time. */ int (*read_skb)(struct sock *sk, skb_read_actor_t recv_actor); int (*sendmsg_locked)(struct sock *sk, struct msghdr *msg, size_t size); int (*set_rcvlowat)(struct sock *sk, int val); }; #define DECLARE_SOCKADDR(type, dst, src) \ type dst = ({ __sockaddr_check_size(sizeof(*dst)); (type) src; }) struct net_proto_family { int family; int (*create)(struct net *net, struct socket *sock, int protocol, int kern); struct module *owner; }; struct iovec; struct kvec; enum { SOCK_WAKE_IO, SOCK_WAKE_WAITD, SOCK_WAKE_SPACE, SOCK_WAKE_URG, }; int sock_wake_async(struct socket_wq *sk_wq, int how, int band); int sock_register(const struct net_proto_family *fam); void sock_unregister(int family); bool sock_is_registered(int family); int __sock_create(struct net *net, int family, int type, int proto, struct socket **res, int kern); int sock_create(int family, int type, int proto, struct socket **res); int sock_create_kern(struct net *net, int family, int type, int proto, struct socket **res); int sock_create_lite(int family, int type, int proto, struct socket **res); struct socket *sock_alloc(void); void sock_release(struct socket *sock); int sock_sendmsg(struct socket *sock, struct msghdr *msg); int sock_recvmsg(struct socket *sock, struct msghdr *msg, int flags); struct file *sock_alloc_file(struct socket *sock, int flags, const char *dname); struct socket *sockfd_lookup(int fd, int *err); struct socket *sock_from_file(struct file *file); #define sockfd_put(sock) fput(sock->file) int net_ratelimit(void); #define net_ratelimited_function(function, ...) \ do { \ if (net_ratelimit()) \ function(__VA_ARGS__); \ } while (0) #define net_emerg_ratelimited(fmt, ...) \ net_ratelimited_function(pr_emerg, fmt, ##__VA_ARGS__) #define net_alert_ratelimited(fmt, ...) \ net_ratelimited_function(pr_alert, fmt, ##__VA_ARGS__) #define net_crit_ratelimited(fmt, ...) \ net_ratelimited_function(pr_crit, fmt, ##__VA_ARGS__) #define net_err_ratelimited(fmt, ...) \ net_ratelimited_function(pr_err, fmt, ##__VA_ARGS__) #define net_notice_ratelimited(fmt, ...) \ net_ratelimited_function(pr_notice, fmt, ##__VA_ARGS__) #define net_warn_ratelimited(fmt, ...) \ net_ratelimited_function(pr_warn, fmt, ##__VA_ARGS__) #define net_info_ratelimited(fmt, ...) \ net_ratelimited_function(pr_info, fmt, ##__VA_ARGS__) #if defined(CONFIG_DYNAMIC_DEBUG) || \ (defined(CONFIG_DYNAMIC_DEBUG_CORE) && defined(DYNAMIC_DEBUG_MODULE)) #define net_dbg_ratelimited(fmt, ...) \ do { \ DEFINE_DYNAMIC_DEBUG_METADATA(descriptor, fmt); \ if (DYNAMIC_DEBUG_BRANCH(descriptor) && \ net_ratelimit()) \ __dynamic_pr_debug(&descriptor, pr_fmt(fmt), \ ##__VA_ARGS__); \ } while (0) #elif defined(DEBUG) #define net_dbg_ratelimited(fmt, ...) \ net_ratelimited_function(pr_debug, fmt, ##__VA_ARGS__) #else #define net_dbg_ratelimited(fmt, ...) \ no_printk(KERN_DEBUG pr_fmt(fmt), ##__VA_ARGS__) #endif #define net_get_random_once(buf, nbytes) \ get_random_once((buf), (nbytes)) /* * E.g. XFS meta- & log-data is in slab pages, or bcache meta * data pages, or other high order pages allocated by * __get_free_pages() without __GFP_COMP, which have a page_count * of 0 and/or have PageSlab() set. We cannot use send_page for * those, as that does get_page(); put_page(); and would cause * either a VM_BUG directly, or __page_cache_release a page that * would actually still be referenced by someone, leading to some * obscure delayed Oops somewhere else. */ static inline bool sendpage_ok(struct page *page) { return !PageSlab(page) && page_count(page) >= 1; } /* * Check sendpage_ok on contiguous pages. */ static inline bool sendpages_ok(struct page *page, size_t len, size_t offset) { struct page *p = page + (offset >> PAGE_SHIFT); size_t count = 0; while (count < len) { if (!sendpage_ok(p)) return false; p++; count += PAGE_SIZE; } return true; } int kernel_sendmsg(struct socket *sock, struct msghdr *msg, struct kvec *vec, size_t num, size_t len); int kernel_recvmsg(struct socket *sock, struct msghdr *msg, struct kvec *vec, size_t num, size_t len, int flags); int kernel_bind(struct socket *sock, struct sockaddr *addr, int addrlen); int kernel_listen(struct socket *sock, int backlog); int kernel_accept(struct socket *sock, struct socket **newsock, int flags); int kernel_connect(struct socket *sock, struct sockaddr *addr, int addrlen, int flags); int kernel_getsockname(struct socket *sock, struct sockaddr *addr); int kernel_getpeername(struct socket *sock, struct sockaddr *addr); int kernel_sock_shutdown(struct socket *sock, enum sock_shutdown_cmd how); /* Routine returns the IP overhead imposed by a (caller-protected) socket. */ u32 kernel_sock_ip_overhead(struct sock *sk); #define MODULE_ALIAS_NETPROTO(proto) \ MODULE_ALIAS("net-pf-" __stringify(proto)) #define MODULE_ALIAS_NET_PF_PROTO(pf, proto) \ MODULE_ALIAS("net-pf-" __stringify(pf) "-proto-" __stringify(proto)) #define MODULE_ALIAS_NET_PF_PROTO_TYPE(pf, proto, type) \ MODULE_ALIAS("net-pf-" __stringify(pf) "-proto-" __stringify(proto) \ "-type-" __stringify(type)) #define MODULE_ALIAS_NET_PF_PROTO_NAME(pf, proto, name) \ MODULE_ALIAS("net-pf-" __stringify(pf) "-proto-" __stringify(proto) \ name) #endif /* _LINUX_NET_H */ |
| 27 26 26 27 27 27 1 1 26 26 2 2 | 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); |
| 7 7 7 7 7 7 7 7 2 2 2 2 3 3 3 2 2 2 20 20 19 2 2 2 10 5 26 19 19 19 7 7 7 7 7 19 1066 1058 24 20 18 7 3 5 7 7 8 8 9 7 2 14 7 7 412 367 366 2 7 145 143 2 154 148 7 14 49 42 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 | // 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; case NETDEV_NOTIFY_PEERS: case NETDEV_BONDING_FAILOVER: case NETDEV_RESEND_IGMP: list_for_each_entry(ipvlan, &port->ipvlans, pnode) call_netdevice_notifiers(event, ipvlan->dev); } 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"); |
| 42 15 2 25 23 2 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 | // SPDX-License-Identifier: GPL-2.0-only /* * Support Intel/AMD RAPL energy consumption counters * Copyright (C) 2013 Google, Inc., Stephane Eranian * * Intel RAPL interface is specified in the IA-32 Manual Vol3b * section 14.7.1 (September 2013) * * AMD RAPL interface for Fam17h is described in the public PPR: * https://bugzilla.kernel.org/show_bug.cgi?id=206537 * * RAPL provides more controls than just reporting energy consumption * however here we only expose the 3 energy consumption free running * counters (pp0, pkg, dram). * * Each of those counters increments in a power unit defined by the * RAPL_POWER_UNIT MSR. On SandyBridge, this unit is 1/(2^16) Joules * but it can vary. * * Counter to rapl events mappings: * * pp0 counter: consumption of all physical cores (power plane 0) * event: rapl_energy_cores * perf code: 0x1 * * pkg counter: consumption of the whole processor package * event: rapl_energy_pkg * perf code: 0x2 * * dram counter: consumption of the dram domain (servers only) * event: rapl_energy_dram * perf code: 0x3 * * gpu counter: consumption of the builtin-gpu domain (client only) * event: rapl_energy_gpu * perf code: 0x4 * * psys counter: consumption of the builtin-psys domain (client only) * event: rapl_energy_psys * perf code: 0x5 * * core counter: consumption of a single physical core * event: rapl_energy_core (power_core PMU) * perf code: 0x1 * * We manage those counters as free running (read-only). They may be * use simultaneously by other tools, such as turbostat. * * The events only support system-wide mode counting. There is no * sampling support because it does not make sense and is not * supported by the RAPL hardware. * * Because we want to avoid floating-point operations in the kernel, * the events are all reported in fixed point arithmetic (32.32). * Tools must adjust the counts to convert them to Watts using * the duration of the measurement. Tools may use a function such as * ldexp(raw_count, -32); */ #define pr_fmt(fmt) "RAPL PMU: " fmt #include <linux/module.h> #include <linux/slab.h> #include <linux/perf_event.h> #include <linux/nospec.h> #include <asm/cpu_device_id.h> #include <asm/intel-family.h> #include "perf_event.h" #include "probe.h" MODULE_DESCRIPTION("Support Intel/AMD RAPL energy consumption counters"); MODULE_LICENSE("GPL"); /* * RAPL energy status counters */ enum perf_rapl_pkg_events { PERF_RAPL_PP0 = 0, /* all cores */ PERF_RAPL_PKG, /* entire package */ PERF_RAPL_RAM, /* DRAM */ PERF_RAPL_PP1, /* gpu */ PERF_RAPL_PSYS, /* psys */ PERF_RAPL_PKG_EVENTS_MAX, NR_RAPL_PKG_DOMAINS = PERF_RAPL_PKG_EVENTS_MAX, }; #define PERF_RAPL_CORE 0 /* single core */ #define PERF_RAPL_CORE_EVENTS_MAX 1 #define NR_RAPL_CORE_DOMAINS PERF_RAPL_CORE_EVENTS_MAX static const char *const rapl_pkg_domain_names[NR_RAPL_PKG_DOMAINS] __initconst = { "pp0-core", "package", "dram", "pp1-gpu", "psys", }; static const char *const rapl_core_domain_name __initconst = "core"; /* * event code: LSB 8 bits, passed in attr->config * any other bit is reserved */ #define RAPL_EVENT_MASK 0xFFULL #define RAPL_CNTR_WIDTH 32 #define RAPL_EVENT_ATTR_STR(_name, v, str) \ static struct perf_pmu_events_attr event_attr_##v = { \ .attr = __ATTR(_name, 0444, perf_event_sysfs_show, NULL), \ .id = 0, \ .event_str = str, \ }; /* * RAPL Package energy counter scope: * 1. AMD/HYGON platforms have a per-PKG package energy counter * 2. For Intel platforms * 2.1. CLX-AP is multi-die and its RAPL MSRs are die-scope * 2.2. Other Intel platforms are single die systems so the scope can be * considered as either pkg-scope or die-scope, and we are considering * them as die-scope. */ #define rapl_pkg_pmu_is_pkg_scope() \ (boot_cpu_data.x86_vendor == X86_VENDOR_AMD || \ boot_cpu_data.x86_vendor == X86_VENDOR_HYGON) struct rapl_pmu { raw_spinlock_t lock; int n_active; int cpu; struct list_head active_list; struct pmu *pmu; ktime_t timer_interval; struct hrtimer hrtimer; }; struct rapl_pmus { struct pmu pmu; unsigned int nr_rapl_pmu; unsigned int cntr_mask; struct rapl_pmu *rapl_pmu[] __counted_by(nr_rapl_pmu); }; enum rapl_unit_quirk { RAPL_UNIT_QUIRK_NONE, RAPL_UNIT_QUIRK_INTEL_HSW, RAPL_UNIT_QUIRK_INTEL_SPR, }; struct rapl_model { struct perf_msr *rapl_pkg_msrs; struct perf_msr *rapl_core_msrs; unsigned long pkg_events; unsigned long core_events; unsigned int msr_power_unit; enum rapl_unit_quirk unit_quirk; }; /* 1/2^hw_unit Joule */ static int rapl_pkg_hw_unit[NR_RAPL_PKG_DOMAINS] __read_mostly; static int rapl_core_hw_unit __read_mostly; static struct rapl_pmus *rapl_pmus_pkg; static struct rapl_pmus *rapl_pmus_core; static u64 rapl_timer_ms; static struct rapl_model *rapl_model; /* * Helper function to get the correct topology id according to the * RAPL PMU scope. */ static inline unsigned int get_rapl_pmu_idx(int cpu, int scope) { /* * Returns unsigned int, which converts the '-1' return value * (for non-existent mappings in topology map) to UINT_MAX, so * the error check in the caller is simplified. */ switch (scope) { case PERF_PMU_SCOPE_PKG: return topology_logical_package_id(cpu); case PERF_PMU_SCOPE_DIE: return topology_logical_die_id(cpu); case PERF_PMU_SCOPE_CORE: return topology_logical_core_id(cpu); default: return -EINVAL; } } static inline u64 rapl_read_counter(struct perf_event *event) { u64 raw; rdmsrl(event->hw.event_base, raw); return raw; } static inline u64 rapl_scale(u64 v, struct perf_event *event) { int hw_unit = rapl_pkg_hw_unit[event->hw.config - 1]; if (event->pmu->scope == PERF_PMU_SCOPE_CORE) hw_unit = rapl_core_hw_unit; /* * scale delta to smallest unit (1/2^32) * users must then scale back: count * 1/(1e9*2^32) to get Joules * or use ldexp(count, -32). * Watts = Joules/Time delta */ return v << (32 - hw_unit); } static u64 rapl_event_update(struct perf_event *event) { struct hw_perf_event *hwc = &event->hw; u64 prev_raw_count, new_raw_count; s64 delta, sdelta; int shift = RAPL_CNTR_WIDTH; prev_raw_count = local64_read(&hwc->prev_count); do { rdmsrl(event->hw.event_base, new_raw_count); } while (!local64_try_cmpxchg(&hwc->prev_count, &prev_raw_count, new_raw_count)); /* * Now we have the new raw value and have updated the prev * timestamp already. We can now calculate the elapsed delta * (event-)time and add that to the generic event. * * Careful, not all hw sign-extends above the physical width * of the count. */ delta = (new_raw_count << shift) - (prev_raw_count << shift); delta >>= shift; sdelta = rapl_scale(delta, event); local64_add(sdelta, &event->count); return new_raw_count; } static void rapl_start_hrtimer(struct rapl_pmu *pmu) { hrtimer_start(&pmu->hrtimer, pmu->timer_interval, HRTIMER_MODE_REL_PINNED); } static enum hrtimer_restart rapl_hrtimer_handle(struct hrtimer *hrtimer) { struct rapl_pmu *rapl_pmu = container_of(hrtimer, struct rapl_pmu, hrtimer); struct perf_event *event; unsigned long flags; if (!rapl_pmu->n_active) return HRTIMER_NORESTART; raw_spin_lock_irqsave(&rapl_pmu->lock, flags); list_for_each_entry(event, &rapl_pmu->active_list, active_entry) rapl_event_update(event); raw_spin_unlock_irqrestore(&rapl_pmu->lock, flags); hrtimer_forward_now(hrtimer, rapl_pmu->timer_interval); return HRTIMER_RESTART; } static void rapl_hrtimer_init(struct rapl_pmu *rapl_pmu) { struct hrtimer *hr = &rapl_pmu->hrtimer; hrtimer_init(hr, CLOCK_MONOTONIC, HRTIMER_MODE_REL); hr->function = rapl_hrtimer_handle; } static void __rapl_pmu_event_start(struct rapl_pmu *rapl_pmu, struct perf_event *event) { if (WARN_ON_ONCE(!(event->hw.state & PERF_HES_STOPPED))) return; event->hw.state = 0; list_add_tail(&event->active_entry, &rapl_pmu->active_list); local64_set(&event->hw.prev_count, rapl_read_counter(event)); rapl_pmu->n_active++; if (rapl_pmu->n_active == 1) rapl_start_hrtimer(rapl_pmu); } static void rapl_pmu_event_start(struct perf_event *event, int mode) { struct rapl_pmu *rapl_pmu = event->pmu_private; unsigned long flags; raw_spin_lock_irqsave(&rapl_pmu->lock, flags); __rapl_pmu_event_start(rapl_pmu, event); raw_spin_unlock_irqrestore(&rapl_pmu->lock, flags); } static void rapl_pmu_event_stop(struct perf_event *event, int mode) { struct rapl_pmu *rapl_pmu = event->pmu_private; struct hw_perf_event *hwc = &event->hw; unsigned long flags; raw_spin_lock_irqsave(&rapl_pmu->lock, flags); /* mark event as deactivated and stopped */ if (!(hwc->state & PERF_HES_STOPPED)) { WARN_ON_ONCE(rapl_pmu->n_active <= 0); rapl_pmu->n_active--; if (rapl_pmu->n_active == 0) hrtimer_cancel(&rapl_pmu->hrtimer); list_del(&event->active_entry); WARN_ON_ONCE(hwc->state & PERF_HES_STOPPED); hwc->state |= PERF_HES_STOPPED; } /* check if update of sw counter is necessary */ if ((mode & PERF_EF_UPDATE) && !(hwc->state & PERF_HES_UPTODATE)) { /* * Drain the remaining delta count out of a event * that we are disabling: */ rapl_event_update(event); hwc->state |= PERF_HES_UPTODATE; } raw_spin_unlock_irqrestore(&rapl_pmu->lock, flags); } static int rapl_pmu_event_add(struct perf_event *event, int mode) { struct rapl_pmu *rapl_pmu = event->pmu_private; struct hw_perf_event *hwc = &event->hw; unsigned long flags; raw_spin_lock_irqsave(&rapl_pmu->lock, flags); hwc->state = PERF_HES_UPTODATE | PERF_HES_STOPPED; if (mode & PERF_EF_START) __rapl_pmu_event_start(rapl_pmu, event); raw_spin_unlock_irqrestore(&rapl_pmu->lock, flags); return 0; } static void rapl_pmu_event_del(struct perf_event *event, int flags) { rapl_pmu_event_stop(event, PERF_EF_UPDATE); } static int rapl_pmu_event_init(struct perf_event *event) { u64 cfg = event->attr.config & RAPL_EVENT_MASK; int bit, rapl_pmus_scope, ret = 0; struct rapl_pmu *rapl_pmu; unsigned int rapl_pmu_idx; struct rapl_pmus *rapl_pmus; /* unsupported modes and filters */ if (event->attr.sample_period) /* no sampling */ return -EINVAL; /* check only supported bits are set */ if (event->attr.config & ~RAPL_EVENT_MASK) return -EINVAL; if (event->cpu < 0) return -EINVAL; rapl_pmus = container_of(event->pmu, struct rapl_pmus, pmu); if (!rapl_pmus) return -EINVAL; rapl_pmus_scope = rapl_pmus->pmu.scope; if (rapl_pmus_scope == PERF_PMU_SCOPE_PKG || rapl_pmus_scope == PERF_PMU_SCOPE_DIE) { /* only look at RAPL package events */ if (event->attr.type != rapl_pmus_pkg->pmu.type) return -ENOENT; cfg = array_index_nospec((long)cfg, NR_RAPL_PKG_DOMAINS + 1); if (!cfg || cfg >= NR_RAPL_PKG_DOMAINS + 1) return -EINVAL; bit = cfg - 1; event->hw.event_base = rapl_model->rapl_pkg_msrs[bit].msr; } else if (rapl_pmus_scope == PERF_PMU_SCOPE_CORE) { /* only look at RAPL core events */ if (event->attr.type != rapl_pmus_core->pmu.type) return -ENOENT; cfg = array_index_nospec((long)cfg, NR_RAPL_CORE_DOMAINS + 1); if (!cfg || cfg >= NR_RAPL_PKG_DOMAINS + 1) return -EINVAL; bit = cfg - 1; event->hw.event_base = rapl_model->rapl_core_msrs[bit].msr; } else return -EINVAL; /* check event supported */ if (!(rapl_pmus->cntr_mask & (1 << bit))) return -EINVAL; rapl_pmu_idx = get_rapl_pmu_idx(event->cpu, rapl_pmus_scope); if (rapl_pmu_idx >= rapl_pmus->nr_rapl_pmu) return -EINVAL; /* must be done before validate_group */ rapl_pmu = rapl_pmus->rapl_pmu[rapl_pmu_idx]; if (!rapl_pmu) return -EINVAL; event->pmu_private = rapl_pmu; event->hw.config = cfg; event->hw.idx = bit; return ret; } static void rapl_pmu_event_read(struct perf_event *event) { rapl_event_update(event); } RAPL_EVENT_ATTR_STR(energy-cores, rapl_cores, "event=0x01"); RAPL_EVENT_ATTR_STR(energy-pkg , rapl_pkg, "event=0x02"); RAPL_EVENT_ATTR_STR(energy-ram , rapl_ram, "event=0x03"); RAPL_EVENT_ATTR_STR(energy-gpu , rapl_gpu, "event=0x04"); RAPL_EVENT_ATTR_STR(energy-psys, rapl_psys, "event=0x05"); RAPL_EVENT_ATTR_STR(energy-core, rapl_core, "event=0x01"); RAPL_EVENT_ATTR_STR(energy-cores.unit, rapl_cores_unit, "Joules"); RAPL_EVENT_ATTR_STR(energy-pkg.unit , rapl_pkg_unit, "Joules"); RAPL_EVENT_ATTR_STR(energy-ram.unit , rapl_ram_unit, "Joules"); RAPL_EVENT_ATTR_STR(energy-gpu.unit , rapl_gpu_unit, "Joules"); RAPL_EVENT_ATTR_STR(energy-psys.unit, rapl_psys_unit, "Joules"); RAPL_EVENT_ATTR_STR(energy-core.unit, rapl_core_unit, "Joules"); /* * we compute in 0.23 nJ increments regardless of MSR */ RAPL_EVENT_ATTR_STR(energy-cores.scale, rapl_cores_scale, "2.3283064365386962890625e-10"); RAPL_EVENT_ATTR_STR(energy-pkg.scale, rapl_pkg_scale, "2.3283064365386962890625e-10"); RAPL_EVENT_ATTR_STR(energy-ram.scale, rapl_ram_scale, "2.3283064365386962890625e-10"); RAPL_EVENT_ATTR_STR(energy-gpu.scale, rapl_gpu_scale, "2.3283064365386962890625e-10"); RAPL_EVENT_ATTR_STR(energy-psys.scale, rapl_psys_scale, "2.3283064365386962890625e-10"); RAPL_EVENT_ATTR_STR(energy-core.scale, rapl_core_scale, "2.3283064365386962890625e-10"); /* * There are no default events, but we need to create * "events" group (with empty attrs) before updating * it with detected events. */ static struct attribute *attrs_empty[] = { NULL, }; static struct attribute_group rapl_pmu_events_group = { .name = "events", .attrs = attrs_empty, }; PMU_FORMAT_ATTR(event, "config:0-7"); static struct attribute *rapl_formats_attr[] = { &format_attr_event.attr, NULL, }; static struct attribute_group rapl_pmu_format_group = { .name = "format", .attrs = rapl_formats_attr, }; static const struct attribute_group *rapl_attr_groups[] = { &rapl_pmu_format_group, &rapl_pmu_events_group, NULL, }; static const struct attribute_group *rapl_core_attr_groups[] = { &rapl_pmu_format_group, &rapl_pmu_events_group, NULL, }; static struct attribute *rapl_events_cores[] = { EVENT_PTR(rapl_cores), EVENT_PTR(rapl_cores_unit), EVENT_PTR(rapl_cores_scale), NULL, }; static struct attribute_group rapl_events_cores_group = { .name = "events", .attrs = rapl_events_cores, }; static struct attribute *rapl_events_pkg[] = { EVENT_PTR(rapl_pkg), EVENT_PTR(rapl_pkg_unit), EVENT_PTR(rapl_pkg_scale), NULL, }; static struct attribute_group rapl_events_pkg_group = { .name = "events", .attrs = rapl_events_pkg, }; static struct attribute *rapl_events_ram[] = { EVENT_PTR(rapl_ram), EVENT_PTR(rapl_ram_unit), EVENT_PTR(rapl_ram_scale), NULL, }; static struct attribute_group rapl_events_ram_group = { .name = "events", .attrs = rapl_events_ram, }; static struct attribute *rapl_events_gpu[] = { EVENT_PTR(rapl_gpu), EVENT_PTR(rapl_gpu_unit), EVENT_PTR(rapl_gpu_scale), NULL, }; static struct attribute_group rapl_events_gpu_group = { .name = "events", .attrs = rapl_events_gpu, }; static struct attribute *rapl_events_psys[] = { EVENT_PTR(rapl_psys), EVENT_PTR(rapl_psys_unit), EVENT_PTR(rapl_psys_scale), NULL, }; static struct attribute_group rapl_events_psys_group = { .name = "events", .attrs = rapl_events_psys, }; static struct attribute *rapl_events_core[] = { EVENT_PTR(rapl_core), EVENT_PTR(rapl_core_unit), EVENT_PTR(rapl_core_scale), NULL, }; static struct attribute_group rapl_events_core_group = { .name = "events", .attrs = rapl_events_core, }; static bool test_msr(int idx, void *data) { return test_bit(idx, (unsigned long *) data); } /* Only lower 32bits of the MSR represents the energy counter */ #define RAPL_MSR_MASK 0xFFFFFFFF static struct perf_msr intel_rapl_msrs[] = { [PERF_RAPL_PP0] = { MSR_PP0_ENERGY_STATUS, &rapl_events_cores_group, test_msr, false, RAPL_MSR_MASK }, [PERF_RAPL_PKG] = { MSR_PKG_ENERGY_STATUS, &rapl_events_pkg_group, test_msr, false, RAPL_MSR_MASK }, [PERF_RAPL_RAM] = { MSR_DRAM_ENERGY_STATUS, &rapl_events_ram_group, test_msr, false, RAPL_MSR_MASK }, [PERF_RAPL_PP1] = { MSR_PP1_ENERGY_STATUS, &rapl_events_gpu_group, test_msr, false, RAPL_MSR_MASK }, [PERF_RAPL_PSYS] = { MSR_PLATFORM_ENERGY_STATUS, &rapl_events_psys_group, test_msr, false, RAPL_MSR_MASK }, }; static struct perf_msr intel_rapl_spr_msrs[] = { [PERF_RAPL_PP0] = { MSR_PP0_ENERGY_STATUS, &rapl_events_cores_group, test_msr, false, RAPL_MSR_MASK }, [PERF_RAPL_PKG] = { MSR_PKG_ENERGY_STATUS, &rapl_events_pkg_group, test_msr, false, RAPL_MSR_MASK }, [PERF_RAPL_RAM] = { MSR_DRAM_ENERGY_STATUS, &rapl_events_ram_group, test_msr, false, RAPL_MSR_MASK }, [PERF_RAPL_PP1] = { MSR_PP1_ENERGY_STATUS, &rapl_events_gpu_group, test_msr, false, RAPL_MSR_MASK }, [PERF_RAPL_PSYS] = { MSR_PLATFORM_ENERGY_STATUS, &rapl_events_psys_group, test_msr, true, RAPL_MSR_MASK }, }; /* * Force to PERF_RAPL_PKG_EVENTS_MAX size due to: * - perf_msr_probe(PERF_RAPL_PKG_EVENTS_MAX) * - want to use same event codes across both architectures */ static struct perf_msr amd_rapl_pkg_msrs[] = { [PERF_RAPL_PP0] = { 0, &rapl_events_cores_group, NULL, false, 0 }, [PERF_RAPL_PKG] = { MSR_AMD_PKG_ENERGY_STATUS, &rapl_events_pkg_group, test_msr, false, RAPL_MSR_MASK }, [PERF_RAPL_RAM] = { 0, &rapl_events_ram_group, NULL, false, 0 }, [PERF_RAPL_PP1] = { 0, &rapl_events_gpu_group, NULL, false, 0 }, [PERF_RAPL_PSYS] = { 0, &rapl_events_psys_group, NULL, false, 0 }, }; static struct perf_msr amd_rapl_core_msrs[] = { [PERF_RAPL_CORE] = { MSR_AMD_CORE_ENERGY_STATUS, &rapl_events_core_group, test_msr, false, RAPL_MSR_MASK }, }; static int rapl_check_hw_unit(void) { u64 msr_rapl_power_unit_bits; int i; /* protect rdmsrl() to handle virtualization */ if (rdmsrl_safe(rapl_model->msr_power_unit, &msr_rapl_power_unit_bits)) return -1; for (i = 0; i < NR_RAPL_PKG_DOMAINS; i++) rapl_pkg_hw_unit[i] = (msr_rapl_power_unit_bits >> 8) & 0x1FULL; rapl_core_hw_unit = (msr_rapl_power_unit_bits >> 8) & 0x1FULL; switch (rapl_model->unit_quirk) { /* * DRAM domain on HSW server and KNL has fixed energy unit which can be * different than the unit from power unit MSR. See * "Intel Xeon Processor E5-1600 and E5-2600 v3 Product Families, V2 * of 2. Datasheet, September 2014, Reference Number: 330784-001 " */ case RAPL_UNIT_QUIRK_INTEL_HSW: rapl_pkg_hw_unit[PERF_RAPL_RAM] = 16; break; /* SPR uses a fixed energy unit for Psys domain. */ case RAPL_UNIT_QUIRK_INTEL_SPR: rapl_pkg_hw_unit[PERF_RAPL_PSYS] = 0; break; default: break; } /* * Calculate the timer rate: * Use reference of 200W for scaling the timeout to avoid counter * overflows. 200W = 200 Joules/sec * Divide interval by 2 to avoid lockstep (2 * 100) * if hw unit is 32, then we use 2 ms 1/200/2 */ rapl_timer_ms = 2; if (rapl_pkg_hw_unit[0] < 32) { rapl_timer_ms = (1000 / (2 * 100)); rapl_timer_ms *= (1ULL << (32 - rapl_pkg_hw_unit[0] - 1)); } return 0; } static void __init rapl_advertise(void) { int i; int num_counters = hweight32(rapl_pmus_pkg->cntr_mask); if (rapl_pmus_core) num_counters += hweight32(rapl_pmus_core->cntr_mask); pr_info("API unit is 2^-32 Joules, %d fixed counters, %llu ms ovfl timer\n", num_counters, rapl_timer_ms); for (i = 0; i < NR_RAPL_PKG_DOMAINS; i++) { if (rapl_pmus_pkg->cntr_mask & (1 << i)) { pr_info("hw unit of domain %s 2^-%d Joules\n", rapl_pkg_domain_names[i], rapl_pkg_hw_unit[i]); } } if (rapl_pmus_core && (rapl_pmus_core->cntr_mask & (1 << PERF_RAPL_CORE))) pr_info("hw unit of domain %s 2^-%d Joules\n", rapl_core_domain_name, rapl_core_hw_unit); } static void cleanup_rapl_pmus(struct rapl_pmus *rapl_pmus) { int i; for (i = 0; i < rapl_pmus->nr_rapl_pmu; i++) kfree(rapl_pmus->rapl_pmu[i]); kfree(rapl_pmus); } static const struct attribute_group *rapl_attr_update[] = { &rapl_events_cores_group, &rapl_events_pkg_group, &rapl_events_ram_group, &rapl_events_gpu_group, &rapl_events_psys_group, NULL, }; static const struct attribute_group *rapl_core_attr_update[] = { &rapl_events_core_group, NULL, }; static int __init init_rapl_pmu(struct rapl_pmus *rapl_pmus) { struct rapl_pmu *rapl_pmu; int idx; for (idx = 0; idx < rapl_pmus->nr_rapl_pmu; idx++) { rapl_pmu = kzalloc(sizeof(*rapl_pmu), GFP_KERNEL); if (!rapl_pmu) goto free; raw_spin_lock_init(&rapl_pmu->lock); INIT_LIST_HEAD(&rapl_pmu->active_list); rapl_pmu->pmu = &rapl_pmus->pmu; rapl_pmu->timer_interval = ms_to_ktime(rapl_timer_ms); rapl_hrtimer_init(rapl_pmu); rapl_pmus->rapl_pmu[idx] = rapl_pmu; } return 0; free: for (; idx > 0; idx--) kfree(rapl_pmus->rapl_pmu[idx - 1]); return -ENOMEM; } static int __init init_rapl_pmus(struct rapl_pmus **rapl_pmus_ptr, int rapl_pmu_scope, const struct attribute_group **rapl_attr_groups, const struct attribute_group **rapl_attr_update) { int nr_rapl_pmu = topology_max_packages(); struct rapl_pmus *rapl_pmus; /* * rapl_pmu_scope must be either PKG, DIE or CORE */ if (rapl_pmu_scope == PERF_PMU_SCOPE_DIE) nr_rapl_pmu *= topology_max_dies_per_package(); else if (rapl_pmu_scope == PERF_PMU_SCOPE_CORE) nr_rapl_pmu *= topology_num_cores_per_package(); else if (rapl_pmu_scope != PERF_PMU_SCOPE_PKG) return -EINVAL; rapl_pmus = kzalloc(struct_size(rapl_pmus, rapl_pmu, nr_rapl_pmu), GFP_KERNEL); if (!rapl_pmus) return -ENOMEM; *rapl_pmus_ptr = rapl_pmus; rapl_pmus->nr_rapl_pmu = nr_rapl_pmu; rapl_pmus->pmu.attr_groups = rapl_attr_groups; rapl_pmus->pmu.attr_update = rapl_attr_update; rapl_pmus->pmu.task_ctx_nr = perf_invalid_context; rapl_pmus->pmu.event_init = rapl_pmu_event_init; rapl_pmus->pmu.add = rapl_pmu_event_add; rapl_pmus->pmu.del = rapl_pmu_event_del; rapl_pmus->pmu.start = rapl_pmu_event_start; rapl_pmus->pmu.stop = rapl_pmu_event_stop; rapl_pmus->pmu.read = rapl_pmu_event_read; rapl_pmus->pmu.scope = rapl_pmu_scope; rapl_pmus->pmu.module = THIS_MODULE; rapl_pmus->pmu.capabilities = PERF_PMU_CAP_NO_EXCLUDE; return init_rapl_pmu(rapl_pmus); } static struct rapl_model model_snb = { .pkg_events = BIT(PERF_RAPL_PP0) | BIT(PERF_RAPL_PKG) | BIT(PERF_RAPL_PP1), .msr_power_unit = MSR_RAPL_POWER_UNIT, .rapl_pkg_msrs = intel_rapl_msrs, }; static struct rapl_model model_snbep = { .pkg_events = BIT(PERF_RAPL_PP0) | BIT(PERF_RAPL_PKG) | BIT(PERF_RAPL_RAM), .msr_power_unit = MSR_RAPL_POWER_UNIT, .rapl_pkg_msrs = intel_rapl_msrs, }; static struct rapl_model model_hsw = { .pkg_events = BIT(PERF_RAPL_PP0) | BIT(PERF_RAPL_PKG) | BIT(PERF_RAPL_RAM) | BIT(PERF_RAPL_PP1), .msr_power_unit = MSR_RAPL_POWER_UNIT, .rapl_pkg_msrs = intel_rapl_msrs, }; static struct rapl_model model_hsx = { .pkg_events = BIT(PERF_RAPL_PP0) | BIT(PERF_RAPL_PKG) | BIT(PERF_RAPL_RAM), .unit_quirk = RAPL_UNIT_QUIRK_INTEL_HSW, .msr_power_unit = MSR_RAPL_POWER_UNIT, .rapl_pkg_msrs = intel_rapl_msrs, }; static struct rapl_model model_knl = { .pkg_events = BIT(PERF_RAPL_PKG) | BIT(PERF_RAPL_RAM), .unit_quirk = RAPL_UNIT_QUIRK_INTEL_HSW, .msr_power_unit = MSR_RAPL_POWER_UNIT, .rapl_pkg_msrs = intel_rapl_msrs, }; static struct rapl_model model_skl = { .pkg_events = BIT(PERF_RAPL_PP0) | BIT(PERF_RAPL_PKG) | BIT(PERF_RAPL_RAM) | BIT(PERF_RAPL_PP1) | BIT(PERF_RAPL_PSYS), .msr_power_unit = MSR_RAPL_POWER_UNIT, .rapl_pkg_msrs = intel_rapl_msrs, }; static struct rapl_model model_spr = { .pkg_events = BIT(PERF_RAPL_PP0) | BIT(PERF_RAPL_PKG) | BIT(PERF_RAPL_RAM) | BIT(PERF_RAPL_PSYS), .unit_quirk = RAPL_UNIT_QUIRK_INTEL_SPR, .msr_power_unit = MSR_RAPL_POWER_UNIT, .rapl_pkg_msrs = intel_rapl_spr_msrs, }; static struct rapl_model model_amd_hygon = { .pkg_events = BIT(PERF_RAPL_PKG), .core_events = BIT(PERF_RAPL_CORE), .msr_power_unit = MSR_AMD_RAPL_POWER_UNIT, .rapl_pkg_msrs = amd_rapl_pkg_msrs, .rapl_core_msrs = amd_rapl_core_msrs, }; static const struct x86_cpu_id rapl_model_match[] __initconst = { X86_MATCH_FEATURE(X86_FEATURE_RAPL, &model_amd_hygon), X86_MATCH_VFM(INTEL_SANDYBRIDGE, &model_snb), X86_MATCH_VFM(INTEL_SANDYBRIDGE_X, &model_snbep), X86_MATCH_VFM(INTEL_IVYBRIDGE, &model_snb), X86_MATCH_VFM(INTEL_IVYBRIDGE_X, &model_snbep), X86_MATCH_VFM(INTEL_HASWELL, &model_hsw), X86_MATCH_VFM(INTEL_HASWELL_X, &model_hsx), X86_MATCH_VFM(INTEL_HASWELL_L, &model_hsw), X86_MATCH_VFM(INTEL_HASWELL_G, &model_hsw), X86_MATCH_VFM(INTEL_BROADWELL, &model_hsw), X86_MATCH_VFM(INTEL_BROADWELL_G, &model_hsw), X86_MATCH_VFM(INTEL_BROADWELL_X, &model_hsx), X86_MATCH_VFM(INTEL_BROADWELL_D, &model_hsx), X86_MATCH_VFM(INTEL_XEON_PHI_KNL, &model_knl), X86_MATCH_VFM(INTEL_XEON_PHI_KNM, &model_knl), X86_MATCH_VFM(INTEL_SKYLAKE_L, &model_skl), X86_MATCH_VFM(INTEL_SKYLAKE, &model_skl), X86_MATCH_VFM(INTEL_SKYLAKE_X, &model_hsx), X86_MATCH_VFM(INTEL_KABYLAKE_L, &model_skl), X86_MATCH_VFM(INTEL_KABYLAKE, &model_skl), X86_MATCH_VFM(INTEL_CANNONLAKE_L, &model_skl), X86_MATCH_VFM(INTEL_ATOM_GOLDMONT, &model_hsw), X86_MATCH_VFM(INTEL_ATOM_GOLDMONT_D, &model_hsw), X86_MATCH_VFM(INTEL_ATOM_GOLDMONT_PLUS, &model_hsw), X86_MATCH_VFM(INTEL_ICELAKE_L, &model_skl), X86_MATCH_VFM(INTEL_ICELAKE, &model_skl), X86_MATCH_VFM(INTEL_ICELAKE_D, &model_hsx), X86_MATCH_VFM(INTEL_ICELAKE_X, &model_hsx), X86_MATCH_VFM(INTEL_COMETLAKE_L, &model_skl), X86_MATCH_VFM(INTEL_COMETLAKE, &model_skl), X86_MATCH_VFM(INTEL_TIGERLAKE_L, &model_skl), X86_MATCH_VFM(INTEL_TIGERLAKE, &model_skl), X86_MATCH_VFM(INTEL_ALDERLAKE, &model_skl), X86_MATCH_VFM(INTEL_ALDERLAKE_L, &model_skl), X86_MATCH_VFM(INTEL_ATOM_GRACEMONT, &model_skl), X86_MATCH_VFM(INTEL_SAPPHIRERAPIDS_X, &model_spr), X86_MATCH_VFM(INTEL_EMERALDRAPIDS_X, &model_spr), X86_MATCH_VFM(INTEL_RAPTORLAKE, &model_skl), X86_MATCH_VFM(INTEL_RAPTORLAKE_P, &model_skl), X86_MATCH_VFM(INTEL_RAPTORLAKE_S, &model_skl), X86_MATCH_VFM(INTEL_METEORLAKE, &model_skl), X86_MATCH_VFM(INTEL_METEORLAKE_L, &model_skl), X86_MATCH_VFM(INTEL_ARROWLAKE_H, &model_skl), X86_MATCH_VFM(INTEL_ARROWLAKE, &model_skl), X86_MATCH_VFM(INTEL_LUNARLAKE_M, &model_skl), {}, }; MODULE_DEVICE_TABLE(x86cpu, rapl_model_match); static int __init rapl_pmu_init(void) { const struct x86_cpu_id *id; int rapl_pkg_pmu_scope = PERF_PMU_SCOPE_DIE; int ret; if (rapl_pkg_pmu_is_pkg_scope()) rapl_pkg_pmu_scope = PERF_PMU_SCOPE_PKG; id = x86_match_cpu(rapl_model_match); if (!id) return -ENODEV; rapl_model = (struct rapl_model *) id->driver_data; ret = rapl_check_hw_unit(); if (ret) return ret; ret = init_rapl_pmus(&rapl_pmus_pkg, rapl_pkg_pmu_scope, rapl_attr_groups, rapl_attr_update); if (ret) return ret; rapl_pmus_pkg->cntr_mask = perf_msr_probe(rapl_model->rapl_pkg_msrs, PERF_RAPL_PKG_EVENTS_MAX, false, (void *) &rapl_model->pkg_events); ret = perf_pmu_register(&rapl_pmus_pkg->pmu, "power", -1); if (ret) goto out; if (rapl_model->core_events) { ret = init_rapl_pmus(&rapl_pmus_core, PERF_PMU_SCOPE_CORE, rapl_core_attr_groups, rapl_core_attr_update); if (ret) { pr_warn("power-core PMU initialization failed (%d)\n", ret); goto core_init_failed; } rapl_pmus_core->cntr_mask = perf_msr_probe(rapl_model->rapl_core_msrs, PERF_RAPL_CORE_EVENTS_MAX, false, (void *) &rapl_model->core_events); ret = perf_pmu_register(&rapl_pmus_core->pmu, "power_core", -1); if (ret) { pr_warn("power-core PMU registration failed (%d)\n", ret); cleanup_rapl_pmus(rapl_pmus_core); } } core_init_failed: rapl_advertise(); return 0; out: pr_warn("Initialization failed (%d), disabled\n", ret); cleanup_rapl_pmus(rapl_pmus_pkg); return ret; } module_init(rapl_pmu_init); static void __exit intel_rapl_exit(void) { if (rapl_pmus_core) { perf_pmu_unregister(&rapl_pmus_core->pmu); cleanup_rapl_pmus(rapl_pmus_core); } perf_pmu_unregister(&rapl_pmus_pkg->pmu); cleanup_rapl_pmus(rapl_pmus_pkg); } module_exit(intel_rapl_exit); |
| 6 6 6 6 6 6 6 6 | 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 | // SPDX-License-Identifier: GPL-2.0-only #include "netlink.h" #include "common.h" struct pause_req_info { struct ethnl_req_info base; enum ethtool_mac_stats_src src; }; #define PAUSE_REQINFO(__req_base) \ container_of(__req_base, struct pause_req_info, base) struct pause_reply_data { struct ethnl_reply_data base; struct ethtool_pauseparam pauseparam; struct ethtool_pause_stats pausestat; }; #define PAUSE_REPDATA(__reply_base) \ container_of(__reply_base, struct pause_reply_data, base) const struct nla_policy ethnl_pause_get_policy[] = { [ETHTOOL_A_PAUSE_HEADER] = NLA_POLICY_NESTED(ethnl_header_policy_stats), [ETHTOOL_A_PAUSE_STATS_SRC] = NLA_POLICY_MAX(NLA_U32, ETHTOOL_MAC_STATS_SRC_PMAC), }; static int pause_parse_request(struct ethnl_req_info *req_base, struct nlattr **tb, struct netlink_ext_ack *extack) { enum ethtool_mac_stats_src src = ETHTOOL_MAC_STATS_SRC_AGGREGATE; struct pause_req_info *req_info = PAUSE_REQINFO(req_base); if (tb[ETHTOOL_A_PAUSE_STATS_SRC]) { if (!(req_base->flags & ETHTOOL_FLAG_STATS)) { NL_SET_ERR_MSG_MOD(extack, "ETHTOOL_FLAG_STATS must be set when requesting a source of stats"); return -EINVAL; } src = nla_get_u32(tb[ETHTOOL_A_PAUSE_STATS_SRC]); } req_info->src = src; return 0; } static int pause_prepare_data(const struct ethnl_req_info *req_base, struct ethnl_reply_data *reply_base, const struct genl_info *info) { const struct pause_req_info *req_info = PAUSE_REQINFO(req_base); struct pause_reply_data *data = PAUSE_REPDATA(reply_base); enum ethtool_mac_stats_src src = req_info->src; struct net_device *dev = reply_base->dev; int ret; if (!dev->ethtool_ops->get_pauseparam) return -EOPNOTSUPP; ethtool_stats_init((u64 *)&data->pausestat, sizeof(data->pausestat) / 8); data->pausestat.src = src; ret = ethnl_ops_begin(dev); if (ret < 0) return ret; if ((src == ETHTOOL_MAC_STATS_SRC_EMAC || src == ETHTOOL_MAC_STATS_SRC_PMAC) && !__ethtool_dev_mm_supported(dev)) { NL_SET_ERR_MSG_MOD(info->extack, "Device does not support MAC merge layer"); ethnl_ops_complete(dev); return -EOPNOTSUPP; } dev->ethtool_ops->get_pauseparam(dev, &data->pauseparam); if (req_base->flags & ETHTOOL_FLAG_STATS && dev->ethtool_ops->get_pause_stats) dev->ethtool_ops->get_pause_stats(dev, &data->pausestat); ethnl_ops_complete(dev); return 0; } static int pause_reply_size(const struct ethnl_req_info *req_base, const struct ethnl_reply_data *reply_base) { int n = nla_total_size(sizeof(u8)) + /* _PAUSE_AUTONEG */ nla_total_size(sizeof(u8)) + /* _PAUSE_RX */ nla_total_size(sizeof(u8)); /* _PAUSE_TX */ if (req_base->flags & ETHTOOL_FLAG_STATS) n += nla_total_size(0) + /* _PAUSE_STATS */ nla_total_size(sizeof(u32)) + /* _PAUSE_STATS_SRC */ nla_total_size_64bit(sizeof(u64)) * ETHTOOL_PAUSE_STAT_CNT; return n; } static int ethtool_put_stat(struct sk_buff *skb, u64 val, u16 attrtype, u16 padtype) { if (val == ETHTOOL_STAT_NOT_SET) return 0; if (nla_put_u64_64bit(skb, attrtype, val, padtype)) return -EMSGSIZE; return 0; } static int pause_put_stats(struct sk_buff *skb, const struct ethtool_pause_stats *pause_stats) { const u16 pad = ETHTOOL_A_PAUSE_STAT_PAD; struct nlattr *nest; if (nla_put_u32(skb, ETHTOOL_A_PAUSE_STATS_SRC, pause_stats->src)) return -EMSGSIZE; nest = nla_nest_start(skb, ETHTOOL_A_PAUSE_STATS); if (!nest) return -EMSGSIZE; if (ethtool_put_stat(skb, pause_stats->tx_pause_frames, ETHTOOL_A_PAUSE_STAT_TX_FRAMES, pad) || ethtool_put_stat(skb, pause_stats->rx_pause_frames, ETHTOOL_A_PAUSE_STAT_RX_FRAMES, pad)) goto err_cancel; nla_nest_end(skb, nest); return 0; err_cancel: nla_nest_cancel(skb, nest); return -EMSGSIZE; } static int pause_fill_reply(struct sk_buff *skb, const struct ethnl_req_info *req_base, const struct ethnl_reply_data *reply_base) { const struct pause_reply_data *data = PAUSE_REPDATA(reply_base); const struct ethtool_pauseparam *pauseparam = &data->pauseparam; if (nla_put_u8(skb, ETHTOOL_A_PAUSE_AUTONEG, !!pauseparam->autoneg) || nla_put_u8(skb, ETHTOOL_A_PAUSE_RX, !!pauseparam->rx_pause) || nla_put_u8(skb, ETHTOOL_A_PAUSE_TX, !!pauseparam->tx_pause)) return -EMSGSIZE; if (req_base->flags & ETHTOOL_FLAG_STATS && pause_put_stats(skb, &data->pausestat)) return -EMSGSIZE; return 0; } /* PAUSE_SET */ const struct nla_policy ethnl_pause_set_policy[] = { [ETHTOOL_A_PAUSE_HEADER] = NLA_POLICY_NESTED(ethnl_header_policy), [ETHTOOL_A_PAUSE_AUTONEG] = { .type = NLA_U8 }, [ETHTOOL_A_PAUSE_RX] = { .type = NLA_U8 }, [ETHTOOL_A_PAUSE_TX] = { .type = NLA_U8 }, }; static int ethnl_set_pause_validate(struct ethnl_req_info *req_info, struct genl_info *info) { const struct ethtool_ops *ops = req_info->dev->ethtool_ops; return ops->get_pauseparam && ops->set_pauseparam ? 1 : -EOPNOTSUPP; } static int ethnl_set_pause(struct ethnl_req_info *req_info, struct genl_info *info) { struct net_device *dev = req_info->dev; struct ethtool_pauseparam params = {}; struct nlattr **tb = info->attrs; bool mod = false; int ret; dev->ethtool_ops->get_pauseparam(dev, ¶ms); ethnl_update_bool32(¶ms.autoneg, tb[ETHTOOL_A_PAUSE_AUTONEG], &mod); ethnl_update_bool32(¶ms.rx_pause, tb[ETHTOOL_A_PAUSE_RX], &mod); ethnl_update_bool32(¶ms.tx_pause, tb[ETHTOOL_A_PAUSE_TX], &mod); if (!mod) return 0; ret = dev->ethtool_ops->set_pauseparam(dev, ¶ms); return ret < 0 ? ret : 1; } const struct ethnl_request_ops ethnl_pause_request_ops = { .request_cmd = ETHTOOL_MSG_PAUSE_GET, .reply_cmd = ETHTOOL_MSG_PAUSE_GET_REPLY, .hdr_attr = ETHTOOL_A_PAUSE_HEADER, .req_info_size = sizeof(struct pause_req_info), .reply_data_size = sizeof(struct pause_reply_data), .parse_request = pause_parse_request, .prepare_data = pause_prepare_data, .reply_size = pause_reply_size, .fill_reply = pause_fill_reply, .set_validate = ethnl_set_pause_validate, .set = ethnl_set_pause, .set_ntf_cmd = ETHTOOL_MSG_PAUSE_NTF, }; |
| 42 42 42 | 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 | // SPDX-License-Identifier: GPL-2.0-only /* * Copyright 2003-2005 Devicescape Software, Inc. * Copyright (c) 2006 Jiri Benc <jbenc@suse.cz> * Copyright 2007 Johannes Berg <johannes@sipsolutions.net> * Copyright 2013-2014 Intel Mobile Communications GmbH * Copyright(c) 2016 Intel Deutschland GmbH * Copyright (C) 2018 - 2023 Intel Corporation */ #include <linux/debugfs.h> #include <linux/ieee80211.h> #include "ieee80211_i.h" #include "debugfs.h" #include "debugfs_sta.h" #include "sta_info.h" #include "driver-ops.h" /* sta attributes */ #define STA_READ(name, field, format_string) \ static ssize_t sta_ ##name## _read(struct file *file, \ char __user *userbuf, \ size_t count, loff_t *ppos) \ { \ struct sta_info *sta = file->private_data; \ return mac80211_format_buffer(userbuf, count, ppos, \ format_string, sta->field); \ } #define STA_READ_D(name, field) STA_READ(name, field, "%d\n") #define STA_OPS(name) \ static const struct debugfs_short_fops sta_ ##name## _ops = { \ .read = sta_##name##_read, \ .llseek = generic_file_llseek, \ } #define STA_OPS_RW(name) \ static const struct debugfs_short_fops sta_ ##name## _ops = { \ .read = sta_##name##_read, \ .write = sta_##name##_write, \ .llseek = generic_file_llseek, \ } #define STA_FILE(name, field, format) \ STA_READ_##format(name, field) \ STA_OPS(name) STA_FILE(aid, sta.aid, D); static const char * const sta_flag_names[] = { #define FLAG(F) [WLAN_STA_##F] = #F FLAG(AUTH), FLAG(ASSOC), FLAG(PS_STA), FLAG(AUTHORIZED), FLAG(SHORT_PREAMBLE), FLAG(WDS), FLAG(CLEAR_PS_FILT), FLAG(MFP), FLAG(BLOCK_BA), FLAG(PS_DRIVER), FLAG(PSPOLL), FLAG(TDLS_PEER), FLAG(TDLS_PEER_AUTH), FLAG(TDLS_INITIATOR), FLAG(TDLS_CHAN_SWITCH), FLAG(TDLS_OFF_CHANNEL), FLAG(TDLS_WIDER_BW), FLAG(UAPSD), FLAG(SP), FLAG(4ADDR_EVENT), FLAG(INSERTED), FLAG(RATE_CONTROL), FLAG(TOFFSET_KNOWN), FLAG(MPSP_OWNER), FLAG(MPSP_RECIPIENT), FLAG(PS_DELIVER), FLAG(USES_ENCRYPTION), FLAG(DECAP_OFFLOAD), #undef FLAG }; static ssize_t sta_flags_read(struct file *file, char __user *userbuf, size_t count, loff_t *ppos) { char buf[16 * NUM_WLAN_STA_FLAGS], *pos = buf; char *end = buf + sizeof(buf) - 1; struct sta_info *sta = file->private_data; unsigned int flg; BUILD_BUG_ON(ARRAY_SIZE(sta_flag_names) != NUM_WLAN_STA_FLAGS); for (flg = 0; flg < NUM_WLAN_STA_FLAGS; flg++) { if (test_sta_flag(sta, flg)) pos += scnprintf(pos, end - pos, "%s\n", sta_flag_names[flg]); } return simple_read_from_buffer(userbuf, count, ppos, buf, strlen(buf)); } STA_OPS(flags); static ssize_t sta_num_ps_buf_frames_read(struct file *file, char __user *userbuf, size_t count, loff_t *ppos) { struct sta_info *sta = file->private_data; char buf[17*IEEE80211_NUM_ACS], *p = buf; int ac; for (ac = 0; ac < IEEE80211_NUM_ACS; ac++) p += scnprintf(p, sizeof(buf)+buf-p, "AC%d: %d\n", ac, skb_queue_len(&sta->ps_tx_buf[ac]) + skb_queue_len(&sta->tx_filtered[ac])); return simple_read_from_buffer(userbuf, count, ppos, buf, p - buf); } STA_OPS(num_ps_buf_frames); static ssize_t sta_last_seq_ctrl_read(struct file *file, char __user *userbuf, size_t count, loff_t *ppos) { char buf[15*IEEE80211_NUM_TIDS], *p = buf; int i; struct sta_info *sta = file->private_data; for (i = 0; i < IEEE80211_NUM_TIDS; i++) p += scnprintf(p, sizeof(buf)+buf-p, "%x ", le16_to_cpu(sta->last_seq_ctrl[i])); p += scnprintf(p, sizeof(buf)+buf-p, "\n"); return simple_read_from_buffer(userbuf, count, ppos, buf, p - buf); } STA_OPS(last_seq_ctrl); #define AQM_TXQ_ENTRY_LEN 130 static ssize_t sta_aqm_read(struct file *file, char __user *userbuf, size_t count, loff_t *ppos) { struct sta_info *sta = file->private_data; struct ieee80211_local *local = sta->local; size_t bufsz = AQM_TXQ_ENTRY_LEN * (IEEE80211_NUM_TIDS + 2); char *buf = kzalloc(bufsz, GFP_KERNEL), *p = buf; struct txq_info *txqi; ssize_t rv; int i; if (!buf) return -ENOMEM; spin_lock_bh(&local->fq.lock); rcu_read_lock(); p += scnprintf(p, bufsz + buf - p, "target %uus interval %uus ecn %s\n", codel_time_to_us(sta->cparams.target), codel_time_to_us(sta->cparams.interval), sta->cparams.ecn ? "yes" : "no"); p += scnprintf(p, bufsz + buf - p, "tid ac backlog-bytes backlog-packets new-flows drops marks overlimit collisions tx-bytes tx-packets flags\n"); for (i = 0; i < ARRAY_SIZE(sta->sta.txq); i++) { if (!sta->sta.txq[i]) continue; txqi = to_txq_info(sta->sta.txq[i]); p += scnprintf(p, bufsz + buf - p, "%d %d %u %u %u %u %u %u %u %u %u 0x%lx(%s%s%s%s)\n", txqi->txq.tid, txqi->txq.ac, txqi->tin.backlog_bytes, txqi->tin.backlog_packets, txqi->tin.flows, txqi->cstats.drop_count, txqi->cstats.ecn_mark, txqi->tin.overlimit, txqi->tin.collisions, txqi->tin.tx_bytes, txqi->tin.tx_packets, txqi->flags, test_bit(IEEE80211_TXQ_STOP, &txqi->flags) ? "STOP" : "RUN", test_bit(IEEE80211_TXQ_AMPDU, &txqi->flags) ? " AMPDU" : "", test_bit(IEEE80211_TXQ_NO_AMSDU, &txqi->flags) ? " NO-AMSDU" : "", test_bit(IEEE80211_TXQ_DIRTY, &txqi->flags) ? " DIRTY" : ""); } rcu_read_unlock(); spin_unlock_bh(&local->fq.lock); rv = simple_read_from_buffer(userbuf, count, ppos, buf, p - buf); kfree(buf); return rv; } STA_OPS(aqm); static ssize_t sta_airtime_read(struct file *file, char __user *userbuf, size_t count, loff_t *ppos) { struct sta_info *sta = file->private_data; struct ieee80211_local *local = sta->sdata->local; size_t bufsz = 400; char *buf = kzalloc(bufsz, GFP_KERNEL), *p = buf; u64 rx_airtime = 0, tx_airtime = 0; s32 deficit[IEEE80211_NUM_ACS]; ssize_t rv; int ac; if (!buf) return -ENOMEM; for (ac = 0; ac < IEEE80211_NUM_ACS; ac++) { spin_lock_bh(&local->active_txq_lock[ac]); rx_airtime += sta->airtime[ac].rx_airtime; tx_airtime += sta->airtime[ac].tx_airtime; deficit[ac] = sta->airtime[ac].deficit; spin_unlock_bh(&local->active_txq_lock[ac]); } p += scnprintf(p, bufsz + buf - p, "RX: %llu us\nTX: %llu us\nWeight: %u\n" "Deficit: VO: %d us VI: %d us BE: %d us BK: %d us\n", rx_airtime, tx_airtime, sta->airtime_weight, deficit[0], deficit[1], deficit[2], deficit[3]); rv = simple_read_from_buffer(userbuf, count, ppos, buf, p - buf); kfree(buf); return rv; } static ssize_t sta_airtime_write(struct file *file, const char __user *userbuf, size_t count, loff_t *ppos) { struct sta_info *sta = file->private_data; struct ieee80211_local *local = sta->sdata->local; int ac; for (ac = 0; ac < IEEE80211_NUM_ACS; ac++) { spin_lock_bh(&local->active_txq_lock[ac]); sta->airtime[ac].rx_airtime = 0; sta->airtime[ac].tx_airtime = 0; sta->airtime[ac].deficit = sta->airtime_weight; spin_unlock_bh(&local->active_txq_lock[ac]); } return count; } STA_OPS_RW(airtime); static ssize_t sta_aql_read(struct file *file, char __user *userbuf, size_t count, loff_t *ppos) { struct sta_info *sta = file->private_data; struct ieee80211_local *local = sta->sdata->local; size_t bufsz = 400; char *buf = kzalloc(bufsz, GFP_KERNEL), *p = buf; u32 q_depth[IEEE80211_NUM_ACS]; u32 q_limit_l[IEEE80211_NUM_ACS], q_limit_h[IEEE80211_NUM_ACS]; ssize_t rv; int ac; if (!buf) return -ENOMEM; for (ac = 0; ac < IEEE80211_NUM_ACS; ac++) { spin_lock_bh(&local->active_txq_lock[ac]); q_limit_l[ac] = sta->airtime[ac].aql_limit_low; q_limit_h[ac] = sta->airtime[ac].aql_limit_high; spin_unlock_bh(&local->active_txq_lock[ac]); q_depth[ac] = atomic_read(&sta->airtime[ac].aql_tx_pending); } p += scnprintf(p, bufsz + buf - p, "Q depth: VO: %u us VI: %u us BE: %u us BK: %u us\n" "Q limit[low/high]: VO: %u/%u VI: %u/%u BE: %u/%u BK: %u/%u\n", q_depth[0], q_depth[1], q_depth[2], q_depth[3], q_limit_l[0], q_limit_h[0], q_limit_l[1], q_limit_h[1], q_limit_l[2], q_limit_h[2], q_limit_l[3], q_limit_h[3]); rv = simple_read_from_buffer(userbuf, count, ppos, buf, p - buf); kfree(buf); return rv; } static ssize_t sta_aql_write(struct file *file, const char __user *userbuf, size_t count, loff_t *ppos) { struct sta_info *sta = file->private_data; u32 ac, q_limit_l, q_limit_h; char _buf[100] = {}, *buf = _buf; if (count > sizeof(_buf)) return -EINVAL; if (copy_from_user(buf, userbuf, count)) return -EFAULT; buf[sizeof(_buf) - 1] = '\0'; if (sscanf(buf, "limit %u %u %u", &ac, &q_limit_l, &q_limit_h) != 3) return -EINVAL; if (ac >= IEEE80211_NUM_ACS) return -EINVAL; sta->airtime[ac].aql_limit_low = q_limit_l; sta->airtime[ac].aql_limit_high = q_limit_h; return count; } STA_OPS_RW(aql); static ssize_t sta_agg_status_do_read(struct wiphy *wiphy, struct file *file, char *buf, size_t bufsz, void *data) { struct sta_info *sta = data; char *p = buf; int i; struct tid_ampdu_rx *tid_rx; struct tid_ampdu_tx *tid_tx; p += scnprintf(p, bufsz + buf - p, "next dialog_token: %#02x\n", sta->ampdu_mlme.dialog_token_allocator + 1); p += scnprintf(p, bufsz + buf - p, "TID\t\tRX\tDTKN\tSSN\t\tTX\tDTKN\tpending\n"); for (i = 0; i < IEEE80211_NUM_TIDS; i++) { bool tid_rx_valid; tid_rx = wiphy_dereference(wiphy, sta->ampdu_mlme.tid_rx[i]); tid_tx = wiphy_dereference(wiphy, sta->ampdu_mlme.tid_tx[i]); tid_rx_valid = test_bit(i, sta->ampdu_mlme.agg_session_valid); p += scnprintf(p, bufsz + buf - p, "%02d", i); p += scnprintf(p, bufsz + buf - p, "\t\t%x", tid_rx_valid); p += scnprintf(p, bufsz + buf - p, "\t%#.2x", tid_rx_valid ? sta->ampdu_mlme.tid_rx_token[i] : 0); p += scnprintf(p, bufsz + buf - p, "\t%#.3x", tid_rx ? tid_rx->ssn : 0); p += scnprintf(p, bufsz + buf - p, "\t\t%x", !!tid_tx); p += scnprintf(p, bufsz + buf - p, "\t%#.2x", tid_tx ? tid_tx->dialog_token : 0); p += scnprintf(p, bufsz + buf - p, "\t%03d", tid_tx ? skb_queue_len(&tid_tx->pending) : 0); p += scnprintf(p, bufsz + buf - p, "\n"); } return p - buf; } static ssize_t sta_agg_status_read(struct file *file, char __user *userbuf, size_t count, loff_t *ppos) { struct sta_info *sta = file->private_data; struct wiphy *wiphy = sta->local->hw.wiphy; size_t bufsz = 71 + IEEE80211_NUM_TIDS * 40; char *buf = kmalloc(bufsz, GFP_KERNEL); ssize_t ret; if (!buf) return -ENOMEM; ret = wiphy_locked_debugfs_read(wiphy, file, buf, bufsz, userbuf, count, ppos, sta_agg_status_do_read, sta); kfree(buf); return ret; } static ssize_t sta_agg_status_do_write(struct wiphy *wiphy, struct file *file, char *buf, size_t count, void *data) { struct sta_info *sta = data; bool start, tx; unsigned long tid; char *pos = buf; int ret, timeout = 5000; buf = strsep(&pos, " "); if (!buf) return -EINVAL; if (!strcmp(buf, "tx")) tx = true; else if (!strcmp(buf, "rx")) tx = false; else return -EINVAL; buf = strsep(&pos, " "); if (!buf) return -EINVAL; if (!strcmp(buf, "start")) { start = true; if (!tx) return -EINVAL; } else if (!strcmp(buf, "stop")) { start = false; } else { return -EINVAL; } buf = strsep(&pos, " "); if (!buf) return -EINVAL; if (sscanf(buf, "timeout=%d", &timeout) == 1) { buf = strsep(&pos, " "); if (!buf || !tx || !start) return -EINVAL; } ret = kstrtoul(buf, 0, &tid); if (ret || tid >= IEEE80211_NUM_TIDS) return -EINVAL; if (tx) { if (start) ret = ieee80211_start_tx_ba_session(&sta->sta, tid, timeout); else ret = ieee80211_stop_tx_ba_session(&sta->sta, tid); } else { __ieee80211_stop_rx_ba_session(sta, tid, WLAN_BACK_RECIPIENT, 3, true); ret = 0; } return ret ?: count; } static ssize_t sta_agg_status_write(struct file *file, const char __user *userbuf, size_t count, loff_t *ppos) { struct sta_info *sta = file->private_data; struct wiphy *wiphy = sta->local->hw.wiphy; char _buf[26]; return wiphy_locked_debugfs_write(wiphy, file, _buf, sizeof(_buf), userbuf, count, sta_agg_status_do_write, sta); } STA_OPS_RW(agg_status); /* link sta attributes */ #define LINK_STA_OPS(name) \ static const struct debugfs_short_fops link_sta_ ##name## _ops = { \ .read = link_sta_##name##_read, \ .llseek = generic_file_llseek, \ } static ssize_t link_sta_addr_read(struct file *file, char __user *userbuf, size_t count, loff_t *ppos) { struct link_sta_info *link_sta = file->private_data; u8 mac[3 * ETH_ALEN + 1]; snprintf(mac, sizeof(mac), "%pM\n", link_sta->pub->addr); return simple_read_from_buffer(userbuf, count, ppos, mac, 3 * ETH_ALEN); } LINK_STA_OPS(addr); static ssize_t link_sta_ht_capa_read(struct file *file, char __user *userbuf, size_t count, loff_t *ppos) { #define PRINT_HT_CAP(_cond, _str) \ do { \ if (_cond) \ p += scnprintf(p, bufsz + buf - p, "\t" _str "\n"); \ } while (0) char *buf, *p; int i; ssize_t bufsz = 512; struct link_sta_info *link_sta = file->private_data; struct ieee80211_sta_ht_cap *htc = &link_sta->pub->ht_cap; ssize_t ret; buf = kzalloc(bufsz, GFP_KERNEL); if (!buf) return -ENOMEM; p = buf; p += scnprintf(p, bufsz + buf - p, "ht %ssupported\n", htc->ht_supported ? "" : "not "); if (htc->ht_supported) { p += scnprintf(p, bufsz + buf - p, "cap: %#.4x\n", htc->cap); PRINT_HT_CAP((htc->cap & BIT(0)), "RX LDPC"); PRINT_HT_CAP((htc->cap & BIT(1)), "HT20/HT40"); PRINT_HT_CAP(!(htc->cap & BIT(1)), "HT20"); PRINT_HT_CAP(((htc->cap >> 2) & 0x3) == 0, "Static SM Power Save"); PRINT_HT_CAP(((htc->cap >> 2) & 0x3) == 1, "Dynamic SM Power Save"); PRINT_HT_CAP(((htc->cap >> 2) & 0x3) == 3, "SM Power Save disabled"); PRINT_HT_CAP((htc->cap & BIT(4)), "RX Greenfield"); PRINT_HT_CAP((htc->cap & BIT(5)), "RX HT20 SGI"); PRINT_HT_CAP((htc->cap & BIT(6)), "RX HT40 SGI"); PRINT_HT_CAP((htc->cap & BIT(7)), "TX STBC"); PRINT_HT_CAP(((htc->cap >> 8) & 0x3) == 0, "No RX STBC"); PRINT_HT_CAP(((htc->cap >> 8) & 0x3) == 1, "RX STBC 1-stream"); PRINT_HT_CAP(((htc->cap >> 8) & 0x3) == 2, "RX STBC 2-streams"); PRINT_HT_CAP(((htc->cap >> 8) & 0x3) == 3, "RX STBC 3-streams"); PRINT_HT_CAP((htc->cap & BIT(10)), "HT Delayed Block Ack"); PRINT_HT_CAP(!(htc->cap & BIT(11)), "Max AMSDU length: " "3839 bytes"); PRINT_HT_CAP((htc->cap & BIT(11)), "Max AMSDU length: " "7935 bytes"); /* * For beacons and probe response this would mean the BSS * does or does not allow the usage of DSSS/CCK HT40. * Otherwise it means the STA does or does not use * DSSS/CCK HT40. */ PRINT_HT_CAP((htc->cap & BIT(12)), "DSSS/CCK HT40"); PRINT_HT_CAP(!(htc->cap & BIT(12)), "No DSSS/CCK HT40"); /* BIT(13) is reserved */ PRINT_HT_CAP((htc->cap & BIT(14)), "40 MHz Intolerant"); PRINT_HT_CAP((htc->cap & BIT(15)), "L-SIG TXOP protection"); p += scnprintf(p, bufsz + buf - p, "ampdu factor/density: %d/%d\n", htc->ampdu_factor, htc->ampdu_density); p += scnprintf(p, bufsz + buf - p, "MCS mask:"); for (i = 0; i < IEEE80211_HT_MCS_MASK_LEN; i++) p += scnprintf(p, bufsz + buf - p, " %.2x", htc->mcs.rx_mask[i]); p += scnprintf(p, bufsz + buf - p, "\n"); /* If not set this is meaningless */ if (le16_to_cpu(htc->mcs.rx_highest)) { p += scnprintf(p, bufsz + buf - p, "MCS rx highest: %d Mbps\n", le16_to_cpu(htc->mcs.rx_highest)); } p += scnprintf(p, bufsz + buf - p, "MCS tx params: %x\n", htc->mcs.tx_params); } ret = simple_read_from_buffer(userbuf, count, ppos, buf, p - buf); kfree(buf); return ret; } LINK_STA_OPS(ht_capa); static ssize_t link_sta_vht_capa_read(struct file *file, char __user *userbuf, size_t count, loff_t *ppos) { char *buf, *p; struct link_sta_info *link_sta = file->private_data; struct ieee80211_sta_vht_cap *vhtc = &link_sta->pub->vht_cap; ssize_t ret; ssize_t bufsz = 512; buf = kzalloc(bufsz, GFP_KERNEL); if (!buf) return -ENOMEM; p = buf; p += scnprintf(p, bufsz + buf - p, "VHT %ssupported\n", vhtc->vht_supported ? "" : "not "); if (vhtc->vht_supported) { p += scnprintf(p, bufsz + buf - p, "cap: %#.8x\n", vhtc->cap); #define PFLAG(a, b) \ do { \ if (vhtc->cap & IEEE80211_VHT_CAP_ ## a) \ p += scnprintf(p, bufsz + buf - p, \ "\t\t%s\n", b); \ } while (0) switch (vhtc->cap & 0x3) { case IEEE80211_VHT_CAP_MAX_MPDU_LENGTH_3895: p += scnprintf(p, bufsz + buf - p, "\t\tMAX-MPDU-3895\n"); break; case IEEE80211_VHT_CAP_MAX_MPDU_LENGTH_7991: p += scnprintf(p, bufsz + buf - p, "\t\tMAX-MPDU-7991\n"); break; case IEEE80211_VHT_CAP_MAX_MPDU_LENGTH_11454: p += scnprintf(p, bufsz + buf - p, "\t\tMAX-MPDU-11454\n"); break; default: p += scnprintf(p, bufsz + buf - p, "\t\tMAX-MPDU-UNKNOWN\n"); } switch (vhtc->cap & IEEE80211_VHT_CAP_SUPP_CHAN_WIDTH_MASK) { case 0: p += scnprintf(p, bufsz + buf - p, "\t\t80Mhz\n"); break; case IEEE80211_VHT_CAP_SUPP_CHAN_WIDTH_160MHZ: p += scnprintf(p, bufsz + buf - p, "\t\t160Mhz\n"); break; case IEEE80211_VHT_CAP_SUPP_CHAN_WIDTH_160_80PLUS80MHZ: p += scnprintf(p, bufsz + buf - p, "\t\t80+80Mhz\n"); break; default: p += scnprintf(p, bufsz + buf - p, "\t\tUNKNOWN-MHZ: 0x%x\n", (vhtc->cap >> 2) & 0x3); } PFLAG(RXLDPC, "RXLDPC"); PFLAG(SHORT_GI_80, "SHORT-GI-80"); PFLAG(SHORT_GI_160, "SHORT-GI-160"); PFLAG(TXSTBC, "TXSTBC"); p += scnprintf(p, bufsz + buf - p, "\t\tRXSTBC_%d\n", (vhtc->cap >> 8) & 0x7); PFLAG(SU_BEAMFORMER_CAPABLE, "SU-BEAMFORMER-CAPABLE"); PFLAG(SU_BEAMFORMEE_CAPABLE, "SU-BEAMFORMEE-CAPABLE"); p += scnprintf(p, bufsz + buf - p, "\t\tBEAMFORMEE-STS: 0x%x\n", (vhtc->cap & IEEE80211_VHT_CAP_BEAMFORMEE_STS_MASK) >> IEEE80211_VHT_CAP_BEAMFORMEE_STS_SHIFT); p += scnprintf(p, bufsz + buf - p, "\t\tSOUNDING-DIMENSIONS: 0x%x\n", (vhtc->cap & IEEE80211_VHT_CAP_SOUNDING_DIMENSIONS_MASK) >> IEEE80211_VHT_CAP_SOUNDING_DIMENSIONS_SHIFT); PFLAG(MU_BEAMFORMER_CAPABLE, "MU-BEAMFORMER-CAPABLE"); PFLAG(MU_BEAMFORMEE_CAPABLE, "MU-BEAMFORMEE-CAPABLE"); PFLAG(VHT_TXOP_PS, "TXOP-PS"); PFLAG(HTC_VHT, "HTC-VHT"); p += scnprintf(p, bufsz + buf - p, "\t\tMPDU-LENGTH-EXPONENT: 0x%x\n", (vhtc->cap & IEEE80211_VHT_CAP_MAX_A_MPDU_LENGTH_EXPONENT_MASK) >> IEEE80211_VHT_CAP_MAX_A_MPDU_LENGTH_EXPONENT_SHIFT); PFLAG(VHT_LINK_ADAPTATION_VHT_UNSOL_MFB, "LINK-ADAPTATION-VHT-UNSOL-MFB"); p += scnprintf(p, bufsz + buf - p, "\t\tLINK-ADAPTATION-VHT-MRQ-MFB: 0x%x\n", (vhtc->cap & IEEE80211_VHT_CAP_VHT_LINK_ADAPTATION_VHT_MRQ_MFB) >> 26); PFLAG(RX_ANTENNA_PATTERN, "RX-ANTENNA-PATTERN"); PFLAG(TX_ANTENNA_PATTERN, "TX-ANTENNA-PATTERN"); p += scnprintf(p, bufsz + buf - p, "RX MCS: %.4x\n", le16_to_cpu(vhtc->vht_mcs.rx_mcs_map)); if (vhtc->vht_mcs.rx_highest) p += scnprintf(p, bufsz + buf - p, "MCS RX highest: %d Mbps\n", le16_to_cpu(vhtc->vht_mcs.rx_highest)); p += scnprintf(p, bufsz + buf - p, "TX MCS: %.4x\n", le16_to_cpu(vhtc->vht_mcs.tx_mcs_map)); if (vhtc->vht_mcs.tx_highest) p += scnprintf(p, bufsz + buf - p, "MCS TX highest: %d Mbps\n", le16_to_cpu(vhtc->vht_mcs.tx_highest)); #undef PFLAG } ret = simple_read_from_buffer(userbuf, count, ppos, buf, p - buf); kfree(buf); return ret; } LINK_STA_OPS(vht_capa); static ssize_t link_sta_he_capa_read(struct file *file, char __user *userbuf, size_t count, loff_t *ppos) { char *buf, *p; size_t buf_sz = PAGE_SIZE; struct link_sta_info *link_sta = file->private_data; struct ieee80211_sta_he_cap *hec = &link_sta->pub->he_cap; struct ieee80211_he_mcs_nss_supp *nss = &hec->he_mcs_nss_supp; u8 ppe_size; u8 *cap; int i; ssize_t ret; buf = kmalloc(buf_sz, GFP_KERNEL); if (!buf) return -ENOMEM; p = buf; p += scnprintf(p, buf_sz + buf - p, "HE %ssupported\n", hec->has_he ? "" : "not "); if (!hec->has_he) goto out; cap = hec->he_cap_elem.mac_cap_info; p += scnprintf(p, buf_sz + buf - p, "MAC-CAP: %#.2x %#.2x %#.2x %#.2x %#.2x %#.2x\n", cap[0], cap[1], cap[2], cap[3], cap[4], cap[5]); #define PRINT(fmt, ...) \ p += scnprintf(p, buf_sz + buf - p, "\t\t" fmt "\n", \ ##__VA_ARGS__) #define PFLAG(t, n, a, b) \ do { \ if (cap[n] & IEEE80211_HE_##t##_CAP##n##_##a) \ PRINT("%s", b); \ } while (0) #define PFLAG_RANGE(t, i, n, s, m, off, fmt) \ do { \ u8 msk = IEEE80211_HE_##t##_CAP##i##_##n##_MASK; \ u8 idx = ((cap[i] & msk) >> (ffs(msk) - 1)) + off; \ PRINT(fmt, (s << idx) + (m * idx)); \ } while (0) #define PFLAG_RANGE_DEFAULT(t, i, n, s, m, off, fmt, a, b) \ do { \ if (cap[i] == IEEE80211_HE_##t ##_CAP##i##_##n##_##a) { \ PRINT("%s", b); \ break; \ } \ PFLAG_RANGE(t, i, n, s, m, off, fmt); \ } while (0) PFLAG(MAC, 0, HTC_HE, "HTC-HE"); PFLAG(MAC, 0, TWT_REQ, "TWT-REQ"); PFLAG(MAC, 0, TWT_RES, "TWT-RES"); PFLAG_RANGE_DEFAULT(MAC, 0, DYNAMIC_FRAG, 0, 1, 0, "DYNAMIC-FRAG-LEVEL-%d", NOT_SUPP, "NOT-SUPP"); PFLAG_RANGE_DEFAULT(MAC, 0, MAX_NUM_FRAG_MSDU, 1, 0, 0, "MAX-NUM-FRAG-MSDU-%d", UNLIMITED, "UNLIMITED"); PFLAG_RANGE_DEFAULT(MAC, 1, MIN_FRAG_SIZE, 128, 0, -1, "MIN-FRAG-SIZE-%d", UNLIMITED, "UNLIMITED"); PFLAG_RANGE_DEFAULT(MAC, 1, TF_MAC_PAD_DUR, 0, 8, 0, "TF-MAC-PAD-DUR-%dUS", MASK, "UNKNOWN"); PFLAG_RANGE(MAC, 1, MULTI_TID_AGG_RX_QOS, 0, 1, 1, "MULTI-TID-AGG-RX-QOS-%d"); if (cap[0] & IEEE80211_HE_MAC_CAP0_HTC_HE) { switch (((cap[2] << 1) | (cap[1] >> 7)) & 0x3) { case 0: PRINT("LINK-ADAPTATION-NO-FEEDBACK"); break; case 1: PRINT("LINK-ADAPTATION-RESERVED"); break; case 2: PRINT("LINK-ADAPTATION-UNSOLICITED-FEEDBACK"); break; case 3: PRINT("LINK-ADAPTATION-BOTH"); break; } } PFLAG(MAC, 2, ALL_ACK, "ALL-ACK"); PFLAG(MAC, 2, TRS, "TRS"); PFLAG(MAC, 2, BSR, "BSR"); PFLAG(MAC, 2, BCAST_TWT, "BCAST-TWT"); PFLAG(MAC, 2, 32BIT_BA_BITMAP, "32BIT-BA-BITMAP"); PFLAG(MAC, 2, MU_CASCADING, "MU-CASCADING"); PFLAG(MAC, 2, ACK_EN, "ACK-EN"); PFLAG(MAC, 3, OMI_CONTROL, "OMI-CONTROL"); PFLAG(MAC, 3, OFDMA_RA, "OFDMA-RA"); switch (cap[3] & IEEE80211_HE_MAC_CAP3_MAX_AMPDU_LEN_EXP_MASK) { case IEEE80211_HE_MAC_CAP3_MAX_AMPDU_LEN_EXP_EXT_0: PRINT("MAX-AMPDU-LEN-EXP-USE-EXT-0"); break; case IEEE80211_HE_MAC_CAP3_MAX_AMPDU_LEN_EXP_EXT_1: PRINT("MAX-AMPDU-LEN-EXP-VHT-EXT-1"); break; case IEEE80211_HE_MAC_CAP3_MAX_AMPDU_LEN_EXP_EXT_2: PRINT("MAX-AMPDU-LEN-EXP-VHT-EXT-2"); break; case IEEE80211_HE_MAC_CAP3_MAX_AMPDU_LEN_EXP_EXT_3: PRINT("MAX-AMPDU-LEN-EXP-VHT-EXT-3"); break; } PFLAG(MAC, 3, AMSDU_FRAG, "AMSDU-FRAG"); PFLAG(MAC, 3, FLEX_TWT_SCHED, "FLEX-TWT-SCHED"); PFLAG(MAC, 3, RX_CTRL_FRAME_TO_MULTIBSS, "RX-CTRL-FRAME-TO-MULTIBSS"); PFLAG(MAC, 4, BSRP_BQRP_A_MPDU_AGG, "BSRP-BQRP-A-MPDU-AGG"); PFLAG(MAC, 4, QTP, "QTP"); PFLAG(MAC, 4, BQR, "BQR"); PFLAG(MAC, 4, PSR_RESP, "PSR-RESP"); PFLAG(MAC, 4, NDP_FB_REP, "NDP-FB-REP"); PFLAG(MAC, 4, OPS, "OPS"); PFLAG(MAC, 4, AMSDU_IN_AMPDU, "AMSDU-IN-AMPDU"); PRINT("MULTI-TID-AGG-TX-QOS-%d", ((cap[5] << 1) | (cap[4] >> 7)) & 0x7); PFLAG(MAC, 5, SUBCHAN_SELECTIVE_TRANSMISSION, "SUBCHAN-SELECTIVE-TRANSMISSION"); PFLAG(MAC, 5, UL_2x996_TONE_RU, "UL-2x996-TONE-RU"); PFLAG(MAC, 5, OM_CTRL_UL_MU_DATA_DIS_RX, "OM-CTRL-UL-MU-DATA-DIS-RX"); PFLAG(MAC, 5, HE_DYNAMIC_SM_PS, "HE-DYNAMIC-SM-PS"); PFLAG(MAC, 5, PUNCTURED_SOUNDING, "PUNCTURED-SOUNDING"); PFLAG(MAC, 5, HT_VHT_TRIG_FRAME_RX, "HT-VHT-TRIG-FRAME-RX"); cap = hec->he_cap_elem.phy_cap_info; p += scnprintf(p, buf_sz + buf - p, "PHY CAP: %#.2x %#.2x %#.2x %#.2x %#.2x %#.2x %#.2x %#.2x %#.2x %#.2x %#.2x\n", cap[0], cap[1], cap[2], cap[3], cap[4], cap[5], cap[6], cap[7], cap[8], cap[9], cap[10]); PFLAG(PHY, 0, CHANNEL_WIDTH_SET_40MHZ_IN_2G, "CHANNEL-WIDTH-SET-40MHZ-IN-2G"); PFLAG(PHY, 0, CHANNEL_WIDTH_SET_40MHZ_80MHZ_IN_5G, "CHANNEL-WIDTH-SET-40MHZ-80MHZ-IN-5G"); PFLAG(PHY, 0, CHANNEL_WIDTH_SET_160MHZ_IN_5G, "CHANNEL-WIDTH-SET-160MHZ-IN-5G"); PFLAG(PHY, 0, CHANNEL_WIDTH_SET_80PLUS80_MHZ_IN_5G, "CHANNEL-WIDTH-SET-80PLUS80-MHZ-IN-5G"); PFLAG(PHY, 0, CHANNEL_WIDTH_SET_RU_MAPPING_IN_2G, "CHANNEL-WIDTH-SET-RU-MAPPING-IN-2G"); PFLAG(PHY, 0, CHANNEL_WIDTH_SET_RU_MAPPING_IN_5G, "CHANNEL-WIDTH-SET-RU-MAPPING-IN-5G"); switch (cap[1] & IEEE80211_HE_PHY_CAP1_PREAMBLE_PUNC_RX_MASK) { case IEEE80211_HE_PHY_CAP1_PREAMBLE_PUNC_RX_80MHZ_ONLY_SECOND_20MHZ: PRINT("PREAMBLE-PUNC-RX-80MHZ-ONLY-SECOND-20MHZ"); break; case IEEE80211_HE_PHY_CAP1_PREAMBLE_PUNC_RX_80MHZ_ONLY_SECOND_40MHZ: PRINT("PREAMBLE-PUNC-RX-80MHZ-ONLY-SECOND-40MHZ"); break; case IEEE80211_HE_PHY_CAP1_PREAMBLE_PUNC_RX_160MHZ_ONLY_SECOND_20MHZ: PRINT("PREAMBLE-PUNC-RX-160MHZ-ONLY-SECOND-20MHZ"); break; case IEEE80211_HE_PHY_CAP1_PREAMBLE_PUNC_RX_160MHZ_ONLY_SECOND_40MHZ: PRINT("PREAMBLE-PUNC-RX-160MHZ-ONLY-SECOND-40MHZ"); break; } PFLAG(PHY, 1, DEVICE_CLASS_A, "IEEE80211-HE-PHY-CAP1-DEVICE-CLASS-A"); PFLAG(PHY, 1, LDPC_CODING_IN_PAYLOAD, "LDPC-CODING-IN-PAYLOAD"); PFLAG(PHY, 1, HE_LTF_AND_GI_FOR_HE_PPDUS_0_8US, "HY-CAP1-HE-LTF-AND-GI-FOR-HE-PPDUS-0-8US"); PRINT("MIDAMBLE-RX-MAX-NSTS-%d", ((cap[2] << 1) | (cap[1] >> 7)) & 0x3); PFLAG(PHY, 2, NDP_4x_LTF_AND_3_2US, "NDP-4X-LTF-AND-3-2US"); PFLAG(PHY, 2, STBC_TX_UNDER_80MHZ, "STBC-TX-UNDER-80MHZ"); PFLAG(PHY, 2, STBC_RX_UNDER_80MHZ, "STBC-RX-UNDER-80MHZ"); PFLAG(PHY, 2, DOPPLER_TX, "DOPPLER-TX"); PFLAG(PHY, 2, DOPPLER_RX, "DOPPLER-RX"); PFLAG(PHY, 2, UL_MU_FULL_MU_MIMO, "UL-MU-FULL-MU-MIMO"); PFLAG(PHY, 2, UL_MU_PARTIAL_MU_MIMO, "UL-MU-PARTIAL-MU-MIMO"); switch (cap[3] & IEEE80211_HE_PHY_CAP3_DCM_MAX_CONST_TX_MASK) { case IEEE80211_HE_PHY_CAP3_DCM_MAX_CONST_TX_NO_DCM: PRINT("DCM-MAX-CONST-TX-NO-DCM"); break; case IEEE80211_HE_PHY_CAP3_DCM_MAX_CONST_TX_BPSK: PRINT("DCM-MAX-CONST-TX-BPSK"); break; case IEEE80211_HE_PHY_CAP3_DCM_MAX_CONST_TX_QPSK: PRINT("DCM-MAX-CONST-TX-QPSK"); break; case IEEE80211_HE_PHY_CAP3_DCM_MAX_CONST_TX_16_QAM: PRINT("DCM-MAX-CONST-TX-16-QAM"); break; } PFLAG(PHY, 3, DCM_MAX_TX_NSS_1, "DCM-MAX-TX-NSS-1"); PFLAG(PHY, 3, DCM_MAX_TX_NSS_2, "DCM-MAX-TX-NSS-2"); switch (cap[3] & IEEE80211_HE_PHY_CAP3_DCM_MAX_CONST_RX_MASK) { case IEEE80211_HE_PHY_CAP3_DCM_MAX_CONST_RX_NO_DCM: PRINT("DCM-MAX-CONST-RX-NO-DCM"); break; case IEEE80211_HE_PHY_CAP3_DCM_MAX_CONST_RX_BPSK: PRINT("DCM-MAX-CONST-RX-BPSK"); break; case IEEE80211_HE_PHY_CAP3_DCM_MAX_CONST_RX_QPSK: PRINT("DCM-MAX-CONST-RX-QPSK"); break; case IEEE80211_HE_PHY_CAP3_DCM_MAX_CONST_RX_16_QAM: PRINT("DCM-MAX-CONST-RX-16-QAM"); break; } PFLAG(PHY, 3, DCM_MAX_RX_NSS_1, "DCM-MAX-RX-NSS-1"); PFLAG(PHY, 3, DCM_MAX_RX_NSS_2, "DCM-MAX-RX-NSS-2"); PFLAG(PHY, 3, RX_PARTIAL_BW_SU_IN_20MHZ_MU, "RX-PARTIAL-BW-SU-IN-20MHZ-MU"); PFLAG(PHY, 3, SU_BEAMFORMER, "SU-BEAMFORMER"); PFLAG(PHY, 4, SU_BEAMFORMEE, "SU-BEAMFORMEE"); PFLAG(PHY, 4, MU_BEAMFORMER, "MU-BEAMFORMER"); PFLAG_RANGE(PHY, 4, BEAMFORMEE_MAX_STS_UNDER_80MHZ, 0, 1, 4, "BEAMFORMEE-MAX-STS-UNDER-%d"); PFLAG_RANGE(PHY, 4, BEAMFORMEE_MAX_STS_ABOVE_80MHZ, 0, 1, 4, "BEAMFORMEE-MAX-STS-ABOVE-%d"); PFLAG_RANGE(PHY, 5, BEAMFORMEE_NUM_SND_DIM_UNDER_80MHZ, 0, 1, 1, "NUM-SND-DIM-UNDER-80MHZ-%d"); PFLAG_RANGE(PHY, 5, BEAMFORMEE_NUM_SND_DIM_ABOVE_80MHZ, 0, 1, 1, "NUM-SND-DIM-ABOVE-80MHZ-%d"); PFLAG(PHY, 5, NG16_SU_FEEDBACK, "NG16-SU-FEEDBACK"); PFLAG(PHY, 5, NG16_MU_FEEDBACK, "NG16-MU-FEEDBACK"); PFLAG(PHY, 6, CODEBOOK_SIZE_42_SU, "CODEBOOK-SIZE-42-SU"); PFLAG(PHY, 6, CODEBOOK_SIZE_75_MU, "CODEBOOK-SIZE-75-MU"); PFLAG(PHY, 6, TRIG_SU_BEAMFORMING_FB, "TRIG-SU-BEAMFORMING-FB"); PFLAG(PHY, 6, TRIG_MU_BEAMFORMING_PARTIAL_BW_FB, "MU-BEAMFORMING-PARTIAL-BW-FB"); PFLAG(PHY, 6, TRIG_CQI_FB, "TRIG-CQI-FB"); PFLAG(PHY, 6, PARTIAL_BW_EXT_RANGE, "PARTIAL-BW-EXT-RANGE"); PFLAG(PHY, 6, PARTIAL_BANDWIDTH_DL_MUMIMO, "PARTIAL-BANDWIDTH-DL-MUMIMO"); PFLAG(PHY, 6, PPE_THRESHOLD_PRESENT, "PPE-THRESHOLD-PRESENT"); PFLAG(PHY, 7, PSR_BASED_SR, "PSR-BASED-SR"); PFLAG(PHY, 7, POWER_BOOST_FACTOR_SUPP, "POWER-BOOST-FACTOR-SUPP"); PFLAG(PHY, 7, HE_SU_MU_PPDU_4XLTF_AND_08_US_GI, "HE-SU-MU-PPDU-4XLTF-AND-08-US-GI"); PFLAG_RANGE(PHY, 7, MAX_NC, 0, 1, 1, "MAX-NC-%d"); PFLAG(PHY, 7, STBC_TX_ABOVE_80MHZ, "STBC-TX-ABOVE-80MHZ"); PFLAG(PHY, 7, STBC_RX_ABOVE_80MHZ, "STBC-RX-ABOVE-80MHZ"); PFLAG(PHY, 8, HE_ER_SU_PPDU_4XLTF_AND_08_US_GI, "HE-ER-SU-PPDU-4XLTF-AND-08-US-GI"); PFLAG(PHY, 8, 20MHZ_IN_40MHZ_HE_PPDU_IN_2G, "20MHZ-IN-40MHZ-HE-PPDU-IN-2G"); PFLAG(PHY, 8, 20MHZ_IN_160MHZ_HE_PPDU, "20MHZ-IN-160MHZ-HE-PPDU"); PFLAG(PHY, 8, 80MHZ_IN_160MHZ_HE_PPDU, "80MHZ-IN-160MHZ-HE-PPDU"); PFLAG(PHY, 8, HE_ER_SU_1XLTF_AND_08_US_GI, "HE-ER-SU-1XLTF-AND-08-US-GI"); PFLAG(PHY, 8, MIDAMBLE_RX_TX_2X_AND_1XLTF, "MIDAMBLE-RX-TX-2X-AND-1XLTF"); switch (cap[8] & IEEE80211_HE_PHY_CAP8_DCM_MAX_RU_MASK) { case IEEE80211_HE_PHY_CAP8_DCM_MAX_RU_242: PRINT("DCM-MAX-RU-242"); break; case IEEE80211_HE_PHY_CAP8_DCM_MAX_RU_484: PRINT("DCM-MAX-RU-484"); break; case IEEE80211_HE_PHY_CAP8_DCM_MAX_RU_996: PRINT("DCM-MAX-RU-996"); break; case IEEE80211_HE_PHY_CAP8_DCM_MAX_RU_2x996: PRINT("DCM-MAX-RU-2x996"); break; } PFLAG(PHY, 9, LONGER_THAN_16_SIGB_OFDM_SYM, "LONGER-THAN-16-SIGB-OFDM-SYM"); PFLAG(PHY, 9, NON_TRIGGERED_CQI_FEEDBACK, "NON-TRIGGERED-CQI-FEEDBACK"); PFLAG(PHY, 9, TX_1024_QAM_LESS_THAN_242_TONE_RU, "TX-1024-QAM-LESS-THAN-242-TONE-RU"); PFLAG(PHY, 9, RX_1024_QAM_LESS_THAN_242_TONE_RU, "RX-1024-QAM-LESS-THAN-242-TONE-RU"); PFLAG(PHY, 9, RX_FULL_BW_SU_USING_MU_WITH_COMP_SIGB, "RX-FULL-BW-SU-USING-MU-WITH-COMP-SIGB"); PFLAG(PHY, 9, RX_FULL_BW_SU_USING_MU_WITH_NON_COMP_SIGB, "RX-FULL-BW-SU-USING-MU-WITH-NON-COMP-SIGB"); switch (u8_get_bits(cap[9], IEEE80211_HE_PHY_CAP9_NOMINAL_PKT_PADDING_MASK)) { case IEEE80211_HE_PHY_CAP9_NOMINAL_PKT_PADDING_0US: PRINT("NOMINAL-PACKET-PADDING-0US"); break; case IEEE80211_HE_PHY_CAP9_NOMINAL_PKT_PADDING_8US: PRINT("NOMINAL-PACKET-PADDING-8US"); break; case IEEE80211_HE_PHY_CAP9_NOMINAL_PKT_PADDING_16US: PRINT("NOMINAL-PACKET-PADDING-16US"); break; } #undef PFLAG_RANGE_DEFAULT #undef PFLAG_RANGE #undef PFLAG #define PRINT_NSS_SUPP(f, n) \ do { \ int _i; \ u16 v = le16_to_cpu(nss->f); \ p += scnprintf(p, buf_sz + buf - p, n ": %#.4x\n", v); \ for (_i = 0; _i < 8; _i += 2) { \ switch ((v >> _i) & 0x3) { \ case 0: \ PRINT(n "-%d-SUPPORT-0-7", _i / 2); \ break; \ case 1: \ PRINT(n "-%d-SUPPORT-0-9", _i / 2); \ break; \ case 2: \ PRINT(n "-%d-SUPPORT-0-11", _i / 2); \ break; \ case 3: \ PRINT(n "-%d-NOT-SUPPORTED", _i / 2); \ break; \ } \ } \ } while (0) PRINT_NSS_SUPP(rx_mcs_80, "RX-MCS-80"); PRINT_NSS_SUPP(tx_mcs_80, "TX-MCS-80"); if (cap[0] & IEEE80211_HE_PHY_CAP0_CHANNEL_WIDTH_SET_160MHZ_IN_5G) { PRINT_NSS_SUPP(rx_mcs_160, "RX-MCS-160"); PRINT_NSS_SUPP(tx_mcs_160, "TX-MCS-160"); } if (cap[0] & IEEE80211_HE_PHY_CAP0_CHANNEL_WIDTH_SET_80PLUS80_MHZ_IN_5G) { PRINT_NSS_SUPP(rx_mcs_80p80, "RX-MCS-80P80"); PRINT_NSS_SUPP(tx_mcs_80p80, "TX-MCS-80P80"); } #undef PRINT_NSS_SUPP #undef PRINT if (!(cap[6] & IEEE80211_HE_PHY_CAP6_PPE_THRESHOLD_PRESENT)) goto out; p += scnprintf(p, buf_sz + buf - p, "PPE-THRESHOLDS: %#.2x", hec->ppe_thres[0]); ppe_size = ieee80211_he_ppe_size(hec->ppe_thres[0], cap); for (i = 1; i < ppe_size; i++) { p += scnprintf(p, buf_sz + buf - p, " %#.2x", hec->ppe_thres[i]); } p += scnprintf(p, buf_sz + buf - p, "\n"); out: ret = simple_read_from_buffer(userbuf, count, ppos, buf, p - buf); kfree(buf); return ret; } LINK_STA_OPS(he_capa); static ssize_t link_sta_eht_capa_read(struct file *file, char __user *userbuf, size_t count, loff_t *ppos) { char *buf, *p; size_t buf_sz = PAGE_SIZE; struct link_sta_info *link_sta = file->private_data; struct ieee80211_sta_eht_cap *bec = &link_sta->pub->eht_cap; struct ieee80211_eht_cap_elem_fixed *fixed = &bec->eht_cap_elem; struct ieee80211_eht_mcs_nss_supp *nss = &bec->eht_mcs_nss_supp; u8 *cap; int i; ssize_t ret; static const char *mcs_desc[] = { "0-7", "8-9", "10-11", "12-13"}; buf = kmalloc(buf_sz, GFP_KERNEL); if (!buf) return -ENOMEM; p = buf; p += scnprintf(p, buf_sz + buf - p, "EHT %ssupported\n", bec->has_eht ? "" : "not "); if (!bec->has_eht) goto out; p += scnprintf(p, buf_sz + buf - p, "MAC-CAP: %#.2x %#.2x\n", fixed->mac_cap_info[0], fixed->mac_cap_info[1]); p += scnprintf(p, buf_sz + buf - p, "PHY-CAP: %#.2x %#.2x %#.2x %#.2x %#.2x %#.2x %#.2x %#.2x %#.2x\n", fixed->phy_cap_info[0], fixed->phy_cap_info[1], fixed->phy_cap_info[2], fixed->phy_cap_info[3], fixed->phy_cap_info[4], fixed->phy_cap_info[5], fixed->phy_cap_info[6], fixed->phy_cap_info[7], fixed->phy_cap_info[8]); #define PRINT(fmt, ...) \ p += scnprintf(p, buf_sz + buf - p, "\t\t" fmt "\n", \ ##__VA_ARGS__) #define PFLAG(t, n, a, b) \ do { \ if (cap[n] & IEEE80211_EHT_##t##_CAP##n##_##a) \ PRINT("%s", b); \ } while (0) cap = fixed->mac_cap_info; PFLAG(MAC, 0, EPCS_PRIO_ACCESS, "EPCS-PRIO-ACCESS"); PFLAG(MAC, 0, OM_CONTROL, "OM-CONTROL"); PFLAG(MAC, 0, TRIG_TXOP_SHARING_MODE1, "TRIG-TXOP-SHARING-MODE1"); PFLAG(MAC, 0, TRIG_TXOP_SHARING_MODE2, "TRIG-TXOP-SHARING-MODE2"); PFLAG(MAC, 0, RESTRICTED_TWT, "RESTRICTED-TWT"); PFLAG(MAC, 0, SCS_TRAFFIC_DESC, "SCS-TRAFFIC-DESC"); switch ((cap[0] & 0xc0) >> 6) { case IEEE80211_EHT_MAC_CAP0_MAX_MPDU_LEN_3895: PRINT("MAX-MPDU-LEN: 3985"); break; case IEEE80211_EHT_MAC_CAP0_MAX_MPDU_LEN_7991: PRINT("MAX-MPDU-LEN: 7991"); break; case IEEE80211_EHT_MAC_CAP0_MAX_MPDU_LEN_11454: PRINT("MAX-MPDU-LEN: 11454"); break; } cap = fixed->phy_cap_info; PFLAG(PHY, 0, 320MHZ_IN_6GHZ, "320MHZ-IN-6GHZ"); PFLAG(PHY, 0, 242_TONE_RU_GT20MHZ, "242-TONE-RU-GT20MHZ"); PFLAG(PHY, 0, NDP_4_EHT_LFT_32_GI, "NDP-4-EHT-LFT-32-GI"); PFLAG(PHY, 0, PARTIAL_BW_UL_MU_MIMO, "PARTIAL-BW-UL-MU-MIMO"); PFLAG(PHY, 0, SU_BEAMFORMER, "SU-BEAMFORMER"); PFLAG(PHY, 0, SU_BEAMFORMEE, "SU-BEAMFORMEE"); i = cap[0] >> 7; i |= (cap[1] & 0x3) << 1; PRINT("BEAMFORMEE-80-NSS: %i", i); PRINT("BEAMFORMEE-160-NSS: %i", (cap[1] >> 2) & 0x7); PRINT("BEAMFORMEE-320-NSS: %i", (cap[1] >> 5) & 0x7); PRINT("SOUNDING-DIM-80-NSS: %i", (cap[2] & 0x7)); PRINT("SOUNDING-DIM-160-NSS: %i", (cap[2] >> 3) & 0x7); i = cap[2] >> 6; i |= (cap[3] & 0x1) << 3; PRINT("SOUNDING-DIM-320-NSS: %i", i); PFLAG(PHY, 3, NG_16_SU_FEEDBACK, "NG-16-SU-FEEDBACK"); PFLAG(PHY, 3, NG_16_MU_FEEDBACK, "NG-16-MU-FEEDBACK"); PFLAG(PHY, 3, CODEBOOK_4_2_SU_FDBK, "CODEBOOK-4-2-SU-FDBK"); PFLAG(PHY, 3, CODEBOOK_7_5_MU_FDBK, "CODEBOOK-7-5-MU-FDBK"); PFLAG(PHY, 3, TRIG_SU_BF_FDBK, "TRIG-SU-BF-FDBK"); PFLAG(PHY, 3, TRIG_MU_BF_PART_BW_FDBK, "TRIG-MU-BF-PART-BW-FDBK"); PFLAG(PHY, 3, TRIG_CQI_FDBK, "TRIG-CQI-FDBK"); PFLAG(PHY, 4, PART_BW_DL_MU_MIMO, "PART-BW-DL-MU-MIMO"); PFLAG(PHY, 4, PSR_SR_SUPP, "PSR-SR-SUPP"); PFLAG(PHY, 4, POWER_BOOST_FACT_SUPP, "POWER-BOOST-FACT-SUPP"); PFLAG(PHY, 4, EHT_MU_PPDU_4_EHT_LTF_08_GI, "EHT-MU-PPDU-4-EHT-LTF-08-GI"); PRINT("MAX_NC: %i", cap[4] >> 4); PFLAG(PHY, 5, NON_TRIG_CQI_FEEDBACK, "NON-TRIG-CQI-FEEDBACK"); PFLAG(PHY, 5, TX_LESS_242_TONE_RU_SUPP, "TX-LESS-242-TONE-RU-SUPP"); PFLAG(PHY, 5, RX_LESS_242_TONE_RU_SUPP, "RX-LESS-242-TONE-RU-SUPP"); PFLAG(PHY, 5, PPE_THRESHOLD_PRESENT, "PPE_THRESHOLD_PRESENT"); switch (cap[5] >> 4 & 0x3) { case IEEE80211_EHT_PHY_CAP5_COMMON_NOMINAL_PKT_PAD_0US: PRINT("NOMINAL_PKT_PAD: 0us"); break; case IEEE80211_EHT_PHY_CAP5_COMMON_NOMINAL_PKT_PAD_8US: PRINT("NOMINAL_PKT_PAD: 8us"); break; case IEEE80211_EHT_PHY_CAP5_COMMON_NOMINAL_PKT_PAD_16US: PRINT("NOMINAL_PKT_PAD: 16us"); break; case IEEE80211_EHT_PHY_CAP5_COMMON_NOMINAL_PKT_PAD_20US: PRINT("NOMINAL_PKT_PAD: 20us"); break; } i = cap[5] >> 6; i |= cap[6] & 0x7; PRINT("MAX-NUM-SUPP-EHT-LTF: %i", i); PFLAG(PHY, 5, SUPP_EXTRA_EHT_LTF, "SUPP-EXTRA-EHT-LTF"); i = (cap[6] >> 3) & 0xf; PRINT("MCS15-SUPP-MASK: %i", i); PFLAG(PHY, 6, EHT_DUP_6GHZ_SUPP, "EHT-DUP-6GHZ-SUPP"); PFLAG(PHY, 7, 20MHZ_STA_RX_NDP_WIDER_BW, "20MHZ-STA-RX-NDP-WIDER-BW"); PFLAG(PHY, 7, NON_OFDMA_UL_MU_MIMO_80MHZ, "NON-OFDMA-UL-MU-MIMO-80MHZ"); PFLAG(PHY, 7, NON_OFDMA_UL_MU_MIMO_160MHZ, "NON-OFDMA-UL-MU-MIMO-160MHZ"); PFLAG(PHY, 7, NON_OFDMA_UL_MU_MIMO_320MHZ, "NON-OFDMA-UL-MU-MIMO-320MHZ"); PFLAG(PHY, 7, MU_BEAMFORMER_80MHZ, "MU-BEAMFORMER-80MHZ"); PFLAG(PHY, 7, MU_BEAMFORMER_160MHZ, "MU-BEAMFORMER-160MHZ"); PFLAG(PHY, 7, MU_BEAMFORMER_320MHZ, "MU-BEAMFORMER-320MHZ"); PFLAG(PHY, 7, TB_SOUNDING_FDBK_RATE_LIMIT, "TB-SOUNDING-FDBK-RATE-LIMIT"); PFLAG(PHY, 8, RX_1024QAM_WIDER_BW_DL_OFDMA, "RX-1024QAM-WIDER-BW-DL-OFDMA"); PFLAG(PHY, 8, RX_4096QAM_WIDER_BW_DL_OFDMA, "RX-4096QAM-WIDER-BW-DL-OFDMA"); #undef PFLAG PRINT(""); /* newline */ if (!(link_sta->pub->he_cap.he_cap_elem.phy_cap_info[0] & IEEE80211_HE_PHY_CAP0_CHANNEL_WIDTH_SET_MASK_ALL)) { u8 *mcs_vals = (u8 *)(&nss->only_20mhz); for (i = 0; i < 4; i++) PRINT("EHT bw=20 MHz, max NSS for MCS %s: Rx=%u, Tx=%u", mcs_desc[i], mcs_vals[i] & 0xf, mcs_vals[i] >> 4); } else { u8 *mcs_vals = (u8 *)(&nss->bw._80); for (i = 0; i < 3; i++) PRINT("EHT bw <= 80 MHz, max NSS for MCS %s: Rx=%u, Tx=%u", mcs_desc[i + 1], mcs_vals[i] & 0xf, mcs_vals[i] >> 4); mcs_vals = (u8 *)(&nss->bw._160); for (i = 0; i < 3; i++) PRINT("EHT bw <= 160 MHz, max NSS for MCS %s: Rx=%u, Tx=%u", mcs_desc[i + 1], mcs_vals[i] & 0xf, mcs_vals[i] >> 4); mcs_vals = (u8 *)(&nss->bw._320); for (i = 0; i < 3; i++) PRINT("EHT bw <= 320 MHz, max NSS for MCS %s: Rx=%u, Tx=%u", mcs_desc[i + 1], mcs_vals[i] & 0xf, mcs_vals[i] >> 4); } if (cap[5] & IEEE80211_EHT_PHY_CAP5_PPE_THRESHOLD_PRESENT) { u8 ppe_size = ieee80211_eht_ppe_size(bec->eht_ppe_thres[0], cap); p += scnprintf(p, buf_sz + buf - p, "EHT PPE Thresholds: "); for (i = 0; i < ppe_size; i++) p += scnprintf(p, buf_sz + buf - p, "0x%02x ", bec->eht_ppe_thres[i]); PRINT(""); /* newline */ } out: ret = simple_read_from_buffer(userbuf, count, ppos, buf, p - buf); kfree(buf); return ret; } LINK_STA_OPS(eht_capa); #define DEBUGFS_ADD(name) \ debugfs_create_file(#name, 0400, \ sta->debugfs_dir, sta, &sta_ ##name## _ops) #define DEBUGFS_ADD_COUNTER(name, field) \ debugfs_create_ulong(#name, 0400, sta->debugfs_dir, &sta->field); void ieee80211_sta_debugfs_add(struct sta_info *sta) { struct ieee80211_local *local = sta->local; struct ieee80211_sub_if_data *sdata = sta->sdata; struct dentry *stations_dir = sta->sdata->debugfs.subdir_stations; u8 mac[3*ETH_ALEN]; if (!stations_dir) return; snprintf(mac, sizeof(mac), "%pM", sta->sta.addr); /* * This might fail due to a race condition: * When mac80211 unlinks a station, the debugfs entries * remain, but it is already possible to link a new * station with the same address which triggers adding * it to debugfs; therefore, if the old station isn't * destroyed quickly enough the old station's debugfs * dir might still be around. */ sta->debugfs_dir = debugfs_create_dir(mac, stations_dir); DEBUGFS_ADD(flags); DEBUGFS_ADD(aid); DEBUGFS_ADD(num_ps_buf_frames); DEBUGFS_ADD(last_seq_ctrl); DEBUGFS_ADD(agg_status); /* FIXME: Kept here as the statistics are only done on the deflink */ DEBUGFS_ADD_COUNTER(tx_filtered, deflink.status_stats.filtered); DEBUGFS_ADD(aqm); DEBUGFS_ADD(airtime); if (wiphy_ext_feature_isset(local->hw.wiphy, NL80211_EXT_FEATURE_AQL)) DEBUGFS_ADD(aql); debugfs_create_xul("driver_buffered_tids", 0400, sta->debugfs_dir, &sta->driver_buffered_tids); drv_sta_add_debugfs(local, sdata, &sta->sta, sta->debugfs_dir); } void ieee80211_sta_debugfs_remove(struct sta_info *sta) { debugfs_remove_recursive(sta->debugfs_dir); sta->debugfs_dir = NULL; } #undef DEBUGFS_ADD #undef DEBUGFS_ADD_COUNTER #define DEBUGFS_ADD(name) \ debugfs_create_file(#name, 0400, \ link_sta->debugfs_dir, link_sta, &link_sta_ ##name## _ops) #define DEBUGFS_ADD_COUNTER(name, field) \ debugfs_create_ulong(#name, 0400, link_sta->debugfs_dir, &link_sta->field) void ieee80211_link_sta_debugfs_add(struct link_sta_info *link_sta) { if (WARN_ON(!link_sta->sta->debugfs_dir)) return; /* For non-MLO, leave the files in the main directory. */ if (link_sta->sta->sta.valid_links) { char link_dir_name[10]; snprintf(link_dir_name, sizeof(link_dir_name), "link-%d", link_sta->link_id); link_sta->debugfs_dir = debugfs_create_dir(link_dir_name, link_sta->sta->debugfs_dir); DEBUGFS_ADD(addr); } else { if (WARN_ON(link_sta != &link_sta->sta->deflink)) return; link_sta->debugfs_dir = link_sta->sta->debugfs_dir; } DEBUGFS_ADD(ht_capa); DEBUGFS_ADD(vht_capa); DEBUGFS_ADD(he_capa); DEBUGFS_ADD(eht_capa); DEBUGFS_ADD_COUNTER(rx_duplicates, rx_stats.num_duplicates); DEBUGFS_ADD_COUNTER(rx_fragments, rx_stats.fragments); } void ieee80211_link_sta_debugfs_remove(struct link_sta_info *link_sta) { if (!link_sta->debugfs_dir || !link_sta->sta->debugfs_dir) { link_sta->debugfs_dir = NULL; return; } if (link_sta->debugfs_dir == link_sta->sta->debugfs_dir) { WARN_ON(link_sta != &link_sta->sta->deflink); link_sta->sta->debugfs_dir = NULL; return; } debugfs_remove_recursive(link_sta->debugfs_dir); link_sta->debugfs_dir = NULL; } void ieee80211_link_sta_debugfs_drv_add(struct link_sta_info *link_sta) { if (WARN_ON(!link_sta->debugfs_dir)) return; drv_link_sta_add_debugfs(link_sta->sta->local, link_sta->sta->sdata, link_sta->pub, link_sta->debugfs_dir); } void ieee80211_link_sta_debugfs_drv_remove(struct link_sta_info *link_sta) { if (!link_sta->debugfs_dir) return; if (WARN_ON(link_sta->debugfs_dir == link_sta->sta->debugfs_dir)) return; /* Recreate the directory excluding the driver data */ debugfs_remove_recursive(link_sta->debugfs_dir); link_sta->debugfs_dir = NULL; ieee80211_link_sta_debugfs_add(link_sta); } |
| 93 93 7 5 9 260 60 5 2 3 5 7 1 2 2 1 2 2 1 1 80 79 80 80 80 62 15 19 50 13 82 16 73 73 72 2 204 48 36 66 81 41 19 113 50 1 2 6 65 58 162 268 269 212 66 2 267 268 8 265 163 12 159 6 128 72 127 102 102 43 42 96 89 10 94 94 16 75 58 45 62 62 32 62 62 59 59 57 59 59 59 7 56 6 6 4 6 6 39 64 27 19 13 33 32 27 18 1 18 62 64 93 52 52 119 118 162 2 26 15 19 13 26 5 6 6 2 4 29 28 29 1 25 25 26 22 9 9 22 1 2 2 7 3 13 1 8 7 1 4 5 8 24 2 32 4 29 27 208 208 185 40 99 100 207 26 13 13 13 13 6 6 6 6 6 6 6 60 59 46 14 5 13 11 60 60 58 1 1 54 6 6 54 54 41 41 41 13 292 292 291 292 121 117 13 3 119 26 116 11 121 121 121 121 120 120 121 7 7 2 2 4 1 4 16 7 9 10 28 10 28 28 3 1 2 1 1 1 1 15 13 2 11 11 2 15 14 4 5 1 2 1 164 1 3 8 1 1 9 15 1 8 14 110 2 2 2 2 2 1 1 11 9 3 3 2 1 1 1 1 3 2 3 3 2 5 3 2 5 3 2 6 4 3 3 1 1 2 2 4 2 1 2 4 225 61 163 8 3 29 29 7 5 7 5 7 5 9 9 9 9 9 9 9 3 9 86 86 86 86 82 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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 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 | // SPDX-License-Identifier: GPL-2.0-or-later /* * INET An implementation of the TCP/IP protocol suite for the LINUX * operating system. INET is implemented using the BSD Socket * interface as the means of communication with the user level. * * Implementation of the Transmission Control Protocol(TCP). * * Authors: Ross Biro * Fred N. van Kempen, <waltje@uWalt.NL.Mugnet.ORG> * Mark Evans, <evansmp@uhura.aston.ac.uk> * Corey Minyard <wf-rch!minyard@relay.EU.net> * Florian La Roche, <flla@stud.uni-sb.de> * Charles Hedrick, <hedrick@klinzhai.rutgers.edu> * Linus Torvalds, <torvalds@cs.helsinki.fi> * Alan Cox, <gw4pts@gw4pts.ampr.org> * Matthew Dillon, <dillon@apollo.west.oic.com> * Arnt Gulbrandsen, <agulbra@nvg.unit.no> * Jorge Cwik, <jorge@laser.satlink.net> * * Fixes: * Alan Cox : Numerous verify_area() calls * Alan Cox : Set the ACK bit on a reset * Alan Cox : Stopped it crashing if it closed while * sk->inuse=1 and was trying to connect * (tcp_err()). * Alan Cox : All icmp error handling was broken * pointers passed where wrong and the * socket was looked up backwards. Nobody * tested any icmp error code obviously. * Alan Cox : tcp_err() now handled properly. It * wakes people on errors. poll * behaves and the icmp error race * has gone by moving it into sock.c * Alan Cox : tcp_send_reset() fixed to work for * everything not just packets for * unknown sockets. * Alan Cox : tcp option processing. * Alan Cox : Reset tweaked (still not 100%) [Had * syn rule wrong] * Herp Rosmanith : More reset fixes * Alan Cox : No longer acks invalid rst frames. * Acking any kind of RST is right out. * Alan Cox : Sets an ignore me flag on an rst * receive otherwise odd bits of prattle * escape still * Alan Cox : Fixed another acking RST frame bug. * Should stop LAN workplace lockups. * Alan Cox : Some tidyups using the new skb list * facilities * Alan Cox : sk->keepopen now seems to work * Alan Cox : Pulls options out correctly on accepts * Alan Cox : Fixed assorted sk->rqueue->next errors * Alan Cox : PSH doesn't end a TCP read. Switched a * bit to skb ops. * Alan Cox : Tidied tcp_data to avoid a potential * nasty. * Alan Cox : Added some better commenting, as the * tcp is hard to follow * Alan Cox : Removed incorrect check for 20 * psh * Michael O'Reilly : ack < copied bug fix. * Johannes Stille : Misc tcp fixes (not all in yet). * Alan Cox : FIN with no memory -> CRASH * Alan Cox : Added socket option proto entries. * Also added awareness of them to accept. * Alan Cox : Added TCP options (SOL_TCP) * Alan Cox : Switched wakeup calls to callbacks, * so the kernel can layer network * sockets. * Alan Cox : Use ip_tos/ip_ttl settings. * Alan Cox : Handle FIN (more) properly (we hope). * Alan Cox : RST frames sent on unsynchronised * state ack error. * Alan Cox : Put in missing check for SYN bit. * Alan Cox : Added tcp_select_window() aka NET2E * window non shrink trick. * Alan Cox : Added a couple of small NET2E timer * fixes * Charles Hedrick : TCP fixes * Toomas Tamm : TCP window fixes * Alan Cox : Small URG fix to rlogin ^C ack fight * Charles Hedrick : Rewrote most of it to actually work * Linus : Rewrote tcp_read() and URG handling * completely * Gerhard Koerting: Fixed some missing timer handling * Matthew Dillon : Reworked TCP machine states as per RFC * Gerhard Koerting: PC/TCP workarounds * Adam Caldwell : Assorted timer/timing errors * Matthew Dillon : Fixed another RST bug * Alan Cox : Move to kernel side addressing changes. * Alan Cox : Beginning work on TCP fastpathing * (not yet usable) * Arnt Gulbrandsen: Turbocharged tcp_check() routine. * Alan Cox : TCP fast path debugging * Alan Cox : Window clamping * Michael Riepe : Bug in tcp_check() * Matt Dillon : More TCP improvements and RST bug fixes * Matt Dillon : Yet more small nasties remove from the * TCP code (Be very nice to this man if * tcp finally works 100%) 8) * Alan Cox : BSD accept semantics. * Alan Cox : Reset on closedown bug. * Peter De Schrijver : ENOTCONN check missing in tcp_sendto(). * Michael Pall : Handle poll() after URG properly in * all cases. * Michael Pall : Undo the last fix in tcp_read_urg() * (multi URG PUSH broke rlogin). * Michael Pall : Fix the multi URG PUSH problem in * tcp_readable(), poll() after URG * works now. * Michael Pall : recv(...,MSG_OOB) never blocks in the * BSD api. * Alan Cox : Changed the semantics of sk->socket to * fix a race and a signal problem with * accept() and async I/O. * Alan Cox : Relaxed the rules on tcp_sendto(). * Yury Shevchuk : Really fixed accept() blocking problem. * Craig I. Hagan : Allow for BSD compatible TIME_WAIT for * clients/servers which listen in on * fixed ports. * Alan Cox : Cleaned the above up and shrank it to * a sensible code size. * Alan Cox : Self connect lockup fix. * Alan Cox : No connect to multicast. * Ross Biro : Close unaccepted children on master * socket close. * Alan Cox : Reset tracing code. * Alan Cox : Spurious resets on shutdown. * Alan Cox : Giant 15 minute/60 second timer error * Alan Cox : Small whoops in polling before an * accept. * Alan Cox : Kept the state trace facility since * it's handy for debugging. * Alan Cox : More reset handler fixes. * Alan Cox : Started rewriting the code based on * the RFC's for other useful protocol * references see: Comer, KA9Q NOS, and * for a reference on the difference * between specifications and how BSD * works see the 4.4lite source. * A.N.Kuznetsov : Don't time wait on completion of tidy * close. * Linus Torvalds : Fin/Shutdown & copied_seq changes. * Linus Torvalds : Fixed BSD port reuse to work first syn * Alan Cox : Reimplemented timers as per the RFC * and using multiple timers for sanity. * Alan Cox : Small bug fixes, and a lot of new * comments. * Alan Cox : Fixed dual reader crash by locking * the buffers (much like datagram.c) * Alan Cox : Fixed stuck sockets in probe. A probe * now gets fed up of retrying without * (even a no space) answer. * Alan Cox : Extracted closing code better * Alan Cox : Fixed the closing state machine to * resemble the RFC. * Alan Cox : More 'per spec' fixes. * Jorge Cwik : Even faster checksumming. * Alan Cox : tcp_data() doesn't ack illegal PSH * only frames. At least one pc tcp stack * generates them. * Alan Cox : Cache last socket. * Alan Cox : Per route irtt. * Matt Day : poll()->select() match BSD precisely on error * Alan Cox : New buffers * Marc Tamsky : Various sk->prot->retransmits and * sk->retransmits misupdating fixed. * Fixed tcp_write_timeout: stuck close, * and TCP syn retries gets used now. * Mark Yarvis : In tcp_read_wakeup(), don't send an * ack if state is TCP_CLOSED. * Alan Cox : Look up device on a retransmit - routes may * change. Doesn't yet cope with MSS shrink right * but it's a start! * Marc Tamsky : Closing in closing fixes. * Mike Shaver : RFC1122 verifications. * Alan Cox : rcv_saddr errors. * Alan Cox : Block double connect(). * Alan Cox : Small hooks for enSKIP. * Alexey Kuznetsov: Path MTU discovery. * Alan Cox : Support soft errors. * Alan Cox : Fix MTU discovery pathological case * when the remote claims no mtu! * Marc Tamsky : TCP_CLOSE fix. * Colin (G3TNE) : Send a reset on syn ack replies in * window but wrong (fixes NT lpd problems) * Pedro Roque : Better TCP window handling, delayed ack. * Joerg Reuter : No modification of locked buffers in * tcp_do_retransmit() * Eric Schenk : Changed receiver side silly window * avoidance algorithm to BSD style * algorithm. This doubles throughput * against machines running Solaris, * and seems to result in general * improvement. * Stefan Magdalinski : adjusted tcp_readable() to fix FIONREAD * Willy Konynenberg : Transparent proxying support. * Mike McLagan : Routing by source * Keith Owens : Do proper merging with partial SKB's in * tcp_do_sendmsg to avoid burstiness. * Eric Schenk : Fix fast close down bug with * shutdown() followed by close(). * Andi Kleen : Make poll agree with SIGIO * Salvatore Sanfilippo : Support SO_LINGER with linger == 1 and * lingertime == 0 (RFC 793 ABORT Call) * Hirokazu Takahashi : Use copy_from_user() instead of * csum_and_copy_from_user() if possible. * * Description of States: * * TCP_SYN_SENT sent a connection request, waiting for ack * * TCP_SYN_RECV received a connection request, sent ack, * waiting for final ack in three-way handshake. * * TCP_ESTABLISHED connection established * * TCP_FIN_WAIT1 our side has shutdown, waiting to complete * transmission of remaining buffered data * * TCP_FIN_WAIT2 all buffered data sent, waiting for remote * to shutdown * * TCP_CLOSING both sides have shutdown but we still have * data we have to finish sending * * TCP_TIME_WAIT timeout to catch resent junk before entering * closed, can only be entered from FIN_WAIT2 * or CLOSING. Required because the other end * may not have gotten our last ACK causing it * to retransmit the data packet (which we ignore) * * TCP_CLOSE_WAIT remote side has shutdown and is waiting for * us to finish writing our data and to shutdown * (we have to close() to move on to LAST_ACK) * * TCP_LAST_ACK out side has shutdown after remote has * shutdown. There may still be data in our * buffer that we have to finish sending * * TCP_CLOSE socket is finished */ #define pr_fmt(fmt) "TCP: " fmt #include <crypto/hash.h> #include <linux/kernel.h> #include <linux/module.h> #include <linux/types.h> #include <linux/fcntl.h> #include <linux/poll.h> #include <linux/inet_diag.h> #include <linux/init.h> #include <linux/fs.h> #include <linux/skbuff.h> #include <linux/scatterlist.h> #include <linux/splice.h> #include <linux/net.h> #include <linux/socket.h> #include <linux/random.h> #include <linux/memblock.h> #include <linux/highmem.h> #include <linux/cache.h> #include <linux/err.h> #include <linux/time.h> #include <linux/slab.h> #include <linux/errqueue.h> #include <linux/static_key.h> #include <linux/btf.h> #include <net/icmp.h> #include <net/inet_common.h> #include <net/tcp.h> #include <net/mptcp.h> #include <net/proto_memory.h> #include <net/xfrm.h> #include <net/ip.h> #include <net/sock.h> #include <net/rstreason.h> #include <linux/uaccess.h> #include <asm/ioctls.h> #include <net/busy_poll.h> #include <net/hotdata.h> #include <trace/events/tcp.h> #include <net/rps.h> #include "../core/devmem.h" /* Track pending CMSGs. */ enum { TCP_CMSG_INQ = 1, TCP_CMSG_TS = 2 }; DEFINE_PER_CPU(unsigned int, tcp_orphan_count); EXPORT_PER_CPU_SYMBOL_GPL(tcp_orphan_count); DEFINE_PER_CPU(u32, tcp_tw_isn); EXPORT_PER_CPU_SYMBOL_GPL(tcp_tw_isn); long sysctl_tcp_mem[3] __read_mostly; EXPORT_SYMBOL(sysctl_tcp_mem); atomic_long_t tcp_memory_allocated ____cacheline_aligned_in_smp; /* Current allocated memory. */ EXPORT_SYMBOL(tcp_memory_allocated); DEFINE_PER_CPU(int, tcp_memory_per_cpu_fw_alloc); EXPORT_PER_CPU_SYMBOL_GPL(tcp_memory_per_cpu_fw_alloc); #if IS_ENABLED(CONFIG_SMC) DEFINE_STATIC_KEY_FALSE(tcp_have_smc); EXPORT_SYMBOL(tcp_have_smc); #endif /* * Current number of TCP sockets. */ struct percpu_counter tcp_sockets_allocated ____cacheline_aligned_in_smp; EXPORT_SYMBOL(tcp_sockets_allocated); /* * TCP splice context */ struct tcp_splice_state { struct pipe_inode_info *pipe; size_t len; unsigned int flags; }; /* * Pressure flag: try to collapse. * Technical note: it is used by multiple contexts non atomically. * All the __sk_mem_schedule() is of this nature: accounting * is strict, actions are advisory and have some latency. */ unsigned long tcp_memory_pressure __read_mostly; EXPORT_SYMBOL_GPL(tcp_memory_pressure); void tcp_enter_memory_pressure(struct sock *sk) { unsigned long val; if (READ_ONCE(tcp_memory_pressure)) return; val = jiffies; if (!val) val--; if (!cmpxchg(&tcp_memory_pressure, 0, val)) NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPMEMORYPRESSURES); } EXPORT_SYMBOL_GPL(tcp_enter_memory_pressure); void tcp_leave_memory_pressure(struct sock *sk) { unsigned long val; if (!READ_ONCE(tcp_memory_pressure)) return; val = xchg(&tcp_memory_pressure, 0); if (val) NET_ADD_STATS(sock_net(sk), LINUX_MIB_TCPMEMORYPRESSURESCHRONO, jiffies_to_msecs(jiffies - val)); } EXPORT_SYMBOL_GPL(tcp_leave_memory_pressure); /* Convert seconds to retransmits based on initial and max timeout */ static u8 secs_to_retrans(int seconds, int timeout, int rto_max) { u8 res = 0; if (seconds > 0) { int period = timeout; res = 1; while (seconds > period && res < 255) { res++; timeout <<= 1; if (timeout > rto_max) timeout = rto_max; period += timeout; } } return res; } /* Convert retransmits to seconds based on initial and max timeout */ static int retrans_to_secs(u8 retrans, int timeout, int rto_max) { int period = 0; if (retrans > 0) { period = timeout; while (--retrans) { timeout <<= 1; if (timeout > rto_max) timeout = rto_max; period += timeout; } } return period; } static u64 tcp_compute_delivery_rate(const struct tcp_sock *tp) { u32 rate = READ_ONCE(tp->rate_delivered); u32 intv = READ_ONCE(tp->rate_interval_us); u64 rate64 = 0; if (rate && intv) { rate64 = (u64)rate * tp->mss_cache * USEC_PER_SEC; do_div(rate64, intv); } return rate64; } /* Address-family independent initialization for a tcp_sock. * * NOTE: A lot of things set to zero explicitly by call to * sk_alloc() so need not be done here. */ void tcp_init_sock(struct sock *sk) { struct inet_connection_sock *icsk = inet_csk(sk); struct tcp_sock *tp = tcp_sk(sk); int rto_min_us; tp->out_of_order_queue = RB_ROOT; sk->tcp_rtx_queue = RB_ROOT; tcp_init_xmit_timers(sk); INIT_LIST_HEAD(&tp->tsq_node); INIT_LIST_HEAD(&tp->tsorted_sent_queue); icsk->icsk_rto = TCP_TIMEOUT_INIT; rto_min_us = READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_rto_min_us); icsk->icsk_rto_min = usecs_to_jiffies(rto_min_us); icsk->icsk_delack_max = TCP_DELACK_MAX; tp->mdev_us = jiffies_to_usecs(TCP_TIMEOUT_INIT); minmax_reset(&tp->rtt_min, tcp_jiffies32, ~0U); /* So many TCP implementations out there (incorrectly) count the * initial SYN frame in their delayed-ACK and congestion control * algorithms that we must have the following bandaid to talk * efficiently to them. -DaveM */ tcp_snd_cwnd_set(tp, TCP_INIT_CWND); /* There's a bubble in the pipe until at least the first ACK. */ tp->app_limited = ~0U; tp->rate_app_limited = 1; /* See draft-stevens-tcpca-spec-01 for discussion of the * initialization of these values. */ tp->snd_ssthresh = TCP_INFINITE_SSTHRESH; tp->snd_cwnd_clamp = ~0; tp->mss_cache = TCP_MSS_DEFAULT; tp->reordering = READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_reordering); tcp_assign_congestion_control(sk); tp->tsoffset = 0; tp->rack.reo_wnd_steps = 1; sk->sk_write_space = sk_stream_write_space; sock_set_flag(sk, SOCK_USE_WRITE_QUEUE); icsk->icsk_sync_mss = tcp_sync_mss; WRITE_ONCE(sk->sk_sndbuf, READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_wmem[1])); WRITE_ONCE(sk->sk_rcvbuf, READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_rmem[1])); tcp_scaling_ratio_init(sk); set_bit(SOCK_SUPPORT_ZC, &sk->sk_socket->flags); sk_sockets_allocated_inc(sk); xa_init_flags(&sk->sk_user_frags, XA_FLAGS_ALLOC1); } EXPORT_SYMBOL(tcp_init_sock); static void tcp_tx_timestamp(struct sock *sk, struct sockcm_cookie *sockc) { struct sk_buff *skb = tcp_write_queue_tail(sk); u32 tsflags = sockc->tsflags; if (tsflags && skb) { struct skb_shared_info *shinfo = skb_shinfo(skb); struct tcp_skb_cb *tcb = TCP_SKB_CB(skb); sock_tx_timestamp(sk, sockc, &shinfo->tx_flags); if (tsflags & SOF_TIMESTAMPING_TX_ACK) tcb->txstamp_ack = 1; if (tsflags & SOF_TIMESTAMPING_TX_RECORD_MASK) shinfo->tskey = TCP_SKB_CB(skb)->seq + skb->len - 1; } } static bool tcp_stream_is_readable(struct sock *sk, int target) { if (tcp_epollin_ready(sk, target)) return true; return sk_is_readable(sk); } /* * Wait for a TCP event. * * Note that we don't need to lock the socket, as the upper poll layers * take care of normal races (between the test and the event) and we don't * go look at any of the socket buffers directly. */ __poll_t tcp_poll(struct file *file, struct socket *sock, poll_table *wait) { __poll_t mask; struct sock *sk = sock->sk; const struct tcp_sock *tp = tcp_sk(sk); u8 shutdown; int state; sock_poll_wait(file, sock, wait); state = inet_sk_state_load(sk); if (state == TCP_LISTEN) return inet_csk_listen_poll(sk); /* Socket is not locked. We are protected from async events * by poll logic and correct handling of state changes * made by other threads is impossible in any case. */ mask = 0; /* * EPOLLHUP is certainly not done right. But poll() doesn't * have a notion of HUP in just one direction, and for a * socket the read side is more interesting. * * Some poll() documentation says that EPOLLHUP is incompatible * with the EPOLLOUT/POLLWR flags, so somebody should check this * all. But careful, it tends to be safer to return too many * bits than too few, and you can easily break real applications * if you don't tell them that something has hung up! * * Check-me. * * Check number 1. EPOLLHUP is _UNMASKABLE_ event (see UNIX98 and * our fs/select.c). It means that after we received EOF, * poll always returns immediately, making impossible poll() on write() * in state CLOSE_WAIT. One solution is evident --- to set EPOLLHUP * if and only if shutdown has been made in both directions. * Actually, it is interesting to look how Solaris and DUX * solve this dilemma. I would prefer, if EPOLLHUP were maskable, * then we could set it on SND_SHUTDOWN. BTW examples given * in Stevens' books assume exactly this behaviour, it explains * why EPOLLHUP is incompatible with EPOLLOUT. --ANK * * NOTE. Check for TCP_CLOSE is added. The goal is to prevent * blocking on fresh not-connected or disconnected socket. --ANK */ shutdown = READ_ONCE(sk->sk_shutdown); if (shutdown == SHUTDOWN_MASK || state == TCP_CLOSE) mask |= EPOLLHUP; if (shutdown & RCV_SHUTDOWN) mask |= EPOLLIN | EPOLLRDNORM | EPOLLRDHUP; /* Connected or passive Fast Open socket? */ if (state != TCP_SYN_SENT && (state != TCP_SYN_RECV || rcu_access_pointer(tp->fastopen_rsk))) { int target = sock_rcvlowat(sk, 0, INT_MAX); u16 urg_data = READ_ONCE(tp->urg_data); if (unlikely(urg_data) && READ_ONCE(tp->urg_seq) == READ_ONCE(tp->copied_seq) && !sock_flag(sk, SOCK_URGINLINE)) target++; if (tcp_stream_is_readable(sk, target)) mask |= EPOLLIN | EPOLLRDNORM; if (!(shutdown & SEND_SHUTDOWN)) { if (__sk_stream_is_writeable(sk, 1)) { mask |= EPOLLOUT | EPOLLWRNORM; } else { /* send SIGIO later */ sk_set_bit(SOCKWQ_ASYNC_NOSPACE, sk); set_bit(SOCK_NOSPACE, &sk->sk_socket->flags); /* Race breaker. If space is freed after * wspace test but before the flags are set, * IO signal will be lost. Memory barrier * pairs with the input side. */ smp_mb__after_atomic(); if (__sk_stream_is_writeable(sk, 1)) mask |= EPOLLOUT | EPOLLWRNORM; } } else mask |= EPOLLOUT | EPOLLWRNORM; if (urg_data & TCP_URG_VALID) mask |= EPOLLPRI; } else if (state == TCP_SYN_SENT && inet_test_bit(DEFER_CONNECT, sk)) { /* Active TCP fastopen socket with defer_connect * Return EPOLLOUT so application can call write() * in order for kernel to generate SYN+data */ mask |= EPOLLOUT | EPOLLWRNORM; } /* This barrier is coupled with smp_wmb() in tcp_done_with_error() */ smp_rmb(); if (READ_ONCE(sk->sk_err) || !skb_queue_empty_lockless(&sk->sk_error_queue)) mask |= EPOLLERR; return mask; } EXPORT_SYMBOL(tcp_poll); int tcp_ioctl(struct sock *sk, int cmd, int *karg) { struct tcp_sock *tp = tcp_sk(sk); int answ; bool slow; switch (cmd) { case SIOCINQ: if (sk->sk_state == TCP_LISTEN) return -EINVAL; slow = lock_sock_fast(sk); answ = tcp_inq(sk); unlock_sock_fast(sk, slow); break; case SIOCATMARK: answ = READ_ONCE(tp->urg_data) && READ_ONCE(tp->urg_seq) == READ_ONCE(tp->copied_seq); break; case SIOCOUTQ: if (sk->sk_state == TCP_LISTEN) return -EINVAL; if ((1 << sk->sk_state) & (TCPF_SYN_SENT | TCPF_SYN_RECV)) answ = 0; else answ = READ_ONCE(tp->write_seq) - tp->snd_una; break; case SIOCOUTQNSD: if (sk->sk_state == TCP_LISTEN) return -EINVAL; if ((1 << sk->sk_state) & (TCPF_SYN_SENT | TCPF_SYN_RECV)) answ = 0; else answ = READ_ONCE(tp->write_seq) - READ_ONCE(tp->snd_nxt); break; default: return -ENOIOCTLCMD; } *karg = answ; return 0; } EXPORT_SYMBOL(tcp_ioctl); void tcp_mark_push(struct tcp_sock *tp, struct sk_buff *skb) { TCP_SKB_CB(skb)->tcp_flags |= TCPHDR_PSH; tp->pushed_seq = tp->write_seq; } static inline bool forced_push(const struct tcp_sock *tp) { return after(tp->write_seq, tp->pushed_seq + (tp->max_window >> 1)); } void tcp_skb_entail(struct sock *sk, struct sk_buff *skb) { struct tcp_sock *tp = tcp_sk(sk); struct tcp_skb_cb *tcb = TCP_SKB_CB(skb); tcb->seq = tcb->end_seq = tp->write_seq; tcb->tcp_flags = TCPHDR_ACK; __skb_header_release(skb); tcp_add_write_queue_tail(sk, skb); sk_wmem_queued_add(sk, skb->truesize); sk_mem_charge(sk, skb->truesize); if (tp->nonagle & TCP_NAGLE_PUSH) tp->nonagle &= ~TCP_NAGLE_PUSH; tcp_slow_start_after_idle_check(sk); } static inline void tcp_mark_urg(struct tcp_sock *tp, int flags) { if (flags & MSG_OOB) tp->snd_up = tp->write_seq; } /* If a not yet filled skb is pushed, do not send it if * we have data packets in Qdisc or NIC queues : * Because TX completion will happen shortly, it gives a chance * to coalesce future sendmsg() payload into this skb, without * need for a timer, and with no latency trade off. * As packets containing data payload have a bigger truesize * than pure acks (dataless) packets, the last checks prevent * autocorking if we only have an ACK in Qdisc/NIC queues, * or if TX completion was delayed after we processed ACK packet. */ static bool tcp_should_autocork(struct sock *sk, struct sk_buff *skb, int size_goal) { return skb->len < size_goal && READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_autocorking) && !tcp_rtx_queue_empty(sk) && refcount_read(&sk->sk_wmem_alloc) > skb->truesize && tcp_skb_can_collapse_to(skb); } void tcp_push(struct sock *sk, int flags, int mss_now, int nonagle, int size_goal) { struct tcp_sock *tp = tcp_sk(sk); struct sk_buff *skb; skb = tcp_write_queue_tail(sk); if (!skb) return; if (!(flags & MSG_MORE) || forced_push(tp)) tcp_mark_push(tp, skb); tcp_mark_urg(tp, flags); if (tcp_should_autocork(sk, skb, size_goal)) { /* avoid atomic op if TSQ_THROTTLED bit is already set */ if (!test_bit(TSQ_THROTTLED, &sk->sk_tsq_flags)) { NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPAUTOCORKING); set_bit(TSQ_THROTTLED, &sk->sk_tsq_flags); smp_mb__after_atomic(); } /* It is possible TX completion already happened * before we set TSQ_THROTTLED. */ if (refcount_read(&sk->sk_wmem_alloc) > skb->truesize) return; } if (flags & MSG_MORE) nonagle = TCP_NAGLE_CORK; __tcp_push_pending_frames(sk, mss_now, nonagle); } static int tcp_splice_data_recv(read_descriptor_t *rd_desc, struct sk_buff *skb, unsigned int offset, size_t len) { struct tcp_splice_state *tss = rd_desc->arg.data; int ret; ret = skb_splice_bits(skb, skb->sk, offset, tss->pipe, min(rd_desc->count, len), tss->flags); if (ret > 0) rd_desc->count -= ret; return ret; } static int __tcp_splice_read(struct sock *sk, struct tcp_splice_state *tss) { /* Store TCP splice context information in read_descriptor_t. */ read_descriptor_t rd_desc = { .arg.data = tss, .count = tss->len, }; return tcp_read_sock(sk, &rd_desc, tcp_splice_data_recv); } /** * tcp_splice_read - splice data from TCP socket to a pipe * @sock: socket to splice from * @ppos: position (not valid) * @pipe: pipe to splice to * @len: number of bytes to splice * @flags: splice modifier flags * * Description: * Will read pages from given socket and fill them into a pipe. * **/ ssize_t tcp_splice_read(struct socket *sock, loff_t *ppos, struct pipe_inode_info *pipe, size_t len, unsigned int flags) { struct sock *sk = sock->sk; struct tcp_splice_state tss = { .pipe = pipe, .len = len, .flags = flags, }; long timeo; ssize_t spliced; int ret; sock_rps_record_flow(sk); /* * We can't seek on a socket input */ if (unlikely(*ppos)) return -ESPIPE; ret = spliced = 0; lock_sock(sk); timeo = sock_rcvtimeo(sk, sock->file->f_flags & O_NONBLOCK); while (tss.len) { ret = __tcp_splice_read(sk, &tss); if (ret < 0) break; else if (!ret) { if (spliced) break; if (sock_flag(sk, SOCK_DONE)) break; if (sk->sk_err) { ret = sock_error(sk); break; } if (sk->sk_shutdown & RCV_SHUTDOWN) break; if (sk->sk_state == TCP_CLOSE) { /* * This occurs when user tries to read * from never connected socket. */ ret = -ENOTCONN; break; } if (!timeo) { ret = -EAGAIN; break; } /* if __tcp_splice_read() got nothing while we have * an skb in receive queue, we do not want to loop. * This might happen with URG data. */ if (!skb_queue_empty(&sk->sk_receive_queue)) break; ret = sk_wait_data(sk, &timeo, NULL); if (ret < 0) break; if (signal_pending(current)) { ret = sock_intr_errno(timeo); break; } continue; } tss.len -= ret; spliced += ret; if (!tss.len || !timeo) break; release_sock(sk); lock_sock(sk); if (sk->sk_err || sk->sk_state == TCP_CLOSE || (sk->sk_shutdown & RCV_SHUTDOWN) || signal_pending(current)) break; } release_sock(sk); if (spliced) return spliced; return ret; } EXPORT_SYMBOL(tcp_splice_read); struct sk_buff *tcp_stream_alloc_skb(struct sock *sk, gfp_t gfp, bool force_schedule) { struct sk_buff *skb; skb = alloc_skb_fclone(MAX_TCP_HEADER, gfp); if (likely(skb)) { bool mem_scheduled; skb->truesize = SKB_TRUESIZE(skb_end_offset(skb)); if (force_schedule) { mem_scheduled = true; sk_forced_mem_schedule(sk, skb->truesize); } else { mem_scheduled = sk_wmem_schedule(sk, skb->truesize); } if (likely(mem_scheduled)) { skb_reserve(skb, MAX_TCP_HEADER); skb->ip_summed = CHECKSUM_PARTIAL; INIT_LIST_HEAD(&skb->tcp_tsorted_anchor); return skb; } __kfree_skb(skb); } else { sk->sk_prot->enter_memory_pressure(sk); sk_stream_moderate_sndbuf(sk); } return NULL; } static unsigned int tcp_xmit_size_goal(struct sock *sk, u32 mss_now, int large_allowed) { struct tcp_sock *tp = tcp_sk(sk); u32 new_size_goal, size_goal; if (!large_allowed) return mss_now; /* Note : tcp_tso_autosize() will eventually split this later */ new_size_goal = tcp_bound_to_half_wnd(tp, sk->sk_gso_max_size); /* We try hard to avoid divides here */ size_goal = tp->gso_segs * mss_now; if (unlikely(new_size_goal < size_goal || new_size_goal >= size_goal + mss_now)) { tp->gso_segs = min_t(u16, new_size_goal / mss_now, sk->sk_gso_max_segs); size_goal = tp->gso_segs * mss_now; } return max(size_goal, mss_now); } int tcp_send_mss(struct sock *sk, int *size_goal, int flags) { int mss_now; mss_now = tcp_current_mss(sk); *size_goal = tcp_xmit_size_goal(sk, mss_now, !(flags & MSG_OOB)); return mss_now; } /* In some cases, sendmsg() could have added an skb to the write queue, * but failed adding payload on it. We need to remove it to consume less * memory, but more importantly be able to generate EPOLLOUT for Edge Trigger * epoll() users. Another reason is that tcp_write_xmit() does not like * finding an empty skb in the write queue. */ void tcp_remove_empty_skb(struct sock *sk) { struct sk_buff *skb = tcp_write_queue_tail(sk); if (skb && TCP_SKB_CB(skb)->seq == TCP_SKB_CB(skb)->end_seq) { tcp_unlink_write_queue(skb, sk); if (tcp_write_queue_empty(sk)) tcp_chrono_stop(sk, TCP_CHRONO_BUSY); tcp_wmem_free_skb(sk, skb); } } /* skb changing from pure zc to mixed, must charge zc */ static int tcp_downgrade_zcopy_pure(struct sock *sk, struct sk_buff *skb) { if (unlikely(skb_zcopy_pure(skb))) { u32 extra = skb->truesize - SKB_TRUESIZE(skb_end_offset(skb)); if (!sk_wmem_schedule(sk, extra)) return -ENOMEM; sk_mem_charge(sk, extra); skb_shinfo(skb)->flags &= ~SKBFL_PURE_ZEROCOPY; } return 0; } int tcp_wmem_schedule(struct sock *sk, int copy) { int left; if (likely(sk_wmem_schedule(sk, copy))) return copy; /* We could be in trouble if we have nothing queued. * Use whatever is left in sk->sk_forward_alloc and tcp_wmem[0] * to guarantee some progress. */ left = READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_wmem[0]) - sk->sk_wmem_queued; if (left > 0) sk_forced_mem_schedule(sk, min(left, copy)); return min(copy, sk->sk_forward_alloc); } void tcp_free_fastopen_req(struct tcp_sock *tp) { if (tp->fastopen_req) { kfree(tp->fastopen_req); tp->fastopen_req = NULL; } } int tcp_sendmsg_fastopen(struct sock *sk, struct msghdr *msg, int *copied, size_t size, struct ubuf_info *uarg) { struct tcp_sock *tp = tcp_sk(sk); struct inet_sock *inet = inet_sk(sk); struct sockaddr *uaddr = msg->msg_name; int err, flags; if (!(READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_fastopen) & TFO_CLIENT_ENABLE) || (uaddr && msg->msg_namelen >= sizeof(uaddr->sa_family) && uaddr->sa_family == AF_UNSPEC)) return -EOPNOTSUPP; if (tp->fastopen_req) return -EALREADY; /* Another Fast Open is in progress */ tp->fastopen_req = kzalloc(sizeof(struct tcp_fastopen_request), sk->sk_allocation); if (unlikely(!tp->fastopen_req)) return -ENOBUFS; tp->fastopen_req->data = msg; tp->fastopen_req->size = size; tp->fastopen_req->uarg = uarg; if (inet_test_bit(DEFER_CONNECT, sk)) { err = tcp_connect(sk); /* Same failure procedure as in tcp_v4/6_connect */ if (err) { tcp_set_state(sk, TCP_CLOSE); inet->inet_dport = 0; sk->sk_route_caps = 0; } } flags = (msg->msg_flags & MSG_DONTWAIT) ? O_NONBLOCK : 0; err = __inet_stream_connect(sk->sk_socket, uaddr, msg->msg_namelen, flags, 1); /* fastopen_req could already be freed in __inet_stream_connect * if the connection times out or gets rst */ if (tp->fastopen_req) { *copied = tp->fastopen_req->copied; tcp_free_fastopen_req(tp); inet_clear_bit(DEFER_CONNECT, sk); } return err; } int tcp_sendmsg_locked(struct sock *sk, struct msghdr *msg, size_t size) { struct tcp_sock *tp = tcp_sk(sk); struct ubuf_info *uarg = NULL; struct sk_buff *skb; struct sockcm_cookie sockc; int flags, err, copied = 0; int mss_now = 0, size_goal, copied_syn = 0; int process_backlog = 0; int zc = 0; long timeo; flags = msg->msg_flags; if ((flags & MSG_ZEROCOPY) && size) { if (msg->msg_ubuf) { uarg = msg->msg_ubuf; if (sk->sk_route_caps & NETIF_F_SG) zc = MSG_ZEROCOPY; } else if (sock_flag(sk, SOCK_ZEROCOPY)) { skb = tcp_write_queue_tail(sk); uarg = msg_zerocopy_realloc(sk, size, skb_zcopy(skb)); if (!uarg) { err = -ENOBUFS; goto out_err; } if (sk->sk_route_caps & NETIF_F_SG) zc = MSG_ZEROCOPY; else uarg_to_msgzc(uarg)->zerocopy = 0; } } else if (unlikely(msg->msg_flags & MSG_SPLICE_PAGES) && size) { if (sk->sk_route_caps & NETIF_F_SG) zc = MSG_SPLICE_PAGES; } if (unlikely(flags & MSG_FASTOPEN || inet_test_bit(DEFER_CONNECT, sk)) && !tp->repair) { err = tcp_sendmsg_fastopen(sk, msg, &copied_syn, size, uarg); if (err == -EINPROGRESS && copied_syn > 0) goto out; else if (err) goto out_err; } timeo = sock_sndtimeo(sk, flags & MSG_DONTWAIT); tcp_rate_check_app_limited(sk); /* is sending application-limited? */ /* Wait for a connection to finish. One exception is TCP Fast Open * (passive side) where data is allowed to be sent before a connection * is fully established. */ if (((1 << sk->sk_state) & ~(TCPF_ESTABLISHED | TCPF_CLOSE_WAIT)) && !tcp_passive_fastopen(sk)) { err = sk_stream_wait_connect(sk, &timeo); if (err != 0) goto do_error; } if (unlikely(tp->repair)) { if (tp->repair_queue == TCP_RECV_QUEUE) { copied = tcp_send_rcvq(sk, msg, size); goto out_nopush; } err = -EINVAL; if (tp->repair_queue == TCP_NO_QUEUE) goto out_err; /* 'common' sending to sendq */ } sockcm_init(&sockc, sk); if (msg->msg_controllen) { err = sock_cmsg_send(sk, msg, &sockc); if (unlikely(err)) { err = -EINVAL; goto out_err; } } /* This should be in poll */ sk_clear_bit(SOCKWQ_ASYNC_NOSPACE, sk); /* Ok commence sending. */ copied = 0; restart: mss_now = tcp_send_mss(sk, &size_goal, flags); err = -EPIPE; if (sk->sk_err || (sk->sk_shutdown & SEND_SHUTDOWN)) goto do_error; while (msg_data_left(msg)) { ssize_t copy = 0; skb = tcp_write_queue_tail(sk); if (skb) copy = size_goal - skb->len; if (copy <= 0 || !tcp_skb_can_collapse_to(skb)) { bool first_skb; new_segment: if (!sk_stream_memory_free(sk)) goto wait_for_space; if (unlikely(process_backlog >= 16)) { process_backlog = 0; if (sk_flush_backlog(sk)) goto restart; } first_skb = tcp_rtx_and_write_queues_empty(sk); skb = tcp_stream_alloc_skb(sk, sk->sk_allocation, first_skb); if (!skb) goto wait_for_space; process_backlog++; #ifdef CONFIG_SKB_DECRYPTED skb->decrypted = !!(flags & MSG_SENDPAGE_DECRYPTED); #endif tcp_skb_entail(sk, skb); copy = size_goal; /* All packets are restored as if they have * already been sent. skb_mstamp_ns isn't set to * avoid wrong rtt estimation. */ if (tp->repair) TCP_SKB_CB(skb)->sacked |= TCPCB_REPAIRED; } /* Try to append data to the end of skb. */ if (copy > msg_data_left(msg)) copy = msg_data_left(msg); if (zc == 0) { bool merge = true; int i = skb_shinfo(skb)->nr_frags; struct page_frag *pfrag = sk_page_frag(sk); if (!sk_page_frag_refill(sk, pfrag)) goto wait_for_space; if (!skb_can_coalesce(skb, i, pfrag->page, pfrag->offset)) { if (i >= READ_ONCE(net_hotdata.sysctl_max_skb_frags)) { tcp_mark_push(tp, skb); goto new_segment; } merge = false; } copy = min_t(int, copy, pfrag->size - pfrag->offset); if (unlikely(skb_zcopy_pure(skb) || skb_zcopy_managed(skb))) { if (tcp_downgrade_zcopy_pure(sk, skb)) goto wait_for_space; skb_zcopy_downgrade_managed(skb); } copy = tcp_wmem_schedule(sk, copy); if (!copy) goto wait_for_space; err = skb_copy_to_page_nocache(sk, &msg->msg_iter, skb, pfrag->page, pfrag->offset, copy); if (err) goto do_error; /* Update the skb. */ if (merge) { skb_frag_size_add(&skb_shinfo(skb)->frags[i - 1], copy); } else { skb_fill_page_desc(skb, i, pfrag->page, pfrag->offset, copy); page_ref_inc(pfrag->page); } pfrag->offset += copy; } else if (zc == MSG_ZEROCOPY) { /* First append to a fragless skb builds initial * pure zerocopy skb */ if (!skb->len) skb_shinfo(skb)->flags |= SKBFL_PURE_ZEROCOPY; if (!skb_zcopy_pure(skb)) { copy = tcp_wmem_schedule(sk, copy); if (!copy) goto wait_for_space; } err = skb_zerocopy_iter_stream(sk, skb, msg, copy, uarg); if (err == -EMSGSIZE || err == -EEXIST) { tcp_mark_push(tp, skb); goto new_segment; } if (err < 0) goto do_error; copy = err; } else if (zc == MSG_SPLICE_PAGES) { /* Splice in data if we can; copy if we can't. */ if (tcp_downgrade_zcopy_pure(sk, skb)) goto wait_for_space; copy = tcp_wmem_schedule(sk, copy); if (!copy) goto wait_for_space; err = skb_splice_from_iter(skb, &msg->msg_iter, copy, sk->sk_allocation); if (err < 0) { if (err == -EMSGSIZE) { tcp_mark_push(tp, skb); goto new_segment; } goto do_error; } copy = err; if (!(flags & MSG_NO_SHARED_FRAGS)) skb_shinfo(skb)->flags |= SKBFL_SHARED_FRAG; sk_wmem_queued_add(sk, copy); sk_mem_charge(sk, copy); } if (!copied) TCP_SKB_CB(skb)->tcp_flags &= ~TCPHDR_PSH; WRITE_ONCE(tp->write_seq, tp->write_seq + copy); TCP_SKB_CB(skb)->end_seq += copy; tcp_skb_pcount_set(skb, 0); copied += copy; if (!msg_data_left(msg)) { if (unlikely(flags & MSG_EOR)) TCP_SKB_CB(skb)->eor = 1; goto out; } if (skb->len < size_goal || (flags & MSG_OOB) || unlikely(tp->repair)) continue; if (forced_push(tp)) { tcp_mark_push(tp, skb); __tcp_push_pending_frames(sk, mss_now, TCP_NAGLE_PUSH); } else if (skb == tcp_send_head(sk)) tcp_push_one(sk, mss_now); continue; wait_for_space: set_bit(SOCK_NOSPACE, &sk->sk_socket->flags); tcp_remove_empty_skb(sk); if (copied) tcp_push(sk, flags & ~MSG_MORE, mss_now, TCP_NAGLE_PUSH, size_goal); err = sk_stream_wait_memory(sk, &timeo); if (err != 0) goto do_error; mss_now = tcp_send_mss(sk, &size_goal, flags); } out: if (copied) { tcp_tx_timestamp(sk, &sockc); tcp_push(sk, flags, mss_now, tp->nonagle, size_goal); } out_nopush: /* msg->msg_ubuf is pinned by the caller so we don't take extra refs */ if (uarg && !msg->msg_ubuf) net_zcopy_put(uarg); return copied + copied_syn; do_error: tcp_remove_empty_skb(sk); if (copied + copied_syn) goto out; out_err: /* msg->msg_ubuf is pinned by the caller so we don't take extra refs */ if (uarg && !msg->msg_ubuf) net_zcopy_put_abort(uarg, true); err = sk_stream_error(sk, flags, err); /* make sure we wake any epoll edge trigger waiter */ if (unlikely(tcp_rtx_and_write_queues_empty(sk) && err == -EAGAIN)) { sk->sk_write_space(sk); tcp_chrono_stop(sk, TCP_CHRONO_SNDBUF_LIMITED); } return err; } EXPORT_SYMBOL_GPL(tcp_sendmsg_locked); int tcp_sendmsg(struct sock *sk, struct msghdr *msg, size_t size) { int ret; lock_sock(sk); ret = tcp_sendmsg_locked(sk, msg, size); release_sock(sk); return ret; } EXPORT_SYMBOL(tcp_sendmsg); void tcp_splice_eof(struct socket *sock) { struct sock *sk = sock->sk; struct tcp_sock *tp = tcp_sk(sk); int mss_now, size_goal; if (!tcp_write_queue_tail(sk)) return; lock_sock(sk); mss_now = tcp_send_mss(sk, &size_goal, 0); tcp_push(sk, 0, mss_now, tp->nonagle, size_goal); release_sock(sk); } EXPORT_SYMBOL_GPL(tcp_splice_eof); /* * Handle reading urgent data. BSD has very simple semantics for * this, no blocking and very strange errors 8) */ static int tcp_recv_urg(struct sock *sk, struct msghdr *msg, int len, int flags) { struct tcp_sock *tp = tcp_sk(sk); /* No URG data to read. */ if (sock_flag(sk, SOCK_URGINLINE) || !tp->urg_data || tp->urg_data == TCP_URG_READ) return -EINVAL; /* Yes this is right ! */ if (sk->sk_state == TCP_CLOSE && !sock_flag(sk, SOCK_DONE)) return -ENOTCONN; if (tp->urg_data & TCP_URG_VALID) { int err = 0; char c = tp->urg_data; if (!(flags & MSG_PEEK)) WRITE_ONCE(tp->urg_data, TCP_URG_READ); /* Read urgent data. */ msg->msg_flags |= MSG_OOB; if (len > 0) { if (!(flags & MSG_TRUNC)) err = memcpy_to_msg(msg, &c, 1); len = 1; } else msg->msg_flags |= MSG_TRUNC; return err ? -EFAULT : len; } if (sk->sk_state == TCP_CLOSE || (sk->sk_shutdown & RCV_SHUTDOWN)) return 0; /* Fixed the recv(..., MSG_OOB) behaviour. BSD docs and * the available implementations agree in this case: * this call should never block, independent of the * blocking state of the socket. * Mike <pall@rz.uni-karlsruhe.de> */ return -EAGAIN; } static int tcp_peek_sndq(struct sock *sk, struct msghdr *msg, int len) { struct sk_buff *skb; int copied = 0, err = 0; skb_rbtree_walk(skb, &sk->tcp_rtx_queue) { err = skb_copy_datagram_msg(skb, 0, msg, skb->len); if (err) return err; copied += skb->len; } skb_queue_walk(&sk->sk_write_queue, skb) { err = skb_copy_datagram_msg(skb, 0, msg, skb->len); if (err) break; copied += skb->len; } return err ?: copied; } /* Clean up the receive buffer for full frames taken by the user, * then send an ACK if necessary. COPIED is the number of bytes * tcp_recvmsg has given to the user so far, it speeds up the * calculation of whether or not we must ACK for the sake of * a window update. */ void __tcp_cleanup_rbuf(struct sock *sk, int copied) { struct tcp_sock *tp = tcp_sk(sk); bool time_to_ack = false; if (inet_csk_ack_scheduled(sk)) { const struct inet_connection_sock *icsk = inet_csk(sk); if (/* Once-per-two-segments ACK was not sent by tcp_input.c */ tp->rcv_nxt - tp->rcv_wup > icsk->icsk_ack.rcv_mss || /* * If this read emptied read buffer, we send ACK, if * connection is not bidirectional, user drained * receive buffer and there was a small segment * in queue. */ (copied > 0 && ((icsk->icsk_ack.pending & ICSK_ACK_PUSHED2) || ((icsk->icsk_ack.pending & ICSK_ACK_PUSHED) && !inet_csk_in_pingpong_mode(sk))) && !atomic_read(&sk->sk_rmem_alloc))) time_to_ack = true; } /* We send an ACK if we can now advertise a non-zero window * which has been raised "significantly". * * Even if window raised up to infinity, do not send window open ACK * in states, where we will not receive more. It is useless. */ if (copied > 0 && !time_to_ack && !(sk->sk_shutdown & RCV_SHUTDOWN)) { __u32 rcv_window_now = tcp_receive_window(tp); /* Optimize, __tcp_select_window() is not cheap. */ if (2*rcv_window_now <= tp->window_clamp) { __u32 new_window = __tcp_select_window(sk); /* Send ACK now, if this read freed lots of space * in our buffer. Certainly, new_window is new window. * We can advertise it now, if it is not less than current one. * "Lots" means "at least twice" here. */ if (new_window && new_window >= 2 * rcv_window_now) time_to_ack = true; } } if (time_to_ack) tcp_send_ack(sk); } void tcp_cleanup_rbuf(struct sock *sk, int copied) { struct sk_buff *skb = skb_peek(&sk->sk_receive_queue); struct tcp_sock *tp = tcp_sk(sk); WARN(skb && !before(tp->copied_seq, TCP_SKB_CB(skb)->end_seq), "cleanup rbuf bug: copied %X seq %X rcvnxt %X\n", tp->copied_seq, TCP_SKB_CB(skb)->end_seq, tp->rcv_nxt); __tcp_cleanup_rbuf(sk, copied); } static void tcp_eat_recv_skb(struct sock *sk, struct sk_buff *skb) { __skb_unlink(skb, &sk->sk_receive_queue); if (likely(skb->destructor == sock_rfree)) { sock_rfree(skb); skb->destructor = NULL; skb->sk = NULL; return skb_attempt_defer_free(skb); } __kfree_skb(skb); } struct sk_buff *tcp_recv_skb(struct sock *sk, u32 seq, u32 *off) { struct sk_buff *skb; u32 offset; while ((skb = skb_peek(&sk->sk_receive_queue)) != NULL) { offset = seq - TCP_SKB_CB(skb)->seq; if (unlikely(TCP_SKB_CB(skb)->tcp_flags & TCPHDR_SYN)) { pr_err_once("%s: found a SYN, please report !\n", __func__); offset--; } if (offset < skb->len || (TCP_SKB_CB(skb)->tcp_flags & TCPHDR_FIN)) { *off = offset; return skb; } /* This looks weird, but this can happen if TCP collapsing * splitted a fat GRO packet, while we released socket lock * in skb_splice_bits() */ tcp_eat_recv_skb(sk, skb); } return NULL; } EXPORT_SYMBOL(tcp_recv_skb); /* * This routine provides an alternative to tcp_recvmsg() for routines * that would like to handle copying from skbuffs directly in 'sendfile' * fashion. * Note: * - It is assumed that the socket was locked by the caller. * - The routine does not block. * - At present, there is no support for reading OOB data * or for 'peeking' the socket using this routine * (although both would be easy to implement). */ int tcp_read_sock(struct sock *sk, read_descriptor_t *desc, sk_read_actor_t recv_actor) { struct sk_buff *skb; struct tcp_sock *tp = tcp_sk(sk); u32 seq = tp->copied_seq; u32 offset; int copied = 0; if (sk->sk_state == TCP_LISTEN) return -ENOTCONN; while ((skb = tcp_recv_skb(sk, seq, &offset)) != NULL) { if (offset < skb->len) { int used; size_t len; len = skb->len - offset; /* Stop reading if we hit a patch of urgent data */ if (unlikely(tp->urg_data)) { u32 urg_offset = tp->urg_seq - seq; if (urg_offset < len) len = urg_offset; if (!len) break; } used = recv_actor(desc, skb, offset, len); if (used <= 0) { if (!copied) copied = used; break; } if (WARN_ON_ONCE(used > len)) used = len; seq += used; copied += used; offset += used; /* If recv_actor drops the lock (e.g. TCP splice * receive) the skb pointer might be invalid when * getting here: tcp_collapse might have deleted it * while aggregating skbs from the socket queue. */ skb = tcp_recv_skb(sk, seq - 1, &offset); if (!skb) break; /* TCP coalescing might have appended data to the skb. * Try to splice more frags */ if (offset + 1 != skb->len) continue; } if (TCP_SKB_CB(skb)->tcp_flags & TCPHDR_FIN) { tcp_eat_recv_skb(sk, skb); ++seq; break; } tcp_eat_recv_skb(sk, skb); if (!desc->count) break; WRITE_ONCE(tp->copied_seq, seq); } WRITE_ONCE(tp->copied_seq, seq); tcp_rcv_space_adjust(sk); /* Clean up data we have read: This will do ACK frames. */ if (copied > 0) { tcp_recv_skb(sk, seq, &offset); tcp_cleanup_rbuf(sk, copied); } return copied; } EXPORT_SYMBOL(tcp_read_sock); int tcp_read_skb(struct sock *sk, skb_read_actor_t recv_actor) { struct sk_buff *skb; int copied = 0; if (sk->sk_state == TCP_LISTEN) return -ENOTCONN; while ((skb = skb_peek(&sk->sk_receive_queue)) != NULL) { u8 tcp_flags; int used; __skb_unlink(skb, &sk->sk_receive_queue); WARN_ON_ONCE(!skb_set_owner_sk_safe(skb, sk)); tcp_flags = TCP_SKB_CB(skb)->tcp_flags; used = recv_actor(sk, skb); if (used < 0) { if (!copied) copied = used; break; } copied += used; if (tcp_flags & TCPHDR_FIN) break; } return copied; } EXPORT_SYMBOL(tcp_read_skb); void tcp_read_done(struct sock *sk, size_t len) { struct tcp_sock *tp = tcp_sk(sk); u32 seq = tp->copied_seq; struct sk_buff *skb; size_t left; u32 offset; if (sk->sk_state == TCP_LISTEN) return; left = len; while (left && (skb = tcp_recv_skb(sk, seq, &offset)) != NULL) { int used; used = min_t(size_t, skb->len - offset, left); seq += used; left -= used; if (skb->len > offset + used) break; if (TCP_SKB_CB(skb)->tcp_flags & TCPHDR_FIN) { tcp_eat_recv_skb(sk, skb); ++seq; break; } tcp_eat_recv_skb(sk, skb); } WRITE_ONCE(tp->copied_seq, seq); tcp_rcv_space_adjust(sk); /* Clean up data we have read: This will do ACK frames. */ if (left != len) tcp_cleanup_rbuf(sk, len - left); } EXPORT_SYMBOL(tcp_read_done); int tcp_peek_len(struct socket *sock) { return tcp_inq(sock->sk); } EXPORT_SYMBOL(tcp_peek_len); /* Make sure sk_rcvbuf is big enough to satisfy SO_RCVLOWAT hint */ int tcp_set_rcvlowat(struct sock *sk, int val) { int space, cap; if (sk->sk_userlocks & SOCK_RCVBUF_LOCK) cap = sk->sk_rcvbuf >> 1; else cap = READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_rmem[2]) >> 1; val = min(val, cap); WRITE_ONCE(sk->sk_rcvlowat, val ? : 1); /* Check if we need to signal EPOLLIN right now */ tcp_data_ready(sk); if (sk->sk_userlocks & SOCK_RCVBUF_LOCK) return 0; space = tcp_space_from_win(sk, val); if (space > sk->sk_rcvbuf) { WRITE_ONCE(sk->sk_rcvbuf, space); WRITE_ONCE(tcp_sk(sk)->window_clamp, val); } return 0; } EXPORT_SYMBOL(tcp_set_rcvlowat); void tcp_update_recv_tstamps(struct sk_buff *skb, struct scm_timestamping_internal *tss) { if (skb->tstamp) tss->ts[0] = ktime_to_timespec64(skb->tstamp); else tss->ts[0] = (struct timespec64) {0}; if (skb_hwtstamps(skb)->hwtstamp) tss->ts[2] = ktime_to_timespec64(skb_hwtstamps(skb)->hwtstamp); else tss->ts[2] = (struct timespec64) {0}; } #ifdef CONFIG_MMU static const struct vm_operations_struct tcp_vm_ops = { }; int tcp_mmap(struct file *file, struct socket *sock, struct vm_area_struct *vma) { if (vma->vm_flags & (VM_WRITE | VM_EXEC)) return -EPERM; vm_flags_clear(vma, VM_MAYWRITE | VM_MAYEXEC); /* Instruct vm_insert_page() to not mmap_read_lock(mm) */ vm_flags_set(vma, VM_MIXEDMAP); vma->vm_ops = &tcp_vm_ops; return 0; } EXPORT_SYMBOL(tcp_mmap); static skb_frag_t *skb_advance_to_frag(struct sk_buff *skb, u32 offset_skb, u32 *offset_frag) { skb_frag_t *frag; if (unlikely(offset_skb >= skb->len)) return NULL; offset_skb -= skb_headlen(skb); if ((int)offset_skb < 0 || skb_has_frag_list(skb)) return NULL; frag = skb_shinfo(skb)->frags; while (offset_skb) { if (skb_frag_size(frag) > offset_skb) { *offset_frag = offset_skb; return frag; } offset_skb -= skb_frag_size(frag); ++frag; } *offset_frag = 0; return frag; } static bool can_map_frag(const skb_frag_t *frag) { struct page *page; if (skb_frag_size(frag) != PAGE_SIZE || skb_frag_off(frag)) return false; page = skb_frag_page(frag); if (PageCompound(page) || page->mapping) return false; return true; } static int find_next_mappable_frag(const skb_frag_t *frag, int remaining_in_skb) { int offset = 0; if (likely(can_map_frag(frag))) return 0; while (offset < remaining_in_skb && !can_map_frag(frag)) { offset += skb_frag_size(frag); ++frag; } return offset; } static void tcp_zerocopy_set_hint_for_skb(struct sock *sk, struct tcp_zerocopy_receive *zc, struct sk_buff *skb, u32 offset) { u32 frag_offset, partial_frag_remainder = 0; int mappable_offset; skb_frag_t *frag; /* worst case: skip to next skb. try to improve on this case below */ zc->recv_skip_hint = skb->len - offset; /* Find the frag containing this offset (and how far into that frag) */ frag = skb_advance_to_frag(skb, offset, &frag_offset); if (!frag) return; if (frag_offset) { struct skb_shared_info *info = skb_shinfo(skb); /* We read part of the last frag, must recvmsg() rest of skb. */ if (frag == &info->frags[info->nr_frags - 1]) return; /* Else, we must at least read the remainder in this frag. */ partial_frag_remainder = skb_frag_size(frag) - frag_offset; zc->recv_skip_hint -= partial_frag_remainder; ++frag; } /* partial_frag_remainder: If part way through a frag, must read rest. * mappable_offset: Bytes till next mappable frag, *not* counting bytes * in partial_frag_remainder. */ mappable_offset = find_next_mappable_frag(frag, zc->recv_skip_hint); zc->recv_skip_hint = mappable_offset + partial_frag_remainder; } static int tcp_recvmsg_locked(struct sock *sk, struct msghdr *msg, size_t len, int flags, struct scm_timestamping_internal *tss, int *cmsg_flags); static int receive_fallback_to_copy(struct sock *sk, struct tcp_zerocopy_receive *zc, int inq, struct scm_timestamping_internal *tss) { unsigned long copy_address = (unsigned long)zc->copybuf_address; struct msghdr msg = {}; int err; zc->length = 0; zc->recv_skip_hint = 0; if (copy_address != zc->copybuf_address) return -EINVAL; err = import_ubuf(ITER_DEST, (void __user *)copy_address, inq, &msg.msg_iter); if (err) return err; err = tcp_recvmsg_locked(sk, &msg, inq, MSG_DONTWAIT, tss, &zc->msg_flags); if (err < 0) return err; zc->copybuf_len = err; if (likely(zc->copybuf_len)) { struct sk_buff *skb; u32 offset; skb = tcp_recv_skb(sk, tcp_sk(sk)->copied_seq, &offset); if (skb) tcp_zerocopy_set_hint_for_skb(sk, zc, skb, offset); } return 0; } static int tcp_copy_straggler_data(struct tcp_zerocopy_receive *zc, struct sk_buff *skb, u32 copylen, u32 *offset, u32 *seq) { unsigned long copy_address = (unsigned long)zc->copybuf_address; struct msghdr msg = {}; int err; if (copy_address != zc->copybuf_address) return -EINVAL; err = import_ubuf(ITER_DEST, (void __user *)copy_address, copylen, &msg.msg_iter); if (err) return err; err = skb_copy_datagram_msg(skb, *offset, &msg, copylen); if (err) return err; zc->recv_skip_hint -= copylen; *offset += copylen; *seq += copylen; return (__s32)copylen; } static int tcp_zc_handle_leftover(struct tcp_zerocopy_receive *zc, struct sock *sk, struct sk_buff *skb, u32 *seq, s32 copybuf_len, struct scm_timestamping_internal *tss) { u32 offset, copylen = min_t(u32, copybuf_len, zc->recv_skip_hint); if (!copylen) return 0; /* skb is null if inq < PAGE_SIZE. */ if (skb) { offset = *seq - TCP_SKB_CB(skb)->seq; } else { skb = tcp_recv_skb(sk, *seq, &offset); if (TCP_SKB_CB(skb)->has_rxtstamp) { tcp_update_recv_tstamps(skb, tss); zc->msg_flags |= TCP_CMSG_TS; } } zc->copybuf_len = tcp_copy_straggler_data(zc, skb, copylen, &offset, seq); return zc->copybuf_len < 0 ? 0 : copylen; } static int tcp_zerocopy_vm_insert_batch_error(struct vm_area_struct *vma, struct page **pending_pages, unsigned long pages_remaining, unsigned long *address, u32 *length, u32 *seq, struct tcp_zerocopy_receive *zc, u32 total_bytes_to_map, int err) { /* At least one page did not map. Try zapping if we skipped earlier. */ if (err == -EBUSY && zc->flags & TCP_RECEIVE_ZEROCOPY_FLAG_TLB_CLEAN_HINT) { u32 maybe_zap_len; maybe_zap_len = total_bytes_to_map - /* All bytes to map */ *length + /* Mapped or pending */ (pages_remaining * PAGE_SIZE); /* Failed map. */ zap_page_range_single(vma, *address, maybe_zap_len, NULL); err = 0; } if (!err) { unsigned long leftover_pages = pages_remaining; int bytes_mapped; /* We called zap_page_range_single, try to reinsert. */ err = vm_insert_pages(vma, *address, pending_pages, &pages_remaining); bytes_mapped = PAGE_SIZE * (leftover_pages - pages_remaining); *seq += bytes_mapped; *address += bytes_mapped; } if (err) { /* Either we were unable to zap, OR we zapped, retried an * insert, and still had an issue. Either ways, pages_remaining * is the number of pages we were unable to map, and we unroll * some state we speculatively touched before. */ const int bytes_not_mapped = PAGE_SIZE * pages_remaining; *length -= bytes_not_mapped; zc->recv_skip_hint += bytes_not_mapped; } return err; } static int tcp_zerocopy_vm_insert_batch(struct vm_area_struct *vma, struct page **pages, unsigned int pages_to_map, unsigned long *address, u32 *length, u32 *seq, struct tcp_zerocopy_receive *zc, u32 total_bytes_to_map) { unsigned long pages_remaining = pages_to_map; unsigned int pages_mapped; unsigned int bytes_mapped; int err; err = vm_insert_pages(vma, *address, pages, &pages_remaining); pages_mapped = pages_to_map - (unsigned int)pages_remaining; bytes_mapped = PAGE_SIZE * pages_mapped; /* Even if vm_insert_pages fails, it may have partially succeeded in * mapping (some but not all of the pages). */ *seq += bytes_mapped; *address += bytes_mapped; if (likely(!err)) return 0; /* Error: maybe zap and retry + rollback state for failed inserts. */ return tcp_zerocopy_vm_insert_batch_error(vma, pages + pages_mapped, pages_remaining, address, length, seq, zc, total_bytes_to_map, err); } #define TCP_VALID_ZC_MSG_FLAGS (TCP_CMSG_TS) static void tcp_zc_finalize_rx_tstamp(struct sock *sk, struct tcp_zerocopy_receive *zc, struct scm_timestamping_internal *tss) { unsigned long msg_control_addr; struct msghdr cmsg_dummy; msg_control_addr = (unsigned long)zc->msg_control; cmsg_dummy.msg_control_user = (void __user *)msg_control_addr; cmsg_dummy.msg_controllen = (__kernel_size_t)zc->msg_controllen; cmsg_dummy.msg_flags = in_compat_syscall() ? MSG_CMSG_COMPAT : 0; cmsg_dummy.msg_control_is_user = true; zc->msg_flags = 0; if (zc->msg_control == msg_control_addr && zc->msg_controllen == cmsg_dummy.msg_controllen) { tcp_recv_timestamp(&cmsg_dummy, sk, tss); zc->msg_control = (__u64) ((uintptr_t)cmsg_dummy.msg_control_user); zc->msg_controllen = (__u64)cmsg_dummy.msg_controllen; zc->msg_flags = (__u32)cmsg_dummy.msg_flags; } } static struct vm_area_struct *find_tcp_vma(struct mm_struct *mm, unsigned long address, bool *mmap_locked) { struct vm_area_struct *vma = lock_vma_under_rcu(mm, address); if (vma) { if (vma->vm_ops != &tcp_vm_ops) { vma_end_read(vma); return NULL; } *mmap_locked = false; return vma; } mmap_read_lock(mm); vma = vma_lookup(mm, address); if (!vma || vma->vm_ops != &tcp_vm_ops) { mmap_read_unlock(mm); return NULL; } *mmap_locked = true; return vma; } #define TCP_ZEROCOPY_PAGE_BATCH_SIZE 32 static int tcp_zerocopy_receive(struct sock *sk, struct tcp_zerocopy_receive *zc, struct scm_timestamping_internal *tss) { u32 length = 0, offset, vma_len, avail_len, copylen = 0; unsigned long address = (unsigned long)zc->address; struct page *pages[TCP_ZEROCOPY_PAGE_BATCH_SIZE]; s32 copybuf_len = zc->copybuf_len; struct tcp_sock *tp = tcp_sk(sk); const skb_frag_t *frags = NULL; unsigned int pages_to_map = 0; struct vm_area_struct *vma; struct sk_buff *skb = NULL; u32 seq = tp->copied_seq; u32 total_bytes_to_map; int inq = tcp_inq(sk); bool mmap_locked; int ret; zc->copybuf_len = 0; zc->msg_flags = 0; if (address & (PAGE_SIZE - 1) || address != zc->address) return -EINVAL; if (sk->sk_state == TCP_LISTEN) return -ENOTCONN; sock_rps_record_flow(sk); if (inq && inq <= copybuf_len) return receive_fallback_to_copy(sk, zc, inq, tss); if (inq < PAGE_SIZE) { zc->length = 0; zc->recv_skip_hint = inq; if (!inq && sock_flag(sk, SOCK_DONE)) return -EIO; return 0; } vma = find_tcp_vma(current->mm, address, &mmap_locked); if (!vma) return -EINVAL; vma_len = min_t(unsigned long, zc->length, vma->vm_end - address); avail_len = min_t(u32, vma_len, inq); total_bytes_to_map = avail_len & ~(PAGE_SIZE - 1); if (total_bytes_to_map) { if (!(zc->flags & TCP_RECEIVE_ZEROCOPY_FLAG_TLB_CLEAN_HINT)) zap_page_range_single(vma, address, total_bytes_to_map, NULL); zc->length = total_bytes_to_map; zc->recv_skip_hint = 0; } else { zc->length = avail_len; zc->recv_skip_hint = avail_len; } ret = 0; while (length + PAGE_SIZE <= zc->length) { int mappable_offset; struct page *page; if (zc->recv_skip_hint < PAGE_SIZE) { u32 offset_frag; if (skb) { if (zc->recv_skip_hint > 0) break; skb = skb->next; offset = seq - TCP_SKB_CB(skb)->seq; } else { skb = tcp_recv_skb(sk, seq, &offset); } if (!skb_frags_readable(skb)) break; if (TCP_SKB_CB(skb)->has_rxtstamp) { tcp_update_recv_tstamps(skb, tss); zc->msg_flags |= TCP_CMSG_TS; } zc->recv_skip_hint = skb->len - offset; frags = skb_advance_to_frag(skb, offset, &offset_frag); if (!frags || offset_frag) break; } mappable_offset = find_next_mappable_frag(frags, zc->recv_skip_hint); if (mappable_offset) { zc->recv_skip_hint = mappable_offset; break; } page = skb_frag_page(frags); if (WARN_ON_ONCE(!page)) break; prefetchw(page); pages[pages_to_map++] = page; length += PAGE_SIZE; zc->recv_skip_hint -= PAGE_SIZE; frags++; if (pages_to_map == TCP_ZEROCOPY_PAGE_BATCH_SIZE || zc->recv_skip_hint < PAGE_SIZE) { /* Either full batch, or we're about to go to next skb * (and we cannot unroll failed ops across skbs). */ ret = tcp_zerocopy_vm_insert_batch(vma, pages, pages_to_map, &address, &length, &seq, zc, total_bytes_to_map); if (ret) goto out; pages_to_map = 0; } } if (pages_to_map) { ret = tcp_zerocopy_vm_insert_batch(vma, pages, pages_to_map, &address, &length, &seq, zc, total_bytes_to_map); } out: if (mmap_locked) mmap_read_unlock(current->mm); else vma_end_read(vma); /* Try to copy straggler data. */ if (!ret) copylen = tcp_zc_handle_leftover(zc, sk, skb, &seq, copybuf_len, tss); if (length + copylen) { WRITE_ONCE(tp->copied_seq, seq); tcp_rcv_space_adjust(sk); /* Clean up data we have read: This will do ACK frames. */ tcp_recv_skb(sk, seq, &offset); tcp_cleanup_rbuf(sk, length + copylen); ret = 0; if (length == zc->length) zc->recv_skip_hint = 0; } else { if (!zc->recv_skip_hint && sock_flag(sk, SOCK_DONE)) ret = -EIO; } zc->length = length; return ret; } #endif /* Similar to __sock_recv_timestamp, but does not require an skb */ void tcp_recv_timestamp(struct msghdr *msg, const struct sock *sk, struct scm_timestamping_internal *tss) { int new_tstamp = sock_flag(sk, SOCK_TSTAMP_NEW); u32 tsflags = READ_ONCE(sk->sk_tsflags); bool has_timestamping = false; if (tss->ts[0].tv_sec || tss->ts[0].tv_nsec) { if (sock_flag(sk, SOCK_RCVTSTAMP)) { if (sock_flag(sk, SOCK_RCVTSTAMPNS)) { if (new_tstamp) { struct __kernel_timespec kts = { .tv_sec = tss->ts[0].tv_sec, .tv_nsec = tss->ts[0].tv_nsec, }; put_cmsg(msg, SOL_SOCKET, SO_TIMESTAMPNS_NEW, sizeof(kts), &kts); } else { struct __kernel_old_timespec ts_old = { .tv_sec = tss->ts[0].tv_sec, .tv_nsec = tss->ts[0].tv_nsec, }; put_cmsg(msg, SOL_SOCKET, SO_TIMESTAMPNS_OLD, sizeof(ts_old), &ts_old); } } else { if (new_tstamp) { struct __kernel_sock_timeval stv = { .tv_sec = tss->ts[0].tv_sec, .tv_usec = tss->ts[0].tv_nsec / 1000, }; put_cmsg(msg, SOL_SOCKET, SO_TIMESTAMP_NEW, sizeof(stv), &stv); } else { struct __kernel_old_timeval tv = { .tv_sec = tss->ts[0].tv_sec, .tv_usec = tss->ts[0].tv_nsec / 1000, }; put_cmsg(msg, SOL_SOCKET, SO_TIMESTAMP_OLD, sizeof(tv), &tv); } } } if (tsflags & SOF_TIMESTAMPING_SOFTWARE && (tsflags & SOF_TIMESTAMPING_RX_SOFTWARE || !(tsflags & SOF_TIMESTAMPING_OPT_RX_FILTER))) has_timestamping = true; else tss->ts[0] = (struct timespec64) {0}; } if (tss->ts[2].tv_sec || tss->ts[2].tv_nsec) { if (tsflags & SOF_TIMESTAMPING_RAW_HARDWARE && (tsflags & SOF_TIMESTAMPING_RX_HARDWARE || !(tsflags & SOF_TIMESTAMPING_OPT_RX_FILTER))) has_timestamping = true; else tss->ts[2] = (struct timespec64) {0}; } if (has_timestamping) { tss->ts[1] = (struct timespec64) {0}; if (sock_flag(sk, SOCK_TSTAMP_NEW)) put_cmsg_scm_timestamping64(msg, tss); else put_cmsg_scm_timestamping(msg, tss); } } static int tcp_inq_hint(struct sock *sk) { const struct tcp_sock *tp = tcp_sk(sk); u32 copied_seq = READ_ONCE(tp->copied_seq); u32 rcv_nxt = READ_ONCE(tp->rcv_nxt); int inq; inq = rcv_nxt - copied_seq; if (unlikely(inq < 0 || copied_seq != READ_ONCE(tp->copied_seq))) { lock_sock(sk); inq = tp->rcv_nxt - tp->copied_seq; release_sock(sk); } /* After receiving a FIN, tell the user-space to continue reading * by returning a non-zero inq. */ if (inq == 0 && sock_flag(sk, SOCK_DONE)) inq = 1; return inq; } /* batch __xa_alloc() calls and reduce xa_lock()/xa_unlock() overhead. */ struct tcp_xa_pool { u8 max; /* max <= MAX_SKB_FRAGS */ u8 idx; /* idx <= max */ __u32 tokens[MAX_SKB_FRAGS]; netmem_ref netmems[MAX_SKB_FRAGS]; }; static void tcp_xa_pool_commit_locked(struct sock *sk, struct tcp_xa_pool *p) { int i; /* Commit part that has been copied to user space. */ for (i = 0; i < p->idx; i++) __xa_cmpxchg(&sk->sk_user_frags, p->tokens[i], XA_ZERO_ENTRY, (__force void *)p->netmems[i], GFP_KERNEL); /* Rollback what has been pre-allocated and is no longer needed. */ for (; i < p->max; i++) __xa_erase(&sk->sk_user_frags, p->tokens[i]); p->max = 0; p->idx = 0; } static void tcp_xa_pool_commit(struct sock *sk, struct tcp_xa_pool *p) { if (!p->max) return; xa_lock_bh(&sk->sk_user_frags); tcp_xa_pool_commit_locked(sk, p); xa_unlock_bh(&sk->sk_user_frags); } static int tcp_xa_pool_refill(struct sock *sk, struct tcp_xa_pool *p, unsigned int max_frags) { int err, k; if (p->idx < p->max) return 0; xa_lock_bh(&sk->sk_user_frags); tcp_xa_pool_commit_locked(sk, p); for (k = 0; k < max_frags; k++) { err = __xa_alloc(&sk->sk_user_frags, &p->tokens[k], XA_ZERO_ENTRY, xa_limit_31b, GFP_KERNEL); if (err) break; } xa_unlock_bh(&sk->sk_user_frags); p->max = k; p->idx = 0; return k ? 0 : err; } /* On error, returns the -errno. On success, returns number of bytes sent to the * user. May not consume all of @remaining_len. */ static int tcp_recvmsg_dmabuf(struct sock *sk, const struct sk_buff *skb, unsigned int offset, struct msghdr *msg, int remaining_len) { struct dmabuf_cmsg dmabuf_cmsg = { 0 }; struct tcp_xa_pool tcp_xa_pool; unsigned int start; int i, copy, n; int sent = 0; int err = 0; tcp_xa_pool.max = 0; tcp_xa_pool.idx = 0; do { start = skb_headlen(skb); if (skb_frags_readable(skb)) { err = -ENODEV; goto out; } /* Copy header. */ copy = start - offset; if (copy > 0) { copy = min(copy, remaining_len); n = copy_to_iter(skb->data + offset, copy, &msg->msg_iter); if (n != copy) { err = -EFAULT; goto out; } offset += copy; remaining_len -= copy; /* First a dmabuf_cmsg for # bytes copied to user * buffer. */ memset(&dmabuf_cmsg, 0, sizeof(dmabuf_cmsg)); dmabuf_cmsg.frag_size = copy; err = put_cmsg(msg, SOL_SOCKET, SO_DEVMEM_LINEAR, sizeof(dmabuf_cmsg), &dmabuf_cmsg); if (err || msg->msg_flags & MSG_CTRUNC) { msg->msg_flags &= ~MSG_CTRUNC; if (!err) err = -ETOOSMALL; goto out; } sent += copy; if (remaining_len == 0) goto out; } /* after that, send information of dmabuf pages through a * sequence of cmsg */ for (i = 0; i < skb_shinfo(skb)->nr_frags; i++) { skb_frag_t *frag = &skb_shinfo(skb)->frags[i]; struct net_iov *niov; u64 frag_offset; int end; /* !skb_frags_readable() should indicate that ALL the * frags in this skb are dmabuf net_iovs. We're checking * for that flag above, but also check individual frags * here. If the tcp stack is not setting * skb_frags_readable() correctly, we still don't want * to crash here. */ if (!skb_frag_net_iov(frag)) { net_err_ratelimited("Found non-dmabuf skb with net_iov"); err = -ENODEV; goto out; } niov = skb_frag_net_iov(frag); end = start + skb_frag_size(frag); copy = end - offset; if (copy > 0) { copy = min(copy, remaining_len); frag_offset = net_iov_virtual_addr(niov) + skb_frag_off(frag) + offset - start; dmabuf_cmsg.frag_offset = frag_offset; dmabuf_cmsg.frag_size = copy; err = tcp_xa_pool_refill(sk, &tcp_xa_pool, skb_shinfo(skb)->nr_frags - i); if (err) goto out; /* Will perform the exchange later */ dmabuf_cmsg.frag_token = tcp_xa_pool.tokens[tcp_xa_pool.idx]; dmabuf_cmsg.dmabuf_id = net_iov_binding_id(niov); offset += copy; remaining_len -= copy; err = put_cmsg(msg, SOL_SOCKET, SO_DEVMEM_DMABUF, sizeof(dmabuf_cmsg), &dmabuf_cmsg); if (err || msg->msg_flags & MSG_CTRUNC) { msg->msg_flags &= ~MSG_CTRUNC; if (!err) err = -ETOOSMALL; goto out; } atomic_long_inc(&niov->pp_ref_count); tcp_xa_pool.netmems[tcp_xa_pool.idx++] = skb_frag_netmem(frag); sent += copy; if (remaining_len == 0) goto out; } start = end; } tcp_xa_pool_commit(sk, &tcp_xa_pool); if (!remaining_len) goto out; /* if remaining_len is not satisfied yet, we need to go to the * next frag in the frag_list to satisfy remaining_len. */ skb = skb_shinfo(skb)->frag_list ?: skb->next; offset = offset - start; } while (skb); if (remaining_len) { err = -EFAULT; goto out; } out: tcp_xa_pool_commit(sk, &tcp_xa_pool); if (!sent) sent = err; return sent; } /* * This routine copies from a sock struct into the user buffer. * * Technical note: in 2.3 we work on _locked_ socket, so that * tricks with *seq access order and skb->users are not required. * Probably, code can be easily improved even more. */ static int tcp_recvmsg_locked(struct sock *sk, struct msghdr *msg, size_t len, int flags, struct scm_timestamping_internal *tss, int *cmsg_flags) { struct tcp_sock *tp = tcp_sk(sk); int last_copied_dmabuf = -1; /* uninitialized */ int copied = 0; u32 peek_seq; u32 *seq; unsigned long used; int err; int target; /* Read at least this many bytes */ long timeo; struct sk_buff *skb, *last; u32 peek_offset = 0; u32 urg_hole = 0; err = -ENOTCONN; if (sk->sk_state == TCP_LISTEN) goto out; if (tp->recvmsg_inq) { *cmsg_flags = TCP_CMSG_INQ; msg->msg_get_inq = 1; } timeo = sock_rcvtimeo(sk, flags & MSG_DONTWAIT); /* Urgent data needs to be handled specially. */ if (flags & MSG_OOB) goto recv_urg; if (unlikely(tp->repair)) { err = -EPERM; if (!(flags & MSG_PEEK)) goto out; if (tp->repair_queue == TCP_SEND_QUEUE) goto recv_sndq; err = -EINVAL; if (tp->repair_queue == TCP_NO_QUEUE) goto out; /* 'common' recv queue MSG_PEEK-ing */ } seq = &tp->copied_seq; if (flags & MSG_PEEK) { peek_offset = max(sk_peek_offset(sk, flags), 0); peek_seq = tp->copied_seq + peek_offset; seq = &peek_seq; } target = sock_rcvlowat(sk, flags & MSG_WAITALL, len); do { u32 offset; /* Are we at urgent data? Stop if we have read anything or have SIGURG pending. */ if (unlikely(tp->urg_data) && tp->urg_seq == *seq) { if (copied) break; if (signal_pending(current)) { copied = timeo ? sock_intr_errno(timeo) : -EAGAIN; break; } } /* Next get a buffer. */ last = skb_peek_tail(&sk->sk_receive_queue); skb_queue_walk(&sk->sk_receive_queue, skb) { last = skb; /* Now that we have two receive queues this * shouldn't happen. */ if (WARN(before(*seq, TCP_SKB_CB(skb)->seq), "TCP recvmsg seq # bug: copied %X, seq %X, rcvnxt %X, fl %X\n", *seq, TCP_SKB_CB(skb)->seq, tp->rcv_nxt, flags)) break; offset = *seq - TCP_SKB_CB(skb)->seq; if (unlikely(TCP_SKB_CB(skb)->tcp_flags & TCPHDR_SYN)) { pr_err_once("%s: found a SYN, please report !\n", __func__); offset--; } if (offset < skb->len) goto found_ok_skb; if (TCP_SKB_CB(skb)->tcp_flags & TCPHDR_FIN) goto found_fin_ok; WARN(!(flags & MSG_PEEK), "TCP recvmsg seq # bug 2: copied %X, seq %X, rcvnxt %X, fl %X\n", *seq, TCP_SKB_CB(skb)->seq, tp->rcv_nxt, flags); } /* Well, if we have backlog, try to process it now yet. */ if (copied >= target && !READ_ONCE(sk->sk_backlog.tail)) break; if (copied) { if (!timeo || sk->sk_err || sk->sk_state == TCP_CLOSE || (sk->sk_shutdown & RCV_SHUTDOWN) || signal_pending(current)) break; } else { if (sock_flag(sk, SOCK_DONE)) break; if (sk->sk_err) { copied = sock_error(sk); break; } if (sk->sk_shutdown & RCV_SHUTDOWN) break; if (sk->sk_state == TCP_CLOSE) { /* This occurs when user tries to read * from never connected socket. */ copied = -ENOTCONN; break; } if (!timeo) { copied = -EAGAIN; break; } if (signal_pending(current)) { copied = sock_intr_errno(timeo); break; } } if (copied >= target) { /* Do not sleep, just process backlog. */ __sk_flush_backlog(sk); } else { tcp_cleanup_rbuf(sk, copied); err = sk_wait_data(sk, &timeo, last); if (err < 0) { err = copied ? : err; goto out; } } if ((flags & MSG_PEEK) && (peek_seq - peek_offset - copied - urg_hole != tp->copied_seq)) { net_dbg_ratelimited("TCP(%s:%d): Application bug, race in MSG_PEEK\n", current->comm, task_pid_nr(current)); peek_seq = tp->copied_seq + peek_offset; } continue; found_ok_skb: /* Ok so how much can we use? */ used = skb->len - offset; if (len < used) used = len; /* Do we have urgent data here? */ if (unlikely(tp->urg_data)) { u32 urg_offset = tp->urg_seq - *seq; if (urg_offset < used) { if (!urg_offset) { if (!sock_flag(sk, SOCK_URGINLINE)) { WRITE_ONCE(*seq, *seq + 1); urg_hole++; offset++; used--; if (!used) goto skip_copy; } } else used = urg_offset; } } if (!(flags & MSG_TRUNC)) { if (last_copied_dmabuf != -1 && last_copied_dmabuf != !skb_frags_readable(skb)) break; if (skb_frags_readable(skb)) { err = skb_copy_datagram_msg(skb, offset, msg, used); if (err) { /* Exception. Bailout! */ if (!copied) copied = -EFAULT; break; } } else { if (!(flags & MSG_SOCK_DEVMEM)) { /* dmabuf skbs can only be received * with the MSG_SOCK_DEVMEM flag. */ if (!copied) copied = -EFAULT; break; } err = tcp_recvmsg_dmabuf(sk, skb, offset, msg, used); if (err <= 0) { if (!copied) copied = -EFAULT; break; } used = err; } } last_copied_dmabuf = !skb_frags_readable(skb); WRITE_ONCE(*seq, *seq + used); copied += used; len -= used; if (flags & MSG_PEEK) sk_peek_offset_fwd(sk, used); else sk_peek_offset_bwd(sk, used); tcp_rcv_space_adjust(sk); skip_copy: if (unlikely(tp->urg_data) && after(tp->copied_seq, tp->urg_seq)) { WRITE_ONCE(tp->urg_data, 0); tcp_fast_path_check(sk); } if (TCP_SKB_CB(skb)->has_rxtstamp) { tcp_update_recv_tstamps(skb, tss); *cmsg_flags |= TCP_CMSG_TS; } if (used + offset < skb->len) continue; if (TCP_SKB_CB(skb)->tcp_flags & TCPHDR_FIN) goto found_fin_ok; if (!(flags & MSG_PEEK)) tcp_eat_recv_skb(sk, skb); continue; found_fin_ok: /* Process the FIN. */ WRITE_ONCE(*seq, *seq + 1); if (!(flags & MSG_PEEK)) tcp_eat_recv_skb(sk, skb); break; } while (len > 0); /* According to UNIX98, msg_name/msg_namelen are ignored * on connected socket. I was just happy when found this 8) --ANK */ /* Clean up data we have read: This will do ACK frames. */ tcp_cleanup_rbuf(sk, copied); return copied; out: return err; recv_urg: err = tcp_recv_urg(sk, msg, len, flags); goto out; recv_sndq: err = tcp_peek_sndq(sk, msg, len); goto out; } int tcp_recvmsg(struct sock *sk, struct msghdr *msg, size_t len, int flags, int *addr_len) { int cmsg_flags = 0, ret; struct scm_timestamping_internal tss; if (unlikely(flags & MSG_ERRQUEUE)) return inet_recv_error(sk, msg, len, addr_len); if (sk_can_busy_loop(sk) && skb_queue_empty_lockless(&sk->sk_receive_queue) && sk->sk_state == TCP_ESTABLISHED) sk_busy_loop(sk, flags & MSG_DONTWAIT); lock_sock(sk); ret = tcp_recvmsg_locked(sk, msg, len, flags, &tss, &cmsg_flags); release_sock(sk); if ((cmsg_flags || msg->msg_get_inq) && ret >= 0) { if (cmsg_flags & TCP_CMSG_TS) tcp_recv_timestamp(msg, sk, &tss); if (msg->msg_get_inq) { msg->msg_inq = tcp_inq_hint(sk); if (cmsg_flags & TCP_CMSG_INQ) put_cmsg(msg, SOL_TCP, TCP_CM_INQ, sizeof(msg->msg_inq), &msg->msg_inq); } } return ret; } EXPORT_SYMBOL(tcp_recvmsg); void tcp_set_state(struct sock *sk, int state) { int oldstate = sk->sk_state; /* We defined a new enum for TCP states that are exported in BPF * so as not force the internal TCP states to be frozen. The * following checks will detect if an internal state value ever * differs from the BPF value. If this ever happens, then we will * need to remap the internal value to the BPF value before calling * tcp_call_bpf_2arg. */ BUILD_BUG_ON((int)BPF_TCP_ESTABLISHED != (int)TCP_ESTABLISHED); BUILD_BUG_ON((int)BPF_TCP_SYN_SENT != (int)TCP_SYN_SENT); BUILD_BUG_ON((int)BPF_TCP_SYN_RECV != (int)TCP_SYN_RECV); BUILD_BUG_ON((int)BPF_TCP_FIN_WAIT1 != (int)TCP_FIN_WAIT1); BUILD_BUG_ON((int)BPF_TCP_FIN_WAIT2 != (int)TCP_FIN_WAIT2); BUILD_BUG_ON((int)BPF_TCP_TIME_WAIT != (int)TCP_TIME_WAIT); BUILD_BUG_ON((int)BPF_TCP_CLOSE != (int)TCP_CLOSE); BUILD_BUG_ON((int)BPF_TCP_CLOSE_WAIT != (int)TCP_CLOSE_WAIT); BUILD_BUG_ON((int)BPF_TCP_LAST_ACK != (int)TCP_LAST_ACK); BUILD_BUG_ON((int)BPF_TCP_LISTEN != (int)TCP_LISTEN); BUILD_BUG_ON((int)BPF_TCP_CLOSING != (int)TCP_CLOSING); BUILD_BUG_ON((int)BPF_TCP_NEW_SYN_RECV != (int)TCP_NEW_SYN_RECV); BUILD_BUG_ON((int)BPF_TCP_BOUND_INACTIVE != (int)TCP_BOUND_INACTIVE); BUILD_BUG_ON((int)BPF_TCP_MAX_STATES != (int)TCP_MAX_STATES); /* bpf uapi header bpf.h defines an anonymous enum with values * BPF_TCP_* used by bpf programs. Currently gcc built vmlinux * is able to emit this enum in DWARF due to the above BUILD_BUG_ON. * But clang built vmlinux does not have this enum in DWARF * since clang removes the above code before generating IR/debuginfo. * Let us explicitly emit the type debuginfo to ensure the * above-mentioned anonymous enum in the vmlinux DWARF and hence BTF * regardless of which compiler is used. */ BTF_TYPE_EMIT_ENUM(BPF_TCP_ESTABLISHED); if (BPF_SOCK_OPS_TEST_FLAG(tcp_sk(sk), BPF_SOCK_OPS_STATE_CB_FLAG)) tcp_call_bpf_2arg(sk, BPF_SOCK_OPS_STATE_CB, oldstate, state); switch (state) { case TCP_ESTABLISHED: if (oldstate != TCP_ESTABLISHED) TCP_INC_STATS(sock_net(sk), TCP_MIB_CURRESTAB); break; case TCP_CLOSE_WAIT: if (oldstate == TCP_SYN_RECV) TCP_INC_STATS(sock_net(sk), TCP_MIB_CURRESTAB); break; case TCP_CLOSE: if (oldstate == TCP_CLOSE_WAIT || oldstate == TCP_ESTABLISHED) TCP_INC_STATS(sock_net(sk), TCP_MIB_ESTABRESETS); sk->sk_prot->unhash(sk); if (inet_csk(sk)->icsk_bind_hash && !(sk->sk_userlocks & SOCK_BINDPORT_LOCK)) inet_put_port(sk); fallthrough; default: if (oldstate == TCP_ESTABLISHED || oldstate == TCP_CLOSE_WAIT) TCP_DEC_STATS(sock_net(sk), TCP_MIB_CURRESTAB); } /* Change state AFTER socket is unhashed to avoid closed * socket sitting in hash tables. */ inet_sk_state_store(sk, state); } EXPORT_SYMBOL_GPL(tcp_set_state); /* * State processing on a close. This implements the state shift for * sending our FIN frame. Note that we only send a FIN for some * states. A shutdown() may have already sent the FIN, or we may be * closed. */ static const unsigned char new_state[16] = { /* current state: new state: action: */ [0 /* (Invalid) */] = TCP_CLOSE, [TCP_ESTABLISHED] = TCP_FIN_WAIT1 | TCP_ACTION_FIN, [TCP_SYN_SENT] = TCP_CLOSE, [TCP_SYN_RECV] = TCP_FIN_WAIT1 | TCP_ACTION_FIN, [TCP_FIN_WAIT1] = TCP_FIN_WAIT1, [TCP_FIN_WAIT2] = TCP_FIN_WAIT2, [TCP_TIME_WAIT] = TCP_CLOSE, [TCP_CLOSE] = TCP_CLOSE, [TCP_CLOSE_WAIT] = TCP_LAST_ACK | TCP_ACTION_FIN, [TCP_LAST_ACK] = TCP_LAST_ACK, [TCP_LISTEN] = TCP_CLOSE, [TCP_CLOSING] = TCP_CLOSING, [TCP_NEW_SYN_RECV] = TCP_CLOSE, /* should not happen ! */ }; static int tcp_close_state(struct sock *sk) { int next = (int)new_state[sk->sk_state]; int ns = next & TCP_STATE_MASK; tcp_set_state(sk, ns); return next & TCP_ACTION_FIN; } /* * Shutdown the sending side of a connection. Much like close except * that we don't receive shut down or sock_set_flag(sk, SOCK_DEAD). */ void tcp_shutdown(struct sock *sk, int how) { /* We need to grab some memory, and put together a FIN, * and then put it into the queue to be sent. * Tim MacKenzie(tym@dibbler.cs.monash.edu.au) 4 Dec '92. */ if (!(how & SEND_SHUTDOWN)) return; /* If we've already sent a FIN, or it's a closed state, skip this. */ if ((1 << sk->sk_state) & (TCPF_ESTABLISHED | TCPF_SYN_SENT | TCPF_CLOSE_WAIT)) { /* Clear out any half completed packets. FIN if needed. */ if (tcp_close_state(sk)) tcp_send_fin(sk); } } EXPORT_SYMBOL(tcp_shutdown); int tcp_orphan_count_sum(void) { int i, total = 0; for_each_possible_cpu(i) total += per_cpu(tcp_orphan_count, i); return max(total, 0); } static int tcp_orphan_cache; static struct timer_list tcp_orphan_timer; #define TCP_ORPHAN_TIMER_PERIOD msecs_to_jiffies(100) static void tcp_orphan_update(struct timer_list *unused) { WRITE_ONCE(tcp_orphan_cache, tcp_orphan_count_sum()); mod_timer(&tcp_orphan_timer, jiffies + TCP_ORPHAN_TIMER_PERIOD); } static bool tcp_too_many_orphans(int shift) { return READ_ONCE(tcp_orphan_cache) << shift > READ_ONCE(sysctl_tcp_max_orphans); } static bool tcp_out_of_memory(const struct sock *sk) { if (sk->sk_wmem_queued > SOCK_MIN_SNDBUF && sk_memory_allocated(sk) > sk_prot_mem_limits(sk, 2)) return true; return false; } bool tcp_check_oom(const struct sock *sk, int shift) { bool too_many_orphans, out_of_socket_memory; too_many_orphans = tcp_too_many_orphans(shift); out_of_socket_memory = tcp_out_of_memory(sk); if (too_many_orphans) net_info_ratelimited("too many orphaned sockets\n"); if (out_of_socket_memory) net_info_ratelimited("out of memory -- consider tuning tcp_mem\n"); return too_many_orphans || out_of_socket_memory; } void __tcp_close(struct sock *sk, long timeout) { struct sk_buff *skb; int data_was_unread = 0; int state; WRITE_ONCE(sk->sk_shutdown, SHUTDOWN_MASK); if (sk->sk_state == TCP_LISTEN) { tcp_set_state(sk, TCP_CLOSE); /* Special case. */ inet_csk_listen_stop(sk); goto adjudge_to_death; } /* We need to flush the recv. buffs. We do this only on the * descriptor close, not protocol-sourced closes, because the * reader process may not have drained the data yet! */ while ((skb = __skb_dequeue(&sk->sk_receive_queue)) != NULL) { u32 len = TCP_SKB_CB(skb)->end_seq - TCP_SKB_CB(skb)->seq; if (TCP_SKB_CB(skb)->tcp_flags & TCPHDR_FIN) len--; data_was_unread += len; __kfree_skb(skb); } /* If socket has been already reset (e.g. in tcp_reset()) - kill it. */ if (sk->sk_state == TCP_CLOSE) goto adjudge_to_death; /* As outlined in RFC 2525, section 2.17, we send a RST here because * data was lost. To witness the awful effects of the old behavior of * always doing a FIN, run an older 2.1.x kernel or 2.0.x, start a bulk * GET in an FTP client, suspend the process, wait for the client to * advertise a zero window, then kill -9 the FTP client, wheee... * Note: timeout is always zero in such a case. */ if (unlikely(tcp_sk(sk)->repair)) { sk->sk_prot->disconnect(sk, 0); } else if (data_was_unread) { /* Unread data was tossed, zap the connection. */ NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPABORTONCLOSE); tcp_set_state(sk, TCP_CLOSE); tcp_send_active_reset(sk, sk->sk_allocation, SK_RST_REASON_TCP_ABORT_ON_CLOSE); } else if (sock_flag(sk, SOCK_LINGER) && !sk->sk_lingertime) { /* Check zero linger _after_ checking for unread data. */ sk->sk_prot->disconnect(sk, 0); NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPABORTONDATA); } else if (tcp_close_state(sk)) { /* We FIN if the application ate all the data before * zapping the connection. */ /* RED-PEN. Formally speaking, we have broken TCP state * machine. State transitions: * * TCP_ESTABLISHED -> TCP_FIN_WAIT1 * TCP_SYN_RECV -> TCP_FIN_WAIT1 (it is difficult) * TCP_CLOSE_WAIT -> TCP_LAST_ACK * * are legal only when FIN has been sent (i.e. in window), * rather than queued out of window. Purists blame. * * F.e. "RFC state" is ESTABLISHED, * if Linux state is FIN-WAIT-1, but FIN is still not sent. * * The visible declinations are that sometimes * we enter time-wait state, when it is not required really * (harmless), do not send active resets, when they are * required by specs (TCP_ESTABLISHED, TCP_CLOSE_WAIT, when * they look as CLOSING or LAST_ACK for Linux) * Probably, I missed some more holelets. * --ANK * XXX (TFO) - To start off we don't support SYN+ACK+FIN * in a single packet! (May consider it later but will * probably need API support or TCP_CORK SYN-ACK until * data is written and socket is closed.) */ tcp_send_fin(sk); } sk_stream_wait_close(sk, timeout); adjudge_to_death: state = sk->sk_state; sock_hold(sk); sock_orphan(sk); local_bh_disable(); bh_lock_sock(sk); /* remove backlog if any, without releasing ownership. */ __release_sock(sk); this_cpu_inc(tcp_orphan_count); /* Have we already been destroyed by a softirq or backlog? */ if (state != TCP_CLOSE && sk->sk_state == TCP_CLOSE) goto out; /* This is a (useful) BSD violating of the RFC. There is a * problem with TCP as specified in that the other end could * keep a socket open forever with no application left this end. * We use a 1 minute timeout (about the same as BSD) then kill * our end. If they send after that then tough - BUT: long enough * that we won't make the old 4*rto = almost no time - whoops * reset mistake. * * Nope, it was not mistake. It is really desired behaviour * f.e. on http servers, when such sockets are useless, but * consume significant resources. Let's do it with special * linger2 option. --ANK */ if (sk->sk_state == TCP_FIN_WAIT2) { struct tcp_sock *tp = tcp_sk(sk); if (READ_ONCE(tp->linger2) < 0) { tcp_set_state(sk, TCP_CLOSE); tcp_send_active_reset(sk, GFP_ATOMIC, SK_RST_REASON_TCP_ABORT_ON_LINGER); __NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPABORTONLINGER); } else { const int tmo = tcp_fin_time(sk); if (tmo > TCP_TIMEWAIT_LEN) { inet_csk_reset_keepalive_timer(sk, tmo - TCP_TIMEWAIT_LEN); } else { tcp_time_wait(sk, TCP_FIN_WAIT2, tmo); goto out; } } } if (sk->sk_state != TCP_CLOSE) { if (tcp_check_oom(sk, 0)) { tcp_set_state(sk, TCP_CLOSE); tcp_send_active_reset(sk, GFP_ATOMIC, SK_RST_REASON_TCP_ABORT_ON_MEMORY); __NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPABORTONMEMORY); } else if (!check_net(sock_net(sk))) { /* Not possible to send reset; just close */ tcp_set_state(sk, TCP_CLOSE); } } if (sk->sk_state == TCP_CLOSE) { struct request_sock *req; req = rcu_dereference_protected(tcp_sk(sk)->fastopen_rsk, lockdep_sock_is_held(sk)); /* We could get here with a non-NULL req if the socket is * aborted (e.g., closed with unread data) before 3WHS * finishes. */ if (req) reqsk_fastopen_remove(sk, req, false); inet_csk_destroy_sock(sk); } /* Otherwise, socket is reprieved until protocol close. */ out: bh_unlock_sock(sk); local_bh_enable(); } void tcp_close(struct sock *sk, long timeout) { lock_sock(sk); __tcp_close(sk, timeout); release_sock(sk); if (!sk->sk_net_refcnt) inet_csk_clear_xmit_timers_sync(sk); sock_put(sk); } EXPORT_SYMBOL(tcp_close); /* These states need RST on ABORT according to RFC793 */ static inline bool tcp_need_reset(int state) { return (1 << state) & (TCPF_ESTABLISHED | TCPF_CLOSE_WAIT | TCPF_FIN_WAIT1 | TCPF_FIN_WAIT2 | TCPF_SYN_RECV); } static void tcp_rtx_queue_purge(struct sock *sk) { struct rb_node *p = rb_first(&sk->tcp_rtx_queue); tcp_sk(sk)->highest_sack = NULL; while (p) { struct sk_buff *skb = rb_to_skb(p); p = rb_next(p); /* Since we are deleting whole queue, no need to * list_del(&skb->tcp_tsorted_anchor) */ tcp_rtx_queue_unlink(skb, sk); tcp_wmem_free_skb(sk, skb); } } void tcp_write_queue_purge(struct sock *sk) { struct sk_buff *skb; tcp_chrono_stop(sk, TCP_CHRONO_BUSY); while ((skb = __skb_dequeue(&sk->sk_write_queue)) != NULL) { tcp_skb_tsorted_anchor_cleanup(skb); tcp_wmem_free_skb(sk, skb); } tcp_rtx_queue_purge(sk); INIT_LIST_HEAD(&tcp_sk(sk)->tsorted_sent_queue); tcp_clear_all_retrans_hints(tcp_sk(sk)); tcp_sk(sk)->packets_out = 0; inet_csk(sk)->icsk_backoff = 0; } int tcp_disconnect(struct sock *sk, int flags) { struct inet_sock *inet = inet_sk(sk); struct inet_connection_sock *icsk = inet_csk(sk); struct tcp_sock *tp = tcp_sk(sk); int old_state = sk->sk_state; u32 seq; if (old_state != TCP_CLOSE) tcp_set_state(sk, TCP_CLOSE); /* ABORT function of RFC793 */ if (old_state == TCP_LISTEN) { inet_csk_listen_stop(sk); } else if (unlikely(tp->repair)) { WRITE_ONCE(sk->sk_err, ECONNABORTED); } else if (tcp_need_reset(old_state)) { tcp_send_active_reset(sk, gfp_any(), SK_RST_REASON_TCP_STATE); WRITE_ONCE(sk->sk_err, ECONNRESET); } else if (tp->snd_nxt != tp->write_seq && (1 << old_state) & (TCPF_CLOSING | TCPF_LAST_ACK)) { /* The last check adjusts for discrepancy of Linux wrt. RFC * states */ tcp_send_active_reset(sk, gfp_any(), SK_RST_REASON_TCP_DISCONNECT_WITH_DATA); WRITE_ONCE(sk->sk_err, ECONNRESET); } else if (old_state == TCP_SYN_SENT) WRITE_ONCE(sk->sk_err, ECONNRESET); tcp_clear_xmit_timers(sk); __skb_queue_purge(&sk->sk_receive_queue); WRITE_ONCE(tp->copied_seq, tp->rcv_nxt); WRITE_ONCE(tp->urg_data, 0); sk_set_peek_off(sk, -1); tcp_write_queue_purge(sk); tcp_fastopen_active_disable_ofo_check(sk); skb_rbtree_purge(&tp->out_of_order_queue); inet->inet_dport = 0; inet_bhash2_reset_saddr(sk); WRITE_ONCE(sk->sk_shutdown, 0); sock_reset_flag(sk, SOCK_DONE); tp->srtt_us = 0; tp->mdev_us = jiffies_to_usecs(TCP_TIMEOUT_INIT); tp->rcv_rtt_last_tsecr = 0; seq = tp->write_seq + tp->max_window + 2; if (!seq) seq = 1; WRITE_ONCE(tp->write_seq, seq); icsk->icsk_backoff = 0; icsk->icsk_probes_out = 0; icsk->icsk_probes_tstamp = 0; icsk->icsk_rto = TCP_TIMEOUT_INIT; icsk->icsk_rto_min = TCP_RTO_MIN; icsk->icsk_delack_max = TCP_DELACK_MAX; tp->snd_ssthresh = TCP_INFINITE_SSTHRESH; tcp_snd_cwnd_set(tp, TCP_INIT_CWND); tp->snd_cwnd_cnt = 0; tp->is_cwnd_limited = 0; tp->max_packets_out = 0; tp->window_clamp = 0; tp->delivered = 0; tp->delivered_ce = 0; if (icsk->icsk_ca_initialized && icsk->icsk_ca_ops->release) icsk->icsk_ca_ops->release(sk); memset(icsk->icsk_ca_priv, 0, sizeof(icsk->icsk_ca_priv)); icsk->icsk_ca_initialized = 0; tcp_set_ca_state(sk, TCP_CA_Open); tp->is_sack_reneg = 0; tcp_clear_retrans(tp); tp->total_retrans = 0; inet_csk_delack_init(sk); /* Initialize rcv_mss to TCP_MIN_MSS to avoid division by 0 * issue in __tcp_select_window() */ icsk->icsk_ack.rcv_mss = TCP_MIN_MSS; memset(&tp->rx_opt, 0, sizeof(tp->rx_opt)); __sk_dst_reset(sk); dst_release(unrcu_pointer(xchg(&sk->sk_rx_dst, NULL))); tcp_saved_syn_free(tp); tp->compressed_ack = 0; tp->segs_in = 0; tp->segs_out = 0; tp->bytes_sent = 0; tp->bytes_acked = 0; tp->bytes_received = 0; tp->bytes_retrans = 0; tp->data_segs_in = 0; tp->data_segs_out = 0; tp->duplicate_sack[0].start_seq = 0; tp->duplicate_sack[0].end_seq = 0; tp->dsack_dups = 0; tp->reord_seen = 0; tp->retrans_out = 0; tp->sacked_out = 0; tp->tlp_high_seq = 0; tp->last_oow_ack_time = 0; tp->plb_rehash = 0; /* There's a bubble in the pipe until at least the first ACK. */ tp->app_limited = ~0U; tp->rate_app_limited = 1; tp->rack.mstamp = 0; tp->rack.advanced = 0; tp->rack.reo_wnd_steps = 1; tp->rack.last_delivered = 0; tp->rack.reo_wnd_persist = 0; tp->rack.dsack_seen = 0; tp->syn_data_acked = 0; tp->rx_opt.saw_tstamp = 0; tp->rx_opt.dsack = 0; tp->rx_opt.num_sacks = 0; tp->rcv_ooopack = 0; /* Clean up fastopen related fields */ tcp_free_fastopen_req(tp); inet_clear_bit(DEFER_CONNECT, sk); tp->fastopen_client_fail = 0; WARN_ON(inet->inet_num && !icsk->icsk_bind_hash); if (sk->sk_frag.page) { put_page(sk->sk_frag.page); sk->sk_frag.page = NULL; sk->sk_frag.offset = 0; } sk_error_report(sk); return 0; } EXPORT_SYMBOL(tcp_disconnect); static inline bool tcp_can_repair_sock(const struct sock *sk) { return sockopt_ns_capable(sock_net(sk)->user_ns, CAP_NET_ADMIN) && (sk->sk_state != TCP_LISTEN); } static int tcp_repair_set_window(struct tcp_sock *tp, sockptr_t optbuf, int len) { struct tcp_repair_window opt; if (!tp->repair) return -EPERM; if (len != sizeof(opt)) return -EINVAL; if (copy_from_sockptr(&opt, optbuf, sizeof(opt))) return -EFAULT; if (opt.max_window < opt.snd_wnd) return -EINVAL; if (after(opt.snd_wl1, tp->rcv_nxt + opt.rcv_wnd)) return -EINVAL; if (after(opt.rcv_wup, tp->rcv_nxt)) return -EINVAL; tp->snd_wl1 = opt.snd_wl1; tp->snd_wnd = opt.snd_wnd; tp->max_window = opt.max_window; tp->rcv_wnd = opt.rcv_wnd; tp->rcv_wup = opt.rcv_wup; return 0; } static int tcp_repair_options_est(struct sock *sk, sockptr_t optbuf, unsigned int len) { struct tcp_sock *tp = tcp_sk(sk); struct tcp_repair_opt opt; size_t offset = 0; while (len >= sizeof(opt)) { if (copy_from_sockptr_offset(&opt, optbuf, offset, sizeof(opt))) return -EFAULT; offset += sizeof(opt); len -= sizeof(opt); switch (opt.opt_code) { case TCPOPT_MSS: tp->rx_opt.mss_clamp = opt.opt_val; tcp_mtup_init(sk); break; case TCPOPT_WINDOW: { u16 snd_wscale = opt.opt_val & 0xFFFF; u16 rcv_wscale = opt.opt_val >> 16; if (snd_wscale > TCP_MAX_WSCALE || rcv_wscale > TCP_MAX_WSCALE) return -EFBIG; tp->rx_opt.snd_wscale = snd_wscale; tp->rx_opt.rcv_wscale = rcv_wscale; tp->rx_opt.wscale_ok = 1; } break; case TCPOPT_SACK_PERM: if (opt.opt_val != 0) return -EINVAL; tp->rx_opt.sack_ok |= TCP_SACK_SEEN; break; case TCPOPT_TIMESTAMP: if (opt.opt_val != 0) return -EINVAL; tp->rx_opt.tstamp_ok = 1; break; } } return 0; } DEFINE_STATIC_KEY_FALSE(tcp_tx_delay_enabled); EXPORT_SYMBOL(tcp_tx_delay_enabled); static void tcp_enable_tx_delay(void) { if (!static_branch_unlikely(&tcp_tx_delay_enabled)) { static int __tcp_tx_delay_enabled = 0; if (cmpxchg(&__tcp_tx_delay_enabled, 0, 1) == 0) { static_branch_enable(&tcp_tx_delay_enabled); pr_info("TCP_TX_DELAY enabled\n"); } } } /* When set indicates to always queue non-full frames. Later the user clears * this option and we transmit any pending partial frames in the queue. This is * meant to be used alongside sendfile() to get properly filled frames when the * user (for example) must write out headers with a write() call first and then * use sendfile to send out the data parts. * * TCP_CORK can be set together with TCP_NODELAY and it is stronger than * TCP_NODELAY. */ void __tcp_sock_set_cork(struct sock *sk, bool on) { struct tcp_sock *tp = tcp_sk(sk); if (on) { tp->nonagle |= TCP_NAGLE_CORK; } else { tp->nonagle &= ~TCP_NAGLE_CORK; if (tp->nonagle & TCP_NAGLE_OFF) tp->nonagle |= TCP_NAGLE_PUSH; tcp_push_pending_frames(sk); } } void tcp_sock_set_cork(struct sock *sk, bool on) { lock_sock(sk); __tcp_sock_set_cork(sk, on); release_sock(sk); } EXPORT_SYMBOL(tcp_sock_set_cork); /* TCP_NODELAY is weaker than TCP_CORK, so that this option on corked socket is * remembered, but it is not activated until cork is cleared. * * However, when TCP_NODELAY is set we make an explicit push, which overrides * even TCP_CORK for currently queued segments. */ void __tcp_sock_set_nodelay(struct sock *sk, bool on) { if (on) { tcp_sk(sk)->nonagle |= TCP_NAGLE_OFF|TCP_NAGLE_PUSH; tcp_push_pending_frames(sk); } else { tcp_sk(sk)->nonagle &= ~TCP_NAGLE_OFF; } } void tcp_sock_set_nodelay(struct sock *sk) { lock_sock(sk); __tcp_sock_set_nodelay(sk, true); release_sock(sk); } EXPORT_SYMBOL(tcp_sock_set_nodelay); static void __tcp_sock_set_quickack(struct sock *sk, int val) { if (!val) { inet_csk_enter_pingpong_mode(sk); return; } inet_csk_exit_pingpong_mode(sk); if ((1 << sk->sk_state) & (TCPF_ESTABLISHED | TCPF_CLOSE_WAIT) && inet_csk_ack_scheduled(sk)) { inet_csk(sk)->icsk_ack.pending |= ICSK_ACK_PUSHED; tcp_cleanup_rbuf(sk, 1); if (!(val & 1)) inet_csk_enter_pingpong_mode(sk); } } void tcp_sock_set_quickack(struct sock *sk, int val) { lock_sock(sk); __tcp_sock_set_quickack(sk, val); release_sock(sk); } EXPORT_SYMBOL(tcp_sock_set_quickack); int tcp_sock_set_syncnt(struct sock *sk, int val) { if (val < 1 || val > MAX_TCP_SYNCNT) return -EINVAL; WRITE_ONCE(inet_csk(sk)->icsk_syn_retries, val); return 0; } EXPORT_SYMBOL(tcp_sock_set_syncnt); int tcp_sock_set_user_timeout(struct sock *sk, int val) { /* Cap the max time in ms TCP will retry or probe the window * before giving up and aborting (ETIMEDOUT) a connection. */ if (val < 0) return -EINVAL; WRITE_ONCE(inet_csk(sk)->icsk_user_timeout, val); return 0; } EXPORT_SYMBOL(tcp_sock_set_user_timeout); int tcp_sock_set_keepidle_locked(struct sock *sk, int val) { struct tcp_sock *tp = tcp_sk(sk); if (val < 1 || val > MAX_TCP_KEEPIDLE) return -EINVAL; /* Paired with WRITE_ONCE() in keepalive_time_when() */ WRITE_ONCE(tp->keepalive_time, val * HZ); if (sock_flag(sk, SOCK_KEEPOPEN) && !((1 << sk->sk_state) & (TCPF_CLOSE | TCPF_LISTEN))) { u32 elapsed = keepalive_time_elapsed(tp); if (tp->keepalive_time > elapsed) elapsed = tp->keepalive_time - elapsed; else elapsed = 0; inet_csk_reset_keepalive_timer(sk, elapsed); } return 0; } int tcp_sock_set_keepidle(struct sock *sk, int val) { int err; lock_sock(sk); err = tcp_sock_set_keepidle_locked(sk, val); release_sock(sk); return err; } EXPORT_SYMBOL(tcp_sock_set_keepidle); int tcp_sock_set_keepintvl(struct sock *sk, int val) { if (val < 1 || val > MAX_TCP_KEEPINTVL) return -EINVAL; WRITE_ONCE(tcp_sk(sk)->keepalive_intvl, val * HZ); return 0; } EXPORT_SYMBOL(tcp_sock_set_keepintvl); int tcp_sock_set_keepcnt(struct sock *sk, int val) { if (val < 1 || val > MAX_TCP_KEEPCNT) return -EINVAL; /* Paired with READ_ONCE() in keepalive_probes() */ WRITE_ONCE(tcp_sk(sk)->keepalive_probes, val); return 0; } EXPORT_SYMBOL(tcp_sock_set_keepcnt); int tcp_set_window_clamp(struct sock *sk, int val) { struct tcp_sock *tp = tcp_sk(sk); if (!val) { if (sk->sk_state != TCP_CLOSE) return -EINVAL; WRITE_ONCE(tp->window_clamp, 0); } else { u32 new_rcv_ssthresh, old_window_clamp = tp->window_clamp; u32 new_window_clamp = val < SOCK_MIN_RCVBUF / 2 ? SOCK_MIN_RCVBUF / 2 : val; if (new_window_clamp == old_window_clamp) return 0; WRITE_ONCE(tp->window_clamp, new_window_clamp); if (new_window_clamp < old_window_clamp) { /* need to apply the reserved mem provisioning only * when shrinking the window clamp */ __tcp_adjust_rcv_ssthresh(sk, tp->window_clamp); } else { new_rcv_ssthresh = min(tp->rcv_wnd, tp->window_clamp); tp->rcv_ssthresh = max(new_rcv_ssthresh, tp->rcv_ssthresh); } } return 0; } /* * Socket option code for TCP. */ int do_tcp_setsockopt(struct sock *sk, int level, int optname, sockptr_t optval, unsigned int optlen) { struct tcp_sock *tp = tcp_sk(sk); struct inet_connection_sock *icsk = inet_csk(sk); struct net *net = sock_net(sk); int val; int err = 0; /* These are data/string values, all the others are ints */ switch (optname) { case TCP_CONGESTION: { char name[TCP_CA_NAME_MAX]; if (optlen < 1) return -EINVAL; val = strncpy_from_sockptr(name, optval, min_t(long, TCP_CA_NAME_MAX-1, optlen)); if (val < 0) return -EFAULT; name[val] = 0; sockopt_lock_sock(sk); err = tcp_set_congestion_control(sk, name, !has_current_bpf_ctx(), sockopt_ns_capable(sock_net(sk)->user_ns, CAP_NET_ADMIN)); sockopt_release_sock(sk); return err; } case TCP_ULP: { char name[TCP_ULP_NAME_MAX]; if (optlen < 1) return -EINVAL; val = strncpy_from_sockptr(name, optval, min_t(long, TCP_ULP_NAME_MAX - 1, optlen)); if (val < 0) return -EFAULT; name[val] = 0; sockopt_lock_sock(sk); err = tcp_set_ulp(sk, name); sockopt_release_sock(sk); return err; } case TCP_FASTOPEN_KEY: { __u8 key[TCP_FASTOPEN_KEY_BUF_LENGTH]; __u8 *backup_key = NULL; /* Allow a backup key as well to facilitate key rotation * First key is the active one. */ if (optlen != TCP_FASTOPEN_KEY_LENGTH && optlen != TCP_FASTOPEN_KEY_BUF_LENGTH) return -EINVAL; if (copy_from_sockptr(key, optval, optlen)) return -EFAULT; if (optlen == TCP_FASTOPEN_KEY_BUF_LENGTH) backup_key = key + TCP_FASTOPEN_KEY_LENGTH; return tcp_fastopen_reset_cipher(net, sk, key, backup_key); } default: /* fallthru */ break; } if (optlen < sizeof(int)) return -EINVAL; if (copy_from_sockptr(&val, optval, sizeof(val))) return -EFAULT; /* Handle options that can be set without locking the socket. */ switch (optname) { case TCP_SYNCNT: return tcp_sock_set_syncnt(sk, val); case TCP_USER_TIMEOUT: return tcp_sock_set_user_timeout(sk, val); case TCP_KEEPINTVL: return tcp_sock_set_keepintvl(sk, val); case TCP_KEEPCNT: return tcp_sock_set_keepcnt(sk, val); case TCP_LINGER2: if (val < 0) WRITE_ONCE(tp->linger2, -1); else if (val > TCP_FIN_TIMEOUT_MAX / HZ) WRITE_ONCE(tp->linger2, TCP_FIN_TIMEOUT_MAX); else WRITE_ONCE(tp->linger2, val * HZ); return 0; case TCP_DEFER_ACCEPT: /* Translate value in seconds to number of retransmits */ WRITE_ONCE(icsk->icsk_accept_queue.rskq_defer_accept, secs_to_retrans(val, TCP_TIMEOUT_INIT / HZ, TCP_RTO_MAX / HZ)); return 0; } sockopt_lock_sock(sk); switch (optname) { case TCP_MAXSEG: /* Values greater than interface MTU won't take effect. However * at the point when this call is done we typically don't yet * know which interface is going to be used */ if (val && (val < TCP_MIN_MSS || val > MAX_TCP_WINDOW)) { err = -EINVAL; break; } tp->rx_opt.user_mss = val; break; case TCP_NODELAY: __tcp_sock_set_nodelay(sk, val); break; case TCP_THIN_LINEAR_TIMEOUTS: if (val < 0 || val > 1) err = -EINVAL; else tp->thin_lto = val; break; case TCP_THIN_DUPACK: if (val < 0 || val > 1) err = -EINVAL; break; case TCP_REPAIR: if (!tcp_can_repair_sock(sk)) err = -EPERM; else if (val == TCP_REPAIR_ON) { tp->repair = 1; sk->sk_reuse = SK_FORCE_REUSE; tp->repair_queue = TCP_NO_QUEUE; } else if (val == TCP_REPAIR_OFF) { tp->repair = 0; sk->sk_reuse = SK_NO_REUSE; tcp_send_window_probe(sk); } else if (val == TCP_REPAIR_OFF_NO_WP) { tp->repair = 0; sk->sk_reuse = SK_NO_REUSE; } else err = -EINVAL; break; case TCP_REPAIR_QUEUE: if (!tp->repair) err = -EPERM; else if ((unsigned int)val < TCP_QUEUES_NR) tp->repair_queue = val; else err = -EINVAL; break; case TCP_QUEUE_SEQ: if (sk->sk_state != TCP_CLOSE) { err = -EPERM; } else if (tp->repair_queue == TCP_SEND_QUEUE) { if (!tcp_rtx_queue_empty(sk)) err = -EPERM; else WRITE_ONCE(tp->write_seq, val); } else if (tp->repair_queue == TCP_RECV_QUEUE) { if (tp->rcv_nxt != tp->copied_seq) { err = -EPERM; } else { WRITE_ONCE(tp->rcv_nxt, val); WRITE_ONCE(tp->copied_seq, val); } } else { err = -EINVAL; } break; case TCP_REPAIR_OPTIONS: if (!tp->repair) err = -EINVAL; else if (sk->sk_state == TCP_ESTABLISHED && !tp->bytes_sent) err = tcp_repair_options_est(sk, optval, optlen); else err = -EPERM; break; case TCP_CORK: __tcp_sock_set_cork(sk, val); break; case TCP_KEEPIDLE: err = tcp_sock_set_keepidle_locked(sk, val); break; case TCP_SAVE_SYN: /* 0: disable, 1: enable, 2: start from ether_header */ if (val < 0 || val > 2) err = -EINVAL; else tp->save_syn = val; break; case TCP_WINDOW_CLAMP: err = tcp_set_window_clamp(sk, val); break; case TCP_QUICKACK: __tcp_sock_set_quickack(sk, val); break; case TCP_AO_REPAIR: if (!tcp_can_repair_sock(sk)) { err = -EPERM; break; } err = tcp_ao_set_repair(sk, optval, optlen); break; #ifdef CONFIG_TCP_AO case TCP_AO_ADD_KEY: case TCP_AO_DEL_KEY: case TCP_AO_INFO: { /* If this is the first TCP-AO setsockopt() on the socket, * sk_state has to be LISTEN or CLOSE. Allow TCP_REPAIR * in any state. */ if ((1 << sk->sk_state) & (TCPF_LISTEN | TCPF_CLOSE)) goto ao_parse; if (rcu_dereference_protected(tcp_sk(sk)->ao_info, lockdep_sock_is_held(sk))) goto ao_parse; if (tp->repair) goto ao_parse; err = -EISCONN; break; ao_parse: err = tp->af_specific->ao_parse(sk, optname, optval, optlen); break; } #endif #ifdef CONFIG_TCP_MD5SIG case TCP_MD5SIG: case TCP_MD5SIG_EXT: err = tp->af_specific->md5_parse(sk, optname, optval, optlen); break; #endif case TCP_FASTOPEN: if (val >= 0 && ((1 << sk->sk_state) & (TCPF_CLOSE | TCPF_LISTEN))) { tcp_fastopen_init_key_once(net); fastopen_queue_tune(sk, val); } else { err = -EINVAL; } break; case TCP_FASTOPEN_CONNECT: if (val > 1 || val < 0) { err = -EINVAL; } else if (READ_ONCE(net->ipv4.sysctl_tcp_fastopen) & TFO_CLIENT_ENABLE) { if (sk->sk_state == TCP_CLOSE) tp->fastopen_connect = val; else err = -EINVAL; } else { err = -EOPNOTSUPP; } break; case TCP_FASTOPEN_NO_COOKIE: if (val > 1 || val < 0) err = -EINVAL; else if (!((1 << sk->sk_state) & (TCPF_CLOSE | TCPF_LISTEN))) err = -EINVAL; else tp->fastopen_no_cookie = val; break; case TCP_TIMESTAMP: if (!tp->repair) { err = -EPERM; break; } /* val is an opaque field, * and low order bit contains usec_ts enable bit. * Its a best effort, and we do not care if user makes an error. */ tp->tcp_usec_ts = val & 1; WRITE_ONCE(tp->tsoffset, val - tcp_clock_ts(tp->tcp_usec_ts)); break; case TCP_REPAIR_WINDOW: err = tcp_repair_set_window(tp, optval, optlen); break; case TCP_NOTSENT_LOWAT: WRITE_ONCE(tp->notsent_lowat, val); sk->sk_write_space(sk); break; case TCP_INQ: if (val > 1 || val < 0) err = -EINVAL; else tp->recvmsg_inq = val; break; case TCP_TX_DELAY: if (val) tcp_enable_tx_delay(); WRITE_ONCE(tp->tcp_tx_delay, val); break; default: err = -ENOPROTOOPT; break; } sockopt_release_sock(sk); return err; } int tcp_setsockopt(struct sock *sk, int level, int optname, sockptr_t optval, unsigned int optlen) { const struct inet_connection_sock *icsk = inet_csk(sk); if (level != SOL_TCP) /* Paired with WRITE_ONCE() in do_ipv6_setsockopt() and tcp_v6_connect() */ return READ_ONCE(icsk->icsk_af_ops)->setsockopt(sk, level, optname, optval, optlen); return do_tcp_setsockopt(sk, level, optname, optval, optlen); } EXPORT_SYMBOL(tcp_setsockopt); static void tcp_get_info_chrono_stats(const struct tcp_sock *tp, struct tcp_info *info) { u64 stats[__TCP_CHRONO_MAX], total = 0; enum tcp_chrono i; for (i = TCP_CHRONO_BUSY; i < __TCP_CHRONO_MAX; ++i) { stats[i] = tp->chrono_stat[i - 1]; if (i == tp->chrono_type) stats[i] += tcp_jiffies32 - tp->chrono_start; stats[i] *= USEC_PER_SEC / HZ; total += stats[i]; } info->tcpi_busy_time = total; info->tcpi_rwnd_limited = stats[TCP_CHRONO_RWND_LIMITED]; info->tcpi_sndbuf_limited = stats[TCP_CHRONO_SNDBUF_LIMITED]; } /* Return information about state of tcp endpoint in API format. */ void tcp_get_info(struct sock *sk, struct tcp_info *info) { const struct tcp_sock *tp = tcp_sk(sk); /* iff sk_type == SOCK_STREAM */ const struct inet_connection_sock *icsk = inet_csk(sk); unsigned long rate; u32 now; u64 rate64; bool slow; memset(info, 0, sizeof(*info)); if (sk->sk_type != SOCK_STREAM) return; info->tcpi_state = inet_sk_state_load(sk); /* Report meaningful fields for all TCP states, including listeners */ rate = READ_ONCE(sk->sk_pacing_rate); rate64 = (rate != ~0UL) ? rate : ~0ULL; info->tcpi_pacing_rate = rate64; rate = READ_ONCE(sk->sk_max_pacing_rate); rate64 = (rate != ~0UL) ? rate : ~0ULL; info->tcpi_max_pacing_rate = rate64; info->tcpi_reordering = tp->reordering; info->tcpi_snd_cwnd = tcp_snd_cwnd(tp); if (info->tcpi_state == TCP_LISTEN) { /* listeners aliased fields : * tcpi_unacked -> Number of children ready for accept() * tcpi_sacked -> max backlog */ info->tcpi_unacked = READ_ONCE(sk->sk_ack_backlog); info->tcpi_sacked = READ_ONCE(sk->sk_max_ack_backlog); return; } slow = lock_sock_fast(sk); info->tcpi_ca_state = icsk->icsk_ca_state; info->tcpi_retransmits = icsk->icsk_retransmits; info->tcpi_probes = icsk->icsk_probes_out; info->tcpi_backoff = icsk->icsk_backoff; if (tp->rx_opt.tstamp_ok) info->tcpi_options |= TCPI_OPT_TIMESTAMPS; if (tcp_is_sack(tp)) info->tcpi_options |= TCPI_OPT_SACK; if (tp->rx_opt.wscale_ok) { info->tcpi_options |= TCPI_OPT_WSCALE; info->tcpi_snd_wscale = tp->rx_opt.snd_wscale; info->tcpi_rcv_wscale = tp->rx_opt.rcv_wscale; } if (tp->ecn_flags & TCP_ECN_OK) info->tcpi_options |= TCPI_OPT_ECN; if (tp->ecn_flags & TCP_ECN_SEEN) info->tcpi_options |= TCPI_OPT_ECN_SEEN; if (tp->syn_data_acked) info->tcpi_options |= TCPI_OPT_SYN_DATA; if (tp->tcp_usec_ts) info->tcpi_options |= TCPI_OPT_USEC_TS; info->tcpi_rto = jiffies_to_usecs(icsk->icsk_rto); info->tcpi_ato = jiffies_to_usecs(min_t(u32, icsk->icsk_ack.ato, tcp_delack_max(sk))); info->tcpi_snd_mss = tp->mss_cache; info->tcpi_rcv_mss = icsk->icsk_ack.rcv_mss; info->tcpi_unacked = tp->packets_out; info->tcpi_sacked = tp->sacked_out; info->tcpi_lost = tp->lost_out; info->tcpi_retrans = tp->retrans_out; now = tcp_jiffies32; info->tcpi_last_data_sent = jiffies_to_msecs(now - tp->lsndtime); info->tcpi_last_data_recv = jiffies_to_msecs(now - icsk->icsk_ack.lrcvtime); info->tcpi_last_ack_recv = jiffies_to_msecs(now - tp->rcv_tstamp); info->tcpi_pmtu = icsk->icsk_pmtu_cookie; info->tcpi_rcv_ssthresh = tp->rcv_ssthresh; info->tcpi_rtt = tp->srtt_us >> 3; info->tcpi_rttvar = tp->mdev_us >> 2; info->tcpi_snd_ssthresh = tp->snd_ssthresh; info->tcpi_advmss = tp->advmss; info->tcpi_rcv_rtt = tp->rcv_rtt_est.rtt_us >> 3; info->tcpi_rcv_space = tp->rcvq_space.space; info->tcpi_total_retrans = tp->total_retrans; info->tcpi_bytes_acked = tp->bytes_acked; info->tcpi_bytes_received = tp->bytes_received; info->tcpi_notsent_bytes = max_t(int, 0, tp->write_seq - tp->snd_nxt); tcp_get_info_chrono_stats(tp, info); info->tcpi_segs_out = tp->segs_out; /* segs_in and data_segs_in can be updated from tcp_segs_in() from BH */ info->tcpi_segs_in = READ_ONCE(tp->segs_in); info->tcpi_data_segs_in = READ_ONCE(tp->data_segs_in); info->tcpi_min_rtt = tcp_min_rtt(tp); info->tcpi_data_segs_out = tp->data_segs_out; info->tcpi_delivery_rate_app_limited = tp->rate_app_limited ? 1 : 0; rate64 = tcp_compute_delivery_rate(tp); if (rate64) info->tcpi_delivery_rate = rate64; info->tcpi_delivered = tp->delivered; info->tcpi_delivered_ce = tp->delivered_ce; info->tcpi_bytes_sent = tp->bytes_sent; info->tcpi_bytes_retrans = tp->bytes_retrans; info->tcpi_dsack_dups = tp->dsack_dups; info->tcpi_reord_seen = tp->reord_seen; info->tcpi_rcv_ooopack = tp->rcv_ooopack; info->tcpi_snd_wnd = tp->snd_wnd; info->tcpi_rcv_wnd = tp->rcv_wnd; info->tcpi_rehash = tp->plb_rehash + tp->timeout_rehash; info->tcpi_fastopen_client_fail = tp->fastopen_client_fail; info->tcpi_total_rto = tp->total_rto; info->tcpi_total_rto_recoveries = tp->total_rto_recoveries; info->tcpi_total_rto_time = tp->total_rto_time; if (tp->rto_stamp) info->tcpi_total_rto_time += tcp_clock_ms() - tp->rto_stamp; unlock_sock_fast(sk, slow); } EXPORT_SYMBOL_GPL(tcp_get_info); static size_t tcp_opt_stats_get_size(void) { return nla_total_size_64bit(sizeof(u64)) + /* TCP_NLA_BUSY */ nla_total_size_64bit(sizeof(u64)) + /* TCP_NLA_RWND_LIMITED */ nla_total_size_64bit(sizeof(u64)) + /* TCP_NLA_SNDBUF_LIMITED */ nla_total_size_64bit(sizeof(u64)) + /* TCP_NLA_DATA_SEGS_OUT */ nla_total_size_64bit(sizeof(u64)) + /* TCP_NLA_TOTAL_RETRANS */ nla_total_size_64bit(sizeof(u64)) + /* TCP_NLA_PACING_RATE */ nla_total_size_64bit(sizeof(u64)) + /* TCP_NLA_DELIVERY_RATE */ nla_total_size(sizeof(u32)) + /* TCP_NLA_SND_CWND */ nla_total_size(sizeof(u32)) + /* TCP_NLA_REORDERING */ nla_total_size(sizeof(u32)) + /* TCP_NLA_MIN_RTT */ nla_total_size(sizeof(u8)) + /* TCP_NLA_RECUR_RETRANS */ nla_total_size(sizeof(u8)) + /* TCP_NLA_DELIVERY_RATE_APP_LMT */ nla_total_size(sizeof(u32)) + /* TCP_NLA_SNDQ_SIZE */ nla_total_size(sizeof(u8)) + /* TCP_NLA_CA_STATE */ nla_total_size(sizeof(u32)) + /* TCP_NLA_SND_SSTHRESH */ nla_total_size(sizeof(u32)) + /* TCP_NLA_DELIVERED */ nla_total_size(sizeof(u32)) + /* TCP_NLA_DELIVERED_CE */ nla_total_size_64bit(sizeof(u64)) + /* TCP_NLA_BYTES_SENT */ nla_total_size_64bit(sizeof(u64)) + /* TCP_NLA_BYTES_RETRANS */ nla_total_size(sizeof(u32)) + /* TCP_NLA_DSACK_DUPS */ nla_total_size(sizeof(u32)) + /* TCP_NLA_REORD_SEEN */ nla_total_size(sizeof(u32)) + /* TCP_NLA_SRTT */ nla_total_size(sizeof(u16)) + /* TCP_NLA_TIMEOUT_REHASH */ nla_total_size(sizeof(u32)) + /* TCP_NLA_BYTES_NOTSENT */ nla_total_size_64bit(sizeof(u64)) + /* TCP_NLA_EDT */ nla_total_size(sizeof(u8)) + /* TCP_NLA_TTL */ nla_total_size(sizeof(u32)) + /* TCP_NLA_REHASH */ 0; } /* Returns TTL or hop limit of an incoming packet from skb. */ static u8 tcp_skb_ttl_or_hop_limit(const struct sk_buff *skb) { if (skb->protocol == htons(ETH_P_IP)) return ip_hdr(skb)->ttl; else if (skb->protocol == htons(ETH_P_IPV6)) return ipv6_hdr(skb)->hop_limit; else return 0; } struct sk_buff *tcp_get_timestamping_opt_stats(const struct sock *sk, const struct sk_buff *orig_skb, const struct sk_buff *ack_skb) { const struct tcp_sock *tp = tcp_sk(sk); struct sk_buff *stats; struct tcp_info info; unsigned long rate; u64 rate64; stats = alloc_skb(tcp_opt_stats_get_size(), GFP_ATOMIC); if (!stats) return NULL; tcp_get_info_chrono_stats(tp, &info); nla_put_u64_64bit(stats, TCP_NLA_BUSY, info.tcpi_busy_time, TCP_NLA_PAD); nla_put_u64_64bit(stats, TCP_NLA_RWND_LIMITED, info.tcpi_rwnd_limited, TCP_NLA_PAD); nla_put_u64_64bit(stats, TCP_NLA_SNDBUF_LIMITED, info.tcpi_sndbuf_limited, TCP_NLA_PAD); nla_put_u64_64bit(stats, TCP_NLA_DATA_SEGS_OUT, tp->data_segs_out, TCP_NLA_PAD); nla_put_u64_64bit(stats, TCP_NLA_TOTAL_RETRANS, tp->total_retrans, TCP_NLA_PAD); rate = READ_ONCE(sk->sk_pacing_rate); rate64 = (rate != ~0UL) ? rate : ~0ULL; nla_put_u64_64bit(stats, TCP_NLA_PACING_RATE, rate64, TCP_NLA_PAD); rate64 = tcp_compute_delivery_rate(tp); nla_put_u64_64bit(stats, TCP_NLA_DELIVERY_RATE, rate64, TCP_NLA_PAD); nla_put_u32(stats, TCP_NLA_SND_CWND, tcp_snd_cwnd(tp)); nla_put_u32(stats, TCP_NLA_REORDERING, tp->reordering); nla_put_u32(stats, TCP_NLA_MIN_RTT, tcp_min_rtt(tp)); nla_put_u8(stats, TCP_NLA_RECUR_RETRANS, inet_csk(sk)->icsk_retransmits); nla_put_u8(stats, TCP_NLA_DELIVERY_RATE_APP_LMT, !!tp->rate_app_limited); nla_put_u32(stats, TCP_NLA_SND_SSTHRESH, tp->snd_ssthresh); nla_put_u32(stats, TCP_NLA_DELIVERED, tp->delivered); nla_put_u32(stats, TCP_NLA_DELIVERED_CE, tp->delivered_ce); nla_put_u32(stats, TCP_NLA_SNDQ_SIZE, tp->write_seq - tp->snd_una); nla_put_u8(stats, TCP_NLA_CA_STATE, inet_csk(sk)->icsk_ca_state); nla_put_u64_64bit(stats, TCP_NLA_BYTES_SENT, tp->bytes_sent, TCP_NLA_PAD); nla_put_u64_64bit(stats, TCP_NLA_BYTES_RETRANS, tp->bytes_retrans, TCP_NLA_PAD); nla_put_u32(stats, TCP_NLA_DSACK_DUPS, tp->dsack_dups); nla_put_u32(stats, TCP_NLA_REORD_SEEN, tp->reord_seen); nla_put_u32(stats, TCP_NLA_SRTT, tp->srtt_us >> 3); nla_put_u16(stats, TCP_NLA_TIMEOUT_REHASH, tp->timeout_rehash); nla_put_u32(stats, TCP_NLA_BYTES_NOTSENT, max_t(int, 0, tp->write_seq - tp->snd_nxt)); nla_put_u64_64bit(stats, TCP_NLA_EDT, orig_skb->skb_mstamp_ns, TCP_NLA_PAD); if (ack_skb) nla_put_u8(stats, TCP_NLA_TTL, tcp_skb_ttl_or_hop_limit(ack_skb)); nla_put_u32(stats, TCP_NLA_REHASH, tp->plb_rehash + tp->timeout_rehash); return stats; } int do_tcp_getsockopt(struct sock *sk, int level, int optname, sockptr_t optval, sockptr_t optlen) { struct inet_connection_sock *icsk = inet_csk(sk); struct tcp_sock *tp = tcp_sk(sk); struct net *net = sock_net(sk); int val, len; if (copy_from_sockptr(&len, optlen, sizeof(int))) return -EFAULT; if (len < 0) return -EINVAL; len = min_t(unsigned int, len, sizeof(int)); switch (optname) { case TCP_MAXSEG: val = tp->mss_cache; if (tp->rx_opt.user_mss && ((1 << sk->sk_state) & (TCPF_CLOSE | TCPF_LISTEN))) val = tp->rx_opt.user_mss; if (tp->repair) val = tp->rx_opt.mss_clamp; break; case TCP_NODELAY: val = !!(tp->nonagle&TCP_NAGLE_OFF); break; case TCP_CORK: val = !!(tp->nonagle&TCP_NAGLE_CORK); break; case TCP_KEEPIDLE: val = keepalive_time_when(tp) / HZ; break; case TCP_KEEPINTVL: val = keepalive_intvl_when(tp) / HZ; break; case TCP_KEEPCNT: val = keepalive_probes(tp); break; case TCP_SYNCNT: val = READ_ONCE(icsk->icsk_syn_retries) ? : READ_ONCE(net->ipv4.sysctl_tcp_syn_retries); break; case TCP_LINGER2: val = READ_ONCE(tp->linger2); if (val >= 0) val = (val ? : READ_ONCE(net->ipv4.sysctl_tcp_fin_timeout)) / HZ; break; case TCP_DEFER_ACCEPT: val = READ_ONCE(icsk->icsk_accept_queue.rskq_defer_accept); val = retrans_to_secs(val, TCP_TIMEOUT_INIT / HZ, TCP_RTO_MAX / HZ); break; case TCP_WINDOW_CLAMP: val = READ_ONCE(tp->window_clamp); break; case TCP_INFO: { struct tcp_info info; if (copy_from_sockptr(&len, optlen, sizeof(int))) return -EFAULT; tcp_get_info(sk, &info); len = min_t(unsigned int, len, sizeof(info)); if (copy_to_sockptr(optlen, &len, sizeof(int))) return -EFAULT; if (copy_to_sockptr(optval, &info, len)) return -EFAULT; return 0; } case TCP_CC_INFO: { const struct tcp_congestion_ops *ca_ops; union tcp_cc_info info; size_t sz = 0; int attr; if (copy_from_sockptr(&len, optlen, sizeof(int))) return -EFAULT; ca_ops = icsk->icsk_ca_ops; if (ca_ops && ca_ops->get_info) sz = ca_ops->get_info(sk, ~0U, &attr, &info); len = min_t(unsigned int, len, sz); if (copy_to_sockptr(optlen, &len, sizeof(int))) return -EFAULT; if (copy_to_sockptr(optval, &info, len)) return -EFAULT; return 0; } case TCP_QUICKACK: val = !inet_csk_in_pingpong_mode(sk); break; case TCP_CONGESTION: if (copy_from_sockptr(&len, optlen, sizeof(int))) return -EFAULT; len = min_t(unsigned int, len, TCP_CA_NAME_MAX); if (copy_to_sockptr(optlen, &len, sizeof(int))) return -EFAULT; if (copy_to_sockptr(optval, icsk->icsk_ca_ops->name, len)) return -EFAULT; return 0; case TCP_ULP: if (copy_from_sockptr(&len, optlen, sizeof(int))) return -EFAULT; len = min_t(unsigned int, len, TCP_ULP_NAME_MAX); if (!icsk->icsk_ulp_ops) { len = 0; if (copy_to_sockptr(optlen, &len, sizeof(int))) return -EFAULT; return 0; } if (copy_to_sockptr(optlen, &len, sizeof(int))) return -EFAULT; if (copy_to_sockptr(optval, icsk->icsk_ulp_ops->name, len)) return -EFAULT; return 0; case TCP_FASTOPEN_KEY: { u64 key[TCP_FASTOPEN_KEY_BUF_LENGTH / sizeof(u64)]; unsigned int key_len; if (copy_from_sockptr(&len, optlen, sizeof(int))) return -EFAULT; key_len = tcp_fastopen_get_cipher(net, icsk, key) * TCP_FASTOPEN_KEY_LENGTH; len = min_t(unsigned int, len, key_len); if (copy_to_sockptr(optlen, &len, sizeof(int))) return -EFAULT; if (copy_to_sockptr(optval, key, len)) return -EFAULT; return 0; } case TCP_THIN_LINEAR_TIMEOUTS: val = tp->thin_lto; break; case TCP_THIN_DUPACK: val = 0; break; case TCP_REPAIR: val = tp->repair; break; case TCP_REPAIR_QUEUE: if (tp->repair) val = tp->repair_queue; else return -EINVAL; break; case TCP_REPAIR_WINDOW: { struct tcp_repair_window opt; if (copy_from_sockptr(&len, optlen, sizeof(int))) return -EFAULT; if (len != sizeof(opt)) return -EINVAL; if (!tp->repair) return -EPERM; opt.snd_wl1 = tp->snd_wl1; opt.snd_wnd = tp->snd_wnd; opt.max_window = tp->max_window; opt.rcv_wnd = tp->rcv_wnd; opt.rcv_wup = tp->rcv_wup; if (copy_to_sockptr(optval, &opt, len)) return -EFAULT; return 0; } case TCP_QUEUE_SEQ: if (tp->repair_queue == TCP_SEND_QUEUE) val = tp->write_seq; else if (tp->repair_queue == TCP_RECV_QUEUE) val = tp->rcv_nxt; else return -EINVAL; break; case TCP_USER_TIMEOUT: val = READ_ONCE(icsk->icsk_user_timeout); break; case TCP_FASTOPEN: val = READ_ONCE(icsk->icsk_accept_queue.fastopenq.max_qlen); break; case TCP_FASTOPEN_CONNECT: val = tp->fastopen_connect; break; case TCP_FASTOPEN_NO_COOKIE: val = tp->fastopen_no_cookie; break; case TCP_TX_DELAY: val = READ_ONCE(tp->tcp_tx_delay); break; case TCP_TIMESTAMP: val = tcp_clock_ts(tp->tcp_usec_ts) + READ_ONCE(tp->tsoffset); if (tp->tcp_usec_ts) val |= 1; else val &= ~1; break; case TCP_NOTSENT_LOWAT: val = READ_ONCE(tp->notsent_lowat); break; case TCP_INQ: val = tp->recvmsg_inq; break; case TCP_SAVE_SYN: val = tp->save_syn; break; case TCP_SAVED_SYN: { if (copy_from_sockptr(&len, optlen, sizeof(int))) return -EFAULT; sockopt_lock_sock(sk); if (tp->saved_syn) { if (len < tcp_saved_syn_len(tp->saved_syn)) { len = tcp_saved_syn_len(tp->saved_syn); if (copy_to_sockptr(optlen, &len, sizeof(int))) { sockopt_release_sock(sk); return -EFAULT; } sockopt_release_sock(sk); return -EINVAL; } len = tcp_saved_syn_len(tp->saved_syn); if (copy_to_sockptr(optlen, &len, sizeof(int))) { sockopt_release_sock(sk); return -EFAULT; } if (copy_to_sockptr(optval, tp->saved_syn->data, len)) { sockopt_release_sock(sk); return -EFAULT; } tcp_saved_syn_free(tp); sockopt_release_sock(sk); } else { sockopt_release_sock(sk); len = 0; if (copy_to_sockptr(optlen, &len, sizeof(int))) return -EFAULT; } return 0; } #ifdef CONFIG_MMU case TCP_ZEROCOPY_RECEIVE: { struct scm_timestamping_internal tss; struct tcp_zerocopy_receive zc = {}; int err; if (copy_from_sockptr(&len, optlen, sizeof(int))) return -EFAULT; if (len < 0 || len < offsetofend(struct tcp_zerocopy_receive, length)) return -EINVAL; if (unlikely(len > sizeof(zc))) { err = check_zeroed_sockptr(optval, sizeof(zc), len - sizeof(zc)); if (err < 1) return err == 0 ? -EINVAL : err; len = sizeof(zc); if (copy_to_sockptr(optlen, &len, sizeof(int))) return -EFAULT; } if (copy_from_sockptr(&zc, optval, len)) return -EFAULT; if (zc.reserved) return -EINVAL; if (zc.msg_flags & ~(TCP_VALID_ZC_MSG_FLAGS)) return -EINVAL; sockopt_lock_sock(sk); err = tcp_zerocopy_receive(sk, &zc, &tss); err = BPF_CGROUP_RUN_PROG_GETSOCKOPT_KERN(sk, level, optname, &zc, &len, err); sockopt_release_sock(sk); if (len >= offsetofend(struct tcp_zerocopy_receive, msg_flags)) goto zerocopy_rcv_cmsg; switch (len) { case offsetofend(struct tcp_zerocopy_receive, msg_flags): goto zerocopy_rcv_cmsg; case offsetofend(struct tcp_zerocopy_receive, msg_controllen): case offsetofend(struct tcp_zerocopy_receive, msg_control): case offsetofend(struct tcp_zerocopy_receive, flags): case offsetofend(struct tcp_zerocopy_receive, copybuf_len): case offsetofend(struct tcp_zerocopy_receive, copybuf_address): case offsetofend(struct tcp_zerocopy_receive, err): goto zerocopy_rcv_sk_err; case offsetofend(struct tcp_zerocopy_receive, inq): goto zerocopy_rcv_inq; case offsetofend(struct tcp_zerocopy_receive, length): default: goto zerocopy_rcv_out; } zerocopy_rcv_cmsg: if (zc.msg_flags & TCP_CMSG_TS) tcp_zc_finalize_rx_tstamp(sk, &zc, &tss); else zc.msg_flags = 0; zerocopy_rcv_sk_err: if (!err) zc.err = sock_error(sk); zerocopy_rcv_inq: zc.inq = tcp_inq_hint(sk); zerocopy_rcv_out: if (!err && copy_to_sockptr(optval, &zc, len)) err = -EFAULT; return err; } #endif case TCP_AO_REPAIR: if (!tcp_can_repair_sock(sk)) return -EPERM; return tcp_ao_get_repair(sk, optval, optlen); case TCP_AO_GET_KEYS: case TCP_AO_INFO: { int err; sockopt_lock_sock(sk); if (optname == TCP_AO_GET_KEYS) err = tcp_ao_get_mkts(sk, optval, optlen); else err = tcp_ao_get_sock_info(sk, optval, optlen); sockopt_release_sock(sk); return err; } case TCP_IS_MPTCP: val = 0; break; default: return -ENOPROTOOPT; } if (copy_to_sockptr(optlen, &len, sizeof(int))) return -EFAULT; if (copy_to_sockptr(optval, &val, len)) return -EFAULT; return 0; } bool tcp_bpf_bypass_getsockopt(int level, int optname) { /* TCP do_tcp_getsockopt has optimized getsockopt implementation * to avoid extra socket lock for TCP_ZEROCOPY_RECEIVE. */ if (level == SOL_TCP && optname == TCP_ZEROCOPY_RECEIVE) return true; return false; } EXPORT_SYMBOL(tcp_bpf_bypass_getsockopt); int tcp_getsockopt(struct sock *sk, int level, int optname, char __user *optval, int __user *optlen) { struct inet_connection_sock *icsk = inet_csk(sk); if (level != SOL_TCP) /* Paired with WRITE_ONCE() in do_ipv6_setsockopt() and tcp_v6_connect() */ return READ_ONCE(icsk->icsk_af_ops)->getsockopt(sk, level, optname, optval, optlen); return do_tcp_getsockopt(sk, level, optname, USER_SOCKPTR(optval), USER_SOCKPTR(optlen)); } EXPORT_SYMBOL(tcp_getsockopt); #ifdef CONFIG_TCP_MD5SIG int tcp_md5_sigpool_id = -1; EXPORT_SYMBOL_GPL(tcp_md5_sigpool_id); int tcp_md5_alloc_sigpool(void) { size_t scratch_size; int ret; scratch_size = sizeof(union tcp_md5sum_block) + sizeof(struct tcphdr); ret = tcp_sigpool_alloc_ahash("md5", scratch_size); if (ret >= 0) { /* As long as any md5 sigpool was allocated, the return * id would stay the same. Re-write the id only for the case * when previously all MD5 keys were deleted and this call * allocates the first MD5 key, which may return a different * sigpool id than was used previously. */ WRITE_ONCE(tcp_md5_sigpool_id, ret); /* Avoids the compiler potentially being smart here */ return 0; } return ret; } void tcp_md5_release_sigpool(void) { tcp_sigpool_release(READ_ONCE(tcp_md5_sigpool_id)); } void tcp_md5_add_sigpool(void) { tcp_sigpool_get(READ_ONCE(tcp_md5_sigpool_id)); } int tcp_md5_hash_key(struct tcp_sigpool *hp, const struct tcp_md5sig_key *key) { u8 keylen = READ_ONCE(key->keylen); /* paired with WRITE_ONCE() in tcp_md5_do_add */ struct scatterlist sg; sg_init_one(&sg, key->key, keylen); ahash_request_set_crypt(hp->req, &sg, NULL, keylen); /* We use data_race() because tcp_md5_do_add() might change * key->key under us */ return data_race(crypto_ahash_update(hp->req)); } EXPORT_SYMBOL(tcp_md5_hash_key); /* Called with rcu_read_lock() */ static enum skb_drop_reason tcp_inbound_md5_hash(const struct sock *sk, const struct sk_buff *skb, const void *saddr, const void *daddr, int family, int l3index, const __u8 *hash_location) { /* This gets called for each TCP segment that has TCP-MD5 option. * We have 3 drop cases: * o No MD5 hash and one expected. * o MD5 hash and we're not expecting one. * o MD5 hash and its wrong. */ const struct tcp_sock *tp = tcp_sk(sk); struct tcp_md5sig_key *key; u8 newhash[16]; int genhash; key = tcp_md5_do_lookup(sk, l3index, saddr, family); if (!key && hash_location) { NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPMD5UNEXPECTED); trace_tcp_hash_md5_unexpected(sk, skb); return SKB_DROP_REASON_TCP_MD5UNEXPECTED; } /* Check the signature. * To support dual stack listeners, we need to handle * IPv4-mapped case. */ if (family == AF_INET) genhash = tcp_v4_md5_hash_skb(newhash, key, NULL, skb); else genhash = tp->af_specific->calc_md5_hash(newhash, key, NULL, skb); if (genhash || memcmp(hash_location, newhash, 16) != 0) { NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPMD5FAILURE); trace_tcp_hash_md5_mismatch(sk, skb); return SKB_DROP_REASON_TCP_MD5FAILURE; } return SKB_NOT_DROPPED_YET; } #else static inline enum skb_drop_reason tcp_inbound_md5_hash(const struct sock *sk, const struct sk_buff *skb, const void *saddr, const void *daddr, int family, int l3index, const __u8 *hash_location) { return SKB_NOT_DROPPED_YET; } #endif /* Called with rcu_read_lock() */ enum skb_drop_reason tcp_inbound_hash(struct sock *sk, const struct request_sock *req, const struct sk_buff *skb, const void *saddr, const void *daddr, int family, int dif, int sdif) { const struct tcphdr *th = tcp_hdr(skb); const struct tcp_ao_hdr *aoh; const __u8 *md5_location; int l3index; /* Invalid option or two times meet any of auth options */ if (tcp_parse_auth_options(th, &md5_location, &aoh)) { trace_tcp_hash_bad_header(sk, skb); return SKB_DROP_REASON_TCP_AUTH_HDR; } if (req) { if (tcp_rsk_used_ao(req) != !!aoh) { u8 keyid, rnext, maclen; if (aoh) { keyid = aoh->keyid; rnext = aoh->rnext_keyid; maclen = tcp_ao_hdr_maclen(aoh); } else { keyid = rnext = maclen = 0; } NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPAOBAD); trace_tcp_ao_handshake_failure(sk, skb, keyid, rnext, maclen); return SKB_DROP_REASON_TCP_AOFAILURE; } } /* sdif set, means packet ingressed via a device * in an L3 domain and dif is set to the l3mdev */ l3index = sdif ? dif : 0; /* Fast path: unsigned segments */ if (likely(!md5_location && !aoh)) { /* Drop if there's TCP-MD5 or TCP-AO key with any rcvid/sndid * for the remote peer. On TCP-AO established connection * the last key is impossible to remove, so there's * always at least one current_key. */ if (tcp_ao_required(sk, saddr, family, l3index, true)) { trace_tcp_hash_ao_required(sk, skb); return SKB_DROP_REASON_TCP_AONOTFOUND; } if (unlikely(tcp_md5_do_lookup(sk, l3index, saddr, family))) { NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPMD5NOTFOUND); trace_tcp_hash_md5_required(sk, skb); return SKB_DROP_REASON_TCP_MD5NOTFOUND; } return SKB_NOT_DROPPED_YET; } if (aoh) return tcp_inbound_ao_hash(sk, skb, family, req, l3index, aoh); return tcp_inbound_md5_hash(sk, skb, saddr, daddr, family, l3index, md5_location); } EXPORT_SYMBOL_GPL(tcp_inbound_hash); void tcp_done(struct sock *sk) { struct request_sock *req; /* We might be called with a new socket, after * inet_csk_prepare_forced_close() has been called * so we can not use lockdep_sock_is_held(sk) */ req = rcu_dereference_protected(tcp_sk(sk)->fastopen_rsk, 1); if (sk->sk_state == TCP_SYN_SENT || sk->sk_state == TCP_SYN_RECV) TCP_INC_STATS(sock_net(sk), TCP_MIB_ATTEMPTFAILS); tcp_set_state(sk, TCP_CLOSE); tcp_clear_xmit_timers(sk); if (req) reqsk_fastopen_remove(sk, req, false); WRITE_ONCE(sk->sk_shutdown, SHUTDOWN_MASK); if (!sock_flag(sk, SOCK_DEAD)) sk->sk_state_change(sk); else inet_csk_destroy_sock(sk); } EXPORT_SYMBOL_GPL(tcp_done); int tcp_abort(struct sock *sk, int err) { int state = inet_sk_state_load(sk); if (state == TCP_NEW_SYN_RECV) { struct request_sock *req = inet_reqsk(sk); local_bh_disable(); inet_csk_reqsk_queue_drop(req->rsk_listener, req); local_bh_enable(); return 0; } if (state == TCP_TIME_WAIT) { struct inet_timewait_sock *tw = inet_twsk(sk); refcount_inc(&tw->tw_refcnt); local_bh_disable(); inet_twsk_deschedule_put(tw); local_bh_enable(); return 0; } /* BPF context ensures sock locking. */ if (!has_current_bpf_ctx()) /* Don't race with userspace socket closes such as tcp_close. */ lock_sock(sk); /* Avoid closing the same socket twice. */ if (sk->sk_state == TCP_CLOSE) { if (!has_current_bpf_ctx()) release_sock(sk); return -ENOENT; } if (sk->sk_state == TCP_LISTEN) { tcp_set_state(sk, TCP_CLOSE); inet_csk_listen_stop(sk); } /* Don't race with BH socket closes such as inet_csk_listen_stop. */ local_bh_disable(); bh_lock_sock(sk); if (tcp_need_reset(sk->sk_state)) tcp_send_active_reset(sk, GFP_ATOMIC, SK_RST_REASON_TCP_STATE); tcp_done_with_error(sk, err); bh_unlock_sock(sk); local_bh_enable(); if (!has_current_bpf_ctx()) release_sock(sk); return 0; } EXPORT_SYMBOL_GPL(tcp_abort); extern struct tcp_congestion_ops tcp_reno; static __initdata unsigned long thash_entries; static int __init set_thash_entries(char *str) { ssize_t ret; if (!str) return 0; ret = kstrtoul(str, 0, &thash_entries); if (ret) return 0; return 1; } __setup("thash_entries=", set_thash_entries); static void __init tcp_init_mem(void) { unsigned long limit = nr_free_buffer_pages() / 16; limit = max(limit, 128UL); sysctl_tcp_mem[0] = limit / 4 * 3; /* 4.68 % */ sysctl_tcp_mem[1] = limit; /* 6.25 % */ sysctl_tcp_mem[2] = sysctl_tcp_mem[0] * 2; /* 9.37 % */ } static void __init tcp_struct_check(void) { /* TX read-mostly hotpath cache lines */ CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_read_tx, max_window); CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_read_tx, rcv_ssthresh); CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_read_tx, reordering); CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_read_tx, notsent_lowat); CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_read_tx, gso_segs); CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_read_tx, lost_skb_hint); CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_read_tx, retransmit_skb_hint); CACHELINE_ASSERT_GROUP_SIZE(struct tcp_sock, tcp_sock_read_tx, 40); /* TXRX read-mostly hotpath cache lines */ CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_read_txrx, tsoffset); CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_read_txrx, snd_wnd); CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_read_txrx, mss_cache); CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_read_txrx, snd_cwnd); CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_read_txrx, prr_out); CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_read_txrx, lost_out); CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_read_txrx, sacked_out); CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_read_txrx, scaling_ratio); CACHELINE_ASSERT_GROUP_SIZE(struct tcp_sock, tcp_sock_read_txrx, 32); /* RX read-mostly hotpath cache lines */ CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_read_rx, copied_seq); CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_read_rx, rcv_tstamp); CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_read_rx, snd_wl1); CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_read_rx, tlp_high_seq); CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_read_rx, rttvar_us); CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_read_rx, retrans_out); CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_read_rx, advmss); CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_read_rx, urg_data); CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_read_rx, lost); CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_read_rx, rtt_min); CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_read_rx, out_of_order_queue); CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_read_rx, snd_ssthresh); CACHELINE_ASSERT_GROUP_SIZE(struct tcp_sock, tcp_sock_read_rx, 69); /* TX read-write hotpath cache lines */ CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_write_tx, segs_out); CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_write_tx, data_segs_out); CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_write_tx, bytes_sent); CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_write_tx, snd_sml); CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_write_tx, chrono_start); CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_write_tx, chrono_stat); CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_write_tx, write_seq); CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_write_tx, pushed_seq); CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_write_tx, lsndtime); CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_write_tx, mdev_us); CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_write_tx, tcp_wstamp_ns); CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_write_tx, rtt_seq); CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_write_tx, tsorted_sent_queue); CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_write_tx, highest_sack); CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_write_tx, ecn_flags); CACHELINE_ASSERT_GROUP_SIZE(struct tcp_sock, tcp_sock_write_tx, 89); /* TXRX read-write hotpath cache lines */ CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_write_txrx, pred_flags); CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_write_txrx, tcp_clock_cache); CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_write_txrx, tcp_mstamp); CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_write_txrx, rcv_nxt); CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_write_txrx, snd_nxt); CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_write_txrx, snd_una); CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_write_txrx, window_clamp); CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_write_txrx, srtt_us); CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_write_txrx, packets_out); CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_write_txrx, snd_up); CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_write_txrx, delivered); CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_write_txrx, delivered_ce); CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_write_txrx, app_limited); CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_write_txrx, rcv_wnd); CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_write_txrx, rx_opt); /* 32bit arches with 8byte alignment on u64 fields might need padding * before tcp_clock_cache. */ CACHELINE_ASSERT_GROUP_SIZE(struct tcp_sock, tcp_sock_write_txrx, 92 + 4); /* RX read-write hotpath cache lines */ CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_write_rx, bytes_received); CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_write_rx, segs_in); CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_write_rx, data_segs_in); CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_write_rx, rcv_wup); CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_write_rx, max_packets_out); CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_write_rx, cwnd_usage_seq); CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_write_rx, rate_delivered); CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_write_rx, rate_interval_us); CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_write_rx, rcv_rtt_last_tsecr); CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_write_rx, first_tx_mstamp); CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_write_rx, delivered_mstamp); CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_write_rx, bytes_acked); CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_write_rx, rcv_rtt_est); CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_write_rx, rcvq_space); CACHELINE_ASSERT_GROUP_SIZE(struct tcp_sock, tcp_sock_write_rx, 99); } void __init tcp_init(void) { int max_rshare, max_wshare, cnt; unsigned long limit; unsigned int i; BUILD_BUG_ON(TCP_MIN_SND_MSS <= MAX_TCP_OPTION_SPACE); BUILD_BUG_ON(sizeof(struct tcp_skb_cb) > sizeof_field(struct sk_buff, cb)); tcp_struct_check(); percpu_counter_init(&tcp_sockets_allocated, 0, GFP_KERNEL); timer_setup(&tcp_orphan_timer, tcp_orphan_update, TIMER_DEFERRABLE); mod_timer(&tcp_orphan_timer, jiffies + TCP_ORPHAN_TIMER_PERIOD); inet_hashinfo2_init(&tcp_hashinfo, "tcp_listen_portaddr_hash", thash_entries, 21, /* one slot per 2 MB*/ 0, 64 * 1024); tcp_hashinfo.bind_bucket_cachep = kmem_cache_create("tcp_bind_bucket", sizeof(struct inet_bind_bucket), 0, SLAB_HWCACHE_ALIGN | SLAB_PANIC | SLAB_ACCOUNT, NULL); tcp_hashinfo.bind2_bucket_cachep = kmem_cache_create("tcp_bind2_bucket", sizeof(struct inet_bind2_bucket), 0, SLAB_HWCACHE_ALIGN | SLAB_PANIC | SLAB_ACCOUNT, NULL); /* Size and allocate the main established and bind bucket * hash tables. * * The methodology is similar to that of the buffer cache. */ tcp_hashinfo.ehash = alloc_large_system_hash("TCP established", sizeof(struct inet_ehash_bucket), thash_entries, 17, /* one slot per 128 KB of memory */ 0, NULL, &tcp_hashinfo.ehash_mask, 0, thash_entries ? 0 : 512 * 1024); for (i = 0; i <= tcp_hashinfo.ehash_mask; i++) INIT_HLIST_NULLS_HEAD(&tcp_hashinfo.ehash[i].chain, i); if (inet_ehash_locks_alloc(&tcp_hashinfo)) panic("TCP: failed to alloc ehash_locks"); tcp_hashinfo.bhash = alloc_large_system_hash("TCP bind", 2 * sizeof(struct inet_bind_hashbucket), tcp_hashinfo.ehash_mask + 1, 17, /* one slot per 128 KB of memory */ 0, &tcp_hashinfo.bhash_size, NULL, 0, 64 * 1024); tcp_hashinfo.bhash_size = 1U << tcp_hashinfo.bhash_size; tcp_hashinfo.bhash2 = tcp_hashinfo.bhash + tcp_hashinfo.bhash_size; for (i = 0; i < tcp_hashinfo.bhash_size; i++) { spin_lock_init(&tcp_hashinfo.bhash[i].lock); INIT_HLIST_HEAD(&tcp_hashinfo.bhash[i].chain); spin_lock_init(&tcp_hashinfo.bhash2[i].lock); INIT_HLIST_HEAD(&tcp_hashinfo.bhash2[i].chain); } tcp_hashinfo.pernet = false; cnt = tcp_hashinfo.ehash_mask + 1; sysctl_tcp_max_orphans = cnt / 2; tcp_init_mem(); /* Set per-socket limits to no more than 1/128 the pressure threshold */ limit = nr_free_buffer_pages() << (PAGE_SHIFT - 7); max_wshare = min(4UL*1024*1024, limit); max_rshare = min(6UL*1024*1024, limit); init_net.ipv4.sysctl_tcp_wmem[0] = PAGE_SIZE; init_net.ipv4.sysctl_tcp_wmem[1] = 16*1024; init_net.ipv4.sysctl_tcp_wmem[2] = max(64*1024, max_wshare); init_net.ipv4.sysctl_tcp_rmem[0] = PAGE_SIZE; init_net.ipv4.sysctl_tcp_rmem[1] = 131072; init_net.ipv4.sysctl_tcp_rmem[2] = max(131072, max_rshare); pr_info("Hash tables configured (established %u bind %u)\n", tcp_hashinfo.ehash_mask + 1, tcp_hashinfo.bhash_size); tcp_v4_init(); tcp_metrics_init(); BUG_ON(tcp_register_congestion_control(&tcp_reno) != 0); tcp_tasklet_init(); mptcp_init(); } |
| 149 194 408 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 | /* 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); } static inline bool timespec64_is_epoch(const struct timespec64 *ts) { return ts->tv_sec == 0 && ts->tv_nsec == 0; } /* * 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 */ |
| 22 120 360 341 343 342 341 1 343 339 158 196 343 100 3 99 100 100 15 15 15 15 15 15 2 100 100 100 100 100 98 2 100 100 2 98 100 100 23 23 1 22 15 234 236 236 236 236 235 8 8 8 8 8 8 55 54 55 48 7 55 54 678 681 10 679 681 528 160 682 | 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 | // SPDX-License-Identifier: GPL-2.0-only /* * fs/kernfs/file.c - kernfs file implementation * * Copyright (c) 2001-3 Patrick Mochel * Copyright (c) 2007 SUSE Linux Products GmbH * Copyright (c) 2007, 2013 Tejun Heo <tj@kernel.org> */ #include <linux/fs.h> #include <linux/seq_file.h> #include <linux/slab.h> #include <linux/poll.h> #include <linux/pagemap.h> #include <linux/sched/mm.h> #include <linux/fsnotify.h> #include <linux/uio.h> #include "kernfs-internal.h" struct kernfs_open_node { struct rcu_head rcu_head; atomic_t event; wait_queue_head_t poll; struct list_head files; /* goes through kernfs_open_file.list */ unsigned int nr_mmapped; unsigned int nr_to_release; }; /* * kernfs_notify() may be called from any context and bounces notifications * through a work item. To minimize space overhead in kernfs_node, the * pending queue is implemented as a singly linked list of kernfs_nodes. * The list is terminated with the self pointer so that whether a * kernfs_node is on the list or not can be determined by testing the next * pointer for %NULL. */ #define KERNFS_NOTIFY_EOL ((void *)&kernfs_notify_list) static DEFINE_SPINLOCK(kernfs_notify_lock); static struct kernfs_node *kernfs_notify_list = KERNFS_NOTIFY_EOL; static inline struct mutex *kernfs_open_file_mutex_ptr(struct kernfs_node *kn) { int idx = hash_ptr(kn, NR_KERNFS_LOCK_BITS); return &kernfs_locks->open_file_mutex[idx]; } static inline struct mutex *kernfs_open_file_mutex_lock(struct kernfs_node *kn) { struct mutex *lock; lock = kernfs_open_file_mutex_ptr(kn); mutex_lock(lock); return lock; } /** * of_on - Get the kernfs_open_node of the specified kernfs_open_file * @of: target kernfs_open_file * * Return: the kernfs_open_node of the kernfs_open_file */ static struct kernfs_open_node *of_on(struct kernfs_open_file *of) { return rcu_dereference_protected(of->kn->attr.open, !list_empty(&of->list)); } /** * kernfs_deref_open_node_locked - Get kernfs_open_node corresponding to @kn * * @kn: target kernfs_node. * * Fetch and return ->attr.open of @kn when caller holds the * kernfs_open_file_mutex_ptr(kn). * * Update of ->attr.open happens under kernfs_open_file_mutex_ptr(kn). So when * the caller guarantees that this mutex is being held, other updaters can't * change ->attr.open and this means that we can safely deref ->attr.open * outside RCU read-side critical section. * * The caller needs to make sure that kernfs_open_file_mutex is held. * * Return: @kn->attr.open when kernfs_open_file_mutex is held. */ static struct kernfs_open_node * kernfs_deref_open_node_locked(struct kernfs_node *kn) { return rcu_dereference_protected(kn->attr.open, lockdep_is_held(kernfs_open_file_mutex_ptr(kn))); } static struct kernfs_open_file *kernfs_of(struct file *file) { return ((struct seq_file *)file->private_data)->private; } /* * Determine the kernfs_ops for the given kernfs_node. This function must * be called while holding an active reference. */ static const struct kernfs_ops *kernfs_ops(struct kernfs_node *kn) { if (kn->flags & KERNFS_LOCKDEP) lockdep_assert_held(kn); return kn->attr.ops; } /* * As kernfs_seq_stop() is also called after kernfs_seq_start() or * kernfs_seq_next() failure, it needs to distinguish whether it's stopping * a seq_file iteration which is fully initialized with an active reference * or an aborted kernfs_seq_start() due to get_active failure. The * position pointer is the only context for each seq_file iteration and * thus the stop condition should be encoded in it. As the return value is * directly visible to userland, ERR_PTR(-ENODEV) is the only acceptable * choice to indicate get_active failure. * * Unfortunately, this is complicated due to the optional custom seq_file * operations which may return ERR_PTR(-ENODEV) too. kernfs_seq_stop() * can't distinguish whether ERR_PTR(-ENODEV) is from get_active failure or * custom seq_file operations and thus can't decide whether put_active * should be performed or not only on ERR_PTR(-ENODEV). * * This is worked around by factoring out the custom seq_stop() and * put_active part into kernfs_seq_stop_active(), skipping it from * kernfs_seq_stop() if ERR_PTR(-ENODEV) while invoking it directly after * custom seq_file operations fail with ERR_PTR(-ENODEV) - this ensures * that kernfs_seq_stop_active() is skipped only after get_active failure. */ static void kernfs_seq_stop_active(struct seq_file *sf, void *v) { struct kernfs_open_file *of = sf->private; const struct kernfs_ops *ops = kernfs_ops(of->kn); if (ops->seq_stop) ops->seq_stop(sf, v); kernfs_put_active(of->kn); } static void *kernfs_seq_start(struct seq_file *sf, loff_t *ppos) { struct kernfs_open_file *of = sf->private; const struct kernfs_ops *ops; /* * @of->mutex nests outside active ref and is primarily to ensure that * the ops aren't called concurrently for the same open file. */ mutex_lock(&of->mutex); if (!kernfs_get_active(of->kn)) return ERR_PTR(-ENODEV); ops = kernfs_ops(of->kn); if (ops->seq_start) { void *next = ops->seq_start(sf, ppos); /* see the comment above kernfs_seq_stop_active() */ if (next == ERR_PTR(-ENODEV)) kernfs_seq_stop_active(sf, next); return next; } return single_start(sf, ppos); } static void *kernfs_seq_next(struct seq_file *sf, void *v, loff_t *ppos) { struct kernfs_open_file *of = sf->private; const struct kernfs_ops *ops = kernfs_ops(of->kn); if (ops->seq_next) { void *next = ops->seq_next(sf, v, ppos); /* see the comment above kernfs_seq_stop_active() */ if (next == ERR_PTR(-ENODEV)) kernfs_seq_stop_active(sf, next); return next; } else { /* * The same behavior and code as single_open(), always * terminate after the initial read. */ ++*ppos; return NULL; } } static void kernfs_seq_stop(struct seq_file *sf, void *v) { struct kernfs_open_file *of = sf->private; if (v != ERR_PTR(-ENODEV)) kernfs_seq_stop_active(sf, v); mutex_unlock(&of->mutex); } static int kernfs_seq_show(struct seq_file *sf, void *v) { struct kernfs_open_file *of = sf->private; of->event = atomic_read(&of_on(of)->event); return of->kn->attr.ops->seq_show(sf, v); } static const struct seq_operations kernfs_seq_ops = { .start = kernfs_seq_start, .next = kernfs_seq_next, .stop = kernfs_seq_stop, .show = kernfs_seq_show, }; /* * As reading a bin file can have side-effects, the exact offset and bytes * specified in read(2) call should be passed to the read callback making * it difficult to use seq_file. Implement simplistic custom buffering for * bin files. */ static ssize_t kernfs_file_read_iter(struct kiocb *iocb, struct iov_iter *iter) { struct kernfs_open_file *of = kernfs_of(iocb->ki_filp); ssize_t len = min_t(size_t, iov_iter_count(iter), PAGE_SIZE); const struct kernfs_ops *ops; char *buf; buf = of->prealloc_buf; if (buf) mutex_lock(&of->prealloc_mutex); else buf = kmalloc(len, GFP_KERNEL); if (!buf) return -ENOMEM; /* * @of->mutex nests outside active ref and is used both to ensure that * the ops aren't called concurrently for the same open file. */ mutex_lock(&of->mutex); if (!kernfs_get_active(of->kn)) { len = -ENODEV; mutex_unlock(&of->mutex); goto out_free; } of->event = atomic_read(&of_on(of)->event); ops = kernfs_ops(of->kn); if (ops->read) len = ops->read(of, buf, len, iocb->ki_pos); else len = -EINVAL; kernfs_put_active(of->kn); mutex_unlock(&of->mutex); if (len < 0) goto out_free; if (copy_to_iter(buf, len, iter) != len) { len = -EFAULT; goto out_free; } iocb->ki_pos += len; out_free: if (buf == of->prealloc_buf) mutex_unlock(&of->prealloc_mutex); else kfree(buf); return len; } static ssize_t kernfs_fop_read_iter(struct kiocb *iocb, struct iov_iter *iter) { if (kernfs_of(iocb->ki_filp)->kn->flags & KERNFS_HAS_SEQ_SHOW) return seq_read_iter(iocb, iter); return kernfs_file_read_iter(iocb, iter); } /* * Copy data in from userland and pass it to the matching kernfs write * operation. * * There is no easy way for us to know if userspace is only doing a partial * write, so we don't support them. We expect the entire buffer to come on * the first write. Hint: if you're writing a value, first read the file, * modify only the value you're changing, then write entire buffer * back. */ static ssize_t kernfs_fop_write_iter(struct kiocb *iocb, struct iov_iter *iter) { struct kernfs_open_file *of = kernfs_of(iocb->ki_filp); ssize_t len = iov_iter_count(iter); const struct kernfs_ops *ops; char *buf; if (of->atomic_write_len) { if (len > of->atomic_write_len) return -E2BIG; } else { len = min_t(size_t, len, PAGE_SIZE); } buf = of->prealloc_buf; if (buf) mutex_lock(&of->prealloc_mutex); else buf = kmalloc(len + 1, GFP_KERNEL); if (!buf) return -ENOMEM; if (copy_from_iter(buf, len, iter) != len) { len = -EFAULT; goto out_free; } buf[len] = '\0'; /* guarantee string termination */ /* * @of->mutex nests outside active ref and is used both to ensure that * the ops aren't called concurrently for the same open file. */ mutex_lock(&of->mutex); if (!kernfs_get_active(of->kn)) { mutex_unlock(&of->mutex); len = -ENODEV; goto out_free; } ops = kernfs_ops(of->kn); if (ops->write) len = ops->write(of, buf, len, iocb->ki_pos); else len = -EINVAL; kernfs_put_active(of->kn); mutex_unlock(&of->mutex); if (len > 0) iocb->ki_pos += len; out_free: if (buf == of->prealloc_buf) mutex_unlock(&of->prealloc_mutex); else kfree(buf); return len; } static void kernfs_vma_open(struct vm_area_struct *vma) { struct file *file = vma->vm_file; struct kernfs_open_file *of = kernfs_of(file); if (!of->vm_ops) return; if (!kernfs_get_active(of->kn)) return; if (of->vm_ops->open) of->vm_ops->open(vma); kernfs_put_active(of->kn); } static vm_fault_t kernfs_vma_fault(struct vm_fault *vmf) { struct file *file = vmf->vma->vm_file; struct kernfs_open_file *of = kernfs_of(file); vm_fault_t ret; if (!of->vm_ops) return VM_FAULT_SIGBUS; if (!kernfs_get_active(of->kn)) return VM_FAULT_SIGBUS; ret = VM_FAULT_SIGBUS; if (of->vm_ops->fault) ret = of->vm_ops->fault(vmf); kernfs_put_active(of->kn); return ret; } static vm_fault_t kernfs_vma_page_mkwrite(struct vm_fault *vmf) { struct file *file = vmf->vma->vm_file; struct kernfs_open_file *of = kernfs_of(file); vm_fault_t ret; if (!of->vm_ops) return VM_FAULT_SIGBUS; if (!kernfs_get_active(of->kn)) return VM_FAULT_SIGBUS; ret = 0; if (of->vm_ops->page_mkwrite) ret = of->vm_ops->page_mkwrite(vmf); else file_update_time(file); kernfs_put_active(of->kn); return ret; } static int kernfs_vma_access(struct vm_area_struct *vma, unsigned long addr, void *buf, int len, int write) { struct file *file = vma->vm_file; struct kernfs_open_file *of = kernfs_of(file); int ret; if (!of->vm_ops) return -EINVAL; if (!kernfs_get_active(of->kn)) return -EINVAL; ret = -EINVAL; if (of->vm_ops->access) ret = of->vm_ops->access(vma, addr, buf, len, write); kernfs_put_active(of->kn); return ret; } static const struct vm_operations_struct kernfs_vm_ops = { .open = kernfs_vma_open, .fault = kernfs_vma_fault, .page_mkwrite = kernfs_vma_page_mkwrite, .access = kernfs_vma_access, }; static int kernfs_fop_mmap(struct file *file, struct vm_area_struct *vma) { struct kernfs_open_file *of = kernfs_of(file); const struct kernfs_ops *ops; int rc; /* * mmap path and of->mutex are prone to triggering spurious lockdep * warnings and we don't want to add spurious locking dependency * between the two. Check whether mmap is actually implemented * without grabbing @of->mutex by testing HAS_MMAP flag. See the * comment in kernfs_fop_open() for more details. */ if (!(of->kn->flags & KERNFS_HAS_MMAP)) return -ENODEV; mutex_lock(&of->mutex); rc = -ENODEV; if (!kernfs_get_active(of->kn)) goto out_unlock; ops = kernfs_ops(of->kn); rc = ops->mmap(of, vma); if (rc) goto out_put; /* * PowerPC's pci_mmap of legacy_mem uses shmem_zero_setup() * to satisfy versions of X which crash if the mmap fails: that * substitutes a new vm_file, and we don't then want bin_vm_ops. */ if (vma->vm_file != file) goto out_put; rc = -EINVAL; if (of->mmapped && of->vm_ops != vma->vm_ops) goto out_put; /* * It is not possible to successfully wrap close. * So error if someone is trying to use close. */ if (vma->vm_ops && vma->vm_ops->close) goto out_put; rc = 0; if (!of->mmapped) { of->mmapped = true; of_on(of)->nr_mmapped++; of->vm_ops = vma->vm_ops; } vma->vm_ops = &kernfs_vm_ops; out_put: kernfs_put_active(of->kn); out_unlock: mutex_unlock(&of->mutex); return rc; } /** * kernfs_get_open_node - get or create kernfs_open_node * @kn: target kernfs_node * @of: kernfs_open_file for this instance of open * * If @kn->attr.open exists, increment its reference count; otherwise, * create one. @of is chained to the files list. * * Locking: * Kernel thread context (may sleep). * * Return: * %0 on success, -errno on failure. */ static int kernfs_get_open_node(struct kernfs_node *kn, struct kernfs_open_file *of) { struct kernfs_open_node *on; struct mutex *mutex; mutex = kernfs_open_file_mutex_lock(kn); on = kernfs_deref_open_node_locked(kn); if (!on) { /* not there, initialize a new one */ on = kzalloc(sizeof(*on), GFP_KERNEL); if (!on) { mutex_unlock(mutex); return -ENOMEM; } atomic_set(&on->event, 1); init_waitqueue_head(&on->poll); INIT_LIST_HEAD(&on->files); rcu_assign_pointer(kn->attr.open, on); } list_add_tail(&of->list, &on->files); if (kn->flags & KERNFS_HAS_RELEASE) on->nr_to_release++; mutex_unlock(mutex); return 0; } /** * kernfs_unlink_open_file - Unlink @of from @kn. * * @kn: target kernfs_node * @of: associated kernfs_open_file * @open_failed: ->open() failed, cancel ->release() * * Unlink @of from list of @kn's associated open files. If list of * associated open files becomes empty, disassociate and free * kernfs_open_node. * * LOCKING: * None. */ static void kernfs_unlink_open_file(struct kernfs_node *kn, struct kernfs_open_file *of, bool open_failed) { struct kernfs_open_node *on; struct mutex *mutex; mutex = kernfs_open_file_mutex_lock(kn); on = kernfs_deref_open_node_locked(kn); if (!on) { mutex_unlock(mutex); return; } if (of) { if (kn->flags & KERNFS_HAS_RELEASE) { WARN_ON_ONCE(of->released == open_failed); if (open_failed) on->nr_to_release--; } if (of->mmapped) on->nr_mmapped--; list_del(&of->list); } if (list_empty(&on->files)) { rcu_assign_pointer(kn->attr.open, NULL); kfree_rcu(on, rcu_head); } mutex_unlock(mutex); } static int kernfs_fop_open(struct inode *inode, struct file *file) { struct kernfs_node *kn = inode->i_private; struct kernfs_root *root = kernfs_root(kn); const struct kernfs_ops *ops; struct kernfs_open_file *of; bool has_read, has_write, has_mmap; int error = -EACCES; if (!kernfs_get_active(kn)) return -ENODEV; ops = kernfs_ops(kn); has_read = ops->seq_show || ops->read || ops->mmap; has_write = ops->write || ops->mmap; has_mmap = ops->mmap; /* see the flag definition for details */ if (root->flags & KERNFS_ROOT_EXTRA_OPEN_PERM_CHECK) { if ((file->f_mode & FMODE_WRITE) && (!(inode->i_mode & S_IWUGO) || !has_write)) goto err_out; if ((file->f_mode & FMODE_READ) && (!(inode->i_mode & S_IRUGO) || !has_read)) goto err_out; } /* allocate a kernfs_open_file for the file */ error = -ENOMEM; of = kzalloc(sizeof(struct kernfs_open_file), GFP_KERNEL); if (!of) goto err_out; /* * The following is done to give a different lockdep key to * @of->mutex for files which implement mmap. This is a rather * crude way to avoid false positive lockdep warning around * mm->mmap_lock - mmap nests @of->mutex under mm->mmap_lock and * reading /sys/block/sda/trace/act_mask grabs sr_mutex, under * which mm->mmap_lock nests, while holding @of->mutex. As each * open file has a separate mutex, it's okay as long as those don't * happen on the same file. At this point, we can't easily give * each file a separate locking class. Let's differentiate on * whether the file has mmap or not for now. * * For similar reasons, writable and readonly files are given different * lockdep key, because the writable file /sys/power/resume may call vfs * lookup helpers for arbitrary paths and readonly files can be read by * overlayfs from vfs helpers when sysfs is a lower layer of overalyfs. * * All three cases look the same. They're supposed to * look that way and give @of->mutex different static lockdep keys. */ if (has_mmap) mutex_init(&of->mutex); else if (file->f_mode & FMODE_WRITE) mutex_init(&of->mutex); else mutex_init(&of->mutex); of->kn = kn; of->file = file; /* * Write path needs to atomic_write_len outside active reference. * Cache it in open_file. See kernfs_fop_write_iter() for details. */ of->atomic_write_len = ops->atomic_write_len; error = -EINVAL; /* * ->seq_show is incompatible with ->prealloc, * as seq_read does its own allocation. * ->read must be used instead. */ if (ops->prealloc && ops->seq_show) goto err_free; if (ops->prealloc) { int len = of->atomic_write_len ?: PAGE_SIZE; of->prealloc_buf = kmalloc(len + 1, GFP_KERNEL); error = -ENOMEM; if (!of->prealloc_buf) goto err_free; mutex_init(&of->prealloc_mutex); } /* * Always instantiate seq_file even if read access doesn't use * seq_file or is not requested. This unifies private data access * and readable regular files are the vast majority anyway. */ if (ops->seq_show) error = seq_open(file, &kernfs_seq_ops); else error = seq_open(file, NULL); if (error) goto err_free; of->seq_file = file->private_data; of->seq_file->private = of; /* seq_file clears PWRITE unconditionally, restore it if WRITE */ if (file->f_mode & FMODE_WRITE) file->f_mode |= FMODE_PWRITE; /* make sure we have open node struct */ error = kernfs_get_open_node(kn, of); if (error) goto err_seq_release; if (ops->open) { /* nobody has access to @of yet, skip @of->mutex */ error = ops->open(of); if (error) goto err_put_node; } /* open succeeded, put active references */ kernfs_put_active(kn); return 0; err_put_node: kernfs_unlink_open_file(kn, of, true); err_seq_release: seq_release(inode, file); err_free: kfree(of->prealloc_buf); kfree(of); err_out: kernfs_put_active(kn); return error; } /* used from release/drain to ensure that ->release() is called exactly once */ static void kernfs_release_file(struct kernfs_node *kn, struct kernfs_open_file *of) { /* * @of is guaranteed to have no other file operations in flight and * we just want to synchronize release and drain paths. * @kernfs_open_file_mutex_ptr(kn) is enough. @of->mutex can't be used * here because drain path may be called from places which can * cause circular dependency. */ lockdep_assert_held(kernfs_open_file_mutex_ptr(kn)); if (!of->released) { /* * A file is never detached without being released and we * need to be able to release files which are deactivated * and being drained. Don't use kernfs_ops(). */ kn->attr.ops->release(of); of->released = true; of_on(of)->nr_to_release--; } } static int kernfs_fop_release(struct inode *inode, struct file *filp) { struct kernfs_node *kn = inode->i_private; struct kernfs_open_file *of = kernfs_of(filp); if (kn->flags & KERNFS_HAS_RELEASE) { struct mutex *mutex; mutex = kernfs_open_file_mutex_lock(kn); kernfs_release_file(kn, of); mutex_unlock(mutex); } kernfs_unlink_open_file(kn, of, false); seq_release(inode, filp); kfree(of->prealloc_buf); kfree(of); return 0; } bool kernfs_should_drain_open_files(struct kernfs_node *kn) { struct kernfs_open_node *on; bool ret; /* * @kn being deactivated guarantees that @kn->attr.open can't change * beneath us making the lockless test below safe. */ WARN_ON_ONCE(atomic_read(&kn->active) != KN_DEACTIVATED_BIAS); rcu_read_lock(); on = rcu_dereference(kn->attr.open); ret = on && (on->nr_mmapped || on->nr_to_release); rcu_read_unlock(); return ret; } void kernfs_drain_open_files(struct kernfs_node *kn) { struct kernfs_open_node *on; struct kernfs_open_file *of; struct mutex *mutex; mutex = kernfs_open_file_mutex_lock(kn); on = kernfs_deref_open_node_locked(kn); if (!on) { mutex_unlock(mutex); return; } list_for_each_entry(of, &on->files, list) { struct inode *inode = file_inode(of->file); if (of->mmapped) { unmap_mapping_range(inode->i_mapping, 0, 0, 1); of->mmapped = false; on->nr_mmapped--; } if (kn->flags & KERNFS_HAS_RELEASE) kernfs_release_file(kn, of); } WARN_ON_ONCE(on->nr_mmapped || on->nr_to_release); mutex_unlock(mutex); } /* * Kernfs attribute files are pollable. The idea is that you read * the content and then you use 'poll' or 'select' to wait for * the content to change. When the content changes (assuming the * manager for the kobject supports notification), poll will * return EPOLLERR|EPOLLPRI, and select will return the fd whether * it is waiting for read, write, or exceptions. * Once poll/select indicates that the value has changed, you * need to close and re-open the file, or seek to 0 and read again. * Reminder: this only works for attributes which actively support * it, and it is not possible to test an attribute from userspace * to see if it supports poll (Neither 'poll' nor 'select' return * an appropriate error code). When in doubt, set a suitable timeout value. */ __poll_t kernfs_generic_poll(struct kernfs_open_file *of, poll_table *wait) { struct kernfs_open_node *on = of_on(of); poll_wait(of->file, &on->poll, wait); if (of->event != atomic_read(&on->event)) return DEFAULT_POLLMASK|EPOLLERR|EPOLLPRI; return DEFAULT_POLLMASK; } static __poll_t kernfs_fop_poll(struct file *filp, poll_table *wait) { struct kernfs_open_file *of = kernfs_of(filp); struct kernfs_node *kn = kernfs_dentry_node(filp->f_path.dentry); __poll_t ret; if (!kernfs_get_active(kn)) return DEFAULT_POLLMASK|EPOLLERR|EPOLLPRI; if (kn->attr.ops->poll) ret = kn->attr.ops->poll(of, wait); else ret = kernfs_generic_poll(of, wait); kernfs_put_active(kn); return ret; } static loff_t kernfs_fop_llseek(struct file *file, loff_t offset, int whence) { struct kernfs_open_file *of = kernfs_of(file); const struct kernfs_ops *ops; loff_t ret; /* * @of->mutex nests outside active ref and is primarily to ensure that * the ops aren't called concurrently for the same open file. */ mutex_lock(&of->mutex); if (!kernfs_get_active(of->kn)) { mutex_unlock(&of->mutex); return -ENODEV; } ops = kernfs_ops(of->kn); if (ops->llseek) ret = ops->llseek(of, offset, whence); else ret = generic_file_llseek(file, offset, whence); kernfs_put_active(of->kn); mutex_unlock(&of->mutex); return ret; } static void kernfs_notify_workfn(struct work_struct *work) { struct kernfs_node *kn; struct kernfs_super_info *info; struct kernfs_root *root; repeat: /* pop one off the notify_list */ spin_lock_irq(&kernfs_notify_lock); kn = kernfs_notify_list; if (kn == KERNFS_NOTIFY_EOL) { spin_unlock_irq(&kernfs_notify_lock); return; } kernfs_notify_list = kn->attr.notify_next; kn->attr.notify_next = NULL; spin_unlock_irq(&kernfs_notify_lock); root = kernfs_root(kn); /* kick fsnotify */ down_read(&root->kernfs_supers_rwsem); list_for_each_entry(info, &kernfs_root(kn)->supers, node) { struct kernfs_node *parent; struct inode *p_inode = NULL; struct inode *inode; struct qstr name; /* * We want fsnotify_modify() on @kn but as the * modifications aren't originating from userland don't * have the matching @file available. Look up the inodes * and generate the events manually. */ inode = ilookup(info->sb, kernfs_ino(kn)); if (!inode) continue; name = QSTR(kn->name); parent = kernfs_get_parent(kn); if (parent) { p_inode = ilookup(info->sb, kernfs_ino(parent)); if (p_inode) { fsnotify(FS_MODIFY | FS_EVENT_ON_CHILD, inode, FSNOTIFY_EVENT_INODE, p_inode, &name, inode, 0); iput(p_inode); } kernfs_put(parent); } if (!p_inode) fsnotify_inode(inode, FS_MODIFY); iput(inode); } up_read(&root->kernfs_supers_rwsem); kernfs_put(kn); goto repeat; } /** * kernfs_notify - notify a kernfs file * @kn: file to notify * * Notify @kn such that poll(2) on @kn wakes up. Maybe be called from any * context. */ void kernfs_notify(struct kernfs_node *kn) { static DECLARE_WORK(kernfs_notify_work, kernfs_notify_workfn); unsigned long flags; struct kernfs_open_node *on; if (WARN_ON(kernfs_type(kn) != KERNFS_FILE)) return; /* kick poll immediately */ rcu_read_lock(); on = rcu_dereference(kn->attr.open); if (on) { atomic_inc(&on->event); wake_up_interruptible(&on->poll); } rcu_read_unlock(); /* schedule work to kick fsnotify */ spin_lock_irqsave(&kernfs_notify_lock, flags); if (!kn->attr.notify_next) { kernfs_get(kn); kn->attr.notify_next = kernfs_notify_list; kernfs_notify_list = kn; schedule_work(&kernfs_notify_work); } spin_unlock_irqrestore(&kernfs_notify_lock, flags); } EXPORT_SYMBOL_GPL(kernfs_notify); const struct file_operations kernfs_file_fops = { .read_iter = kernfs_fop_read_iter, .write_iter = kernfs_fop_write_iter, .llseek = kernfs_fop_llseek, .mmap = kernfs_fop_mmap, .open = kernfs_fop_open, .release = kernfs_fop_release, .poll = kernfs_fop_poll, .fsync = noop_fsync, .splice_read = copy_splice_read, .splice_write = iter_file_splice_write, }; /** * __kernfs_create_file - kernfs internal function to create a file * @parent: directory to create the file in * @name: name of the file * @mode: mode of the file * @uid: uid of the file * @gid: gid of the file * @size: size of the file * @ops: kernfs operations for the file * @priv: private data for the file * @ns: optional namespace tag of the file * @key: lockdep key for the file's active_ref, %NULL to disable lockdep * * Return: the created node on success, ERR_PTR() value on error. */ struct kernfs_node *__kernfs_create_file(struct kernfs_node *parent, const char *name, umode_t mode, kuid_t uid, kgid_t gid, loff_t size, const struct kernfs_ops *ops, void *priv, const void *ns, struct lock_class_key *key) { struct kernfs_node *kn; unsigned flags; int rc; flags = KERNFS_FILE; kn = kernfs_new_node(parent, name, (mode & S_IALLUGO) | S_IFREG, uid, gid, flags); if (!kn) return ERR_PTR(-ENOMEM); kn->attr.ops = ops; kn->attr.size = size; kn->ns = ns; kn->priv = priv; #ifdef CONFIG_DEBUG_LOCK_ALLOC if (key) { lockdep_init_map(&kn->dep_map, "kn->active", key, 0); kn->flags |= KERNFS_LOCKDEP; } #endif /* * kn->attr.ops is accessible only while holding active ref. We * need to know whether some ops are implemented outside active * ref. Cache their existence in flags. */ if (ops->seq_show) kn->flags |= KERNFS_HAS_SEQ_SHOW; if (ops->mmap) kn->flags |= KERNFS_HAS_MMAP; if (ops->release) kn->flags |= KERNFS_HAS_RELEASE; rc = kernfs_add_one(kn); if (rc) { kernfs_put(kn); return ERR_PTR(rc); } return kn; } |
| 77 24 53 54 22 33 34 5 29 1 1 27 24 25 5 2 4 2 8 4 3 9 5 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 | // SPDX-License-Identifier: GPL-2.0 /* Copyright (c) 2021 Facebook */ #include <linux/bitmap.h> #include <linux/bpf.h> #include <linux/btf.h> #include <linux/err.h> #include <linux/jhash.h> #include <linux/random.h> #include <linux/btf_ids.h> #define BLOOM_CREATE_FLAG_MASK \ (BPF_F_NUMA_NODE | BPF_F_ZERO_SEED | BPF_F_ACCESS_MASK) struct bpf_bloom_filter { struct bpf_map map; u32 bitset_mask; u32 hash_seed; u32 nr_hash_funcs; unsigned long bitset[]; }; static u32 hash(struct bpf_bloom_filter *bloom, void *value, u32 value_size, u32 index) { u32 h; if (likely(value_size % 4 == 0)) h = jhash2(value, value_size / 4, bloom->hash_seed + index); else h = jhash(value, value_size, bloom->hash_seed + index); return h & bloom->bitset_mask; } static long bloom_map_peek_elem(struct bpf_map *map, void *value) { struct bpf_bloom_filter *bloom = container_of(map, struct bpf_bloom_filter, map); u32 i, h; for (i = 0; i < bloom->nr_hash_funcs; i++) { h = hash(bloom, value, map->value_size, i); if (!test_bit(h, bloom->bitset)) return -ENOENT; } return 0; } static long bloom_map_push_elem(struct bpf_map *map, void *value, u64 flags) { struct bpf_bloom_filter *bloom = container_of(map, struct bpf_bloom_filter, map); u32 i, h; if (flags != BPF_ANY) return -EINVAL; for (i = 0; i < bloom->nr_hash_funcs; i++) { h = hash(bloom, value, map->value_size, i); set_bit(h, bloom->bitset); } return 0; } static long bloom_map_pop_elem(struct bpf_map *map, void *value) { return -EOPNOTSUPP; } static long bloom_map_delete_elem(struct bpf_map *map, void *value) { return -EOPNOTSUPP; } static int bloom_map_get_next_key(struct bpf_map *map, void *key, void *next_key) { return -EOPNOTSUPP; } /* Called from syscall */ static int bloom_map_alloc_check(union bpf_attr *attr) { if (attr->value_size > KMALLOC_MAX_SIZE) /* if value_size is bigger, the user space won't be able to * access the elements. */ return -E2BIG; return 0; } static struct bpf_map *bloom_map_alloc(union bpf_attr *attr) { u32 bitset_bytes, bitset_mask, nr_hash_funcs, nr_bits; int numa_node = bpf_map_attr_numa_node(attr); struct bpf_bloom_filter *bloom; if (attr->key_size != 0 || attr->value_size == 0 || attr->max_entries == 0 || attr->map_flags & ~BLOOM_CREATE_FLAG_MASK || !bpf_map_flags_access_ok(attr->map_flags) || /* The lower 4 bits of map_extra (0xF) specify the number * of hash functions */ (attr->map_extra & ~0xF)) return ERR_PTR(-EINVAL); nr_hash_funcs = attr->map_extra; if (nr_hash_funcs == 0) /* Default to using 5 hash functions if unspecified */ nr_hash_funcs = 5; /* For the bloom filter, the optimal bit array size that minimizes the * false positive probability is n * k / ln(2) where n is the number of * expected entries in the bloom filter and k is the number of hash * functions. We use 7 / 5 to approximate 1 / ln(2). * * We round this up to the nearest power of two to enable more efficient * hashing using bitmasks. The bitmask will be the bit array size - 1. * * If this overflows a u32, the bit array size will have 2^32 (4 * GB) bits. */ if (check_mul_overflow(attr->max_entries, nr_hash_funcs, &nr_bits) || check_mul_overflow(nr_bits / 5, (u32)7, &nr_bits) || nr_bits > (1UL << 31)) { /* The bit array size is 2^32 bits but to avoid overflowing the * u32, we use U32_MAX, which will round up to the equivalent * number of bytes */ bitset_bytes = BITS_TO_BYTES(U32_MAX); bitset_mask = U32_MAX; } else { if (nr_bits <= BITS_PER_LONG) nr_bits = BITS_PER_LONG; else nr_bits = roundup_pow_of_two(nr_bits); bitset_bytes = BITS_TO_BYTES(nr_bits); bitset_mask = nr_bits - 1; } bitset_bytes = roundup(bitset_bytes, sizeof(unsigned long)); bloom = bpf_map_area_alloc(sizeof(*bloom) + bitset_bytes, numa_node); if (!bloom) return ERR_PTR(-ENOMEM); bpf_map_init_from_attr(&bloom->map, attr); bloom->nr_hash_funcs = nr_hash_funcs; bloom->bitset_mask = bitset_mask; if (!(attr->map_flags & BPF_F_ZERO_SEED)) bloom->hash_seed = get_random_u32(); return &bloom->map; } static void bloom_map_free(struct bpf_map *map) { struct bpf_bloom_filter *bloom = container_of(map, struct bpf_bloom_filter, map); bpf_map_area_free(bloom); } static void *bloom_map_lookup_elem(struct bpf_map *map, void *key) { /* The eBPF program should use map_peek_elem instead */ return ERR_PTR(-EINVAL); } static long bloom_map_update_elem(struct bpf_map *map, void *key, void *value, u64 flags) { /* The eBPF program should use map_push_elem instead */ return -EINVAL; } static int bloom_map_check_btf(const struct bpf_map *map, const struct btf *btf, const struct btf_type *key_type, const struct btf_type *value_type) { /* Bloom filter maps are keyless */ return btf_type_is_void(key_type) ? 0 : -EINVAL; } static u64 bloom_map_mem_usage(const struct bpf_map *map) { struct bpf_bloom_filter *bloom; u64 bitset_bytes; bloom = container_of(map, struct bpf_bloom_filter, map); bitset_bytes = BITS_TO_BYTES((u64)bloom->bitset_mask + 1); bitset_bytes = roundup(bitset_bytes, sizeof(unsigned long)); return sizeof(*bloom) + bitset_bytes; } BTF_ID_LIST_SINGLE(bpf_bloom_map_btf_ids, struct, bpf_bloom_filter) const struct bpf_map_ops bloom_filter_map_ops = { .map_meta_equal = bpf_map_meta_equal, .map_alloc_check = bloom_map_alloc_check, .map_alloc = bloom_map_alloc, .map_free = bloom_map_free, .map_get_next_key = bloom_map_get_next_key, .map_push_elem = bloom_map_push_elem, .map_peek_elem = bloom_map_peek_elem, .map_pop_elem = bloom_map_pop_elem, .map_lookup_elem = bloom_map_lookup_elem, .map_update_elem = bloom_map_update_elem, .map_delete_elem = bloom_map_delete_elem, .map_check_btf = bloom_map_check_btf, .map_mem_usage = bloom_map_mem_usage, .map_btf_id = &bpf_bloom_map_btf_ids[0], }; |
| 53 52 53 53 1 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 | // SPDX-License-Identifier: GPL-2.0 #include <linux/slab.h> #include <linux/spinlock.h> #include <linux/once.h> #include <linux/random.h> #include <linux/module.h> struct once_work { struct work_struct work; struct static_key_true *key; struct module *module; }; static void once_deferred(struct work_struct *w) { struct once_work *work; work = container_of(w, struct once_work, work); BUG_ON(!static_key_enabled(work->key)); static_branch_disable(work->key); module_put(work->module); kfree(work); } static void once_disable_jump(struct static_key_true *key, struct module *mod) { struct once_work *w; w = kmalloc(sizeof(*w), GFP_ATOMIC); if (!w) return; INIT_WORK(&w->work, once_deferred); w->key = key; w->module = mod; __module_get(mod); schedule_work(&w->work); } static DEFINE_SPINLOCK(once_lock); bool __do_once_start(bool *done, unsigned long *flags) __acquires(once_lock) { spin_lock_irqsave(&once_lock, *flags); if (*done) { spin_unlock_irqrestore(&once_lock, *flags); /* Keep sparse happy by restoring an even lock count on * this lock. In case we return here, we don't call into * __do_once_done but return early in the DO_ONCE() macro. */ __acquire(once_lock); return false; } return true; } EXPORT_SYMBOL(__do_once_start); void __do_once_done(bool *done, struct static_key_true *once_key, unsigned long *flags, struct module *mod) __releases(once_lock) { *done = true; spin_unlock_irqrestore(&once_lock, *flags); once_disable_jump(once_key, mod); } EXPORT_SYMBOL(__do_once_done); static DEFINE_MUTEX(once_mutex); bool __do_once_sleepable_start(bool *done) __acquires(once_mutex) { mutex_lock(&once_mutex); if (*done) { mutex_unlock(&once_mutex); /* Keep sparse happy by restoring an even lock count on * this mutex. In case we return here, we don't call into * __do_once_done but return early in the DO_ONCE_SLEEPABLE() macro. */ __acquire(once_mutex); return false; } return true; } EXPORT_SYMBOL(__do_once_sleepable_start); void __do_once_sleepable_done(bool *done, struct static_key_true *once_key, struct module *mod) __releases(once_mutex) { *done = true; mutex_unlock(&once_mutex); once_disable_jump(once_key, mod); } EXPORT_SYMBOL(__do_once_sleepable_done); |
| 27 27 27 27 27 27 27 7 27 27 27 27 27 27 27 27 27 27 27 27 27 42 42 42 17 | 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 | /* SPDX-License-Identifier: GPL-2.0-only */ /* * Copyright (c) 2016 Qualcomm Atheros, Inc * * Based on net/sched/sch_fq_codel.c */ #ifndef __NET_SCHED_FQ_IMPL_H #define __NET_SCHED_FQ_IMPL_H #include <net/fq.h> /* functions that are embedded into includer */ static void __fq_adjust_removal(struct fq *fq, struct fq_flow *flow, unsigned int packets, unsigned int bytes, unsigned int truesize) { struct fq_tin *tin = flow->tin; int idx; tin->backlog_bytes -= bytes; tin->backlog_packets -= packets; flow->backlog -= bytes; fq->backlog -= packets; fq->memory_usage -= truesize; if (flow->backlog) return; if (flow == &tin->default_flow) { list_del_init(&tin->tin_list); return; } idx = flow - fq->flows; __clear_bit(idx, fq->flows_bitmap); } static void fq_adjust_removal(struct fq *fq, struct fq_flow *flow, struct sk_buff *skb) { __fq_adjust_removal(fq, flow, 1, skb->len, skb->truesize); } static struct sk_buff *fq_flow_dequeue(struct fq *fq, struct fq_flow *flow) { struct sk_buff *skb; lockdep_assert_held(&fq->lock); skb = __skb_dequeue(&flow->queue); if (!skb) return NULL; fq_adjust_removal(fq, flow, skb); return skb; } static int fq_flow_drop(struct fq *fq, struct fq_flow *flow, fq_skb_free_t free_func) { unsigned int packets = 0, bytes = 0, truesize = 0; struct fq_tin *tin = flow->tin; struct sk_buff *skb; int pending; lockdep_assert_held(&fq->lock); pending = min_t(int, 32, skb_queue_len(&flow->queue) / 2); do { skb = __skb_dequeue(&flow->queue); if (!skb) break; packets++; bytes += skb->len; truesize += skb->truesize; free_func(fq, tin, flow, skb); } while (packets < pending); __fq_adjust_removal(fq, flow, packets, bytes, truesize); return packets; } static struct sk_buff *fq_tin_dequeue(struct fq *fq, struct fq_tin *tin, fq_tin_dequeue_t dequeue_func) { struct fq_flow *flow; struct list_head *head; struct sk_buff *skb; lockdep_assert_held(&fq->lock); begin: head = &tin->new_flows; if (list_empty(head)) { head = &tin->old_flows; if (list_empty(head)) return NULL; } flow = list_first_entry(head, struct fq_flow, flowchain); if (flow->deficit <= 0) { flow->deficit += fq->quantum; list_move_tail(&flow->flowchain, &tin->old_flows); goto begin; } skb = dequeue_func(fq, tin, flow); if (!skb) { /* force a pass through old_flows to prevent starvation */ if ((head == &tin->new_flows) && !list_empty(&tin->old_flows)) { list_move_tail(&flow->flowchain, &tin->old_flows); } else { list_del_init(&flow->flowchain); flow->tin = NULL; } goto begin; } flow->deficit -= skb->len; tin->tx_bytes += skb->len; tin->tx_packets++; return skb; } static u32 fq_flow_idx(struct fq *fq, struct sk_buff *skb) { u32 hash = skb_get_hash(skb); return reciprocal_scale(hash, fq->flows_cnt); } static struct fq_flow *fq_flow_classify(struct fq *fq, struct fq_tin *tin, u32 idx, struct sk_buff *skb) { struct fq_flow *flow; lockdep_assert_held(&fq->lock); flow = &fq->flows[idx]; if (flow->tin && flow->tin != tin) { flow = &tin->default_flow; tin->collisions++; fq->collisions++; } if (!flow->tin) tin->flows++; return flow; } static struct fq_flow *fq_find_fattest_flow(struct fq *fq) { struct fq_tin *tin; struct fq_flow *flow = NULL; u32 len = 0; int i; for_each_set_bit(i, fq->flows_bitmap, fq->flows_cnt) { struct fq_flow *cur = &fq->flows[i]; unsigned int cur_len; cur_len = cur->backlog; if (cur_len <= len) continue; flow = cur; len = cur_len; } list_for_each_entry(tin, &fq->tin_backlog, tin_list) { unsigned int cur_len = tin->default_flow.backlog; if (cur_len <= len) continue; flow = &tin->default_flow; len = cur_len; } return flow; } static void fq_tin_enqueue(struct fq *fq, struct fq_tin *tin, u32 idx, struct sk_buff *skb, fq_skb_free_t free_func) { struct fq_flow *flow; struct sk_buff *next; bool oom; lockdep_assert_held(&fq->lock); flow = fq_flow_classify(fq, tin, idx, skb); if (!flow->backlog) { if (flow != &tin->default_flow) __set_bit(idx, fq->flows_bitmap); else if (list_empty(&tin->tin_list)) list_add(&tin->tin_list, &fq->tin_backlog); } flow->tin = tin; skb_list_walk_safe(skb, skb, next) { skb_mark_not_on_list(skb); flow->backlog += skb->len; tin->backlog_bytes += skb->len; tin->backlog_packets++; fq->memory_usage += skb->truesize; fq->backlog++; __skb_queue_tail(&flow->queue, skb); } if (list_empty(&flow->flowchain)) { flow->deficit = fq->quantum; list_add_tail(&flow->flowchain, &tin->new_flows); } oom = (fq->memory_usage > fq->memory_limit); while (fq->backlog > fq->limit || oom) { flow = fq_find_fattest_flow(fq); if (!flow) return; if (!fq_flow_drop(fq, flow, free_func)) return; flow->tin->overlimit++; fq->overlimit++; if (oom) { fq->overmemory++; oom = (fq->memory_usage > fq->memory_limit); } } } static void fq_flow_filter(struct fq *fq, struct fq_flow *flow, fq_skb_filter_t filter_func, void *filter_data, fq_skb_free_t free_func) { struct fq_tin *tin = flow->tin; struct sk_buff *skb, *tmp; lockdep_assert_held(&fq->lock); skb_queue_walk_safe(&flow->queue, skb, tmp) { if (!filter_func(fq, tin, flow, skb, filter_data)) continue; __skb_unlink(skb, &flow->queue); fq_adjust_removal(fq, flow, skb); free_func(fq, tin, flow, skb); } } static void fq_tin_filter(struct fq *fq, struct fq_tin *tin, fq_skb_filter_t filter_func, void *filter_data, fq_skb_free_t free_func) { struct fq_flow *flow; lockdep_assert_held(&fq->lock); list_for_each_entry(flow, &tin->new_flows, flowchain) fq_flow_filter(fq, flow, filter_func, filter_data, free_func); list_for_each_entry(flow, &tin->old_flows, flowchain) fq_flow_filter(fq, flow, filter_func, filter_data, free_func); } static void fq_flow_reset(struct fq *fq, struct fq_flow *flow, fq_skb_free_t free_func) { struct fq_tin *tin = flow->tin; struct sk_buff *skb; while ((skb = fq_flow_dequeue(fq, flow))) free_func(fq, tin, flow, skb); if (!list_empty(&flow->flowchain)) { list_del_init(&flow->flowchain); if (list_empty(&tin->new_flows) && list_empty(&tin->old_flows)) list_del_init(&tin->tin_list); } flow->tin = NULL; WARN_ON_ONCE(flow->backlog); } static void fq_tin_reset(struct fq *fq, struct fq_tin *tin, fq_skb_free_t free_func) { struct list_head *head; struct fq_flow *flow; for (;;) { head = &tin->new_flows; if (list_empty(head)) { head = &tin->old_flows; if (list_empty(head)) break; } flow = list_first_entry(head, struct fq_flow, flowchain); fq_flow_reset(fq, flow, free_func); } WARN_ON_ONCE(!list_empty(&tin->tin_list)); WARN_ON_ONCE(tin->backlog_bytes); WARN_ON_ONCE(tin->backlog_packets); } static void fq_flow_init(struct fq_flow *flow) { INIT_LIST_HEAD(&flow->flowchain); __skb_queue_head_init(&flow->queue); } static void fq_tin_init(struct fq_tin *tin) { INIT_LIST_HEAD(&tin->new_flows); INIT_LIST_HEAD(&tin->old_flows); INIT_LIST_HEAD(&tin->tin_list); fq_flow_init(&tin->default_flow); } static int fq_init(struct fq *fq, int flows_cnt) { int i; memset(fq, 0, sizeof(fq[0])); spin_lock_init(&fq->lock); INIT_LIST_HEAD(&fq->tin_backlog); fq->flows_cnt = max_t(u32, flows_cnt, 1); fq->quantum = 300; fq->limit = 8192; fq->memory_limit = 16 << 20; /* 16 MBytes */ fq->flows = kvcalloc(fq->flows_cnt, sizeof(fq->flows[0]), GFP_KERNEL); if (!fq->flows) return -ENOMEM; fq->flows_bitmap = bitmap_zalloc(fq->flows_cnt, GFP_KERNEL); if (!fq->flows_bitmap) { kvfree(fq->flows); fq->flows = NULL; return -ENOMEM; } for (i = 0; i < fq->flows_cnt; i++) fq_flow_init(&fq->flows[i]); return 0; } static void fq_reset(struct fq *fq, fq_skb_free_t free_func) { int i; for (i = 0; i < fq->flows_cnt; i++) fq_flow_reset(fq, &fq->flows[i], free_func); kvfree(fq->flows); fq->flows = NULL; bitmap_free(fq->flows_bitmap); fq->flows_bitmap = NULL; } #endif |
| 11 1 10 6 1 5 1 4 10 10 10 12 12 12 10 9 10 10 10 6 5 1 6 6 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 | // SPDX-License-Identifier: GPL-2.0 /* * To speed up listener socket lookup, create an array to store all sockets * listening on the same port. This allows a decision to be made after finding * the first socket. An optional BPF program can also be configured for * selecting the socket index from the array of available sockets. */ #include <net/ip.h> #include <net/sock_reuseport.h> #include <linux/bpf.h> #include <linux/idr.h> #include <linux/filter.h> #include <linux/rcupdate.h> #define INIT_SOCKS 128 DEFINE_SPINLOCK(reuseport_lock); static DEFINE_IDA(reuseport_ida); static int reuseport_resurrect(struct sock *sk, struct sock_reuseport *old_reuse, struct sock_reuseport *reuse, bool bind_inany); void reuseport_has_conns_set(struct sock *sk) { struct sock_reuseport *reuse; if (!rcu_access_pointer(sk->sk_reuseport_cb)) return; spin_lock_bh(&reuseport_lock); reuse = rcu_dereference_protected(sk->sk_reuseport_cb, lockdep_is_held(&reuseport_lock)); if (likely(reuse)) reuse->has_conns = 1; spin_unlock_bh(&reuseport_lock); } EXPORT_SYMBOL(reuseport_has_conns_set); static void __reuseport_get_incoming_cpu(struct sock_reuseport *reuse) { /* Paired with READ_ONCE() in reuseport_select_sock_by_hash(). */ WRITE_ONCE(reuse->incoming_cpu, reuse->incoming_cpu + 1); } static void __reuseport_put_incoming_cpu(struct sock_reuseport *reuse) { /* Paired with READ_ONCE() in reuseport_select_sock_by_hash(). */ WRITE_ONCE(reuse->incoming_cpu, reuse->incoming_cpu - 1); } static void reuseport_get_incoming_cpu(struct sock *sk, struct sock_reuseport *reuse) { if (sk->sk_incoming_cpu >= 0) __reuseport_get_incoming_cpu(reuse); } static void reuseport_put_incoming_cpu(struct sock *sk, struct sock_reuseport *reuse) { if (sk->sk_incoming_cpu >= 0) __reuseport_put_incoming_cpu(reuse); } void reuseport_update_incoming_cpu(struct sock *sk, int val) { struct sock_reuseport *reuse; int old_sk_incoming_cpu; if (unlikely(!rcu_access_pointer(sk->sk_reuseport_cb))) { /* Paired with REAE_ONCE() in sk_incoming_cpu_update() * and compute_score(). */ WRITE_ONCE(sk->sk_incoming_cpu, val); return; } spin_lock_bh(&reuseport_lock); /* This must be done under reuseport_lock to avoid a race with * reuseport_grow(), which accesses sk->sk_incoming_cpu without * lock_sock() when detaching a shutdown()ed sk. * * Paired with READ_ONCE() in reuseport_select_sock_by_hash(). */ old_sk_incoming_cpu = sk->sk_incoming_cpu; WRITE_ONCE(sk->sk_incoming_cpu, val); reuse = rcu_dereference_protected(sk->sk_reuseport_cb, lockdep_is_held(&reuseport_lock)); /* reuseport_grow() has detached a closed sk. */ if (!reuse) goto out; if (old_sk_incoming_cpu < 0 && val >= 0) __reuseport_get_incoming_cpu(reuse); else if (old_sk_incoming_cpu >= 0 && val < 0) __reuseport_put_incoming_cpu(reuse); out: spin_unlock_bh(&reuseport_lock); } static int reuseport_sock_index(struct sock *sk, const struct sock_reuseport *reuse, bool closed) { int left, right; if (!closed) { left = 0; right = reuse->num_socks; } else { left = reuse->max_socks - reuse->num_closed_socks; right = reuse->max_socks; } for (; left < right; left++) if (reuse->socks[left] == sk) return left; return -1; } static void __reuseport_add_sock(struct sock *sk, struct sock_reuseport *reuse) { reuse->socks[reuse->num_socks] = sk; /* paired with smp_rmb() in reuseport_(select|migrate)_sock() */ smp_wmb(); reuse->num_socks++; reuseport_get_incoming_cpu(sk, reuse); } static bool __reuseport_detach_sock(struct sock *sk, struct sock_reuseport *reuse) { int i = reuseport_sock_index(sk, reuse, false); if (i == -1) return false; reuse->socks[i] = reuse->socks[reuse->num_socks - 1]; reuse->num_socks--; reuseport_put_incoming_cpu(sk, reuse); return true; } static void __reuseport_add_closed_sock(struct sock *sk, struct sock_reuseport *reuse) { reuse->socks[reuse->max_socks - reuse->num_closed_socks - 1] = sk; /* paired with READ_ONCE() in inet_csk_bind_conflict() */ WRITE_ONCE(reuse->num_closed_socks, reuse->num_closed_socks + 1); reuseport_get_incoming_cpu(sk, reuse); } static bool __reuseport_detach_closed_sock(struct sock *sk, struct sock_reuseport *reuse) { int i = reuseport_sock_index(sk, reuse, true); if (i == -1) return false; reuse->socks[i] = reuse->socks[reuse->max_socks - reuse->num_closed_socks]; /* paired with READ_ONCE() in inet_csk_bind_conflict() */ WRITE_ONCE(reuse->num_closed_socks, reuse->num_closed_socks - 1); reuseport_put_incoming_cpu(sk, reuse); return true; } static struct sock_reuseport *__reuseport_alloc(unsigned int max_socks) { struct sock_reuseport *reuse; reuse = kzalloc(struct_size(reuse, socks, max_socks), GFP_ATOMIC); if (!reuse) return NULL; reuse->max_socks = max_socks; RCU_INIT_POINTER(reuse->prog, NULL); return reuse; } int reuseport_alloc(struct sock *sk, bool bind_inany) { struct sock_reuseport *reuse; int id, ret = 0; /* bh lock used since this function call may precede hlist lock in * soft irq of receive path or setsockopt from process context */ spin_lock_bh(&reuseport_lock); /* Allocation attempts can occur concurrently via the setsockopt path * and the bind/hash path. Nothing to do when we lose the race. */ reuse = rcu_dereference_protected(sk->sk_reuseport_cb, lockdep_is_held(&reuseport_lock)); if (reuse) { if (reuse->num_closed_socks) { /* sk was shutdown()ed before */ ret = reuseport_resurrect(sk, reuse, NULL, bind_inany); goto out; } /* Only set reuse->bind_inany if the bind_inany is true. * Otherwise, it will overwrite the reuse->bind_inany * which was set by the bind/hash path. */ if (bind_inany) reuse->bind_inany = bind_inany; goto out; } reuse = __reuseport_alloc(INIT_SOCKS); if (!reuse) { ret = -ENOMEM; goto out; } id = ida_alloc(&reuseport_ida, GFP_ATOMIC); if (id < 0) { kfree(reuse); ret = id; goto out; } reuse->reuseport_id = id; reuse->bind_inany = bind_inany; reuse->socks[0] = sk; reuse->num_socks = 1; reuseport_get_incoming_cpu(sk, reuse); rcu_assign_pointer(sk->sk_reuseport_cb, reuse); out: spin_unlock_bh(&reuseport_lock); return ret; } EXPORT_SYMBOL(reuseport_alloc); static struct sock_reuseport *reuseport_grow(struct sock_reuseport *reuse) { struct sock_reuseport *more_reuse; u32 more_socks_size, i; more_socks_size = reuse->max_socks * 2U; if (more_socks_size > U16_MAX) { if (reuse->num_closed_socks) { /* Make room by removing a closed sk. * The child has already been migrated. * Only reqsk left at this point. */ struct sock *sk; sk = reuse->socks[reuse->max_socks - reuse->num_closed_socks]; RCU_INIT_POINTER(sk->sk_reuseport_cb, NULL); __reuseport_detach_closed_sock(sk, reuse); return reuse; } return NULL; } more_reuse = __reuseport_alloc(more_socks_size); if (!more_reuse) return NULL; more_reuse->num_socks = reuse->num_socks; more_reuse->num_closed_socks = reuse->num_closed_socks; more_reuse->prog = reuse->prog; more_reuse->reuseport_id = reuse->reuseport_id; more_reuse->bind_inany = reuse->bind_inany; more_reuse->has_conns = reuse->has_conns; more_reuse->incoming_cpu = reuse->incoming_cpu; memcpy(more_reuse->socks, reuse->socks, reuse->num_socks * sizeof(struct sock *)); memcpy(more_reuse->socks + (more_reuse->max_socks - more_reuse->num_closed_socks), reuse->socks + (reuse->max_socks - reuse->num_closed_socks), reuse->num_closed_socks * sizeof(struct sock *)); more_reuse->synq_overflow_ts = READ_ONCE(reuse->synq_overflow_ts); for (i = 0; i < reuse->max_socks; ++i) rcu_assign_pointer(reuse->socks[i]->sk_reuseport_cb, more_reuse); /* Note: we use kfree_rcu here instead of reuseport_free_rcu so * that reuse and more_reuse can temporarily share a reference * to prog. */ kfree_rcu(reuse, rcu); return more_reuse; } static void reuseport_free_rcu(struct rcu_head *head) { struct sock_reuseport *reuse; reuse = container_of(head, struct sock_reuseport, rcu); sk_reuseport_prog_free(rcu_dereference_protected(reuse->prog, 1)); ida_free(&reuseport_ida, reuse->reuseport_id); kfree(reuse); } /** * reuseport_add_sock - Add a socket to the reuseport group of another. * @sk: New socket to add to the group. * @sk2: Socket belonging to the existing reuseport group. * @bind_inany: Whether or not the group is bound to a local INANY address. * * May return ENOMEM and not add socket to group under memory pressure. */ int reuseport_add_sock(struct sock *sk, struct sock *sk2, bool bind_inany) { struct sock_reuseport *old_reuse, *reuse; if (!rcu_access_pointer(sk2->sk_reuseport_cb)) { int err = reuseport_alloc(sk2, bind_inany); if (err) return err; } spin_lock_bh(&reuseport_lock); reuse = rcu_dereference_protected(sk2->sk_reuseport_cb, lockdep_is_held(&reuseport_lock)); old_reuse = rcu_dereference_protected(sk->sk_reuseport_cb, lockdep_is_held(&reuseport_lock)); if (old_reuse && old_reuse->num_closed_socks) { /* sk was shutdown()ed before */ int err = reuseport_resurrect(sk, old_reuse, reuse, reuse->bind_inany); spin_unlock_bh(&reuseport_lock); return err; } if (old_reuse && old_reuse->num_socks != 1) { spin_unlock_bh(&reuseport_lock); return -EBUSY; } if (reuse->num_socks + reuse->num_closed_socks == reuse->max_socks) { reuse = reuseport_grow(reuse); if (!reuse) { spin_unlock_bh(&reuseport_lock); return -ENOMEM; } } __reuseport_add_sock(sk, reuse); rcu_assign_pointer(sk->sk_reuseport_cb, reuse); spin_unlock_bh(&reuseport_lock); if (old_reuse) call_rcu(&old_reuse->rcu, reuseport_free_rcu); return 0; } EXPORT_SYMBOL(reuseport_add_sock); static int reuseport_resurrect(struct sock *sk, struct sock_reuseport *old_reuse, struct sock_reuseport *reuse, bool bind_inany) { if (old_reuse == reuse) { /* If sk was in the same reuseport group, just pop sk out of * the closed section and push sk into the listening section. */ __reuseport_detach_closed_sock(sk, old_reuse); __reuseport_add_sock(sk, old_reuse); return 0; } if (!reuse) { /* In bind()/listen() path, we cannot carry over the eBPF prog * for the shutdown()ed socket. In setsockopt() path, we should * not change the eBPF prog of listening sockets by attaching a * prog to the shutdown()ed socket. Thus, we will allocate a new * reuseport group and detach sk from the old group. */ int id; reuse = __reuseport_alloc(INIT_SOCKS); if (!reuse) return -ENOMEM; id = ida_alloc(&reuseport_ida, GFP_ATOMIC); if (id < 0) { kfree(reuse); return id; } reuse->reuseport_id = id; reuse->bind_inany = bind_inany; } else { /* Move sk from the old group to the new one if * - all the other listeners in the old group were close()d or * shutdown()ed, and then sk2 has listen()ed on the same port * OR * - sk listen()ed without bind() (or with autobind), was * shutdown()ed, and then listen()s on another port which * sk2 listen()s on. */ if (reuse->num_socks + reuse->num_closed_socks == reuse->max_socks) { reuse = reuseport_grow(reuse); if (!reuse) return -ENOMEM; } } __reuseport_detach_closed_sock(sk, old_reuse); __reuseport_add_sock(sk, reuse); rcu_assign_pointer(sk->sk_reuseport_cb, reuse); if (old_reuse->num_socks + old_reuse->num_closed_socks == 0) call_rcu(&old_reuse->rcu, reuseport_free_rcu); return 0; } void reuseport_detach_sock(struct sock *sk) { struct sock_reuseport *reuse; spin_lock_bh(&reuseport_lock); reuse = rcu_dereference_protected(sk->sk_reuseport_cb, lockdep_is_held(&reuseport_lock)); /* reuseport_grow() has detached a closed sk */ if (!reuse) goto out; /* Notify the bpf side. The sk may be added to a sockarray * map. If so, sockarray logic will remove it from the map. * * Other bpf map types that work with reuseport, like sockmap, * don't need an explicit callback from here. They override sk * unhash/close ops to remove the sk from the map before we * get to this point. */ bpf_sk_reuseport_detach(sk); rcu_assign_pointer(sk->sk_reuseport_cb, NULL); if (!__reuseport_detach_closed_sock(sk, reuse)) __reuseport_detach_sock(sk, reuse); if (reuse->num_socks + reuse->num_closed_socks == 0) call_rcu(&reuse->rcu, reuseport_free_rcu); out: spin_unlock_bh(&reuseport_lock); } EXPORT_SYMBOL(reuseport_detach_sock); void reuseport_stop_listen_sock(struct sock *sk) { if (sk->sk_protocol == IPPROTO_TCP) { struct sock_reuseport *reuse; struct bpf_prog *prog; spin_lock_bh(&reuseport_lock); reuse = rcu_dereference_protected(sk->sk_reuseport_cb, lockdep_is_held(&reuseport_lock)); prog = rcu_dereference_protected(reuse->prog, lockdep_is_held(&reuseport_lock)); if (READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_migrate_req) || (prog && prog->expected_attach_type == BPF_SK_REUSEPORT_SELECT_OR_MIGRATE)) { /* Migration capable, move sk from the listening section * to the closed section. */ bpf_sk_reuseport_detach(sk); __reuseport_detach_sock(sk, reuse); __reuseport_add_closed_sock(sk, reuse); spin_unlock_bh(&reuseport_lock); return; } spin_unlock_bh(&reuseport_lock); } /* Not capable to do migration, detach immediately */ reuseport_detach_sock(sk); } EXPORT_SYMBOL(reuseport_stop_listen_sock); static struct sock *run_bpf_filter(struct sock_reuseport *reuse, u16 socks, struct bpf_prog *prog, struct sk_buff *skb, int hdr_len) { struct sk_buff *nskb = NULL; u32 index; if (skb_shared(skb)) { nskb = skb_clone(skb, GFP_ATOMIC); if (!nskb) return NULL; skb = nskb; } /* temporarily advance data past protocol header */ if (!pskb_pull(skb, hdr_len)) { kfree_skb(nskb); return NULL; } index = bpf_prog_run_save_cb(prog, skb); __skb_push(skb, hdr_len); consume_skb(nskb); if (index >= socks) return NULL; return reuse->socks[index]; } static struct sock *reuseport_select_sock_by_hash(struct sock_reuseport *reuse, u32 hash, u16 num_socks) { struct sock *first_valid_sk = NULL; int i, j; i = j = reciprocal_scale(hash, num_socks); do { struct sock *sk = reuse->socks[i]; if (sk->sk_state != TCP_ESTABLISHED) { /* Paired with WRITE_ONCE() in __reuseport_(get|put)_incoming_cpu(). */ if (!READ_ONCE(reuse->incoming_cpu)) return sk; /* Paired with WRITE_ONCE() in reuseport_update_incoming_cpu(). */ if (READ_ONCE(sk->sk_incoming_cpu) == raw_smp_processor_id()) return sk; if (!first_valid_sk) first_valid_sk = sk; } i++; if (i >= num_socks) i = 0; } while (i != j); return first_valid_sk; } /** * reuseport_select_sock - Select a socket from an SO_REUSEPORT group. * @sk: First socket in the group. * @hash: When no BPF filter is available, use this hash to select. * @skb: skb to run through BPF filter. * @hdr_len: BPF filter expects skb data pointer at payload data. If * the skb does not yet point at the payload, this parameter represents * how far the pointer needs to advance to reach the payload. * Returns a socket that should receive the packet (or NULL on error). */ struct sock *reuseport_select_sock(struct sock *sk, u32 hash, struct sk_buff *skb, int hdr_len) { struct sock_reuseport *reuse; struct bpf_prog *prog; struct sock *sk2 = NULL; u16 socks; rcu_read_lock(); reuse = rcu_dereference(sk->sk_reuseport_cb); /* if memory allocation failed or add call is not yet complete */ if (!reuse) goto out; prog = rcu_dereference(reuse->prog); socks = READ_ONCE(reuse->num_socks); if (likely(socks)) { /* paired with smp_wmb() in __reuseport_add_sock() */ smp_rmb(); if (!prog || !skb) goto select_by_hash; if (prog->type == BPF_PROG_TYPE_SK_REUSEPORT) sk2 = bpf_run_sk_reuseport(reuse, sk, prog, skb, NULL, hash); else sk2 = run_bpf_filter(reuse, socks, prog, skb, hdr_len); select_by_hash: /* no bpf or invalid bpf result: fall back to hash usage */ if (!sk2) sk2 = reuseport_select_sock_by_hash(reuse, hash, socks); } out: rcu_read_unlock(); return sk2; } EXPORT_SYMBOL(reuseport_select_sock); /** * reuseport_migrate_sock - Select a socket from an SO_REUSEPORT group. * @sk: close()ed or shutdown()ed socket in the group. * @migrating_sk: ESTABLISHED/SYN_RECV full socket in the accept queue or * NEW_SYN_RECV request socket during 3WHS. * @skb: skb to run through BPF filter. * Returns a socket (with sk_refcnt +1) that should accept the child socket * (or NULL on error). */ struct sock *reuseport_migrate_sock(struct sock *sk, struct sock *migrating_sk, struct sk_buff *skb) { struct sock_reuseport *reuse; struct sock *nsk = NULL; bool allocated = false; struct bpf_prog *prog; u16 socks; u32 hash; rcu_read_lock(); reuse = rcu_dereference(sk->sk_reuseport_cb); if (!reuse) goto out; socks = READ_ONCE(reuse->num_socks); if (unlikely(!socks)) goto failure; /* paired with smp_wmb() in __reuseport_add_sock() */ smp_rmb(); hash = migrating_sk->sk_hash; prog = rcu_dereference(reuse->prog); if (!prog || prog->expected_attach_type != BPF_SK_REUSEPORT_SELECT_OR_MIGRATE) { if (READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_migrate_req)) goto select_by_hash; goto failure; } if (!skb) { skb = alloc_skb(0, GFP_ATOMIC); if (!skb) goto failure; allocated = true; } nsk = bpf_run_sk_reuseport(reuse, sk, prog, skb, migrating_sk, hash); if (allocated) kfree_skb(skb); select_by_hash: if (!nsk) nsk = reuseport_select_sock_by_hash(reuse, hash, socks); if (IS_ERR_OR_NULL(nsk) || unlikely(!refcount_inc_not_zero(&nsk->sk_refcnt))) { nsk = NULL; goto failure; } out: rcu_read_unlock(); return nsk; failure: __NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPMIGRATEREQFAILURE); goto out; } EXPORT_SYMBOL(reuseport_migrate_sock); int reuseport_attach_prog(struct sock *sk, struct bpf_prog *prog) { struct sock_reuseport *reuse; struct bpf_prog *old_prog; if (sk_unhashed(sk)) { int err; if (!sk->sk_reuseport) return -EINVAL; err = reuseport_alloc(sk, false); if (err) return err; } else if (!rcu_access_pointer(sk->sk_reuseport_cb)) { /* The socket wasn't bound with SO_REUSEPORT */ return -EINVAL; } spin_lock_bh(&reuseport_lock); reuse = rcu_dereference_protected(sk->sk_reuseport_cb, lockdep_is_held(&reuseport_lock)); old_prog = rcu_dereference_protected(reuse->prog, lockdep_is_held(&reuseport_lock)); rcu_assign_pointer(reuse->prog, prog); spin_unlock_bh(&reuseport_lock); sk_reuseport_prog_free(old_prog); return 0; } EXPORT_SYMBOL(reuseport_attach_prog); int reuseport_detach_prog(struct sock *sk) { struct sock_reuseport *reuse; struct bpf_prog *old_prog; old_prog = NULL; spin_lock_bh(&reuseport_lock); reuse = rcu_dereference_protected(sk->sk_reuseport_cb, lockdep_is_held(&reuseport_lock)); /* reuse must be checked after acquiring the reuseport_lock * because reuseport_grow() can detach a closed sk. */ if (!reuse) { spin_unlock_bh(&reuseport_lock); return sk->sk_reuseport ? -ENOENT : -EINVAL; } if (sk_unhashed(sk) && reuse->num_closed_socks) { spin_unlock_bh(&reuseport_lock); return -ENOENT; } old_prog = rcu_replace_pointer(reuse->prog, old_prog, lockdep_is_held(&reuseport_lock)); spin_unlock_bh(&reuseport_lock); if (!old_prog) return -ENOENT; sk_reuseport_prog_free(old_prog); return 0; } EXPORT_SYMBOL(reuseport_detach_prog); |
| 100 233 | 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 | /* SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB */ /* * Copyright (c) 2005 Voltaire Inc. All rights reserved. * Copyright (c) 2005 Intel Corporation. All rights reserved. */ #ifndef IB_ADDR_H #define IB_ADDR_H #include <linux/ethtool.h> #include <linux/in.h> #include <linux/in6.h> #include <linux/if_arp.h> #include <linux/netdevice.h> #include <linux/inetdevice.h> #include <linux/socket.h> #include <linux/if_vlan.h> #include <net/ipv6.h> #include <net/if_inet6.h> #include <net/ip.h> #include <rdma/ib_verbs.h> #include <rdma/ib_pack.h> #include <net/net_namespace.h> /** * struct rdma_dev_addr - Contains resolved RDMA hardware addresses * @src_dev_addr: Source MAC address. * @dst_dev_addr: Destination MAC address. * @broadcast: Broadcast address of the device. * @dev_type: The interface hardware type of the device. * @bound_dev_if: An optional device interface index. * @transport: The transport type used. * @net: Network namespace containing the bound_dev_if net_dev. * @sgid_attr: GID attribute to use for identified SGID */ struct rdma_dev_addr { unsigned char src_dev_addr[MAX_ADDR_LEN]; unsigned char dst_dev_addr[MAX_ADDR_LEN]; unsigned char broadcast[MAX_ADDR_LEN]; unsigned short dev_type; int bound_dev_if; enum rdma_transport_type transport; struct net *net; const struct ib_gid_attr *sgid_attr; enum rdma_network_type network; int hoplimit; }; /** * rdma_translate_ip - Translate a local IP address to an RDMA hardware * address. * * The dev_addr->net field must be initialized. */ int rdma_translate_ip(const struct sockaddr *addr, struct rdma_dev_addr *dev_addr); /** * rdma_resolve_ip - Resolve source and destination IP addresses to * RDMA hardware addresses. * @src_addr: An optional source address to use in the resolution. If a * source address is not provided, a usable address will be returned via * the callback. * @dst_addr: The destination address to resolve. * @addr: A reference to a data location that will receive the resolved * addresses. The data location must remain valid until the callback has * been invoked. The net field of the addr struct must be valid. * @timeout_ms: Amount of time to wait for the address resolution to complete. * @callback: Call invoked once address resolution has completed, timed out, * or been canceled. A status of 0 indicates success. * @resolve_by_gid_attr: Resolve the ip based on the GID attribute from * rdma_dev_addr. * @context: User-specified context associated with the call. */ int rdma_resolve_ip(struct sockaddr *src_addr, const struct sockaddr *dst_addr, struct rdma_dev_addr *addr, unsigned long timeout_ms, void (*callback)(int status, struct sockaddr *src_addr, struct rdma_dev_addr *addr, void *context), bool resolve_by_gid_attr, void *context); void rdma_addr_cancel(struct rdma_dev_addr *addr); int rdma_addr_size(const struct sockaddr *addr); int rdma_addr_size_in6(struct sockaddr_in6 *addr); int rdma_addr_size_kss(struct __kernel_sockaddr_storage *addr); static inline u16 ib_addr_get_pkey(struct rdma_dev_addr *dev_addr) { return ((u16)dev_addr->broadcast[8] << 8) | (u16)dev_addr->broadcast[9]; } static inline void ib_addr_set_pkey(struct rdma_dev_addr *dev_addr, u16 pkey) { dev_addr->broadcast[8] = pkey >> 8; dev_addr->broadcast[9] = (unsigned char) pkey; } static inline void ib_addr_get_mgid(struct rdma_dev_addr *dev_addr, union ib_gid *gid) { memcpy(gid, dev_addr->broadcast + 4, sizeof *gid); } static inline int rdma_addr_gid_offset(struct rdma_dev_addr *dev_addr) { return dev_addr->dev_type == ARPHRD_INFINIBAND ? 4 : 0; } static inline u16 rdma_vlan_dev_vlan_id(const struct net_device *dev) { return is_vlan_dev(dev) ? vlan_dev_vlan_id(dev) : 0xffff; } static inline int rdma_ip2gid(struct sockaddr *addr, union ib_gid *gid) { switch (addr->sa_family) { case AF_INET: ipv6_addr_set_v4mapped(((struct sockaddr_in *) addr)->sin_addr.s_addr, (struct in6_addr *)gid); break; case AF_INET6: *(struct in6_addr *)&gid->raw = ((struct sockaddr_in6 *)addr)->sin6_addr; break; default: return -EINVAL; } return 0; } /* Important - sockaddr should be a union of sockaddr_in and sockaddr_in6 */ static inline void rdma_gid2ip(struct sockaddr *out, const union ib_gid *gid) { if (ipv6_addr_v4mapped((struct in6_addr *)gid)) { struct sockaddr_in *out_in = (struct sockaddr_in *)out; memset(out_in, 0, sizeof(*out_in)); out_in->sin_family = AF_INET; memcpy(&out_in->sin_addr.s_addr, gid->raw + 12, 4); } else { struct sockaddr_in6 *out_in = (struct sockaddr_in6 *)out; memset(out_in, 0, sizeof(*out_in)); out_in->sin6_family = AF_INET6; memcpy(&out_in->sin6_addr.s6_addr, gid->raw, 16); } } /* * rdma_get/set_sgid/dgid() APIs are applicable to IB, and iWarp. * They are not applicable to RoCE. * RoCE GIDs are derived from the IP addresses. */ static inline void rdma_addr_get_sgid(struct rdma_dev_addr *dev_addr, union ib_gid *gid) { memcpy(gid, dev_addr->src_dev_addr + rdma_addr_gid_offset(dev_addr), sizeof(*gid)); } static inline void rdma_addr_set_sgid(struct rdma_dev_addr *dev_addr, union ib_gid *gid) { memcpy(dev_addr->src_dev_addr + rdma_addr_gid_offset(dev_addr), gid, sizeof *gid); } static inline void rdma_addr_get_dgid(struct rdma_dev_addr *dev_addr, union ib_gid *gid) { memcpy(gid, dev_addr->dst_dev_addr + rdma_addr_gid_offset(dev_addr), sizeof *gid); } static inline void rdma_addr_set_dgid(struct rdma_dev_addr *dev_addr, union ib_gid *gid) { memcpy(dev_addr->dst_dev_addr + rdma_addr_gid_offset(dev_addr), gid, sizeof *gid); } static inline enum ib_mtu iboe_get_mtu(int mtu) { /* * Reduce IB headers from effective IBoE MTU. */ mtu = mtu - (IB_GRH_BYTES + IB_UDP_BYTES + IB_BTH_BYTES + IB_EXT_XRC_BYTES + IB_EXT_ATOMICETH_BYTES + IB_ICRC_BYTES); if (mtu >= ib_mtu_enum_to_int(IB_MTU_4096)) return IB_MTU_4096; else if (mtu >= ib_mtu_enum_to_int(IB_MTU_2048)) return IB_MTU_2048; else if (mtu >= ib_mtu_enum_to_int(IB_MTU_1024)) return IB_MTU_1024; else if (mtu >= ib_mtu_enum_to_int(IB_MTU_512)) return IB_MTU_512; else if (mtu >= ib_mtu_enum_to_int(IB_MTU_256)) return IB_MTU_256; else return 0; } static inline int rdma_link_local_addr(struct in6_addr *addr) { if (addr->s6_addr32[0] == htonl(0xfe800000) && addr->s6_addr32[1] == 0) return 1; return 0; } static inline void rdma_get_ll_mac(struct in6_addr *addr, u8 *mac) { memcpy(mac, &addr->s6_addr[8], 3); memcpy(mac + 3, &addr->s6_addr[13], 3); mac[0] ^= 2; } static inline int rdma_is_multicast_addr(struct in6_addr *addr) { __be32 ipv4_addr; if (addr->s6_addr[0] == 0xff) return 1; ipv4_addr = addr->s6_addr32[3]; return (ipv6_addr_v4mapped(addr) && ipv4_is_multicast(ipv4_addr)); } static inline void rdma_get_mcast_mac(struct in6_addr *addr, u8 *mac) { int i; mac[0] = 0x33; mac[1] = 0x33; for (i = 2; i < 6; ++i) mac[i] = addr->s6_addr[i + 10]; } static inline u16 rdma_get_vlan_id(union ib_gid *dgid) { u16 vid; vid = dgid->raw[11] << 8 | dgid->raw[12]; return vid < 0x1000 ? vid : 0xffff; } static inline struct net_device *rdma_vlan_dev_real_dev(const struct net_device *dev) { return is_vlan_dev(dev) ? vlan_dev_real_dev(dev) : NULL; } #endif /* IB_ADDR_H */ |
| 131 129 4 4 17 17 21 21 131 130 2 | 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 | // SPDX-License-Identifier: GPL-2.0 /* * Author: Andrei Vagin <avagin@openvz.org> * Author: Dmitry Safonov <dima@arista.com> */ #include <linux/time_namespace.h> #include <linux/user_namespace.h> #include <linux/sched/signal.h> #include <linux/sched/task.h> #include <linux/clocksource.h> #include <linux/seq_file.h> #include <linux/proc_ns.h> #include <linux/export.h> #include <linux/time.h> #include <linux/slab.h> #include <linux/cred.h> #include <linux/err.h> #include <linux/mm.h> #include <vdso/datapage.h> ktime_t do_timens_ktime_to_host(clockid_t clockid, ktime_t tim, struct timens_offsets *ns_offsets) { ktime_t offset; switch (clockid) { case CLOCK_MONOTONIC: offset = timespec64_to_ktime(ns_offsets->monotonic); break; case CLOCK_BOOTTIME: case CLOCK_BOOTTIME_ALARM: offset = timespec64_to_ktime(ns_offsets->boottime); break; default: return tim; } /* * Check that @tim value is in [offset, KTIME_MAX + offset] * and subtract offset. */ if (tim < offset) { /* * User can specify @tim *absolute* value - if it's lesser than * the time namespace's offset - it's already expired. */ tim = 0; } else { tim = ktime_sub(tim, offset); if (unlikely(tim > KTIME_MAX)) tim = KTIME_MAX; } return tim; } static struct ucounts *inc_time_namespaces(struct user_namespace *ns) { return inc_ucount(ns, current_euid(), UCOUNT_TIME_NAMESPACES); } static void dec_time_namespaces(struct ucounts *ucounts) { dec_ucount(ucounts, UCOUNT_TIME_NAMESPACES); } /** * clone_time_ns - Clone a time namespace * @user_ns: User namespace which owns a new namespace. * @old_ns: Namespace to clone * * Clone @old_ns and set the clone refcount to 1 * * Return: The new namespace or ERR_PTR. */ static struct time_namespace *clone_time_ns(struct user_namespace *user_ns, struct time_namespace *old_ns) { struct time_namespace *ns; struct ucounts *ucounts; int err; err = -ENOSPC; ucounts = inc_time_namespaces(user_ns); if (!ucounts) goto fail; err = -ENOMEM; ns = kmalloc(sizeof(*ns), GFP_KERNEL_ACCOUNT); if (!ns) goto fail_dec; refcount_set(&ns->ns.count, 1); ns->vvar_page = alloc_page(GFP_KERNEL_ACCOUNT | __GFP_ZERO); if (!ns->vvar_page) goto fail_free; err = ns_alloc_inum(&ns->ns); if (err) goto fail_free_page; ns->ucounts = ucounts; ns->ns.ops = &timens_operations; ns->user_ns = get_user_ns(user_ns); ns->offsets = old_ns->offsets; ns->frozen_offsets = false; return ns; fail_free_page: __free_page(ns->vvar_page); fail_free: kfree(ns); fail_dec: dec_time_namespaces(ucounts); fail: return ERR_PTR(err); } /** * copy_time_ns - Create timens_for_children from @old_ns * @flags: Cloning flags * @user_ns: User namespace which owns a new namespace. * @old_ns: Namespace to clone * * If CLONE_NEWTIME specified in @flags, creates a new timens_for_children; * adds a refcounter to @old_ns otherwise. * * Return: timens_for_children namespace or ERR_PTR. */ struct time_namespace *copy_time_ns(unsigned long flags, struct user_namespace *user_ns, struct time_namespace *old_ns) { if (!(flags & CLONE_NEWTIME)) return get_time_ns(old_ns); return clone_time_ns(user_ns, old_ns); } static struct timens_offset offset_from_ts(struct timespec64 off) { struct timens_offset ret; ret.sec = off.tv_sec; ret.nsec = off.tv_nsec; return ret; } /* * A time namespace VVAR page has the same layout as the VVAR page which * contains the system wide VDSO data. * * For a normal task the VVAR pages are installed in the normal ordering: * VVAR * PVCLOCK * HVCLOCK * TIMENS <- Not really required * * Now for a timens task the pages are installed in the following order: * TIMENS * PVCLOCK * HVCLOCK * VVAR * * The check for vdso_data->clock_mode is in the unlikely path of * the seq begin magic. So for the non-timens case most of the time * 'seq' is even, so the branch is not taken. * * If 'seq' is odd, i.e. a concurrent update is in progress, the extra check * for vdso_data->clock_mode is a non-issue. The task is spin waiting for the * update to finish and for 'seq' to become even anyway. * * Timens page has vdso_data->clock_mode set to VDSO_CLOCKMODE_TIMENS which * enforces the time namespace handling path. */ static void timens_setup_vdso_data(struct vdso_data *vdata, struct time_namespace *ns) { struct timens_offset *offset = vdata->offset; struct timens_offset monotonic = offset_from_ts(ns->offsets.monotonic); struct timens_offset boottime = offset_from_ts(ns->offsets.boottime); vdata->seq = 1; vdata->clock_mode = VDSO_CLOCKMODE_TIMENS; offset[CLOCK_MONOTONIC] = monotonic; offset[CLOCK_MONOTONIC_RAW] = monotonic; offset[CLOCK_MONOTONIC_COARSE] = monotonic; offset[CLOCK_BOOTTIME] = boottime; offset[CLOCK_BOOTTIME_ALARM] = boottime; } struct page *find_timens_vvar_page(struct vm_area_struct *vma) { if (likely(vma->vm_mm == current->mm)) return current->nsproxy->time_ns->vvar_page; /* * VM_PFNMAP | VM_IO protect .fault() handler from being called * through interfaces like /proc/$pid/mem or * process_vm_{readv,writev}() as long as there's no .access() * in special_mapping_vmops(). * For more details check_vma_flags() and __access_remote_vm() */ WARN(1, "vvar_page accessed remotely"); return NULL; } /* * Protects possibly multiple offsets writers racing each other * and tasks entering the namespace. */ static DEFINE_MUTEX(offset_lock); static void timens_set_vvar_page(struct task_struct *task, struct time_namespace *ns) { struct vdso_data *vdata; unsigned int i; if (ns == &init_time_ns) return; /* Fast-path, taken by every task in namespace except the first. */ if (likely(ns->frozen_offsets)) return; mutex_lock(&offset_lock); /* Nothing to-do: vvar_page has been already initialized. */ if (ns->frozen_offsets) goto out; ns->frozen_offsets = true; vdata = arch_get_vdso_data(page_address(ns->vvar_page)); for (i = 0; i < CS_BASES; i++) timens_setup_vdso_data(&vdata[i], ns); out: mutex_unlock(&offset_lock); } void free_time_ns(struct time_namespace *ns) { dec_time_namespaces(ns->ucounts); put_user_ns(ns->user_ns); ns_free_inum(&ns->ns); __free_page(ns->vvar_page); kfree(ns); } static struct time_namespace *to_time_ns(struct ns_common *ns) { return container_of(ns, struct time_namespace, ns); } static struct ns_common *timens_get(struct task_struct *task) { struct time_namespace *ns = NULL; struct nsproxy *nsproxy; task_lock(task); nsproxy = task->nsproxy; if (nsproxy) { ns = nsproxy->time_ns; get_time_ns(ns); } task_unlock(task); return ns ? &ns->ns : NULL; } static struct ns_common *timens_for_children_get(struct task_struct *task) { struct time_namespace *ns = NULL; struct nsproxy *nsproxy; task_lock(task); nsproxy = task->nsproxy; if (nsproxy) { ns = nsproxy->time_ns_for_children; get_time_ns(ns); } task_unlock(task); return ns ? &ns->ns : NULL; } static void timens_put(struct ns_common *ns) { put_time_ns(to_time_ns(ns)); } void timens_commit(struct task_struct *tsk, struct time_namespace *ns) { timens_set_vvar_page(tsk, ns); vdso_join_timens(tsk, ns); } static int timens_install(struct nsset *nsset, struct ns_common *new) { struct nsproxy *nsproxy = nsset->nsproxy; struct time_namespace *ns = to_time_ns(new); if (!current_is_single_threaded()) return -EUSERS; if (!ns_capable(ns->user_ns, CAP_SYS_ADMIN) || !ns_capable(nsset->cred->user_ns, CAP_SYS_ADMIN)) return -EPERM; get_time_ns(ns); put_time_ns(nsproxy->time_ns); nsproxy->time_ns = ns; get_time_ns(ns); put_time_ns(nsproxy->time_ns_for_children); nsproxy->time_ns_for_children = ns; return 0; } void timens_on_fork(struct nsproxy *nsproxy, struct task_struct *tsk) { struct ns_common *nsc = &nsproxy->time_ns_for_children->ns; struct time_namespace *ns = to_time_ns(nsc); /* create_new_namespaces() already incremented the ref counter */ if (nsproxy->time_ns == nsproxy->time_ns_for_children) return; get_time_ns(ns); put_time_ns(nsproxy->time_ns); nsproxy->time_ns = ns; timens_commit(tsk, ns); } static struct user_namespace *timens_owner(struct ns_common *ns) { return to_time_ns(ns)->user_ns; } static void show_offset(struct seq_file *m, int clockid, struct timespec64 *ts) { char *clock; switch (clockid) { case CLOCK_BOOTTIME: clock = "boottime"; break; case CLOCK_MONOTONIC: clock = "monotonic"; break; default: clock = "unknown"; break; } seq_printf(m, "%-10s %10lld %9ld\n", clock, ts->tv_sec, ts->tv_nsec); } void proc_timens_show_offsets(struct task_struct *p, struct seq_file *m) { struct ns_common *ns; struct time_namespace *time_ns; ns = timens_for_children_get(p); if (!ns) return; time_ns = to_time_ns(ns); show_offset(m, CLOCK_MONOTONIC, &time_ns->offsets.monotonic); show_offset(m, CLOCK_BOOTTIME, &time_ns->offsets.boottime); put_time_ns(time_ns); } int proc_timens_set_offset(struct file *file, struct task_struct *p, struct proc_timens_offset *offsets, int noffsets) { struct ns_common *ns; struct time_namespace *time_ns; struct timespec64 tp; int i, err; ns = timens_for_children_get(p); if (!ns) return -ESRCH; time_ns = to_time_ns(ns); if (!file_ns_capable(file, time_ns->user_ns, CAP_SYS_TIME)) { put_time_ns(time_ns); return -EPERM; } for (i = 0; i < noffsets; i++) { struct proc_timens_offset *off = &offsets[i]; switch (off->clockid) { case CLOCK_MONOTONIC: ktime_get_ts64(&tp); break; case CLOCK_BOOTTIME: ktime_get_boottime_ts64(&tp); break; default: err = -EINVAL; goto out; } err = -ERANGE; if (off->val.tv_sec > KTIME_SEC_MAX || off->val.tv_sec < -KTIME_SEC_MAX) goto out; tp = timespec64_add(tp, off->val); /* * KTIME_SEC_MAX is divided by 2 to be sure that KTIME_MAX is * still unreachable. */ if (tp.tv_sec < 0 || tp.tv_sec > KTIME_SEC_MAX / 2) goto out; } mutex_lock(&offset_lock); if (time_ns->frozen_offsets) { err = -EACCES; goto out_unlock; } err = 0; /* Don't report errors after this line */ for (i = 0; i < noffsets; i++) { struct proc_timens_offset *off = &offsets[i]; struct timespec64 *offset = NULL; switch (off->clockid) { case CLOCK_MONOTONIC: offset = &time_ns->offsets.monotonic; break; case CLOCK_BOOTTIME: offset = &time_ns->offsets.boottime; break; } *offset = off->val; } out_unlock: mutex_unlock(&offset_lock); out: put_time_ns(time_ns); return err; } const struct proc_ns_operations timens_operations = { .name = "time", .type = CLONE_NEWTIME, .get = timens_get, .put = timens_put, .install = timens_install, .owner = timens_owner, }; const struct proc_ns_operations timens_for_children_operations = { .name = "time_for_children", .real_ns_name = "time", .type = CLONE_NEWTIME, .get = timens_for_children_get, .put = timens_put, .install = timens_install, .owner = timens_owner, }; struct time_namespace init_time_ns = { .ns.count = REFCOUNT_INIT(3), .user_ns = &init_user_ns, .ns.inum = PROC_TIME_INIT_INO, .ns.ops = &timens_operations, .frozen_offsets = true, }; |
| 53 53 53 53 53 53 53 53 53 53 53 53 53 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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 | // SPDX-License-Identifier: GPL-2.0-or-later /* Provide a way to create a superblock configuration context within the kernel * that allows a superblock to be set up prior to mounting. * * Copyright (C) 2017 Red Hat, Inc. All Rights Reserved. * Written by David Howells (dhowells@redhat.com) */ #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt #include <linux/module.h> #include <linux/fs_context.h> #include <linux/fs_parser.h> #include <linux/fs.h> #include <linux/mount.h> #include <linux/nsproxy.h> #include <linux/slab.h> #include <linux/magic.h> #include <linux/security.h> #include <linux/mnt_namespace.h> #include <linux/pid_namespace.h> #include <linux/user_namespace.h> #include <net/net_namespace.h> #include <asm/sections.h> #include "mount.h" #include "internal.h" enum legacy_fs_param { LEGACY_FS_UNSET_PARAMS, LEGACY_FS_MONOLITHIC_PARAMS, LEGACY_FS_INDIVIDUAL_PARAMS, }; struct legacy_fs_context { char *legacy_data; /* Data page for legacy filesystems */ size_t data_size; enum legacy_fs_param param_type; }; static int legacy_init_fs_context(struct fs_context *fc); static const struct constant_table common_set_sb_flag[] = { { "dirsync", SB_DIRSYNC }, { "lazytime", SB_LAZYTIME }, { "mand", SB_MANDLOCK }, { "ro", SB_RDONLY }, { "sync", SB_SYNCHRONOUS }, { }, }; static const struct constant_table common_clear_sb_flag[] = { { "async", SB_SYNCHRONOUS }, { "nolazytime", SB_LAZYTIME }, { "nomand", SB_MANDLOCK }, { "rw", SB_RDONLY }, { }, }; /* * Check for a common mount option that manipulates s_flags. */ static int vfs_parse_sb_flag(struct fs_context *fc, const char *key) { unsigned int token; token = lookup_constant(common_set_sb_flag, key, 0); if (token) { fc->sb_flags |= token; fc->sb_flags_mask |= token; return 0; } token = lookup_constant(common_clear_sb_flag, key, 0); if (token) { fc->sb_flags &= ~token; fc->sb_flags_mask |= token; return 0; } return -ENOPARAM; } /** * vfs_parse_fs_param_source - Handle setting "source" via parameter * @fc: The filesystem context to modify * @param: The parameter * * This is a simple helper for filesystems to verify that the "source" they * accept is sane. * * Returns 0 on success, -ENOPARAM if this is not "source" parameter, and * -EINVAL otherwise. In the event of failure, supplementary error information * is logged. */ int vfs_parse_fs_param_source(struct fs_context *fc, struct fs_parameter *param) { if (strcmp(param->key, "source") != 0) return -ENOPARAM; if (param->type != fs_value_is_string) return invalf(fc, "Non-string source"); if (fc->source) return invalf(fc, "Multiple sources"); fc->source = param->string; param->string = NULL; return 0; } EXPORT_SYMBOL(vfs_parse_fs_param_source); /** * vfs_parse_fs_param - Add a single parameter to a superblock config * @fc: The filesystem context to modify * @param: The parameter * * A single mount option in string form is applied to the filesystem context * being set up. Certain standard options (for example "ro") are translated * into flag bits without going to the filesystem. The active security module * is allowed to observe and poach options. Any other options are passed over * to the filesystem to parse. * * This may be called multiple times for a context. * * Returns 0 on success and a negative error code on failure. In the event of * failure, supplementary error information may have been set. */ int vfs_parse_fs_param(struct fs_context *fc, struct fs_parameter *param) { int ret; if (!param->key) return invalf(fc, "Unnamed parameter\n"); ret = vfs_parse_sb_flag(fc, param->key); if (ret != -ENOPARAM) return ret; ret = security_fs_context_parse_param(fc, param); if (ret != -ENOPARAM) /* Param belongs to the LSM or is disallowed by the LSM; so * don't pass to the FS. */ return ret; if (fc->ops->parse_param) { ret = fc->ops->parse_param(fc, param); if (ret != -ENOPARAM) return ret; } /* If the filesystem doesn't take any arguments, give it the * default handling of source. */ ret = vfs_parse_fs_param_source(fc, param); if (ret != -ENOPARAM) return ret; return invalf(fc, "%s: Unknown parameter '%s'", fc->fs_type->name, param->key); } EXPORT_SYMBOL(vfs_parse_fs_param); /** * vfs_parse_fs_string - Convenience function to just parse a string. * @fc: Filesystem context. * @key: Parameter name. * @value: Default value. * @v_size: Maximum number of bytes in the value. */ int vfs_parse_fs_string(struct fs_context *fc, const char *key, const char *value, size_t v_size) { int ret; struct fs_parameter param = { .key = key, .type = fs_value_is_flag, .size = v_size, }; if (value) { param.string = kmemdup_nul(value, v_size, GFP_KERNEL); if (!param.string) return -ENOMEM; param.type = fs_value_is_string; } ret = vfs_parse_fs_param(fc, ¶m); kfree(param.string); return ret; } EXPORT_SYMBOL(vfs_parse_fs_string); /** * vfs_parse_monolithic_sep - Parse key[=val][,key[=val]]* mount data * @fc: The superblock configuration to fill in. * @data: The data to parse * @sep: callback for separating next option * * Parse a blob of data that's in key[=val][,key[=val]]* form with a custom * option separator callback. * * Returns 0 on success or the error returned by the ->parse_option() fs_context * operation on failure. */ int vfs_parse_monolithic_sep(struct fs_context *fc, void *data, char *(*sep)(char **)) { char *options = data, *key; int ret = 0; if (!options) return 0; ret = security_sb_eat_lsm_opts(options, &fc->security); if (ret) return ret; while ((key = sep(&options)) != NULL) { if (*key) { size_t v_len = 0; char *value = strchr(key, '='); if (value) { if (value == key) continue; *value++ = 0; v_len = strlen(value); } ret = vfs_parse_fs_string(fc, key, value, v_len); if (ret < 0) break; } } return ret; } EXPORT_SYMBOL(vfs_parse_monolithic_sep); static char *vfs_parse_comma_sep(char **s) { return strsep(s, ","); } /** * generic_parse_monolithic - Parse key[=val][,key[=val]]* mount data * @fc: The superblock configuration to fill in. * @data: The data to parse * * Parse a blob of data that's in key[=val][,key[=val]]* form. This can be * called from the ->monolithic_mount_data() fs_context operation. * * Returns 0 on success or the error returned by the ->parse_option() fs_context * operation on failure. */ int generic_parse_monolithic(struct fs_context *fc, void *data) { return vfs_parse_monolithic_sep(fc, data, vfs_parse_comma_sep); } EXPORT_SYMBOL(generic_parse_monolithic); /** * alloc_fs_context - Create a filesystem context. * @fs_type: The filesystem type. * @reference: The dentry from which this one derives (or NULL) * @sb_flags: Filesystem/superblock flags (SB_*) * @sb_flags_mask: Applicable members of @sb_flags * @purpose: The purpose that this configuration shall be used for. * * Open a filesystem and create a mount context. The mount context is * initialised with the supplied flags and, if a submount/automount from * another superblock (referred to by @reference) is supplied, may have * parameters such as namespaces copied across from that superblock. */ static struct fs_context *alloc_fs_context(struct file_system_type *fs_type, struct dentry *reference, unsigned int sb_flags, unsigned int sb_flags_mask, enum fs_context_purpose purpose) { int (*init_fs_context)(struct fs_context *); struct fs_context *fc; int ret = -ENOMEM; fc = kzalloc(sizeof(struct fs_context), GFP_KERNEL_ACCOUNT); if (!fc) return ERR_PTR(-ENOMEM); fc->purpose = purpose; fc->sb_flags = sb_flags; fc->sb_flags_mask = sb_flags_mask; fc->fs_type = get_filesystem(fs_type); fc->cred = get_current_cred(); fc->net_ns = get_net(current->nsproxy->net_ns); fc->log.prefix = fs_type->name; mutex_init(&fc->uapi_mutex); switch (purpose) { case FS_CONTEXT_FOR_MOUNT: fc->user_ns = get_user_ns(fc->cred->user_ns); break; case FS_CONTEXT_FOR_SUBMOUNT: fc->user_ns = get_user_ns(reference->d_sb->s_user_ns); break; case FS_CONTEXT_FOR_RECONFIGURE: atomic_inc(&reference->d_sb->s_active); fc->user_ns = get_user_ns(reference->d_sb->s_user_ns); fc->root = dget(reference); break; } /* TODO: Make all filesystems support this unconditionally */ init_fs_context = fc->fs_type->init_fs_context; if (!init_fs_context) init_fs_context = legacy_init_fs_context; ret = init_fs_context(fc); if (ret < 0) goto err_fc; fc->need_free = true; return fc; err_fc: put_fs_context(fc); return ERR_PTR(ret); } struct fs_context *fs_context_for_mount(struct file_system_type *fs_type, unsigned int sb_flags) { return alloc_fs_context(fs_type, NULL, sb_flags, 0, FS_CONTEXT_FOR_MOUNT); } EXPORT_SYMBOL(fs_context_for_mount); struct fs_context *fs_context_for_reconfigure(struct dentry *dentry, unsigned int sb_flags, unsigned int sb_flags_mask) { return alloc_fs_context(dentry->d_sb->s_type, dentry, sb_flags, sb_flags_mask, FS_CONTEXT_FOR_RECONFIGURE); } EXPORT_SYMBOL(fs_context_for_reconfigure); /** * fs_context_for_submount: allocate a new fs_context for a submount * @type: file_system_type of the new context * @reference: reference dentry from which to copy relevant info * * Allocate a new fs_context suitable for a submount. This also ensures that * the fc->security object is inherited from @reference (if needed). */ struct fs_context *fs_context_for_submount(struct file_system_type *type, struct dentry *reference) { struct fs_context *fc; int ret; fc = alloc_fs_context(type, reference, 0, 0, FS_CONTEXT_FOR_SUBMOUNT); if (IS_ERR(fc)) return fc; ret = security_fs_context_submount(fc, reference->d_sb); if (ret) { put_fs_context(fc); return ERR_PTR(ret); } return fc; } EXPORT_SYMBOL(fs_context_for_submount); void fc_drop_locked(struct fs_context *fc) { struct super_block *sb = fc->root->d_sb; dput(fc->root); fc->root = NULL; deactivate_locked_super(sb); } static void legacy_fs_context_free(struct fs_context *fc); /** * vfs_dup_fs_context - Duplicate a filesystem context. * @src_fc: The context to copy. */ struct fs_context *vfs_dup_fs_context(struct fs_context *src_fc) { struct fs_context *fc; int ret; if (!src_fc->ops->dup) return ERR_PTR(-EOPNOTSUPP); fc = kmemdup(src_fc, sizeof(struct fs_context), GFP_KERNEL); if (!fc) return ERR_PTR(-ENOMEM); mutex_init(&fc->uapi_mutex); fc->fs_private = NULL; fc->s_fs_info = NULL; fc->source = NULL; fc->security = NULL; get_filesystem(fc->fs_type); get_net(fc->net_ns); get_user_ns(fc->user_ns); get_cred(fc->cred); if (fc->log.log) refcount_inc(&fc->log.log->usage); /* Can't call put until we've called ->dup */ ret = fc->ops->dup(fc, src_fc); if (ret < 0) goto err_fc; ret = security_fs_context_dup(fc, src_fc); if (ret < 0) goto err_fc; return fc; err_fc: put_fs_context(fc); return ERR_PTR(ret); } EXPORT_SYMBOL(vfs_dup_fs_context); /** * logfc - Log a message to a filesystem context * @log: The filesystem context to log to, or NULL to use printk. * @prefix: A string to prefix the output with, or NULL. * @level: 'w' for a warning, 'e' for an error. Anything else is a notice. * @fmt: The format of the buffer. */ void logfc(struct fc_log *log, const char *prefix, char level, const char *fmt, ...) { va_list va; struct va_format vaf = {.fmt = fmt, .va = &va}; va_start(va, fmt); if (!log) { switch (level) { case 'w': printk(KERN_WARNING "%s%s%pV\n", prefix ? prefix : "", prefix ? ": " : "", &vaf); break; case 'e': printk(KERN_ERR "%s%s%pV\n", prefix ? prefix : "", prefix ? ": " : "", &vaf); break; default: printk(KERN_NOTICE "%s%s%pV\n", prefix ? prefix : "", prefix ? ": " : "", &vaf); break; } } else { unsigned int logsize = ARRAY_SIZE(log->buffer); u8 index; char *q = kasprintf(GFP_KERNEL, "%c %s%s%pV\n", level, prefix ? prefix : "", prefix ? ": " : "", &vaf); index = log->head & (logsize - 1); BUILD_BUG_ON(sizeof(log->head) != sizeof(u8) || sizeof(log->tail) != sizeof(u8)); if ((u8)(log->head - log->tail) == logsize) { /* The buffer is full, discard the oldest message */ if (log->need_free & (1 << index)) kfree(log->buffer[index]); log->tail++; } log->buffer[index] = q ? q : "OOM: Can't store error string"; if (q) log->need_free |= 1 << index; else log->need_free &= ~(1 << index); log->head++; } va_end(va); } EXPORT_SYMBOL(logfc); /* * Free a logging structure. */ static void put_fc_log(struct fs_context *fc) { struct fc_log *log = fc->log.log; int i; if (log) { if (refcount_dec_and_test(&log->usage)) { fc->log.log = NULL; for (i = 0; i < ARRAY_SIZE(log->buffer) ; i++) if (log->need_free & (1 << i)) kfree(log->buffer[i]); kfree(log); } } } /** * put_fs_context - Dispose of a superblock configuration context. * @fc: The context to dispose of. */ void put_fs_context(struct fs_context *fc) { struct super_block *sb; if (fc->root) { sb = fc->root->d_sb; dput(fc->root); fc->root = NULL; deactivate_super(sb); } if (fc->need_free && fc->ops && fc->ops->free) fc->ops->free(fc); security_free_mnt_opts(&fc->security); put_net(fc->net_ns); put_user_ns(fc->user_ns); put_cred(fc->cred); put_fc_log(fc); put_filesystem(fc->fs_type); kfree(fc->source); kfree(fc); } EXPORT_SYMBOL(put_fs_context); /* * Free the config for a filesystem that doesn't support fs_context. */ static void legacy_fs_context_free(struct fs_context *fc) { struct legacy_fs_context *ctx = fc->fs_private; if (ctx) { if (ctx->param_type == LEGACY_FS_INDIVIDUAL_PARAMS) kfree(ctx->legacy_data); kfree(ctx); } } /* * Duplicate a legacy config. */ static int legacy_fs_context_dup(struct fs_context *fc, struct fs_context *src_fc) { struct legacy_fs_context *ctx; struct legacy_fs_context *src_ctx = src_fc->fs_private; ctx = kmemdup(src_ctx, sizeof(*src_ctx), GFP_KERNEL); if (!ctx) return -ENOMEM; if (ctx->param_type == LEGACY_FS_INDIVIDUAL_PARAMS) { ctx->legacy_data = kmemdup(src_ctx->legacy_data, src_ctx->data_size, GFP_KERNEL); if (!ctx->legacy_data) { kfree(ctx); return -ENOMEM; } } fc->fs_private = ctx; return 0; } /* * Add a parameter to a legacy config. We build up a comma-separated list of * options. */ static int legacy_parse_param(struct fs_context *fc, struct fs_parameter *param) { struct legacy_fs_context *ctx = fc->fs_private; unsigned int size = ctx->data_size; size_t len = 0; int ret; ret = vfs_parse_fs_param_source(fc, param); if (ret != -ENOPARAM) return ret; if (ctx->param_type == LEGACY_FS_MONOLITHIC_PARAMS) return invalf(fc, "VFS: Legacy: Can't mix monolithic and individual options"); switch (param->type) { case fs_value_is_string: len = 1 + param->size; fallthrough; case fs_value_is_flag: len += strlen(param->key); break; default: return invalf(fc, "VFS: Legacy: Parameter type for '%s' not supported", param->key); } if (size + len + 2 > PAGE_SIZE) return invalf(fc, "VFS: Legacy: Cumulative options too large"); if (strchr(param->key, ',') || (param->type == fs_value_is_string && memchr(param->string, ',', param->size))) return invalf(fc, "VFS: Legacy: Option '%s' contained comma", param->key); if (!ctx->legacy_data) { ctx->legacy_data = kmalloc(PAGE_SIZE, GFP_KERNEL); if (!ctx->legacy_data) return -ENOMEM; } if (size) ctx->legacy_data[size++] = ','; len = strlen(param->key); memcpy(ctx->legacy_data + size, param->key, len); size += len; if (param->type == fs_value_is_string) { ctx->legacy_data[size++] = '='; memcpy(ctx->legacy_data + size, param->string, param->size); size += param->size; } ctx->legacy_data[size] = '\0'; ctx->data_size = size; ctx->param_type = LEGACY_FS_INDIVIDUAL_PARAMS; return 0; } /* * Add monolithic mount data. */ static int legacy_parse_monolithic(struct fs_context *fc, void *data) { struct legacy_fs_context *ctx = fc->fs_private; if (ctx->param_type != LEGACY_FS_UNSET_PARAMS) { pr_warn("VFS: Can't mix monolithic and individual options\n"); return -EINVAL; } ctx->legacy_data = data; ctx->param_type = LEGACY_FS_MONOLITHIC_PARAMS; if (!ctx->legacy_data) return 0; if (fc->fs_type->fs_flags & FS_BINARY_MOUNTDATA) return 0; return security_sb_eat_lsm_opts(ctx->legacy_data, &fc->security); } /* * Get a mountable root with the legacy mount command. */ static int legacy_get_tree(struct fs_context *fc) { struct legacy_fs_context *ctx = fc->fs_private; struct super_block *sb; struct dentry *root; root = fc->fs_type->mount(fc->fs_type, fc->sb_flags, fc->source, ctx->legacy_data); if (IS_ERR(root)) return PTR_ERR(root); sb = root->d_sb; BUG_ON(!sb); fc->root = root; return 0; } /* * Handle remount. */ static int legacy_reconfigure(struct fs_context *fc) { struct legacy_fs_context *ctx = fc->fs_private; struct super_block *sb = fc->root->d_sb; if (!sb->s_op->remount_fs) return 0; return sb->s_op->remount_fs(sb, &fc->sb_flags, ctx ? ctx->legacy_data : NULL); } const struct fs_context_operations legacy_fs_context_ops = { .free = legacy_fs_context_free, .dup = legacy_fs_context_dup, .parse_param = legacy_parse_param, .parse_monolithic = legacy_parse_monolithic, .get_tree = legacy_get_tree, .reconfigure = legacy_reconfigure, }; /* * Initialise a legacy context for a filesystem that doesn't support * fs_context. */ static int legacy_init_fs_context(struct fs_context *fc) { fc->fs_private = kzalloc(sizeof(struct legacy_fs_context), GFP_KERNEL_ACCOUNT); if (!fc->fs_private) return -ENOMEM; fc->ops = &legacy_fs_context_ops; return 0; } int parse_monolithic_mount_data(struct fs_context *fc, void *data) { int (*monolithic_mount_data)(struct fs_context *, void *); monolithic_mount_data = fc->ops->parse_monolithic; if (!monolithic_mount_data) monolithic_mount_data = generic_parse_monolithic; return monolithic_mount_data(fc, data); } /* * Clean up a context after performing an action on it and put it into a state * from where it can be used to reconfigure a superblock. * * Note that here we do only the parts that can't fail; the rest is in * finish_clean_context() below and in between those fs_context is marked * FS_CONTEXT_AWAITING_RECONF. The reason for splitup is that after * successful mount or remount we need to report success to userland. * Trying to do full reinit (for the sake of possible subsequent remount) * and failing to allocate memory would've put us into a nasty situation. * So here we only discard the old state and reinitialization is left * until we actually try to reconfigure. */ void vfs_clean_context(struct fs_context *fc) { if (fc->need_free && fc->ops && fc->ops->free) fc->ops->free(fc); fc->need_free = false; fc->fs_private = NULL; fc->s_fs_info = NULL; fc->sb_flags = 0; security_free_mnt_opts(&fc->security); kfree(fc->source); fc->source = NULL; fc->exclusive = false; fc->purpose = FS_CONTEXT_FOR_RECONFIGURE; fc->phase = FS_CONTEXT_AWAITING_RECONF; } int finish_clean_context(struct fs_context *fc) { int error; if (fc->phase != FS_CONTEXT_AWAITING_RECONF) return 0; if (fc->fs_type->init_fs_context) error = fc->fs_type->init_fs_context(fc); else error = legacy_init_fs_context(fc); if (unlikely(error)) { fc->phase = FS_CONTEXT_FAILED; return error; } fc->need_free = true; fc->phase = FS_CONTEXT_RECONF_PARAMS; return 0; } |
| 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 | // SPDX-License-Identifier: GPL-2.0-or-later /* Socket buffer accounting * * Copyright (C) 2007 Red Hat, Inc. All Rights Reserved. * Written by David Howells (dhowells@redhat.com) */ #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt #include <linux/module.h> #include <linux/net.h> #include <linux/skbuff.h> #include <net/sock.h> #include <net/af_rxrpc.h> #include "ar-internal.h" #define select_skb_count(skb) (&rxrpc_n_rx_skbs) /* * Note the allocation or reception of a socket buffer. */ void rxrpc_new_skb(struct sk_buff *skb, enum rxrpc_skb_trace why) { int n = atomic_inc_return(select_skb_count(skb)); trace_rxrpc_skb(skb, refcount_read(&skb->users), n, why); } /* * Note the re-emergence of a socket buffer from a queue or buffer. */ void rxrpc_see_skb(struct sk_buff *skb, enum rxrpc_skb_trace why) { if (skb) { int n = atomic_read(select_skb_count(skb)); trace_rxrpc_skb(skb, refcount_read(&skb->users), n, why); } } /* * Note the addition of a ref on a socket buffer. */ void rxrpc_get_skb(struct sk_buff *skb, enum rxrpc_skb_trace why) { int n = atomic_inc_return(select_skb_count(skb)); trace_rxrpc_skb(skb, refcount_read(&skb->users), n, why); skb_get(skb); } /* * Note the dropping of a ref on a socket buffer by the core. */ void rxrpc_eaten_skb(struct sk_buff *skb, enum rxrpc_skb_trace why) { int n = atomic_inc_return(&rxrpc_n_rx_skbs); trace_rxrpc_skb(skb, 0, n, why); } /* * Note the destruction of a socket buffer. */ void rxrpc_free_skb(struct sk_buff *skb, enum rxrpc_skb_trace why) { if (skb) { int n = atomic_dec_return(select_skb_count(skb)); trace_rxrpc_skb(skb, refcount_read(&skb->users), n, why); consume_skb(skb); } } /* * Clear a queue of socket buffers. */ void rxrpc_purge_queue(struct sk_buff_head *list) { struct sk_buff *skb; while ((skb = skb_dequeue((list))) != NULL) { int n = atomic_dec_return(select_skb_count(skb)); trace_rxrpc_skb(skb, refcount_read(&skb->users), n, rxrpc_skb_put_purge); consume_skb(skb); } } |
| 4 1 3 3 1 6 6 5 4 2 5 5 19 19 | 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 | // SPDX-License-Identifier: GPL-2.0 /* * Shared Memory Communications over RDMA (SMC-R) and RoCE * * Basic Transport Functions exploiting Infiniband API * * Copyright IBM Corp. 2016 * * Author(s): Ursula Braun <ubraun@linux.vnet.ibm.com> */ #include <linux/socket.h> #include <linux/if_vlan.h> #include <linux/random.h> #include <linux/workqueue.h> #include <linux/wait.h> #include <linux/reboot.h> #include <linux/mutex.h> #include <linux/list.h> #include <linux/smc.h> #include <net/tcp.h> #include <net/sock.h> #include <rdma/ib_verbs.h> #include <rdma/ib_cache.h> #include "smc.h" #include "smc_clc.h" #include "smc_core.h" #include "smc_ib.h" #include "smc_wr.h" #include "smc_llc.h" #include "smc_cdc.h" #include "smc_close.h" #include "smc_ism.h" #include "smc_netlink.h" #include "smc_stats.h" #include "smc_tracepoint.h" #define SMC_LGR_NUM_INCR 256 #define SMC_LGR_FREE_DELAY_SERV (600 * HZ) #define SMC_LGR_FREE_DELAY_CLNT (SMC_LGR_FREE_DELAY_SERV + 10 * HZ) struct smc_lgr_list smc_lgr_list = { /* established link groups */ .lock = __SPIN_LOCK_UNLOCKED(smc_lgr_list.lock), .list = LIST_HEAD_INIT(smc_lgr_list.list), .num = 0, }; static atomic_t lgr_cnt = ATOMIC_INIT(0); /* number of existing link groups */ static DECLARE_WAIT_QUEUE_HEAD(lgrs_deleted); static void smc_buf_free(struct smc_link_group *lgr, bool is_rmb, struct smc_buf_desc *buf_desc); static void __smc_lgr_terminate(struct smc_link_group *lgr, bool soft); static void smc_link_down_work(struct work_struct *work); /* return head of link group list and its lock for a given link group */ static inline struct list_head *smc_lgr_list_head(struct smc_link_group *lgr, spinlock_t **lgr_lock) { if (lgr->is_smcd) { *lgr_lock = &lgr->smcd->lgr_lock; return &lgr->smcd->lgr_list; } *lgr_lock = &smc_lgr_list.lock; return &smc_lgr_list.list; } static void smc_ibdev_cnt_inc(struct smc_link *lnk) { atomic_inc(&lnk->smcibdev->lnk_cnt_by_port[lnk->ibport - 1]); } static void smc_ibdev_cnt_dec(struct smc_link *lnk) { atomic_dec(&lnk->smcibdev->lnk_cnt_by_port[lnk->ibport - 1]); } static void smc_lgr_schedule_free_work(struct smc_link_group *lgr) { /* client link group creation always follows the server link group * creation. For client use a somewhat higher removal delay time, * otherwise there is a risk of out-of-sync link groups. */ if (!lgr->freeing) { mod_delayed_work(system_wq, &lgr->free_work, (!lgr->is_smcd && lgr->role == SMC_CLNT) ? SMC_LGR_FREE_DELAY_CLNT : SMC_LGR_FREE_DELAY_SERV); } } /* Register connection's alert token in our lookup structure. * To use rbtrees we have to implement our own insert core. * Requires @conns_lock * @smc connection to register * Returns 0 on success, != otherwise. */ static void smc_lgr_add_alert_token(struct smc_connection *conn) { struct rb_node **link, *parent = NULL; u32 token = conn->alert_token_local; link = &conn->lgr->conns_all.rb_node; while (*link) { struct smc_connection *cur = rb_entry(*link, struct smc_connection, alert_node); parent = *link; if (cur->alert_token_local > token) link = &parent->rb_left; else link = &parent->rb_right; } /* Put the new node there */ rb_link_node(&conn->alert_node, parent, link); rb_insert_color(&conn->alert_node, &conn->lgr->conns_all); } /* assign an SMC-R link to the connection */ static int smcr_lgr_conn_assign_link(struct smc_connection *conn, bool first) { enum smc_link_state expected = first ? SMC_LNK_ACTIVATING : SMC_LNK_ACTIVE; int i, j; /* do link balancing */ conn->lnk = NULL; /* reset conn->lnk first */ for (i = 0; i < SMC_LINKS_PER_LGR_MAX; i++) { struct smc_link *lnk = &conn->lgr->lnk[i]; if (lnk->state != expected || lnk->link_is_asym) continue; if (conn->lgr->role == SMC_CLNT) { conn->lnk = lnk; /* temporary, SMC server assigns link*/ break; } if (conn->lgr->conns_num % 2) { for (j = i + 1; j < SMC_LINKS_PER_LGR_MAX; j++) { struct smc_link *lnk2; lnk2 = &conn->lgr->lnk[j]; if (lnk2->state == expected && !lnk2->link_is_asym) { conn->lnk = lnk2; break; } } } if (!conn->lnk) conn->lnk = lnk; break; } if (!conn->lnk) return SMC_CLC_DECL_NOACTLINK; atomic_inc(&conn->lnk->conn_cnt); return 0; } /* Register connection in link group by assigning an alert token * registered in a search tree. * Requires @conns_lock * Note that '0' is a reserved value and not assigned. */ static int smc_lgr_register_conn(struct smc_connection *conn, bool first) { struct smc_sock *smc = container_of(conn, struct smc_sock, conn); static atomic_t nexttoken = ATOMIC_INIT(0); int rc; if (!conn->lgr->is_smcd) { rc = smcr_lgr_conn_assign_link(conn, first); if (rc) { conn->lgr = NULL; return rc; } } /* find a new alert_token_local value not yet used by some connection * in this link group */ sock_hold(&smc->sk); /* sock_put in smc_lgr_unregister_conn() */ while (!conn->alert_token_local) { conn->alert_token_local = atomic_inc_return(&nexttoken); if (smc_lgr_find_conn(conn->alert_token_local, conn->lgr)) conn->alert_token_local = 0; } smc_lgr_add_alert_token(conn); conn->lgr->conns_num++; return 0; } /* Unregister connection and reset the alert token of the given connection< */ static void __smc_lgr_unregister_conn(struct smc_connection *conn) { struct smc_sock *smc = container_of(conn, struct smc_sock, conn); struct smc_link_group *lgr = conn->lgr; rb_erase(&conn->alert_node, &lgr->conns_all); if (conn->lnk) atomic_dec(&conn->lnk->conn_cnt); lgr->conns_num--; conn->alert_token_local = 0; sock_put(&smc->sk); /* sock_hold in smc_lgr_register_conn() */ } /* Unregister connection from lgr */ static void smc_lgr_unregister_conn(struct smc_connection *conn) { struct smc_link_group *lgr = conn->lgr; if (!smc_conn_lgr_valid(conn)) return; write_lock_bh(&lgr->conns_lock); if (conn->alert_token_local) { __smc_lgr_unregister_conn(conn); } write_unlock_bh(&lgr->conns_lock); } static void smc_lgr_buf_list_add(struct smc_link_group *lgr, bool is_rmb, struct list_head *buf_list, struct smc_buf_desc *buf_desc) { list_add(&buf_desc->list, buf_list); if (is_rmb) { lgr->alloc_rmbs += buf_desc->len; lgr->alloc_rmbs += lgr->is_smcd ? sizeof(struct smcd_cdc_msg) : 0; } else { lgr->alloc_sndbufs += buf_desc->len; } } static void smc_lgr_buf_list_del(struct smc_link_group *lgr, bool is_rmb, struct smc_buf_desc *buf_desc) { list_del(&buf_desc->list); if (is_rmb) { lgr->alloc_rmbs -= buf_desc->len; lgr->alloc_rmbs -= lgr->is_smcd ? sizeof(struct smcd_cdc_msg) : 0; } else { lgr->alloc_sndbufs -= buf_desc->len; } } int smc_nl_get_sys_info(struct sk_buff *skb, struct netlink_callback *cb) { struct smc_nl_dmp_ctx *cb_ctx = smc_nl_dmp_ctx(cb); char hostname[SMC_MAX_HOSTNAME_LEN + 1]; char smc_seid[SMC_MAX_EID_LEN + 1]; struct nlattr *attrs; u8 *seid = NULL; u8 *host = NULL; void *nlh; nlh = genlmsg_put(skb, NETLINK_CB(cb->skb).portid, cb->nlh->nlmsg_seq, &smc_gen_nl_family, NLM_F_MULTI, SMC_NETLINK_GET_SYS_INFO); if (!nlh) goto errmsg; if (cb_ctx->pos[0]) goto errout; attrs = nla_nest_start(skb, SMC_GEN_SYS_INFO); if (!attrs) goto errout; if (nla_put_u8(skb, SMC_NLA_SYS_VER, SMC_V2)) goto errattr; if (nla_put_u8(skb, SMC_NLA_SYS_REL, SMC_RELEASE)) goto errattr; if (nla_put_u8(skb, SMC_NLA_SYS_IS_ISM_V2, smc_ism_is_v2_capable())) goto errattr; if (nla_put_u8(skb, SMC_NLA_SYS_IS_SMCR_V2, true)) goto errattr; smc_clc_get_hostname(&host); if (host) { memcpy(hostname, host, SMC_MAX_HOSTNAME_LEN); hostname[SMC_MAX_HOSTNAME_LEN] = 0; if (nla_put_string(skb, SMC_NLA_SYS_LOCAL_HOST, hostname)) goto errattr; } if (smc_ism_is_v2_capable()) { smc_ism_get_system_eid(&seid); memcpy(smc_seid, seid, SMC_MAX_EID_LEN); smc_seid[SMC_MAX_EID_LEN] = 0; if (nla_put_string(skb, SMC_NLA_SYS_SEID, smc_seid)) goto errattr; } nla_nest_end(skb, attrs); genlmsg_end(skb, nlh); cb_ctx->pos[0] = 1; return skb->len; errattr: nla_nest_cancel(skb, attrs); errout: genlmsg_cancel(skb, nlh); errmsg: return skb->len; } /* Fill SMC_NLA_LGR_D_V2_COMMON/SMC_NLA_LGR_R_V2_COMMON nested attributes */ static int smc_nl_fill_lgr_v2_common(struct smc_link_group *lgr, struct sk_buff *skb, struct netlink_callback *cb, struct nlattr *v2_attrs) { char smc_host[SMC_MAX_HOSTNAME_LEN + 1]; char smc_eid[SMC_MAX_EID_LEN + 1]; if (nla_put_u8(skb, SMC_NLA_LGR_V2_VER, lgr->smc_version)) goto errv2attr; if (nla_put_u8(skb, SMC_NLA_LGR_V2_REL, lgr->peer_smc_release)) goto errv2attr; if (nla_put_u8(skb, SMC_NLA_LGR_V2_OS, lgr->peer_os)) goto errv2attr; memcpy(smc_host, lgr->peer_hostname, SMC_MAX_HOSTNAME_LEN); smc_host[SMC_MAX_HOSTNAME_LEN] = 0; if (nla_put_string(skb, SMC_NLA_LGR_V2_PEER_HOST, smc_host)) goto errv2attr; memcpy(smc_eid, lgr->negotiated_eid, SMC_MAX_EID_LEN); smc_eid[SMC_MAX_EID_LEN] = 0; if (nla_put_string(skb, SMC_NLA_LGR_V2_NEG_EID, smc_eid)) goto errv2attr; nla_nest_end(skb, v2_attrs); return 0; errv2attr: nla_nest_cancel(skb, v2_attrs); return -EMSGSIZE; } static int smc_nl_fill_smcr_lgr_v2(struct smc_link_group *lgr, struct sk_buff *skb, struct netlink_callback *cb) { struct nlattr *v2_attrs; v2_attrs = nla_nest_start(skb, SMC_NLA_LGR_R_V2); if (!v2_attrs) goto errattr; if (nla_put_u8(skb, SMC_NLA_LGR_R_V2_DIRECT, !lgr->uses_gateway)) goto errv2attr; if (nla_put_u8(skb, SMC_NLA_LGR_R_V2_MAX_CONNS, lgr->max_conns)) goto errv2attr; if (nla_put_u8(skb, SMC_NLA_LGR_R_V2_MAX_LINKS, lgr->max_links)) goto errv2attr; nla_nest_end(skb, v2_attrs); return 0; errv2attr: nla_nest_cancel(skb, v2_attrs); errattr: return -EMSGSIZE; } static int smc_nl_fill_lgr(struct smc_link_group *lgr, struct sk_buff *skb, struct netlink_callback *cb) { char smc_target[SMC_MAX_PNETID_LEN + 1]; struct nlattr *attrs, *v2_attrs; attrs = nla_nest_start(skb, SMC_GEN_LGR_SMCR); if (!attrs) goto errout; if (nla_put_u32(skb, SMC_NLA_LGR_R_ID, *((u32 *)&lgr->id))) goto errattr; if (nla_put_u32(skb, SMC_NLA_LGR_R_CONNS_NUM, lgr->conns_num)) goto errattr; if (nla_put_u8(skb, SMC_NLA_LGR_R_ROLE, lgr->role)) goto errattr; if (nla_put_u8(skb, SMC_NLA_LGR_R_TYPE, lgr->type)) goto errattr; if (nla_put_u8(skb, SMC_NLA_LGR_R_BUF_TYPE, lgr->buf_type)) goto errattr; if (nla_put_u8(skb, SMC_NLA_LGR_R_VLAN_ID, lgr->vlan_id)) goto errattr; if (nla_put_u64_64bit(skb, SMC_NLA_LGR_R_NET_COOKIE, lgr->net->net_cookie, SMC_NLA_LGR_R_PAD)) goto errattr; memcpy(smc_target, lgr->pnet_id, SMC_MAX_PNETID_LEN); smc_target[SMC_MAX_PNETID_LEN] = 0; if (nla_put_string(skb, SMC_NLA_LGR_R_PNETID, smc_target)) goto errattr; if (nla_put_uint(skb, SMC_NLA_LGR_R_SNDBUF_ALLOC, lgr->alloc_sndbufs)) goto errattr; if (nla_put_uint(skb, SMC_NLA_LGR_R_RMB_ALLOC, lgr->alloc_rmbs)) goto errattr; if (lgr->smc_version > SMC_V1) { v2_attrs = nla_nest_start(skb, SMC_NLA_LGR_R_V2_COMMON); if (!v2_attrs) goto errattr; if (smc_nl_fill_lgr_v2_common(lgr, skb, cb, v2_attrs)) goto errattr; if (smc_nl_fill_smcr_lgr_v2(lgr, skb, cb)) goto errattr; } nla_nest_end(skb, attrs); return 0; errattr: nla_nest_cancel(skb, attrs); errout: return -EMSGSIZE; } static int smc_nl_fill_lgr_link(struct smc_link_group *lgr, struct smc_link *link, struct sk_buff *skb, struct netlink_callback *cb) { char smc_ibname[IB_DEVICE_NAME_MAX]; u8 smc_gid_target[41]; struct nlattr *attrs; u32 link_uid = 0; void *nlh; nlh = genlmsg_put(skb, NETLINK_CB(cb->skb).portid, cb->nlh->nlmsg_seq, &smc_gen_nl_family, NLM_F_MULTI, SMC_NETLINK_GET_LINK_SMCR); if (!nlh) goto errmsg; attrs = nla_nest_start(skb, SMC_GEN_LINK_SMCR); if (!attrs) goto errout; if (nla_put_u8(skb, SMC_NLA_LINK_ID, link->link_id)) goto errattr; if (nla_put_u32(skb, SMC_NLA_LINK_STATE, link->state)) goto errattr; if (nla_put_u32(skb, SMC_NLA_LINK_CONN_CNT, atomic_read(&link->conn_cnt))) goto errattr; if (nla_put_u8(skb, SMC_NLA_LINK_IB_PORT, link->ibport)) goto errattr; if (nla_put_u32(skb, SMC_NLA_LINK_NET_DEV, link->ndev_ifidx)) goto errattr; snprintf(smc_ibname, sizeof(smc_ibname), "%s", link->ibname); if (nla_put_string(skb, SMC_NLA_LINK_IB_DEV, smc_ibname)) goto errattr; memcpy(&link_uid, link->link_uid, sizeof(link_uid)); if (nla_put_u32(skb, SMC_NLA_LINK_UID, link_uid)) goto errattr; memcpy(&link_uid, link->peer_link_uid, sizeof(link_uid)); if (nla_put_u32(skb, SMC_NLA_LINK_PEER_UID, link_uid)) goto errattr; memset(smc_gid_target, 0, sizeof(smc_gid_target)); smc_gid_be16_convert(smc_gid_target, link->gid); if (nla_put_string(skb, SMC_NLA_LINK_GID, smc_gid_target)) goto errattr; memset(smc_gid_target, 0, sizeof(smc_gid_target)); smc_gid_be16_convert(smc_gid_target, link->peer_gid); if (nla_put_string(skb, SMC_NLA_LINK_PEER_GID, smc_gid_target)) goto errattr; nla_nest_end(skb, attrs); genlmsg_end(skb, nlh); return 0; errattr: nla_nest_cancel(skb, attrs); errout: genlmsg_cancel(skb, nlh); errmsg: return -EMSGSIZE; } static int smc_nl_handle_lgr(struct smc_link_group *lgr, struct sk_buff *skb, struct netlink_callback *cb, bool list_links) { void *nlh; int i; nlh = genlmsg_put(skb, NETLINK_CB(cb->skb).portid, cb->nlh->nlmsg_seq, &smc_gen_nl_family, NLM_F_MULTI, SMC_NETLINK_GET_LGR_SMCR); if (!nlh) goto errmsg; if (smc_nl_fill_lgr(lgr, skb, cb)) goto errout; genlmsg_end(skb, nlh); if (!list_links) goto out; for (i = 0; i < SMC_LINKS_PER_LGR_MAX; i++) { if (!smc_link_usable(&lgr->lnk[i])) continue; if (smc_nl_fill_lgr_link(lgr, &lgr->lnk[i], skb, cb)) goto errout; } out: return 0; errout: genlmsg_cancel(skb, nlh); errmsg: return -EMSGSIZE; } static void smc_nl_fill_lgr_list(struct smc_lgr_list *smc_lgr, struct sk_buff *skb, struct netlink_callback *cb, bool list_links) { struct smc_nl_dmp_ctx *cb_ctx = smc_nl_dmp_ctx(cb); struct smc_link_group *lgr; int snum = cb_ctx->pos[0]; int num = 0; spin_lock_bh(&smc_lgr->lock); list_for_each_entry(lgr, &smc_lgr->list, list) { if (num < snum) goto next; if (smc_nl_handle_lgr(lgr, skb, cb, list_links)) goto errout; next: num++; } errout: spin_unlock_bh(&smc_lgr->lock); cb_ctx->pos[0] = num; } static int smc_nl_fill_smcd_lgr(struct smc_link_group *lgr, struct sk_buff *skb, struct netlink_callback *cb) { char smc_pnet[SMC_MAX_PNETID_LEN + 1]; struct smcd_dev *smcd = lgr->smcd; struct smcd_gid smcd_gid; struct nlattr *attrs; void *nlh; nlh = genlmsg_put(skb, NETLINK_CB(cb->skb).portid, cb->nlh->nlmsg_seq, &smc_gen_nl_family, NLM_F_MULTI, SMC_NETLINK_GET_LGR_SMCD); if (!nlh) goto errmsg; attrs = nla_nest_start(skb, SMC_GEN_LGR_SMCD); if (!attrs) goto errout; if (nla_put_u32(skb, SMC_NLA_LGR_D_ID, *((u32 *)&lgr->id))) goto errattr; smcd->ops->get_local_gid(smcd, &smcd_gid); if (nla_put_u64_64bit(skb, SMC_NLA_LGR_D_GID, smcd_gid.gid, SMC_NLA_LGR_D_PAD)) goto errattr; if (nla_put_u64_64bit(skb, SMC_NLA_LGR_D_EXT_GID, smcd_gid.gid_ext, SMC_NLA_LGR_D_PAD)) goto errattr; if (nla_put_u64_64bit(skb, SMC_NLA_LGR_D_PEER_GID, lgr->peer_gid.gid, SMC_NLA_LGR_D_PAD)) goto errattr; if (nla_put_u64_64bit(skb, SMC_NLA_LGR_D_PEER_EXT_GID, lgr->peer_gid.gid_ext, SMC_NLA_LGR_D_PAD)) goto errattr; if (nla_put_u8(skb, SMC_NLA_LGR_D_VLAN_ID, lgr->vlan_id)) goto errattr; if (nla_put_u32(skb, SMC_NLA_LGR_D_CONNS_NUM, lgr->conns_num)) goto errattr; if (nla_put_u32(skb, SMC_NLA_LGR_D_CHID, smc_ism_get_chid(lgr->smcd))) goto errattr; if (nla_put_uint(skb, SMC_NLA_LGR_D_SNDBUF_ALLOC, lgr->alloc_sndbufs)) goto errattr; if (nla_put_uint(skb, SMC_NLA_LGR_D_DMB_ALLOC, lgr->alloc_rmbs)) goto errattr; memcpy(smc_pnet, lgr->smcd->pnetid, SMC_MAX_PNETID_LEN); smc_pnet[SMC_MAX_PNETID_LEN] = 0; if (nla_put_string(skb, SMC_NLA_LGR_D_PNETID, smc_pnet)) goto errattr; if (lgr->smc_version > SMC_V1) { struct nlattr *v2_attrs; v2_attrs = nla_nest_start(skb, SMC_NLA_LGR_D_V2_COMMON); if (!v2_attrs) goto errattr; if (smc_nl_fill_lgr_v2_common(lgr, skb, cb, v2_attrs)) goto errattr; } nla_nest_end(skb, attrs); genlmsg_end(skb, nlh); return 0; errattr: nla_nest_cancel(skb, attrs); errout: genlmsg_cancel(skb, nlh); errmsg: return -EMSGSIZE; } static int smc_nl_handle_smcd_lgr(struct smcd_dev *dev, struct sk_buff *skb, struct netlink_callback *cb) { struct smc_nl_dmp_ctx *cb_ctx = smc_nl_dmp_ctx(cb); struct smc_link_group *lgr; int snum = cb_ctx->pos[1]; int rc = 0, num = 0; spin_lock_bh(&dev->lgr_lock); list_for_each_entry(lgr, &dev->lgr_list, list) { if (!lgr->is_smcd) continue; if (num < snum) goto next; rc = smc_nl_fill_smcd_lgr(lgr, skb, cb); if (rc) goto errout; next: num++; } errout: spin_unlock_bh(&dev->lgr_lock); cb_ctx->pos[1] = num; return rc; } static int smc_nl_fill_smcd_dev(struct smcd_dev_list *dev_list, struct sk_buff *skb, struct netlink_callback *cb) { struct smc_nl_dmp_ctx *cb_ctx = smc_nl_dmp_ctx(cb); struct smcd_dev *smcd_dev; int snum = cb_ctx->pos[0]; int rc = 0, num = 0; mutex_lock(&dev_list->mutex); list_for_each_entry(smcd_dev, &dev_list->list, list) { if (list_empty(&smcd_dev->lgr_list)) continue; if (num < snum) goto next; rc = smc_nl_handle_smcd_lgr(smcd_dev, skb, cb); if (rc) goto errout; next: num++; } errout: mutex_unlock(&dev_list->mutex); cb_ctx->pos[0] = num; return rc; } int smcr_nl_get_lgr(struct sk_buff *skb, struct netlink_callback *cb) { bool list_links = false; smc_nl_fill_lgr_list(&smc_lgr_list, skb, cb, list_links); return skb->len; } int smcr_nl_get_link(struct sk_buff *skb, struct netlink_callback *cb) { bool list_links = true; smc_nl_fill_lgr_list(&smc_lgr_list, skb, cb, list_links); return skb->len; } int smcd_nl_get_lgr(struct sk_buff *skb, struct netlink_callback *cb) { smc_nl_fill_smcd_dev(&smcd_dev_list, skb, cb); return skb->len; } void smc_lgr_cleanup_early(struct smc_link_group *lgr) { spinlock_t *lgr_lock; if (!lgr) return; smc_lgr_list_head(lgr, &lgr_lock); spin_lock_bh(lgr_lock); /* do not use this link group for new connections */ if (!list_empty(&lgr->list)) list_del_init(&lgr->list); spin_unlock_bh(lgr_lock); __smc_lgr_terminate(lgr, true); } static void smcr_lgr_link_deactivate_all(struct smc_link_group *lgr) { int i; for (i = 0; i < SMC_LINKS_PER_LGR_MAX; i++) { struct smc_link *lnk = &lgr->lnk[i]; if (smc_link_sendable(lnk)) lnk->state = SMC_LNK_INACTIVE; } wake_up_all(&lgr->llc_msg_waiter); wake_up_all(&lgr->llc_flow_waiter); } static void smc_lgr_free(struct smc_link_group *lgr); static void smc_lgr_free_work(struct work_struct *work) { struct smc_link_group *lgr = container_of(to_delayed_work(work), struct smc_link_group, free_work); spinlock_t *lgr_lock; bool conns; smc_lgr_list_head(lgr, &lgr_lock); spin_lock_bh(lgr_lock); if (lgr->freeing) { spin_unlock_bh(lgr_lock); return; } read_lock_bh(&lgr->conns_lock); conns = RB_EMPTY_ROOT(&lgr->conns_all); read_unlock_bh(&lgr->conns_lock); if (!conns) { /* number of lgr connections is no longer zero */ spin_unlock_bh(lgr_lock); return; } list_del_init(&lgr->list); /* remove from smc_lgr_list */ lgr->freeing = 1; /* this instance does the freeing, no new schedule */ spin_unlock_bh(lgr_lock); cancel_delayed_work(&lgr->free_work); if (!lgr->is_smcd && !lgr->terminating) smc_llc_send_link_delete_all(lgr, true, SMC_LLC_DEL_PROG_INIT_TERM); if (lgr->is_smcd && !lgr->terminating) smc_ism_signal_shutdown(lgr); if (!lgr->is_smcd) smcr_lgr_link_deactivate_all(lgr); smc_lgr_free(lgr); } static void smc_lgr_terminate_work(struct work_struct *work) { struct smc_link_group *lgr = container_of(work, struct smc_link_group, terminate_work); __smc_lgr_terminate(lgr, true); } /* return next unique link id for the lgr */ static u8 smcr_next_link_id(struct smc_link_group *lgr) { u8 link_id; int i; while (1) { again: link_id = ++lgr->next_link_id; if (!link_id) /* skip zero as link_id */ link_id = ++lgr->next_link_id; for (i = 0; i < SMC_LINKS_PER_LGR_MAX; i++) { if (smc_link_usable(&lgr->lnk[i]) && lgr->lnk[i].link_id == link_id) goto again; } break; } return link_id; } static void smcr_copy_dev_info_to_link(struct smc_link *link) { struct smc_ib_device *smcibdev = link->smcibdev; snprintf(link->ibname, sizeof(link->ibname), "%s", smcibdev->ibdev->name); link->ndev_ifidx = smcibdev->ndev_ifidx[link->ibport - 1]; } int smcr_link_init(struct smc_link_group *lgr, struct smc_link *lnk, u8 link_idx, struct smc_init_info *ini) { struct smc_ib_device *smcibdev; u8 rndvec[3]; int rc; if (lgr->smc_version == SMC_V2) { lnk->smcibdev = ini->smcrv2.ib_dev_v2; lnk->ibport = ini->smcrv2.ib_port_v2; lnk->wr_rx_sge_cnt = lnk->smcibdev->ibdev->attrs.max_recv_sge < 2 ? 1 : 2; lnk->wr_rx_buflen = smc_link_shared_v2_rxbuf(lnk) ? SMC_WR_BUF_SIZE : SMC_WR_BUF_V2_SIZE; } else { lnk->smcibdev = ini->ib_dev; lnk->ibport = ini->ib_port; lnk->wr_rx_sge_cnt = 1; lnk->wr_rx_buflen = SMC_WR_BUF_SIZE; } get_device(&lnk->smcibdev->ibdev->dev); atomic_inc(&lnk->smcibdev->lnk_cnt); refcount_set(&lnk->refcnt, 1); /* link refcnt is set to 1 */ lnk->clearing = 0; lnk->path_mtu = lnk->smcibdev->pattr[lnk->ibport - 1].active_mtu; lnk->link_id = smcr_next_link_id(lgr); lnk->lgr = lgr; smc_lgr_hold(lgr); /* lgr_put in smcr_link_clear() */ lnk->link_idx = link_idx; lnk->wr_rx_id_compl = 0; smc_ibdev_cnt_inc(lnk); smcr_copy_dev_info_to_link(lnk); atomic_set(&lnk->conn_cnt, 0); smc_llc_link_set_uid(lnk); INIT_WORK(&lnk->link_down_wrk, smc_link_down_work); if (!lnk->smcibdev->initialized) { rc = (int)smc_ib_setup_per_ibdev(lnk->smcibdev); if (rc) goto out; } get_random_bytes(rndvec, sizeof(rndvec)); lnk->psn_initial = rndvec[0] + (rndvec[1] << 8) + (rndvec[2] << 16); rc = smc_ib_determine_gid(lnk->smcibdev, lnk->ibport, ini->vlan_id, lnk->gid, &lnk->sgid_index, lgr->smc_version == SMC_V2 ? &ini->smcrv2 : NULL); if (rc) goto out; rc = smc_llc_link_init(lnk); if (rc) goto out; rc = smc_wr_alloc_link_mem(lnk); if (rc) goto clear_llc_lnk; rc = smc_ib_create_protection_domain(lnk); if (rc) goto free_link_mem; rc = smc_ib_create_queue_pair(lnk); if (rc) goto dealloc_pd; rc = smc_wr_create_link(lnk); if (rc) goto destroy_qp; lnk->state = SMC_LNK_ACTIVATING; return 0; destroy_qp: smc_ib_destroy_queue_pair(lnk); dealloc_pd: smc_ib_dealloc_protection_domain(lnk); free_link_mem: smc_wr_free_link_mem(lnk); clear_llc_lnk: smc_llc_link_clear(lnk, false); out: smc_ibdev_cnt_dec(lnk); put_device(&lnk->smcibdev->ibdev->dev); smcibdev = lnk->smcibdev; memset(lnk, 0, sizeof(struct smc_link)); lnk->state = SMC_LNK_UNUSED; if (!atomic_dec_return(&smcibdev->lnk_cnt)) wake_up(&smcibdev->lnks_deleted); smc_lgr_put(lgr); /* lgr_hold above */ return rc; } /* create a new SMC link group */ static int smc_lgr_create(struct smc_sock *smc, struct smc_init_info *ini) { struct smc_link_group *lgr; struct list_head *lgr_list; struct smcd_dev *smcd; struct smc_link *lnk; spinlock_t *lgr_lock; u8 link_idx; int rc = 0; int i; if (ini->is_smcd && ini->vlan_id) { if (smc_ism_get_vlan(ini->ism_dev[ini->ism_selected], ini->vlan_id)) { rc = SMC_CLC_DECL_ISMVLANERR; goto out; } } lgr = kzalloc(sizeof(*lgr), GFP_KERNEL); if (!lgr) { rc = SMC_CLC_DECL_MEM; goto ism_put_vlan; } lgr->tx_wq = alloc_workqueue("smc_tx_wq-%*phN", 0, 0, SMC_LGR_ID_SIZE, &lgr->id); if (!lgr->tx_wq) { rc = -ENOMEM; goto free_lgr; } lgr->is_smcd = ini->is_smcd; lgr->sync_err = 0; lgr->terminating = 0; lgr->freeing = 0; lgr->vlan_id = ini->vlan_id; refcount_set(&lgr->refcnt, 1); /* set lgr refcnt to 1 */ init_rwsem(&lgr->sndbufs_lock); init_rwsem(&lgr->rmbs_lock); rwlock_init(&lgr->conns_lock); for (i = 0; i < SMC_RMBE_SIZES; i++) { INIT_LIST_HEAD(&lgr->sndbufs[i]); INIT_LIST_HEAD(&lgr->rmbs[i]); } lgr->next_link_id = 0; smc_lgr_list.num += SMC_LGR_NUM_INCR; memcpy(&lgr->id, (u8 *)&smc_lgr_list.num, SMC_LGR_ID_SIZE); INIT_DELAYED_WORK(&lgr->free_work, smc_lgr_free_work); INIT_WORK(&lgr->terminate_work, smc_lgr_terminate_work); lgr->conns_all = RB_ROOT; if (ini->is_smcd) { /* SMC-D specific settings */ smcd = ini->ism_dev[ini->ism_selected]; get_device(smcd->ops->get_dev(smcd)); lgr->peer_gid.gid = ini->ism_peer_gid[ini->ism_selected].gid; lgr->peer_gid.gid_ext = ini->ism_peer_gid[ini->ism_selected].gid_ext; lgr->smcd = ini->ism_dev[ini->ism_selected]; lgr_list = &ini->ism_dev[ini->ism_selected]->lgr_list; lgr_lock = &lgr->smcd->lgr_lock; lgr->smc_version = ini->smcd_version; lgr->peer_shutdown = 0; atomic_inc(&ini->ism_dev[ini->ism_selected]->lgr_cnt); } else { /* SMC-R specific settings */ struct smc_ib_device *ibdev; int ibport; lgr->role = smc->listen_smc ? SMC_SERV : SMC_CLNT; lgr->smc_version = ini->smcr_version; memcpy(lgr->peer_systemid, ini->peer_systemid, SMC_SYSTEMID_LEN); if (lgr->smc_version == SMC_V2) { ibdev = ini->smcrv2.ib_dev_v2; ibport = ini->smcrv2.ib_port_v2; lgr->saddr = ini->smcrv2.saddr; lgr->uses_gateway = ini->smcrv2.uses_gateway; memcpy(lgr->nexthop_mac, ini->smcrv2.nexthop_mac, ETH_ALEN); lgr->max_conns = ini->max_conns; lgr->max_links = ini->max_links; } else { ibdev = ini->ib_dev; ibport = ini->ib_port; lgr->max_conns = SMC_CONN_PER_LGR_MAX; lgr->max_links = SMC_LINKS_ADD_LNK_MAX; } memcpy(lgr->pnet_id, ibdev->pnetid[ibport - 1], SMC_MAX_PNETID_LEN); rc = smc_wr_alloc_lgr_mem(lgr); if (rc) goto free_wq; smc_llc_lgr_init(lgr, smc); link_idx = SMC_SINGLE_LINK; lnk = &lgr->lnk[link_idx]; rc = smcr_link_init(lgr, lnk, link_idx, ini); if (rc) { smc_wr_free_lgr_mem(lgr); goto free_wq; } lgr->net = smc_ib_net(lnk->smcibdev); lgr_list = &smc_lgr_list.list; lgr_lock = &smc_lgr_list.lock; lgr->buf_type = lgr->net->smc.sysctl_smcr_buf_type; atomic_inc(&lgr_cnt); } smc->conn.lgr = lgr; spin_lock_bh(lgr_lock); list_add_tail(&lgr->list, lgr_list); spin_unlock_bh(lgr_lock); return 0; free_wq: destroy_workqueue(lgr->tx_wq); free_lgr: kfree(lgr); ism_put_vlan: if (ini->is_smcd && ini->vlan_id) smc_ism_put_vlan(ini->ism_dev[ini->ism_selected], ini->vlan_id); out: if (rc < 0) { if (rc == -ENOMEM) rc = SMC_CLC_DECL_MEM; else rc = SMC_CLC_DECL_INTERR; } return rc; } static int smc_write_space(struct smc_connection *conn) { int buffer_len = conn->peer_rmbe_size; union smc_host_cursor prod; union smc_host_cursor cons; int space; smc_curs_copy(&prod, &conn->local_tx_ctrl.prod, conn); smc_curs_copy(&cons, &conn->local_rx_ctrl.cons, conn); /* determine rx_buf space */ space = buffer_len - smc_curs_diff(buffer_len, &cons, &prod); return space; } static int smc_switch_cursor(struct smc_sock *smc, struct smc_cdc_tx_pend *pend, struct smc_wr_buf *wr_buf) { struct smc_connection *conn = &smc->conn; union smc_host_cursor cons, fin; int rc = 0; int diff; smc_curs_copy(&conn->tx_curs_sent, &conn->tx_curs_fin, conn); smc_curs_copy(&fin, &conn->local_tx_ctrl_fin, conn); /* set prod cursor to old state, enforce tx_rdma_writes() */ smc_curs_copy(&conn->local_tx_ctrl.prod, &fin, conn); smc_curs_copy(&cons, &conn->local_rx_ctrl.cons, conn); if (smc_curs_comp(conn->peer_rmbe_size, &cons, &fin) < 0) { /* cons cursor advanced more than fin, and prod was set * fin above, so now prod is smaller than cons. Fix that. */ diff = smc_curs_diff(conn->peer_rmbe_size, &fin, &cons); smc_curs_add(conn->sndbuf_desc->len, &conn->tx_curs_sent, diff); smc_curs_add(conn->sndbuf_desc->len, &conn->tx_curs_fin, diff); smp_mb__before_atomic(); atomic_add(diff, &conn->sndbuf_space); smp_mb__after_atomic(); smc_curs_add(conn->peer_rmbe_size, &conn->local_tx_ctrl.prod, diff); smc_curs_add(conn->peer_rmbe_size, &conn->local_tx_ctrl_fin, diff); } /* recalculate, value is used by tx_rdma_writes() */ atomic_set(&smc->conn.peer_rmbe_space, smc_write_space(conn)); if (smc->sk.sk_state != SMC_INIT && smc->sk.sk_state != SMC_CLOSED) { rc = smcr_cdc_msg_send_validation(conn, pend, wr_buf); if (!rc) { queue_delayed_work(conn->lgr->tx_wq, &conn->tx_work, 0); smc->sk.sk_data_ready(&smc->sk); } } else { smc_wr_tx_put_slot(conn->lnk, (struct smc_wr_tx_pend_priv *)pend); } return rc; } void smc_switch_link_and_count(struct smc_connection *conn, struct smc_link *to_lnk) { atomic_dec(&conn->lnk->conn_cnt); /* link_hold in smc_conn_create() */ smcr_link_put(conn->lnk); conn->lnk = to_lnk; atomic_inc(&conn->lnk->conn_cnt); /* link_put in smc_conn_free() */ smcr_link_hold(conn->lnk); } struct smc_link *smc_switch_conns(struct smc_link_group *lgr, struct smc_link *from_lnk, bool is_dev_err) { struct smc_link *to_lnk = NULL; struct smc_cdc_tx_pend *pend; struct smc_connection *conn; struct smc_wr_buf *wr_buf; struct smc_sock *smc; struct rb_node *node; int i, rc = 0; /* link is inactive, wake up tx waiters */ smc_wr_wakeup_tx_wait(from_lnk); for (i = 0; i < SMC_LINKS_PER_LGR_MAX; i++) { if (!smc_link_active(&lgr->lnk[i]) || i == from_lnk->link_idx) continue; if (is_dev_err && from_lnk->smcibdev == lgr->lnk[i].smcibdev && from_lnk->ibport == lgr->lnk[i].ibport) { continue; } to_lnk = &lgr->lnk[i]; break; } if (!to_lnk || !smc_wr_tx_link_hold(to_lnk)) { smc_lgr_terminate_sched(lgr); return NULL; } again: read_lock_bh(&lgr->conns_lock); for (node = rb_first(&lgr->conns_all); node; node = rb_next(node)) { conn = rb_entry(node, struct smc_connection, alert_node); if (conn->lnk != from_lnk) continue; smc = container_of(conn, struct smc_sock, conn); /* conn->lnk not yet set in SMC_INIT state */ if (smc->sk.sk_state == SMC_INIT) continue; if (smc->sk.sk_state == SMC_CLOSED || smc->sk.sk_state == SMC_PEERCLOSEWAIT1 || smc->sk.sk_state == SMC_PEERCLOSEWAIT2 || smc->sk.sk_state == SMC_APPFINCLOSEWAIT || smc->sk.sk_state == SMC_APPCLOSEWAIT1 || smc->sk.sk_state == SMC_APPCLOSEWAIT2 || smc->sk.sk_state == SMC_PEERFINCLOSEWAIT || smc->sk.sk_state == SMC_PEERABORTWAIT || smc->sk.sk_state == SMC_PROCESSABORT) { spin_lock_bh(&conn->send_lock); smc_switch_link_and_count(conn, to_lnk); spin_unlock_bh(&conn->send_lock); continue; } sock_hold(&smc->sk); read_unlock_bh(&lgr->conns_lock); /* pre-fetch buffer outside of send_lock, might sleep */ rc = smc_cdc_get_free_slot(conn, to_lnk, &wr_buf, NULL, &pend); if (rc) goto err_out; /* avoid race with smcr_tx_sndbuf_nonempty() */ spin_lock_bh(&conn->send_lock); smc_switch_link_and_count(conn, to_lnk); rc = smc_switch_cursor(smc, pend, wr_buf); spin_unlock_bh(&conn->send_lock); sock_put(&smc->sk); if (rc) goto err_out; goto again; } read_unlock_bh(&lgr->conns_lock); smc_wr_tx_link_put(to_lnk); return to_lnk; err_out: smcr_link_down_cond_sched(to_lnk); smc_wr_tx_link_put(to_lnk); return NULL; } static void smcr_buf_unuse(struct smc_buf_desc *buf_desc, bool is_rmb, struct smc_link_group *lgr) { struct rw_semaphore *lock; /* lock buffer list */ int rc; if (is_rmb && buf_desc->is_conf_rkey && !list_empty(&lgr->list)) { /* unregister rmb with peer */ rc = smc_llc_flow_initiate(lgr, SMC_LLC_FLOW_RKEY); if (!rc) { /* protect against smc_llc_cli_rkey_exchange() */ down_read(&lgr->llc_conf_mutex); smc_llc_do_delete_rkey(lgr, buf_desc); buf_desc->is_conf_rkey = false; up_read(&lgr->llc_conf_mutex); smc_llc_flow_stop(lgr, &lgr->llc_flow_lcl); } } if (buf_desc->is_reg_err) { /* buf registration failed, reuse not possible */ lock = is_rmb ? &lgr->rmbs_lock : &lgr->sndbufs_lock; down_write(lock); smc_lgr_buf_list_del(lgr, is_rmb, buf_desc); up_write(lock); smc_buf_free(lgr, is_rmb, buf_desc); } else { /* memzero_explicit provides potential memory barrier semantics */ memzero_explicit(buf_desc->cpu_addr, buf_desc->len); WRITE_ONCE(buf_desc->used, 0); } } static void smcd_buf_detach(struct smc_connection *conn) { struct smcd_dev *smcd = conn->lgr->smcd; u64 peer_token = conn->peer_token; if (!conn->sndbuf_desc) return; smc_ism_detach_dmb(smcd, peer_token); kfree(conn->sndbuf_desc); conn->sndbuf_desc = NULL; } static void smc_buf_unuse(struct smc_connection *conn, struct smc_link_group *lgr) { struct smc_sock *smc = container_of(conn, struct smc_sock, conn); bool is_smcd = lgr->is_smcd; int bufsize; if (conn->sndbuf_desc) { bufsize = conn->sndbuf_desc->len; if (!is_smcd && conn->sndbuf_desc->is_vm) { smcr_buf_unuse(conn->sndbuf_desc, false, lgr); } else { memzero_explicit(conn->sndbuf_desc->cpu_addr, bufsize); WRITE_ONCE(conn->sndbuf_desc->used, 0); } SMC_STAT_RMB_SIZE(smc, is_smcd, false, false, bufsize); } if (conn->rmb_desc) { bufsize = conn->rmb_desc->len; if (!is_smcd) { smcr_buf_unuse(conn->rmb_desc, true, lgr); } else { bufsize += sizeof(struct smcd_cdc_msg); memzero_explicit(conn->rmb_desc->cpu_addr, bufsize); WRITE_ONCE(conn->rmb_desc->used, 0); } SMC_STAT_RMB_SIZE(smc, is_smcd, true, false, bufsize); } } /* remove a finished connection from its link group */ void smc_conn_free(struct smc_connection *conn) { struct smc_link_group *lgr = conn->lgr; if (!lgr || conn->freed) /* Connection has never been registered in a * link group, or has already been freed. */ return; conn->freed = 1; if (!smc_conn_lgr_valid(conn)) /* Connection has already unregistered from * link group. */ goto lgr_put; if (lgr->is_smcd) { if (!list_empty(&lgr->list)) smc_ism_unset_conn(conn); if (smc_ism_support_dmb_nocopy(lgr->smcd)) smcd_buf_detach(conn); tasklet_kill(&conn->rx_tsklet); } else { smc_cdc_wait_pend_tx_wr(conn); if (current_work() != &conn->abort_work) cancel_work_sync(&conn->abort_work); } if (!list_empty(&lgr->list)) { smc_buf_unuse(conn, lgr); /* allow buffer reuse */ smc_lgr_unregister_conn(conn); } if (!lgr->conns_num) smc_lgr_schedule_free_work(lgr); lgr_put: if (!lgr->is_smcd) smcr_link_put(conn->lnk); /* link_hold in smc_conn_create() */ smc_lgr_put(lgr); /* lgr_hold in smc_conn_create() */ } /* unregister a link from a buf_desc */ static void smcr_buf_unmap_link(struct smc_buf_desc *buf_desc, bool is_rmb, struct smc_link *lnk) { if (is_rmb || buf_desc->is_vm) buf_desc->is_reg_mr[lnk->link_idx] = false; if (!buf_desc->is_map_ib[lnk->link_idx]) return; if ((is_rmb || buf_desc->is_vm) && buf_desc->mr[lnk->link_idx]) { smc_ib_put_memory_region(buf_desc->mr[lnk->link_idx]); buf_desc->mr[lnk->link_idx] = NULL; } if (is_rmb) smc_ib_buf_unmap_sg(lnk, buf_desc, DMA_FROM_DEVICE); else smc_ib_buf_unmap_sg(lnk, buf_desc, DMA_TO_DEVICE); sg_free_table(&buf_desc->sgt[lnk->link_idx]); buf_desc->is_map_ib[lnk->link_idx] = false; } /* unmap all buffers of lgr for a deleted link */ static void smcr_buf_unmap_lgr(struct smc_link *lnk) { struct smc_link_group *lgr = lnk->lgr; struct smc_buf_desc *buf_desc, *bf; int i; for (i = 0; i < SMC_RMBE_SIZES; i++) { down_write(&lgr->rmbs_lock); list_for_each_entry_safe(buf_desc, bf, &lgr->rmbs[i], list) smcr_buf_unmap_link(buf_desc, true, lnk); up_write(&lgr->rmbs_lock); down_write(&lgr->sndbufs_lock); list_for_each_entry_safe(buf_desc, bf, &lgr->sndbufs[i], list) smcr_buf_unmap_link(buf_desc, false, lnk); up_write(&lgr->sndbufs_lock); } } static void smcr_rtoken_clear_link(struct smc_link *lnk) { struct smc_link_group *lgr = lnk->lgr; int i; for (i = 0; i < SMC_RMBS_PER_LGR_MAX; i++) { lgr->rtokens[i][lnk->link_idx].rkey = 0; lgr->rtokens[i][lnk->link_idx].dma_addr = 0; } } static void __smcr_link_clear(struct smc_link *lnk) { struct smc_link_group *lgr = lnk->lgr; struct smc_ib_device *smcibdev; smc_wr_free_link_mem(lnk); smc_ibdev_cnt_dec(lnk); put_device(&lnk->smcibdev->ibdev->dev); smcibdev = lnk->smcibdev; memset(lnk, 0, sizeof(struct smc_link)); lnk->state = SMC_LNK_UNUSED; if (!atomic_dec_return(&smcibdev->lnk_cnt)) wake_up(&smcibdev->lnks_deleted); smc_lgr_put(lgr); /* lgr_hold in smcr_link_init() */ } /* must be called under lgr->llc_conf_mutex lock */ void smcr_link_clear(struct smc_link *lnk, bool log) { if (!lnk->lgr || lnk->clearing || lnk->state == SMC_LNK_UNUSED) return; lnk->clearing = 1; lnk->peer_qpn = 0; smc_llc_link_clear(lnk, log); smcr_buf_unmap_lgr(lnk); smcr_rtoken_clear_link(lnk); smc_ib_modify_qp_error(lnk); smc_wr_free_link(lnk); smc_ib_destroy_queue_pair(lnk); smc_ib_dealloc_protection_domain(lnk); smcr_link_put(lnk); /* theoretically last link_put */ } void smcr_link_hold(struct smc_link *lnk) { refcount_inc(&lnk->refcnt); } void smcr_link_put(struct smc_link *lnk) { if (refcount_dec_and_test(&lnk->refcnt)) __smcr_link_clear(lnk); } static void smcr_buf_free(struct smc_link_group *lgr, bool is_rmb, struct smc_buf_desc *buf_desc) { int i; for (i = 0; i < SMC_LINKS_PER_LGR_MAX; i++) smcr_buf_unmap_link(buf_desc, is_rmb, &lgr->lnk[i]); if (!buf_desc->is_vm && buf_desc->pages) __free_pages(buf_desc->pages, buf_desc->order); else if (buf_desc->is_vm && buf_desc->cpu_addr) vfree(buf_desc->cpu_addr); kfree(buf_desc); } static void smcd_buf_free(struct smc_link_group *lgr, bool is_dmb, struct smc_buf_desc *buf_desc) { if (is_dmb) { /* restore original buf len */ buf_desc->len += sizeof(struct smcd_cdc_msg); smc_ism_unregister_dmb(lgr->smcd, buf_desc); } else { kfree(buf_desc->cpu_addr); } kfree(buf_desc); } static void smc_buf_free(struct smc_link_group *lgr, bool is_rmb, struct smc_buf_desc *buf_desc) { if (lgr->is_smcd) smcd_buf_free(lgr, is_rmb, buf_desc); else smcr_buf_free(lgr, is_rmb, buf_desc); } static void __smc_lgr_free_bufs(struct smc_link_group *lgr, bool is_rmb) { struct smc_buf_desc *buf_desc, *bf_desc; struct list_head *buf_list; int i; for (i = 0; i < SMC_RMBE_SIZES; i++) { if (is_rmb) buf_list = &lgr->rmbs[i]; else buf_list = &lgr->sndbufs[i]; list_for_each_entry_safe(buf_desc, bf_desc, buf_list, list) { smc_lgr_buf_list_del(lgr, is_rmb, buf_desc); smc_buf_free(lgr, is_rmb, buf_desc); } } } static void smc_lgr_free_bufs(struct smc_link_group *lgr) { /* free send buffers */ __smc_lgr_free_bufs(lgr, false); /* free rmbs */ __smc_lgr_free_bufs(lgr, true); } /* won't be freed until no one accesses to lgr anymore */ static void __smc_lgr_free(struct smc_link_group *lgr) { smc_lgr_free_bufs(lgr); if (lgr->is_smcd) { if (!atomic_dec_return(&lgr->smcd->lgr_cnt)) wake_up(&lgr->smcd->lgrs_deleted); } else { smc_wr_free_lgr_mem(lgr); if (!atomic_dec_return(&lgr_cnt)) wake_up(&lgrs_deleted); } kfree(lgr); } /* remove a link group */ static void smc_lgr_free(struct smc_link_group *lgr) { int i; if (!lgr->is_smcd) { down_write(&lgr->llc_conf_mutex); for (i = 0; i < SMC_LINKS_PER_LGR_MAX; i++) { if (lgr->lnk[i].state != SMC_LNK_UNUSED) smcr_link_clear(&lgr->lnk[i], false); } up_write(&lgr->llc_conf_mutex); smc_llc_lgr_clear(lgr); } destroy_workqueue(lgr->tx_wq); if (lgr->is_smcd) { smc_ism_put_vlan(lgr->smcd, lgr->vlan_id); put_device(lgr->smcd->ops->get_dev(lgr->smcd)); } smc_lgr_put(lgr); /* theoretically last lgr_put */ } void smc_lgr_hold(struct smc_link_group *lgr) { refcount_inc(&lgr->refcnt); } void smc_lgr_put(struct smc_link_group *lgr) { if (refcount_dec_and_test(&lgr->refcnt)) __smc_lgr_free(lgr); } static void smc_sk_wake_ups(struct smc_sock *smc) { smc->sk.sk_write_space(&smc->sk); smc->sk.sk_data_ready(&smc->sk); smc->sk.sk_state_change(&smc->sk); } /* kill a connection */ static void smc_conn_kill(struct smc_connection *conn, bool soft) { struct smc_sock *smc = container_of(conn, struct smc_sock, conn); if (conn->lgr->is_smcd && conn->lgr->peer_shutdown) conn->local_tx_ctrl.conn_state_flags.peer_conn_abort = 1; else smc_close_abort(conn); conn->killed = 1; smc->sk.sk_err = ECONNABORTED; smc_sk_wake_ups(smc); if (conn->lgr->is_smcd) { smc_ism_unset_conn(conn); if (smc_ism_support_dmb_nocopy(conn->lgr->smcd)) smcd_buf_detach(conn); if (soft) tasklet_kill(&conn->rx_tsklet); else tasklet_unlock_wait(&conn->rx_tsklet); } else { smc_cdc_wait_pend_tx_wr(conn); } smc_lgr_unregister_conn(conn); smc_close_active_abort(smc); } static void smc_lgr_cleanup(struct smc_link_group *lgr) { if (lgr->is_smcd) { smc_ism_signal_shutdown(lgr); } else { u32 rsn = lgr->llc_termination_rsn; if (!rsn) rsn = SMC_LLC_DEL_PROG_INIT_TERM; smc_llc_send_link_delete_all(lgr, false, rsn); smcr_lgr_link_deactivate_all(lgr); } } /* terminate link group * @soft: true if link group shutdown can take its time * false if immediate link group shutdown is required */ static void __smc_lgr_terminate(struct smc_link_group *lgr, bool soft) { struct smc_connection *conn; struct smc_sock *smc; struct rb_node *node; if (lgr->terminating) return; /* lgr already terminating */ /* cancel free_work sync, will terminate when lgr->freeing is set */ cancel_delayed_work(&lgr->free_work); lgr->terminating = 1; /* kill remaining link group connections */ read_lock_bh(&lgr->conns_lock); node = rb_first(&lgr->conns_all); while (node) { read_unlock_bh(&lgr->conns_lock); conn = rb_entry(node, struct smc_connection, alert_node); smc = container_of(conn, struct smc_sock, conn); sock_hold(&smc->sk); /* sock_put below */ lock_sock(&smc->sk); smc_conn_kill(conn, soft); release_sock(&smc->sk); sock_put(&smc->sk); /* sock_hold above */ read_lock_bh(&lgr->conns_lock); node = rb_first(&lgr->conns_all); } read_unlock_bh(&lgr->conns_lock); smc_lgr_cleanup(lgr); smc_lgr_free(lgr); } /* unlink link group and schedule termination */ void smc_lgr_terminate_sched(struct smc_link_group *lgr) { spinlock_t *lgr_lock; smc_lgr_list_head(lgr, &lgr_lock); spin_lock_bh(lgr_lock); if (list_empty(&lgr->list) || lgr->terminating || lgr->freeing) { spin_unlock_bh(lgr_lock); return; /* lgr already terminating */ } list_del_init(&lgr->list); lgr->freeing = 1; spin_unlock_bh(lgr_lock); schedule_work(&lgr->terminate_work); } /* Called when peer lgr shutdown (regularly or abnormally) is received */ void smc_smcd_terminate(struct smcd_dev *dev, struct smcd_gid *peer_gid, unsigned short vlan) { struct smc_link_group *lgr, *l; LIST_HEAD(lgr_free_list); /* run common cleanup function and build free list */ spin_lock_bh(&dev->lgr_lock); list_for_each_entry_safe(lgr, l, &dev->lgr_list, list) { if ((!peer_gid->gid || (lgr->peer_gid.gid == peer_gid->gid && !smc_ism_is_emulated(dev) ? 1 : lgr->peer_gid.gid_ext == peer_gid->gid_ext)) && (vlan == VLAN_VID_MASK || lgr->vlan_id == vlan)) { if (peer_gid->gid) /* peer triggered termination */ lgr->peer_shutdown = 1; list_move(&lgr->list, &lgr_free_list); lgr->freeing = 1; } } spin_unlock_bh(&dev->lgr_lock); /* cancel the regular free workers and actually free lgrs */ list_for_each_entry_safe(lgr, l, &lgr_free_list, list) { list_del_init(&lgr->list); schedule_work(&lgr->terminate_work); } } /* Called when an SMCD device is removed or the smc module is unloaded */ void smc_smcd_terminate_all(struct smcd_dev *smcd) { struct smc_link_group *lgr, *lg; LIST_HEAD(lgr_free_list); spin_lock_bh(&smcd->lgr_lock); list_splice_init(&smcd->lgr_list, &lgr_free_list); list_for_each_entry(lgr, &lgr_free_list, list) lgr->freeing = 1; spin_unlock_bh(&smcd->lgr_lock); list_for_each_entry_safe(lgr, lg, &lgr_free_list, list) { list_del_init(&lgr->list); __smc_lgr_terminate(lgr, false); } if (atomic_read(&smcd->lgr_cnt)) wait_event(smcd->lgrs_deleted, !atomic_read(&smcd->lgr_cnt)); } /* Called when an SMCR device is removed or the smc module is unloaded. * If smcibdev is given, all SMCR link groups using this device are terminated. * If smcibdev is NULL, all SMCR link groups are terminated. */ void smc_smcr_terminate_all(struct smc_ib_device *smcibdev) { struct smc_link_group *lgr, *lg; LIST_HEAD(lgr_free_list); int i; spin_lock_bh(&smc_lgr_list.lock); if (!smcibdev) { list_splice_init(&smc_lgr_list.list, &lgr_free_list); list_for_each_entry(lgr, &lgr_free_list, list) lgr->freeing = 1; } else { list_for_each_entry_safe(lgr, lg, &smc_lgr_list.list, list) { for (i = 0; i < SMC_LINKS_PER_LGR_MAX; i++) { if (lgr->lnk[i].smcibdev == smcibdev) smcr_link_down_cond_sched(&lgr->lnk[i]); } } } spin_unlock_bh(&smc_lgr_list.lock); list_for_each_entry_safe(lgr, lg, &lgr_free_list, list) { list_del_init(&lgr->list); smc_llc_set_termination_rsn(lgr, SMC_LLC_DEL_OP_INIT_TERM); __smc_lgr_terminate(lgr, false); } if (smcibdev) { if (atomic_read(&smcibdev->lnk_cnt)) wait_event(smcibdev->lnks_deleted, !atomic_read(&smcibdev->lnk_cnt)); } else { if (atomic_read(&lgr_cnt)) wait_event(lgrs_deleted, !atomic_read(&lgr_cnt)); } } /* set new lgr type and clear all asymmetric link tagging */ void smcr_lgr_set_type(struct smc_link_group *lgr, enum smc_lgr_type new_type) { char *lgr_type = ""; int i; for (i = 0; i < SMC_LINKS_PER_LGR_MAX; i++) if (smc_link_usable(&lgr->lnk[i])) lgr->lnk[i].link_is_asym = false; if (lgr->type == new_type) return; lgr->type = new_type; switch (lgr->type) { case SMC_LGR_NONE: lgr_type = "NONE"; break; case SMC_LGR_SINGLE: lgr_type = "SINGLE"; break; case SMC_LGR_SYMMETRIC: lgr_type = "SYMMETRIC"; break; case SMC_LGR_ASYMMETRIC_PEER: lgr_type = "ASYMMETRIC_PEER"; break; case SMC_LGR_ASYMMETRIC_LOCAL: lgr_type = "ASYMMETRIC_LOCAL"; break; } pr_warn_ratelimited("smc: SMC-R lg %*phN net %llu state changed: " "%s, pnetid %.16s\n", SMC_LGR_ID_SIZE, &lgr->id, lgr->net->net_cookie, lgr_type, lgr->pnet_id); } /* set new lgr type and tag a link as asymmetric */ void smcr_lgr_set_type_asym(struct smc_link_group *lgr, enum smc_lgr_type new_type, int asym_lnk_idx) { smcr_lgr_set_type(lgr, new_type); lgr->lnk[asym_lnk_idx].link_is_asym = true; } /* abort connection, abort_work scheduled from tasklet context */ static void smc_conn_abort_work(struct work_struct *work) { struct smc_connection *conn = container_of(work, struct smc_connection, abort_work); struct smc_sock *smc = container_of(conn, struct smc_sock, conn); lock_sock(&smc->sk); smc_conn_kill(conn, true); release_sock(&smc->sk); sock_put(&smc->sk); /* sock_hold done by schedulers of abort_work */ } void smcr_port_add(struct smc_ib_device *smcibdev, u8 ibport) { struct smc_link_group *lgr, *n; spin_lock_bh(&smc_lgr_list.lock); list_for_each_entry_safe(lgr, n, &smc_lgr_list.list, list) { struct smc_link *link; if (strncmp(smcibdev->pnetid[ibport - 1], lgr->pnet_id, SMC_MAX_PNETID_LEN) || lgr->type == SMC_LGR_SYMMETRIC || lgr->type == SMC_LGR_ASYMMETRIC_PEER || !rdma_dev_access_netns(smcibdev->ibdev, lgr->net)) continue; if (lgr->type == SMC_LGR_SINGLE && lgr->max_links <= 1) continue; /* trigger local add link processing */ link = smc_llc_usable_link(lgr); if (link) smc_llc_add_link_local(link); } spin_unlock_bh(&smc_lgr_list.lock); } /* link is down - switch connections to alternate link, * must be called under lgr->llc_conf_mutex lock */ static void smcr_link_down(struct smc_link *lnk) { struct smc_link_group *lgr = lnk->lgr; struct smc_link *to_lnk; int del_link_id; if (!lgr || lnk->state == SMC_LNK_UNUSED || list_empty(&lgr->list)) return; to_lnk = smc_switch_conns(lgr, lnk, true); if (!to_lnk) { /* no backup link available */ smcr_link_clear(lnk, true); return; } smcr_lgr_set_type(lgr, SMC_LGR_SINGLE); del_link_id = lnk->link_id; if (lgr->role == SMC_SERV) { /* trigger local delete link processing */ smc_llc_srv_delete_link_local(to_lnk, del_link_id); } else { if (lgr->llc_flow_lcl.type != SMC_LLC_FLOW_NONE) { /* another llc task is ongoing */ up_write(&lgr->llc_conf_mutex); wait_event_timeout(lgr->llc_flow_waiter, (list_empty(&lgr->list) || lgr->llc_flow_lcl.type == SMC_LLC_FLOW_NONE), SMC_LLC_WAIT_TIME); down_write(&lgr->llc_conf_mutex); } if (!list_empty(&lgr->list)) { smc_llc_send_delete_link(to_lnk, del_link_id, SMC_LLC_REQ, true, SMC_LLC_DEL_LOST_PATH); smcr_link_clear(lnk, true); } wake_up(&lgr->llc_flow_waiter); /* wake up next waiter */ } } /* must be called under lgr->llc_conf_mutex lock */ void smcr_link_down_cond(struct smc_link *lnk) { if (smc_link_downing(&lnk->state)) { trace_smcr_link_down(lnk, __builtin_return_address(0)); smcr_link_down(lnk); } } /* will get the lgr->llc_conf_mutex lock */ void smcr_link_down_cond_sched(struct smc_link *lnk) { if (smc_link_downing(&lnk->state)) { trace_smcr_link_down(lnk, __builtin_return_address(0)); smcr_link_hold(lnk); /* smcr_link_put in link_down_wrk */ if (!schedule_work(&lnk->link_down_wrk)) smcr_link_put(lnk); } } void smcr_port_err(struct smc_ib_device *smcibdev, u8 ibport) { struct smc_link_group *lgr, *n; int i; list_for_each_entry_safe(lgr, n, &smc_lgr_list.list, list) { if (strncmp(smcibdev->pnetid[ibport - 1], lgr->pnet_id, SMC_MAX_PNETID_LEN)) continue; /* lgr is not affected */ if (list_empty(&lgr->list)) continue; for (i = 0; i < SMC_LINKS_PER_LGR_MAX; i++) { struct smc_link *lnk = &lgr->lnk[i]; if (smc_link_usable(lnk) && lnk->smcibdev == smcibdev && lnk->ibport == ibport) smcr_link_down_cond_sched(lnk); } } } static void smc_link_down_work(struct work_struct *work) { struct smc_link *link = container_of(work, struct smc_link, link_down_wrk); struct smc_link_group *lgr = link->lgr; if (list_empty(&lgr->list)) goto out; wake_up_all(&lgr->llc_msg_waiter); down_write(&lgr->llc_conf_mutex); smcr_link_down(link); up_write(&lgr->llc_conf_mutex); out: smcr_link_put(link); /* smcr_link_hold by schedulers of link_down_work */ } static int smc_vlan_by_tcpsk_walk(struct net_device *lower_dev, struct netdev_nested_priv *priv) { unsigned short *vlan_id = (unsigned short *)priv->data; if (is_vlan_dev(lower_dev)) { *vlan_id = vlan_dev_vlan_id(lower_dev); return 1; } return 0; } /* Determine vlan of internal TCP socket. */ int smc_vlan_by_tcpsk(struct socket *clcsock, struct smc_init_info *ini) { struct dst_entry *dst = sk_dst_get(clcsock->sk); struct netdev_nested_priv priv; struct net_device *ndev; int rc = 0; ini->vlan_id = 0; if (!dst) { rc = -ENOTCONN; goto out; } if (!dst->dev) { rc = -ENODEV; goto out_rel; } ndev = dst->dev; if (is_vlan_dev(ndev)) { ini->vlan_id = vlan_dev_vlan_id(ndev); goto out_rel; } priv.data = (void *)&ini->vlan_id; rtnl_lock(); netdev_walk_all_lower_dev(ndev, smc_vlan_by_tcpsk_walk, &priv); rtnl_unlock(); out_rel: dst_release(dst); out: return rc; } static bool smcr_lgr_match(struct smc_link_group *lgr, u8 smcr_version, u8 peer_systemid[], u8 peer_gid[], u8 peer_mac_v1[], enum smc_lgr_role role, u32 clcqpn, struct net *net) { struct smc_link *lnk; int i; if (memcmp(lgr->peer_systemid, peer_systemid, SMC_SYSTEMID_LEN) || lgr->role != role) return false; for (i = 0; i < SMC_LINKS_PER_LGR_MAX; i++) { lnk = &lgr->lnk[i]; if (!smc_link_active(lnk)) continue; /* use verbs API to check netns, instead of lgr->net */ if (!rdma_dev_access_netns(lnk->smcibdev->ibdev, net)) return false; if ((lgr->role == SMC_SERV || lnk->peer_qpn == clcqpn) && !memcmp(lnk->peer_gid, peer_gid, SMC_GID_SIZE) && (smcr_version == SMC_V2 || !memcmp(lnk->peer_mac, peer_mac_v1, ETH_ALEN))) return true; } return false; } static bool smcd_lgr_match(struct smc_link_group *lgr, struct smcd_dev *smcismdev, struct smcd_gid *peer_gid) { if (lgr->peer_gid.gid != peer_gid->gid || lgr->smcd != smcismdev) return false; if (smc_ism_is_emulated(smcismdev) && lgr->peer_gid.gid_ext != peer_gid->gid_ext) return false; return true; } /* create a new SMC connection (and a new link group if necessary) */ int smc_conn_create(struct smc_sock *smc, struct smc_init_info *ini) { struct smc_connection *conn = &smc->conn; struct net *net = sock_net(&smc->sk); struct list_head *lgr_list; struct smc_link_group *lgr; enum smc_lgr_role role; spinlock_t *lgr_lock; int rc = 0; lgr_list = ini->is_smcd ? &ini->ism_dev[ini->ism_selected]->lgr_list : &smc_lgr_list.list; lgr_lock = ini->is_smcd ? &ini->ism_dev[ini->ism_selected]->lgr_lock : &smc_lgr_list.lock; ini->first_contact_local = 1; role = smc->listen_smc ? SMC_SERV : SMC_CLNT; if (role == SMC_CLNT && ini->first_contact_peer) /* create new link group as well */ goto create; /* determine if an existing link group can be reused */ spin_lock_bh(lgr_lock); list_for_each_entry(lgr, lgr_list, list) { write_lock_bh(&lgr->conns_lock); if ((ini->is_smcd ? smcd_lgr_match(lgr, ini->ism_dev[ini->ism_selected], &ini->ism_peer_gid[ini->ism_selected]) : smcr_lgr_match(lgr, ini->smcr_version, ini->peer_systemid, ini->peer_gid, ini->peer_mac, role, ini->ib_clcqpn, net)) && !lgr->sync_err && (ini->smcd_version == SMC_V2 || lgr->vlan_id == ini->vlan_id) && (role == SMC_CLNT || ini->is_smcd || (lgr->conns_num < lgr->max_conns && !bitmap_full(lgr->rtokens_used_mask, SMC_RMBS_PER_LGR_MAX)))) { /* link group found */ ini->first_contact_local = 0; conn->lgr = lgr; rc = smc_lgr_register_conn(conn, false); write_unlock_bh(&lgr->conns_lock); if (!rc && delayed_work_pending(&lgr->free_work)) cancel_delayed_work(&lgr->free_work); break; } write_unlock_bh(&lgr->conns_lock); } spin_unlock_bh(lgr_lock); if (rc) return rc; if (role == SMC_CLNT && !ini->first_contact_peer && ini->first_contact_local) { /* Server reuses a link group, but Client wants to start * a new one * send out_of_sync decline, reason synchr. error */ return SMC_CLC_DECL_SYNCERR; } create: if (ini->first_contact_local) { rc = smc_lgr_create(smc, ini); if (rc) goto out; lgr = conn->lgr; write_lock_bh(&lgr->conns_lock); rc = smc_lgr_register_conn(conn, true); write_unlock_bh(&lgr->conns_lock); if (rc) { smc_lgr_cleanup_early(lgr); goto out; } } smc_lgr_hold(conn->lgr); /* lgr_put in smc_conn_free() */ if (!conn->lgr->is_smcd) smcr_link_hold(conn->lnk); /* link_put in smc_conn_free() */ conn->freed = 0; conn->local_tx_ctrl.common.type = SMC_CDC_MSG_TYPE; conn->local_tx_ctrl.len = SMC_WR_TX_SIZE; conn->urg_state = SMC_URG_READ; init_waitqueue_head(&conn->cdc_pend_tx_wq); INIT_WORK(&smc->conn.abort_work, smc_conn_abort_work); if (ini->is_smcd) { conn->rx_off = sizeof(struct smcd_cdc_msg); smcd_cdc_rx_init(conn); /* init tasklet for this conn */ } else { conn->rx_off = 0; } #ifndef KERNEL_HAS_ATOMIC64 spin_lock_init(&conn->acurs_lock); #endif out: return rc; } #define SMCD_DMBE_SIZES 6 /* 0 -> 16KB, 1 -> 32KB, .. 6 -> 1MB */ #define SMCR_RMBE_SIZES 15 /* 0 -> 16KB, 1 -> 32KB, .. 15 -> 512MB */ /* convert the RMB size into the compressed notation (minimum 16K, see * SMCD/R_DMBE_SIZES. * In contrast to plain ilog2, this rounds towards the next power of 2, * so the socket application gets at least its desired sndbuf / rcvbuf size. */ static u8 smc_compress_bufsize(int size, bool is_smcd, bool is_rmb) { u8 compressed; if (size <= SMC_BUF_MIN_SIZE) return 0; size = (size - 1) >> 14; /* convert to 16K multiple */ compressed = min_t(u8, ilog2(size) + 1, is_smcd ? SMCD_DMBE_SIZES : SMCR_RMBE_SIZES); #ifdef CONFIG_ARCH_NO_SG_CHAIN if (!is_smcd && is_rmb) /* RMBs are backed by & limited to max size of scatterlists */ compressed = min_t(u8, compressed, ilog2((SG_MAX_SINGLE_ALLOC * PAGE_SIZE) >> 14)); #endif return compressed; } /* convert the RMB size from compressed notation into integer */ int smc_uncompress_bufsize(u8 compressed) { u32 size; size = 0x00000001 << (((int)compressed) + 14); return (int)size; } /* try to reuse a sndbuf or rmb description slot for a certain * buffer size; if not available, return NULL */ static struct smc_buf_desc *smc_buf_get_slot(int compressed_bufsize, struct rw_semaphore *lock, struct list_head *buf_list) { struct smc_buf_desc *buf_slot; down_read(lock); list_for_each_entry(buf_slot, buf_list, list) { if (cmpxchg(&buf_slot->used, 0, 1) == 0) { up_read(lock); return buf_slot; } } up_read(lock); return NULL; } /* one of the conditions for announcing a receiver's current window size is * that it "results in a minimum increase in the window size of 10% of the * receive buffer space" [RFC7609] */ static inline int smc_rmb_wnd_update_limit(int rmbe_size) { return max_t(int, rmbe_size / 10, SOCK_MIN_SNDBUF / 2); } /* map an buf to a link */ static int smcr_buf_map_link(struct smc_buf_desc *buf_desc, bool is_rmb, struct smc_link *lnk) { int rc, i, nents, offset, buf_size, size, access_flags; struct scatterlist *sg; void *buf; if (buf_desc->is_map_ib[lnk->link_idx]) return 0; if (buf_desc->is_vm) { buf = buf_desc->cpu_addr; buf_size = buf_desc->len; offset = offset_in_page(buf_desc->cpu_addr); nents = PAGE_ALIGN(buf_size + offset) / PAGE_SIZE; } else { nents = 1; } rc = sg_alloc_table(&buf_desc->sgt[lnk->link_idx], nents, GFP_KERNEL); if (rc) return rc; if (buf_desc->is_vm) { /* virtually contiguous buffer */ for_each_sg(buf_desc->sgt[lnk->link_idx].sgl, sg, nents, i) { size = min_t(int, PAGE_SIZE - offset, buf_size); sg_set_page(sg, vmalloc_to_page(buf), size, offset); buf += size; buf_size -= size; offset = 0; } } else { /* physically contiguous buffer */ sg_set_buf(buf_desc->sgt[lnk->link_idx].sgl, buf_desc->cpu_addr, buf_desc->len); } /* map sg table to DMA address */ rc = smc_ib_buf_map_sg(lnk, buf_desc, is_rmb ? DMA_FROM_DEVICE : DMA_TO_DEVICE); /* SMC protocol depends on mapping to one DMA address only */ if (rc != nents) { rc = -EAGAIN; goto free_table; } buf_desc->is_dma_need_sync |= smc_ib_is_sg_need_sync(lnk, buf_desc) << lnk->link_idx; if (is_rmb || buf_desc->is_vm) { /* create a new memory region for the RMB or vzalloced sndbuf */ access_flags = is_rmb ? IB_ACCESS_REMOTE_WRITE | IB_ACCESS_LOCAL_WRITE : IB_ACCESS_LOCAL_WRITE; rc = smc_ib_get_memory_region(lnk->roce_pd, access_flags, buf_desc, lnk->link_idx); if (rc) goto buf_unmap; smc_ib_sync_sg_for_device(lnk, buf_desc, is_rmb ? DMA_FROM_DEVICE : DMA_TO_DEVICE); } buf_desc->is_map_ib[lnk->link_idx] = true; return 0; buf_unmap: smc_ib_buf_unmap_sg(lnk, buf_desc, is_rmb ? DMA_FROM_DEVICE : DMA_TO_DEVICE); free_table: sg_free_table(&buf_desc->sgt[lnk->link_idx]); return rc; } /* register a new buf on IB device, rmb or vzalloced sndbuf * must be called under lgr->llc_conf_mutex lock */ int smcr_link_reg_buf(struct smc_link *link, struct smc_buf_desc *buf_desc) { if (list_empty(&link->lgr->list)) return -ENOLINK; if (!buf_desc->is_reg_mr[link->link_idx]) { /* register memory region for new buf */ if (buf_desc->is_vm) buf_desc->mr[link->link_idx]->iova = (uintptr_t)buf_desc->cpu_addr; if (smc_wr_reg_send(link, buf_desc->mr[link->link_idx])) { buf_desc->is_reg_err = true; return -EFAULT; } buf_desc->is_reg_mr[link->link_idx] = true; } return 0; } static int _smcr_buf_map_lgr(struct smc_link *lnk, struct rw_semaphore *lock, struct list_head *lst, bool is_rmb) { struct smc_buf_desc *buf_desc, *bf; int rc = 0; down_write(lock); list_for_each_entry_safe(buf_desc, bf, lst, list) { if (!buf_desc->used) continue; rc = smcr_buf_map_link(buf_desc, is_rmb, lnk); if (rc) goto out; } out: up_write(lock); return rc; } /* map all used buffers of lgr for a new link */ int smcr_buf_map_lgr(struct smc_link *lnk) { struct smc_link_group *lgr = lnk->lgr; int i, rc = 0; for (i = 0; i < SMC_RMBE_SIZES; i++) { rc = _smcr_buf_map_lgr(lnk, &lgr->rmbs_lock, &lgr->rmbs[i], true); if (rc) return rc; rc = _smcr_buf_map_lgr(lnk, &lgr->sndbufs_lock, &lgr->sndbufs[i], false); if (rc) return rc; } return 0; } /* register all used buffers of lgr for a new link, * must be called under lgr->llc_conf_mutex lock */ int smcr_buf_reg_lgr(struct smc_link *lnk) { struct smc_link_group *lgr = lnk->lgr; struct smc_buf_desc *buf_desc, *bf; int i, rc = 0; /* reg all RMBs for a new link */ down_write(&lgr->rmbs_lock); for (i = 0; i < SMC_RMBE_SIZES; i++) { list_for_each_entry_safe(buf_desc, bf, &lgr->rmbs[i], list) { if (!buf_desc->used) continue; rc = smcr_link_reg_buf(lnk, buf_desc); if (rc) { up_write(&lgr->rmbs_lock); return rc; } } } up_write(&lgr->rmbs_lock); if (lgr->buf_type == SMCR_PHYS_CONT_BUFS) return rc; /* reg all vzalloced sndbufs for a new link */ down_write(&lgr->sndbufs_lock); for (i = 0; i < SMC_RMBE_SIZES; i++) { list_for_each_entry_safe(buf_desc, bf, &lgr->sndbufs[i], list) { if (!buf_desc->used || !buf_desc->is_vm) continue; rc = smcr_link_reg_buf(lnk, buf_desc); if (rc) { up_write(&lgr->sndbufs_lock); return rc; } } } up_write(&lgr->sndbufs_lock); return rc; } static struct smc_buf_desc *smcr_new_buf_create(struct smc_link_group *lgr, int bufsize) { struct smc_buf_desc *buf_desc; /* try to alloc a new buffer */ buf_desc = kzalloc(sizeof(*buf_desc), GFP_KERNEL); if (!buf_desc) return ERR_PTR(-ENOMEM); switch (lgr->buf_type) { case SMCR_PHYS_CONT_BUFS: case SMCR_MIXED_BUFS: buf_desc->order = get_order(bufsize); buf_desc->pages = alloc_pages(GFP_KERNEL | __GFP_NOWARN | __GFP_NOMEMALLOC | __GFP_COMP | __GFP_NORETRY | __GFP_ZERO, buf_desc->order); if (buf_desc->pages) { buf_desc->cpu_addr = (void *)page_address(buf_desc->pages); buf_desc->len = bufsize; buf_desc->is_vm = false; break; } if (lgr->buf_type == SMCR_PHYS_CONT_BUFS) goto out; fallthrough; // try virtually contiguous buf case SMCR_VIRT_CONT_BUFS: buf_desc->order = get_order(bufsize); buf_desc->cpu_addr = vzalloc(PAGE_SIZE << buf_desc->order); if (!buf_desc->cpu_addr) goto out; buf_desc->pages = NULL; buf_desc->len = bufsize; buf_desc->is_vm = true; break; } return buf_desc; out: kfree(buf_desc); return ERR_PTR(-EAGAIN); } /* map buf_desc on all usable links, * unused buffers stay mapped as long as the link is up */ static int smcr_buf_map_usable_links(struct smc_link_group *lgr, struct smc_buf_desc *buf_desc, bool is_rmb) { int i, rc = 0, cnt = 0; /* protect against parallel link reconfiguration */ down_read(&lgr->llc_conf_mutex); for (i = 0; i < SMC_LINKS_PER_LGR_MAX; i++) { struct smc_link *lnk = &lgr->lnk[i]; if (!smc_link_usable(lnk)) continue; if (smcr_buf_map_link(buf_desc, is_rmb, lnk)) { rc = -ENOMEM; goto out; } cnt++; } out: up_read(&lgr->llc_conf_mutex); if (!rc && !cnt) rc = -EINVAL; return rc; } static struct smc_buf_desc *smcd_new_buf_create(struct smc_link_group *lgr, bool is_dmb, int bufsize) { struct smc_buf_desc *buf_desc; int rc; /* try to alloc a new DMB */ buf_desc = kzalloc(sizeof(*buf_desc), GFP_KERNEL); if (!buf_desc) return ERR_PTR(-ENOMEM); if (is_dmb) { rc = smc_ism_register_dmb(lgr, bufsize, buf_desc); if (rc) { kfree(buf_desc); if (rc == -ENOMEM) return ERR_PTR(-EAGAIN); if (rc == -ENOSPC) return ERR_PTR(-ENOSPC); return ERR_PTR(-EIO); } buf_desc->pages = virt_to_page(buf_desc->cpu_addr); /* CDC header stored in buf. So, pretend it was smaller */ buf_desc->len = bufsize - sizeof(struct smcd_cdc_msg); } else { buf_desc->cpu_addr = kzalloc(bufsize, GFP_KERNEL | __GFP_NOWARN | __GFP_NORETRY | __GFP_NOMEMALLOC); if (!buf_desc->cpu_addr) { kfree(buf_desc); return ERR_PTR(-EAGAIN); } buf_desc->len = bufsize; } return buf_desc; } static int __smc_buf_create(struct smc_sock *smc, bool is_smcd, bool is_rmb) { struct smc_buf_desc *buf_desc = ERR_PTR(-ENOMEM); struct smc_connection *conn = &smc->conn; struct smc_link_group *lgr = conn->lgr; struct list_head *buf_list; int bufsize, bufsize_comp; struct rw_semaphore *lock; /* lock buffer list */ bool is_dgraded = false; if (is_rmb) /* use socket recv buffer size (w/o overhead) as start value */ bufsize = smc->sk.sk_rcvbuf / 2; else /* use socket send buffer size (w/o overhead) as start value */ bufsize = smc->sk.sk_sndbuf / 2; for (bufsize_comp = smc_compress_bufsize(bufsize, is_smcd, is_rmb); bufsize_comp >= 0; bufsize_comp--) { if (is_rmb) { lock = &lgr->rmbs_lock; buf_list = &lgr->rmbs[bufsize_comp]; } else { lock = &lgr->sndbufs_lock; buf_list = &lgr->sndbufs[bufsize_comp]; } bufsize = smc_uncompress_bufsize(bufsize_comp); /* check for reusable slot in the link group */ buf_desc = smc_buf_get_slot(bufsize_comp, lock, buf_list); if (buf_desc) { buf_desc->is_dma_need_sync = 0; SMC_STAT_RMB_SIZE(smc, is_smcd, is_rmb, true, bufsize); SMC_STAT_BUF_REUSE(smc, is_smcd, is_rmb); break; /* found reusable slot */ } if (is_smcd) buf_desc = smcd_new_buf_create(lgr, is_rmb, bufsize); else buf_desc = smcr_new_buf_create(lgr, bufsize); if (PTR_ERR(buf_desc) == -ENOMEM) break; if (IS_ERR(buf_desc)) { if (!is_dgraded) { is_dgraded = true; SMC_STAT_RMB_DOWNGRADED(smc, is_smcd, is_rmb); } continue; } SMC_STAT_RMB_ALLOC(smc, is_smcd, is_rmb); SMC_STAT_RMB_SIZE(smc, is_smcd, is_rmb, true, bufsize); buf_desc->used = 1; down_write(lock); smc_lgr_buf_list_add(lgr, is_rmb, buf_list, buf_desc); up_write(lock); break; /* found */ } if (IS_ERR(buf_desc)) return PTR_ERR(buf_desc); if (!is_smcd) { if (smcr_buf_map_usable_links(lgr, buf_desc, is_rmb)) { smcr_buf_unuse(buf_desc, is_rmb, lgr); return -ENOMEM; } } if (is_rmb) { conn->rmb_desc = buf_desc; conn->rmbe_size_comp = bufsize_comp; smc->sk.sk_rcvbuf = bufsize * 2; atomic_set(&conn->bytes_to_rcv, 0); conn->rmbe_update_limit = smc_rmb_wnd_update_limit(buf_desc->len); if (is_smcd) smc_ism_set_conn(conn); /* map RMB/smcd_dev to conn */ } else { conn->sndbuf_desc = buf_desc; smc->sk.sk_sndbuf = bufsize * 2; atomic_set(&conn->sndbuf_space, bufsize); } return 0; } void smc_sndbuf_sync_sg_for_device(struct smc_connection *conn) { if (!conn->sndbuf_desc->is_dma_need_sync) return; if (!smc_conn_lgr_valid(conn) || conn->lgr->is_smcd || !smc_link_active(conn->lnk)) return; smc_ib_sync_sg_for_device(conn->lnk, conn->sndbuf_desc, DMA_TO_DEVICE); } void smc_rmb_sync_sg_for_cpu(struct smc_connection *conn) { int i; if (!conn->rmb_desc->is_dma_need_sync) return; if (!smc_conn_lgr_valid(conn) || conn->lgr->is_smcd) return; for (i = 0; i < SMC_LINKS_PER_LGR_MAX; i++) { if (!smc_link_active(&conn->lgr->lnk[i])) continue; smc_ib_sync_sg_for_cpu(&conn->lgr->lnk[i], conn->rmb_desc, DMA_FROM_DEVICE); } } /* create the send and receive buffer for an SMC socket; * receive buffers are called RMBs; * (even though the SMC protocol allows more than one RMB-element per RMB, * the Linux implementation uses just one RMB-element per RMB, i.e. uses an * extra RMB for every connection in a link group */ int smc_buf_create(struct smc_sock *smc, bool is_smcd) { int rc; /* create send buffer */ if (is_smcd && smc_ism_support_dmb_nocopy(smc->conn.lgr->smcd)) goto create_rmb; rc = __smc_buf_create(smc, is_smcd, false); if (rc) return rc; create_rmb: /* create rmb */ rc = __smc_buf_create(smc, is_smcd, true); if (rc && smc->conn.sndbuf_desc) { down_write(&smc->conn.lgr->sndbufs_lock); smc_lgr_buf_list_del(smc->conn.lgr, false, smc->conn.sndbuf_desc); up_write(&smc->conn.lgr->sndbufs_lock); smc_buf_free(smc->conn.lgr, false, smc->conn.sndbuf_desc); smc->conn.sndbuf_desc = NULL; } return rc; } int smcd_buf_attach(struct smc_sock *smc) { struct smc_connection *conn = &smc->conn; struct smcd_dev *smcd = conn->lgr->smcd; u64 peer_token = conn->peer_token; struct smc_buf_desc *buf_desc; int rc; buf_desc = kzalloc(sizeof(*buf_desc), GFP_KERNEL); if (!buf_desc) return -ENOMEM; /* The ghost sndbuf_desc describes the same memory region as * peer RMB. Its lifecycle is consistent with the connection's * and it will be freed with the connections instead of the * link group. */ rc = smc_ism_attach_dmb(smcd, peer_token, buf_desc); if (rc) goto free; smc->sk.sk_sndbuf = buf_desc->len; buf_desc->cpu_addr = (u8 *)buf_desc->cpu_addr + sizeof(struct smcd_cdc_msg); buf_desc->len -= sizeof(struct smcd_cdc_msg); conn->sndbuf_desc = buf_desc; conn->sndbuf_desc->used = 1; atomic_set(&conn->sndbuf_space, conn->sndbuf_desc->len); return 0; free: kfree(buf_desc); return rc; } static inline int smc_rmb_reserve_rtoken_idx(struct smc_link_group *lgr) { int i; for_each_clear_bit(i, lgr->rtokens_used_mask, SMC_RMBS_PER_LGR_MAX) { if (!test_and_set_bit(i, lgr->rtokens_used_mask)) return i; } return -ENOSPC; } static int smc_rtoken_find_by_link(struct smc_link_group *lgr, int lnk_idx, u32 rkey) { int i; for (i = 0; i < SMC_RMBS_PER_LGR_MAX; i++) { if (test_bit(i, lgr->rtokens_used_mask) && lgr->rtokens[i][lnk_idx].rkey == rkey) return i; } return -ENOENT; } /* set rtoken for a new link to an existing rmb */ void smc_rtoken_set(struct smc_link_group *lgr, int link_idx, int link_idx_new, __be32 nw_rkey_known, __be64 nw_vaddr, __be32 nw_rkey) { int rtok_idx; rtok_idx = smc_rtoken_find_by_link(lgr, link_idx, ntohl(nw_rkey_known)); if (rtok_idx == -ENOENT) return; lgr->rtokens[rtok_idx][link_idx_new].rkey = ntohl(nw_rkey); lgr->rtokens[rtok_idx][link_idx_new].dma_addr = be64_to_cpu(nw_vaddr); } /* set rtoken for a new link whose link_id is given */ void smc_rtoken_set2(struct smc_link_group *lgr, int rtok_idx, int link_id, __be64 nw_vaddr, __be32 nw_rkey) { u64 dma_addr = be64_to_cpu(nw_vaddr); u32 rkey = ntohl(nw_rkey); bool found = false; int link_idx; for (link_idx = 0; link_idx < SMC_LINKS_PER_LGR_MAX; link_idx++) { if (lgr->lnk[link_idx].link_id == link_id) { found = true; break; } } if (!found) return; lgr->rtokens[rtok_idx][link_idx].rkey = rkey; lgr->rtokens[rtok_idx][link_idx].dma_addr = dma_addr; } /* add a new rtoken from peer */ int smc_rtoken_add(struct smc_link *lnk, __be64 nw_vaddr, __be32 nw_rkey) { struct smc_link_group *lgr = smc_get_lgr(lnk); u64 dma_addr = be64_to_cpu(nw_vaddr); u32 rkey = ntohl(nw_rkey); int i; for (i = 0; i < SMC_RMBS_PER_LGR_MAX; i++) { if (lgr->rtokens[i][lnk->link_idx].rkey == rkey && lgr->rtokens[i][lnk->link_idx].dma_addr == dma_addr && test_bit(i, lgr->rtokens_used_mask)) { /* already in list */ return i; } } i = smc_rmb_reserve_rtoken_idx(lgr); if (i < 0) return i; lgr->rtokens[i][lnk->link_idx].rkey = rkey; lgr->rtokens[i][lnk->link_idx].dma_addr = dma_addr; return i; } /* delete an rtoken from all links */ int smc_rtoken_delete(struct smc_link *lnk, __be32 nw_rkey) { struct smc_link_group *lgr = smc_get_lgr(lnk); u32 rkey = ntohl(nw_rkey); int i, j; for (i = 0; i < SMC_RMBS_PER_LGR_MAX; i++) { if (lgr->rtokens[i][lnk->link_idx].rkey == rkey && test_bit(i, lgr->rtokens_used_mask)) { for (j = 0; j < SMC_LINKS_PER_LGR_MAX; j++) { lgr->rtokens[i][j].rkey = 0; lgr->rtokens[i][j].dma_addr = 0; } clear_bit(i, lgr->rtokens_used_mask); return 0; } } return -ENOENT; } /* save rkey and dma_addr received from peer during clc handshake */ int smc_rmb_rtoken_handling(struct smc_connection *conn, struct smc_link *lnk, struct smc_clc_msg_accept_confirm *clc) { conn->rtoken_idx = smc_rtoken_add(lnk, clc->r0.rmb_dma_addr, clc->r0.rmb_rkey); if (conn->rtoken_idx < 0) return conn->rtoken_idx; return 0; } static void smc_core_going_away(void) { struct smc_ib_device *smcibdev; struct smcd_dev *smcd; mutex_lock(&smc_ib_devices.mutex); list_for_each_entry(smcibdev, &smc_ib_devices.list, list) { int i; for (i = 0; i < SMC_MAX_PORTS; i++) set_bit(i, smcibdev->ports_going_away); } mutex_unlock(&smc_ib_devices.mutex); mutex_lock(&smcd_dev_list.mutex); list_for_each_entry(smcd, &smcd_dev_list.list, list) { smcd->going_away = 1; } mutex_unlock(&smcd_dev_list.mutex); } /* Clean up all SMC link groups */ static void smc_lgrs_shutdown(void) { struct smcd_dev *smcd; smc_core_going_away(); smc_smcr_terminate_all(NULL); mutex_lock(&smcd_dev_list.mutex); list_for_each_entry(smcd, &smcd_dev_list.list, list) smc_smcd_terminate_all(smcd); mutex_unlock(&smcd_dev_list.mutex); } static int smc_core_reboot_event(struct notifier_block *this, unsigned long event, void *ptr) { smc_lgrs_shutdown(); smc_ib_unregister_client(); smc_ism_exit(); return 0; } static struct notifier_block smc_reboot_notifier = { .notifier_call = smc_core_reboot_event, }; int __init smc_core_init(void) { return register_reboot_notifier(&smc_reboot_notifier); } /* Called (from smc_exit) when module is removed */ void smc_core_exit(void) { unregister_reboot_notifier(&smc_reboot_notifier); smc_lgrs_shutdown(); } |
| 38 86 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 | /* SPDX-License-Identifier: GPL-2.0 */ /* * Definitions for diskquota-operations. When diskquota is configured these * macros expand to the right source-code. * * Author: Marco van Wieringen <mvw@planets.elm.net> */ #ifndef _LINUX_QUOTAOPS_ #define _LINUX_QUOTAOPS_ #include <linux/fs.h> #define DQUOT_SPACE_WARN 0x1 #define DQUOT_SPACE_RESERVE 0x2 #define DQUOT_SPACE_NOFAIL 0x4 static inline struct quota_info *sb_dqopt(struct super_block *sb) { return &sb->s_dquot; } /* i_mutex must being held */ static inline bool is_quota_modification(struct mnt_idmap *idmap, struct inode *inode, struct iattr *ia) { return ((ia->ia_valid & ATTR_SIZE) || i_uid_needs_update(idmap, ia, inode) || i_gid_needs_update(idmap, ia, inode)); } #if defined(CONFIG_QUOTA) #define quota_error(sb, fmt, args...) \ __quota_error((sb), __func__, fmt , ## args) extern __printf(3, 4) void __quota_error(struct super_block *sb, const char *func, const char *fmt, ...); /* * declaration of quota_function calls in kernel. */ int dquot_initialize(struct inode *inode); bool dquot_initialize_needed(struct inode *inode); void dquot_drop(struct inode *inode); struct dquot *dqget(struct super_block *sb, struct kqid qid); static inline struct dquot *dqgrab(struct dquot *dquot) { /* Make sure someone else has active reference to dquot */ WARN_ON_ONCE(!atomic_read(&dquot->dq_count)); WARN_ON_ONCE(!test_bit(DQ_ACTIVE_B, &dquot->dq_flags)); atomic_inc(&dquot->dq_count); return dquot; } static inline bool dquot_is_busy(struct dquot *dquot) { if (test_bit(DQ_MOD_B, &dquot->dq_flags)) return true; if (atomic_read(&dquot->dq_count) > 0) return true; return false; } void dqput(struct dquot *dquot); int dquot_scan_active(struct super_block *sb, int (*fn)(struct dquot *dquot, unsigned long priv), unsigned long priv); struct dquot *dquot_alloc(struct super_block *sb, int type); void dquot_destroy(struct dquot *dquot); int __dquot_alloc_space(struct inode *inode, qsize_t number, int flags); void __dquot_free_space(struct inode *inode, qsize_t number, int flags); int dquot_alloc_inode(struct inode *inode); void dquot_claim_space_nodirty(struct inode *inode, qsize_t number); void dquot_free_inode(struct inode *inode); void dquot_reclaim_space_nodirty(struct inode *inode, qsize_t number); int dquot_disable(struct super_block *sb, int type, unsigned int flags); /* Suspend quotas on remount RO */ static inline int dquot_suspend(struct super_block *sb, int type) { return dquot_disable(sb, type, DQUOT_SUSPENDED); } int dquot_resume(struct super_block *sb, int type); int dquot_commit(struct dquot *dquot); int dquot_acquire(struct dquot *dquot); int dquot_release(struct dquot *dquot); int dquot_commit_info(struct super_block *sb, int type); int dquot_get_next_id(struct super_block *sb, struct kqid *qid); int dquot_mark_dquot_dirty(struct dquot *dquot); int dquot_file_open(struct inode *inode, struct file *file); int dquot_load_quota_sb(struct super_block *sb, int type, int format_id, unsigned int flags); int dquot_load_quota_inode(struct inode *inode, int type, int format_id, unsigned int flags); int dquot_quota_on(struct super_block *sb, int type, int format_id, const struct path *path); int dquot_quota_on_mount(struct super_block *sb, char *qf_name, int format_id, int type); int dquot_quota_off(struct super_block *sb, int type); int dquot_writeback_dquots(struct super_block *sb, int type); int dquot_quota_sync(struct super_block *sb, int type); int dquot_get_state(struct super_block *sb, struct qc_state *state); int dquot_set_dqinfo(struct super_block *sb, int type, struct qc_info *ii); int dquot_get_dqblk(struct super_block *sb, struct kqid id, struct qc_dqblk *di); int dquot_get_next_dqblk(struct super_block *sb, struct kqid *id, struct qc_dqblk *di); int dquot_set_dqblk(struct super_block *sb, struct kqid id, struct qc_dqblk *di); int __dquot_transfer(struct inode *inode, struct dquot **transfer_to); int dquot_transfer(struct mnt_idmap *idmap, struct inode *inode, struct iattr *iattr); static inline struct mem_dqinfo *sb_dqinfo(struct super_block *sb, int type) { return sb_dqopt(sb)->info + type; } /* * Functions for checking status of quota */ static inline bool sb_has_quota_usage_enabled(struct super_block *sb, int type) { return sb_dqopt(sb)->flags & dquot_state_flag(DQUOT_USAGE_ENABLED, type); } static inline bool sb_has_quota_limits_enabled(struct super_block *sb, int type) { return sb_dqopt(sb)->flags & dquot_state_flag(DQUOT_LIMITS_ENABLED, type); } static inline bool sb_has_quota_suspended(struct super_block *sb, int type) { return sb_dqopt(sb)->flags & dquot_state_flag(DQUOT_SUSPENDED, type); } static inline unsigned sb_any_quota_suspended(struct super_block *sb) { return dquot_state_types(sb_dqopt(sb)->flags, DQUOT_SUSPENDED); } /* Does kernel know about any quota information for given sb + type? */ static inline bool sb_has_quota_loaded(struct super_block *sb, int type) { /* Currently if anything is on, then quota usage is on as well */ return sb_has_quota_usage_enabled(sb, type); } static inline unsigned sb_any_quota_loaded(struct super_block *sb) { return dquot_state_types(sb_dqopt(sb)->flags, DQUOT_USAGE_ENABLED); } static inline bool sb_has_quota_active(struct super_block *sb, int type) { return sb_has_quota_loaded(sb, type) && !sb_has_quota_suspended(sb, type); } /* * Operations supported for diskquotas. */ extern const struct dquot_operations dquot_operations; extern const struct quotactl_ops dquot_quotactl_sysfile_ops; #else static inline int sb_has_quota_usage_enabled(struct super_block *sb, int type) { return 0; } static inline int sb_has_quota_limits_enabled(struct super_block *sb, int type) { return 0; } static inline int sb_has_quota_suspended(struct super_block *sb, int type) { return 0; } static inline int sb_any_quota_suspended(struct super_block *sb) { return 0; } /* Does kernel know about any quota information for given sb + type? */ static inline int sb_has_quota_loaded(struct super_block *sb, int type) { return 0; } static inline int sb_any_quota_loaded(struct super_block *sb) { return 0; } static inline int sb_has_quota_active(struct super_block *sb, int type) { return 0; } static inline int dquot_initialize(struct inode *inode) { return 0; } static inline bool dquot_initialize_needed(struct inode *inode) { return false; } static inline void dquot_drop(struct inode *inode) { } static inline int dquot_alloc_inode(struct inode *inode) { return 0; } static inline void dquot_free_inode(struct inode *inode) { } static inline int dquot_transfer(struct mnt_idmap *idmap, struct inode *inode, struct iattr *iattr) { return 0; } static inline int __dquot_alloc_space(struct inode *inode, qsize_t number, int flags) { if (!(flags & DQUOT_SPACE_RESERVE)) inode_add_bytes(inode, number); return 0; } static inline void __dquot_free_space(struct inode *inode, qsize_t number, int flags) { if (!(flags & DQUOT_SPACE_RESERVE)) inode_sub_bytes(inode, number); } static inline void dquot_claim_space_nodirty(struct inode *inode, qsize_t number) { inode_add_bytes(inode, number); } static inline int dquot_reclaim_space_nodirty(struct inode *inode, qsize_t number) { inode_sub_bytes(inode, number); return 0; } static inline int dquot_disable(struct super_block *sb, int type, unsigned int flags) { return 0; } static inline int dquot_suspend(struct super_block *sb, int type) { return 0; } static inline int dquot_resume(struct super_block *sb, int type) { return 0; } #define dquot_file_open generic_file_open static inline int dquot_writeback_dquots(struct super_block *sb, int type) { return 0; } #endif /* CONFIG_QUOTA */ static inline int dquot_alloc_space_nodirty(struct inode *inode, qsize_t nr) { return __dquot_alloc_space(inode, nr, DQUOT_SPACE_WARN); } static inline void dquot_alloc_space_nofail(struct inode *inode, qsize_t nr) { __dquot_alloc_space(inode, nr, DQUOT_SPACE_WARN|DQUOT_SPACE_NOFAIL); mark_inode_dirty_sync(inode); } static inline int dquot_alloc_space(struct inode *inode, qsize_t nr) { int ret; ret = dquot_alloc_space_nodirty(inode, nr); if (!ret) { /* * Mark inode fully dirty. Since we are allocating blocks, inode * would become fully dirty soon anyway and it reportedly * reduces lock contention. */ mark_inode_dirty(inode); } return ret; } static inline int dquot_alloc_block_nodirty(struct inode *inode, qsize_t nr) { return dquot_alloc_space_nodirty(inode, nr << inode->i_blkbits); } static inline void dquot_alloc_block_nofail(struct inode *inode, qsize_t nr) { dquot_alloc_space_nofail(inode, nr << inode->i_blkbits); } static inline int dquot_alloc_block(struct inode *inode, qsize_t nr) { return dquot_alloc_space(inode, nr << inode->i_blkbits); } static inline int dquot_prealloc_block_nodirty(struct inode *inode, qsize_t nr) { return __dquot_alloc_space(inode, nr << inode->i_blkbits, 0); } static inline int dquot_prealloc_block(struct inode *inode, qsize_t nr) { int ret; ret = dquot_prealloc_block_nodirty(inode, nr); if (!ret) mark_inode_dirty_sync(inode); return ret; } static inline int dquot_reserve_block(struct inode *inode, qsize_t nr) { return __dquot_alloc_space(inode, nr << inode->i_blkbits, DQUOT_SPACE_WARN|DQUOT_SPACE_RESERVE); } static inline void dquot_claim_block(struct inode *inode, qsize_t nr) { dquot_claim_space_nodirty(inode, nr << inode->i_blkbits); mark_inode_dirty_sync(inode); } static inline void dquot_reclaim_block(struct inode *inode, qsize_t nr) { dquot_reclaim_space_nodirty(inode, nr << inode->i_blkbits); mark_inode_dirty_sync(inode); } static inline void dquot_free_space_nodirty(struct inode *inode, qsize_t nr) { __dquot_free_space(inode, nr, 0); } static inline void dquot_free_space(struct inode *inode, qsize_t nr) { dquot_free_space_nodirty(inode, nr); mark_inode_dirty_sync(inode); } static inline void dquot_free_block_nodirty(struct inode *inode, qsize_t nr) { dquot_free_space_nodirty(inode, nr << inode->i_blkbits); } static inline void dquot_free_block(struct inode *inode, qsize_t nr) { dquot_free_space(inode, nr << inode->i_blkbits); } static inline void dquot_release_reservation_block(struct inode *inode, qsize_t nr) { __dquot_free_space(inode, nr << inode->i_blkbits, DQUOT_SPACE_RESERVE); } unsigned int qtype_enforce_flag(int type); #endif /* _LINUX_QUOTAOPS_ */ |
| 15 15 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 | // SPDX-License-Identifier: GPL-2.0-only /* * AppArmor security module * * This file contains AppArmor task related definitions and mediation * * Copyright 2017 Canonical Ltd. * * TODO * If a task uses change_hat it currently does not return to the old * cred or task context but instead creates a new one. Ideally the task * should return to the previous cred if it has not been modified. */ #include <linux/gfp.h> #include <linux/ptrace.h> #include "include/audit.h" #include "include/cred.h" #include "include/policy.h" #include "include/task.h" /** * aa_get_task_label - Get another task's label * @task: task to query (NOT NULL) * * Returns: counted reference to @task's label */ struct aa_label *aa_get_task_label(struct task_struct *task) { struct aa_label *p; rcu_read_lock(); p = aa_get_newest_cred_label(__task_cred(task)); rcu_read_unlock(); return p; } /** * aa_replace_current_label - replace the current tasks label * @label: new label (NOT NULL) * * Returns: 0 or error on failure */ int aa_replace_current_label(struct aa_label *label) { struct aa_label *old = aa_current_raw_label(); struct aa_task_ctx *ctx = task_ctx(current); struct cred *new; AA_BUG(!label); if (old == label) return 0; if (current_cred() != current_real_cred()) return -EBUSY; new = prepare_creds(); if (!new) return -ENOMEM; if (ctx->nnp && label_is_stale(ctx->nnp)) { struct aa_label *tmp = ctx->nnp; ctx->nnp = aa_get_newest_label(tmp); aa_put_label(tmp); } if (unconfined(label) || (labels_ns(old) != labels_ns(label))) /* * if switching to unconfined or a different label namespace * clear out context state */ aa_clear_task_ctx_trans(task_ctx(current)); /* * be careful switching cred label, when racing replacement it * is possible that the cred labels's->proxy->label is the reference * keeping @label valid, so make sure to get its reference before * dropping the reference on the cred's label */ aa_get_label(label); aa_put_label(cred_label(new)); set_cred_label(new, label); commit_creds(new); return 0; } /** * aa_set_current_onexec - set the tasks change_profile to happen onexec * @label: system label to set at exec (MAYBE NULL to clear value) * @stack: whether stacking should be done */ void aa_set_current_onexec(struct aa_label *label, bool stack) { struct aa_task_ctx *ctx = task_ctx(current); aa_get_label(label); aa_put_label(ctx->onexec); ctx->onexec = label; ctx->token = stack; } /** * aa_set_current_hat - set the current tasks hat * @label: label to set as the current hat (NOT NULL) * @token: token value that must be specified to change from the hat * * Do switch of tasks hat. If the task is currently in a hat * validate the token to match. * * Returns: 0 or error on failure */ int aa_set_current_hat(struct aa_label *label, u64 token) { struct aa_task_ctx *ctx = task_ctx(current); struct cred *new; new = prepare_creds(); if (!new) return -ENOMEM; AA_BUG(!label); if (!ctx->previous) { /* transfer refcount */ ctx->previous = cred_label(new); ctx->token = token; } else if (ctx->token == token) { aa_put_label(cred_label(new)); } else { /* previous_profile && ctx->token != token */ abort_creds(new); return -EACCES; } set_cred_label(new, aa_get_newest_label(label)); /* clear exec on switching context */ aa_put_label(ctx->onexec); ctx->onexec = NULL; commit_creds(new); return 0; } /** * aa_restore_previous_label - exit from hat context restoring previous label * @token: the token that must be matched to exit hat context * * Attempt to return out of a hat to the previous label. The token * must match the stored token value. * * Returns: 0 or error of failure */ int aa_restore_previous_label(u64 token) { struct aa_task_ctx *ctx = task_ctx(current); struct cred *new; if (ctx->token != token) return -EACCES; /* ignore restores when there is no saved label */ if (!ctx->previous) return 0; new = prepare_creds(); if (!new) return -ENOMEM; aa_put_label(cred_label(new)); set_cred_label(new, aa_get_newest_label(ctx->previous)); AA_BUG(!cred_label(new)); /* clear exec && prev information when restoring to previous context */ aa_clear_task_ctx_trans(ctx); commit_creds(new); return 0; } /** * audit_ptrace_mask - convert mask to permission string * @mask: permission mask to convert * * Returns: pointer to static string */ static const char *audit_ptrace_mask(u32 mask) { switch (mask) { case MAY_READ: return "read"; case MAY_WRITE: return "trace"; case AA_MAY_BE_READ: return "readby"; case AA_MAY_BE_TRACED: return "tracedby"; } return ""; } /* call back to audit ptrace fields */ static void audit_ptrace_cb(struct audit_buffer *ab, void *va) { struct common_audit_data *sa = va; struct apparmor_audit_data *ad = aad(sa); if (ad->request & AA_PTRACE_PERM_MASK) { audit_log_format(ab, " requested_mask=\"%s\"", audit_ptrace_mask(ad->request)); if (ad->denied & AA_PTRACE_PERM_MASK) { audit_log_format(ab, " denied_mask=\"%s\"", audit_ptrace_mask(ad->denied)); } } audit_log_format(ab, " peer="); aa_label_xaudit(ab, labels_ns(ad->subj_label), ad->peer, FLAGS_NONE, GFP_ATOMIC); } /* assumes check for RULE_MEDIATES is already done */ /* TODO: conditionals */ static int profile_ptrace_perm(const struct cred *cred, struct aa_profile *profile, struct aa_label *peer, u32 request, struct apparmor_audit_data *ad) { struct aa_ruleset *rules = list_first_entry(&profile->rules, typeof(*rules), list); struct aa_perms perms = { }; ad->subj_cred = cred; ad->peer = peer; aa_profile_match_label(profile, rules, peer, AA_CLASS_PTRACE, request, &perms); aa_apply_modes_to_perms(profile, &perms); return aa_check_perms(profile, &perms, request, ad, audit_ptrace_cb); } static int profile_tracee_perm(const struct cred *cred, struct aa_profile *tracee, struct aa_label *tracer, u32 request, struct apparmor_audit_data *ad) { if (profile_unconfined(tracee) || unconfined(tracer) || !ANY_RULE_MEDIATES(&tracee->rules, AA_CLASS_PTRACE)) return 0; return profile_ptrace_perm(cred, tracee, tracer, request, ad); } static int profile_tracer_perm(const struct cred *cred, struct aa_profile *tracer, struct aa_label *tracee, u32 request, struct apparmor_audit_data *ad) { if (profile_unconfined(tracer)) return 0; if (ANY_RULE_MEDIATES(&tracer->rules, AA_CLASS_PTRACE)) return profile_ptrace_perm(cred, tracer, tracee, request, ad); /* profile uses the old style capability check for ptrace */ if (&tracer->label == tracee) return 0; ad->subj_label = &tracer->label; ad->peer = tracee; ad->request = 0; ad->error = aa_capable(cred, &tracer->label, CAP_SYS_PTRACE, CAP_OPT_NONE); return aa_audit(AUDIT_APPARMOR_AUTO, tracer, ad, audit_ptrace_cb); } /** * aa_may_ptrace - test if tracer task can trace the tracee * @tracer_cred: cred of task doing the tracing (NOT NULL) * @tracer: label of the task doing the tracing (NOT NULL) * @tracee_cred: cred of task to be traced * @tracee: task label to be traced * @request: permission request * * Returns: %0 else error code if permission denied or error */ int aa_may_ptrace(const struct cred *tracer_cred, struct aa_label *tracer, const struct cred *tracee_cred, struct aa_label *tracee, u32 request) { struct aa_profile *profile; u32 xrequest = request << PTRACE_PERM_SHIFT; DEFINE_AUDIT_DATA(sa, LSM_AUDIT_DATA_NONE, AA_CLASS_PTRACE, OP_PTRACE); return xcheck_labels(tracer, tracee, profile, profile_tracer_perm(tracer_cred, profile, tracee, request, &sa), profile_tracee_perm(tracee_cred, profile, tracer, xrequest, &sa)); } /* call back to audit ptrace fields */ static void audit_ns_cb(struct audit_buffer *ab, void *va) { struct apparmor_audit_data *ad = aad_of_va(va); if (ad->request & AA_USERNS_CREATE) audit_log_format(ab, " requested=\"userns_create\""); if (ad->denied & AA_USERNS_CREATE) audit_log_format(ab, " denied=\"userns_create\""); } int aa_profile_ns_perm(struct aa_profile *profile, struct apparmor_audit_data *ad, u32 request) { struct aa_perms perms = { }; int error = 0; ad->subj_label = &profile->label; ad->request = request; if (!profile_unconfined(profile)) { struct aa_ruleset *rules = list_first_entry(&profile->rules, typeof(*rules), list); aa_state_t state; state = RULE_MEDIATES(rules, ad->class); if (!state) /* TODO: add flag to complain about unmediated */ return 0; perms = *aa_lookup_perms(rules->policy, state); aa_apply_modes_to_perms(profile, &perms); error = aa_check_perms(profile, &perms, request, ad, audit_ns_cb); } return error; } |
| 3 3 3 1 2 15 15 2 3 1 24 24 | 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 | // SPDX-License-Identifier: GPL-2.0-or-later /* * * Bluetooth virtual HCI driver * * Copyright (C) 2000-2001 Qualcomm Incorporated * Copyright (C) 2002-2003 Maxim Krasnyansky <maxk@qualcomm.com> * Copyright (C) 2004-2006 Marcel Holtmann <marcel@holtmann.org> */ #include <linux/module.h> #include <linux/unaligned.h> #include <linux/atomic.h> #include <linux/kernel.h> #include <linux/init.h> #include <linux/slab.h> #include <linux/types.h> #include <linux/errno.h> #include <linux/sched.h> #include <linux/poll.h> #include <linux/skbuff.h> #include <linux/miscdevice.h> #include <linux/debugfs.h> #include <net/bluetooth/bluetooth.h> #include <net/bluetooth/hci_core.h> #define VERSION "1.5" static bool amp; struct vhci_data { struct hci_dev *hdev; wait_queue_head_t read_wait; struct sk_buff_head readq; struct mutex open_mutex; struct delayed_work open_timeout; struct work_struct suspend_work; bool suspended; bool wakeup; __u16 msft_opcode; bool aosp_capable; atomic_t initialized; }; static int vhci_open_dev(struct hci_dev *hdev) { return 0; } static int vhci_close_dev(struct hci_dev *hdev) { struct vhci_data *data = hci_get_drvdata(hdev); skb_queue_purge(&data->readq); return 0; } static int vhci_flush(struct hci_dev *hdev) { struct vhci_data *data = hci_get_drvdata(hdev); skb_queue_purge(&data->readq); return 0; } static int vhci_send_frame(struct hci_dev *hdev, struct sk_buff *skb) { struct vhci_data *data = hci_get_drvdata(hdev); memcpy(skb_push(skb, 1), &hci_skb_pkt_type(skb), 1); skb_queue_tail(&data->readq, skb); if (atomic_read(&data->initialized)) wake_up_interruptible(&data->read_wait); return 0; } static int vhci_get_data_path_id(struct hci_dev *hdev, u8 *data_path_id) { *data_path_id = 0; return 0; } static int vhci_get_codec_config_data(struct hci_dev *hdev, __u8 type, struct bt_codec *codec, __u8 *vnd_len, __u8 **vnd_data) { if (type != ESCO_LINK) return -EINVAL; *vnd_len = 0; *vnd_data = NULL; return 0; } static bool vhci_wakeup(struct hci_dev *hdev) { struct vhci_data *data = hci_get_drvdata(hdev); return data->wakeup; } static ssize_t force_suspend_read(struct file *file, char __user *user_buf, size_t count, loff_t *ppos) { struct vhci_data *data = file->private_data; char buf[3]; buf[0] = data->suspended ? 'Y' : 'N'; buf[1] = '\n'; buf[2] = '\0'; return simple_read_from_buffer(user_buf, count, ppos, buf, 2); } static void vhci_suspend_work(struct work_struct *work) { struct vhci_data *data = container_of(work, struct vhci_data, suspend_work); if (data->suspended) hci_suspend_dev(data->hdev); else hci_resume_dev(data->hdev); } static ssize_t force_suspend_write(struct file *file, const char __user *user_buf, size_t count, loff_t *ppos) { struct vhci_data *data = file->private_data; bool enable; int err; err = kstrtobool_from_user(user_buf, count, &enable); if (err) return err; if (data->suspended == enable) return -EALREADY; data->suspended = enable; schedule_work(&data->suspend_work); return count; } static const struct file_operations force_suspend_fops = { .open = simple_open, .read = force_suspend_read, .write = force_suspend_write, .llseek = default_llseek, }; static ssize_t force_wakeup_read(struct file *file, char __user *user_buf, size_t count, loff_t *ppos) { struct vhci_data *data = file->private_data; char buf[3]; buf[0] = data->wakeup ? 'Y' : 'N'; buf[1] = '\n'; buf[2] = '\0'; return simple_read_from_buffer(user_buf, count, ppos, buf, 2); } static ssize_t force_wakeup_write(struct file *file, const char __user *user_buf, size_t count, loff_t *ppos) { struct vhci_data *data = file->private_data; bool enable; int err; err = kstrtobool_from_user(user_buf, count, &enable); if (err) return err; if (data->wakeup == enable) return -EALREADY; data->wakeup = enable; return count; } static const struct file_operations force_wakeup_fops = { .open = simple_open, .read = force_wakeup_read, .write = force_wakeup_write, .llseek = default_llseek, }; static int msft_opcode_set(void *data, u64 val) { struct vhci_data *vhci = data; if (val > 0xffff || hci_opcode_ogf(val) != 0x3f) return -EINVAL; if (vhci->msft_opcode) return -EALREADY; vhci->msft_opcode = val; return 0; } static int msft_opcode_get(void *data, u64 *val) { struct vhci_data *vhci = data; *val = vhci->msft_opcode; return 0; } DEFINE_DEBUGFS_ATTRIBUTE(msft_opcode_fops, msft_opcode_get, msft_opcode_set, "%llu\n"); static ssize_t aosp_capable_read(struct file *file, char __user *user_buf, size_t count, loff_t *ppos) { struct vhci_data *vhci = file->private_data; char buf[3]; buf[0] = vhci->aosp_capable ? 'Y' : 'N'; buf[1] = '\n'; buf[2] = '\0'; return simple_read_from_buffer(user_buf, count, ppos, buf, 2); } static ssize_t aosp_capable_write(struct file *file, const char __user *user_buf, size_t count, loff_t *ppos) { struct vhci_data *vhci = file->private_data; bool enable; int err; err = kstrtobool_from_user(user_buf, count, &enable); if (err) return err; if (!enable) return -EINVAL; if (vhci->aosp_capable) return -EALREADY; vhci->aosp_capable = enable; return count; } static const struct file_operations aosp_capable_fops = { .open = simple_open, .read = aosp_capable_read, .write = aosp_capable_write, .llseek = default_llseek, }; static int vhci_setup(struct hci_dev *hdev) { struct vhci_data *vhci = hci_get_drvdata(hdev); if (vhci->msft_opcode) hci_set_msft_opcode(hdev, vhci->msft_opcode); if (vhci->aosp_capable) hci_set_aosp_capable(hdev); return 0; } static void vhci_coredump(struct hci_dev *hdev) { /* No need to do anything */ } static void vhci_coredump_hdr(struct hci_dev *hdev, struct sk_buff *skb) { char buf[80]; snprintf(buf, sizeof(buf), "Controller Name: vhci_ctrl\n"); skb_put_data(skb, buf, strlen(buf)); snprintf(buf, sizeof(buf), "Firmware Version: vhci_fw\n"); skb_put_data(skb, buf, strlen(buf)); snprintf(buf, sizeof(buf), "Driver: vhci_drv\n"); skb_put_data(skb, buf, strlen(buf)); snprintf(buf, sizeof(buf), "Vendor: vhci\n"); skb_put_data(skb, buf, strlen(buf)); } #define MAX_COREDUMP_LINE_LEN 40 struct devcoredump_test_data { enum devcoredump_state state; unsigned int timeout; char data[MAX_COREDUMP_LINE_LEN]; }; static inline void force_devcd_timeout(struct hci_dev *hdev, unsigned int timeout) { #ifdef CONFIG_DEV_COREDUMP hdev->dump.timeout = msecs_to_jiffies(timeout * 1000); #endif } static ssize_t force_devcd_write(struct file *file, const char __user *user_buf, size_t count, loff_t *ppos) { struct vhci_data *data = file->private_data; struct hci_dev *hdev = data->hdev; struct sk_buff *skb = NULL; struct devcoredump_test_data dump_data; size_t data_size; int ret; if (count < offsetof(struct devcoredump_test_data, data) || count > sizeof(dump_data)) return -EINVAL; if (copy_from_user(&dump_data, user_buf, count)) return -EFAULT; data_size = count - offsetof(struct devcoredump_test_data, data); skb = alloc_skb(data_size, GFP_ATOMIC); if (!skb) return -ENOMEM; skb_put_data(skb, &dump_data.data, data_size); hci_devcd_register(hdev, vhci_coredump, vhci_coredump_hdr, NULL); /* Force the devcoredump timeout */ if (dump_data.timeout) force_devcd_timeout(hdev, dump_data.timeout); ret = hci_devcd_init(hdev, skb->len); if (ret) { BT_ERR("Failed to generate devcoredump"); kfree_skb(skb); return ret; } hci_devcd_append(hdev, skb); switch (dump_data.state) { case HCI_DEVCOREDUMP_DONE: hci_devcd_complete(hdev); break; case HCI_DEVCOREDUMP_ABORT: hci_devcd_abort(hdev); break; case HCI_DEVCOREDUMP_TIMEOUT: /* Do nothing */ break; default: return -EINVAL; } return count; } static const struct file_operations force_devcoredump_fops = { .open = simple_open, .write = force_devcd_write, }; static int __vhci_create_device(struct vhci_data *data, __u8 opcode) { struct hci_dev *hdev; struct sk_buff *skb; if (data->hdev) return -EBADFD; /* bits 2-5 are reserved (must be zero) */ if (opcode & 0x3c) return -EINVAL; skb = bt_skb_alloc(4, GFP_KERNEL); if (!skb) return -ENOMEM; hdev = hci_alloc_dev(); if (!hdev) { kfree_skb(skb); return -ENOMEM; } data->hdev = hdev; hdev->bus = HCI_VIRTUAL; hci_set_drvdata(hdev, data); hdev->open = vhci_open_dev; hdev->close = vhci_close_dev; hdev->flush = vhci_flush; hdev->send = vhci_send_frame; hdev->get_data_path_id = vhci_get_data_path_id; hdev->get_codec_config_data = vhci_get_codec_config_data; hdev->wakeup = vhci_wakeup; hdev->setup = vhci_setup; set_bit(HCI_QUIRK_NON_PERSISTENT_SETUP, &hdev->quirks); /* bit 6 is for external configuration */ if (opcode & 0x40) set_bit(HCI_QUIRK_EXTERNAL_CONFIG, &hdev->quirks); /* bit 7 is for raw device */ if (opcode & 0x80) set_bit(HCI_QUIRK_RAW_DEVICE, &hdev->quirks); if (hci_register_dev(hdev) < 0) { BT_ERR("Can't register HCI device"); hci_free_dev(hdev); data->hdev = NULL; kfree_skb(skb); return -EBUSY; } debugfs_create_file("force_suspend", 0644, hdev->debugfs, data, &force_suspend_fops); debugfs_create_file("force_wakeup", 0644, hdev->debugfs, data, &force_wakeup_fops); if (IS_ENABLED(CONFIG_BT_MSFTEXT)) debugfs_create_file("msft_opcode", 0644, hdev->debugfs, data, &msft_opcode_fops); if (IS_ENABLED(CONFIG_BT_AOSPEXT)) debugfs_create_file("aosp_capable", 0644, hdev->debugfs, data, &aosp_capable_fops); debugfs_create_file("force_devcoredump", 0644, hdev->debugfs, data, &force_devcoredump_fops); hci_skb_pkt_type(skb) = HCI_VENDOR_PKT; skb_put_u8(skb, 0xff); skb_put_u8(skb, opcode); put_unaligned_le16(hdev->id, skb_put(skb, 2)); skb_queue_head(&data->readq, skb); atomic_inc(&data->initialized); wake_up_interruptible(&data->read_wait); return 0; } static int vhci_create_device(struct vhci_data *data, __u8 opcode) { int err; mutex_lock(&data->open_mutex); err = __vhci_create_device(data, opcode); mutex_unlock(&data->open_mutex); return err; } static inline ssize_t vhci_get_user(struct vhci_data *data, struct iov_iter *from) { size_t len = iov_iter_count(from); struct sk_buff *skb; __u8 pkt_type, opcode; int ret; if (len < 2 || len > HCI_MAX_FRAME_SIZE) return -EINVAL; skb = bt_skb_alloc(len, GFP_KERNEL); if (!skb) return -ENOMEM; if (!copy_from_iter_full(skb_put(skb, len), len, from)) { kfree_skb(skb); return -EFAULT; } pkt_type = *((__u8 *) skb->data); skb_pull(skb, 1); switch (pkt_type) { case HCI_EVENT_PKT: case HCI_ACLDATA_PKT: case HCI_SCODATA_PKT: case HCI_ISODATA_PKT: if (!data->hdev) { kfree_skb(skb); return -ENODEV; } hci_skb_pkt_type(skb) = pkt_type; ret = hci_recv_frame(data->hdev, skb); break; case HCI_VENDOR_PKT: cancel_delayed_work_sync(&data->open_timeout); opcode = *((__u8 *) skb->data); skb_pull(skb, 1); if (skb->len > 0) { kfree_skb(skb); return -EINVAL; } kfree_skb(skb); ret = vhci_create_device(data, opcode); break; default: kfree_skb(skb); return -EINVAL; } return (ret < 0) ? ret : len; } static inline ssize_t vhci_put_user(struct vhci_data *data, struct sk_buff *skb, char __user *buf, int count) { char __user *ptr = buf; int len; len = min_t(unsigned int, skb->len, count); if (copy_to_user(ptr, skb->data, len)) return -EFAULT; if (!data->hdev) return len; data->hdev->stat.byte_tx += len; switch (hci_skb_pkt_type(skb)) { case HCI_COMMAND_PKT: data->hdev->stat.cmd_tx++; break; case HCI_ACLDATA_PKT: data->hdev->stat.acl_tx++; break; case HCI_SCODATA_PKT: data->hdev->stat.sco_tx++; break; } return len; } static ssize_t vhci_read(struct file *file, char __user *buf, size_t count, loff_t *pos) { struct vhci_data *data = file->private_data; struct sk_buff *skb; ssize_t ret = 0; while (count) { skb = skb_dequeue(&data->readq); if (skb) { ret = vhci_put_user(data, skb, buf, count); if (ret < 0) skb_queue_head(&data->readq, skb); else kfree_skb(skb); break; } if (file->f_flags & O_NONBLOCK) { ret = -EAGAIN; break; } ret = wait_event_interruptible(data->read_wait, !skb_queue_empty(&data->readq)); if (ret < 0) break; } return ret; } static ssize_t vhci_write(struct kiocb *iocb, struct iov_iter *from) { struct file *file = iocb->ki_filp; struct vhci_data *data = file->private_data; return vhci_get_user(data, from); } static __poll_t vhci_poll(struct file *file, poll_table *wait) { struct vhci_data *data = file->private_data; poll_wait(file, &data->read_wait, wait); if (!skb_queue_empty(&data->readq)) return EPOLLIN | EPOLLRDNORM; return EPOLLOUT | EPOLLWRNORM; } static void vhci_open_timeout(struct work_struct *work) { struct vhci_data *data = container_of(work, struct vhci_data, open_timeout.work); vhci_create_device(data, 0x00); } static int vhci_open(struct inode *inode, struct file *file) { struct vhci_data *data; data = kzalloc(sizeof(*data), GFP_KERNEL); if (!data) return -ENOMEM; skb_queue_head_init(&data->readq); init_waitqueue_head(&data->read_wait); mutex_init(&data->open_mutex); INIT_DELAYED_WORK(&data->open_timeout, vhci_open_timeout); INIT_WORK(&data->suspend_work, vhci_suspend_work); file->private_data = data; nonseekable_open(inode, file); schedule_delayed_work(&data->open_timeout, msecs_to_jiffies(1000)); return 0; } static int vhci_release(struct inode *inode, struct file *file) { struct vhci_data *data = file->private_data; struct hci_dev *hdev; cancel_delayed_work_sync(&data->open_timeout); flush_work(&data->suspend_work); hdev = data->hdev; if (hdev) { hci_unregister_dev(hdev); hci_free_dev(hdev); } skb_queue_purge(&data->readq); file->private_data = NULL; kfree(data); return 0; } static const struct file_operations vhci_fops = { .owner = THIS_MODULE, .read = vhci_read, .write_iter = vhci_write, .poll = vhci_poll, .open = vhci_open, .release = vhci_release, }; static struct miscdevice vhci_miscdev = { .name = "vhci", .fops = &vhci_fops, .minor = VHCI_MINOR, }; module_misc_device(vhci_miscdev); module_param(amp, bool, 0644); MODULE_PARM_DESC(amp, "Create AMP controller device"); MODULE_AUTHOR("Marcel Holtmann <marcel@holtmann.org>"); MODULE_DESCRIPTION("Bluetooth virtual HCI driver ver " VERSION); MODULE_VERSION(VERSION); MODULE_LICENSE("GPL"); MODULE_ALIAS("devname:vhci"); MODULE_ALIAS_MISCDEV(VHCI_MINOR); |
| 106 22 320 398 90 154 99 90 91 91 91 197 196 195 194 117 154 181 99 197 197 43 197 196 42 91 91 91 91 90 39 91 88 90 91 90 91 91 91 91 91 91 91 39 90 91 91 69 91 16 16 39 39 38 39 39 14 14 13 14 14 14 14 63 62 63 63 63 238 237 238 30 237 317 283 307 213 63 307 306 319 320 317 319 319 320 91 91 317 91 307 14 14 307 63 304 107 98 19 4 118 11 330 330 216 330 329 328 235 24 125 211 6 224 118 100 69 69 69 118 118 118 216 118 10 133 123 134 134 5 138 11 2 1 325 2 326 130 179 9 5 118 5 109 2 9 3 7 9 108 109 1 128 101 118 197 2 749 752 746 969 972 131 967 969 559 958 965 333 421 348 384 341 398 46 46 151 795 749 750 748 750 751 749 133 132 60 106 133 133 40 10 247 141 140 1 139 128 132 127 5 133 133 1 131 1 131 4 132 133 66 123 30 30 30 30 30 30 30 30 30 30 30 30 21 18 16 16 16 16 16 16 16 16 16 16 16 16 16 16 16 16 16 16 212 212 206 212 212 212 211 212 212 212 211 212 106 212 212 212 210 14 212 16 14 14 1 14 14 14 14 14 14 14 97 98 59 59 | 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 | // SPDX-License-Identifier: GPL-2.0-or-later /* * * Robert Olsson <robert.olsson@its.uu.se> Uppsala Universitet * & Swedish University of Agricultural Sciences. * * Jens Laas <jens.laas@data.slu.se> Swedish University of * Agricultural Sciences. * * Hans Liss <hans.liss@its.uu.se> Uppsala Universitet * * This work is based on the LPC-trie which is originally described in: * * An experimental study of compression methods for dynamic tries * Stefan Nilsson and Matti Tikkanen. Algorithmica, 33(1):19-33, 2002. * https://www.csc.kth.se/~snilsson/software/dyntrie2/ * * IP-address lookup using LC-tries. Stefan Nilsson and Gunnar Karlsson * IEEE Journal on Selected Areas in Communications, 17(6):1083-1092, June 1999 * * Code from fib_hash has been reused which includes the following header: * * INET An implementation of the TCP/IP protocol suite for the LINUX * operating system. INET is implemented using the BSD Socket * interface as the means of communication with the user level. * * IPv4 FIB: lookup engine and maintenance routines. * * Authors: Alexey Kuznetsov, <kuznet@ms2.inr.ac.ru> * * Substantial contributions to this work comes from: * * David S. Miller, <davem@davemloft.net> * Stephen Hemminger <shemminger@osdl.org> * Paul E. McKenney <paulmck@us.ibm.com> * Patrick McHardy <kaber@trash.net> */ #include <linux/cache.h> #include <linux/uaccess.h> #include <linux/bitops.h> #include <linux/types.h> #include <linux/kernel.h> #include <linux/mm.h> #include <linux/string.h> #include <linux/socket.h> #include <linux/sockios.h> #include <linux/errno.h> #include <linux/in.h> #include <linux/inet.h> #include <linux/inetdevice.h> #include <linux/netdevice.h> #include <linux/if_arp.h> #include <linux/proc_fs.h> #include <linux/rcupdate.h> #include <linux/rcupdate_wait.h> #include <linux/skbuff.h> #include <linux/netlink.h> #include <linux/init.h> #include <linux/list.h> #include <linux/slab.h> #include <linux/export.h> #include <linux/vmalloc.h> #include <linux/notifier.h> #include <net/net_namespace.h> #include <net/inet_dscp.h> #include <net/ip.h> #include <net/protocol.h> #include <net/route.h> #include <net/tcp.h> #include <net/sock.h> #include <net/ip_fib.h> #include <net/fib_notifier.h> #include <trace/events/fib.h> #include "fib_lookup.h" static int call_fib_entry_notifier(struct notifier_block *nb, enum fib_event_type event_type, u32 dst, int dst_len, struct fib_alias *fa, struct netlink_ext_ack *extack) { struct fib_entry_notifier_info info = { .info.extack = extack, .dst = dst, .dst_len = dst_len, .fi = fa->fa_info, .dscp = fa->fa_dscp, .type = fa->fa_type, .tb_id = fa->tb_id, }; return call_fib4_notifier(nb, event_type, &info.info); } static int call_fib_entry_notifiers(struct net *net, enum fib_event_type event_type, u32 dst, int dst_len, struct fib_alias *fa, struct netlink_ext_ack *extack) { struct fib_entry_notifier_info info = { .info.extack = extack, .dst = dst, .dst_len = dst_len, .fi = fa->fa_info, .dscp = fa->fa_dscp, .type = fa->fa_type, .tb_id = fa->tb_id, }; return call_fib4_notifiers(net, event_type, &info.info); } #define MAX_STAT_DEPTH 32 #define KEYLENGTH (8*sizeof(t_key)) #define KEY_MAX ((t_key)~0) typedef unsigned int t_key; #define IS_TRIE(n) ((n)->pos >= KEYLENGTH) #define IS_TNODE(n) ((n)->bits) #define IS_LEAF(n) (!(n)->bits) struct key_vector { t_key key; unsigned char pos; /* 2log(KEYLENGTH) bits needed */ unsigned char bits; /* 2log(KEYLENGTH) bits needed */ unsigned char slen; union { /* This list pointer if valid if (pos | bits) == 0 (LEAF) */ struct hlist_head leaf; /* This array is valid if (pos | bits) > 0 (TNODE) */ DECLARE_FLEX_ARRAY(struct key_vector __rcu *, tnode); }; }; struct tnode { struct rcu_head rcu; t_key empty_children; /* KEYLENGTH bits needed */ t_key full_children; /* KEYLENGTH bits needed */ struct key_vector __rcu *parent; struct key_vector kv[1]; #define tn_bits kv[0].bits }; #define TNODE_SIZE(n) offsetof(struct tnode, kv[0].tnode[n]) #define LEAF_SIZE TNODE_SIZE(1) #ifdef CONFIG_IP_FIB_TRIE_STATS struct trie_use_stats { unsigned int gets; unsigned int backtrack; unsigned int semantic_match_passed; unsigned int semantic_match_miss; unsigned int null_node_hit; unsigned int resize_node_skipped; }; #endif struct trie_stat { unsigned int totdepth; unsigned int maxdepth; unsigned int tnodes; unsigned int leaves; unsigned int nullpointers; unsigned int prefixes; unsigned int nodesizes[MAX_STAT_DEPTH]; }; struct trie { struct key_vector kv[1]; #ifdef CONFIG_IP_FIB_TRIE_STATS struct trie_use_stats __percpu *stats; #endif }; static struct key_vector *resize(struct trie *t, struct key_vector *tn); static unsigned int tnode_free_size; /* * synchronize_rcu after call_rcu for outstanding dirty memory; it should be * especially useful before resizing the root node with PREEMPT_NONE configs; * the value was obtained experimentally, aiming to avoid visible slowdown. */ unsigned int sysctl_fib_sync_mem = 512 * 1024; unsigned int sysctl_fib_sync_mem_min = 64 * 1024; unsigned int sysctl_fib_sync_mem_max = 64 * 1024 * 1024; static struct kmem_cache *fn_alias_kmem __ro_after_init; static struct kmem_cache *trie_leaf_kmem __ro_after_init; static inline struct tnode *tn_info(struct key_vector *kv) { return container_of(kv, struct tnode, kv[0]); } /* caller must hold RTNL */ #define node_parent(tn) rtnl_dereference(tn_info(tn)->parent) #define get_child(tn, i) rtnl_dereference((tn)->tnode[i]) /* caller must hold RCU read lock or RTNL */ #define node_parent_rcu(tn) rcu_dereference_rtnl(tn_info(tn)->parent) #define get_child_rcu(tn, i) rcu_dereference_rtnl((tn)->tnode[i]) /* wrapper for rcu_assign_pointer */ static inline void node_set_parent(struct key_vector *n, struct key_vector *tp) { if (n) rcu_assign_pointer(tn_info(n)->parent, tp); } #define NODE_INIT_PARENT(n, p) RCU_INIT_POINTER(tn_info(n)->parent, p) /* This provides us with the number of children in this node, in the case of a * leaf this will return 0 meaning none of the children are accessible. */ static inline unsigned long child_length(const struct key_vector *tn) { return (1ul << tn->bits) & ~(1ul); } #define get_cindex(key, kv) (((key) ^ (kv)->key) >> (kv)->pos) static inline unsigned long get_index(t_key key, struct key_vector *kv) { unsigned long index = key ^ kv->key; if ((BITS_PER_LONG <= KEYLENGTH) && (KEYLENGTH == kv->pos)) return 0; return index >> kv->pos; } /* To understand this stuff, an understanding of keys and all their bits is * necessary. Every node in the trie has a key associated with it, but not * all of the bits in that key are significant. * * Consider a node 'n' and its parent 'tp'. * * If n is a leaf, every bit in its key is significant. Its presence is * necessitated by path compression, since during a tree traversal (when * searching for a leaf - unless we are doing an insertion) we will completely * ignore all skipped bits we encounter. Thus we need to verify, at the end of * a potentially successful search, that we have indeed been walking the * correct key path. * * Note that we can never "miss" the correct key in the tree if present by * following the wrong path. Path compression ensures that segments of the key * that are the same for all keys with a given prefix are skipped, but the * skipped part *is* identical for each node in the subtrie below the skipped * bit! trie_insert() in this implementation takes care of that. * * if n is an internal node - a 'tnode' here, the various parts of its key * have many different meanings. * * Example: * _________________________________________________________________ * | i | i | i | i | i | i | i | N | N | N | S | S | S | S | S | C | * ----------------------------------------------------------------- * 31 30 29 28 27 26 25 24 23 22 21 20 19 18 17 16 * * _________________________________________________________________ * | C | C | C | u | u | u | u | u | u | u | u | u | u | u | u | u | * ----------------------------------------------------------------- * 15 14 13 12 11 10 9 8 7 6 5 4 3 2 1 0 * * tp->pos = 22 * tp->bits = 3 * n->pos = 13 * n->bits = 4 * * First, let's just ignore the bits that come before the parent tp, that is * the bits from (tp->pos + tp->bits) to 31. They are *known* but at this * point we do not use them for anything. * * The bits from (tp->pos) to (tp->pos + tp->bits - 1) - "N", above - are the * index into the parent's child array. That is, they will be used to find * 'n' among tp's children. * * The bits from (n->pos + n->bits) to (tp->pos - 1) - "S" - are skipped bits * for the node n. * * All the bits we have seen so far are significant to the node n. The rest * of the bits are really not needed or indeed known in n->key. * * The bits from (n->pos) to (n->pos + n->bits - 1) - "C" - are the index into * n's child array, and will of course be different for each child. * * The rest of the bits, from 0 to (n->pos -1) - "u" - are completely unknown * at this point. */ static const int halve_threshold = 25; static const int inflate_threshold = 50; static const int halve_threshold_root = 15; static const int inflate_threshold_root = 30; static inline void alias_free_mem_rcu(struct fib_alias *fa) { kfree_rcu(fa, rcu); } #define TNODE_VMALLOC_MAX \ ilog2((SIZE_MAX - TNODE_SIZE(0)) / sizeof(struct key_vector *)) static void __node_free_rcu(struct rcu_head *head) { struct tnode *n = container_of(head, struct tnode, rcu); if (!n->tn_bits) kmem_cache_free(trie_leaf_kmem, n); else kvfree(n); } #define node_free(n) call_rcu(&tn_info(n)->rcu, __node_free_rcu) static struct tnode *tnode_alloc(int bits) { size_t size; /* verify bits is within bounds */ if (bits > TNODE_VMALLOC_MAX) return NULL; /* determine size and verify it is non-zero and didn't overflow */ size = TNODE_SIZE(1ul << bits); if (size <= PAGE_SIZE) return kzalloc(size, GFP_KERNEL); else return vzalloc(size); } static inline void empty_child_inc(struct key_vector *n) { tn_info(n)->empty_children++; if (!tn_info(n)->empty_children) tn_info(n)->full_children++; } static inline void empty_child_dec(struct key_vector *n) { if (!tn_info(n)->empty_children) tn_info(n)->full_children--; tn_info(n)->empty_children--; } static struct key_vector *leaf_new(t_key key, struct fib_alias *fa) { struct key_vector *l; struct tnode *kv; kv = kmem_cache_alloc(trie_leaf_kmem, GFP_KERNEL); if (!kv) return NULL; /* initialize key vector */ l = kv->kv; l->key = key; l->pos = 0; l->bits = 0; l->slen = fa->fa_slen; /* link leaf to fib alias */ INIT_HLIST_HEAD(&l->leaf); hlist_add_head(&fa->fa_list, &l->leaf); return l; } static struct key_vector *tnode_new(t_key key, int pos, int bits) { unsigned int shift = pos + bits; struct key_vector *tn; struct tnode *tnode; /* verify bits and pos their msb bits clear and values are valid */ BUG_ON(!bits || (shift > KEYLENGTH)); tnode = tnode_alloc(bits); if (!tnode) return NULL; pr_debug("AT %p s=%zu %zu\n", tnode, TNODE_SIZE(0), sizeof(struct key_vector *) << bits); if (bits == KEYLENGTH) tnode->full_children = 1; else tnode->empty_children = 1ul << bits; tn = tnode->kv; tn->key = (shift < KEYLENGTH) ? (key >> shift) << shift : 0; tn->pos = pos; tn->bits = bits; tn->slen = pos; return tn; } /* Check whether a tnode 'n' is "full", i.e. it is an internal node * and no bits are skipped. See discussion in dyntree paper p. 6 */ static inline int tnode_full(struct key_vector *tn, struct key_vector *n) { return n && ((n->pos + n->bits) == tn->pos) && IS_TNODE(n); } /* Add a child at position i overwriting the old value. * Update the value of full_children and empty_children. */ static void put_child(struct key_vector *tn, unsigned long i, struct key_vector *n) { struct key_vector *chi = get_child(tn, i); int isfull, wasfull; BUG_ON(i >= child_length(tn)); /* update emptyChildren, overflow into fullChildren */ if (!n && chi) empty_child_inc(tn); if (n && !chi) empty_child_dec(tn); /* update fullChildren */ wasfull = tnode_full(tn, chi); isfull = tnode_full(tn, n); if (wasfull && !isfull) tn_info(tn)->full_children--; else if (!wasfull && isfull) tn_info(tn)->full_children++; if (n && (tn->slen < n->slen)) tn->slen = n->slen; rcu_assign_pointer(tn->tnode[i], n); } static void update_children(struct key_vector *tn) { unsigned long i; /* update all of the child parent pointers */ for (i = child_length(tn); i;) { struct key_vector *inode = get_child(tn, --i); if (!inode) continue; /* Either update the children of a tnode that * already belongs to us or update the child * to point to ourselves. */ if (node_parent(inode) == tn) update_children(inode); else node_set_parent(inode, tn); } } static inline void put_child_root(struct key_vector *tp, t_key key, struct key_vector *n) { if (IS_TRIE(tp)) rcu_assign_pointer(tp->tnode[0], n); else put_child(tp, get_index(key, tp), n); } static inline void tnode_free_init(struct key_vector *tn) { tn_info(tn)->rcu.next = NULL; } static inline void tnode_free_append(struct key_vector *tn, struct key_vector *n) { tn_info(n)->rcu.next = tn_info(tn)->rcu.next; tn_info(tn)->rcu.next = &tn_info(n)->rcu; } static void tnode_free(struct key_vector *tn) { struct callback_head *head = &tn_info(tn)->rcu; while (head) { head = head->next; tnode_free_size += TNODE_SIZE(1ul << tn->bits); node_free(tn); tn = container_of(head, struct tnode, rcu)->kv; } if (tnode_free_size >= READ_ONCE(sysctl_fib_sync_mem)) { tnode_free_size = 0; synchronize_net(); } } static struct key_vector *replace(struct trie *t, struct key_vector *oldtnode, struct key_vector *tn) { struct key_vector *tp = node_parent(oldtnode); unsigned long i; /* setup the parent pointer out of and back into this node */ NODE_INIT_PARENT(tn, tp); put_child_root(tp, tn->key, tn); /* update all of the child parent pointers */ update_children(tn); /* all pointers should be clean so we are done */ tnode_free(oldtnode); /* resize children now that oldtnode is freed */ for (i = child_length(tn); i;) { struct key_vector *inode = get_child(tn, --i); /* resize child node */ if (tnode_full(tn, inode)) tn = resize(t, inode); } return tp; } static struct key_vector *inflate(struct trie *t, struct key_vector *oldtnode) { struct key_vector *tn; unsigned long i; t_key m; pr_debug("In inflate\n"); tn = tnode_new(oldtnode->key, oldtnode->pos - 1, oldtnode->bits + 1); if (!tn) goto notnode; /* prepare oldtnode to be freed */ tnode_free_init(oldtnode); /* Assemble all of the pointers in our cluster, in this case that * represents all of the pointers out of our allocated nodes that * point to existing tnodes and the links between our allocated * nodes. */ for (i = child_length(oldtnode), m = 1u << tn->pos; i;) { struct key_vector *inode = get_child(oldtnode, --i); struct key_vector *node0, *node1; unsigned long j, k; /* An empty child */ if (!inode) continue; /* A leaf or an internal node with skipped bits */ if (!tnode_full(oldtnode, inode)) { put_child(tn, get_index(inode->key, tn), inode); continue; } /* drop the node in the old tnode free list */ tnode_free_append(oldtnode, inode); /* An internal node with two children */ if (inode->bits == 1) { put_child(tn, 2 * i + 1, get_child(inode, 1)); put_child(tn, 2 * i, get_child(inode, 0)); continue; } /* We will replace this node 'inode' with two new * ones, 'node0' and 'node1', each with half of the * original children. The two new nodes will have * a position one bit further down the key and this * means that the "significant" part of their keys * (see the discussion near the top of this file) * will differ by one bit, which will be "0" in * node0's key and "1" in node1's key. Since we are * moving the key position by one step, the bit that * we are moving away from - the bit at position * (tn->pos) - is the one that will differ between * node0 and node1. So... we synthesize that bit in the * two new keys. */ node1 = tnode_new(inode->key | m, inode->pos, inode->bits - 1); if (!node1) goto nomem; node0 = tnode_new(inode->key, inode->pos, inode->bits - 1); tnode_free_append(tn, node1); if (!node0) goto nomem; tnode_free_append(tn, node0); /* populate child pointers in new nodes */ for (k = child_length(inode), j = k / 2; j;) { put_child(node1, --j, get_child(inode, --k)); put_child(node0, j, get_child(inode, j)); put_child(node1, --j, get_child(inode, --k)); put_child(node0, j, get_child(inode, j)); } /* link new nodes to parent */ NODE_INIT_PARENT(node1, tn); NODE_INIT_PARENT(node0, tn); /* link parent to nodes */ put_child(tn, 2 * i + 1, node1); put_child(tn, 2 * i, node0); } /* setup the parent pointers into and out of this node */ return replace(t, oldtnode, tn); nomem: /* all pointers should be clean so we are done */ tnode_free(tn); notnode: return NULL; } static struct key_vector *halve(struct trie *t, struct key_vector *oldtnode) { struct key_vector *tn; unsigned long i; pr_debug("In halve\n"); tn = tnode_new(oldtnode->key, oldtnode->pos + 1, oldtnode->bits - 1); if (!tn) goto notnode; /* prepare oldtnode to be freed */ tnode_free_init(oldtnode); /* Assemble all of the pointers in our cluster, in this case that * represents all of the pointers out of our allocated nodes that * point to existing tnodes and the links between our allocated * nodes. */ for (i = child_length(oldtnode); i;) { struct key_vector *node1 = get_child(oldtnode, --i); struct key_vector *node0 = get_child(oldtnode, --i); struct key_vector *inode; /* At least one of the children is empty */ if (!node1 || !node0) { put_child(tn, i / 2, node1 ? : node0); continue; } /* Two nonempty children */ inode = tnode_new(node0->key, oldtnode->pos, 1); if (!inode) goto nomem; tnode_free_append(tn, inode); /* initialize pointers out of node */ put_child(inode, 1, node1); put_child(inode, 0, node0); NODE_INIT_PARENT(inode, tn); /* link parent to node */ put_child(tn, i / 2, inode); } /* setup the parent pointers into and out of this node */ return replace(t, oldtnode, tn); nomem: /* all pointers should be clean so we are done */ tnode_free(tn); notnode: return NULL; } static struct key_vector *collapse(struct trie *t, struct key_vector *oldtnode) { struct key_vector *n, *tp; unsigned long i; /* scan the tnode looking for that one child that might still exist */ for (n = NULL, i = child_length(oldtnode); !n && i;) n = get_child(oldtnode, --i); /* compress one level */ tp = node_parent(oldtnode); put_child_root(tp, oldtnode->key, n); node_set_parent(n, tp); /* drop dead node */ node_free(oldtnode); return tp; } static unsigned char update_suffix(struct key_vector *tn) { unsigned char slen = tn->pos; unsigned long stride, i; unsigned char slen_max; /* only vector 0 can have a suffix length greater than or equal to * tn->pos + tn->bits, the second highest node will have a suffix * length at most of tn->pos + tn->bits - 1 */ slen_max = min_t(unsigned char, tn->pos + tn->bits - 1, tn->slen); /* search though the list of children looking for nodes that might * have a suffix greater than the one we currently have. This is * why we start with a stride of 2 since a stride of 1 would * represent the nodes with suffix length equal to tn->pos */ for (i = 0, stride = 0x2ul ; i < child_length(tn); i += stride) { struct key_vector *n = get_child(tn, i); if (!n || (n->slen <= slen)) continue; /* update stride and slen based on new value */ stride <<= (n->slen - slen); slen = n->slen; i &= ~(stride - 1); /* stop searching if we have hit the maximum possible value */ if (slen >= slen_max) break; } tn->slen = slen; return slen; } /* From "Implementing a dynamic compressed trie" by Stefan Nilsson of * the Helsinki University of Technology and Matti Tikkanen of Nokia * Telecommunications, page 6: * "A node is doubled if the ratio of non-empty children to all * children in the *doubled* node is at least 'high'." * * 'high' in this instance is the variable 'inflate_threshold'. It * is expressed as a percentage, so we multiply it with * child_length() and instead of multiplying by 2 (since the * child array will be doubled by inflate()) and multiplying * the left-hand side by 100 (to handle the percentage thing) we * multiply the left-hand side by 50. * * The left-hand side may look a bit weird: child_length(tn) * - tn->empty_children is of course the number of non-null children * in the current node. tn->full_children is the number of "full" * children, that is non-null tnodes with a skip value of 0. * All of those will be doubled in the resulting inflated tnode, so * we just count them one extra time here. * * A clearer way to write this would be: * * to_be_doubled = tn->full_children; * not_to_be_doubled = child_length(tn) - tn->empty_children - * tn->full_children; * * new_child_length = child_length(tn) * 2; * * new_fill_factor = 100 * (not_to_be_doubled + 2*to_be_doubled) / * new_child_length; * if (new_fill_factor >= inflate_threshold) * * ...and so on, tho it would mess up the while () loop. * * anyway, * 100 * (not_to_be_doubled + 2*to_be_doubled) / new_child_length >= * inflate_threshold * * avoid a division: * 100 * (not_to_be_doubled + 2*to_be_doubled) >= * inflate_threshold * new_child_length * * expand not_to_be_doubled and to_be_doubled, and shorten: * 100 * (child_length(tn) - tn->empty_children + * tn->full_children) >= inflate_threshold * new_child_length * * expand new_child_length: * 100 * (child_length(tn) - tn->empty_children + * tn->full_children) >= * inflate_threshold * child_length(tn) * 2 * * shorten again: * 50 * (tn->full_children + child_length(tn) - * tn->empty_children) >= inflate_threshold * * child_length(tn) * */ static inline bool should_inflate(struct key_vector *tp, struct key_vector *tn) { unsigned long used = child_length(tn); unsigned long threshold = used; /* Keep root node larger */ threshold *= IS_TRIE(tp) ? inflate_threshold_root : inflate_threshold; used -= tn_info(tn)->empty_children; used += tn_info(tn)->full_children; /* if bits == KEYLENGTH then pos = 0, and will fail below */ return (used > 1) && tn->pos && ((50 * used) >= threshold); } static inline bool should_halve(struct key_vector *tp, struct key_vector *tn) { unsigned long used = child_length(tn); unsigned long threshold = used; /* Keep root node larger */ threshold *= IS_TRIE(tp) ? halve_threshold_root : halve_threshold; used -= tn_info(tn)->empty_children; /* if bits == KEYLENGTH then used = 100% on wrap, and will fail below */ return (used > 1) && (tn->bits > 1) && ((100 * used) < threshold); } static inline bool should_collapse(struct key_vector *tn) { unsigned long used = child_length(tn); used -= tn_info(tn)->empty_children; /* account for bits == KEYLENGTH case */ if ((tn->bits == KEYLENGTH) && tn_info(tn)->full_children) used -= KEY_MAX; /* One child or none, time to drop us from the trie */ return used < 2; } #define MAX_WORK 10 static struct key_vector *resize(struct trie *t, struct key_vector *tn) { #ifdef CONFIG_IP_FIB_TRIE_STATS struct trie_use_stats __percpu *stats = t->stats; #endif struct key_vector *tp = node_parent(tn); unsigned long cindex = get_index(tn->key, tp); int max_work = MAX_WORK; pr_debug("In tnode_resize %p inflate_threshold=%d threshold=%d\n", tn, inflate_threshold, halve_threshold); /* track the tnode via the pointer from the parent instead of * doing it ourselves. This way we can let RCU fully do its * thing without us interfering */ BUG_ON(tn != get_child(tp, cindex)); /* Double as long as the resulting node has a number of * nonempty nodes that are above the threshold. */ while (should_inflate(tp, tn) && max_work) { tp = inflate(t, tn); if (!tp) { #ifdef CONFIG_IP_FIB_TRIE_STATS this_cpu_inc(stats->resize_node_skipped); #endif break; } max_work--; tn = get_child(tp, cindex); } /* update parent in case inflate failed */ tp = node_parent(tn); /* Return if at least one inflate is run */ if (max_work != MAX_WORK) return tp; /* Halve as long as the number of empty children in this * node is above threshold. */ while (should_halve(tp, tn) && max_work) { tp = halve(t, tn); if (!tp) { #ifdef CONFIG_IP_FIB_TRIE_STATS this_cpu_inc(stats->resize_node_skipped); #endif break; } max_work--; tn = get_child(tp, cindex); } /* Only one child remains */ if (should_collapse(tn)) return collapse(t, tn); /* update parent in case halve failed */ return node_parent(tn); } static void node_pull_suffix(struct key_vector *tn, unsigned char slen) { unsigned char node_slen = tn->slen; while ((node_slen > tn->pos) && (node_slen > slen)) { slen = update_suffix(tn); if (node_slen == slen) break; tn = node_parent(tn); node_slen = tn->slen; } } static void node_push_suffix(struct key_vector *tn, unsigned char slen) { while (tn->slen < slen) { tn->slen = slen; tn = node_parent(tn); } } /* rcu_read_lock needs to be hold by caller from readside */ static struct key_vector *fib_find_node(struct trie *t, struct key_vector **tp, u32 key) { struct key_vector *pn, *n = t->kv; unsigned long index = 0; do { pn = n; n = get_child_rcu(n, index); if (!n) break; index = get_cindex(key, n); /* This bit of code is a bit tricky but it combines multiple * checks into a single check. The prefix consists of the * prefix plus zeros for the bits in the cindex. The index * is the difference between the key and this value. From * this we can actually derive several pieces of data. * if (index >= (1ul << bits)) * we have a mismatch in skip bits and failed * else * we know the value is cindex * * This check is safe even if bits == KEYLENGTH due to the * fact that we can only allocate a node with 32 bits if a * long is greater than 32 bits. */ if (index >= (1ul << n->bits)) { n = NULL; break; } /* keep searching until we find a perfect match leaf or NULL */ } while (IS_TNODE(n)); *tp = pn; return n; } /* Return the first fib alias matching DSCP with * priority less than or equal to PRIO. * If 'find_first' is set, return the first matching * fib alias, regardless of DSCP and priority. */ static struct fib_alias *fib_find_alias(struct hlist_head *fah, u8 slen, dscp_t dscp, u32 prio, u32 tb_id, bool find_first) { struct fib_alias *fa; if (!fah) return NULL; hlist_for_each_entry(fa, fah, fa_list) { /* Avoid Sparse warning when using dscp_t in inequalities */ u8 __fa_dscp = inet_dscp_to_dsfield(fa->fa_dscp); u8 __dscp = inet_dscp_to_dsfield(dscp); if (fa->fa_slen < slen) continue; if (fa->fa_slen != slen) break; if (fa->tb_id > tb_id) continue; if (fa->tb_id != tb_id) break; if (find_first) return fa; if (__fa_dscp > __dscp) continue; if (fa->fa_info->fib_priority >= prio || __fa_dscp < __dscp) return fa; } return NULL; } static struct fib_alias * fib_find_matching_alias(struct net *net, const struct fib_rt_info *fri) { u8 slen = KEYLENGTH - fri->dst_len; struct key_vector *l, *tp; struct fib_table *tb; struct fib_alias *fa; struct trie *t; tb = fib_get_table(net, fri->tb_id); if (!tb) return NULL; t = (struct trie *)tb->tb_data; l = fib_find_node(t, &tp, be32_to_cpu(fri->dst)); if (!l) return NULL; hlist_for_each_entry_rcu(fa, &l->leaf, fa_list) { if (fa->fa_slen == slen && fa->tb_id == fri->tb_id && fa->fa_dscp == fri->dscp && fa->fa_info == fri->fi && fa->fa_type == fri->type) return fa; } return NULL; } void fib_alias_hw_flags_set(struct net *net, const struct fib_rt_info *fri) { u8 fib_notify_on_flag_change; struct fib_alias *fa_match; struct sk_buff *skb; int err; rcu_read_lock(); fa_match = fib_find_matching_alias(net, fri); if (!fa_match) goto out; /* These are paired with the WRITE_ONCE() happening in this function. * The reason is that we are only protected by RCU at this point. */ if (READ_ONCE(fa_match->offload) == fri->offload && READ_ONCE(fa_match->trap) == fri->trap && READ_ONCE(fa_match->offload_failed) == fri->offload_failed) goto out; WRITE_ONCE(fa_match->offload, fri->offload); WRITE_ONCE(fa_match->trap, fri->trap); fib_notify_on_flag_change = READ_ONCE(net->ipv4.sysctl_fib_notify_on_flag_change); /* 2 means send notifications only if offload_failed was changed. */ if (fib_notify_on_flag_change == 2 && READ_ONCE(fa_match->offload_failed) == fri->offload_failed) goto out; WRITE_ONCE(fa_match->offload_failed, fri->offload_failed); if (!fib_notify_on_flag_change) goto out; skb = nlmsg_new(fib_nlmsg_size(fa_match->fa_info), GFP_ATOMIC); if (!skb) { err = -ENOBUFS; goto errout; } err = fib_dump_info(skb, 0, 0, RTM_NEWROUTE, fri, 0); if (err < 0) { /* -EMSGSIZE implies BUG in fib_nlmsg_size() */ WARN_ON(err == -EMSGSIZE); kfree_skb(skb); goto errout; } rtnl_notify(skb, net, 0, RTNLGRP_IPV4_ROUTE, NULL, GFP_ATOMIC); goto out; errout: rtnl_set_sk_err(net, RTNLGRP_IPV4_ROUTE, err); out: rcu_read_unlock(); } EXPORT_SYMBOL_GPL(fib_alias_hw_flags_set); static void trie_rebalance(struct trie *t, struct key_vector *tn) { while (!IS_TRIE(tn)) tn = resize(t, tn); } static int fib_insert_node(struct trie *t, struct key_vector *tp, struct fib_alias *new, t_key key) { struct key_vector *n, *l; l = leaf_new(key, new); if (!l) goto noleaf; /* retrieve child from parent node */ n = get_child(tp, get_index(key, tp)); /* Case 2: n is a LEAF or a TNODE and the key doesn't match. * * Add a new tnode here * first tnode need some special handling * leaves us in position for handling as case 3 */ if (n) { struct key_vector *tn; tn = tnode_new(key, __fls(key ^ n->key), 1); if (!tn) goto notnode; /* initialize routes out of node */ NODE_INIT_PARENT(tn, tp); put_child(tn, get_index(key, tn) ^ 1, n); /* start adding routes into the node */ put_child_root(tp, key, tn); node_set_parent(n, tn); /* parent now has a NULL spot where the leaf can go */ tp = tn; } /* Case 3: n is NULL, and will just insert a new leaf */ node_push_suffix(tp, new->fa_slen); NODE_INIT_PARENT(l, tp); put_child_root(tp, key, l); trie_rebalance(t, tp); return 0; notnode: node_free(l); noleaf: return -ENOMEM; } static int fib_insert_alias(struct trie *t, struct key_vector *tp, struct key_vector *l, struct fib_alias *new, struct fib_alias *fa, t_key key) { if (!l) return fib_insert_node(t, tp, new, key); if (fa) { hlist_add_before_rcu(&new->fa_list, &fa->fa_list); } else { struct fib_alias *last; hlist_for_each_entry(last, &l->leaf, fa_list) { if (new->fa_slen < last->fa_slen) break; if ((new->fa_slen == last->fa_slen) && (new->tb_id > last->tb_id)) break; fa = last; } if (fa) hlist_add_behind_rcu(&new->fa_list, &fa->fa_list); else hlist_add_head_rcu(&new->fa_list, &l->leaf); } /* if we added to the tail node then we need to update slen */ if (l->slen < new->fa_slen) { l->slen = new->fa_slen; node_push_suffix(tp, new->fa_slen); } return 0; } static bool fib_valid_key_len(u32 key, u8 plen, struct netlink_ext_ack *extack) { if (plen > KEYLENGTH) { NL_SET_ERR_MSG(extack, "Invalid prefix length"); return false; } if ((plen < KEYLENGTH) && (key << plen)) { NL_SET_ERR_MSG(extack, "Invalid prefix for given prefix length"); return false; } return true; } static void fib_remove_alias(struct trie *t, struct key_vector *tp, struct key_vector *l, struct fib_alias *old); /* Caller must hold RTNL. */ int fib_table_insert(struct net *net, struct fib_table *tb, struct fib_config *cfg, struct netlink_ext_ack *extack) { struct trie *t = (struct trie *)tb->tb_data; struct fib_alias *fa, *new_fa; struct key_vector *l, *tp; u16 nlflags = NLM_F_EXCL; struct fib_info *fi; u8 plen = cfg->fc_dst_len; u8 slen = KEYLENGTH - plen; dscp_t dscp; u32 key; int err; key = ntohl(cfg->fc_dst); if (!fib_valid_key_len(key, plen, extack)) return -EINVAL; pr_debug("Insert table=%u %08x/%d\n", tb->tb_id, key, plen); fi = fib_create_info(cfg, extack); if (IS_ERR(fi)) { err = PTR_ERR(fi); goto err; } dscp = cfg->fc_dscp; l = fib_find_node(t, &tp, key); fa = l ? fib_find_alias(&l->leaf, slen, dscp, fi->fib_priority, tb->tb_id, false) : NULL; /* Now fa, if non-NULL, points to the first fib alias * with the same keys [prefix,dscp,priority], if such key already * exists or to the node before which we will insert new one. * * If fa is NULL, we will need to allocate a new one and * insert to the tail of the section matching the suffix length * of the new alias. */ if (fa && fa->fa_dscp == dscp && fa->fa_info->fib_priority == fi->fib_priority) { struct fib_alias *fa_first, *fa_match; err = -EEXIST; if (cfg->fc_nlflags & NLM_F_EXCL) goto out; nlflags &= ~NLM_F_EXCL; /* We have 2 goals: * 1. Find exact match for type, scope, fib_info to avoid * duplicate routes * 2. Find next 'fa' (or head), NLM_F_APPEND inserts before it */ fa_match = NULL; fa_first = fa; hlist_for_each_entry_from(fa, fa_list) { if ((fa->fa_slen != slen) || (fa->tb_id != tb->tb_id) || (fa->fa_dscp != dscp)) break; if (fa->fa_info->fib_priority != fi->fib_priority) break; if (fa->fa_type == cfg->fc_type && fa->fa_info == fi) { fa_match = fa; break; } } if (cfg->fc_nlflags & NLM_F_REPLACE) { struct fib_info *fi_drop; u8 state; nlflags |= NLM_F_REPLACE; fa = fa_first; if (fa_match) { if (fa == fa_match) err = 0; goto out; } err = -ENOBUFS; new_fa = kmem_cache_alloc(fn_alias_kmem, GFP_KERNEL); if (!new_fa) goto out; fi_drop = fa->fa_info; new_fa->fa_dscp = fa->fa_dscp; new_fa->fa_info = fi; new_fa->fa_type = cfg->fc_type; state = fa->fa_state; new_fa->fa_state = state & ~FA_S_ACCESSED; new_fa->fa_slen = fa->fa_slen; new_fa->tb_id = tb->tb_id; new_fa->fa_default = -1; new_fa->offload = 0; new_fa->trap = 0; new_fa->offload_failed = 0; hlist_replace_rcu(&fa->fa_list, &new_fa->fa_list); if (fib_find_alias(&l->leaf, fa->fa_slen, 0, 0, tb->tb_id, true) == new_fa) { enum fib_event_type fib_event; fib_event = FIB_EVENT_ENTRY_REPLACE; err = call_fib_entry_notifiers(net, fib_event, key, plen, new_fa, extack); if (err) { hlist_replace_rcu(&new_fa->fa_list, &fa->fa_list); goto out_free_new_fa; } } rtmsg_fib(RTM_NEWROUTE, htonl(key), new_fa, plen, tb->tb_id, &cfg->fc_nlinfo, nlflags); alias_free_mem_rcu(fa); fib_release_info(fi_drop); if (state & FA_S_ACCESSED) rt_cache_flush(cfg->fc_nlinfo.nl_net); goto succeeded; } /* Error if we find a perfect match which * uses the same scope, type, and nexthop * information. */ if (fa_match) goto out; if (cfg->fc_nlflags & NLM_F_APPEND) nlflags |= NLM_F_APPEND; else fa = fa_first; } err = -ENOENT; if (!(cfg->fc_nlflags & NLM_F_CREATE)) goto out; nlflags |= NLM_F_CREATE; err = -ENOBUFS; new_fa = kmem_cache_alloc(fn_alias_kmem, GFP_KERNEL); if (!new_fa) goto out; new_fa->fa_info = fi; new_fa->fa_dscp = dscp; new_fa->fa_type = cfg->fc_type; new_fa->fa_state = 0; new_fa->fa_slen = slen; new_fa->tb_id = tb->tb_id; new_fa->fa_default = -1; new_fa->offload = 0; new_fa->trap = 0; new_fa->offload_failed = 0; /* Insert new entry to the list. */ err = fib_insert_alias(t, tp, l, new_fa, fa, key); if (err) goto out_free_new_fa; /* The alias was already inserted, so the node must exist. */ l = l ? l : fib_find_node(t, &tp, key); if (WARN_ON_ONCE(!l)) { err = -ENOENT; goto out_free_new_fa; } if (fib_find_alias(&l->leaf, new_fa->fa_slen, 0, 0, tb->tb_id, true) == new_fa) { enum fib_event_type fib_event; fib_event = FIB_EVENT_ENTRY_REPLACE; err = call_fib_entry_notifiers(net, fib_event, key, plen, new_fa, extack); if (err) goto out_remove_new_fa; } if (!plen) tb->tb_num_default++; rt_cache_flush(cfg->fc_nlinfo.nl_net); rtmsg_fib(RTM_NEWROUTE, htonl(key), new_fa, plen, new_fa->tb_id, &cfg->fc_nlinfo, nlflags); succeeded: return 0; out_remove_new_fa: fib_remove_alias(t, tp, l, new_fa); out_free_new_fa: kmem_cache_free(fn_alias_kmem, new_fa); out: fib_release_info(fi); err: return err; } static inline t_key prefix_mismatch(t_key key, struct key_vector *n) { t_key prefix = n->key; return (key ^ prefix) & (prefix | -prefix); } bool fib_lookup_good_nhc(const struct fib_nh_common *nhc, int fib_flags, const struct flowi4 *flp) { if (nhc->nhc_flags & RTNH_F_DEAD) return false; if (ip_ignore_linkdown(nhc->nhc_dev) && nhc->nhc_flags & RTNH_F_LINKDOWN && !(fib_flags & FIB_LOOKUP_IGNORE_LINKSTATE)) return false; if (flp->flowi4_oif && flp->flowi4_oif != nhc->nhc_oif) return false; return true; } /* should be called with rcu_read_lock */ int fib_table_lookup(struct fib_table *tb, const struct flowi4 *flp, struct fib_result *res, int fib_flags) { struct trie *t = (struct trie *) tb->tb_data; #ifdef CONFIG_IP_FIB_TRIE_STATS struct trie_use_stats __percpu *stats = t->stats; #endif const t_key key = ntohl(flp->daddr); struct key_vector *n, *pn; struct fib_alias *fa; unsigned long index; t_key cindex; pn = t->kv; cindex = 0; n = get_child_rcu(pn, cindex); if (!n) { trace_fib_table_lookup(tb->tb_id, flp, NULL, -EAGAIN); return -EAGAIN; } #ifdef CONFIG_IP_FIB_TRIE_STATS this_cpu_inc(stats->gets); #endif /* Step 1: Travel to the longest prefix match in the trie */ for (;;) { index = get_cindex(key, n); /* This bit of code is a bit tricky but it combines multiple * checks into a single check. The prefix consists of the * prefix plus zeros for the "bits" in the prefix. The index * is the difference between the key and this value. From * this we can actually derive several pieces of data. * if (index >= (1ul << bits)) * we have a mismatch in skip bits and failed * else * we know the value is cindex * * This check is safe even if bits == KEYLENGTH due to the * fact that we can only allocate a node with 32 bits if a * long is greater than 32 bits. */ if (index >= (1ul << n->bits)) break; /* we have found a leaf. Prefixes have already been compared */ if (IS_LEAF(n)) goto found; /* only record pn and cindex if we are going to be chopping * bits later. Otherwise we are just wasting cycles. */ if (n->slen > n->pos) { pn = n; cindex = index; } n = get_child_rcu(n, index); if (unlikely(!n)) goto backtrace; } /* Step 2: Sort out leaves and begin backtracing for longest prefix */ for (;;) { /* record the pointer where our next node pointer is stored */ struct key_vector __rcu **cptr = n->tnode; /* This test verifies that none of the bits that differ * between the key and the prefix exist in the region of * the lsb and higher in the prefix. */ if (unlikely(prefix_mismatch(key, n)) || (n->slen == n->pos)) goto backtrace; /* exit out and process leaf */ if (unlikely(IS_LEAF(n))) break; /* Don't bother recording parent info. Since we are in * prefix match mode we will have to come back to wherever * we started this traversal anyway */ while ((n = rcu_dereference(*cptr)) == NULL) { backtrace: #ifdef CONFIG_IP_FIB_TRIE_STATS if (!n) this_cpu_inc(stats->null_node_hit); #endif /* If we are at cindex 0 there are no more bits for * us to strip at this level so we must ascend back * up one level to see if there are any more bits to * be stripped there. */ while (!cindex) { t_key pkey = pn->key; /* If we don't have a parent then there is * nothing for us to do as we do not have any * further nodes to parse. */ if (IS_TRIE(pn)) { trace_fib_table_lookup(tb->tb_id, flp, NULL, -EAGAIN); return -EAGAIN; } #ifdef CONFIG_IP_FIB_TRIE_STATS this_cpu_inc(stats->backtrack); #endif /* Get Child's index */ pn = node_parent_rcu(pn); cindex = get_index(pkey, pn); } /* strip the least significant bit from the cindex */ cindex &= cindex - 1; /* grab pointer for next child node */ cptr = &pn->tnode[cindex]; } } found: /* this line carries forward the xor from earlier in the function */ index = key ^ n->key; /* Step 3: Process the leaf, if that fails fall back to backtracing */ hlist_for_each_entry_rcu(fa, &n->leaf, fa_list) { struct fib_info *fi = fa->fa_info; struct fib_nh_common *nhc; int nhsel, err; if ((BITS_PER_LONG > KEYLENGTH) || (fa->fa_slen < KEYLENGTH)) { if (index >= (1ul << fa->fa_slen)) continue; } if (fa->fa_dscp && !fib_dscp_masked_match(fa->fa_dscp, flp)) continue; /* Paired with WRITE_ONCE() in fib_release_info() */ if (READ_ONCE(fi->fib_dead)) continue; if (fa->fa_info->fib_scope < flp->flowi4_scope) continue; fib_alias_accessed(fa); err = fib_props[fa->fa_type].error; if (unlikely(err < 0)) { out_reject: #ifdef CONFIG_IP_FIB_TRIE_STATS this_cpu_inc(stats->semantic_match_passed); #endif trace_fib_table_lookup(tb->tb_id, flp, NULL, err); return err; } if (fi->fib_flags & RTNH_F_DEAD) continue; if (unlikely(fi->nh)) { if (nexthop_is_blackhole(fi->nh)) { err = fib_props[RTN_BLACKHOLE].error; goto out_reject; } nhc = nexthop_get_nhc_lookup(fi->nh, fib_flags, flp, &nhsel); if (nhc) goto set_result; goto miss; } for (nhsel = 0; nhsel < fib_info_num_path(fi); nhsel++) { nhc = fib_info_nhc(fi, nhsel); if (!fib_lookup_good_nhc(nhc, fib_flags, flp)) continue; set_result: if (!(fib_flags & FIB_LOOKUP_NOREF)) refcount_inc(&fi->fib_clntref); res->prefix = htonl(n->key); res->prefixlen = KEYLENGTH - fa->fa_slen; res->nh_sel = nhsel; res->nhc = nhc; res->type = fa->fa_type; res->scope = fi->fib_scope; res->dscp = fa->fa_dscp; res->fi = fi; res->table = tb; res->fa_head = &n->leaf; #ifdef CONFIG_IP_FIB_TRIE_STATS this_cpu_inc(stats->semantic_match_passed); #endif trace_fib_table_lookup(tb->tb_id, flp, nhc, err); return err; } } miss: #ifdef CONFIG_IP_FIB_TRIE_STATS this_cpu_inc(stats->semantic_match_miss); #endif goto backtrace; } EXPORT_SYMBOL_GPL(fib_table_lookup); static void fib_remove_alias(struct trie *t, struct key_vector *tp, struct key_vector *l, struct fib_alias *old) { /* record the location of the previous list_info entry */ struct hlist_node **pprev = old->fa_list.pprev; struct fib_alias *fa = hlist_entry(pprev, typeof(*fa), fa_list.next); /* remove the fib_alias from the list */ hlist_del_rcu(&old->fa_list); /* if we emptied the list this leaf will be freed and we can sort * out parent suffix lengths as a part of trie_rebalance */ if (hlist_empty(&l->leaf)) { if (tp->slen == l->slen) node_pull_suffix(tp, tp->pos); put_child_root(tp, l->key, NULL); node_free(l); trie_rebalance(t, tp); return; } /* only access fa if it is pointing at the last valid hlist_node */ if (*pprev) return; /* update the trie with the latest suffix length */ l->slen = fa->fa_slen; node_pull_suffix(tp, fa->fa_slen); } static void fib_notify_alias_delete(struct net *net, u32 key, struct hlist_head *fah, struct fib_alias *fa_to_delete, struct netlink_ext_ack *extack) { struct fib_alias *fa_next, *fa_to_notify; u32 tb_id = fa_to_delete->tb_id; u8 slen = fa_to_delete->fa_slen; enum fib_event_type fib_event; /* Do not notify if we do not care about the route. */ if (fib_find_alias(fah, slen, 0, 0, tb_id, true) != fa_to_delete) return; /* Determine if the route should be replaced by the next route in the * list. */ fa_next = hlist_entry_safe(fa_to_delete->fa_list.next, struct fib_alias, fa_list); if (fa_next && fa_next->fa_slen == slen && fa_next->tb_id == tb_id) { fib_event = FIB_EVENT_ENTRY_REPLACE; fa_to_notify = fa_next; } else { fib_event = FIB_EVENT_ENTRY_DEL; fa_to_notify = fa_to_delete; } call_fib_entry_notifiers(net, fib_event, key, KEYLENGTH - slen, fa_to_notify, extack); } /* Caller must hold RTNL. */ int fib_table_delete(struct net *net, struct fib_table *tb, struct fib_config *cfg, struct netlink_ext_ack *extack) { struct trie *t = (struct trie *) tb->tb_data; struct fib_alias *fa, *fa_to_delete; struct key_vector *l, *tp; u8 plen = cfg->fc_dst_len; u8 slen = KEYLENGTH - plen; dscp_t dscp; u32 key; key = ntohl(cfg->fc_dst); if (!fib_valid_key_len(key, plen, extack)) return -EINVAL; l = fib_find_node(t, &tp, key); if (!l) return -ESRCH; dscp = cfg->fc_dscp; fa = fib_find_alias(&l->leaf, slen, dscp, 0, tb->tb_id, false); if (!fa) return -ESRCH; pr_debug("Deleting %08x/%d dsfield=0x%02x t=%p\n", key, plen, inet_dscp_to_dsfield(dscp), t); fa_to_delete = NULL; hlist_for_each_entry_from(fa, fa_list) { struct fib_info *fi = fa->fa_info; if ((fa->fa_slen != slen) || (fa->tb_id != tb->tb_id) || (fa->fa_dscp != dscp)) break; if ((!cfg->fc_type || fa->fa_type == cfg->fc_type) && (cfg->fc_scope == RT_SCOPE_NOWHERE || fa->fa_info->fib_scope == cfg->fc_scope) && (!cfg->fc_prefsrc || fi->fib_prefsrc == cfg->fc_prefsrc) && (!cfg->fc_protocol || fi->fib_protocol == cfg->fc_protocol) && fib_nh_match(net, cfg, fi, extack) == 0 && fib_metrics_match(cfg, fi)) { fa_to_delete = fa; break; } } if (!fa_to_delete) return -ESRCH; fib_notify_alias_delete(net, key, &l->leaf, fa_to_delete, extack); rtmsg_fib(RTM_DELROUTE, htonl(key), fa_to_delete, plen, tb->tb_id, &cfg->fc_nlinfo, 0); if (!plen) tb->tb_num_default--; fib_remove_alias(t, tp, l, fa_to_delete); if (fa_to_delete->fa_state & FA_S_ACCESSED) rt_cache_flush(cfg->fc_nlinfo.nl_net); fib_release_info(fa_to_delete->fa_info); alias_free_mem_rcu(fa_to_delete); return 0; } /* Scan for the next leaf starting at the provided key value */ static struct key_vector *leaf_walk_rcu(struct key_vector **tn, t_key key) { struct key_vector *pn, *n = *tn; unsigned long cindex; /* this loop is meant to try and find the key in the trie */ do { /* record parent and next child index */ pn = n; cindex = (key > pn->key) ? get_index(key, pn) : 0; if (cindex >> pn->bits) break; /* descend into the next child */ n = get_child_rcu(pn, cindex++); if (!n) break; /* guarantee forward progress on the keys */ if (IS_LEAF(n) && (n->key >= key)) goto found; } while (IS_TNODE(n)); /* this loop will search for the next leaf with a greater key */ while (!IS_TRIE(pn)) { /* if we exhausted the parent node we will need to climb */ if (cindex >= (1ul << pn->bits)) { t_key pkey = pn->key; pn = node_parent_rcu(pn); cindex = get_index(pkey, pn) + 1; continue; } /* grab the next available node */ n = get_child_rcu(pn, cindex++); if (!n) continue; /* no need to compare keys since we bumped the index */ if (IS_LEAF(n)) goto found; /* Rescan start scanning in new node */ pn = n; cindex = 0; } *tn = pn; return NULL; /* Root of trie */ found: /* if we are at the limit for keys just return NULL for the tnode */ *tn = pn; return n; } static void fib_trie_free(struct fib_table *tb) { struct trie *t = (struct trie *)tb->tb_data; struct key_vector *pn = t->kv; unsigned long cindex = 1; struct hlist_node *tmp; struct fib_alias *fa; /* walk trie in reverse order and free everything */ for (;;) { struct key_vector *n; if (!(cindex--)) { t_key pkey = pn->key; if (IS_TRIE(pn)) break; n = pn; pn = node_parent(pn); /* drop emptied tnode */ put_child_root(pn, n->key, NULL); node_free(n); cindex = get_index(pkey, pn); continue; } /* grab the next available node */ n = get_child(pn, cindex); if (!n) continue; if (IS_TNODE(n)) { /* record pn and cindex for leaf walking */ pn = n; cindex = 1ul << n->bits; continue; } hlist_for_each_entry_safe(fa, tmp, &n->leaf, fa_list) { hlist_del_rcu(&fa->fa_list); alias_free_mem_rcu(fa); } put_child_root(pn, n->key, NULL); node_free(n); } #ifdef CONFIG_IP_FIB_TRIE_STATS free_percpu(t->stats); #endif kfree(tb); } struct fib_table *fib_trie_unmerge(struct fib_table *oldtb) { struct trie *ot = (struct trie *)oldtb->tb_data; struct key_vector *l, *tp = ot->kv; struct fib_table *local_tb; struct fib_alias *fa; struct trie *lt; t_key key = 0; if (oldtb->tb_data == oldtb->__data) return oldtb; local_tb = fib_trie_table(RT_TABLE_LOCAL, NULL); if (!local_tb) return NULL; lt = (struct trie *)local_tb->tb_data; while ((l = leaf_walk_rcu(&tp, key)) != NULL) { struct key_vector *local_l = NULL, *local_tp; hlist_for_each_entry(fa, &l->leaf, fa_list) { struct fib_alias *new_fa; if (local_tb->tb_id != fa->tb_id) continue; /* clone fa for new local table */ new_fa = kmem_cache_alloc(fn_alias_kmem, GFP_KERNEL); if (!new_fa) goto out; memcpy(new_fa, fa, sizeof(*fa)); /* insert clone into table */ if (!local_l) local_l = fib_find_node(lt, &local_tp, l->key); if (fib_insert_alias(lt, local_tp, local_l, new_fa, NULL, l->key)) { kmem_cache_free(fn_alias_kmem, new_fa); goto out; } } /* stop loop if key wrapped back to 0 */ key = l->key + 1; if (key < l->key) break; } return local_tb; out: fib_trie_free(local_tb); return NULL; } /* Caller must hold RTNL */ void fib_table_flush_external(struct fib_table *tb) { struct trie *t = (struct trie *)tb->tb_data; struct key_vector *pn = t->kv; unsigned long cindex = 1; struct hlist_node *tmp; struct fib_alias *fa; /* walk trie in reverse order */ for (;;) { unsigned char slen = 0; struct key_vector *n; if (!(cindex--)) { t_key pkey = pn->key; /* cannot resize the trie vector */ if (IS_TRIE(pn)) break; /* update the suffix to address pulled leaves */ if (pn->slen > pn->pos) update_suffix(pn); /* resize completed node */ pn = resize(t, pn); cindex = get_index(pkey, pn); continue; } /* grab the next available node */ n = get_child(pn, cindex); if (!n) continue; if (IS_TNODE(n)) { /* record pn and cindex for leaf walking */ pn = n; cindex = 1ul << n->bits; continue; } hlist_for_each_entry_safe(fa, tmp, &n->leaf, fa_list) { /* if alias was cloned to local then we just * need to remove the local copy from main */ if (tb->tb_id != fa->tb_id) { hlist_del_rcu(&fa->fa_list); alias_free_mem_rcu(fa); continue; } /* record local slen */ slen = fa->fa_slen; } /* update leaf slen */ n->slen = slen; if (hlist_empty(&n->leaf)) { put_child_root(pn, n->key, NULL); node_free(n); } } } /* Caller must hold RTNL. */ int fib_table_flush(struct net *net, struct fib_table *tb, bool flush_all) { struct trie *t = (struct trie *)tb->tb_data; struct nl_info info = { .nl_net = net }; struct key_vector *pn = t->kv; unsigned long cindex = 1; struct hlist_node *tmp; struct fib_alias *fa; int found = 0; /* walk trie in reverse order */ for (;;) { unsigned char slen = 0; struct key_vector *n; if (!(cindex--)) { t_key pkey = pn->key; /* cannot resize the trie vector */ if (IS_TRIE(pn)) break; /* update the suffix to address pulled leaves */ if (pn->slen > pn->pos) update_suffix(pn); /* resize completed node */ pn = resize(t, pn); cindex = get_index(pkey, pn); continue; } /* grab the next available node */ n = get_child(pn, cindex); if (!n) continue; if (IS_TNODE(n)) { /* record pn and cindex for leaf walking */ pn = n; cindex = 1ul << n->bits; continue; } hlist_for_each_entry_safe(fa, tmp, &n->leaf, fa_list) { struct fib_info *fi = fa->fa_info; if (!fi || tb->tb_id != fa->tb_id || (!(fi->fib_flags & RTNH_F_DEAD) && !fib_props[fa->fa_type].error)) { slen = fa->fa_slen; continue; } /* Do not flush error routes if network namespace is * not being dismantled */ if (!flush_all && fib_props[fa->fa_type].error) { slen = fa->fa_slen; continue; } fib_notify_alias_delete(net, n->key, &n->leaf, fa, NULL); if (fi->pfsrc_removed) rtmsg_fib(RTM_DELROUTE, htonl(n->key), fa, KEYLENGTH - fa->fa_slen, tb->tb_id, &info, 0); hlist_del_rcu(&fa->fa_list); fib_release_info(fa->fa_info); alias_free_mem_rcu(fa); found++; } /* update leaf slen */ n->slen = slen; if (hlist_empty(&n->leaf)) { put_child_root(pn, n->key, NULL); node_free(n); } } pr_debug("trie_flush found=%d\n", found); return found; } /* derived from fib_trie_free */ static void __fib_info_notify_update(struct net *net, struct fib_table *tb, struct nl_info *info) { struct trie *t = (struct trie *)tb->tb_data; struct key_vector *pn = t->kv; unsigned long cindex = 1; struct fib_alias *fa; for (;;) { struct key_vector *n; if (!(cindex--)) { t_key pkey = pn->key; if (IS_TRIE(pn)) break; pn = node_parent(pn); cindex = get_index(pkey, pn); continue; } /* grab the next available node */ n = get_child(pn, cindex); if (!n) continue; if (IS_TNODE(n)) { /* record pn and cindex for leaf walking */ pn = n; cindex = 1ul << n->bits; continue; } hlist_for_each_entry(fa, &n->leaf, fa_list) { struct fib_info *fi = fa->fa_info; if (!fi || !fi->nh_updated || fa->tb_id != tb->tb_id) continue; rtmsg_fib(RTM_NEWROUTE, htonl(n->key), fa, KEYLENGTH - fa->fa_slen, tb->tb_id, info, NLM_F_REPLACE); } } } void fib_info_notify_update(struct net *net, struct nl_info *info) { unsigned int h; for (h = 0; h < FIB_TABLE_HASHSZ; h++) { struct hlist_head *head = &net->ipv4.fib_table_hash[h]; struct fib_table *tb; hlist_for_each_entry_rcu(tb, head, tb_hlist, lockdep_rtnl_is_held()) __fib_info_notify_update(net, tb, info); } } static int fib_leaf_notify(struct key_vector *l, struct fib_table *tb, struct notifier_block *nb, struct netlink_ext_ack *extack) { struct fib_alias *fa; int last_slen = -1; int err; hlist_for_each_entry_rcu(fa, &l->leaf, fa_list) { struct fib_info *fi = fa->fa_info; if (!fi) continue; /* local and main table can share the same trie, * so don't notify twice for the same entry. */ if (tb->tb_id != fa->tb_id) continue; if (fa->fa_slen == last_slen) continue; last_slen = fa->fa_slen; err = call_fib_entry_notifier(nb, FIB_EVENT_ENTRY_REPLACE, l->key, KEYLENGTH - fa->fa_slen, fa, extack); if (err) return err; } return 0; } static int fib_table_notify(struct fib_table *tb, struct notifier_block *nb, struct netlink_ext_ack *extack) { struct trie *t = (struct trie *)tb->tb_data; struct key_vector *l, *tp = t->kv; t_key key = 0; int err; while ((l = leaf_walk_rcu(&tp, key)) != NULL) { err = fib_leaf_notify(l, tb, nb, extack); if (err) return err; key = l->key + 1; /* stop in case of wrap around */ if (key < l->key) break; } return 0; } int fib_notify(struct net *net, struct notifier_block *nb, struct netlink_ext_ack *extack) { unsigned int h; int err; for (h = 0; h < FIB_TABLE_HASHSZ; h++) { struct hlist_head *head = &net->ipv4.fib_table_hash[h]; struct fib_table *tb; hlist_for_each_entry_rcu(tb, head, tb_hlist) { err = fib_table_notify(tb, nb, extack); if (err) return err; } } return 0; } static void __trie_free_rcu(struct rcu_head *head) { struct fib_table *tb = container_of(head, struct fib_table, rcu); #ifdef CONFIG_IP_FIB_TRIE_STATS struct trie *t = (struct trie *)tb->tb_data; if (tb->tb_data == tb->__data) free_percpu(t->stats); #endif /* CONFIG_IP_FIB_TRIE_STATS */ kfree(tb); } void fib_free_table(struct fib_table *tb) { call_rcu(&tb->rcu, __trie_free_rcu); } static int fn_trie_dump_leaf(struct key_vector *l, struct fib_table *tb, struct sk_buff *skb, struct netlink_callback *cb, struct fib_dump_filter *filter) { unsigned int flags = NLM_F_MULTI; __be32 xkey = htonl(l->key); int i, s_i, i_fa, s_fa, err; struct fib_alias *fa; if (filter->filter_set || !filter->dump_exceptions || !filter->dump_routes) flags |= NLM_F_DUMP_FILTERED; s_i = cb->args[4]; s_fa = cb->args[5]; i = 0; /* rcu_read_lock is hold by caller */ hlist_for_each_entry_rcu(fa, &l->leaf, fa_list) { struct fib_info *fi = fa->fa_info; if (i < s_i) goto next; i_fa = 0; if (tb->tb_id != fa->tb_id) goto next; if (filter->filter_set) { if (filter->rt_type && fa->fa_type != filter->rt_type) goto next; if ((filter->protocol && fi->fib_protocol != filter->protocol)) goto next; if (filter->dev && !fib_info_nh_uses_dev(fi, filter->dev)) goto next; } if (filter->dump_routes) { if (!s_fa) { struct fib_rt_info fri; fri.fi = fi; fri.tb_id = tb->tb_id; fri.dst = xkey; fri.dst_len = KEYLENGTH - fa->fa_slen; fri.dscp = fa->fa_dscp; fri.type = fa->fa_type; fri.offload = READ_ONCE(fa->offload); fri.trap = READ_ONCE(fa->trap); fri.offload_failed = READ_ONCE(fa->offload_failed); err = fib_dump_info(skb, NETLINK_CB(cb->skb).portid, cb->nlh->nlmsg_seq, RTM_NEWROUTE, &fri, flags); if (err < 0) goto stop; } i_fa++; } if (filter->dump_exceptions) { err = fib_dump_info_fnhe(skb, cb, tb->tb_id, fi, &i_fa, s_fa, flags); if (err < 0) goto stop; } next: i++; } cb->args[4] = i; return skb->len; stop: cb->args[4] = i; cb->args[5] = i_fa; return err; } /* rcu_read_lock needs to be hold by caller from readside */ int fib_table_dump(struct fib_table *tb, struct sk_buff *skb, struct netlink_callback *cb, struct fib_dump_filter *filter) { struct trie *t = (struct trie *)tb->tb_data; struct key_vector *l, *tp = t->kv; /* Dump starting at last key. * Note: 0.0.0.0/0 (ie default) is first key. */ int count = cb->args[2]; t_key key = cb->args[3]; /* First time here, count and key are both always 0. Count > 0 * and key == 0 means the dump has wrapped around and we are done. */ if (count && !key) return 0; while ((l = leaf_walk_rcu(&tp, key)) != NULL) { int err; err = fn_trie_dump_leaf(l, tb, skb, cb, filter); if (err < 0) { cb->args[3] = key; cb->args[2] = count; return err; } ++count; key = l->key + 1; memset(&cb->args[4], 0, sizeof(cb->args) - 4*sizeof(cb->args[0])); /* stop loop if key wrapped back to 0 */ if (key < l->key) break; } cb->args[3] = key; cb->args[2] = count; return 0; } void __init fib_trie_init(void) { fn_alias_kmem = kmem_cache_create("ip_fib_alias", sizeof(struct fib_alias), 0, SLAB_PANIC | SLAB_ACCOUNT, NULL); trie_leaf_kmem = kmem_cache_create("ip_fib_trie", LEAF_SIZE, 0, SLAB_PANIC | SLAB_ACCOUNT, NULL); } struct fib_table *fib_trie_table(u32 id, struct fib_table *alias) { struct fib_table *tb; struct trie *t; size_t sz = sizeof(*tb); if (!alias) sz += sizeof(struct trie); tb = kzalloc(sz, GFP_KERNEL); if (!tb) return NULL; tb->tb_id = id; tb->tb_num_default = 0; tb->tb_data = (alias ? alias->__data : tb->__data); if (alias) return tb; t = (struct trie *) tb->tb_data; t->kv[0].pos = KEYLENGTH; t->kv[0].slen = KEYLENGTH; #ifdef CONFIG_IP_FIB_TRIE_STATS t->stats = alloc_percpu(struct trie_use_stats); if (!t->stats) { kfree(tb); tb = NULL; } #endif return tb; } #ifdef CONFIG_PROC_FS /* Depth first Trie walk iterator */ struct fib_trie_iter { struct seq_net_private p; struct fib_table *tb; struct key_vector *tnode; unsigned int index; unsigned int depth; }; static struct key_vector *fib_trie_get_next(struct fib_trie_iter *iter) { unsigned long cindex = iter->index; struct key_vector *pn = iter->tnode; t_key pkey; pr_debug("get_next iter={node=%p index=%d depth=%d}\n", iter->tnode, iter->index, iter->depth); while (!IS_TRIE(pn)) { while (cindex < child_length(pn)) { struct key_vector *n = get_child_rcu(pn, cindex++); if (!n) continue; if (IS_LEAF(n)) { iter->tnode = pn; iter->index = cindex; } else { /* push down one level */ iter->tnode = n; iter->index = 0; ++iter->depth; } return n; } /* Current node exhausted, pop back up */ pkey = pn->key; pn = node_parent_rcu(pn); cindex = get_index(pkey, pn) + 1; --iter->depth; } /* record root node so further searches know we are done */ iter->tnode = pn; iter->index = 0; return NULL; } static struct key_vector *fib_trie_get_first(struct fib_trie_iter *iter, struct trie *t) { struct key_vector *n, *pn; if (!t) return NULL; pn = t->kv; n = rcu_dereference(pn->tnode[0]); if (!n) return NULL; if (IS_TNODE(n)) { iter->tnode = n; iter->index = 0; iter->depth = 1; } else { iter->tnode = pn; iter->index = 0; iter->depth = 0; } return n; } static void trie_collect_stats(struct trie *t, struct trie_stat *s) { struct key_vector *n; struct fib_trie_iter iter; memset(s, 0, sizeof(*s)); rcu_read_lock(); for (n = fib_trie_get_first(&iter, t); n; n = fib_trie_get_next(&iter)) { if (IS_LEAF(n)) { struct fib_alias *fa; s->leaves++; s->totdepth += iter.depth; if (iter.depth > s->maxdepth) s->maxdepth = iter.depth; hlist_for_each_entry_rcu(fa, &n->leaf, fa_list) ++s->prefixes; } else { s->tnodes++; if (n->bits < MAX_STAT_DEPTH) s->nodesizes[n->bits]++; s->nullpointers += tn_info(n)->empty_children; } } rcu_read_unlock(); } /* * This outputs /proc/net/fib_triestats */ static void trie_show_stats(struct seq_file *seq, struct trie_stat *stat) { unsigned int i, max, pointers, bytes, avdepth; if (stat->leaves) avdepth = stat->totdepth*100 / stat->leaves; else avdepth = 0; seq_printf(seq, "\tAver depth: %u.%02d\n", avdepth / 100, avdepth % 100); seq_printf(seq, "\tMax depth: %u\n", stat->maxdepth); seq_printf(seq, "\tLeaves: %u\n", stat->leaves); bytes = LEAF_SIZE * stat->leaves; seq_printf(seq, "\tPrefixes: %u\n", stat->prefixes); bytes += sizeof(struct fib_alias) * stat->prefixes; seq_printf(seq, "\tInternal nodes: %u\n\t", stat->tnodes); bytes += TNODE_SIZE(0) * stat->tnodes; max = MAX_STAT_DEPTH; while (max > 0 && stat->nodesizes[max-1] == 0) max--; pointers = 0; for (i = 1; i < max; i++) if (stat->nodesizes[i] != 0) { seq_printf(seq, " %u: %u", i, stat->nodesizes[i]); pointers += (1<<i) * stat->nodesizes[i]; } seq_putc(seq, '\n'); seq_printf(seq, "\tPointers: %u\n", pointers); bytes += sizeof(struct key_vector *) * pointers; seq_printf(seq, "Null ptrs: %u\n", stat->nullpointers); seq_printf(seq, "Total size: %u kB\n", (bytes + 1023) / 1024); } #ifdef CONFIG_IP_FIB_TRIE_STATS static void trie_show_usage(struct seq_file *seq, const struct trie_use_stats __percpu *stats) { struct trie_use_stats s = { 0 }; int cpu; /* loop through all of the CPUs and gather up the stats */ for_each_possible_cpu(cpu) { const struct trie_use_stats *pcpu = per_cpu_ptr(stats, cpu); s.gets += pcpu->gets; s.backtrack += pcpu->backtrack; s.semantic_match_passed += pcpu->semantic_match_passed; s.semantic_match_miss += pcpu->semantic_match_miss; s.null_node_hit += pcpu->null_node_hit; s.resize_node_skipped += pcpu->resize_node_skipped; } seq_printf(seq, "\nCounters:\n---------\n"); seq_printf(seq, "gets = %u\n", s.gets); seq_printf(seq, "backtracks = %u\n", s.backtrack); seq_printf(seq, "semantic match passed = %u\n", s.semantic_match_passed); seq_printf(seq, "semantic match miss = %u\n", s.semantic_match_miss); seq_printf(seq, "null node hit= %u\n", s.null_node_hit); seq_printf(seq, "skipped node resize = %u\n\n", s.resize_node_skipped); } #endif /* CONFIG_IP_FIB_TRIE_STATS */ static void fib_table_print(struct seq_file *seq, struct fib_table *tb) { if (tb->tb_id == RT_TABLE_LOCAL) seq_puts(seq, "Local:\n"); else if (tb->tb_id == RT_TABLE_MAIN) seq_puts(seq, "Main:\n"); else seq_printf(seq, "Id %d:\n", tb->tb_id); } static int fib_triestat_seq_show(struct seq_file *seq, void *v) { struct net *net = seq->private; unsigned int h; seq_printf(seq, "Basic info: size of leaf:" " %zd bytes, size of tnode: %zd bytes.\n", LEAF_SIZE, TNODE_SIZE(0)); rcu_read_lock(); for (h = 0; h < FIB_TABLE_HASHSZ; h++) { struct hlist_head *head = &net->ipv4.fib_table_hash[h]; struct fib_table *tb; hlist_for_each_entry_rcu(tb, head, tb_hlist) { struct trie *t = (struct trie *) tb->tb_data; struct trie_stat stat; if (!t) continue; fib_table_print(seq, tb); trie_collect_stats(t, &stat); trie_show_stats(seq, &stat); #ifdef CONFIG_IP_FIB_TRIE_STATS trie_show_usage(seq, t->stats); #endif } cond_resched_rcu(); } rcu_read_unlock(); return 0; } static struct key_vector *fib_trie_get_idx(struct seq_file *seq, loff_t pos) { struct fib_trie_iter *iter = seq->private; struct net *net = seq_file_net(seq); loff_t idx = 0; unsigned int h; for (h = 0; h < FIB_TABLE_HASHSZ; h++) { struct hlist_head *head = &net->ipv4.fib_table_hash[h]; struct fib_table *tb; hlist_for_each_entry_rcu(tb, head, tb_hlist) { struct key_vector *n; for (n = fib_trie_get_first(iter, (struct trie *) tb->tb_data); n; n = fib_trie_get_next(iter)) if (pos == idx++) { iter->tb = tb; return n; } } } return NULL; } static void *fib_trie_seq_start(struct seq_file *seq, loff_t *pos) __acquires(RCU) { rcu_read_lock(); return fib_trie_get_idx(seq, *pos); } static void *fib_trie_seq_next(struct seq_file *seq, void *v, loff_t *pos) { struct fib_trie_iter *iter = seq->private; struct net *net = seq_file_net(seq); struct fib_table *tb = iter->tb; struct hlist_node *tb_node; unsigned int h; struct key_vector *n; ++*pos; /* next node in same table */ n = fib_trie_get_next(iter); if (n) return n; /* walk rest of this hash chain */ h = tb->tb_id & (FIB_TABLE_HASHSZ - 1); while ((tb_node = rcu_dereference(hlist_next_rcu(&tb->tb_hlist)))) { tb = hlist_entry(tb_node, struct fib_table, tb_hlist); n = fib_trie_get_first(iter, (struct trie *) tb->tb_data); if (n) goto found; } /* new hash chain */ while (++h < FIB_TABLE_HASHSZ) { struct hlist_head *head = &net->ipv4.fib_table_hash[h]; hlist_for_each_entry_rcu(tb, head, tb_hlist) { n = fib_trie_get_first(iter, (struct trie *) tb->tb_data); if (n) goto found; } } return NULL; found: iter->tb = tb; return n; } static void fib_trie_seq_stop(struct seq_file *seq, void *v) __releases(RCU) { rcu_read_unlock(); } static void seq_indent(struct seq_file *seq, int n) { while (n-- > 0) seq_puts(seq, " "); } static inline const char *rtn_scope(char *buf, size_t len, enum rt_scope_t s) { switch (s) { case RT_SCOPE_UNIVERSE: return "universe"; case RT_SCOPE_SITE: return "site"; case RT_SCOPE_LINK: return "link"; case RT_SCOPE_HOST: return "host"; case RT_SCOPE_NOWHERE: return "nowhere"; default: snprintf(buf, len, "scope=%d", s); return buf; } } static const char *const rtn_type_names[__RTN_MAX] = { [RTN_UNSPEC] = "UNSPEC", [RTN_UNICAST] = "UNICAST", [RTN_LOCAL] = "LOCAL", [RTN_BROADCAST] = "BROADCAST", [RTN_ANYCAST] = "ANYCAST", [RTN_MULTICAST] = "MULTICAST", [RTN_BLACKHOLE] = "BLACKHOLE", [RTN_UNREACHABLE] = "UNREACHABLE", [RTN_PROHIBIT] = "PROHIBIT", [RTN_THROW] = "THROW", [RTN_NAT] = "NAT", [RTN_XRESOLVE] = "XRESOLVE", }; static inline const char *rtn_type(char *buf, size_t len, unsigned int t) { if (t < __RTN_MAX && rtn_type_names[t]) return rtn_type_names[t]; snprintf(buf, len, "type %u", t); return buf; } /* Pretty print the trie */ static int fib_trie_seq_show(struct seq_file *seq, void *v) { const struct fib_trie_iter *iter = seq->private; struct key_vector *n = v; if (IS_TRIE(node_parent_rcu(n))) fib_table_print(seq, iter->tb); if (IS_TNODE(n)) { __be32 prf = htonl(n->key); seq_indent(seq, iter->depth-1); seq_printf(seq, " +-- %pI4/%zu %u %u %u\n", &prf, KEYLENGTH - n->pos - n->bits, n->bits, tn_info(n)->full_children, tn_info(n)->empty_children); } else { __be32 val = htonl(n->key); struct fib_alias *fa; seq_indent(seq, iter->depth); seq_printf(seq, " |-- %pI4\n", &val); hlist_for_each_entry_rcu(fa, &n->leaf, fa_list) { char buf1[32], buf2[32]; seq_indent(seq, iter->depth + 1); seq_printf(seq, " /%zu %s %s", KEYLENGTH - fa->fa_slen, rtn_scope(buf1, sizeof(buf1), fa->fa_info->fib_scope), rtn_type(buf2, sizeof(buf2), fa->fa_type)); if (fa->fa_dscp) seq_printf(seq, " tos=%d", inet_dscp_to_dsfield(fa->fa_dscp)); seq_putc(seq, '\n'); } } return 0; } static const struct seq_operations fib_trie_seq_ops = { .start = fib_trie_seq_start, .next = fib_trie_seq_next, .stop = fib_trie_seq_stop, .show = fib_trie_seq_show, }; struct fib_route_iter { struct seq_net_private p; struct fib_table *main_tb; struct key_vector *tnode; loff_t pos; t_key key; }; static struct key_vector *fib_route_get_idx(struct fib_route_iter *iter, loff_t pos) { struct key_vector *l, **tp = &iter->tnode; t_key key; /* use cached location of previously found key */ if (iter->pos > 0 && pos >= iter->pos) { key = iter->key; } else { iter->pos = 1; key = 0; } pos -= iter->pos; while ((l = leaf_walk_rcu(tp, key)) && (pos-- > 0)) { key = l->key + 1; iter->pos++; l = NULL; /* handle unlikely case of a key wrap */ if (!key) break; } if (l) iter->key = l->key; /* remember it */ else iter->pos = 0; /* forget it */ return l; } static void *fib_route_seq_start(struct seq_file *seq, loff_t *pos) __acquires(RCU) { struct fib_route_iter *iter = seq->private; struct fib_table *tb; struct trie *t; rcu_read_lock(); tb = fib_get_table(seq_file_net(seq), RT_TABLE_MAIN); if (!tb) return NULL; iter->main_tb = tb; t = (struct trie *)tb->tb_data; iter->tnode = t->kv; if (*pos != 0) return fib_route_get_idx(iter, *pos); iter->pos = 0; iter->key = KEY_MAX; return SEQ_START_TOKEN; } static void *fib_route_seq_next(struct seq_file *seq, void *v, loff_t *pos) { struct fib_route_iter *iter = seq->private; struct key_vector *l = NULL; t_key key = iter->key + 1; ++*pos; /* only allow key of 0 for start of sequence */ if ((v == SEQ_START_TOKEN) || key) l = leaf_walk_rcu(&iter->tnode, key); if (l) { iter->key = l->key; iter->pos++; } else { iter->pos = 0; } return l; } static void fib_route_seq_stop(struct seq_file *seq, void *v) __releases(RCU) { rcu_read_unlock(); } static unsigned int fib_flag_trans(int type, __be32 mask, struct fib_info *fi) { unsigned int flags = 0; if (type == RTN_UNREACHABLE || type == RTN_PROHIBIT) flags = RTF_REJECT; if (fi) { const struct fib_nh_common *nhc = fib_info_nhc(fi, 0); if (nhc->nhc_gw.ipv4) flags |= RTF_GATEWAY; } if (mask == htonl(0xFFFFFFFF)) flags |= RTF_HOST; flags |= RTF_UP; return flags; } /* * This outputs /proc/net/route. * The format of the file is not supposed to be changed * and needs to be same as fib_hash output to avoid breaking * legacy utilities */ static int fib_route_seq_show(struct seq_file *seq, void *v) { struct fib_route_iter *iter = seq->private; struct fib_table *tb = iter->main_tb; struct fib_alias *fa; struct key_vector *l = v; __be32 prefix; if (v == SEQ_START_TOKEN) { seq_printf(seq, "%-127s\n", "Iface\tDestination\tGateway " "\tFlags\tRefCnt\tUse\tMetric\tMask\t\tMTU" "\tWindow\tIRTT"); return 0; } prefix = htonl(l->key); hlist_for_each_entry_rcu(fa, &l->leaf, fa_list) { struct fib_info *fi = fa->fa_info; __be32 mask = inet_make_mask(KEYLENGTH - fa->fa_slen); unsigned int flags = fib_flag_trans(fa->fa_type, mask, fi); if ((fa->fa_type == RTN_BROADCAST) || (fa->fa_type == RTN_MULTICAST)) continue; if (fa->tb_id != tb->tb_id) continue; seq_setwidth(seq, 127); if (fi) { struct fib_nh_common *nhc = fib_info_nhc(fi, 0); __be32 gw = 0; if (nhc->nhc_gw_family == AF_INET) gw = nhc->nhc_gw.ipv4; seq_printf(seq, "%s\t%08X\t%08X\t%04X\t%d\t%u\t" "%u\t%08X\t%d\t%u\t%u", nhc->nhc_dev ? nhc->nhc_dev->name : "*", prefix, gw, flags, 0, 0, fi->fib_priority, mask, (fi->fib_advmss ? fi->fib_advmss + 40 : 0), fi->fib_window, fi->fib_rtt >> 3); } else { seq_printf(seq, "*\t%08X\t%08X\t%04X\t%d\t%u\t" "%u\t%08X\t%d\t%u\t%u", prefix, 0, flags, 0, 0, 0, mask, 0, 0, 0); } seq_pad(seq, '\n'); } return 0; } static const struct seq_operations fib_route_seq_ops = { .start = fib_route_seq_start, .next = fib_route_seq_next, .stop = fib_route_seq_stop, .show = fib_route_seq_show, }; int __net_init fib_proc_init(struct net *net) { if (!proc_create_net("fib_trie", 0444, net->proc_net, &fib_trie_seq_ops, sizeof(struct fib_trie_iter))) goto out1; if (!proc_create_net_single("fib_triestat", 0444, net->proc_net, fib_triestat_seq_show, NULL)) goto out2; if (!proc_create_net("route", 0444, net->proc_net, &fib_route_seq_ops, sizeof(struct fib_route_iter))) goto out3; return 0; out3: remove_proc_entry("fib_triestat", net->proc_net); out2: remove_proc_entry("fib_trie", net->proc_net); out1: return -ENOMEM; } void __net_exit fib_proc_exit(struct net *net) { remove_proc_entry("fib_trie", net->proc_net); remove_proc_entry("fib_triestat", net->proc_net); remove_proc_entry("route", net->proc_net); } #endif /* CONFIG_PROC_FS */ |
| 20 20 2 2 12 4 10 | 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 | // SPDX-License-Identifier: GPL-2.0-or-later /* * SR-IPv6 implementation * * Author: * David Lebrun <david.lebrun@uclouvain.be> */ #include <linux/types.h> #include <linux/skbuff.h> #include <linux/net.h> #include <linux/module.h> #include <net/ip.h> #include <net/ip_tunnels.h> #include <net/lwtunnel.h> #include <net/netevent.h> #include <net/netns/generic.h> #include <net/ip6_fib.h> #include <net/route.h> #include <net/seg6.h> #include <linux/seg6.h> #include <linux/seg6_iptunnel.h> #include <net/addrconf.h> #include <net/ip6_route.h> #include <net/dst_cache.h> #ifdef CONFIG_IPV6_SEG6_HMAC #include <net/seg6_hmac.h> #endif #include <linux/netfilter.h> static size_t seg6_lwt_headroom(struct seg6_iptunnel_encap *tuninfo) { int head = 0; switch (tuninfo->mode) { case SEG6_IPTUN_MODE_INLINE: break; case SEG6_IPTUN_MODE_ENCAP: case SEG6_IPTUN_MODE_ENCAP_RED: head = sizeof(struct ipv6hdr); break; case SEG6_IPTUN_MODE_L2ENCAP: case SEG6_IPTUN_MODE_L2ENCAP_RED: return 0; } return ((tuninfo->srh->hdrlen + 1) << 3) + head; } struct seg6_lwt { struct dst_cache cache; struct seg6_iptunnel_encap tuninfo[]; }; static inline struct seg6_lwt *seg6_lwt_lwtunnel(struct lwtunnel_state *lwt) { return (struct seg6_lwt *)lwt->data; } static inline struct seg6_iptunnel_encap * seg6_encap_lwtunnel(struct lwtunnel_state *lwt) { return seg6_lwt_lwtunnel(lwt)->tuninfo; } static const struct nla_policy seg6_iptunnel_policy[SEG6_IPTUNNEL_MAX + 1] = { [SEG6_IPTUNNEL_SRH] = { .type = NLA_BINARY }, }; static int nla_put_srh(struct sk_buff *skb, int attrtype, struct seg6_iptunnel_encap *tuninfo) { struct seg6_iptunnel_encap *data; struct nlattr *nla; int len; len = SEG6_IPTUN_ENCAP_SIZE(tuninfo); nla = nla_reserve(skb, attrtype, len); if (!nla) return -EMSGSIZE; data = nla_data(nla); memcpy(data, tuninfo, len); return 0; } static void set_tun_src(struct net *net, struct net_device *dev, struct in6_addr *daddr, struct in6_addr *saddr) { struct seg6_pernet_data *sdata = seg6_pernet(net); struct in6_addr *tun_src; rcu_read_lock(); tun_src = rcu_dereference(sdata->tun_src); if (!ipv6_addr_any(tun_src)) { memcpy(saddr, tun_src, sizeof(struct in6_addr)); } else { ipv6_dev_get_saddr(net, dev, daddr, IPV6_PREFER_SRC_PUBLIC, saddr); } rcu_read_unlock(); } /* Compute flowlabel for outer IPv6 header */ static __be32 seg6_make_flowlabel(struct net *net, struct sk_buff *skb, struct ipv6hdr *inner_hdr) { int do_flowlabel = net->ipv6.sysctl.seg6_flowlabel; __be32 flowlabel = 0; u32 hash; if (do_flowlabel > 0) { hash = skb_get_hash(skb); hash = rol32(hash, 16); flowlabel = (__force __be32)hash & IPV6_FLOWLABEL_MASK; } else if (!do_flowlabel && skb->protocol == htons(ETH_P_IPV6)) { flowlabel = ip6_flowlabel(inner_hdr); } return flowlabel; } static int __seg6_do_srh_encap(struct sk_buff *skb, struct ipv6_sr_hdr *osrh, int proto, struct dst_entry *cache_dst) { struct dst_entry *dst = skb_dst(skb); struct net *net = dev_net(dst->dev); struct ipv6hdr *hdr, *inner_hdr; struct ipv6_sr_hdr *isrh; int hdrlen, tot_len, err; __be32 flowlabel; hdrlen = (osrh->hdrlen + 1) << 3; tot_len = hdrlen + sizeof(*hdr); err = skb_cow_head(skb, tot_len + dst_dev_overhead(cache_dst, skb)); if (unlikely(err)) return err; inner_hdr = ipv6_hdr(skb); flowlabel = seg6_make_flowlabel(net, skb, inner_hdr); skb_push(skb, tot_len); skb_reset_network_header(skb); skb_mac_header_rebuild(skb); hdr = ipv6_hdr(skb); /* inherit tc, flowlabel and hlim * hlim will be decremented in ip6_forward() afterwards and * decapsulation will overwrite inner hlim with outer hlim */ if (skb->protocol == htons(ETH_P_IPV6)) { ip6_flow_hdr(hdr, ip6_tclass(ip6_flowinfo(inner_hdr)), flowlabel); hdr->hop_limit = inner_hdr->hop_limit; } else { ip6_flow_hdr(hdr, 0, flowlabel); hdr->hop_limit = ip6_dst_hoplimit(skb_dst(skb)); memset(IP6CB(skb), 0, sizeof(*IP6CB(skb))); /* the control block has been erased, so we have to set the * iif once again. * We read the receiving interface index directly from the * skb->skb_iif as it is done in the IPv4 receiving path (i.e.: * ip_rcv_core(...)). */ IP6CB(skb)->iif = skb->skb_iif; } hdr->nexthdr = NEXTHDR_ROUTING; isrh = (void *)hdr + sizeof(*hdr); memcpy(isrh, osrh, hdrlen); isrh->nexthdr = proto; hdr->daddr = isrh->segments[isrh->first_segment]; set_tun_src(net, dst->dev, &hdr->daddr, &hdr->saddr); #ifdef CONFIG_IPV6_SEG6_HMAC if (sr_has_hmac(isrh)) { err = seg6_push_hmac(net, &hdr->saddr, isrh); if (unlikely(err)) return err; } #endif hdr->payload_len = htons(skb->len - sizeof(struct ipv6hdr)); skb_postpush_rcsum(skb, hdr, tot_len); return 0; } /* encapsulate an IPv6 packet within an outer IPv6 header with a given SRH */ int seg6_do_srh_encap(struct sk_buff *skb, struct ipv6_sr_hdr *osrh, int proto) { return __seg6_do_srh_encap(skb, osrh, proto, NULL); } EXPORT_SYMBOL_GPL(seg6_do_srh_encap); /* encapsulate an IPv6 packet within an outer IPv6 header with reduced SRH */ static int seg6_do_srh_encap_red(struct sk_buff *skb, struct ipv6_sr_hdr *osrh, int proto, struct dst_entry *cache_dst) { __u8 first_seg = osrh->first_segment; struct dst_entry *dst = skb_dst(skb); struct net *net = dev_net(dst->dev); struct ipv6hdr *hdr, *inner_hdr; int hdrlen = ipv6_optlen(osrh); int red_tlv_offset, tlv_offset; struct ipv6_sr_hdr *isrh; bool skip_srh = false; __be32 flowlabel; int tot_len, err; int red_hdrlen; int tlvs_len; if (first_seg > 0) { red_hdrlen = hdrlen - sizeof(struct in6_addr); } else { /* NOTE: if tag/flags and/or other TLVs are introduced in the * seg6_iptunnel infrastructure, they should be considered when * deciding to skip the SRH. */ skip_srh = !sr_has_hmac(osrh); red_hdrlen = skip_srh ? 0 : hdrlen; } tot_len = red_hdrlen + sizeof(struct ipv6hdr); err = skb_cow_head(skb, tot_len + dst_dev_overhead(cache_dst, skb)); if (unlikely(err)) return err; inner_hdr = ipv6_hdr(skb); flowlabel = seg6_make_flowlabel(net, skb, inner_hdr); skb_push(skb, tot_len); skb_reset_network_header(skb); skb_mac_header_rebuild(skb); hdr = ipv6_hdr(skb); /* based on seg6_do_srh_encap() */ if (skb->protocol == htons(ETH_P_IPV6)) { ip6_flow_hdr(hdr, ip6_tclass(ip6_flowinfo(inner_hdr)), flowlabel); hdr->hop_limit = inner_hdr->hop_limit; } else { ip6_flow_hdr(hdr, 0, flowlabel); hdr->hop_limit = ip6_dst_hoplimit(skb_dst(skb)); memset(IP6CB(skb), 0, sizeof(*IP6CB(skb))); IP6CB(skb)->iif = skb->skb_iif; } /* no matter if we have to skip the SRH or not, the first segment * always comes in the pushed IPv6 header. */ hdr->daddr = osrh->segments[first_seg]; if (skip_srh) { hdr->nexthdr = proto; set_tun_src(net, dst->dev, &hdr->daddr, &hdr->saddr); goto out; } /* we cannot skip the SRH, slow path */ hdr->nexthdr = NEXTHDR_ROUTING; isrh = (void *)hdr + sizeof(struct ipv6hdr); if (unlikely(!first_seg)) { /* this is a very rare case; we have only one SID but * we cannot skip the SRH since we are carrying some * other info. */ memcpy(isrh, osrh, hdrlen); goto srcaddr; } tlv_offset = sizeof(*osrh) + (first_seg + 1) * sizeof(struct in6_addr); red_tlv_offset = tlv_offset - sizeof(struct in6_addr); memcpy(isrh, osrh, red_tlv_offset); tlvs_len = hdrlen - tlv_offset; if (unlikely(tlvs_len > 0)) { const void *s = (const void *)osrh + tlv_offset; void *d = (void *)isrh + red_tlv_offset; memcpy(d, s, tlvs_len); } --isrh->first_segment; isrh->hdrlen -= 2; srcaddr: isrh->nexthdr = proto; set_tun_src(net, dst->dev, &hdr->daddr, &hdr->saddr); #ifdef CONFIG_IPV6_SEG6_HMAC if (unlikely(!skip_srh && sr_has_hmac(isrh))) { err = seg6_push_hmac(net, &hdr->saddr, isrh); if (unlikely(err)) return err; } #endif out: hdr->payload_len = htons(skb->len - sizeof(struct ipv6hdr)); skb_postpush_rcsum(skb, hdr, tot_len); return 0; } static int __seg6_do_srh_inline(struct sk_buff *skb, struct ipv6_sr_hdr *osrh, struct dst_entry *cache_dst) { struct ipv6hdr *hdr, *oldhdr; struct ipv6_sr_hdr *isrh; int hdrlen, err; hdrlen = (osrh->hdrlen + 1) << 3; err = skb_cow_head(skb, hdrlen + dst_dev_overhead(cache_dst, skb)); if (unlikely(err)) return err; oldhdr = ipv6_hdr(skb); skb_pull(skb, sizeof(struct ipv6hdr)); skb_postpull_rcsum(skb, skb_network_header(skb), sizeof(struct ipv6hdr)); skb_push(skb, sizeof(struct ipv6hdr) + hdrlen); skb_reset_network_header(skb); skb_mac_header_rebuild(skb); hdr = ipv6_hdr(skb); memmove(hdr, oldhdr, sizeof(*hdr)); isrh = (void *)hdr + sizeof(*hdr); memcpy(isrh, osrh, hdrlen); isrh->nexthdr = hdr->nexthdr; hdr->nexthdr = NEXTHDR_ROUTING; isrh->segments[0] = hdr->daddr; hdr->daddr = isrh->segments[isrh->first_segment]; #ifdef CONFIG_IPV6_SEG6_HMAC if (sr_has_hmac(isrh)) { struct net *net = dev_net(skb_dst(skb)->dev); err = seg6_push_hmac(net, &hdr->saddr, isrh); if (unlikely(err)) return err; } #endif hdr->payload_len = htons(skb->len - sizeof(struct ipv6hdr)); skb_postpush_rcsum(skb, hdr, sizeof(struct ipv6hdr) + hdrlen); return 0; } static int seg6_do_srh(struct sk_buff *skb, struct dst_entry *cache_dst) { struct dst_entry *dst = skb_dst(skb); struct seg6_iptunnel_encap *tinfo; int proto, err = 0; tinfo = seg6_encap_lwtunnel(dst->lwtstate); switch (tinfo->mode) { case SEG6_IPTUN_MODE_INLINE: if (skb->protocol != htons(ETH_P_IPV6)) return -EINVAL; err = __seg6_do_srh_inline(skb, tinfo->srh, cache_dst); if (err) return err; break; case SEG6_IPTUN_MODE_ENCAP: case SEG6_IPTUN_MODE_ENCAP_RED: err = iptunnel_handle_offloads(skb, SKB_GSO_IPXIP6); if (err) return err; if (skb->protocol == htons(ETH_P_IPV6)) proto = IPPROTO_IPV6; else if (skb->protocol == htons(ETH_P_IP)) proto = IPPROTO_IPIP; else return -EINVAL; if (tinfo->mode == SEG6_IPTUN_MODE_ENCAP) err = __seg6_do_srh_encap(skb, tinfo->srh, proto, cache_dst); else err = seg6_do_srh_encap_red(skb, tinfo->srh, proto, cache_dst); if (err) return err; skb_set_inner_transport_header(skb, skb_transport_offset(skb)); skb_set_inner_protocol(skb, skb->protocol); skb->protocol = htons(ETH_P_IPV6); break; case SEG6_IPTUN_MODE_L2ENCAP: case SEG6_IPTUN_MODE_L2ENCAP_RED: if (!skb_mac_header_was_set(skb)) return -EINVAL; if (pskb_expand_head(skb, skb->mac_len, 0, GFP_ATOMIC) < 0) return -ENOMEM; skb_mac_header_rebuild(skb); skb_push(skb, skb->mac_len); if (tinfo->mode == SEG6_IPTUN_MODE_L2ENCAP) err = __seg6_do_srh_encap(skb, tinfo->srh, IPPROTO_ETHERNET, cache_dst); else err = seg6_do_srh_encap_red(skb, tinfo->srh, IPPROTO_ETHERNET, cache_dst); if (err) return err; skb->protocol = htons(ETH_P_IPV6); break; } skb_set_transport_header(skb, sizeof(struct ipv6hdr)); nf_reset_ct(skb); return 0; } /* insert an SRH within an IPv6 packet, just after the IPv6 header */ int seg6_do_srh_inline(struct sk_buff *skb, struct ipv6_sr_hdr *osrh) { return __seg6_do_srh_inline(skb, osrh, NULL); } EXPORT_SYMBOL_GPL(seg6_do_srh_inline); static int seg6_input_finish(struct net *net, struct sock *sk, struct sk_buff *skb) { return dst_input(skb); } static int seg6_input_core(struct net *net, struct sock *sk, struct sk_buff *skb) { struct dst_entry *orig_dst = skb_dst(skb); struct dst_entry *dst = NULL; struct seg6_lwt *slwt; int err; slwt = seg6_lwt_lwtunnel(orig_dst->lwtstate); local_bh_disable(); dst = dst_cache_get(&slwt->cache); local_bh_enable(); err = seg6_do_srh(skb, dst); if (unlikely(err)) goto drop; if (!dst) { ip6_route_input(skb); dst = skb_dst(skb); if (!dst->error) { local_bh_disable(); dst_cache_set_ip6(&slwt->cache, dst, &ipv6_hdr(skb)->saddr); local_bh_enable(); } err = skb_cow_head(skb, LL_RESERVED_SPACE(dst->dev)); if (unlikely(err)) goto drop; } else { skb_dst_drop(skb); skb_dst_set(skb, dst); } if (static_branch_unlikely(&nf_hooks_lwtunnel_enabled)) return NF_HOOK(NFPROTO_IPV6, NF_INET_LOCAL_OUT, dev_net(skb->dev), NULL, skb, NULL, skb_dst(skb)->dev, seg6_input_finish); return seg6_input_finish(dev_net(skb->dev), NULL, skb); drop: kfree_skb(skb); return err; } static int seg6_input_nf(struct sk_buff *skb) { struct net_device *dev = skb_dst(skb)->dev; struct net *net = dev_net(skb->dev); switch (skb->protocol) { case htons(ETH_P_IP): return NF_HOOK(NFPROTO_IPV4, NF_INET_POST_ROUTING, net, NULL, skb, NULL, dev, seg6_input_core); case htons(ETH_P_IPV6): return NF_HOOK(NFPROTO_IPV6, NF_INET_POST_ROUTING, net, NULL, skb, NULL, dev, seg6_input_core); } return -EINVAL; } static int seg6_input(struct sk_buff *skb) { if (static_branch_unlikely(&nf_hooks_lwtunnel_enabled)) return seg6_input_nf(skb); return seg6_input_core(dev_net(skb->dev), NULL, skb); } static int seg6_output_core(struct net *net, struct sock *sk, struct sk_buff *skb) { struct dst_entry *orig_dst = skb_dst(skb); struct dst_entry *dst = NULL; struct seg6_lwt *slwt; int err; slwt = seg6_lwt_lwtunnel(orig_dst->lwtstate); local_bh_disable(); dst = dst_cache_get(&slwt->cache); local_bh_enable(); err = seg6_do_srh(skb, dst); if (unlikely(err)) goto drop; if (unlikely(!dst)) { struct ipv6hdr *hdr = ipv6_hdr(skb); struct flowi6 fl6; memset(&fl6, 0, sizeof(fl6)); fl6.daddr = hdr->daddr; fl6.saddr = hdr->saddr; fl6.flowlabel = ip6_flowinfo(hdr); fl6.flowi6_mark = skb->mark; fl6.flowi6_proto = hdr->nexthdr; dst = ip6_route_output(net, NULL, &fl6); if (dst->error) { err = dst->error; dst_release(dst); goto drop; } local_bh_disable(); dst_cache_set_ip6(&slwt->cache, dst, &fl6.saddr); local_bh_enable(); err = skb_cow_head(skb, LL_RESERVED_SPACE(dst->dev)); if (unlikely(err)) goto drop; } skb_dst_drop(skb); skb_dst_set(skb, dst); if (static_branch_unlikely(&nf_hooks_lwtunnel_enabled)) return NF_HOOK(NFPROTO_IPV6, NF_INET_LOCAL_OUT, net, sk, skb, NULL, skb_dst(skb)->dev, dst_output); return dst_output(net, sk, skb); drop: kfree_skb(skb); return err; } static int seg6_output_nf(struct net *net, struct sock *sk, struct sk_buff *skb) { struct net_device *dev = skb_dst(skb)->dev; switch (skb->protocol) { case htons(ETH_P_IP): return NF_HOOK(NFPROTO_IPV4, NF_INET_POST_ROUTING, net, sk, skb, NULL, dev, seg6_output_core); case htons(ETH_P_IPV6): return NF_HOOK(NFPROTO_IPV6, NF_INET_POST_ROUTING, net, sk, skb, NULL, dev, seg6_output_core); } return -EINVAL; } static int seg6_output(struct net *net, struct sock *sk, struct sk_buff *skb) { if (static_branch_unlikely(&nf_hooks_lwtunnel_enabled)) return seg6_output_nf(net, sk, skb); return seg6_output_core(net, sk, skb); } static int seg6_build_state(struct net *net, struct nlattr *nla, unsigned int family, const void *cfg, struct lwtunnel_state **ts, struct netlink_ext_ack *extack) { struct nlattr *tb[SEG6_IPTUNNEL_MAX + 1]; struct seg6_iptunnel_encap *tuninfo; struct lwtunnel_state *newts; int tuninfo_len, min_size; struct seg6_lwt *slwt; int err; if (family != AF_INET && family != AF_INET6) return -EINVAL; err = nla_parse_nested_deprecated(tb, SEG6_IPTUNNEL_MAX, nla, seg6_iptunnel_policy, extack); if (err < 0) return err; if (!tb[SEG6_IPTUNNEL_SRH]) return -EINVAL; tuninfo = nla_data(tb[SEG6_IPTUNNEL_SRH]); tuninfo_len = nla_len(tb[SEG6_IPTUNNEL_SRH]); /* tuninfo must contain at least the iptunnel encap structure, * the SRH and one segment */ min_size = sizeof(*tuninfo) + sizeof(struct ipv6_sr_hdr) + sizeof(struct in6_addr); if (tuninfo_len < min_size) return -EINVAL; switch (tuninfo->mode) { case SEG6_IPTUN_MODE_INLINE: if (family != AF_INET6) return -EINVAL; break; case SEG6_IPTUN_MODE_ENCAP: break; case SEG6_IPTUN_MODE_L2ENCAP: break; case SEG6_IPTUN_MODE_ENCAP_RED: break; case SEG6_IPTUN_MODE_L2ENCAP_RED: break; default: return -EINVAL; } /* verify that SRH is consistent */ if (!seg6_validate_srh(tuninfo->srh, tuninfo_len - sizeof(*tuninfo), false)) return -EINVAL; newts = lwtunnel_state_alloc(tuninfo_len + sizeof(*slwt)); if (!newts) return -ENOMEM; slwt = seg6_lwt_lwtunnel(newts); err = dst_cache_init(&slwt->cache, GFP_ATOMIC); if (err) { kfree(newts); return err; } memcpy(&slwt->tuninfo, tuninfo, tuninfo_len); newts->type = LWTUNNEL_ENCAP_SEG6; newts->flags |= LWTUNNEL_STATE_INPUT_REDIRECT; if (tuninfo->mode != SEG6_IPTUN_MODE_L2ENCAP) newts->flags |= LWTUNNEL_STATE_OUTPUT_REDIRECT; newts->headroom = seg6_lwt_headroom(tuninfo); *ts = newts; return 0; } static void seg6_destroy_state(struct lwtunnel_state *lwt) { dst_cache_destroy(&seg6_lwt_lwtunnel(lwt)->cache); } static int seg6_fill_encap_info(struct sk_buff *skb, struct lwtunnel_state *lwtstate) { struct seg6_iptunnel_encap *tuninfo = seg6_encap_lwtunnel(lwtstate); if (nla_put_srh(skb, SEG6_IPTUNNEL_SRH, tuninfo)) return -EMSGSIZE; return 0; } static int seg6_encap_nlsize(struct lwtunnel_state *lwtstate) { struct seg6_iptunnel_encap *tuninfo = seg6_encap_lwtunnel(lwtstate); return nla_total_size(SEG6_IPTUN_ENCAP_SIZE(tuninfo)); } static int seg6_encap_cmp(struct lwtunnel_state *a, struct lwtunnel_state *b) { struct seg6_iptunnel_encap *a_hdr = seg6_encap_lwtunnel(a); struct seg6_iptunnel_encap *b_hdr = seg6_encap_lwtunnel(b); int len = SEG6_IPTUN_ENCAP_SIZE(a_hdr); if (len != SEG6_IPTUN_ENCAP_SIZE(b_hdr)) return 1; return memcmp(a_hdr, b_hdr, len); } static const struct lwtunnel_encap_ops seg6_iptun_ops = { .build_state = seg6_build_state, .destroy_state = seg6_destroy_state, .output = seg6_output, .input = seg6_input, .fill_encap = seg6_fill_encap_info, .get_encap_size = seg6_encap_nlsize, .cmp_encap = seg6_encap_cmp, .owner = THIS_MODULE, }; int __init seg6_iptunnel_init(void) { return lwtunnel_encap_add_ops(&seg6_iptun_ops, LWTUNNEL_ENCAP_SEG6); } void seg6_iptunnel_exit(void) { lwtunnel_encap_del_ops(&seg6_iptun_ops, LWTUNNEL_ENCAP_SEG6); } |
| 18 18 18 6 16 16 10 3 3 1 3 6 2 2 2 2 2 2 1 1 4 1 1 3 2 2 3 1 2 | 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 | // SPDX-License-Identifier: GPL-2.0 /* * cfg80211 wext compat for managed mode. * * Copyright 2009 Johannes Berg <johannes@sipsolutions.net> * Copyright (C) 2009, 2020-2023 Intel Corporation */ #include <linux/export.h> #include <linux/etherdevice.h> #include <linux/if_arp.h> #include <linux/slab.h> #include <net/cfg80211.h> #include <net/cfg80211-wext.h> #include "wext-compat.h" #include "nl80211.h" int cfg80211_mgd_wext_connect(struct cfg80211_registered_device *rdev, struct wireless_dev *wdev) { struct cfg80211_cached_keys *ck = NULL; const u8 *prev_bssid = NULL; int err, i; ASSERT_RTNL(); lockdep_assert_wiphy(wdev->wiphy); if (!netif_running(wdev->netdev)) return 0; wdev->wext.connect.ie = wdev->wext.ie; wdev->wext.connect.ie_len = wdev->wext.ie_len; /* Use default background scan period */ wdev->wext.connect.bg_scan_period = -1; if (wdev->wext.keys) { wdev->wext.keys->def = wdev->wext.default_key; if (wdev->wext.default_key != -1) wdev->wext.connect.privacy = true; } if (!wdev->wext.connect.ssid_len) return 0; if (wdev->wext.keys && wdev->wext.keys->def != -1) { ck = kmemdup(wdev->wext.keys, sizeof(*ck), GFP_KERNEL); if (!ck) return -ENOMEM; for (i = 0; i < 4; i++) ck->params[i].key = ck->data[i]; } if (wdev->wext.prev_bssid_valid) prev_bssid = wdev->wext.prev_bssid; err = cfg80211_connect(rdev, wdev->netdev, &wdev->wext.connect, ck, prev_bssid); if (err) kfree_sensitive(ck); return err; } int cfg80211_mgd_wext_siwfreq(struct net_device *dev, struct iw_request_info *info, struct iw_freq *wextfreq, char *extra) { struct wireless_dev *wdev = dev->ieee80211_ptr; struct cfg80211_registered_device *rdev = wiphy_to_rdev(wdev->wiphy); struct ieee80211_channel *chan = NULL; int err, freq; /* call only for station! */ if (WARN_ON(wdev->iftype != NL80211_IFTYPE_STATION)) return -EINVAL; freq = cfg80211_wext_freq(wextfreq); if (freq < 0) return freq; if (freq) { chan = ieee80211_get_channel(wdev->wiphy, freq); if (!chan) return -EINVAL; if (chan->flags & IEEE80211_CHAN_DISABLED) return -EINVAL; } if (wdev->conn) { bool event = true; if (wdev->wext.connect.channel == chan) return 0; /* if SSID set, we'll try right again, avoid event */ if (wdev->wext.connect.ssid_len) event = false; err = cfg80211_disconnect(rdev, dev, WLAN_REASON_DEAUTH_LEAVING, event); if (err) return err; } wdev->wext.connect.channel = chan; return cfg80211_mgd_wext_connect(rdev, wdev); } int cfg80211_mgd_wext_giwfreq(struct net_device *dev, struct iw_request_info *info, struct iw_freq *freq, char *extra) { struct wireless_dev *wdev = dev->ieee80211_ptr; struct ieee80211_channel *chan = NULL; /* call only for station! */ if (WARN_ON(wdev->iftype != NL80211_IFTYPE_STATION)) return -EINVAL; if (wdev->valid_links) return -EOPNOTSUPP; if (wdev->links[0].client.current_bss) chan = wdev->links[0].client.current_bss->pub.channel; else if (wdev->wext.connect.channel) chan = wdev->wext.connect.channel; if (chan) { freq->m = chan->center_freq; freq->e = 6; return 0; } /* no channel if not joining */ return -EINVAL; } int cfg80211_mgd_wext_siwessid(struct net_device *dev, struct iw_request_info *info, struct iw_point *data, char *ssid) { struct wireless_dev *wdev = dev->ieee80211_ptr; struct cfg80211_registered_device *rdev = wiphy_to_rdev(wdev->wiphy); size_t len = data->length; int err; /* call only for station! */ if (WARN_ON(wdev->iftype != NL80211_IFTYPE_STATION)) return -EINVAL; if (!data->flags) len = 0; /* iwconfig uses nul termination in SSID.. */ if (len > 0 && ssid[len - 1] == '\0') len--; if (wdev->conn) { bool event = true; if (wdev->wext.connect.ssid && len && len == wdev->wext.connect.ssid_len && memcmp(wdev->wext.connect.ssid, ssid, len) == 0) return 0; /* if SSID set now, we'll try to connect, avoid event */ if (len) event = false; err = cfg80211_disconnect(rdev, dev, WLAN_REASON_DEAUTH_LEAVING, event); if (err) return err; } wdev->wext.prev_bssid_valid = false; wdev->wext.connect.ssid = wdev->wext.ssid; memcpy(wdev->wext.ssid, ssid, len); wdev->wext.connect.ssid_len = len; wdev->wext.connect.crypto.control_port = false; wdev->wext.connect.crypto.control_port_ethertype = cpu_to_be16(ETH_P_PAE); return cfg80211_mgd_wext_connect(rdev, wdev); } int cfg80211_mgd_wext_giwessid(struct net_device *dev, struct iw_request_info *info, struct iw_point *data, char *ssid) { struct wireless_dev *wdev = dev->ieee80211_ptr; int ret = 0; /* call only for station! */ if (WARN_ON(wdev->iftype != NL80211_IFTYPE_STATION)) return -EINVAL; if (wdev->valid_links) return -EINVAL; data->flags = 0; if (wdev->links[0].client.current_bss) { const struct element *ssid_elem; rcu_read_lock(); ssid_elem = ieee80211_bss_get_elem( &wdev->links[0].client.current_bss->pub, WLAN_EID_SSID); if (ssid_elem) { data->flags = 1; data->length = ssid_elem->datalen; if (data->length > IW_ESSID_MAX_SIZE) ret = -EINVAL; else memcpy(ssid, ssid_elem->data, data->length); } rcu_read_unlock(); } else if (wdev->wext.connect.ssid && wdev->wext.connect.ssid_len) { data->flags = 1; data->length = wdev->wext.connect.ssid_len; memcpy(ssid, wdev->wext.connect.ssid, data->length); } return ret; } int cfg80211_mgd_wext_siwap(struct net_device *dev, struct iw_request_info *info, struct sockaddr *ap_addr, char *extra) { struct wireless_dev *wdev = dev->ieee80211_ptr; struct cfg80211_registered_device *rdev = wiphy_to_rdev(wdev->wiphy); u8 *bssid = ap_addr->sa_data; int err; /* call only for station! */ if (WARN_ON(wdev->iftype != NL80211_IFTYPE_STATION)) return -EINVAL; if (ap_addr->sa_family != ARPHRD_ETHER) return -EINVAL; /* automatic mode */ if (is_zero_ether_addr(bssid) || is_broadcast_ether_addr(bssid)) bssid = NULL; if (wdev->conn) { /* both automatic */ if (!bssid && !wdev->wext.connect.bssid) return 0; /* fixed already - and no change */ if (wdev->wext.connect.bssid && bssid && ether_addr_equal(bssid, wdev->wext.connect.bssid)) return 0; err = cfg80211_disconnect(rdev, dev, WLAN_REASON_DEAUTH_LEAVING, false); if (err) return err; } if (bssid) { memcpy(wdev->wext.bssid, bssid, ETH_ALEN); wdev->wext.connect.bssid = wdev->wext.bssid; } else wdev->wext.connect.bssid = NULL; return cfg80211_mgd_wext_connect(rdev, wdev); } int cfg80211_mgd_wext_giwap(struct net_device *dev, struct iw_request_info *info, struct sockaddr *ap_addr, char *extra) { struct wireless_dev *wdev = dev->ieee80211_ptr; /* call only for station! */ if (WARN_ON(wdev->iftype != NL80211_IFTYPE_STATION)) return -EINVAL; ap_addr->sa_family = ARPHRD_ETHER; if (wdev->valid_links) return -EOPNOTSUPP; if (wdev->links[0].client.current_bss) memcpy(ap_addr->sa_data, wdev->links[0].client.current_bss->pub.bssid, ETH_ALEN); else eth_zero_addr(ap_addr->sa_data); return 0; } int cfg80211_wext_siwgenie(struct net_device *dev, struct iw_request_info *info, union iwreq_data *wrqu, char *extra) { struct iw_point *data = &wrqu->data; struct wireless_dev *wdev = dev->ieee80211_ptr; struct cfg80211_registered_device *rdev = wiphy_to_rdev(wdev->wiphy); int ie_len = data->length; u8 *ie = extra; if (wdev->iftype != NL80211_IFTYPE_STATION) return -EOPNOTSUPP; if (!ie_len) ie = NULL; guard(wiphy)(wdev->wiphy); /* no change */ if (wdev->wext.ie_len == ie_len && memcmp(wdev->wext.ie, ie, ie_len) == 0) return 0; if (ie_len) { ie = kmemdup(extra, ie_len, GFP_KERNEL); if (!ie) return -ENOMEM; } else { ie = NULL; } kfree(wdev->wext.ie); wdev->wext.ie = ie; wdev->wext.ie_len = ie_len; if (wdev->conn) return cfg80211_disconnect(rdev, dev, WLAN_REASON_DEAUTH_LEAVING, false); /* userspace better not think we'll reconnect */ return 0; } int cfg80211_wext_siwmlme(struct net_device *dev, struct iw_request_info *info, union iwreq_data *wrqu, char *extra) { struct wireless_dev *wdev = dev->ieee80211_ptr; struct iw_mlme *mlme = (struct iw_mlme *)extra; struct cfg80211_registered_device *rdev; if (!wdev) return -EOPNOTSUPP; rdev = wiphy_to_rdev(wdev->wiphy); if (wdev->iftype != NL80211_IFTYPE_STATION) return -EINVAL; if (mlme->addr.sa_family != ARPHRD_ETHER) return -EINVAL; guard(wiphy)(&rdev->wiphy); switch (mlme->cmd) { case IW_MLME_DEAUTH: case IW_MLME_DISASSOC: return cfg80211_disconnect(rdev, dev, mlme->reason_code, true); default: return -EOPNOTSUPP; } } |
| 1065 1066 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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 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 | // SPDX-License-Identifier: GPL-2.0-only /* Copyright (c) 2013-2014 Intel Corp. */ #include <linux/if_arp.h> #include <linux/netdevice.h> #include <linux/etherdevice.h> #include <linux/module.h> #include <linux/debugfs.h> #include <net/ipv6.h> #include <net/ip6_route.h> #include <net/addrconf.h> #include <net/pkt_sched.h> #include <net/bluetooth/bluetooth.h> #include <net/bluetooth/hci_core.h> #include <net/bluetooth/l2cap.h> #include <net/6lowpan.h> /* for the compression support */ #define VERSION "0.1" static struct dentry *lowpan_enable_debugfs; static struct dentry *lowpan_control_debugfs; #define IFACE_NAME_TEMPLATE "bt%d" struct skb_cb { struct in6_addr addr; struct in6_addr gw; struct l2cap_chan *chan; }; #define lowpan_cb(skb) ((struct skb_cb *)((skb)->cb)) /* The devices list contains those devices that we are acting * as a proxy. The BT 6LoWPAN device is a virtual device that * connects to the Bluetooth LE device. The real connection to * BT device is done via l2cap layer. There exists one * virtual device / one BT 6LoWPAN network (=hciX device). * The list contains struct lowpan_dev elements. */ static LIST_HEAD(bt_6lowpan_devices); static DEFINE_SPINLOCK(devices_lock); static bool enable_6lowpan; /* We are listening incoming connections via this channel */ static struct l2cap_chan *listen_chan; static DEFINE_MUTEX(set_lock); struct lowpan_peer { struct list_head list; struct rcu_head rcu; struct l2cap_chan *chan; /* peer addresses in various formats */ unsigned char lladdr[ETH_ALEN]; struct in6_addr peer_addr; }; struct lowpan_btle_dev { struct list_head list; struct hci_dev *hdev; struct net_device *netdev; struct list_head peers; atomic_t peer_count; /* number of items in peers list */ struct work_struct delete_netdev; struct delayed_work notify_peers; }; static inline struct lowpan_btle_dev * lowpan_btle_dev(const struct net_device *netdev) { return (struct lowpan_btle_dev *)lowpan_dev(netdev)->priv; } static inline void peer_add(struct lowpan_btle_dev *dev, struct lowpan_peer *peer) { list_add_rcu(&peer->list, &dev->peers); atomic_inc(&dev->peer_count); } static inline bool peer_del(struct lowpan_btle_dev *dev, struct lowpan_peer *peer) { list_del_rcu(&peer->list); kfree_rcu(peer, rcu); module_put(THIS_MODULE); if (atomic_dec_and_test(&dev->peer_count)) { BT_DBG("last peer"); return true; } return false; } static inline struct lowpan_peer * __peer_lookup_chan(struct lowpan_btle_dev *dev, struct l2cap_chan *chan) { struct lowpan_peer *peer; list_for_each_entry_rcu(peer, &dev->peers, list) { if (peer->chan == chan) return peer; } return NULL; } static inline struct lowpan_peer * __peer_lookup_conn(struct lowpan_btle_dev *dev, struct l2cap_conn *conn) { struct lowpan_peer *peer; list_for_each_entry_rcu(peer, &dev->peers, list) { if (peer->chan->conn == conn) return peer; } return NULL; } static inline struct lowpan_peer *peer_lookup_dst(struct lowpan_btle_dev *dev, struct in6_addr *daddr, struct sk_buff *skb) { struct rt6_info *rt = dst_rt6_info(skb_dst(skb)); int count = atomic_read(&dev->peer_count); const struct in6_addr *nexthop; struct lowpan_peer *peer; struct neighbour *neigh; BT_DBG("peers %d addr %pI6c rt %p", count, daddr, rt); if (!rt) { if (ipv6_addr_any(&lowpan_cb(skb)->gw)) { /* There is neither route nor gateway, * probably the destination is a direct peer. */ nexthop = daddr; } else { /* There is a known gateway */ nexthop = &lowpan_cb(skb)->gw; } } else { nexthop = rt6_nexthop(rt, daddr); /* We need to remember the address because it is needed * by bt_xmit() when sending the packet. In bt_xmit(), the * destination routing info is not set. */ memcpy(&lowpan_cb(skb)->gw, nexthop, sizeof(struct in6_addr)); } BT_DBG("gw %pI6c", nexthop); rcu_read_lock(); list_for_each_entry_rcu(peer, &dev->peers, list) { BT_DBG("dst addr %pMR dst type %u ip %pI6c", &peer->chan->dst, peer->chan->dst_type, &peer->peer_addr); if (!ipv6_addr_cmp(&peer->peer_addr, nexthop)) { rcu_read_unlock(); return peer; } } /* use the neighbour cache for matching addresses assigned by SLAAC */ neigh = __ipv6_neigh_lookup(dev->netdev, nexthop); if (neigh) { list_for_each_entry_rcu(peer, &dev->peers, list) { if (!memcmp(neigh->ha, peer->lladdr, ETH_ALEN)) { neigh_release(neigh); rcu_read_unlock(); return peer; } } neigh_release(neigh); } rcu_read_unlock(); return NULL; } static struct lowpan_peer *lookup_peer(struct l2cap_conn *conn) { struct lowpan_btle_dev *entry; struct lowpan_peer *peer = NULL; rcu_read_lock(); list_for_each_entry_rcu(entry, &bt_6lowpan_devices, list) { peer = __peer_lookup_conn(entry, conn); if (peer) break; } rcu_read_unlock(); return peer; } static struct lowpan_btle_dev *lookup_dev(struct l2cap_conn *conn) { struct lowpan_btle_dev *entry; struct lowpan_btle_dev *dev = NULL; rcu_read_lock(); list_for_each_entry_rcu(entry, &bt_6lowpan_devices, list) { if (conn->hcon->hdev == entry->hdev) { dev = entry; break; } } rcu_read_unlock(); return dev; } static int give_skb_to_upper(struct sk_buff *skb, struct net_device *dev) { struct sk_buff *skb_cp; skb_cp = skb_copy(skb, GFP_ATOMIC); if (!skb_cp) return NET_RX_DROP; return netif_rx(skb_cp); } static int iphc_decompress(struct sk_buff *skb, struct net_device *netdev, struct lowpan_peer *peer) { const u8 *saddr; saddr = peer->lladdr; return lowpan_header_decompress(skb, netdev, netdev->dev_addr, saddr); } static int recv_pkt(struct sk_buff *skb, struct net_device *dev, struct lowpan_peer *peer) { struct sk_buff *local_skb; int ret; if (!netif_running(dev)) goto drop; if (dev->type != ARPHRD_6LOWPAN || !skb->len) goto drop; skb_reset_network_header(skb); skb = skb_share_check(skb, GFP_ATOMIC); if (!skb) goto drop; /* check that it's our buffer */ if (lowpan_is_ipv6(*skb_network_header(skb))) { /* Pull off the 1-byte of 6lowpan header. */ skb_pull(skb, 1); /* Copy the packet so that the IPv6 header is * properly aligned. */ local_skb = skb_copy_expand(skb, NET_SKB_PAD - 1, skb_tailroom(skb), GFP_ATOMIC); if (!local_skb) goto drop; local_skb->protocol = htons(ETH_P_IPV6); local_skb->pkt_type = PACKET_HOST; local_skb->dev = dev; skb_set_transport_header(local_skb, sizeof(struct ipv6hdr)); if (give_skb_to_upper(local_skb, dev) != NET_RX_SUCCESS) { kfree_skb(local_skb); goto drop; } dev->stats.rx_bytes += skb->len; dev->stats.rx_packets++; consume_skb(local_skb); consume_skb(skb); } else if (lowpan_is_iphc(*skb_network_header(skb))) { local_skb = skb_clone(skb, GFP_ATOMIC); if (!local_skb) goto drop; local_skb->dev = dev; ret = iphc_decompress(local_skb, dev, peer); if (ret < 0) { BT_DBG("iphc_decompress failed: %d", ret); kfree_skb(local_skb); goto drop; } local_skb->protocol = htons(ETH_P_IPV6); local_skb->pkt_type = PACKET_HOST; if (give_skb_to_upper(local_skb, dev) != NET_RX_SUCCESS) { kfree_skb(local_skb); goto drop; } dev->stats.rx_bytes += skb->len; dev->stats.rx_packets++; consume_skb(local_skb); consume_skb(skb); } else { BT_DBG("unknown packet type"); goto drop; } return NET_RX_SUCCESS; drop: dev->stats.rx_dropped++; return NET_RX_DROP; } /* Packet from BT LE device */ static int chan_recv_cb(struct l2cap_chan *chan, struct sk_buff *skb) { struct lowpan_btle_dev *dev; struct lowpan_peer *peer; int err; peer = lookup_peer(chan->conn); if (!peer) return -ENOENT; dev = lookup_dev(chan->conn); if (!dev || !dev->netdev) return -ENOENT; err = recv_pkt(skb, dev->netdev, peer); if (err) { BT_DBG("recv pkt %d", err); err = -EAGAIN; } return err; } static int setup_header(struct sk_buff *skb, struct net_device *netdev, bdaddr_t *peer_addr, u8 *peer_addr_type) { struct in6_addr ipv6_daddr; struct ipv6hdr *hdr; struct lowpan_btle_dev *dev; struct lowpan_peer *peer; u8 *daddr; int err, status = 0; hdr = ipv6_hdr(skb); dev = lowpan_btle_dev(netdev); memcpy(&ipv6_daddr, &hdr->daddr, sizeof(ipv6_daddr)); if (ipv6_addr_is_multicast(&ipv6_daddr)) { lowpan_cb(skb)->chan = NULL; daddr = NULL; } else { BT_DBG("dest IP %pI6c", &ipv6_daddr); /* The packet might be sent to 6lowpan interface * because of routing (either via default route * or user set route) so get peer according to * the destination address. */ peer = peer_lookup_dst(dev, &ipv6_daddr, skb); if (!peer) { BT_DBG("no such peer"); return -ENOENT; } daddr = peer->lladdr; *peer_addr = peer->chan->dst; *peer_addr_type = peer->chan->dst_type; lowpan_cb(skb)->chan = peer->chan; status = 1; } lowpan_header_compress(skb, netdev, daddr, dev->netdev->dev_addr); err = dev_hard_header(skb, netdev, ETH_P_IPV6, NULL, NULL, 0); if (err < 0) return err; return status; } static int header_create(struct sk_buff *skb, struct net_device *netdev, unsigned short type, const void *_daddr, const void *_saddr, unsigned int len) { if (type != ETH_P_IPV6) return -EINVAL; return 0; } /* Packet to BT LE device */ static int send_pkt(struct l2cap_chan *chan, struct sk_buff *skb, struct net_device *netdev) { struct msghdr msg; struct kvec iv; int err; /* Remember the skb so that we can send EAGAIN to the caller if * we run out of credits. */ chan->data = skb; iv.iov_base = skb->data; iv.iov_len = skb->len; memset(&msg, 0, sizeof(msg)); iov_iter_kvec(&msg.msg_iter, ITER_SOURCE, &iv, 1, skb->len); err = l2cap_chan_send(chan, &msg, skb->len); if (err > 0) { netdev->stats.tx_bytes += err; netdev->stats.tx_packets++; return 0; } if (err < 0) netdev->stats.tx_errors++; return err; } static int send_mcast_pkt(struct sk_buff *skb, struct net_device *netdev) { struct sk_buff *local_skb; struct lowpan_btle_dev *entry; int err = 0; rcu_read_lock(); list_for_each_entry_rcu(entry, &bt_6lowpan_devices, list) { struct lowpan_peer *pentry; struct lowpan_btle_dev *dev; if (entry->netdev != netdev) continue; dev = lowpan_btle_dev(entry->netdev); list_for_each_entry_rcu(pentry, &dev->peers, list) { int ret; local_skb = skb_clone(skb, GFP_ATOMIC); BT_DBG("xmit %s to %pMR type %u IP %pI6c chan %p", netdev->name, &pentry->chan->dst, pentry->chan->dst_type, &pentry->peer_addr, pentry->chan); ret = send_pkt(pentry->chan, local_skb, netdev); if (ret < 0) err = ret; kfree_skb(local_skb); } } rcu_read_unlock(); return err; } static netdev_tx_t bt_xmit(struct sk_buff *skb, struct net_device *netdev) { int err = 0; bdaddr_t addr; u8 addr_type; /* We must take a copy of the skb before we modify/replace the ipv6 * header as the header could be used elsewhere */ skb = skb_unshare(skb, GFP_ATOMIC); if (!skb) return NET_XMIT_DROP; /* Return values from setup_header() * <0 - error, packet is dropped * 0 - this is a multicast packet * 1 - this is unicast packet */ err = setup_header(skb, netdev, &addr, &addr_type); if (err < 0) { kfree_skb(skb); return NET_XMIT_DROP; } if (err) { if (lowpan_cb(skb)->chan) { BT_DBG("xmit %s to %pMR type %u IP %pI6c chan %p", netdev->name, &addr, addr_type, &lowpan_cb(skb)->addr, lowpan_cb(skb)->chan); err = send_pkt(lowpan_cb(skb)->chan, skb, netdev); } else { err = -ENOENT; } } else { /* We need to send the packet to every device behind this * interface. */ err = send_mcast_pkt(skb, netdev); } dev_kfree_skb(skb); if (err) BT_DBG("ERROR: xmit failed (%d)", err); return err < 0 ? NET_XMIT_DROP : err; } static int bt_dev_init(struct net_device *dev) { netdev_lockdep_set_classes(dev); return 0; } static const struct net_device_ops netdev_ops = { .ndo_init = bt_dev_init, .ndo_start_xmit = bt_xmit, }; static const struct header_ops header_ops = { .create = header_create, }; static void netdev_setup(struct net_device *dev) { dev->hard_header_len = 0; dev->needed_tailroom = 0; dev->flags = IFF_RUNNING | IFF_MULTICAST; dev->watchdog_timeo = 0; dev->tx_queue_len = DEFAULT_TX_QUEUE_LEN; dev->netdev_ops = &netdev_ops; dev->header_ops = &header_ops; dev->needs_free_netdev = true; } static const struct device_type bt_type = { .name = "bluetooth", }; static void ifup(struct net_device *netdev) { int err; rtnl_lock(); err = dev_open(netdev, NULL); if (err < 0) BT_INFO("iface %s cannot be opened (%d)", netdev->name, err); rtnl_unlock(); } static void ifdown(struct net_device *netdev) { rtnl_lock(); dev_close(netdev); rtnl_unlock(); } static void do_notify_peers(struct work_struct *work) { struct lowpan_btle_dev *dev = container_of(work, struct lowpan_btle_dev, notify_peers.work); netdev_notify_peers(dev->netdev); /* send neighbour adv at startup */ } static bool is_bt_6lowpan(struct hci_conn *hcon) { if (hcon->type != LE_LINK) return false; if (!enable_6lowpan) return false; return true; } static struct l2cap_chan *chan_create(void) { struct l2cap_chan *chan; chan = l2cap_chan_create(); if (!chan) return NULL; l2cap_chan_set_defaults(chan); chan->chan_type = L2CAP_CHAN_CONN_ORIENTED; chan->mode = L2CAP_MODE_LE_FLOWCTL; chan->imtu = 1280; return chan; } static struct l2cap_chan *add_peer_chan(struct l2cap_chan *chan, struct lowpan_btle_dev *dev, bool new_netdev) { struct lowpan_peer *peer; peer = kzalloc(sizeof(*peer), GFP_ATOMIC); if (!peer) return NULL; peer->chan = chan; baswap((void *)peer->lladdr, &chan->dst); lowpan_iphc_uncompress_eui48_lladdr(&peer->peer_addr, peer->lladdr); spin_lock(&devices_lock); INIT_LIST_HEAD(&peer->list); peer_add(dev, peer); spin_unlock(&devices_lock); /* Notifying peers about us needs to be done without locks held */ if (new_netdev) INIT_DELAYED_WORK(&dev->notify_peers, do_notify_peers); schedule_delayed_work(&dev->notify_peers, msecs_to_jiffies(100)); return peer->chan; } static int setup_netdev(struct l2cap_chan *chan, struct lowpan_btle_dev **dev) { struct net_device *netdev; bdaddr_t addr; int err; netdev = alloc_netdev(LOWPAN_PRIV_SIZE(sizeof(struct lowpan_btle_dev)), IFACE_NAME_TEMPLATE, NET_NAME_UNKNOWN, netdev_setup); if (!netdev) return -ENOMEM; netdev->addr_assign_type = NET_ADDR_PERM; baswap(&addr, &chan->src); __dev_addr_set(netdev, &addr, sizeof(addr)); netdev->netdev_ops = &netdev_ops; SET_NETDEV_DEV(netdev, &chan->conn->hcon->hdev->dev); SET_NETDEV_DEVTYPE(netdev, &bt_type); *dev = lowpan_btle_dev(netdev); (*dev)->netdev = netdev; (*dev)->hdev = chan->conn->hcon->hdev; INIT_LIST_HEAD(&(*dev)->peers); spin_lock(&devices_lock); INIT_LIST_HEAD(&(*dev)->list); list_add_rcu(&(*dev)->list, &bt_6lowpan_devices); spin_unlock(&devices_lock); err = lowpan_register_netdev(netdev, LOWPAN_LLTYPE_BTLE); if (err < 0) { BT_INFO("register_netdev failed %d", err); spin_lock(&devices_lock); list_del_rcu(&(*dev)->list); spin_unlock(&devices_lock); free_netdev(netdev); goto out; } BT_DBG("ifindex %d peer bdaddr %pMR type %d my addr %pMR type %d", netdev->ifindex, &chan->dst, chan->dst_type, &chan->src, chan->src_type); set_bit(__LINK_STATE_PRESENT, &netdev->state); return 0; out: return err; } static inline void chan_ready_cb(struct l2cap_chan *chan) { struct lowpan_btle_dev *dev; bool new_netdev = false; dev = lookup_dev(chan->conn); BT_DBG("chan %p conn %p dev %p", chan, chan->conn, dev); if (!dev) { if (setup_netdev(chan, &dev) < 0) { l2cap_chan_del(chan, -ENOENT); return; } new_netdev = true; } if (!try_module_get(THIS_MODULE)) return; add_peer_chan(chan, dev, new_netdev); ifup(dev->netdev); } static inline struct l2cap_chan *chan_new_conn_cb(struct l2cap_chan *pchan) { struct l2cap_chan *chan; chan = chan_create(); if (!chan) return NULL; chan->ops = pchan->ops; BT_DBG("chan %p pchan %p", chan, pchan); return chan; } static void delete_netdev(struct work_struct *work) { struct lowpan_btle_dev *entry = container_of(work, struct lowpan_btle_dev, delete_netdev); lowpan_unregister_netdev(entry->netdev); /* The entry pointer is deleted by the netdev destructor. */ } static void chan_close_cb(struct l2cap_chan *chan) { struct lowpan_btle_dev *entry; struct lowpan_btle_dev *dev = NULL; struct lowpan_peer *peer; int err = -ENOENT; bool last = false, remove = true; BT_DBG("chan %p conn %p", chan, chan->conn); if (chan->conn && chan->conn->hcon) { if (!is_bt_6lowpan(chan->conn->hcon)) return; /* If conn is set, then the netdev is also there and we should * not remove it. */ remove = false; } spin_lock(&devices_lock); list_for_each_entry_rcu(entry, &bt_6lowpan_devices, list) { dev = lowpan_btle_dev(entry->netdev); peer = __peer_lookup_chan(dev, chan); if (peer) { last = peer_del(dev, peer); err = 0; BT_DBG("dev %p removing %speer %p", dev, last ? "last " : "1 ", peer); BT_DBG("chan %p orig refcnt %u", chan, kref_read(&chan->kref)); l2cap_chan_put(chan); break; } } if (!err && last && dev && !atomic_read(&dev->peer_count)) { spin_unlock(&devices_lock); cancel_delayed_work_sync(&dev->notify_peers); ifdown(dev->netdev); if (remove) { INIT_WORK(&entry->delete_netdev, delete_netdev); schedule_work(&entry->delete_netdev); } } else { spin_unlock(&devices_lock); } } static void chan_state_change_cb(struct l2cap_chan *chan, int state, int err) { BT_DBG("chan %p conn %p state %s err %d", chan, chan->conn, state_to_string(state), err); } static struct sk_buff *chan_alloc_skb_cb(struct l2cap_chan *chan, unsigned long hdr_len, unsigned long len, int nb) { /* Note that we must allocate using GFP_ATOMIC here as * this function is called originally from netdev hard xmit * function in atomic context. */ return bt_skb_alloc(hdr_len + len, GFP_ATOMIC); } static void chan_suspend_cb(struct l2cap_chan *chan) { struct lowpan_btle_dev *dev; BT_DBG("chan %p suspend", chan); dev = lookup_dev(chan->conn); if (!dev || !dev->netdev) return; netif_stop_queue(dev->netdev); } static void chan_resume_cb(struct l2cap_chan *chan) { struct lowpan_btle_dev *dev; BT_DBG("chan %p resume", chan); dev = lookup_dev(chan->conn); if (!dev || !dev->netdev) return; netif_wake_queue(dev->netdev); } static long chan_get_sndtimeo_cb(struct l2cap_chan *chan) { return L2CAP_CONN_TIMEOUT; } static const struct l2cap_ops bt_6lowpan_chan_ops = { .name = "L2CAP 6LoWPAN channel", .new_connection = chan_new_conn_cb, .recv = chan_recv_cb, .close = chan_close_cb, .state_change = chan_state_change_cb, .ready = chan_ready_cb, .resume = chan_resume_cb, .suspend = chan_suspend_cb, .get_sndtimeo = chan_get_sndtimeo_cb, .alloc_skb = chan_alloc_skb_cb, .teardown = l2cap_chan_no_teardown, .defer = l2cap_chan_no_defer, .set_shutdown = l2cap_chan_no_set_shutdown, }; static int bt_6lowpan_connect(bdaddr_t *addr, u8 dst_type) { struct l2cap_chan *chan; int err; chan = chan_create(); if (!chan) return -EINVAL; chan->ops = &bt_6lowpan_chan_ops; err = l2cap_chan_connect(chan, cpu_to_le16(L2CAP_PSM_IPSP), 0, addr, dst_type, L2CAP_CONN_TIMEOUT); BT_DBG("chan %p err %d", chan, err); if (err < 0) l2cap_chan_put(chan); return err; } static int bt_6lowpan_disconnect(struct l2cap_conn *conn, u8 dst_type) { struct lowpan_peer *peer; BT_DBG("conn %p dst type %u", conn, dst_type); peer = lookup_peer(conn); if (!peer) return -ENOENT; BT_DBG("peer %p chan %p", peer, peer->chan); l2cap_chan_close(peer->chan, ENOENT); return 0; } static struct l2cap_chan *bt_6lowpan_listen(void) { bdaddr_t *addr = BDADDR_ANY; struct l2cap_chan *chan; int err; if (!enable_6lowpan) return NULL; chan = chan_create(); if (!chan) return NULL; chan->ops = &bt_6lowpan_chan_ops; chan->state = BT_LISTEN; chan->src_type = BDADDR_LE_PUBLIC; atomic_set(&chan->nesting, L2CAP_NESTING_PARENT); BT_DBG("chan %p src type %u", chan, chan->src_type); err = l2cap_add_psm(chan, addr, cpu_to_le16(L2CAP_PSM_IPSP)); if (err) { l2cap_chan_put(chan); BT_ERR("psm cannot be added err %d", err); return NULL; } return chan; } static int get_l2cap_conn(char *buf, bdaddr_t *addr, u8 *addr_type, struct l2cap_conn **conn) { struct hci_conn *hcon; struct hci_dev *hdev; int n; n = sscanf(buf, "%hhx:%hhx:%hhx:%hhx:%hhx:%hhx %hhu", &addr->b[5], &addr->b[4], &addr->b[3], &addr->b[2], &addr->b[1], &addr->b[0], addr_type); if (n < 7) return -EINVAL; /* The LE_PUBLIC address type is ignored because of BDADDR_ANY */ hdev = hci_get_route(addr, BDADDR_ANY, BDADDR_LE_PUBLIC); if (!hdev) return -ENOENT; hci_dev_lock(hdev); hcon = hci_conn_hash_lookup_le(hdev, addr, *addr_type); hci_dev_unlock(hdev); hci_dev_put(hdev); if (!hcon) return -ENOENT; *conn = (struct l2cap_conn *)hcon->l2cap_data; BT_DBG("conn %p dst %pMR type %u", *conn, &hcon->dst, hcon->dst_type); return 0; } static void disconnect_all_peers(void) { struct lowpan_btle_dev *entry; struct lowpan_peer *peer, *tmp_peer, *new_peer; struct list_head peers; INIT_LIST_HEAD(&peers); /* We make a separate list of peers as the close_cb() will * modify the device peers list so it is better not to mess * with the same list at the same time. */ rcu_read_lock(); list_for_each_entry_rcu(entry, &bt_6lowpan_devices, list) { list_for_each_entry_rcu(peer, &entry->peers, list) { new_peer = kmalloc(sizeof(*new_peer), GFP_ATOMIC); if (!new_peer) break; new_peer->chan = peer->chan; INIT_LIST_HEAD(&new_peer->list); list_add(&new_peer->list, &peers); } } rcu_read_unlock(); spin_lock(&devices_lock); list_for_each_entry_safe(peer, tmp_peer, &peers, list) { l2cap_chan_close(peer->chan, ENOENT); list_del_rcu(&peer->list); kfree_rcu(peer, rcu); } spin_unlock(&devices_lock); } struct set_enable { struct work_struct work; bool flag; }; static void do_enable_set(struct work_struct *work) { struct set_enable *set_enable = container_of(work, struct set_enable, work); if (!set_enable->flag || enable_6lowpan != set_enable->flag) /* Disconnect existing connections if 6lowpan is * disabled */ disconnect_all_peers(); enable_6lowpan = set_enable->flag; mutex_lock(&set_lock); if (listen_chan) { l2cap_chan_close(listen_chan, 0); l2cap_chan_put(listen_chan); } listen_chan = bt_6lowpan_listen(); mutex_unlock(&set_lock); kfree(set_enable); } static int lowpan_enable_set(void *data, u64 val) { struct set_enable *set_enable; set_enable = kzalloc(sizeof(*set_enable), GFP_KERNEL); if (!set_enable) return -ENOMEM; set_enable->flag = !!val; INIT_WORK(&set_enable->work, do_enable_set); schedule_work(&set_enable->work); return 0; } static int lowpan_enable_get(void *data, u64 *val) { *val = enable_6lowpan; return 0; } DEFINE_DEBUGFS_ATTRIBUTE(lowpan_enable_fops, lowpan_enable_get, lowpan_enable_set, "%llu\n"); static ssize_t lowpan_control_write(struct file *fp, const char __user *user_buffer, size_t count, loff_t *position) { char buf[32]; size_t buf_size = min(count, sizeof(buf) - 1); int ret; bdaddr_t addr; u8 addr_type; struct l2cap_conn *conn = NULL; if (copy_from_user(buf, user_buffer, buf_size)) return -EFAULT; buf[buf_size] = '\0'; if (memcmp(buf, "connect ", 8) == 0) { ret = get_l2cap_conn(&buf[8], &addr, &addr_type, &conn); if (ret == -EINVAL) return ret; mutex_lock(&set_lock); if (listen_chan) { l2cap_chan_close(listen_chan, 0); l2cap_chan_put(listen_chan); listen_chan = NULL; } mutex_unlock(&set_lock); if (conn) { struct lowpan_peer *peer; if (!is_bt_6lowpan(conn->hcon)) return -EINVAL; peer = lookup_peer(conn); if (peer) { BT_DBG("6LoWPAN connection already exists"); return -EALREADY; } BT_DBG("conn %p dst %pMR type %d user %u", conn, &conn->hcon->dst, conn->hcon->dst_type, addr_type); } ret = bt_6lowpan_connect(&addr, addr_type); if (ret < 0) return ret; return count; } if (memcmp(buf, "disconnect ", 11) == 0) { ret = get_l2cap_conn(&buf[11], &addr, &addr_type, &conn); if (ret < 0) return ret; ret = bt_6lowpan_disconnect(conn, addr_type); if (ret < 0) return ret; return count; } return count; } static int lowpan_control_show(struct seq_file *f, void *ptr) { struct lowpan_btle_dev *entry; struct lowpan_peer *peer; spin_lock(&devices_lock); list_for_each_entry(entry, &bt_6lowpan_devices, list) { list_for_each_entry(peer, &entry->peers, list) seq_printf(f, "%pMR (type %u)\n", &peer->chan->dst, peer->chan->dst_type); } spin_unlock(&devices_lock); return 0; } static int lowpan_control_open(struct inode *inode, struct file *file) { return single_open(file, lowpan_control_show, inode->i_private); } static const struct file_operations lowpan_control_fops = { .open = lowpan_control_open, .read = seq_read, .write = lowpan_control_write, .llseek = seq_lseek, .release = single_release, }; static void disconnect_devices(void) { struct lowpan_btle_dev *entry, *tmp, *new_dev; struct list_head devices; INIT_LIST_HEAD(&devices); /* We make a separate list of devices because the unregister_netdev() * will call device_event() which will also want to modify the same * devices list. */ rcu_read_lock(); list_for_each_entry_rcu(entry, &bt_6lowpan_devices, list) { new_dev = kmalloc(sizeof(*new_dev), GFP_ATOMIC); if (!new_dev) break; new_dev->netdev = entry->netdev; INIT_LIST_HEAD(&new_dev->list); list_add_rcu(&new_dev->list, &devices); } rcu_read_unlock(); list_for_each_entry_safe(entry, tmp, &devices, list) { ifdown(entry->netdev); BT_DBG("Unregistering netdev %s %p", entry->netdev->name, entry->netdev); lowpan_unregister_netdev(entry->netdev); kfree(entry); } } static int device_event(struct notifier_block *unused, unsigned long event, void *ptr) { struct net_device *netdev = netdev_notifier_info_to_dev(ptr); struct lowpan_btle_dev *entry; if (netdev->type != ARPHRD_6LOWPAN) return NOTIFY_DONE; switch (event) { case NETDEV_UNREGISTER: spin_lock(&devices_lock); list_for_each_entry(entry, &bt_6lowpan_devices, list) { if (entry->netdev == netdev) { BT_DBG("Unregistered netdev %s %p", netdev->name, netdev); list_del(&entry->list); break; } } spin_unlock(&devices_lock); break; } return NOTIFY_DONE; } static struct notifier_block bt_6lowpan_dev_notifier = { .notifier_call = device_event, }; static int __init bt_6lowpan_init(void) { lowpan_enable_debugfs = debugfs_create_file_unsafe("6lowpan_enable", 0644, bt_debugfs, NULL, &lowpan_enable_fops); lowpan_control_debugfs = debugfs_create_file("6lowpan_control", 0644, bt_debugfs, NULL, &lowpan_control_fops); return register_netdevice_notifier(&bt_6lowpan_dev_notifier); } static void __exit bt_6lowpan_exit(void) { debugfs_remove(lowpan_enable_debugfs); debugfs_remove(lowpan_control_debugfs); if (listen_chan) { l2cap_chan_close(listen_chan, 0); l2cap_chan_put(listen_chan); } disconnect_devices(); unregister_netdevice_notifier(&bt_6lowpan_dev_notifier); } module_init(bt_6lowpan_init); module_exit(bt_6lowpan_exit); MODULE_AUTHOR("Jukka Rissanen <jukka.rissanen@linux.intel.com>"); MODULE_DESCRIPTION("Bluetooth 6LoWPAN"); MODULE_VERSION(VERSION); MODULE_LICENSE("GPL"); |
| 2 125 125 4 125 | 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 */ #undef TRACE_SYSTEM #define TRACE_SYSTEM rpm #if !defined(_TRACE_RUNTIME_POWER_H) || defined(TRACE_HEADER_MULTI_READ) #define _TRACE_RUNTIME_POWER_H #include <linux/ktime.h> #include <linux/tracepoint.h> struct device; /* * The rpm_internal events are used for tracing some important * runtime pm internal functions. */ DECLARE_EVENT_CLASS(rpm_internal, TP_PROTO(struct device *dev, int flags), TP_ARGS(dev, flags), TP_STRUCT__entry( __string( name, dev_name(dev) ) __field( int, flags ) __field( int , usage_count ) __field( int , disable_depth ) __field( int , runtime_auto ) __field( int , request_pending ) __field( int , irq_safe ) __field( int , child_count ) ), TP_fast_assign( __assign_str(name); __entry->flags = flags; __entry->usage_count = atomic_read( &dev->power.usage_count); __entry->disable_depth = dev->power.disable_depth; __entry->runtime_auto = dev->power.runtime_auto; __entry->request_pending = dev->power.request_pending; __entry->irq_safe = dev->power.irq_safe; __entry->child_count = atomic_read( &dev->power.child_count); ), TP_printk("%s flags-%x cnt-%-2d dep-%-2d auto-%-1d p-%-1d" " irq-%-1d child-%d", __get_str(name), __entry->flags, __entry->usage_count, __entry->disable_depth, __entry->runtime_auto, __entry->request_pending, __entry->irq_safe, __entry->child_count ) ); DEFINE_EVENT(rpm_internal, rpm_suspend, TP_PROTO(struct device *dev, int flags), TP_ARGS(dev, flags) ); DEFINE_EVENT(rpm_internal, rpm_resume, TP_PROTO(struct device *dev, int flags), TP_ARGS(dev, flags) ); DEFINE_EVENT(rpm_internal, rpm_idle, TP_PROTO(struct device *dev, int flags), TP_ARGS(dev, flags) ); DEFINE_EVENT(rpm_internal, rpm_usage, TP_PROTO(struct device *dev, int flags), TP_ARGS(dev, flags) ); TRACE_EVENT(rpm_return_int, TP_PROTO(struct device *dev, unsigned long ip, int ret), TP_ARGS(dev, ip, ret), TP_STRUCT__entry( __string( name, dev_name(dev)) __field( unsigned long, ip ) __field( int, ret ) ), TP_fast_assign( __assign_str(name); __entry->ip = ip; __entry->ret = ret; ), TP_printk("%pS:%s ret=%d", (void *)__entry->ip, __get_str(name), __entry->ret) ); #define RPM_STATUS_STRINGS \ EM(RPM_INVALID, "RPM_INVALID") \ EM(RPM_ACTIVE, "RPM_ACTIVE") \ EM(RPM_RESUMING, "RPM_RESUMING") \ EM(RPM_SUSPENDED, "RPM_SUSPENDED") \ EMe(RPM_SUSPENDING, "RPM_SUSPENDING") /* Enums require being exported to userspace, for user tool parsing. */ #undef EM #undef EMe #define EM(a, b) TRACE_DEFINE_ENUM(a); #define EMe(a, b) TRACE_DEFINE_ENUM(a); RPM_STATUS_STRINGS /* * Now redefine the EM() and EMe() macros to map the enums to the strings that * will be printed in the output. */ #undef EM #undef EMe #define EM(a, b) { a, b }, #define EMe(a, b) { a, b } TRACE_EVENT(rpm_status, TP_PROTO(struct device *dev, enum rpm_status status), TP_ARGS(dev, status), TP_STRUCT__entry( __string(name, dev_name(dev)) __field(int, status) ), TP_fast_assign( __assign_str(name); __entry->status = status; ), TP_printk("%s status=%s", __get_str(name), __print_symbolic(__entry->status, RPM_STATUS_STRINGS)) ); #endif /* _TRACE_RUNTIME_POWER_H */ /* This part must be outside protection */ #include <trace/define_trace.h> |
| 499 58 59 59 59 59 | 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 | #include <linux/rtnetlink.h> #include <linux/notifier.h> #include <linux/rcupdate.h> #include <linux/kernel.h> #include <linux/module.h> #include <linux/init.h> #include <net/net_namespace.h> #include <net/netns/generic.h> #include <net/fib_notifier.h> static unsigned int fib_notifier_net_id; struct fib_notifier_net { struct list_head fib_notifier_ops; struct atomic_notifier_head fib_chain; }; int call_fib_notifier(struct notifier_block *nb, enum fib_event_type event_type, struct fib_notifier_info *info) { int err; err = nb->notifier_call(nb, event_type, info); return notifier_to_errno(err); } EXPORT_SYMBOL(call_fib_notifier); int call_fib_notifiers(struct net *net, enum fib_event_type event_type, struct fib_notifier_info *info) { struct fib_notifier_net *fn_net = net_generic(net, fib_notifier_net_id); int err; err = atomic_notifier_call_chain(&fn_net->fib_chain, event_type, info); return notifier_to_errno(err); } EXPORT_SYMBOL(call_fib_notifiers); static unsigned int fib_seq_sum(struct net *net) { struct fib_notifier_net *fn_net = net_generic(net, fib_notifier_net_id); struct fib_notifier_ops *ops; unsigned int fib_seq = 0; rcu_read_lock(); list_for_each_entry_rcu(ops, &fn_net->fib_notifier_ops, list) { if (!try_module_get(ops->owner)) continue; fib_seq += ops->fib_seq_read(net); module_put(ops->owner); } rcu_read_unlock(); return fib_seq; } static int fib_net_dump(struct net *net, struct notifier_block *nb, struct netlink_ext_ack *extack) { struct fib_notifier_net *fn_net = net_generic(net, fib_notifier_net_id); struct fib_notifier_ops *ops; int err = 0; rcu_read_lock(); list_for_each_entry_rcu(ops, &fn_net->fib_notifier_ops, list) { if (!try_module_get(ops->owner)) continue; err = ops->fib_dump(net, nb, extack); module_put(ops->owner); if (err) goto unlock; } unlock: rcu_read_unlock(); return err; } static bool fib_dump_is_consistent(struct net *net, struct notifier_block *nb, void (*cb)(struct notifier_block *nb), unsigned int fib_seq) { struct fib_notifier_net *fn_net = net_generic(net, fib_notifier_net_id); atomic_notifier_chain_register(&fn_net->fib_chain, nb); if (fib_seq == fib_seq_sum(net)) return true; atomic_notifier_chain_unregister(&fn_net->fib_chain, nb); if (cb) cb(nb); return false; } #define FIB_DUMP_MAX_RETRIES 5 int register_fib_notifier(struct net *net, struct notifier_block *nb, void (*cb)(struct notifier_block *nb), struct netlink_ext_ack *extack) { int retries = 0; int err; do { unsigned int fib_seq = fib_seq_sum(net); err = fib_net_dump(net, nb, extack); if (err) return err; if (fib_dump_is_consistent(net, nb, cb, fib_seq)) return 0; } while (++retries < FIB_DUMP_MAX_RETRIES); return -EBUSY; } EXPORT_SYMBOL(register_fib_notifier); int unregister_fib_notifier(struct net *net, struct notifier_block *nb) { struct fib_notifier_net *fn_net = net_generic(net, fib_notifier_net_id); return atomic_notifier_chain_unregister(&fn_net->fib_chain, nb); } EXPORT_SYMBOL(unregister_fib_notifier); static int __fib_notifier_ops_register(struct fib_notifier_ops *ops, struct net *net) { struct fib_notifier_net *fn_net = net_generic(net, fib_notifier_net_id); struct fib_notifier_ops *o; list_for_each_entry(o, &fn_net->fib_notifier_ops, list) if (ops->family == o->family) return -EEXIST; list_add_tail_rcu(&ops->list, &fn_net->fib_notifier_ops); return 0; } struct fib_notifier_ops * fib_notifier_ops_register(const struct fib_notifier_ops *tmpl, struct net *net) { struct fib_notifier_ops *ops; int err; ops = kmemdup(tmpl, sizeof(*ops), GFP_KERNEL); if (!ops) return ERR_PTR(-ENOMEM); err = __fib_notifier_ops_register(ops, net); if (err) goto err_register; return ops; err_register: kfree(ops); return ERR_PTR(err); } EXPORT_SYMBOL(fib_notifier_ops_register); void fib_notifier_ops_unregister(struct fib_notifier_ops *ops) { list_del_rcu(&ops->list); kfree_rcu(ops, rcu); } EXPORT_SYMBOL(fib_notifier_ops_unregister); static int __net_init fib_notifier_net_init(struct net *net) { struct fib_notifier_net *fn_net = net_generic(net, fib_notifier_net_id); INIT_LIST_HEAD(&fn_net->fib_notifier_ops); ATOMIC_INIT_NOTIFIER_HEAD(&fn_net->fib_chain); return 0; } static void __net_exit fib_notifier_net_exit(struct net *net) { struct fib_notifier_net *fn_net = net_generic(net, fib_notifier_net_id); WARN_ON_ONCE(!list_empty(&fn_net->fib_notifier_ops)); } static struct pernet_operations fib_notifier_net_ops = { .init = fib_notifier_net_init, .exit = fib_notifier_net_exit, .id = &fib_notifier_net_id, .size = sizeof(struct fib_notifier_net), }; static int __init fib_notifier_init(void) { return register_pernet_subsys(&fib_notifier_net_ops); } subsys_initcall(fib_notifier_init); |
| 58 58 58 58 | 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 | // SPDX-License-Identifier: GPL-2.0 #include <linux/types.h> #include <linux/netfilter.h> #include <linux/slab.h> #include <linux/module.h> #include <linux/skbuff.h> #include <linux/proc_fs.h> #include <linux/seq_file.h> #include <linux/percpu.h> #include <linux/netdevice.h> #include <linux/security.h> #include <net/net_namespace.h> #ifdef CONFIG_SYSCTL #include <linux/sysctl.h> #endif #include <net/netfilter/nf_conntrack.h> #include <net/netfilter/nf_conntrack_core.h> #include <net/netfilter/nf_conntrack_l4proto.h> #include <net/netfilter/nf_conntrack_expect.h> #include <net/netfilter/nf_conntrack_helper.h> #include <net/netfilter/nf_conntrack_acct.h> #include <net/netfilter/nf_conntrack_zones.h> #include <net/netfilter/nf_conntrack_timestamp.h> #include <linux/rculist_nulls.h> static bool enable_hooks __read_mostly; MODULE_PARM_DESC(enable_hooks, "Always enable conntrack hooks"); module_param(enable_hooks, bool, 0000); unsigned int nf_conntrack_net_id __read_mostly; #ifdef CONFIG_NF_CONNTRACK_PROCFS void print_tuple(struct seq_file *s, const struct nf_conntrack_tuple *tuple, const struct nf_conntrack_l4proto *l4proto) { switch (tuple->src.l3num) { case NFPROTO_IPV4: seq_printf(s, "src=%pI4 dst=%pI4 ", &tuple->src.u3.ip, &tuple->dst.u3.ip); break; case NFPROTO_IPV6: seq_printf(s, "src=%pI6 dst=%pI6 ", tuple->src.u3.ip6, tuple->dst.u3.ip6); break; default: break; } switch (l4proto->l4proto) { case IPPROTO_ICMP: seq_printf(s, "type=%u code=%u id=%u ", tuple->dst.u.icmp.type, tuple->dst.u.icmp.code, ntohs(tuple->src.u.icmp.id)); break; case IPPROTO_TCP: seq_printf(s, "sport=%hu dport=%hu ", ntohs(tuple->src.u.tcp.port), ntohs(tuple->dst.u.tcp.port)); break; case IPPROTO_UDPLITE: case IPPROTO_UDP: seq_printf(s, "sport=%hu dport=%hu ", ntohs(tuple->src.u.udp.port), ntohs(tuple->dst.u.udp.port)); break; case IPPROTO_DCCP: seq_printf(s, "sport=%hu dport=%hu ", ntohs(tuple->src.u.dccp.port), ntohs(tuple->dst.u.dccp.port)); break; case IPPROTO_SCTP: seq_printf(s, "sport=%hu dport=%hu ", ntohs(tuple->src.u.sctp.port), ntohs(tuple->dst.u.sctp.port)); break; case IPPROTO_ICMPV6: seq_printf(s, "type=%u code=%u id=%u ", tuple->dst.u.icmp.type, tuple->dst.u.icmp.code, ntohs(tuple->src.u.icmp.id)); break; case IPPROTO_GRE: seq_printf(s, "srckey=0x%x dstkey=0x%x ", ntohs(tuple->src.u.gre.key), ntohs(tuple->dst.u.gre.key)); break; default: break; } } EXPORT_SYMBOL_GPL(print_tuple); struct ct_iter_state { struct seq_net_private p; struct hlist_nulls_head *hash; unsigned int htable_size; unsigned int bucket; u_int64_t time_now; }; static struct hlist_nulls_node *ct_get_first(struct seq_file *seq) { struct ct_iter_state *st = seq->private; struct hlist_nulls_node *n; for (st->bucket = 0; st->bucket < st->htable_size; st->bucket++) { n = rcu_dereference( hlist_nulls_first_rcu(&st->hash[st->bucket])); if (!is_a_nulls(n)) return n; } return NULL; } static struct hlist_nulls_node *ct_get_next(struct seq_file *seq, struct hlist_nulls_node *head) { struct ct_iter_state *st = seq->private; head = rcu_dereference(hlist_nulls_next_rcu(head)); while (is_a_nulls(head)) { if (likely(get_nulls_value(head) == st->bucket)) { if (++st->bucket >= st->htable_size) return NULL; } head = rcu_dereference( hlist_nulls_first_rcu(&st->hash[st->bucket])); } return head; } static struct hlist_nulls_node *ct_get_idx(struct seq_file *seq, loff_t pos) { struct hlist_nulls_node *head = ct_get_first(seq); if (head) while (pos && (head = ct_get_next(seq, head))) pos--; return pos ? NULL : head; } static void *ct_seq_start(struct seq_file *seq, loff_t *pos) __acquires(RCU) { struct ct_iter_state *st = seq->private; st->time_now = ktime_get_real_ns(); rcu_read_lock(); nf_conntrack_get_ht(&st->hash, &st->htable_size); return ct_get_idx(seq, *pos); } static void *ct_seq_next(struct seq_file *s, void *v, loff_t *pos) { (*pos)++; return ct_get_next(s, v); } static void ct_seq_stop(struct seq_file *s, void *v) __releases(RCU) { rcu_read_unlock(); } #ifdef CONFIG_NF_CONNTRACK_SECMARK static void ct_show_secctx(struct seq_file *s, const struct nf_conn *ct) { struct lsm_context ctx; int ret; ret = security_secid_to_secctx(ct->secmark, &ctx); if (ret < 0) return; seq_printf(s, "secctx=%s ", ctx.context); security_release_secctx(&ctx); } #else static inline void ct_show_secctx(struct seq_file *s, const struct nf_conn *ct) { } #endif #ifdef CONFIG_NF_CONNTRACK_ZONES static void ct_show_zone(struct seq_file *s, const struct nf_conn *ct, int dir) { const struct nf_conntrack_zone *zone = nf_ct_zone(ct); if (zone->dir != dir) return; switch (zone->dir) { case NF_CT_DEFAULT_ZONE_DIR: seq_printf(s, "zone=%u ", zone->id); break; case NF_CT_ZONE_DIR_ORIG: seq_printf(s, "zone-orig=%u ", zone->id); break; case NF_CT_ZONE_DIR_REPL: seq_printf(s, "zone-reply=%u ", zone->id); break; default: break; } } #else static inline void ct_show_zone(struct seq_file *s, const struct nf_conn *ct, int dir) { } #endif #ifdef CONFIG_NF_CONNTRACK_TIMESTAMP static void ct_show_delta_time(struct seq_file *s, const struct nf_conn *ct) { struct ct_iter_state *st = s->private; struct nf_conn_tstamp *tstamp; s64 delta_time; tstamp = nf_conn_tstamp_find(ct); if (tstamp) { delta_time = st->time_now - tstamp->start; if (delta_time > 0) delta_time = div_s64(delta_time, NSEC_PER_SEC); else delta_time = 0; seq_printf(s, "delta-time=%llu ", (unsigned long long)delta_time); } return; } #else static inline void ct_show_delta_time(struct seq_file *s, const struct nf_conn *ct) { } #endif static const char* l3proto_name(u16 proto) { switch (proto) { case AF_INET: return "ipv4"; case AF_INET6: return "ipv6"; } return "unknown"; } static const char* l4proto_name(u16 proto) { switch (proto) { case IPPROTO_ICMP: return "icmp"; case IPPROTO_TCP: return "tcp"; case IPPROTO_UDP: return "udp"; case IPPROTO_DCCP: return "dccp"; case IPPROTO_GRE: return "gre"; case IPPROTO_SCTP: return "sctp"; case IPPROTO_UDPLITE: return "udplite"; case IPPROTO_ICMPV6: return "icmpv6"; } return "unknown"; } static void seq_print_acct(struct seq_file *s, const struct nf_conn *ct, int dir) { struct nf_conn_acct *acct; struct nf_conn_counter *counter; acct = nf_conn_acct_find(ct); if (!acct) return; counter = acct->counter; seq_printf(s, "packets=%llu bytes=%llu ", (unsigned long long)atomic64_read(&counter[dir].packets), (unsigned long long)atomic64_read(&counter[dir].bytes)); } /* return 0 on success, 1 in case of error */ static int ct_seq_show(struct seq_file *s, void *v) { struct nf_conntrack_tuple_hash *hash = v; struct nf_conn *ct = nf_ct_tuplehash_to_ctrack(hash); const struct nf_conntrack_l4proto *l4proto; struct net *net = seq_file_net(s); int ret = 0; WARN_ON(!ct); if (unlikely(!refcount_inc_not_zero(&ct->ct_general.use))) return 0; /* load ->status after refcount increase */ smp_acquire__after_ctrl_dep(); if (nf_ct_should_gc(ct)) { nf_ct_kill(ct); goto release; } /* we only want to print DIR_ORIGINAL */ if (NF_CT_DIRECTION(hash)) goto release; if (!net_eq(nf_ct_net(ct), net)) goto release; l4proto = nf_ct_l4proto_find(nf_ct_protonum(ct)); ret = -ENOSPC; seq_printf(s, "%-8s %u %-8s %u ", l3proto_name(nf_ct_l3num(ct)), nf_ct_l3num(ct), l4proto_name(l4proto->l4proto), nf_ct_protonum(ct)); if (!test_bit(IPS_OFFLOAD_BIT, &ct->status)) seq_printf(s, "%ld ", nf_ct_expires(ct) / HZ); if (l4proto->print_conntrack) l4proto->print_conntrack(s, ct); print_tuple(s, &ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple, l4proto); ct_show_zone(s, ct, NF_CT_ZONE_DIR_ORIG); if (seq_has_overflowed(s)) goto release; seq_print_acct(s, ct, IP_CT_DIR_ORIGINAL); if (!(test_bit(IPS_SEEN_REPLY_BIT, &ct->status))) seq_puts(s, "[UNREPLIED] "); print_tuple(s, &ct->tuplehash[IP_CT_DIR_REPLY].tuple, l4proto); ct_show_zone(s, ct, NF_CT_ZONE_DIR_REPL); seq_print_acct(s, ct, IP_CT_DIR_REPLY); if (test_bit(IPS_HW_OFFLOAD_BIT, &ct->status)) seq_puts(s, "[HW_OFFLOAD] "); else if (test_bit(IPS_OFFLOAD_BIT, &ct->status)) seq_puts(s, "[OFFLOAD] "); else if (test_bit(IPS_ASSURED_BIT, &ct->status)) seq_puts(s, "[ASSURED] "); if (seq_has_overflowed(s)) goto release; #if defined(CONFIG_NF_CONNTRACK_MARK) seq_printf(s, "mark=%u ", READ_ONCE(ct->mark)); #endif ct_show_secctx(s, ct); ct_show_zone(s, ct, NF_CT_DEFAULT_ZONE_DIR); ct_show_delta_time(s, ct); seq_printf(s, "use=%u\n", refcount_read(&ct->ct_general.use)); if (seq_has_overflowed(s)) goto release; ret = 0; release: nf_ct_put(ct); return ret; } static const struct seq_operations ct_seq_ops = { .start = ct_seq_start, .next = ct_seq_next, .stop = ct_seq_stop, .show = ct_seq_show }; static void *ct_cpu_seq_start(struct seq_file *seq, loff_t *pos) { struct net *net = seq_file_net(seq); int cpu; if (*pos == 0) return SEQ_START_TOKEN; for (cpu = *pos-1; cpu < nr_cpu_ids; ++cpu) { if (!cpu_possible(cpu)) continue; *pos = cpu + 1; return per_cpu_ptr(net->ct.stat, cpu); } return NULL; } static void *ct_cpu_seq_next(struct seq_file *seq, void *v, loff_t *pos) { struct net *net = seq_file_net(seq); int cpu; for (cpu = *pos; cpu < nr_cpu_ids; ++cpu) { if (!cpu_possible(cpu)) continue; *pos = cpu + 1; return per_cpu_ptr(net->ct.stat, cpu); } (*pos)++; return NULL; } static void ct_cpu_seq_stop(struct seq_file *seq, void *v) { } static int ct_cpu_seq_show(struct seq_file *seq, void *v) { struct net *net = seq_file_net(seq); const struct ip_conntrack_stat *st = v; unsigned int nr_conntracks; if (v == SEQ_START_TOKEN) { seq_puts(seq, "entries clashres found new invalid ignore delete chainlength insert insert_failed drop early_drop icmp_error expect_new expect_create expect_delete search_restart\n"); return 0; } nr_conntracks = nf_conntrack_count(net); seq_printf(seq, "%08x %08x %08x %08x %08x %08x %08x %08x " "%08x %08x %08x %08x %08x %08x %08x %08x %08x\n", nr_conntracks, st->clash_resolve, st->found, 0, st->invalid, 0, 0, st->chaintoolong, st->insert, st->insert_failed, st->drop, st->early_drop, st->error, st->expect_new, st->expect_create, st->expect_delete, st->search_restart ); return 0; } static const struct seq_operations ct_cpu_seq_ops = { .start = ct_cpu_seq_start, .next = ct_cpu_seq_next, .stop = ct_cpu_seq_stop, .show = ct_cpu_seq_show, }; static int nf_conntrack_standalone_init_proc(struct net *net) { struct proc_dir_entry *pde; kuid_t root_uid; kgid_t root_gid; pde = proc_create_net("nf_conntrack", 0440, net->proc_net, &ct_seq_ops, sizeof(struct ct_iter_state)); if (!pde) goto out_nf_conntrack; root_uid = make_kuid(net->user_ns, 0); root_gid = make_kgid(net->user_ns, 0); if (uid_valid(root_uid) && gid_valid(root_gid)) proc_set_user(pde, root_uid, root_gid); pde = proc_create_net("nf_conntrack", 0444, net->proc_net_stat, &ct_cpu_seq_ops, sizeof(struct seq_net_private)); if (!pde) goto out_stat_nf_conntrack; return 0; out_stat_nf_conntrack: remove_proc_entry("nf_conntrack", net->proc_net); out_nf_conntrack: return -ENOMEM; } static void nf_conntrack_standalone_fini_proc(struct net *net) { remove_proc_entry("nf_conntrack", net->proc_net_stat); remove_proc_entry("nf_conntrack", net->proc_net); } #else static int nf_conntrack_standalone_init_proc(struct net *net) { return 0; } static void nf_conntrack_standalone_fini_proc(struct net *net) { } #endif /* CONFIG_NF_CONNTRACK_PROCFS */ u32 nf_conntrack_count(const struct net *net) { const struct nf_conntrack_net *cnet = nf_ct_pernet(net); return atomic_read(&cnet->count); } EXPORT_SYMBOL_GPL(nf_conntrack_count); /* Sysctl support */ #ifdef CONFIG_SYSCTL /* size the user *wants to set */ static unsigned int nf_conntrack_htable_size_user __read_mostly; static int nf_conntrack_hash_sysctl(const struct ctl_table *table, int write, void *buffer, size_t *lenp, loff_t *ppos) { int ret; /* module_param hashsize could have changed value */ nf_conntrack_htable_size_user = nf_conntrack_htable_size; ret = proc_dointvec(table, write, buffer, lenp, ppos); if (ret < 0 || !write) return ret; /* update ret, we might not be able to satisfy request */ ret = nf_conntrack_hash_resize(nf_conntrack_htable_size_user); /* update it to the actual value used by conntrack */ nf_conntrack_htable_size_user = nf_conntrack_htable_size; return ret; } static struct ctl_table_header *nf_ct_netfilter_header; enum nf_ct_sysctl_index { NF_SYSCTL_CT_MAX, NF_SYSCTL_CT_COUNT, NF_SYSCTL_CT_BUCKETS, NF_SYSCTL_CT_CHECKSUM, NF_SYSCTL_CT_LOG_INVALID, NF_SYSCTL_CT_EXPECT_MAX, NF_SYSCTL_CT_ACCT, #ifdef CONFIG_NF_CONNTRACK_EVENTS NF_SYSCTL_CT_EVENTS, #endif #ifdef CONFIG_NF_CONNTRACK_TIMESTAMP NF_SYSCTL_CT_TIMESTAMP, #endif NF_SYSCTL_CT_PROTO_TIMEOUT_GENERIC, NF_SYSCTL_CT_PROTO_TIMEOUT_TCP_SYN_SENT, NF_SYSCTL_CT_PROTO_TIMEOUT_TCP_SYN_RECV, NF_SYSCTL_CT_PROTO_TIMEOUT_TCP_ESTABLISHED, NF_SYSCTL_CT_PROTO_TIMEOUT_TCP_FIN_WAIT, NF_SYSCTL_CT_PROTO_TIMEOUT_TCP_CLOSE_WAIT, NF_SYSCTL_CT_PROTO_TIMEOUT_TCP_LAST_ACK, NF_SYSCTL_CT_PROTO_TIMEOUT_TCP_TIME_WAIT, NF_SYSCTL_CT_PROTO_TIMEOUT_TCP_CLOSE, NF_SYSCTL_CT_PROTO_TIMEOUT_TCP_RETRANS, NF_SYSCTL_CT_PROTO_TIMEOUT_TCP_UNACK, #if IS_ENABLED(CONFIG_NF_FLOW_TABLE) NF_SYSCTL_CT_PROTO_TIMEOUT_TCP_OFFLOAD, #endif NF_SYSCTL_CT_PROTO_TCP_LOOSE, NF_SYSCTL_CT_PROTO_TCP_LIBERAL, NF_SYSCTL_CT_PROTO_TCP_IGNORE_INVALID_RST, NF_SYSCTL_CT_PROTO_TCP_MAX_RETRANS, NF_SYSCTL_CT_PROTO_TIMEOUT_UDP, NF_SYSCTL_CT_PROTO_TIMEOUT_UDP_STREAM, #if IS_ENABLED(CONFIG_NF_FLOW_TABLE) NF_SYSCTL_CT_PROTO_TIMEOUT_UDP_OFFLOAD, #endif NF_SYSCTL_CT_PROTO_TIMEOUT_ICMP, NF_SYSCTL_CT_PROTO_TIMEOUT_ICMPV6, #ifdef CONFIG_NF_CT_PROTO_SCTP NF_SYSCTL_CT_PROTO_TIMEOUT_SCTP_CLOSED, NF_SYSCTL_CT_PROTO_TIMEOUT_SCTP_COOKIE_WAIT, NF_SYSCTL_CT_PROTO_TIMEOUT_SCTP_COOKIE_ECHOED, NF_SYSCTL_CT_PROTO_TIMEOUT_SCTP_ESTABLISHED, NF_SYSCTL_CT_PROTO_TIMEOUT_SCTP_SHUTDOWN_SENT, NF_SYSCTL_CT_PROTO_TIMEOUT_SCTP_SHUTDOWN_RECD, NF_SYSCTL_CT_PROTO_TIMEOUT_SCTP_SHUTDOWN_ACK_SENT, NF_SYSCTL_CT_PROTO_TIMEOUT_SCTP_HEARTBEAT_SENT, #endif #ifdef CONFIG_NF_CT_PROTO_DCCP NF_SYSCTL_CT_PROTO_TIMEOUT_DCCP_REQUEST, NF_SYSCTL_CT_PROTO_TIMEOUT_DCCP_RESPOND, NF_SYSCTL_CT_PROTO_TIMEOUT_DCCP_PARTOPEN, NF_SYSCTL_CT_PROTO_TIMEOUT_DCCP_OPEN, NF_SYSCTL_CT_PROTO_TIMEOUT_DCCP_CLOSEREQ, NF_SYSCTL_CT_PROTO_TIMEOUT_DCCP_CLOSING, NF_SYSCTL_CT_PROTO_TIMEOUT_DCCP_TIMEWAIT, NF_SYSCTL_CT_PROTO_DCCP_LOOSE, #endif #ifdef CONFIG_NF_CT_PROTO_GRE NF_SYSCTL_CT_PROTO_TIMEOUT_GRE, NF_SYSCTL_CT_PROTO_TIMEOUT_GRE_STREAM, #endif NF_SYSCTL_CT_LAST_SYSCTL, }; static struct ctl_table nf_ct_sysctl_table[] = { [NF_SYSCTL_CT_MAX] = { .procname = "nf_conntrack_max", .data = &nf_conntrack_max, .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec, }, [NF_SYSCTL_CT_COUNT] = { .procname = "nf_conntrack_count", .maxlen = sizeof(int), .mode = 0444, .proc_handler = proc_dointvec, }, [NF_SYSCTL_CT_BUCKETS] = { .procname = "nf_conntrack_buckets", .data = &nf_conntrack_htable_size_user, .maxlen = sizeof(unsigned int), .mode = 0644, .proc_handler = nf_conntrack_hash_sysctl, }, [NF_SYSCTL_CT_CHECKSUM] = { .procname = "nf_conntrack_checksum", .data = &init_net.ct.sysctl_checksum, .maxlen = sizeof(u8), .mode = 0644, .proc_handler = proc_dou8vec_minmax, .extra1 = SYSCTL_ZERO, .extra2 = SYSCTL_ONE, }, [NF_SYSCTL_CT_LOG_INVALID] = { .procname = "nf_conntrack_log_invalid", .data = &init_net.ct.sysctl_log_invalid, .maxlen = sizeof(u8), .mode = 0644, .proc_handler = proc_dou8vec_minmax, }, [NF_SYSCTL_CT_EXPECT_MAX] = { .procname = "nf_conntrack_expect_max", .data = &nf_ct_expect_max, .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec, }, [NF_SYSCTL_CT_ACCT] = { .procname = "nf_conntrack_acct", .data = &init_net.ct.sysctl_acct, .maxlen = sizeof(u8), .mode = 0644, .proc_handler = proc_dou8vec_minmax, .extra1 = SYSCTL_ZERO, .extra2 = SYSCTL_ONE, }, #ifdef CONFIG_NF_CONNTRACK_EVENTS [NF_SYSCTL_CT_EVENTS] = { .procname = "nf_conntrack_events", .data = &init_net.ct.sysctl_events, .maxlen = sizeof(u8), .mode = 0644, .proc_handler = proc_dou8vec_minmax, .extra1 = SYSCTL_ZERO, .extra2 = SYSCTL_TWO, }, #endif #ifdef CONFIG_NF_CONNTRACK_TIMESTAMP [NF_SYSCTL_CT_TIMESTAMP] = { .procname = "nf_conntrack_timestamp", .data = &init_net.ct.sysctl_tstamp, .maxlen = sizeof(u8), .mode = 0644, .proc_handler = proc_dou8vec_minmax, .extra1 = SYSCTL_ZERO, .extra2 = SYSCTL_ONE, }, #endif [NF_SYSCTL_CT_PROTO_TIMEOUT_GENERIC] = { .procname = "nf_conntrack_generic_timeout", .maxlen = sizeof(unsigned int), .mode = 0644, .proc_handler = proc_dointvec_jiffies, }, [NF_SYSCTL_CT_PROTO_TIMEOUT_TCP_SYN_SENT] = { .procname = "nf_conntrack_tcp_timeout_syn_sent", .maxlen = sizeof(unsigned int), .mode = 0644, .proc_handler = proc_dointvec_jiffies, }, [NF_SYSCTL_CT_PROTO_TIMEOUT_TCP_SYN_RECV] = { .procname = "nf_conntrack_tcp_timeout_syn_recv", .maxlen = sizeof(unsigned int), .mode = 0644, .proc_handler = proc_dointvec_jiffies, }, [NF_SYSCTL_CT_PROTO_TIMEOUT_TCP_ESTABLISHED] = { .procname = "nf_conntrack_tcp_timeout_established", .maxlen = sizeof(unsigned int), .mode = 0644, .proc_handler = proc_dointvec_jiffies, }, [NF_SYSCTL_CT_PROTO_TIMEOUT_TCP_FIN_WAIT] = { .procname = "nf_conntrack_tcp_timeout_fin_wait", .maxlen = sizeof(unsigned int), .mode = 0644, .proc_handler = proc_dointvec_jiffies, }, [NF_SYSCTL_CT_PROTO_TIMEOUT_TCP_CLOSE_WAIT] = { .procname = "nf_conntrack_tcp_timeout_close_wait", .maxlen = sizeof(unsigned int), .mode = 0644, .proc_handler = proc_dointvec_jiffies, }, [NF_SYSCTL_CT_PROTO_TIMEOUT_TCP_LAST_ACK] = { .procname = "nf_conntrack_tcp_timeout_last_ack", .maxlen = sizeof(unsigned int), .mode = 0644, .proc_handler = proc_dointvec_jiffies, }, [NF_SYSCTL_CT_PROTO_TIMEOUT_TCP_TIME_WAIT] = { .procname = "nf_conntrack_tcp_timeout_time_wait", .maxlen = sizeof(unsigned int), .mode = 0644, .proc_handler = proc_dointvec_jiffies, }, [NF_SYSCTL_CT_PROTO_TIMEOUT_TCP_CLOSE] = { .procname = "nf_conntrack_tcp_timeout_close", .maxlen = sizeof(unsigned int), .mode = 0644, .proc_handler = proc_dointvec_jiffies, }, [NF_SYSCTL_CT_PROTO_TIMEOUT_TCP_RETRANS] = { .procname = "nf_conntrack_tcp_timeout_max_retrans", .maxlen = sizeof(unsigned int), .mode = 0644, .proc_handler = proc_dointvec_jiffies, }, [NF_SYSCTL_CT_PROTO_TIMEOUT_TCP_UNACK] = { .procname = "nf_conntrack_tcp_timeout_unacknowledged", .maxlen = sizeof(unsigned int), .mode = 0644, .proc_handler = proc_dointvec_jiffies, }, #if IS_ENABLED(CONFIG_NF_FLOW_TABLE) [NF_SYSCTL_CT_PROTO_TIMEOUT_TCP_OFFLOAD] = { .procname = "nf_flowtable_tcp_timeout", .maxlen = sizeof(unsigned int), .mode = 0644, .proc_handler = proc_dointvec_jiffies, }, #endif [NF_SYSCTL_CT_PROTO_TCP_LOOSE] = { .procname = "nf_conntrack_tcp_loose", .maxlen = sizeof(u8), .mode = 0644, .proc_handler = proc_dou8vec_minmax, .extra1 = SYSCTL_ZERO, .extra2 = SYSCTL_ONE, }, [NF_SYSCTL_CT_PROTO_TCP_LIBERAL] = { .procname = "nf_conntrack_tcp_be_liberal", .maxlen = sizeof(u8), .mode = 0644, .proc_handler = proc_dou8vec_minmax, .extra1 = SYSCTL_ZERO, .extra2 = SYSCTL_ONE, }, [NF_SYSCTL_CT_PROTO_TCP_IGNORE_INVALID_RST] = { .procname = "nf_conntrack_tcp_ignore_invalid_rst", .maxlen = sizeof(u8), .mode = 0644, .proc_handler = proc_dou8vec_minmax, .extra1 = SYSCTL_ZERO, .extra2 = SYSCTL_ONE, }, [NF_SYSCTL_CT_PROTO_TCP_MAX_RETRANS] = { .procname = "nf_conntrack_tcp_max_retrans", .maxlen = sizeof(u8), .mode = 0644, .proc_handler = proc_dou8vec_minmax, }, [NF_SYSCTL_CT_PROTO_TIMEOUT_UDP] = { .procname = "nf_conntrack_udp_timeout", .maxlen = sizeof(unsigned int), .mode = 0644, .proc_handler = proc_dointvec_jiffies, }, [NF_SYSCTL_CT_PROTO_TIMEOUT_UDP_STREAM] = { .procname = "nf_conntrack_udp_timeout_stream", .maxlen = sizeof(unsigned int), .mode = 0644, .proc_handler = proc_dointvec_jiffies, }, #if IS_ENABLED(CONFIG_NF_FLOW_TABLE) [NF_SYSCTL_CT_PROTO_TIMEOUT_UDP_OFFLOAD] = { .procname = "nf_flowtable_udp_timeout", .maxlen = sizeof(unsigned int), .mode = 0644, .proc_handler = proc_dointvec_jiffies, }, #endif [NF_SYSCTL_CT_PROTO_TIMEOUT_ICMP] = { .procname = "nf_conntrack_icmp_timeout", .maxlen = sizeof(unsigned int), .mode = 0644, .proc_handler = proc_dointvec_jiffies, }, [NF_SYSCTL_CT_PROTO_TIMEOUT_ICMPV6] = { .procname = "nf_conntrack_icmpv6_timeout", .maxlen = sizeof(unsigned int), .mode = 0644, .proc_handler = proc_dointvec_jiffies, }, #ifdef CONFIG_NF_CT_PROTO_SCTP [NF_SYSCTL_CT_PROTO_TIMEOUT_SCTP_CLOSED] = { .procname = "nf_conntrack_sctp_timeout_closed", .maxlen = sizeof(unsigned int), .mode = 0644, .proc_handler = proc_dointvec_jiffies, }, [NF_SYSCTL_CT_PROTO_TIMEOUT_SCTP_COOKIE_WAIT] = { .procname = "nf_conntrack_sctp_timeout_cookie_wait", .maxlen = sizeof(unsigned int), .mode = 0644, .proc_handler = proc_dointvec_jiffies, }, [NF_SYSCTL_CT_PROTO_TIMEOUT_SCTP_COOKIE_ECHOED] = { .procname = "nf_conntrack_sctp_timeout_cookie_echoed", .maxlen = sizeof(unsigned int), .mode = 0644, .proc_handler = proc_dointvec_jiffies, }, [NF_SYSCTL_CT_PROTO_TIMEOUT_SCTP_ESTABLISHED] = { .procname = "nf_conntrack_sctp_timeout_established", .maxlen = sizeof(unsigned int), .mode = 0644, .proc_handler = proc_dointvec_jiffies, }, [NF_SYSCTL_CT_PROTO_TIMEOUT_SCTP_SHUTDOWN_SENT] = { .procname = "nf_conntrack_sctp_timeout_shutdown_sent", .maxlen = sizeof(unsigned int), .mode = 0644, .proc_handler = proc_dointvec_jiffies, }, [NF_SYSCTL_CT_PROTO_TIMEOUT_SCTP_SHUTDOWN_RECD] = { .procname = "nf_conntrack_sctp_timeout_shutdown_recd", .maxlen = sizeof(unsigned int), .mode = 0644, .proc_handler = proc_dointvec_jiffies, }, [NF_SYSCTL_CT_PROTO_TIMEOUT_SCTP_SHUTDOWN_ACK_SENT] = { .procname = "nf_conntrack_sctp_timeout_shutdown_ack_sent", .maxlen = sizeof(unsigned int), .mode = 0644, .proc_handler = proc_dointvec_jiffies, }, [NF_SYSCTL_CT_PROTO_TIMEOUT_SCTP_HEARTBEAT_SENT] = { .procname = "nf_conntrack_sctp_timeout_heartbeat_sent", .maxlen = sizeof(unsigned int), .mode = 0644, .proc_handler = proc_dointvec_jiffies, }, #endif #ifdef CONFIG_NF_CT_PROTO_DCCP [NF_SYSCTL_CT_PROTO_TIMEOUT_DCCP_REQUEST] = { .procname = "nf_conntrack_dccp_timeout_request", .maxlen = sizeof(unsigned int), .mode = 0644, .proc_handler = proc_dointvec_jiffies, }, [NF_SYSCTL_CT_PROTO_TIMEOUT_DCCP_RESPOND] = { .procname = "nf_conntrack_dccp_timeout_respond", .maxlen = sizeof(unsigned int), .mode = 0644, .proc_handler = proc_dointvec_jiffies, }, [NF_SYSCTL_CT_PROTO_TIMEOUT_DCCP_PARTOPEN] = { .procname = "nf_conntrack_dccp_timeout_partopen", .maxlen = sizeof(unsigned int), .mode = 0644, .proc_handler = proc_dointvec_jiffies, }, [NF_SYSCTL_CT_PROTO_TIMEOUT_DCCP_OPEN] = { .procname = "nf_conntrack_dccp_timeout_open", .maxlen = sizeof(unsigned int), .mode = 0644, .proc_handler = proc_dointvec_jiffies, }, [NF_SYSCTL_CT_PROTO_TIMEOUT_DCCP_CLOSEREQ] = { .procname = "nf_conntrack_dccp_timeout_closereq", .maxlen = sizeof(unsigned int), .mode = 0644, .proc_handler = proc_dointvec_jiffies, }, [NF_SYSCTL_CT_PROTO_TIMEOUT_DCCP_CLOSING] = { .procname = "nf_conntrack_dccp_timeout_closing", .maxlen = sizeof(unsigned int), .mode = 0644, .proc_handler = proc_dointvec_jiffies, }, [NF_SYSCTL_CT_PROTO_TIMEOUT_DCCP_TIMEWAIT] = { .procname = "nf_conntrack_dccp_timeout_timewait", .maxlen = sizeof(unsigned int), .mode = 0644, .proc_handler = proc_dointvec_jiffies, }, [NF_SYSCTL_CT_PROTO_DCCP_LOOSE] = { .procname = "nf_conntrack_dccp_loose", .maxlen = sizeof(u8), .mode = 0644, .proc_handler = proc_dou8vec_minmax, .extra1 = SYSCTL_ZERO, .extra2 = SYSCTL_ONE, }, #endif #ifdef CONFIG_NF_CT_PROTO_GRE [NF_SYSCTL_CT_PROTO_TIMEOUT_GRE] = { .procname = "nf_conntrack_gre_timeout", .maxlen = sizeof(unsigned int), .mode = 0644, .proc_handler = proc_dointvec_jiffies, }, [NF_SYSCTL_CT_PROTO_TIMEOUT_GRE_STREAM] = { .procname = "nf_conntrack_gre_timeout_stream", .maxlen = sizeof(unsigned int), .mode = 0644, .proc_handler = proc_dointvec_jiffies, }, #endif }; static struct ctl_table nf_ct_netfilter_table[] = { { .procname = "nf_conntrack_max", .data = &nf_conntrack_max, .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec, }, }; static void nf_conntrack_standalone_init_tcp_sysctl(struct net *net, struct ctl_table *table) { struct nf_tcp_net *tn = nf_tcp_pernet(net); #define XASSIGN(XNAME, tn) \ table[NF_SYSCTL_CT_PROTO_TIMEOUT_TCP_ ## XNAME].data = \ &(tn)->timeouts[TCP_CONNTRACK_ ## XNAME] XASSIGN(SYN_SENT, tn); XASSIGN(SYN_RECV, tn); XASSIGN(ESTABLISHED, tn); XASSIGN(FIN_WAIT, tn); XASSIGN(CLOSE_WAIT, tn); XASSIGN(LAST_ACK, tn); XASSIGN(TIME_WAIT, tn); XASSIGN(CLOSE, tn); XASSIGN(RETRANS, tn); XASSIGN(UNACK, tn); #undef XASSIGN #define XASSIGN(XNAME, rval) \ table[NF_SYSCTL_CT_PROTO_TCP_ ## XNAME].data = (rval) XASSIGN(LOOSE, &tn->tcp_loose); XASSIGN(LIBERAL, &tn->tcp_be_liberal); XASSIGN(MAX_RETRANS, &tn->tcp_max_retrans); XASSIGN(IGNORE_INVALID_RST, &tn->tcp_ignore_invalid_rst); #undef XASSIGN #if IS_ENABLED(CONFIG_NF_FLOW_TABLE) table[NF_SYSCTL_CT_PROTO_TIMEOUT_TCP_OFFLOAD].data = &tn->offload_timeout; #endif } static void nf_conntrack_standalone_init_sctp_sysctl(struct net *net, struct ctl_table *table) { #ifdef CONFIG_NF_CT_PROTO_SCTP struct nf_sctp_net *sn = nf_sctp_pernet(net); #define XASSIGN(XNAME, sn) \ table[NF_SYSCTL_CT_PROTO_TIMEOUT_SCTP_ ## XNAME].data = \ &(sn)->timeouts[SCTP_CONNTRACK_ ## XNAME] XASSIGN(CLOSED, sn); XASSIGN(COOKIE_WAIT, sn); XASSIGN(COOKIE_ECHOED, sn); XASSIGN(ESTABLISHED, sn); XASSIGN(SHUTDOWN_SENT, sn); XASSIGN(SHUTDOWN_RECD, sn); XASSIGN(SHUTDOWN_ACK_SENT, sn); XASSIGN(HEARTBEAT_SENT, sn); #undef XASSIGN #endif } static void nf_conntrack_standalone_init_dccp_sysctl(struct net *net, struct ctl_table *table) { #ifdef CONFIG_NF_CT_PROTO_DCCP struct nf_dccp_net *dn = nf_dccp_pernet(net); #define XASSIGN(XNAME, dn) \ table[NF_SYSCTL_CT_PROTO_TIMEOUT_DCCP_ ## XNAME].data = \ &(dn)->dccp_timeout[CT_DCCP_ ## XNAME] XASSIGN(REQUEST, dn); XASSIGN(RESPOND, dn); XASSIGN(PARTOPEN, dn); XASSIGN(OPEN, dn); XASSIGN(CLOSEREQ, dn); XASSIGN(CLOSING, dn); XASSIGN(TIMEWAIT, dn); #undef XASSIGN table[NF_SYSCTL_CT_PROTO_DCCP_LOOSE].data = &dn->dccp_loose; #endif } static void nf_conntrack_standalone_init_gre_sysctl(struct net *net, struct ctl_table *table) { #ifdef CONFIG_NF_CT_PROTO_GRE struct nf_gre_net *gn = nf_gre_pernet(net); table[NF_SYSCTL_CT_PROTO_TIMEOUT_GRE].data = &gn->timeouts[GRE_CT_UNREPLIED]; table[NF_SYSCTL_CT_PROTO_TIMEOUT_GRE_STREAM].data = &gn->timeouts[GRE_CT_REPLIED]; #endif } static int nf_conntrack_standalone_init_sysctl(struct net *net) { struct nf_conntrack_net *cnet = nf_ct_pernet(net); struct nf_udp_net *un = nf_udp_pernet(net); struct ctl_table *table; BUILD_BUG_ON(ARRAY_SIZE(nf_ct_sysctl_table) != NF_SYSCTL_CT_LAST_SYSCTL); table = kmemdup(nf_ct_sysctl_table, sizeof(nf_ct_sysctl_table), GFP_KERNEL); if (!table) return -ENOMEM; table[NF_SYSCTL_CT_COUNT].data = &cnet->count; table[NF_SYSCTL_CT_CHECKSUM].data = &net->ct.sysctl_checksum; table[NF_SYSCTL_CT_LOG_INVALID].data = &net->ct.sysctl_log_invalid; table[NF_SYSCTL_CT_ACCT].data = &net->ct.sysctl_acct; #ifdef CONFIG_NF_CONNTRACK_EVENTS table[NF_SYSCTL_CT_EVENTS].data = &net->ct.sysctl_events; #endif #ifdef CONFIG_NF_CONNTRACK_TIMESTAMP table[NF_SYSCTL_CT_TIMESTAMP].data = &net->ct.sysctl_tstamp; #endif table[NF_SYSCTL_CT_PROTO_TIMEOUT_GENERIC].data = &nf_generic_pernet(net)->timeout; table[NF_SYSCTL_CT_PROTO_TIMEOUT_ICMP].data = &nf_icmp_pernet(net)->timeout; table[NF_SYSCTL_CT_PROTO_TIMEOUT_ICMPV6].data = &nf_icmpv6_pernet(net)->timeout; table[NF_SYSCTL_CT_PROTO_TIMEOUT_UDP].data = &un->timeouts[UDP_CT_UNREPLIED]; table[NF_SYSCTL_CT_PROTO_TIMEOUT_UDP_STREAM].data = &un->timeouts[UDP_CT_REPLIED]; #if IS_ENABLED(CONFIG_NF_FLOW_TABLE) table[NF_SYSCTL_CT_PROTO_TIMEOUT_UDP_OFFLOAD].data = &un->offload_timeout; #endif nf_conntrack_standalone_init_tcp_sysctl(net, table); nf_conntrack_standalone_init_sctp_sysctl(net, table); nf_conntrack_standalone_init_dccp_sysctl(net, table); nf_conntrack_standalone_init_gre_sysctl(net, table); /* Don't allow non-init_net ns to alter global sysctls */ if (!net_eq(&init_net, net)) { table[NF_SYSCTL_CT_MAX].mode = 0444; table[NF_SYSCTL_CT_EXPECT_MAX].mode = 0444; table[NF_SYSCTL_CT_BUCKETS].mode = 0444; } cnet->sysctl_header = register_net_sysctl_sz(net, "net/netfilter", table, ARRAY_SIZE(nf_ct_sysctl_table)); if (!cnet->sysctl_header) goto out_unregister_netfilter; return 0; out_unregister_netfilter: kfree(table); return -ENOMEM; } static void nf_conntrack_standalone_fini_sysctl(struct net *net) { struct nf_conntrack_net *cnet = nf_ct_pernet(net); const struct ctl_table *table; table = cnet->sysctl_header->ctl_table_arg; unregister_net_sysctl_table(cnet->sysctl_header); kfree(table); } #else static int nf_conntrack_standalone_init_sysctl(struct net *net) { return 0; } static void nf_conntrack_standalone_fini_sysctl(struct net *net) { } #endif /* CONFIG_SYSCTL */ static void nf_conntrack_fini_net(struct net *net) { if (enable_hooks) nf_ct_netns_put(net, NFPROTO_INET); nf_conntrack_standalone_fini_proc(net); nf_conntrack_standalone_fini_sysctl(net); } static int nf_conntrack_pernet_init(struct net *net) { int ret; net->ct.sysctl_checksum = 1; ret = nf_conntrack_standalone_init_sysctl(net); if (ret < 0) return ret; ret = nf_conntrack_standalone_init_proc(net); if (ret < 0) goto out_proc; ret = nf_conntrack_init_net(net); if (ret < 0) goto out_init_net; if (enable_hooks) { ret = nf_ct_netns_get(net, NFPROTO_INET); if (ret < 0) goto out_hooks; } return 0; out_hooks: nf_conntrack_cleanup_net(net); out_init_net: nf_conntrack_standalone_fini_proc(net); out_proc: nf_conntrack_standalone_fini_sysctl(net); return ret; } static void nf_conntrack_pernet_exit(struct list_head *net_exit_list) { struct net *net; list_for_each_entry(net, net_exit_list, exit_list) nf_conntrack_fini_net(net); nf_conntrack_cleanup_net_list(net_exit_list); } static struct pernet_operations nf_conntrack_net_ops = { .init = nf_conntrack_pernet_init, .exit_batch = nf_conntrack_pernet_exit, .id = &nf_conntrack_net_id, .size = sizeof(struct nf_conntrack_net), }; static int __init nf_conntrack_standalone_init(void) { int ret = nf_conntrack_init_start(); if (ret < 0) goto out_start; BUILD_BUG_ON(NFCT_INFOMASK <= IP_CT_NUMBER); #ifdef CONFIG_SYSCTL nf_ct_netfilter_header = register_net_sysctl(&init_net, "net", nf_ct_netfilter_table); if (!nf_ct_netfilter_header) { pr_err("nf_conntrack: can't register to sysctl.\n"); ret = -ENOMEM; goto out_sysctl; } nf_conntrack_htable_size_user = nf_conntrack_htable_size; #endif nf_conntrack_init_end(); ret = register_pernet_subsys(&nf_conntrack_net_ops); if (ret < 0) goto out_pernet; return 0; out_pernet: #ifdef CONFIG_SYSCTL unregister_net_sysctl_table(nf_ct_netfilter_header); out_sysctl: #endif nf_conntrack_cleanup_end(); out_start: return ret; } static void __exit nf_conntrack_standalone_fini(void) { nf_conntrack_cleanup_start(); unregister_pernet_subsys(&nf_conntrack_net_ops); #ifdef CONFIG_SYSCTL unregister_net_sysctl_table(nf_ct_netfilter_header); #endif nf_conntrack_cleanup_end(); } module_init(nf_conntrack_standalone_init); module_exit(nf_conntrack_standalone_fini); |
| 326 | 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 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _linux_POSIX_TIMERS_H #define _linux_POSIX_TIMERS_H #include <linux/alarmtimer.h> #include <linux/list.h> #include <linux/mutex.h> #include <linux/pid.h> #include <linux/posix-timers_types.h> #include <linux/rcuref.h> #include <linux/spinlock.h> #include <linux/timerqueue.h> struct kernel_siginfo; struct task_struct; struct sigqueue; struct k_itimer; static inline clockid_t make_process_cpuclock(const unsigned int pid, const clockid_t clock) { return ((~pid) << 3) | clock; } static inline clockid_t make_thread_cpuclock(const unsigned int tid, const clockid_t clock) { return make_process_cpuclock(tid, clock | CPUCLOCK_PERTHREAD_MASK); } static inline clockid_t fd_to_clockid(const int fd) { return make_process_cpuclock((unsigned int) fd, CLOCKFD); } static inline int clockid_to_fd(const clockid_t clk) { return ~(clk >> 3); } #ifdef CONFIG_POSIX_TIMERS #include <linux/signal_types.h> /** * cpu_timer - Posix CPU timer representation for k_itimer * @node: timerqueue node to queue in the task/sig * @head: timerqueue head on which this timer is queued * @pid: Pointer to target task PID * @elist: List head for the expiry list * @firing: Timer is currently firing * @nanosleep: Timer is used for nanosleep and is not a regular posix-timer * @handling: Pointer to the task which handles expiry */ struct cpu_timer { struct timerqueue_node node; struct timerqueue_head *head; struct pid *pid; struct list_head elist; bool firing; bool nanosleep; struct task_struct __rcu *handling; }; static inline bool cpu_timer_enqueue(struct timerqueue_head *head, struct cpu_timer *ctmr) { ctmr->head = head; return timerqueue_add(head, &ctmr->node); } static inline bool cpu_timer_queued(struct cpu_timer *ctmr) { return !!ctmr->head; } static inline bool cpu_timer_dequeue(struct cpu_timer *ctmr) { if (cpu_timer_queued(ctmr)) { timerqueue_del(ctmr->head, &ctmr->node); ctmr->head = NULL; return true; } return false; } static inline u64 cpu_timer_getexpires(struct cpu_timer *ctmr) { return ctmr->node.expires; } static inline void cpu_timer_setexpires(struct cpu_timer *ctmr, u64 exp) { ctmr->node.expires = exp; } static inline void posix_cputimers_init(struct posix_cputimers *pct) { memset(pct, 0, sizeof(*pct)); pct->bases[0].nextevt = U64_MAX; pct->bases[1].nextevt = U64_MAX; pct->bases[2].nextevt = U64_MAX; } void posix_cputimers_group_init(struct posix_cputimers *pct, u64 cpu_limit); static inline void posix_cputimers_rt_watchdog(struct posix_cputimers *pct, u64 runtime) { pct->bases[CPUCLOCK_SCHED].nextevt = runtime; } void posixtimer_rearm_itimer(struct task_struct *p); bool posixtimer_init_sigqueue(struct sigqueue *q); void posixtimer_send_sigqueue(struct k_itimer *tmr); bool posixtimer_deliver_signal(struct kernel_siginfo *info, struct sigqueue *timer_sigq); void posixtimer_free_timer(struct k_itimer *timer); /* Init task static initializer */ #define INIT_CPU_TIMERBASE(b) { \ .nextevt = U64_MAX, \ } #define INIT_CPU_TIMERBASES(b) { \ INIT_CPU_TIMERBASE(b[0]), \ INIT_CPU_TIMERBASE(b[1]), \ INIT_CPU_TIMERBASE(b[2]), \ } #define INIT_CPU_TIMERS(s) \ .posix_cputimers = { \ .bases = INIT_CPU_TIMERBASES(s.posix_cputimers.bases), \ }, #else struct cpu_timer { }; #define INIT_CPU_TIMERS(s) static inline void posix_cputimers_init(struct posix_cputimers *pct) { } static inline void posix_cputimers_group_init(struct posix_cputimers *pct, u64 cpu_limit) { } static inline void posixtimer_rearm_itimer(struct task_struct *p) { } static inline bool posixtimer_deliver_signal(struct kernel_siginfo *info, struct sigqueue *timer_sigq) { return false; } static inline void posixtimer_free_timer(struct k_itimer *timer) { } #endif #ifdef CONFIG_POSIX_CPU_TIMERS_TASK_WORK void clear_posix_cputimers_work(struct task_struct *p); void posix_cputimers_init_work(void); #else static inline void clear_posix_cputimers_work(struct task_struct *p) { } static inline void posix_cputimers_init_work(void) { } #endif /** * struct k_itimer - POSIX.1b interval timer structure. * @list: List node for binding the timer to tsk::signal::posix_timers * @ignored_list: List node for tracking ignored timers in tsk::signal::ignored_posix_timers * @t_hash: Entry in the posix timer hash table * @it_lock: Lock protecting the timer * @kclock: Pointer to the k_clock struct handling this timer * @it_clock: The posix timer clock id * @it_id: The posix timer id for identifying the timer * @it_status: The status of the timer * @it_sig_periodic: The periodic status at signal delivery * @it_overrun: The overrun counter for pending signals * @it_overrun_last: The overrun at the time of the last delivered signal * @it_signal_seq: Sequence count to control signal delivery * @it_sigqueue_seq: The sequence count at the point where the signal was queued * @it_sigev_notify: The notify word of sigevent struct for signal delivery * @it_interval: The interval for periodic timers * @it_signal: Pointer to the creators signal struct * @it_pid: The pid of the process/task targeted by the signal * @it_process: The task to wakeup on clock_nanosleep (CPU timers) * @rcuref: Reference count for life time management * @sigq: Embedded sigqueue * @it: Union representing the various posix timer type * internals. * @rcu: RCU head for freeing the timer. */ struct k_itimer { struct hlist_node list; struct hlist_node ignored_list; struct hlist_node t_hash; spinlock_t it_lock; const struct k_clock *kclock; clockid_t it_clock; timer_t it_id; int it_status; bool it_sig_periodic; s64 it_overrun; s64 it_overrun_last; unsigned int it_signal_seq; unsigned int it_sigqueue_seq; int it_sigev_notify; enum pid_type it_pid_type; ktime_t it_interval; struct signal_struct *it_signal; union { struct pid *it_pid; struct task_struct *it_process; }; struct sigqueue sigq; rcuref_t rcuref; union { struct { struct hrtimer timer; } real; struct cpu_timer cpu; struct { struct alarm alarmtimer; } alarm; } it; struct rcu_head rcu; }; void run_posix_cpu_timers(void); void posix_cpu_timers_exit(struct task_struct *task); void posix_cpu_timers_exit_group(struct task_struct *task); void set_process_cpu_timer(struct task_struct *task, unsigned int clock_idx, u64 *newval, u64 *oldval); int update_rlimit_cpu(struct task_struct *task, unsigned long rlim_new); #ifdef CONFIG_POSIX_TIMERS static inline void posixtimer_putref(struct k_itimer *tmr) { if (rcuref_put(&tmr->rcuref)) posixtimer_free_timer(tmr); } static inline void posixtimer_sigqueue_getref(struct sigqueue *q) { struct k_itimer *tmr = container_of(q, struct k_itimer, sigq); WARN_ON_ONCE(!rcuref_get(&tmr->rcuref)); } static inline void posixtimer_sigqueue_putref(struct sigqueue *q) { struct k_itimer *tmr = container_of(q, struct k_itimer, sigq); posixtimer_putref(tmr); } #else /* CONFIG_POSIX_TIMERS */ static inline void posixtimer_sigqueue_getref(struct sigqueue *q) { } static inline void posixtimer_sigqueue_putref(struct sigqueue *q) { } #endif /* !CONFIG_POSIX_TIMERS */ #endif |
| 58 | 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 | // SPDX-License-Identifier: GPL-2.0-only /* * Common code for control of lockd and nfsv4 grace periods. * * Transplanted from lockd code */ #include <linux/module.h> #include <net/net_namespace.h> #include <net/netns/generic.h> #include <linux/fs.h> #include <linux/filelock.h> static unsigned int grace_net_id; static DEFINE_SPINLOCK(grace_lock); /** * locks_start_grace * @net: net namespace that this lock manager belongs to * @lm: who this grace period is for * * A grace period is a period during which locks should not be given * out. Currently grace periods are only enforced by the two lock * managers (lockd and nfsd), using the locks_in_grace() function to * check when they are in a grace period. * * This function is called to start a grace period. */ void locks_start_grace(struct net *net, struct lock_manager *lm) { struct list_head *grace_list = net_generic(net, grace_net_id); spin_lock(&grace_lock); if (list_empty(&lm->list)) list_add(&lm->list, grace_list); else WARN(1, "double list_add attempt detected in net %x %s\n", net->ns.inum, (net == &init_net) ? "(init_net)" : ""); spin_unlock(&grace_lock); } EXPORT_SYMBOL_GPL(locks_start_grace); /** * locks_end_grace * @lm: who this grace period is for * * Call this function to state that the given lock manager is ready to * resume regular locking. The grace period will not end until all lock * managers that called locks_start_grace() also call locks_end_grace(). * Note that callers count on it being safe to call this more than once, * and the second call should be a no-op. */ void locks_end_grace(struct lock_manager *lm) { spin_lock(&grace_lock); list_del_init(&lm->list); spin_unlock(&grace_lock); } EXPORT_SYMBOL_GPL(locks_end_grace); static bool __state_in_grace(struct net *net, bool open) { struct list_head *grace_list = net_generic(net, grace_net_id); struct lock_manager *lm; if (!open) return !list_empty(grace_list); spin_lock(&grace_lock); list_for_each_entry(lm, grace_list, list) { if (lm->block_opens) { spin_unlock(&grace_lock); return true; } } spin_unlock(&grace_lock); return false; } /** * locks_in_grace * @net: network namespace * * Lock managers call this function to determine when it is OK for them * to answer ordinary lock requests, and when they should accept only * lock reclaims. */ bool locks_in_grace(struct net *net) { return __state_in_grace(net, false); } EXPORT_SYMBOL_GPL(locks_in_grace); bool opens_in_grace(struct net *net) { return __state_in_grace(net, true); } EXPORT_SYMBOL_GPL(opens_in_grace); static int __net_init grace_init_net(struct net *net) { struct list_head *grace_list = net_generic(net, grace_net_id); INIT_LIST_HEAD(grace_list); return 0; } static void __net_exit grace_exit_net(struct net *net) { struct list_head *grace_list = net_generic(net, grace_net_id); WARN_ONCE(!list_empty(grace_list), "net %x %s: grace_list is not empty\n", net->ns.inum, __func__); } static struct pernet_operations grace_net_ops = { .init = grace_init_net, .exit = grace_exit_net, .id = &grace_net_id, .size = sizeof(struct list_head), }; static int __init init_grace(void) { return register_pernet_subsys(&grace_net_ops); } static void __exit exit_grace(void) { unregister_pernet_subsys(&grace_net_ops); } MODULE_AUTHOR("Jeff Layton <jlayton@primarydata.com>"); MODULE_DESCRIPTION("NFS client and server infrastructure"); MODULE_LICENSE("GPL"); module_init(init_grace) module_exit(exit_grace) |
| 2692 3606 21 1433 8444 8444 477 484 4698 55 327 327 3525 3518 24 24 | 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 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _ASM_X86_PGTABLE_H #define _ASM_X86_PGTABLE_H #include <linux/mem_encrypt.h> #include <asm/page.h> #include <asm/pgtable_types.h> /* * Macro to mark a page protection value as UC- */ #define pgprot_noncached(prot) \ ((boot_cpu_data.x86 > 3) \ ? (__pgprot(pgprot_val(prot) | \ cachemode2protval(_PAGE_CACHE_MODE_UC_MINUS))) \ : (prot)) #ifndef __ASSEMBLY__ #include <linux/spinlock.h> #include <asm/x86_init.h> #include <asm/pkru.h> #include <asm/fpu/api.h> #include <asm/coco.h> #include <asm-generic/pgtable_uffd.h> #include <linux/page_table_check.h> extern pgd_t early_top_pgt[PTRS_PER_PGD]; bool __init __early_make_pgtable(unsigned long address, pmdval_t pmd); struct seq_file; void ptdump_walk_pgd_level(struct seq_file *m, struct mm_struct *mm); void ptdump_walk_pgd_level_debugfs(struct seq_file *m, struct mm_struct *mm, bool user); bool ptdump_walk_pgd_level_checkwx(void); #define ptdump_check_wx ptdump_walk_pgd_level_checkwx void ptdump_walk_user_pgd_level_checkwx(void); /* * Macros to add or remove encryption attribute */ #define pgprot_encrypted(prot) __pgprot(cc_mkenc(pgprot_val(prot))) #define pgprot_decrypted(prot) __pgprot(cc_mkdec(pgprot_val(prot))) #ifdef CONFIG_DEBUG_WX #define debug_checkwx_user() ptdump_walk_user_pgd_level_checkwx() #else #define debug_checkwx_user() do { } while (0) #endif /* * ZERO_PAGE is a global shared page that is always zero: used * for zero-mapped memory areas etc.. */ extern unsigned long empty_zero_page[PAGE_SIZE / sizeof(unsigned long)] __visible; #define ZERO_PAGE(vaddr) ((void)(vaddr),virt_to_page(empty_zero_page)) extern spinlock_t pgd_lock; extern struct list_head pgd_list; extern struct mm_struct *pgd_page_get_mm(struct page *page); extern pmdval_t early_pmd_flags; #ifdef CONFIG_PARAVIRT_XXL #include <asm/paravirt.h> #else /* !CONFIG_PARAVIRT_XXL */ #define set_pte(ptep, pte) native_set_pte(ptep, pte) #define set_pte_atomic(ptep, pte) \ native_set_pte_atomic(ptep, pte) #define set_pmd(pmdp, pmd) native_set_pmd(pmdp, pmd) #ifndef __PAGETABLE_P4D_FOLDED #define set_pgd(pgdp, pgd) native_set_pgd(pgdp, pgd) #define pgd_clear(pgd) (pgtable_l5_enabled() ? native_pgd_clear(pgd) : 0) #endif #ifndef set_p4d # define set_p4d(p4dp, p4d) native_set_p4d(p4dp, p4d) #endif #ifndef __PAGETABLE_PUD_FOLDED #define p4d_clear(p4d) native_p4d_clear(p4d) #endif #ifndef set_pud # define set_pud(pudp, pud) native_set_pud(pudp, pud) #endif #ifndef __PAGETABLE_PUD_FOLDED #define pud_clear(pud) native_pud_clear(pud) #endif #define pte_clear(mm, addr, ptep) native_pte_clear(mm, addr, ptep) #define pmd_clear(pmd) native_pmd_clear(pmd) #define pgd_val(x) native_pgd_val(x) #define __pgd(x) native_make_pgd(x) #ifndef __PAGETABLE_P4D_FOLDED #define p4d_val(x) native_p4d_val(x) #define __p4d(x) native_make_p4d(x) #endif #ifndef __PAGETABLE_PUD_FOLDED #define pud_val(x) native_pud_val(x) #define __pud(x) native_make_pud(x) #endif #ifndef __PAGETABLE_PMD_FOLDED #define pmd_val(x) native_pmd_val(x) #define __pmd(x) native_make_pmd(x) #endif #define pte_val(x) native_pte_val(x) #define __pte(x) native_make_pte(x) #define arch_end_context_switch(prev) do {} while(0) #endif /* CONFIG_PARAVIRT_XXL */ static inline pmd_t pmd_set_flags(pmd_t pmd, pmdval_t set) { pmdval_t v = native_pmd_val(pmd); return native_make_pmd(v | set); } static inline pmd_t pmd_clear_flags(pmd_t pmd, pmdval_t clear) { pmdval_t v = native_pmd_val(pmd); return native_make_pmd(v & ~clear); } static inline pud_t pud_set_flags(pud_t pud, pudval_t set) { pudval_t v = native_pud_val(pud); return native_make_pud(v | set); } static inline pud_t pud_clear_flags(pud_t pud, pudval_t clear) { pudval_t v = native_pud_val(pud); return native_make_pud(v & ~clear); } /* * The following only work if pte_present() is true. * Undefined behaviour if not.. */ static inline bool pte_dirty(pte_t pte) { return pte_flags(pte) & _PAGE_DIRTY_BITS; } static inline bool pte_shstk(pte_t pte) { return cpu_feature_enabled(X86_FEATURE_SHSTK) && (pte_flags(pte) & (_PAGE_RW | _PAGE_DIRTY)) == _PAGE_DIRTY; } static inline int pte_young(pte_t pte) { return pte_flags(pte) & _PAGE_ACCESSED; } static inline bool pte_decrypted(pte_t pte) { return cc_mkdec(pte_val(pte)) == pte_val(pte); } #define pmd_dirty pmd_dirty static inline bool pmd_dirty(pmd_t pmd) { return pmd_flags(pmd) & _PAGE_DIRTY_BITS; } static inline bool pmd_shstk(pmd_t pmd) { return cpu_feature_enabled(X86_FEATURE_SHSTK) && (pmd_flags(pmd) & (_PAGE_RW | _PAGE_DIRTY | _PAGE_PSE)) == (_PAGE_DIRTY | _PAGE_PSE); } #define pmd_young pmd_young static inline int pmd_young(pmd_t pmd) { return pmd_flags(pmd) & _PAGE_ACCESSED; } static inline bool pud_dirty(pud_t pud) { return pud_flags(pud) & _PAGE_DIRTY_BITS; } static inline int pud_young(pud_t pud) { return pud_flags(pud) & _PAGE_ACCESSED; } static inline bool pud_shstk(pud_t pud) { return cpu_feature_enabled(X86_FEATURE_SHSTK) && (pud_flags(pud) & (_PAGE_RW | _PAGE_DIRTY | _PAGE_PSE)) == (_PAGE_DIRTY | _PAGE_PSE); } static inline int pte_write(pte_t pte) { /* * Shadow stack pages are logically writable, but do not have * _PAGE_RW. Check for them separately from _PAGE_RW itself. */ return (pte_flags(pte) & _PAGE_RW) || pte_shstk(pte); } #define pmd_write pmd_write static inline int pmd_write(pmd_t pmd) { /* * Shadow stack pages are logically writable, but do not have * _PAGE_RW. Check for them separately from _PAGE_RW itself. */ return (pmd_flags(pmd) & _PAGE_RW) || pmd_shstk(pmd); } #define pud_write pud_write static inline int pud_write(pud_t pud) { return pud_flags(pud) & _PAGE_RW; } static inline int pte_huge(pte_t pte) { return pte_flags(pte) & _PAGE_PSE; } static inline int pte_global(pte_t pte) { return pte_flags(pte) & _PAGE_GLOBAL; } static inline int pte_exec(pte_t pte) { return !(pte_flags(pte) & _PAGE_NX); } static inline int pte_special(pte_t pte) { return pte_flags(pte) & _PAGE_SPECIAL; } /* Entries that were set to PROT_NONE are inverted */ static inline u64 protnone_mask(u64 val); #define PFN_PTE_SHIFT PAGE_SHIFT static inline unsigned long pte_pfn(pte_t pte) { phys_addr_t pfn = pte_val(pte); pfn ^= protnone_mask(pfn); return (pfn & PTE_PFN_MASK) >> PAGE_SHIFT; } static inline unsigned long pmd_pfn(pmd_t pmd) { phys_addr_t pfn = pmd_val(pmd); pfn ^= protnone_mask(pfn); return (pfn & pmd_pfn_mask(pmd)) >> PAGE_SHIFT; } #define pud_pfn pud_pfn static inline unsigned long pud_pfn(pud_t pud) { phys_addr_t pfn = pud_val(pud); pfn ^= protnone_mask(pfn); return (pfn & pud_pfn_mask(pud)) >> PAGE_SHIFT; } static inline unsigned long p4d_pfn(p4d_t p4d) { return (p4d_val(p4d) & p4d_pfn_mask(p4d)) >> PAGE_SHIFT; } static inline unsigned long pgd_pfn(pgd_t pgd) { return (pgd_val(pgd) & PTE_PFN_MASK) >> PAGE_SHIFT; } #define p4d_leaf p4d_leaf static inline bool p4d_leaf(p4d_t p4d) { /* No 512 GiB pages yet */ return 0; } #define pte_page(pte) pfn_to_page(pte_pfn(pte)) #define pmd_leaf pmd_leaf static inline bool pmd_leaf(pmd_t pte) { return pmd_flags(pte) & _PAGE_PSE; } #ifdef CONFIG_TRANSPARENT_HUGEPAGE /* NOTE: when predicate huge page, consider also pmd_devmap, or use pmd_leaf */ static inline int pmd_trans_huge(pmd_t pmd) { return (pmd_val(pmd) & (_PAGE_PSE|_PAGE_DEVMAP)) == _PAGE_PSE; } #ifdef CONFIG_HAVE_ARCH_TRANSPARENT_HUGEPAGE_PUD static inline int pud_trans_huge(pud_t pud) { return (pud_val(pud) & (_PAGE_PSE|_PAGE_DEVMAP)) == _PAGE_PSE; } #endif #define has_transparent_hugepage has_transparent_hugepage static inline int has_transparent_hugepage(void) { return boot_cpu_has(X86_FEATURE_PSE); } #ifdef CONFIG_ARCH_HAS_PTE_DEVMAP static inline int pmd_devmap(pmd_t pmd) { return !!(pmd_val(pmd) & _PAGE_DEVMAP); } #ifdef CONFIG_HAVE_ARCH_TRANSPARENT_HUGEPAGE_PUD static inline int pud_devmap(pud_t pud) { return !!(pud_val(pud) & _PAGE_DEVMAP); } #else static inline int pud_devmap(pud_t pud) { return 0; } #endif #ifdef CONFIG_ARCH_SUPPORTS_PMD_PFNMAP static inline bool pmd_special(pmd_t pmd) { return pmd_flags(pmd) & _PAGE_SPECIAL; } static inline pmd_t pmd_mkspecial(pmd_t pmd) { return pmd_set_flags(pmd, _PAGE_SPECIAL); } #endif /* CONFIG_ARCH_SUPPORTS_PMD_PFNMAP */ #ifdef CONFIG_ARCH_SUPPORTS_PUD_PFNMAP static inline bool pud_special(pud_t pud) { return pud_flags(pud) & _PAGE_SPECIAL; } static inline pud_t pud_mkspecial(pud_t pud) { return pud_set_flags(pud, _PAGE_SPECIAL); } #endif /* CONFIG_ARCH_SUPPORTS_PUD_PFNMAP */ static inline int pgd_devmap(pgd_t pgd) { return 0; } #endif #endif /* CONFIG_TRANSPARENT_HUGEPAGE */ static inline pte_t pte_set_flags(pte_t pte, pteval_t set) { pteval_t v = native_pte_val(pte); return native_make_pte(v | set); } static inline pte_t pte_clear_flags(pte_t pte, pteval_t clear) { pteval_t v = native_pte_val(pte); return native_make_pte(v & ~clear); } /* * Write protection operations can result in Dirty=1,Write=0 PTEs. But in the * case of X86_FEATURE_USER_SHSTK, these PTEs denote shadow stack memory. So * when creating dirty, write-protected memory, a software bit is used: * _PAGE_BIT_SAVED_DIRTY. The following functions take a PTE and transition the * Dirty bit to SavedDirty, and vice-vesra. * * This shifting is only done if needed. In the case of shifting * Dirty->SavedDirty, the condition is if the PTE is Write=0. In the case of * shifting SavedDirty->Dirty, the condition is Write=1. */ static inline pgprotval_t mksaveddirty_shift(pgprotval_t v) { pgprotval_t cond = (~v >> _PAGE_BIT_RW) & 1; v |= ((v >> _PAGE_BIT_DIRTY) & cond) << _PAGE_BIT_SAVED_DIRTY; v &= ~(cond << _PAGE_BIT_DIRTY); return v; } static inline pgprotval_t clear_saveddirty_shift(pgprotval_t v) { pgprotval_t cond = (v >> _PAGE_BIT_RW) & 1; v |= ((v >> _PAGE_BIT_SAVED_DIRTY) & cond) << _PAGE_BIT_DIRTY; v &= ~(cond << _PAGE_BIT_SAVED_DIRTY); return v; } static inline pte_t pte_mksaveddirty(pte_t pte) { pteval_t v = native_pte_val(pte); v = mksaveddirty_shift(v); return native_make_pte(v); } static inline pte_t pte_clear_saveddirty(pte_t pte) { pteval_t v = native_pte_val(pte); v = clear_saveddirty_shift(v); return native_make_pte(v); } static inline pte_t pte_wrprotect(pte_t pte) { pte = pte_clear_flags(pte, _PAGE_RW); /* * Blindly clearing _PAGE_RW might accidentally create * a shadow stack PTE (Write=0,Dirty=1). Move the hardware * dirty value to the software bit, if present. */ return pte_mksaveddirty(pte); } #ifdef CONFIG_HAVE_ARCH_USERFAULTFD_WP static inline int pte_uffd_wp(pte_t pte) { return pte_flags(pte) & _PAGE_UFFD_WP; } static inline pte_t pte_mkuffd_wp(pte_t pte) { return pte_wrprotect(pte_set_flags(pte, _PAGE_UFFD_WP)); } static inline pte_t pte_clear_uffd_wp(pte_t pte) { return pte_clear_flags(pte, _PAGE_UFFD_WP); } #endif /* CONFIG_HAVE_ARCH_USERFAULTFD_WP */ static inline pte_t pte_mkclean(pte_t pte) { return pte_clear_flags(pte, _PAGE_DIRTY_BITS); } static inline pte_t pte_mkold(pte_t pte) { return pte_clear_flags(pte, _PAGE_ACCESSED); } static inline pte_t pte_mkexec(pte_t pte) { return pte_clear_flags(pte, _PAGE_NX); } static inline pte_t pte_mkdirty(pte_t pte) { pte = pte_set_flags(pte, _PAGE_DIRTY | _PAGE_SOFT_DIRTY); return pte_mksaveddirty(pte); } static inline pte_t pte_mkwrite_shstk(pte_t pte) { pte = pte_clear_flags(pte, _PAGE_RW); return pte_set_flags(pte, _PAGE_DIRTY); } static inline pte_t pte_mkyoung(pte_t pte) { return pte_set_flags(pte, _PAGE_ACCESSED); } static inline pte_t pte_mkwrite_novma(pte_t pte) { return pte_set_flags(pte, _PAGE_RW); } struct vm_area_struct; pte_t pte_mkwrite(pte_t pte, struct vm_area_struct *vma); #define pte_mkwrite pte_mkwrite static inline pte_t pte_mkhuge(pte_t pte) { return pte_set_flags(pte, _PAGE_PSE); } static inline pte_t pte_clrhuge(pte_t pte) { return pte_clear_flags(pte, _PAGE_PSE); } static inline pte_t pte_mkglobal(pte_t pte) { return pte_set_flags(pte, _PAGE_GLOBAL); } static inline pte_t pte_clrglobal(pte_t pte) { return pte_clear_flags(pte, _PAGE_GLOBAL); } static inline pte_t pte_mkspecial(pte_t pte) { return pte_set_flags(pte, _PAGE_SPECIAL); } static inline pte_t pte_mkdevmap(pte_t pte) { return pte_set_flags(pte, _PAGE_SPECIAL|_PAGE_DEVMAP); } /* See comments above mksaveddirty_shift() */ static inline pmd_t pmd_mksaveddirty(pmd_t pmd) { pmdval_t v = native_pmd_val(pmd); v = mksaveddirty_shift(v); return native_make_pmd(v); } /* See comments above mksaveddirty_shift() */ static inline pmd_t pmd_clear_saveddirty(pmd_t pmd) { pmdval_t v = native_pmd_val(pmd); v = clear_saveddirty_shift(v); return native_make_pmd(v); } static inline pmd_t pmd_wrprotect(pmd_t pmd) { pmd = pmd_clear_flags(pmd, _PAGE_RW); /* * Blindly clearing _PAGE_RW might accidentally create * a shadow stack PMD (RW=0, Dirty=1). Move the hardware * dirty value to the software bit. */ return pmd_mksaveddirty(pmd); } #ifdef CONFIG_HAVE_ARCH_USERFAULTFD_WP static inline int pmd_uffd_wp(pmd_t pmd) { return pmd_flags(pmd) & _PAGE_UFFD_WP; } static inline pmd_t pmd_mkuffd_wp(pmd_t pmd) { return pmd_wrprotect(pmd_set_flags(pmd, _PAGE_UFFD_WP)); } static inline pmd_t pmd_clear_uffd_wp(pmd_t pmd) { return pmd_clear_flags(pmd, _PAGE_UFFD_WP); } #endif /* CONFIG_HAVE_ARCH_USERFAULTFD_WP */ static inline pmd_t pmd_mkold(pmd_t pmd) { return pmd_clear_flags(pmd, _PAGE_ACCESSED); } static inline pmd_t pmd_mkclean(pmd_t pmd) { return pmd_clear_flags(pmd, _PAGE_DIRTY_BITS); } static inline pmd_t pmd_mkdirty(pmd_t pmd) { pmd = pmd_set_flags(pmd, _PAGE_DIRTY | _PAGE_SOFT_DIRTY); return pmd_mksaveddirty(pmd); } static inline pmd_t pmd_mkwrite_shstk(pmd_t pmd) { pmd = pmd_clear_flags(pmd, _PAGE_RW); return pmd_set_flags(pmd, _PAGE_DIRTY); } static inline pmd_t pmd_mkdevmap(pmd_t pmd) { return pmd_set_flags(pmd, _PAGE_DEVMAP); } static inline pmd_t pmd_mkhuge(pmd_t pmd) { return pmd_set_flags(pmd, _PAGE_PSE); } static inline pmd_t pmd_mkyoung(pmd_t pmd) { return pmd_set_flags(pmd, _PAGE_ACCESSED); } static inline pmd_t pmd_mkwrite_novma(pmd_t pmd) { return pmd_set_flags(pmd, _PAGE_RW); } pmd_t pmd_mkwrite(pmd_t pmd, struct vm_area_struct *vma); #define pmd_mkwrite pmd_mkwrite /* See comments above mksaveddirty_shift() */ static inline pud_t pud_mksaveddirty(pud_t pud) { pudval_t v = native_pud_val(pud); v = mksaveddirty_shift(v); return native_make_pud(v); } /* See comments above mksaveddirty_shift() */ static inline pud_t pud_clear_saveddirty(pud_t pud) { pudval_t v = native_pud_val(pud); v = clear_saveddirty_shift(v); return native_make_pud(v); } static inline pud_t pud_mkold(pud_t pud) { return pud_clear_flags(pud, _PAGE_ACCESSED); } static inline pud_t pud_mkclean(pud_t pud) { return pud_clear_flags(pud, _PAGE_DIRTY_BITS); } static inline pud_t pud_wrprotect(pud_t pud) { pud = pud_clear_flags(pud, _PAGE_RW); /* * Blindly clearing _PAGE_RW might accidentally create * a shadow stack PUD (RW=0, Dirty=1). Move the hardware * dirty value to the software bit. */ return pud_mksaveddirty(pud); } static inline pud_t pud_mkdirty(pud_t pud) { pud = pud_set_flags(pud, _PAGE_DIRTY | _PAGE_SOFT_DIRTY); return pud_mksaveddirty(pud); } static inline pud_t pud_mkdevmap(pud_t pud) { return pud_set_flags(pud, _PAGE_DEVMAP); } static inline pud_t pud_mkhuge(pud_t pud) { return pud_set_flags(pud, _PAGE_PSE); } static inline pud_t pud_mkyoung(pud_t pud) { return pud_set_flags(pud, _PAGE_ACCESSED); } static inline pud_t pud_mkwrite(pud_t pud) { pud = pud_set_flags(pud, _PAGE_RW); return pud_clear_saveddirty(pud); } #ifdef CONFIG_HAVE_ARCH_SOFT_DIRTY static inline int pte_soft_dirty(pte_t pte) { return pte_flags(pte) & _PAGE_SOFT_DIRTY; } static inline int pmd_soft_dirty(pmd_t pmd) { return pmd_flags(pmd) & _PAGE_SOFT_DIRTY; } static inline int pud_soft_dirty(pud_t pud) { return pud_flags(pud) & _PAGE_SOFT_DIRTY; } static inline pte_t pte_mksoft_dirty(pte_t pte) { return pte_set_flags(pte, _PAGE_SOFT_DIRTY); } static inline pmd_t pmd_mksoft_dirty(pmd_t pmd) { return pmd_set_flags(pmd, _PAGE_SOFT_DIRTY); } static inline pud_t pud_mksoft_dirty(pud_t pud) { return pud_set_flags(pud, _PAGE_SOFT_DIRTY); } static inline pte_t pte_clear_soft_dirty(pte_t pte) { return pte_clear_flags(pte, _PAGE_SOFT_DIRTY); } static inline pmd_t pmd_clear_soft_dirty(pmd_t pmd) { return pmd_clear_flags(pmd, _PAGE_SOFT_DIRTY); } static inline pud_t pud_clear_soft_dirty(pud_t pud) { return pud_clear_flags(pud, _PAGE_SOFT_DIRTY); } #endif /* CONFIG_HAVE_ARCH_SOFT_DIRTY */ /* * Mask out unsupported bits in a present pgprot. Non-present pgprots * can use those bits for other purposes, so leave them be. */ static inline pgprotval_t massage_pgprot(pgprot_t pgprot) { pgprotval_t protval = pgprot_val(pgprot); if (protval & _PAGE_PRESENT) protval &= __supported_pte_mask; return protval; } static inline pgprotval_t check_pgprot(pgprot_t pgprot) { pgprotval_t massaged_val = massage_pgprot(pgprot); /* mmdebug.h can not be included here because of dependencies */ #ifdef CONFIG_DEBUG_VM WARN_ONCE(pgprot_val(pgprot) != massaged_val, "attempted to set unsupported pgprot: %016llx " "bits: %016llx supported: %016llx\n", (u64)pgprot_val(pgprot), (u64)pgprot_val(pgprot) ^ massaged_val, (u64)__supported_pte_mask); #endif return massaged_val; } static inline pte_t pfn_pte(unsigned long page_nr, pgprot_t pgprot) { phys_addr_t pfn = (phys_addr_t)page_nr << PAGE_SHIFT; pfn ^= protnone_mask(pgprot_val(pgprot)); pfn &= PTE_PFN_MASK; return __pte(pfn | check_pgprot(pgprot)); } static inline pmd_t pfn_pmd(unsigned long page_nr, pgprot_t pgprot) { phys_addr_t pfn = (phys_addr_t)page_nr << PAGE_SHIFT; pfn ^= protnone_mask(pgprot_val(pgprot)); pfn &= PHYSICAL_PMD_PAGE_MASK; return __pmd(pfn | check_pgprot(pgprot)); } static inline pud_t pfn_pud(unsigned long page_nr, pgprot_t pgprot) { phys_addr_t pfn = (phys_addr_t)page_nr << PAGE_SHIFT; pfn ^= protnone_mask(pgprot_val(pgprot)); pfn &= PHYSICAL_PUD_PAGE_MASK; return __pud(pfn | check_pgprot(pgprot)); } static inline pmd_t pmd_mkinvalid(pmd_t pmd) { return pfn_pmd(pmd_pfn(pmd), __pgprot(pmd_flags(pmd) & ~(_PAGE_PRESENT|_PAGE_PROTNONE))); } static inline pud_t pud_mkinvalid(pud_t pud) { return pfn_pud(pud_pfn(pud), __pgprot(pud_flags(pud) & ~(_PAGE_PRESENT|_PAGE_PROTNONE))); } static inline u64 flip_protnone_guard(u64 oldval, u64 val, u64 mask); static inline pte_t pte_modify(pte_t pte, pgprot_t newprot) { pteval_t val = pte_val(pte), oldval = val; pte_t pte_result; /* * Chop off the NX bit (if present), and add the NX portion of * the newprot (if present): */ val &= _PAGE_CHG_MASK; val |= check_pgprot(newprot) & ~_PAGE_CHG_MASK; val = flip_protnone_guard(oldval, val, PTE_PFN_MASK); pte_result = __pte(val); /* * To avoid creating Write=0,Dirty=1 PTEs, pte_modify() needs to avoid: * 1. Marking Write=0 PTEs Dirty=1 * 2. Marking Dirty=1 PTEs Write=0 * * The first case cannot happen because the _PAGE_CHG_MASK will filter * out any Dirty bit passed in newprot. Handle the second case by * going through the mksaveddirty exercise. Only do this if the old * value was Write=1 to avoid doing this on Shadow Stack PTEs. */ if (oldval & _PAGE_RW) pte_result = pte_mksaveddirty(pte_result); else pte_result = pte_clear_saveddirty(pte_result); return pte_result; } static inline pmd_t pmd_modify(pmd_t pmd, pgprot_t newprot) { pmdval_t val = pmd_val(pmd), oldval = val; pmd_t pmd_result; val &= (_HPAGE_CHG_MASK & ~_PAGE_DIRTY); val |= check_pgprot(newprot) & ~_HPAGE_CHG_MASK; val = flip_protnone_guard(oldval, val, PHYSICAL_PMD_PAGE_MASK); pmd_result = __pmd(val); /* * Avoid creating shadow stack PMD by accident. See comment in * pte_modify(). */ if (oldval & _PAGE_RW) pmd_result = pmd_mksaveddirty(pmd_result); else pmd_result = pmd_clear_saveddirty(pmd_result); return pmd_result; } static inline pud_t pud_modify(pud_t pud, pgprot_t newprot) { pudval_t val = pud_val(pud), oldval = val; pud_t pud_result; val &= _HPAGE_CHG_MASK; val |= check_pgprot(newprot) & ~_HPAGE_CHG_MASK; val = flip_protnone_guard(oldval, val, PHYSICAL_PUD_PAGE_MASK); pud_result = __pud(val); /* * Avoid creating shadow stack PUD by accident. See comment in * pte_modify(). */ if (oldval & _PAGE_RW) pud_result = pud_mksaveddirty(pud_result); else pud_result = pud_clear_saveddirty(pud_result); return pud_result; } /* * mprotect needs to preserve PAT and encryption bits when updating * vm_page_prot */ #define pgprot_modify pgprot_modify static inline pgprot_t pgprot_modify(pgprot_t oldprot, pgprot_t newprot) { pgprotval_t preservebits = pgprot_val(oldprot) & _PAGE_CHG_MASK; pgprotval_t addbits = pgprot_val(newprot) & ~_PAGE_CHG_MASK; return __pgprot(preservebits | addbits); } #define pte_pgprot(x) __pgprot(pte_flags(x)) #define pmd_pgprot(x) __pgprot(pmd_flags(x)) #define pud_pgprot(x) __pgprot(pud_flags(x)) #define p4d_pgprot(x) __pgprot(p4d_flags(x)) #define canon_pgprot(p) __pgprot(massage_pgprot(p)) static inline int is_new_memtype_allowed(u64 paddr, unsigned long size, enum page_cache_mode pcm, enum page_cache_mode new_pcm) { /* * PAT type is always WB for untracked ranges, so no need to check. */ if (x86_platform.is_untracked_pat_range(paddr, paddr + size)) return 1; /* * Certain new memtypes are not allowed with certain * requested memtype: * - request is uncached, return cannot be write-back * - request is write-combine, return cannot be write-back * - request is write-through, return cannot be write-back * - request is write-through, return cannot be write-combine */ if ((pcm == _PAGE_CACHE_MODE_UC_MINUS && new_pcm == _PAGE_CACHE_MODE_WB) || (pcm == _PAGE_CACHE_MODE_WC && new_pcm == _PAGE_CACHE_MODE_WB) || (pcm == _PAGE_CACHE_MODE_WT && new_pcm == _PAGE_CACHE_MODE_WB) || (pcm == _PAGE_CACHE_MODE_WT && new_pcm == _PAGE_CACHE_MODE_WC)) { return 0; } return 1; } pmd_t *populate_extra_pmd(unsigned long vaddr); pte_t *populate_extra_pte(unsigned long vaddr); #ifdef CONFIG_MITIGATION_PAGE_TABLE_ISOLATION pgd_t __pti_set_user_pgtbl(pgd_t *pgdp, pgd_t pgd); /* * Take a PGD location (pgdp) and a pgd value that needs to be set there. * Populates the user and returns the resulting PGD that must be set in * the kernel copy of the page tables. */ static inline pgd_t pti_set_user_pgtbl(pgd_t *pgdp, pgd_t pgd) { if (!static_cpu_has(X86_FEATURE_PTI)) return pgd; return __pti_set_user_pgtbl(pgdp, pgd); } #else /* CONFIG_MITIGATION_PAGE_TABLE_ISOLATION */ static inline pgd_t pti_set_user_pgtbl(pgd_t *pgdp, pgd_t pgd) { return pgd; } #endif /* CONFIG_MITIGATION_PAGE_TABLE_ISOLATION */ #endif /* __ASSEMBLY__ */ #ifdef CONFIG_X86_32 # include <asm/pgtable_32.h> #else # include <asm/pgtable_64.h> #endif #ifndef __ASSEMBLY__ #include <linux/mm_types.h> #include <linux/mmdebug.h> #include <linux/log2.h> #include <asm/fixmap.h> static inline int pte_none(pte_t pte) { return !(pte.pte & ~(_PAGE_KNL_ERRATUM_MASK)); } #define __HAVE_ARCH_PTE_SAME static inline int pte_same(pte_t a, pte_t b) { return a.pte == b.pte; } static inline pte_t pte_advance_pfn(pte_t pte, unsigned long nr) { if (__pte_needs_invert(pte_val(pte))) return __pte(pte_val(pte) - (nr << PFN_PTE_SHIFT)); return __pte(pte_val(pte) + (nr << PFN_PTE_SHIFT)); } #define pte_advance_pfn pte_advance_pfn static inline int pte_present(pte_t a) { return pte_flags(a) & (_PAGE_PRESENT | _PAGE_PROTNONE); } #ifdef CONFIG_ARCH_HAS_PTE_DEVMAP static inline int pte_devmap(pte_t a) { return (pte_flags(a) & _PAGE_DEVMAP) == _PAGE_DEVMAP; } #endif #define pte_accessible pte_accessible static inline bool pte_accessible(struct mm_struct *mm, pte_t a) { if (pte_flags(a) & _PAGE_PRESENT) return true; if ((pte_flags(a) & _PAGE_PROTNONE) && atomic_read(&mm->tlb_flush_pending)) return true; return false; } static inline int pmd_present(pmd_t pmd) { /* * Checking for _PAGE_PSE is needed too because * split_huge_page will temporarily clear the present bit (but * the _PAGE_PSE flag will remain set at all times while the * _PAGE_PRESENT bit is clear). */ return pmd_flags(pmd) & (_PAGE_PRESENT | _PAGE_PROTNONE | _PAGE_PSE); } #ifdef CONFIG_NUMA_BALANCING /* * These work without NUMA balancing but the kernel does not care. See the * comment in include/linux/pgtable.h */ static inline int pte_protnone(pte_t pte) { return (pte_flags(pte) & (_PAGE_PROTNONE | _PAGE_PRESENT)) == _PAGE_PROTNONE; } static inline int pmd_protnone(pmd_t pmd) { return (pmd_flags(pmd) & (_PAGE_PROTNONE | _PAGE_PRESENT)) == _PAGE_PROTNONE; } #endif /* CONFIG_NUMA_BALANCING */ static inline int pmd_none(pmd_t pmd) { /* Only check low word on 32-bit platforms, since it might be out of sync with upper half. */ unsigned long val = native_pmd_val(pmd); return (val & ~_PAGE_KNL_ERRATUM_MASK) == 0; } static inline unsigned long pmd_page_vaddr(pmd_t pmd) { return (unsigned long)__va(pmd_val(pmd) & pmd_pfn_mask(pmd)); } /* * Currently stuck as a macro due to indirect forward reference to * linux/mmzone.h's __section_mem_map_addr() definition: */ #define pmd_page(pmd) pfn_to_page(pmd_pfn(pmd)) /* * Conversion functions: convert a page and protection to a page entry, * and a page entry and page directory to the page they refer to. * * (Currently stuck as a macro because of indirect forward reference * to linux/mm.h:page_to_nid()) */ #define mk_pte(page, pgprot) \ ({ \ pgprot_t __pgprot = pgprot; \ \ WARN_ON_ONCE((pgprot_val(__pgprot) & (_PAGE_DIRTY | _PAGE_RW)) == \ _PAGE_DIRTY); \ pfn_pte(page_to_pfn(page), __pgprot); \ }) static inline int pmd_bad(pmd_t pmd) { return (pmd_flags(pmd) & ~(_PAGE_USER | _PAGE_ACCESSED)) != (_KERNPG_TABLE & ~_PAGE_ACCESSED); } static inline unsigned long pages_to_mb(unsigned long npg) { return npg >> (20 - PAGE_SHIFT); } #if CONFIG_PGTABLE_LEVELS > 2 static inline int pud_none(pud_t pud) { return (native_pud_val(pud) & ~(_PAGE_KNL_ERRATUM_MASK)) == 0; } static inline int pud_present(pud_t pud) { return pud_flags(pud) & _PAGE_PRESENT; } static inline pmd_t *pud_pgtable(pud_t pud) { return (pmd_t *)__va(pud_val(pud) & pud_pfn_mask(pud)); } /* * Currently stuck as a macro due to indirect forward reference to * linux/mmzone.h's __section_mem_map_addr() definition: */ #define pud_page(pud) pfn_to_page(pud_pfn(pud)) #define pud_leaf pud_leaf static inline bool pud_leaf(pud_t pud) { return pud_val(pud) & _PAGE_PSE; } static inline int pud_bad(pud_t pud) { return (pud_flags(pud) & ~(_KERNPG_TABLE | _PAGE_USER)) != 0; } #endif /* CONFIG_PGTABLE_LEVELS > 2 */ #if CONFIG_PGTABLE_LEVELS > 3 static inline int p4d_none(p4d_t p4d) { return (native_p4d_val(p4d) & ~(_PAGE_KNL_ERRATUM_MASK)) == 0; } static inline int p4d_present(p4d_t p4d) { return p4d_flags(p4d) & _PAGE_PRESENT; } static inline pud_t *p4d_pgtable(p4d_t p4d) { return (pud_t *)__va(p4d_val(p4d) & p4d_pfn_mask(p4d)); } /* * Currently stuck as a macro due to indirect forward reference to * linux/mmzone.h's __section_mem_map_addr() definition: */ #define p4d_page(p4d) pfn_to_page(p4d_pfn(p4d)) static inline int p4d_bad(p4d_t p4d) { unsigned long ignore_flags = _KERNPG_TABLE | _PAGE_USER; if (IS_ENABLED(CONFIG_MITIGATION_PAGE_TABLE_ISOLATION)) ignore_flags |= _PAGE_NX; return (p4d_flags(p4d) & ~ignore_flags) != 0; } #endif /* CONFIG_PGTABLE_LEVELS > 3 */ static inline unsigned long p4d_index(unsigned long address) { return (address >> P4D_SHIFT) & (PTRS_PER_P4D - 1); } #if CONFIG_PGTABLE_LEVELS > 4 static inline int pgd_present(pgd_t pgd) { if (!pgtable_l5_enabled()) return 1; return pgd_flags(pgd) & _PAGE_PRESENT; } static inline unsigned long pgd_page_vaddr(pgd_t pgd) { return (unsigned long)__va((unsigned long)pgd_val(pgd) & PTE_PFN_MASK); } /* * Currently stuck as a macro due to indirect forward reference to * linux/mmzone.h's __section_mem_map_addr() definition: */ #define pgd_page(pgd) pfn_to_page(pgd_pfn(pgd)) /* to find an entry in a page-table-directory. */ static inline p4d_t *p4d_offset(pgd_t *pgd, unsigned long address) { if (!pgtable_l5_enabled()) return (p4d_t *)pgd; return (p4d_t *)pgd_page_vaddr(*pgd) + p4d_index(address); } static inline int pgd_bad(pgd_t pgd) { unsigned long ignore_flags = _PAGE_USER; if (!pgtable_l5_enabled()) return 0; if (IS_ENABLED(CONFIG_MITIGATION_PAGE_TABLE_ISOLATION)) ignore_flags |= _PAGE_NX; return (pgd_flags(pgd) & ~ignore_flags) != _KERNPG_TABLE; } static inline int pgd_none(pgd_t pgd) { if (!pgtable_l5_enabled()) return 0; /* * There is no need to do a workaround for the KNL stray * A/D bit erratum here. PGDs only point to page tables * except on 32-bit non-PAE which is not supported on * KNL. */ return !native_pgd_val(pgd); } #endif /* CONFIG_PGTABLE_LEVELS > 4 */ #endif /* __ASSEMBLY__ */ #define KERNEL_PGD_BOUNDARY pgd_index(PAGE_OFFSET) #define KERNEL_PGD_PTRS (PTRS_PER_PGD - KERNEL_PGD_BOUNDARY) #ifndef __ASSEMBLY__ extern int direct_gbpages; void init_mem_mapping(void); void early_alloc_pgt_buf(void); void __init poking_init(void); unsigned long init_memory_mapping(unsigned long start, unsigned long end, pgprot_t prot); #ifdef CONFIG_X86_64 extern pgd_t trampoline_pgd_entry; #endif /* local pte updates need not use xchg for locking */ static inline pte_t native_local_ptep_get_and_clear(pte_t *ptep) { pte_t res = *ptep; /* Pure native function needs no input for mm, addr */ native_pte_clear(NULL, 0, ptep); return res; } static inline pmd_t native_local_pmdp_get_and_clear(pmd_t *pmdp) { pmd_t res = *pmdp; native_pmd_clear(pmdp); return res; } static inline pud_t native_local_pudp_get_and_clear(pud_t *pudp) { pud_t res = *pudp; native_pud_clear(pudp); return res; } static inline void set_pmd_at(struct mm_struct *mm, unsigned long addr, pmd_t *pmdp, pmd_t pmd) { page_table_check_pmd_set(mm, pmdp, pmd); set_pmd(pmdp, pmd); } static inline void set_pud_at(struct mm_struct *mm, unsigned long addr, pud_t *pudp, pud_t pud) { page_table_check_pud_set(mm, pudp, pud); native_set_pud(pudp, pud); } /* * We only update the dirty/accessed state if we set * the dirty bit by hand in the kernel, since the hardware * will do the accessed bit for us, and we don't want to * race with other CPU's that might be updating the dirty * bit at the same time. */ struct vm_area_struct; #define __HAVE_ARCH_PTEP_SET_ACCESS_FLAGS extern int ptep_set_access_flags(struct vm_area_struct *vma, unsigned long address, pte_t *ptep, pte_t entry, int dirty); #define __HAVE_ARCH_PTEP_TEST_AND_CLEAR_YOUNG extern int ptep_test_and_clear_young(struct vm_area_struct *vma, unsigned long addr, pte_t *ptep); #define __HAVE_ARCH_PTEP_CLEAR_YOUNG_FLUSH extern int ptep_clear_flush_young(struct vm_area_struct *vma, unsigned long address, pte_t *ptep); #define __HAVE_ARCH_PTEP_GET_AND_CLEAR static inline pte_t ptep_get_and_clear(struct mm_struct *mm, unsigned long addr, pte_t *ptep) { pte_t pte = native_ptep_get_and_clear(ptep); page_table_check_pte_clear(mm, pte); return pte; } #define __HAVE_ARCH_PTEP_GET_AND_CLEAR_FULL static inline pte_t ptep_get_and_clear_full(struct mm_struct *mm, unsigned long addr, pte_t *ptep, int full) { pte_t pte; if (full) { /* * Full address destruction in progress; paravirt does not * care about updates and native needs no locking */ pte = native_local_ptep_get_and_clear(ptep); page_table_check_pte_clear(mm, pte); } else { pte = ptep_get_and_clear(mm, addr, ptep); } return pte; } #define __HAVE_ARCH_PTEP_SET_WRPROTECT static inline void ptep_set_wrprotect(struct mm_struct *mm, unsigned long addr, pte_t *ptep) { /* * Avoid accidentally creating shadow stack PTEs * (Write=0,Dirty=1). Use cmpxchg() to prevent races with * the hardware setting Dirty=1. */ pte_t old_pte, new_pte; old_pte = READ_ONCE(*ptep); do { new_pte = pte_wrprotect(old_pte); } while (!try_cmpxchg((long *)&ptep->pte, (long *)&old_pte, *(long *)&new_pte)); } #define flush_tlb_fix_spurious_fault(vma, address, ptep) do { } while (0) #define mk_pmd(page, pgprot) pfn_pmd(page_to_pfn(page), (pgprot)) #define __HAVE_ARCH_PMDP_SET_ACCESS_FLAGS extern int pmdp_set_access_flags(struct vm_area_struct *vma, unsigned long address, pmd_t *pmdp, pmd_t entry, int dirty); extern int pudp_set_access_flags(struct vm_area_struct *vma, unsigned long address, pud_t *pudp, pud_t entry, int dirty); #define __HAVE_ARCH_PMDP_TEST_AND_CLEAR_YOUNG extern int pmdp_test_and_clear_young(struct vm_area_struct *vma, unsigned long addr, pmd_t *pmdp); extern int pudp_test_and_clear_young(struct vm_area_struct *vma, unsigned long addr, pud_t *pudp); #define __HAVE_ARCH_PMDP_CLEAR_YOUNG_FLUSH extern int pmdp_clear_flush_young(struct vm_area_struct *vma, unsigned long address, pmd_t *pmdp); #define __HAVE_ARCH_PMDP_HUGE_GET_AND_CLEAR static inline pmd_t pmdp_huge_get_and_clear(struct mm_struct *mm, unsigned long addr, pmd_t *pmdp) { pmd_t pmd = native_pmdp_get_and_clear(pmdp); page_table_check_pmd_clear(mm, pmd); return pmd; } #define __HAVE_ARCH_PUDP_HUGE_GET_AND_CLEAR static inline pud_t pudp_huge_get_and_clear(struct mm_struct *mm, unsigned long addr, pud_t *pudp) { pud_t pud = native_pudp_get_and_clear(pudp); page_table_check_pud_clear(mm, pud); return pud; } #define __HAVE_ARCH_PMDP_SET_WRPROTECT static inline void pmdp_set_wrprotect(struct mm_struct *mm, unsigned long addr, pmd_t *pmdp) { /* * Avoid accidentally creating shadow stack PTEs * (Write=0,Dirty=1). Use cmpxchg() to prevent races with * the hardware setting Dirty=1. */ pmd_t old_pmd, new_pmd; old_pmd = READ_ONCE(*pmdp); do { new_pmd = pmd_wrprotect(old_pmd); } while (!try_cmpxchg((long *)pmdp, (long *)&old_pmd, *(long *)&new_pmd)); } #ifndef pmdp_establish #define pmdp_establish pmdp_establish static inline pmd_t pmdp_establish(struct vm_area_struct *vma, unsigned long address, pmd_t *pmdp, pmd_t pmd) { page_table_check_pmd_set(vma->vm_mm, pmdp, pmd); if (IS_ENABLED(CONFIG_SMP)) { return xchg(pmdp, pmd); } else { pmd_t old = *pmdp; WRITE_ONCE(*pmdp, pmd); return old; } } #endif #ifdef CONFIG_HAVE_ARCH_TRANSPARENT_HUGEPAGE_PUD static inline pud_t pudp_establish(struct vm_area_struct *vma, unsigned long address, pud_t *pudp, pud_t pud) { page_table_check_pud_set(vma->vm_mm, pudp, pud); if (IS_ENABLED(CONFIG_SMP)) { return xchg(pudp, pud); } else { pud_t old = *pudp; WRITE_ONCE(*pudp, pud); return old; } } #endif #define __HAVE_ARCH_PMDP_INVALIDATE_AD extern pmd_t pmdp_invalidate_ad(struct vm_area_struct *vma, unsigned long address, pmd_t *pmdp); pud_t pudp_invalidate(struct vm_area_struct *vma, unsigned long address, pud_t *pudp); /* * Page table pages are page-aligned. The lower half of the top * level is used for userspace and the top half for the kernel. * * Returns true for parts of the PGD that map userspace and * false for the parts that map the kernel. */ static inline bool pgdp_maps_userspace(void *__ptr) { unsigned long ptr = (unsigned long)__ptr; return (((ptr & ~PAGE_MASK) / sizeof(pgd_t)) < PGD_KERNEL_START); } #define pgd_leaf pgd_leaf static inline bool pgd_leaf(pgd_t pgd) { return false; } #ifdef CONFIG_MITIGATION_PAGE_TABLE_ISOLATION /* * All top-level MITIGATION_PAGE_TABLE_ISOLATION page tables are order-1 pages * (8k-aligned and 8k in size). The kernel one is at the beginning 4k and * the user one is in the last 4k. To switch between them, you * just need to flip the 12th bit in their addresses. */ #define PTI_PGTABLE_SWITCH_BIT PAGE_SHIFT /* * This generates better code than the inline assembly in * __set_bit(). */ static inline void *ptr_set_bit(void *ptr, int bit) { unsigned long __ptr = (unsigned long)ptr; __ptr |= BIT(bit); return (void *)__ptr; } static inline void *ptr_clear_bit(void *ptr, int bit) { unsigned long __ptr = (unsigned long)ptr; __ptr &= ~BIT(bit); return (void *)__ptr; } static inline pgd_t *kernel_to_user_pgdp(pgd_t *pgdp) { return ptr_set_bit(pgdp, PTI_PGTABLE_SWITCH_BIT); } static inline pgd_t *user_to_kernel_pgdp(pgd_t *pgdp) { return ptr_clear_bit(pgdp, PTI_PGTABLE_SWITCH_BIT); } static inline p4d_t *kernel_to_user_p4dp(p4d_t *p4dp) { return ptr_set_bit(p4dp, PTI_PGTABLE_SWITCH_BIT); } static inline p4d_t *user_to_kernel_p4dp(p4d_t *p4dp) { return ptr_clear_bit(p4dp, PTI_PGTABLE_SWITCH_BIT); } #endif /* CONFIG_MITIGATION_PAGE_TABLE_ISOLATION */ /* * clone_pgd_range(pgd_t *dst, pgd_t *src, int count); * * dst - pointer to pgd range anywhere on a pgd page * src - "" * count - the number of pgds to copy. * * dst and src can be on the same page, but the range must not overlap, * and must not cross a page boundary. */ static inline void clone_pgd_range(pgd_t *dst, pgd_t *src, int count) { memcpy(dst, src, count * sizeof(pgd_t)); #ifdef CONFIG_MITIGATION_PAGE_TABLE_ISOLATION if (!static_cpu_has(X86_FEATURE_PTI)) return; /* Clone the user space pgd as well */ memcpy(kernel_to_user_pgdp(dst), kernel_to_user_pgdp(src), count * sizeof(pgd_t)); #endif } #define PTE_SHIFT ilog2(PTRS_PER_PTE) static inline int page_level_shift(enum pg_level level) { return (PAGE_SHIFT - PTE_SHIFT) + level * PTE_SHIFT; } static inline unsigned long page_level_size(enum pg_level level) { return 1UL << page_level_shift(level); } static inline unsigned long page_level_mask(enum pg_level level) { return ~(page_level_size(level) - 1); } /* * The x86 doesn't have any external MMU info: the kernel page * tables contain all the necessary information. */ static inline void update_mmu_cache(struct vm_area_struct *vma, unsigned long addr, pte_t *ptep) { } static inline void update_mmu_cache_range(struct vm_fault *vmf, struct vm_area_struct *vma, unsigned long addr, pte_t *ptep, unsigned int nr) { } static inline void update_mmu_cache_pmd(struct vm_area_struct *vma, unsigned long addr, pmd_t *pmd) { } static inline void update_mmu_cache_pud(struct vm_area_struct *vma, unsigned long addr, pud_t *pud) { } static inline pte_t pte_swp_mkexclusive(pte_t pte) { return pte_set_flags(pte, _PAGE_SWP_EXCLUSIVE); } static inline int pte_swp_exclusive(pte_t pte) { return pte_flags(pte) & _PAGE_SWP_EXCLUSIVE; } static inline pte_t pte_swp_clear_exclusive(pte_t pte) { return pte_clear_flags(pte, _PAGE_SWP_EXCLUSIVE); } #ifdef CONFIG_HAVE_ARCH_SOFT_DIRTY static inline pte_t pte_swp_mksoft_dirty(pte_t pte) { return pte_set_flags(pte, _PAGE_SWP_SOFT_DIRTY); } static inline int pte_swp_soft_dirty(pte_t pte) { return pte_flags(pte) & _PAGE_SWP_SOFT_DIRTY; } static inline pte_t pte_swp_clear_soft_dirty(pte_t pte) { return pte_clear_flags(pte, _PAGE_SWP_SOFT_DIRTY); } #ifdef CONFIG_ARCH_ENABLE_THP_MIGRATION static inline pmd_t pmd_swp_mksoft_dirty(pmd_t pmd) { return pmd_set_flags(pmd, _PAGE_SWP_SOFT_DIRTY); } static inline int pmd_swp_soft_dirty(pmd_t pmd) { return pmd_flags(pmd) & _PAGE_SWP_SOFT_DIRTY; } static inline pmd_t pmd_swp_clear_soft_dirty(pmd_t pmd) { return pmd_clear_flags(pmd, _PAGE_SWP_SOFT_DIRTY); } #endif #endif #ifdef CONFIG_HAVE_ARCH_USERFAULTFD_WP static inline pte_t pte_swp_mkuffd_wp(pte_t pte) { return pte_set_flags(pte, _PAGE_SWP_UFFD_WP); } static inline int pte_swp_uffd_wp(pte_t pte) { return pte_flags(pte) & _PAGE_SWP_UFFD_WP; } static inline pte_t pte_swp_clear_uffd_wp(pte_t pte) { return pte_clear_flags(pte, _PAGE_SWP_UFFD_WP); } static inline pmd_t pmd_swp_mkuffd_wp(pmd_t pmd) { return pmd_set_flags(pmd, _PAGE_SWP_UFFD_WP); } static inline int pmd_swp_uffd_wp(pmd_t pmd) { return pmd_flags(pmd) & _PAGE_SWP_UFFD_WP; } static inline pmd_t pmd_swp_clear_uffd_wp(pmd_t pmd) { return pmd_clear_flags(pmd, _PAGE_SWP_UFFD_WP); } #endif /* CONFIG_HAVE_ARCH_USERFAULTFD_WP */ static inline u16 pte_flags_pkey(unsigned long pte_flags) { #ifdef CONFIG_X86_INTEL_MEMORY_PROTECTION_KEYS /* ifdef to avoid doing 59-bit shift on 32-bit values */ return (pte_flags & _PAGE_PKEY_MASK) >> _PAGE_BIT_PKEY_BIT0; #else return 0; #endif } static inline bool __pkru_allows_pkey(u16 pkey, bool write) { u32 pkru = read_pkru(); if (!__pkru_allows_read(pkru, pkey)) return false; if (write && !__pkru_allows_write(pkru, pkey)) return false; return true; } /* * 'pteval' can come from a PTE, PMD or PUD. We only check * _PAGE_PRESENT, _PAGE_USER, and _PAGE_RW in here which are the * same value on all 3 types. */ static inline bool __pte_access_permitted(unsigned long pteval, bool write) { unsigned long need_pte_bits = _PAGE_PRESENT|_PAGE_USER; /* * Write=0,Dirty=1 PTEs are shadow stack, which the kernel * shouldn't generally allow access to, but since they * are already Write=0, the below logic covers both cases. */ if (write) need_pte_bits |= _PAGE_RW; if ((pteval & need_pte_bits) != need_pte_bits) return 0; return __pkru_allows_pkey(pte_flags_pkey(pteval), write); } #define pte_access_permitted pte_access_permitted static inline bool pte_access_permitted(pte_t pte, bool write) { return __pte_access_permitted(pte_val(pte), write); } #define pmd_access_permitted pmd_access_permitted static inline bool pmd_access_permitted(pmd_t pmd, bool write) { return __pte_access_permitted(pmd_val(pmd), write); } #define pud_access_permitted pud_access_permitted static inline bool pud_access_permitted(pud_t pud, bool write) { return __pte_access_permitted(pud_val(pud), write); } #define __HAVE_ARCH_PFN_MODIFY_ALLOWED 1 extern bool pfn_modify_allowed(unsigned long pfn, pgprot_t prot); static inline bool arch_has_pfn_modify_check(void) { return boot_cpu_has_bug(X86_BUG_L1TF); } #define arch_check_zapped_pte arch_check_zapped_pte void arch_check_zapped_pte(struct vm_area_struct *vma, pte_t pte); #define arch_check_zapped_pmd arch_check_zapped_pmd void arch_check_zapped_pmd(struct vm_area_struct *vma, pmd_t pmd); #define arch_check_zapped_pud arch_check_zapped_pud void arch_check_zapped_pud(struct vm_area_struct *vma, pud_t pud); #ifdef CONFIG_XEN_PV #define arch_has_hw_nonleaf_pmd_young arch_has_hw_nonleaf_pmd_young static inline bool arch_has_hw_nonleaf_pmd_young(void) { return !cpu_feature_enabled(X86_FEATURE_XENPV); } #endif #ifdef CONFIG_PAGE_TABLE_CHECK static inline bool pte_user_accessible_page(pte_t pte) { return (pte_val(pte) & _PAGE_PRESENT) && (pte_val(pte) & _PAGE_USER); } static inline bool pmd_user_accessible_page(pmd_t pmd) { return pmd_leaf(pmd) && (pmd_val(pmd) & _PAGE_PRESENT) && (pmd_val(pmd) & _PAGE_USER); } static inline bool pud_user_accessible_page(pud_t pud) { return pud_leaf(pud) && (pud_val(pud) & _PAGE_PRESENT) && (pud_val(pud) & _PAGE_USER); } #endif #ifdef CONFIG_X86_SGX int arch_memory_failure(unsigned long pfn, int flags); #define arch_memory_failure arch_memory_failure bool arch_is_platform_page(u64 paddr); #define arch_is_platform_page arch_is_platform_page #endif /* * Use set_p*_safe(), and elide TLB flushing, when confident that *no* * TLB flush will be required as a result of the "set". For example, use * in scenarios where it is known ahead of time that the routine is * setting non-present entries, or re-setting an existing entry to the * same value. Otherwise, use the typical "set" helpers and flush the * TLB. */ #define set_pte_safe(ptep, pte) \ ({ \ WARN_ON_ONCE(pte_present(*ptep) && !pte_same(*ptep, pte)); \ set_pte(ptep, pte); \ }) #define set_pmd_safe(pmdp, pmd) \ ({ \ WARN_ON_ONCE(pmd_present(*pmdp) && !pmd_same(*pmdp, pmd)); \ set_pmd(pmdp, pmd); \ }) #define set_pud_safe(pudp, pud) \ ({ \ WARN_ON_ONCE(pud_present(*pudp) && !pud_same(*pudp, pud)); \ set_pud(pudp, pud); \ }) #define set_p4d_safe(p4dp, p4d) \ ({ \ WARN_ON_ONCE(p4d_present(*p4dp) && !p4d_same(*p4dp, p4d)); \ set_p4d(p4dp, p4d); \ }) #define set_pgd_safe(pgdp, pgd) \ ({ \ WARN_ON_ONCE(pgd_present(*pgdp) && !pgd_same(*pgdp, pgd)); \ set_pgd(pgdp, pgd); \ }) #endif /* __ASSEMBLY__ */ #endif /* _ASM_X86_PGTABLE_H */ |
| 17 17 17 17 17 17 27 27 27 27 27 27 27 27 27 27 27 27 27 17 17 17 17 | 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 | // SPDX-License-Identifier: GPL-2.0-only /* * Copyright 2002-2005, Instant802 Networks, Inc. * Copyright 2005-2006, Devicescape Software, Inc. * Copyright (c) 2006 Jiri Benc <jbenc@suse.cz> * Copyright 2017 Intel Deutschland GmbH * Copyright (C) 2019, 2022-2024 Intel Corporation */ #include <linux/kernel.h> #include <linux/rtnetlink.h> #include <linux/module.h> #include <linux/slab.h> #include "rate.h" #include "ieee80211_i.h" #include "debugfs.h" struct rate_control_alg { struct list_head list; const struct rate_control_ops *ops; }; static LIST_HEAD(rate_ctrl_algs); static DEFINE_MUTEX(rate_ctrl_mutex); static char *ieee80211_default_rc_algo = CONFIG_MAC80211_RC_DEFAULT; module_param(ieee80211_default_rc_algo, charp, 0644); MODULE_PARM_DESC(ieee80211_default_rc_algo, "Default rate control algorithm for mac80211 to use"); void rate_control_rate_init(struct link_sta_info *link_sta) { struct sta_info *sta = link_sta->sta; struct ieee80211_local *local = sta->sdata->local; struct rate_control_ref *ref = sta->rate_ctrl; struct ieee80211_sta *ista = &sta->sta; void *priv_sta = sta->rate_ctrl_priv; struct ieee80211_supported_band *sband; struct ieee80211_chanctx_conf *chanctx_conf; ieee80211_sta_init_nss(link_sta); if (!ref) return; /* SW rate control isn't supported with MLO right now */ if (WARN_ON(ieee80211_vif_is_mld(&sta->sdata->vif))) return; rcu_read_lock(); chanctx_conf = rcu_dereference(sta->sdata->vif.bss_conf.chanctx_conf); if (WARN_ON(!chanctx_conf)) { rcu_read_unlock(); return; } sband = local->hw.wiphy->bands[chanctx_conf->def.chan->band]; /* TODO: check for minstrel_s1g ? */ if (sband->band == NL80211_BAND_S1GHZ) { ieee80211_s1g_sta_rate_init(sta); rcu_read_unlock(); return; } spin_lock_bh(&sta->rate_ctrl_lock); ref->ops->rate_init(ref->priv, sband, &chanctx_conf->def, ista, priv_sta); spin_unlock_bh(&sta->rate_ctrl_lock); rcu_read_unlock(); set_sta_flag(sta, WLAN_STA_RATE_CONTROL); } void rate_control_rate_init_all_links(struct sta_info *sta) { int link_id; for (link_id = 0; link_id < ARRAY_SIZE(sta->link); link_id++) { struct link_sta_info *link_sta; link_sta = sdata_dereference(sta->link[link_id], sta->sdata); if (!link_sta) continue; rate_control_rate_init(link_sta); } } void rate_control_tx_status(struct ieee80211_local *local, struct ieee80211_tx_status *st) { struct rate_control_ref *ref = local->rate_ctrl; struct sta_info *sta = container_of(st->sta, struct sta_info, sta); void *priv_sta = sta->rate_ctrl_priv; struct ieee80211_supported_band *sband; if (!ref || !test_sta_flag(sta, WLAN_STA_RATE_CONTROL)) return; sband = local->hw.wiphy->bands[st->info->band]; spin_lock_bh(&sta->rate_ctrl_lock); if (ref->ops->tx_status_ext) ref->ops->tx_status_ext(ref->priv, sband, priv_sta, st); else if (st->skb) ref->ops->tx_status(ref->priv, sband, st->sta, priv_sta, st->skb); else WARN_ON_ONCE(1); spin_unlock_bh(&sta->rate_ctrl_lock); } void rate_control_rate_update(struct ieee80211_local *local, struct ieee80211_supported_band *sband, struct link_sta_info *link_sta, u32 changed) { struct rate_control_ref *ref = local->rate_ctrl; struct sta_info *sta = link_sta->sta; struct ieee80211_sta *ista = &sta->sta; void *priv_sta = sta->rate_ctrl_priv; struct ieee80211_chanctx_conf *chanctx_conf; if (ref && ref->ops->rate_update) { rcu_read_lock(); chanctx_conf = rcu_dereference(sta->sdata->vif.bss_conf.chanctx_conf); if (WARN_ON(!chanctx_conf)) { rcu_read_unlock(); return; } spin_lock_bh(&sta->rate_ctrl_lock); ref->ops->rate_update(ref->priv, sband, &chanctx_conf->def, ista, priv_sta, changed); spin_unlock_bh(&sta->rate_ctrl_lock); rcu_read_unlock(); } if (sta->uploaded) drv_link_sta_rc_update(local, sta->sdata, link_sta->pub, changed); } int ieee80211_rate_control_register(const struct rate_control_ops *ops) { struct rate_control_alg *alg; if (!ops->name) return -EINVAL; mutex_lock(&rate_ctrl_mutex); list_for_each_entry(alg, &rate_ctrl_algs, list) { if (!strcmp(alg->ops->name, ops->name)) { /* don't register an algorithm twice */ WARN_ON(1); mutex_unlock(&rate_ctrl_mutex); return -EALREADY; } } alg = kzalloc(sizeof(*alg), GFP_KERNEL); if (alg == NULL) { mutex_unlock(&rate_ctrl_mutex); return -ENOMEM; } alg->ops = ops; list_add_tail(&alg->list, &rate_ctrl_algs); mutex_unlock(&rate_ctrl_mutex); return 0; } EXPORT_SYMBOL(ieee80211_rate_control_register); void ieee80211_rate_control_unregister(const struct rate_control_ops *ops) { struct rate_control_alg *alg; mutex_lock(&rate_ctrl_mutex); list_for_each_entry(alg, &rate_ctrl_algs, list) { if (alg->ops == ops) { list_del(&alg->list); kfree(alg); break; } } mutex_unlock(&rate_ctrl_mutex); } EXPORT_SYMBOL(ieee80211_rate_control_unregister); static const struct rate_control_ops * ieee80211_try_rate_control_ops_get(const char *name) { struct rate_control_alg *alg; const struct rate_control_ops *ops = NULL; if (!name) return NULL; mutex_lock(&rate_ctrl_mutex); list_for_each_entry(alg, &rate_ctrl_algs, list) { if (!strcmp(alg->ops->name, name)) { ops = alg->ops; break; } } mutex_unlock(&rate_ctrl_mutex); return ops; } /* Get the rate control algorithm. */ static const struct rate_control_ops * ieee80211_rate_control_ops_get(const char *name) { const struct rate_control_ops *ops; const char *alg_name; kernel_param_lock(THIS_MODULE); if (!name) alg_name = ieee80211_default_rc_algo; else alg_name = name; ops = ieee80211_try_rate_control_ops_get(alg_name); if (!ops && name) /* try default if specific alg requested but not found */ ops = ieee80211_try_rate_control_ops_get(ieee80211_default_rc_algo); /* Note: check for > 0 is intentional to avoid clang warning */ if (!ops && (strlen(CONFIG_MAC80211_RC_DEFAULT) > 0)) /* try built-in one if specific alg requested but not found */ ops = ieee80211_try_rate_control_ops_get(CONFIG_MAC80211_RC_DEFAULT); kernel_param_unlock(THIS_MODULE); return ops; } #ifdef CONFIG_MAC80211_DEBUGFS static ssize_t rcname_read(struct file *file, char __user *userbuf, size_t count, loff_t *ppos) { struct rate_control_ref *ref = file->private_data; int len = strlen(ref->ops->name); return simple_read_from_buffer(userbuf, count, ppos, ref->ops->name, len); } const struct debugfs_short_fops rcname_ops = { .read = rcname_read, .llseek = default_llseek, }; #endif static struct rate_control_ref * rate_control_alloc(const char *name, struct ieee80211_local *local) { struct rate_control_ref *ref; ref = kmalloc(sizeof(struct rate_control_ref), GFP_KERNEL); if (!ref) return NULL; ref->ops = ieee80211_rate_control_ops_get(name); if (!ref->ops) goto free; ref->priv = ref->ops->alloc(&local->hw); if (!ref->priv) goto free; return ref; free: kfree(ref); return NULL; } static void rate_control_free(struct ieee80211_local *local, struct rate_control_ref *ctrl_ref) { ctrl_ref->ops->free(ctrl_ref->priv); #ifdef CONFIG_MAC80211_DEBUGFS debugfs_remove_recursive(local->debugfs.rcdir); local->debugfs.rcdir = NULL; #endif kfree(ctrl_ref); } void ieee80211_check_rate_mask(struct ieee80211_link_data *link) { struct ieee80211_sub_if_data *sdata = link->sdata; struct ieee80211_local *local = sdata->local; struct ieee80211_supported_band *sband; u32 user_mask, basic_rates = link->conf->basic_rates; enum nl80211_band band; if (WARN_ON(!link->conf->chanreq.oper.chan)) return; band = link->conf->chanreq.oper.chan->band; if (band == NL80211_BAND_S1GHZ) { /* TODO */ return; } if (WARN_ON_ONCE(!basic_rates)) return; user_mask = sdata->rc_rateidx_mask[band]; sband = local->hw.wiphy->bands[band]; if (user_mask & basic_rates) return; sdata_dbg(sdata, "no overlap between basic rates (0x%x) and user mask (0x%x on band %d) - clearing the latter", basic_rates, user_mask, band); sdata->rc_rateidx_mask[band] = (1 << sband->n_bitrates) - 1; } static bool rc_no_data_or_no_ack_use_min(struct ieee80211_tx_rate_control *txrc) { struct sk_buff *skb = txrc->skb; struct ieee80211_tx_info *info = IEEE80211_SKB_CB(skb); return (info->flags & (IEEE80211_TX_CTL_NO_ACK | IEEE80211_TX_CTL_USE_MINRATE)) || !ieee80211_is_tx_data(skb); } static void rc_send_low_basicrate(struct ieee80211_tx_rate *rate, u32 basic_rates, struct ieee80211_supported_band *sband) { u8 i; if (sband->band == NL80211_BAND_S1GHZ) { /* TODO */ rate->flags |= IEEE80211_TX_RC_S1G_MCS; rate->idx = 0; return; } if (basic_rates == 0) return; /* assume basic rates unknown and accept rate */ if (rate->idx < 0) return; if (basic_rates & (1 << rate->idx)) return; /* selected rate is a basic rate */ for (i = rate->idx + 1; i <= sband->n_bitrates; i++) { if (basic_rates & (1 << i)) { rate->idx = i; return; } } /* could not find a basic rate; use original selection */ } static void __rate_control_send_low(struct ieee80211_hw *hw, struct ieee80211_supported_band *sband, struct ieee80211_sta *sta, struct ieee80211_tx_info *info, u32 rate_mask) { int i; u32 rate_flags = ieee80211_chandef_rate_flags(&hw->conf.chandef); if (sband->band == NL80211_BAND_S1GHZ) { info->control.rates[0].flags |= IEEE80211_TX_RC_S1G_MCS; info->control.rates[0].idx = 0; return; } if ((sband->band == NL80211_BAND_2GHZ) && (info->flags & IEEE80211_TX_CTL_NO_CCK_RATE)) rate_flags |= IEEE80211_RATE_ERP_G; info->control.rates[0].idx = 0; for (i = 0; i < sband->n_bitrates; i++) { if (!(rate_mask & BIT(i))) continue; if ((rate_flags & sband->bitrates[i].flags) != rate_flags) continue; if (!rate_supported(sta, sband->band, i)) continue; info->control.rates[0].idx = i; break; } WARN_ONCE(i == sband->n_bitrates, "no supported rates for sta %pM (0x%x, band %d) in rate_mask 0x%x with flags 0x%x\n", sta ? sta->addr : NULL, sta ? sta->deflink.supp_rates[sband->band] : -1, sband->band, rate_mask, rate_flags); info->control.rates[0].count = (info->flags & IEEE80211_TX_CTL_NO_ACK) ? 1 : hw->max_rate_tries; info->control.skip_table = 1; } static bool rate_control_send_low(struct ieee80211_sta *pubsta, struct ieee80211_tx_rate_control *txrc) { struct ieee80211_tx_info *info = IEEE80211_SKB_CB(txrc->skb); struct ieee80211_supported_band *sband = txrc->sband; struct sta_info *sta; int mcast_rate; bool use_basicrate = false; if (!pubsta || rc_no_data_or_no_ack_use_min(txrc)) { __rate_control_send_low(txrc->hw, sband, pubsta, info, txrc->rate_idx_mask); if (!pubsta && txrc->bss) { mcast_rate = txrc->bss_conf->mcast_rate[sband->band]; if (mcast_rate > 0) { info->control.rates[0].idx = mcast_rate - 1; return true; } use_basicrate = true; } else if (pubsta) { sta = container_of(pubsta, struct sta_info, sta); if (ieee80211_vif_is_mesh(&sta->sdata->vif)) use_basicrate = true; } if (use_basicrate) rc_send_low_basicrate(&info->control.rates[0], txrc->bss_conf->basic_rates, sband); return true; } return false; } static bool rate_idx_match_legacy_mask(s8 *rate_idx, int n_bitrates, u32 mask) { int j; /* See whether the selected rate or anything below it is allowed. */ for (j = *rate_idx; j >= 0; j--) { if (mask & (1 << j)) { /* Okay, found a suitable rate. Use it. */ *rate_idx = j; return true; } } /* Try to find a higher rate that would be allowed */ for (j = *rate_idx + 1; j < n_bitrates; j++) { if (mask & (1 << j)) { /* Okay, found a suitable rate. Use it. */ *rate_idx = j; return true; } } return false; } static bool rate_idx_match_mcs_mask(s8 *rate_idx, u8 *mcs_mask) { int i, j; int ridx, rbit; ridx = *rate_idx / 8; rbit = *rate_idx % 8; /* sanity check */ if (ridx < 0 || ridx >= IEEE80211_HT_MCS_MASK_LEN) return false; /* See whether the selected rate or anything below it is allowed. */ for (i = ridx; i >= 0; i--) { for (j = rbit; j >= 0; j--) if (mcs_mask[i] & BIT(j)) { *rate_idx = i * 8 + j; return true; } rbit = 7; } /* Try to find a higher rate that would be allowed */ ridx = (*rate_idx + 1) / 8; rbit = (*rate_idx + 1) % 8; for (i = ridx; i < IEEE80211_HT_MCS_MASK_LEN; i++) { for (j = rbit; j < 8; j++) if (mcs_mask[i] & BIT(j)) { *rate_idx = i * 8 + j; return true; } rbit = 0; } return false; } static bool rate_idx_match_vht_mcs_mask(s8 *rate_idx, u16 *vht_mask) { int i, j; int ridx, rbit; ridx = *rate_idx >> 4; rbit = *rate_idx & 0xf; if (ridx < 0 || ridx >= NL80211_VHT_NSS_MAX) return false; /* See whether the selected rate or anything below it is allowed. */ for (i = ridx; i >= 0; i--) { for (j = rbit; j >= 0; j--) { if (vht_mask[i] & BIT(j)) { *rate_idx = (i << 4) | j; return true; } } rbit = 15; } /* Try to find a higher rate that would be allowed */ ridx = (*rate_idx + 1) >> 4; rbit = (*rate_idx + 1) & 0xf; for (i = ridx; i < NL80211_VHT_NSS_MAX; i++) { for (j = rbit; j < 16; j++) { if (vht_mask[i] & BIT(j)) { *rate_idx = (i << 4) | j; return true; } } rbit = 0; } return false; } static void rate_idx_match_mask(s8 *rate_idx, u16 *rate_flags, struct ieee80211_supported_band *sband, enum nl80211_chan_width chan_width, u32 mask, u8 mcs_mask[IEEE80211_HT_MCS_MASK_LEN], u16 vht_mask[NL80211_VHT_NSS_MAX]) { if (*rate_flags & IEEE80211_TX_RC_VHT_MCS) { /* handle VHT rates */ if (rate_idx_match_vht_mcs_mask(rate_idx, vht_mask)) return; *rate_idx = 0; /* keep protection flags */ *rate_flags &= (IEEE80211_TX_RC_USE_RTS_CTS | IEEE80211_TX_RC_USE_CTS_PROTECT | IEEE80211_TX_RC_USE_SHORT_PREAMBLE); *rate_flags |= IEEE80211_TX_RC_MCS; if (chan_width == NL80211_CHAN_WIDTH_40) *rate_flags |= IEEE80211_TX_RC_40_MHZ_WIDTH; if (rate_idx_match_mcs_mask(rate_idx, mcs_mask)) return; /* also try the legacy rates. */ *rate_flags &= ~(IEEE80211_TX_RC_MCS | IEEE80211_TX_RC_40_MHZ_WIDTH); if (rate_idx_match_legacy_mask(rate_idx, sband->n_bitrates, mask)) return; } else if (*rate_flags & IEEE80211_TX_RC_MCS) { /* handle HT rates */ if (rate_idx_match_mcs_mask(rate_idx, mcs_mask)) return; /* also try the legacy rates. */ *rate_idx = 0; /* keep protection flags */ *rate_flags &= (IEEE80211_TX_RC_USE_RTS_CTS | IEEE80211_TX_RC_USE_CTS_PROTECT | IEEE80211_TX_RC_USE_SHORT_PREAMBLE); if (rate_idx_match_legacy_mask(rate_idx, sband->n_bitrates, mask)) return; } else { /* handle legacy rates */ if (rate_idx_match_legacy_mask(rate_idx, sband->n_bitrates, mask)) return; /* if HT BSS, and we handle a data frame, also try HT rates */ switch (chan_width) { case NL80211_CHAN_WIDTH_20_NOHT: case NL80211_CHAN_WIDTH_5: case NL80211_CHAN_WIDTH_10: return; default: break; } *rate_idx = 0; /* keep protection flags */ *rate_flags &= (IEEE80211_TX_RC_USE_RTS_CTS | IEEE80211_TX_RC_USE_CTS_PROTECT | IEEE80211_TX_RC_USE_SHORT_PREAMBLE); *rate_flags |= IEEE80211_TX_RC_MCS; if (chan_width == NL80211_CHAN_WIDTH_40) *rate_flags |= IEEE80211_TX_RC_40_MHZ_WIDTH; if (rate_idx_match_mcs_mask(rate_idx, mcs_mask)) return; } /* * Uh.. No suitable rate exists. This should not really happen with * sane TX rate mask configurations. However, should someone manage to * configure supported rates and TX rate mask in incompatible way, * allow the frame to be transmitted with whatever the rate control * selected. */ } static void rate_fixup_ratelist(struct ieee80211_vif *vif, struct ieee80211_supported_band *sband, struct ieee80211_tx_info *info, struct ieee80211_tx_rate *rates, int max_rates) { struct ieee80211_rate *rate; bool inval = false; int i; /* * Set up the RTS/CTS rate as the fastest basic rate * that is not faster than the data rate unless there * is no basic rate slower than the data rate, in which * case we pick the slowest basic rate * * XXX: Should this check all retry rates? */ if (!(rates[0].flags & (IEEE80211_TX_RC_MCS | IEEE80211_TX_RC_VHT_MCS))) { u32 basic_rates = vif->bss_conf.basic_rates; s8 baserate = basic_rates ? ffs(basic_rates) - 1 : 0; rate = &sband->bitrates[rates[0].idx]; for (i = 0; i < sband->n_bitrates; i++) { /* must be a basic rate */ if (!(basic_rates & BIT(i))) continue; /* must not be faster than the data rate */ if (sband->bitrates[i].bitrate > rate->bitrate) continue; /* maximum */ if (sband->bitrates[baserate].bitrate < sband->bitrates[i].bitrate) baserate = i; } info->control.rts_cts_rate_idx = baserate; } for (i = 0; i < max_rates; i++) { /* * make sure there's no valid rate following * an invalid one, just in case drivers don't * take the API seriously to stop at -1. */ if (inval) { rates[i].idx = -1; continue; } if (rates[i].idx < 0) { inval = true; continue; } /* * For now assume MCS is already set up correctly, this * needs to be fixed. */ if (rates[i].flags & IEEE80211_TX_RC_MCS) { WARN_ON(rates[i].idx > 76); if (!(rates[i].flags & IEEE80211_TX_RC_USE_RTS_CTS) && info->control.use_cts_prot) rates[i].flags |= IEEE80211_TX_RC_USE_CTS_PROTECT; continue; } if (rates[i].flags & IEEE80211_TX_RC_VHT_MCS) { WARN_ON(ieee80211_rate_get_vht_mcs(&rates[i]) > 9); continue; } /* set up RTS protection if desired */ if (info->control.use_rts) { rates[i].flags |= IEEE80211_TX_RC_USE_RTS_CTS; info->control.use_cts_prot = false; } /* RC is busted */ if (WARN_ON_ONCE(rates[i].idx >= sband->n_bitrates)) { rates[i].idx = -1; continue; } rate = &sband->bitrates[rates[i].idx]; /* set up short preamble */ if (info->control.short_preamble && rate->flags & IEEE80211_RATE_SHORT_PREAMBLE) rates[i].flags |= IEEE80211_TX_RC_USE_SHORT_PREAMBLE; /* set up G protection */ if (!(rates[i].flags & IEEE80211_TX_RC_USE_RTS_CTS) && info->control.use_cts_prot && rate->flags & IEEE80211_RATE_ERP_G) rates[i].flags |= IEEE80211_TX_RC_USE_CTS_PROTECT; } } static void rate_control_fill_sta_table(struct ieee80211_sta *sta, struct ieee80211_tx_info *info, struct ieee80211_tx_rate *rates, int max_rates) { struct ieee80211_sta_rates *ratetbl = NULL; int i; if (sta && !info->control.skip_table) ratetbl = rcu_dereference(sta->rates); /* Fill remaining rate slots with data from the sta rate table. */ max_rates = min_t(int, max_rates, IEEE80211_TX_RATE_TABLE_SIZE); for (i = 0; i < max_rates; i++) { if (i < ARRAY_SIZE(info->control.rates) && info->control.rates[i].idx >= 0 && info->control.rates[i].count) { if (rates != info->control.rates) rates[i] = info->control.rates[i]; } else if (ratetbl) { rates[i].idx = ratetbl->rate[i].idx; rates[i].flags = ratetbl->rate[i].flags; if (info->control.use_rts) rates[i].count = ratetbl->rate[i].count_rts; else if (info->control.use_cts_prot) rates[i].count = ratetbl->rate[i].count_cts; else rates[i].count = ratetbl->rate[i].count; } else { rates[i].idx = -1; rates[i].count = 0; } if (rates[i].idx < 0 || !rates[i].count) break; } } static bool rate_control_cap_mask(struct ieee80211_sub_if_data *sdata, struct ieee80211_supported_band *sband, struct ieee80211_sta *sta, u32 *mask, u8 mcs_mask[IEEE80211_HT_MCS_MASK_LEN], u16 vht_mask[NL80211_VHT_NSS_MAX]) { u32 i, flags; *mask = sdata->rc_rateidx_mask[sband->band]; flags = ieee80211_chandef_rate_flags(&sdata->vif.bss_conf.chanreq.oper); for (i = 0; i < sband->n_bitrates; i++) { if ((flags & sband->bitrates[i].flags) != flags) *mask &= ~BIT(i); } if (*mask == (1 << sband->n_bitrates) - 1 && !sdata->rc_has_mcs_mask[sband->band] && !sdata->rc_has_vht_mcs_mask[sband->band]) return false; if (sdata->rc_has_mcs_mask[sband->band]) memcpy(mcs_mask, sdata->rc_rateidx_mcs_mask[sband->band], IEEE80211_HT_MCS_MASK_LEN); else memset(mcs_mask, 0xff, IEEE80211_HT_MCS_MASK_LEN); if (sdata->rc_has_vht_mcs_mask[sband->band]) memcpy(vht_mask, sdata->rc_rateidx_vht_mcs_mask[sband->band], sizeof(u16) * NL80211_VHT_NSS_MAX); else memset(vht_mask, 0xff, sizeof(u16) * NL80211_VHT_NSS_MAX); if (sta) { __le16 sta_vht_cap; u16 sta_vht_mask[NL80211_VHT_NSS_MAX]; /* Filter out rates that the STA does not support */ *mask &= sta->deflink.supp_rates[sband->band]; for (i = 0; i < IEEE80211_HT_MCS_MASK_LEN; i++) mcs_mask[i] &= sta->deflink.ht_cap.mcs.rx_mask[i]; sta_vht_cap = sta->deflink.vht_cap.vht_mcs.rx_mcs_map; ieee80211_get_vht_mask_from_cap(sta_vht_cap, sta_vht_mask); for (i = 0; i < NL80211_VHT_NSS_MAX; i++) vht_mask[i] &= sta_vht_mask[i]; } return true; } static void rate_control_apply_mask_ratetbl(struct sta_info *sta, struct ieee80211_supported_band *sband, struct ieee80211_sta_rates *rates) { int i; u32 mask; u8 mcs_mask[IEEE80211_HT_MCS_MASK_LEN]; u16 vht_mask[NL80211_VHT_NSS_MAX]; enum nl80211_chan_width chan_width; if (!rate_control_cap_mask(sta->sdata, sband, &sta->sta, &mask, mcs_mask, vht_mask)) return; chan_width = sta->sdata->vif.bss_conf.chanreq.oper.width; for (i = 0; i < IEEE80211_TX_RATE_TABLE_SIZE; i++) { if (rates->rate[i].idx < 0) break; rate_idx_match_mask(&rates->rate[i].idx, &rates->rate[i].flags, sband, chan_width, mask, mcs_mask, vht_mask); } } static void rate_control_apply_mask(struct ieee80211_sub_if_data *sdata, struct ieee80211_sta *sta, struct ieee80211_supported_band *sband, struct ieee80211_tx_rate *rates, int max_rates) { enum nl80211_chan_width chan_width; u8 mcs_mask[IEEE80211_HT_MCS_MASK_LEN]; u32 mask; u16 rate_flags, vht_mask[NL80211_VHT_NSS_MAX]; int i; /* * Try to enforce the rateidx mask the user wanted. skip this if the * default mask (allow all rates) is used to save some processing for * the common case. */ if (!rate_control_cap_mask(sdata, sband, sta, &mask, mcs_mask, vht_mask)) return; /* * Make sure the rate index selected for each TX rate is * included in the configured mask and change the rate indexes * if needed. */ chan_width = sdata->vif.bss_conf.chanreq.oper.width; for (i = 0; i < max_rates; i++) { /* Skip invalid rates */ if (rates[i].idx < 0) break; rate_flags = rates[i].flags; rate_idx_match_mask(&rates[i].idx, &rate_flags, sband, chan_width, mask, mcs_mask, vht_mask); rates[i].flags = rate_flags; } } void ieee80211_get_tx_rates(struct ieee80211_vif *vif, struct ieee80211_sta *sta, struct sk_buff *skb, struct ieee80211_tx_rate *dest, int max_rates) { struct ieee80211_sub_if_data *sdata; struct ieee80211_tx_info *info = IEEE80211_SKB_CB(skb); struct ieee80211_supported_band *sband; u32 mask = ~0; rate_control_fill_sta_table(sta, info, dest, max_rates); if (!vif) return; sdata = vif_to_sdata(vif); sband = sdata->local->hw.wiphy->bands[info->band]; if (ieee80211_is_tx_data(skb)) rate_control_apply_mask(sdata, sta, sband, dest, max_rates); if (!(info->control.flags & IEEE80211_TX_CTRL_DONT_USE_RATE_MASK)) mask = sdata->rc_rateidx_mask[info->band]; if (dest[0].idx < 0) __rate_control_send_low(&sdata->local->hw, sband, sta, info, mask); if (sta) rate_fixup_ratelist(vif, sband, info, dest, max_rates); } EXPORT_SYMBOL(ieee80211_get_tx_rates); void rate_control_get_rate(struct ieee80211_sub_if_data *sdata, struct sta_info *sta, struct ieee80211_tx_rate_control *txrc) { struct rate_control_ref *ref = sdata->local->rate_ctrl; void *priv_sta = NULL; struct ieee80211_sta *ista = NULL; struct ieee80211_tx_info *info = IEEE80211_SKB_CB(txrc->skb); int i; for (i = 0; i < IEEE80211_TX_MAX_RATES; i++) { info->control.rates[i].idx = -1; info->control.rates[i].flags = 0; info->control.rates[i].count = 0; } if (rate_control_send_low(sta ? &sta->sta : NULL, txrc)) return; if (ieee80211_hw_check(&sdata->local->hw, HAS_RATE_CONTROL)) return; if (sta && test_sta_flag(sta, WLAN_STA_RATE_CONTROL)) { ista = &sta->sta; priv_sta = sta->rate_ctrl_priv; } if (ista) { spin_lock_bh(&sta->rate_ctrl_lock); ref->ops->get_rate(ref->priv, ista, priv_sta, txrc); spin_unlock_bh(&sta->rate_ctrl_lock); } else { rate_control_send_low(NULL, txrc); } if (ieee80211_hw_check(&sdata->local->hw, SUPPORTS_RC_TABLE)) return; ieee80211_get_tx_rates(&sdata->vif, ista, txrc->skb, info->control.rates, ARRAY_SIZE(info->control.rates)); } int rate_control_set_rates(struct ieee80211_hw *hw, struct ieee80211_sta *pubsta, struct ieee80211_sta_rates *rates) { struct sta_info *sta = container_of(pubsta, struct sta_info, sta); struct ieee80211_sta_rates *old; struct ieee80211_supported_band *sband; sband = ieee80211_get_sband(sta->sdata); if (!sband) return -EINVAL; rate_control_apply_mask_ratetbl(sta, sband, rates); /* * mac80211 guarantees that this function will not be called * concurrently, so the following RCU access is safe, even without * extra locking. This can not be checked easily, so we just set * the condition to true. */ old = rcu_dereference_protected(pubsta->rates, true); rcu_assign_pointer(pubsta->rates, rates); if (old) kfree_rcu(old, rcu_head); if (sta->uploaded) drv_sta_rate_tbl_update(hw_to_local(hw), sta->sdata, pubsta); ieee80211_sta_set_expected_throughput(pubsta, sta_get_expected_throughput(sta)); return 0; } EXPORT_SYMBOL(rate_control_set_rates); int ieee80211_init_rate_ctrl_alg(struct ieee80211_local *local, const char *name) { struct rate_control_ref *ref; ASSERT_RTNL(); if (local->open_count) return -EBUSY; if (ieee80211_hw_check(&local->hw, HAS_RATE_CONTROL)) { if (WARN_ON(!local->ops->set_rts_threshold)) return -EINVAL; return 0; } ref = rate_control_alloc(name, local); if (!ref) { wiphy_warn(local->hw.wiphy, "Failed to select rate control algorithm\n"); return -ENOENT; } WARN_ON(local->rate_ctrl); local->rate_ctrl = ref; wiphy_debug(local->hw.wiphy, "Selected rate control algorithm '%s'\n", ref->ops->name); return 0; } void rate_control_deinitialize(struct ieee80211_local *local) { struct rate_control_ref *ref; ref = local->rate_ctrl; if (!ref) return; local->rate_ctrl = NULL; rate_control_free(local, ref); } |
| 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 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _LINUX_BITOPS_H #define _LINUX_BITOPS_H #include <asm/types.h> #include <linux/bits.h> #include <linux/typecheck.h> #include <uapi/linux/kernel.h> #define BITS_PER_TYPE(type) (sizeof(type) * BITS_PER_BYTE) #define BITS_TO_LONGS(nr) __KERNEL_DIV_ROUND_UP(nr, BITS_PER_TYPE(long)) #define BITS_TO_U64(nr) __KERNEL_DIV_ROUND_UP(nr, BITS_PER_TYPE(u64)) #define BITS_TO_U32(nr) __KERNEL_DIV_ROUND_UP(nr, BITS_PER_TYPE(u32)) #define BITS_TO_BYTES(nr) __KERNEL_DIV_ROUND_UP(nr, BITS_PER_TYPE(char)) #define BYTES_TO_BITS(nb) ((nb) * BITS_PER_BYTE) extern unsigned int __sw_hweight8(unsigned int w); extern unsigned int __sw_hweight16(unsigned int w); extern unsigned int __sw_hweight32(unsigned int w); extern unsigned long __sw_hweight64(__u64 w); /* * Defined here because those may be needed by architecture-specific static * inlines. */ #include <asm-generic/bitops/generic-non-atomic.h> /* * Many architecture-specific non-atomic bitops contain inline asm code and due * to that the compiler can't optimize them to compile-time expressions or * constants. In contrary, generic_*() helpers are defined in pure C and * compilers optimize them just well. * Therefore, to make `unsigned long foo = 0; __set_bit(BAR, &foo)` effectively * equal to `unsigned long foo = BIT(BAR)`, pick the generic C alternative when * the arguments can be resolved at compile time. That expression itself is a * constant and doesn't bring any functional changes to the rest of cases. * The casts to `uintptr_t` are needed to mitigate `-Waddress` warnings when * passing a bitmap from .bss or .data (-> `!!addr` is always true). */ #define bitop(op, nr, addr) \ ((__builtin_constant_p(nr) && \ __builtin_constant_p((uintptr_t)(addr) != (uintptr_t)NULL) && \ (uintptr_t)(addr) != (uintptr_t)NULL && \ __builtin_constant_p(*(const unsigned long *)(addr))) ? \ const##op(nr, addr) : op(nr, addr)) /* * The following macros are non-atomic versions of their non-underscored * counterparts. */ #define __set_bit(nr, addr) bitop(___set_bit, nr, addr) #define __clear_bit(nr, addr) bitop(___clear_bit, nr, addr) #define __change_bit(nr, addr) bitop(___change_bit, nr, addr) #define __test_and_set_bit(nr, addr) bitop(___test_and_set_bit, nr, addr) #define __test_and_clear_bit(nr, addr) bitop(___test_and_clear_bit, nr, addr) #define __test_and_change_bit(nr, addr) bitop(___test_and_change_bit, nr, addr) #define test_bit(nr, addr) bitop(_test_bit, nr, addr) #define test_bit_acquire(nr, addr) bitop(_test_bit_acquire, nr, addr) /* * Include this here because some architectures need generic_ffs/fls in * scope */ #include <asm/bitops.h> /* Check that the bitops prototypes are sane */ #define __check_bitop_pr(name) \ static_assert(__same_type(arch_##name, generic_##name) && \ __same_type(const_##name, generic_##name) && \ __same_type(_##name, generic_##name)) __check_bitop_pr(__set_bit); __check_bitop_pr(__clear_bit); __check_bitop_pr(__change_bit); __check_bitop_pr(__test_and_set_bit); __check_bitop_pr(__test_and_clear_bit); __check_bitop_pr(__test_and_change_bit); __check_bitop_pr(test_bit); __check_bitop_pr(test_bit_acquire); #undef __check_bitop_pr static inline int get_bitmask_order(unsigned int count) { int order; order = fls(count); return order; /* We could be slightly more clever with -1 here... */ } static __always_inline unsigned long hweight_long(unsigned long w) { return sizeof(w) == 4 ? hweight32(w) : hweight64((__u64)w); } /** * rol64 - rotate a 64-bit value left * @word: value to rotate * @shift: bits to roll */ static inline __u64 rol64(__u64 word, unsigned int shift) { return (word << (shift & 63)) | (word >> ((-shift) & 63)); } /** * ror64 - rotate a 64-bit value right * @word: value to rotate * @shift: bits to roll */ static inline __u64 ror64(__u64 word, unsigned int shift) { return (word >> (shift & 63)) | (word << ((-shift) & 63)); } /** * rol32 - rotate a 32-bit value left * @word: value to rotate * @shift: bits to roll */ static inline __u32 rol32(__u32 word, unsigned int shift) { return (word << (shift & 31)) | (word >> ((-shift) & 31)); } /** * ror32 - rotate a 32-bit value right * @word: value to rotate * @shift: bits to roll */ static inline __u32 ror32(__u32 word, unsigned int shift) { return (word >> (shift & 31)) | (word << ((-shift) & 31)); } /** * rol16 - rotate a 16-bit value left * @word: value to rotate * @shift: bits to roll */ static inline __u16 rol16(__u16 word, unsigned int shift) { return (word << (shift & 15)) | (word >> ((-shift) & 15)); } /** * ror16 - rotate a 16-bit value right * @word: value to rotate * @shift: bits to roll */ static inline __u16 ror16(__u16 word, unsigned int shift) { return (word >> (shift & 15)) | (word << ((-shift) & 15)); } /** * rol8 - rotate an 8-bit value left * @word: value to rotate * @shift: bits to roll */ static inline __u8 rol8(__u8 word, unsigned int shift) { return (word << (shift & 7)) | (word >> ((-shift) & 7)); } /** * ror8 - rotate an 8-bit value right * @word: value to rotate * @shift: bits to roll */ static inline __u8 ror8(__u8 word, unsigned int shift) { return (word >> (shift & 7)) | (word << ((-shift) & 7)); } /** * sign_extend32 - sign extend a 32-bit value using specified bit as sign-bit * @value: value to sign extend * @index: 0 based bit index (0<=index<32) to sign bit * * This is safe to use for 16- and 8-bit types as well. */ static __always_inline __s32 sign_extend32(__u32 value, int index) { __u8 shift = 31 - index; return (__s32)(value << shift) >> shift; } /** * sign_extend64 - sign extend a 64-bit value using specified bit as sign-bit * @value: value to sign extend * @index: 0 based bit index (0<=index<64) to sign bit */ static __always_inline __s64 sign_extend64(__u64 value, int index) { __u8 shift = 63 - index; return (__s64)(value << shift) >> shift; } static inline unsigned int fls_long(unsigned long l) { if (sizeof(l) == 4) return fls(l); return fls64(l); } static inline int get_count_order(unsigned int count) { if (count == 0) return -1; return fls(--count); } /** * get_count_order_long - get order after rounding @l up to power of 2 * @l: parameter * * it is same as get_count_order() but with long type parameter */ static inline int get_count_order_long(unsigned long l) { if (l == 0UL) return -1; return (int)fls_long(--l); } /** * parity8 - get the parity of an u8 value * @value: the value to be examined * * Determine the parity of the u8 argument. * * Returns: * 0 for even parity, 1 for odd parity * * Note: This function informs you about the current parity. Example to bail * out when parity is odd: * * if (parity8(val) == 1) * return -EBADMSG; * * If you need to calculate a parity bit, you need to draw the conclusion from * this result yourself. Example to enforce odd parity, parity bit is bit 7: * * if (parity8(val) == 0) * val ^= BIT(7); */ static inline int parity8(u8 val) { /* * One explanation of this algorithm: * https://funloop.org/codex/problem/parity/README.html */ val ^= val >> 4; return (0x6996 >> (val & 0xf)) & 1; } /** * __ffs64 - find first set bit in a 64 bit word * @word: The 64 bit word * * On 64 bit arches this is a synonym for __ffs * The result is not defined if no bits are set, so check that @word * is non-zero before calling this. */ static inline unsigned int __ffs64(u64 word) { #if BITS_PER_LONG == 32 if (((u32)word) == 0UL) return __ffs((u32)(word >> 32)) + 32; #elif BITS_PER_LONG != 64 #error BITS_PER_LONG not 32 or 64 #endif return __ffs((unsigned long)word); } /** * fns - find N'th set bit in a word * @word: The word to search * @n: Bit to find */ static inline unsigned int fns(unsigned long word, unsigned int n) { while (word && n--) word &= word - 1; return word ? __ffs(word) : BITS_PER_LONG; } /** * assign_bit - Assign value to a bit in memory * @nr: the bit to set * @addr: the address to start counting from * @value: the value to assign */ #define assign_bit(nr, addr, value) \ ((value) ? set_bit((nr), (addr)) : clear_bit((nr), (addr))) #define __assign_bit(nr, addr, value) \ ((value) ? __set_bit((nr), (addr)) : __clear_bit((nr), (addr))) /** * __ptr_set_bit - Set bit in a pointer's value * @nr: the bit to set * @addr: the address of the pointer variable * * Example: * void *p = foo(); * __ptr_set_bit(bit, &p); */ #define __ptr_set_bit(nr, addr) \ ({ \ typecheck_pointer(*(addr)); \ __set_bit(nr, (unsigned long *)(addr)); \ }) /** * __ptr_clear_bit - Clear bit in a pointer's value * @nr: the bit to clear * @addr: the address of the pointer variable * * Example: * void *p = foo(); * __ptr_clear_bit(bit, &p); */ #define __ptr_clear_bit(nr, addr) \ ({ \ typecheck_pointer(*(addr)); \ __clear_bit(nr, (unsigned long *)(addr)); \ }) /** * __ptr_test_bit - Test bit in a pointer's value * @nr: the bit to test * @addr: the address of the pointer variable * * Example: * void *p = foo(); * if (__ptr_test_bit(bit, &p)) { * ... * } else { * ... * } */ #define __ptr_test_bit(nr, addr) \ ({ \ typecheck_pointer(*(addr)); \ test_bit(nr, (unsigned long *)(addr)); \ }) #ifdef __KERNEL__ #ifndef set_mask_bits #define set_mask_bits(ptr, mask, bits) \ ({ \ const typeof(*(ptr)) mask__ = (mask), bits__ = (bits); \ typeof(*(ptr)) old__, new__; \ \ old__ = READ_ONCE(*(ptr)); \ do { \ new__ = (old__ & ~mask__) | bits__; \ } while (!try_cmpxchg(ptr, &old__, new__)); \ \ old__; \ }) #endif #ifndef bit_clear_unless #define bit_clear_unless(ptr, clear, test) \ ({ \ const typeof(*(ptr)) clear__ = (clear), test__ = (test);\ typeof(*(ptr)) old__, new__; \ \ old__ = READ_ONCE(*(ptr)); \ do { \ if (old__ & test__) \ break; \ new__ = old__ & ~clear__; \ } while (!try_cmpxchg(ptr, &old__, new__)); \ \ !(old__ & test__); \ }) #endif #endif /* __KERNEL__ */ #endif |
| 58 58 58 | 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 | // SPDX-License-Identifier: GPL-2.0-only /* * linux/fs/nfs/inode.c * * Copyright (C) 1992 Rick Sladkey * * nfs inode and superblock handling functions * * Modularised by Alan Cox <alan@lxorguk.ukuu.org.uk>, while hacking some * experimental NFS changes. Modularisation taken straight from SYS5 fs. * * Change to nfs_read_super() to permit NFS mounts to multi-homed hosts. * J.S.Peatfield@damtp.cam.ac.uk * */ #include <linux/module.h> #include <linux/init.h> #include <linux/sched/signal.h> #include <linux/time.h> #include <linux/kernel.h> #include <linux/mm.h> #include <linux/string.h> #include <linux/stat.h> #include <linux/errno.h> #include <linux/unistd.h> #include <linux/sunrpc/clnt.h> #include <linux/sunrpc/stats.h> #include <linux/sunrpc/metrics.h> #include <linux/nfs_fs.h> #include <linux/nfs_mount.h> #include <linux/nfs4_mount.h> #include <linux/lockd/bind.h> #include <linux/seq_file.h> #include <linux/mount.h> #include <linux/vfs.h> #include <linux/inet.h> #include <linux/nfs_xdr.h> #include <linux/slab.h> #include <linux/compat.h> #include <linux/freezer.h> #include <linux/uaccess.h> #include <linux/iversion.h> #include "nfs4_fs.h" #include "callback.h" #include "delegation.h" #include "iostat.h" #include "internal.h" #include "fscache.h" #include "pnfs.h" #include "nfs.h" #include "netns.h" #include "sysfs.h" #include "nfstrace.h" #define NFSDBG_FACILITY NFSDBG_VFS #define NFS_64_BIT_INODE_NUMBERS_ENABLED 1 /* Default is to see 64-bit inode numbers */ static bool enable_ino64 = NFS_64_BIT_INODE_NUMBERS_ENABLED; static int nfs_update_inode(struct inode *, struct nfs_fattr *); static struct kmem_cache * nfs_inode_cachep; static inline unsigned long nfs_fattr_to_ino_t(struct nfs_fattr *fattr) { return nfs_fileid_to_ino_t(fattr->fileid); } int nfs_wait_bit_killable(struct wait_bit_key *key, int mode) { schedule(); if (signal_pending_state(mode, current)) return -ERESTARTSYS; return 0; } EXPORT_SYMBOL_GPL(nfs_wait_bit_killable); /** * nfs_compat_user_ino64 - returns the user-visible inode number * @fileid: 64-bit fileid * * This function returns a 32-bit inode number if the boot parameter * nfs.enable_ino64 is zero. */ u64 nfs_compat_user_ino64(u64 fileid) { #ifdef CONFIG_COMPAT compat_ulong_t ino; #else unsigned long ino; #endif if (enable_ino64) return fileid; ino = fileid; if (sizeof(ino) < sizeof(fileid)) ino ^= fileid >> (sizeof(fileid)-sizeof(ino)) * 8; return ino; } int nfs_drop_inode(struct inode *inode) { return NFS_STALE(inode) || generic_drop_inode(inode); } EXPORT_SYMBOL_GPL(nfs_drop_inode); void nfs_clear_inode(struct inode *inode) { /* * The following should never happen... */ WARN_ON_ONCE(nfs_have_writebacks(inode)); WARN_ON_ONCE(!list_empty(&NFS_I(inode)->open_files)); nfs_zap_acl_cache(inode); nfs_access_zap_cache(inode); nfs_fscache_clear_inode(inode); } EXPORT_SYMBOL_GPL(nfs_clear_inode); void nfs_evict_inode(struct inode *inode) { truncate_inode_pages_final(&inode->i_data); clear_inode(inode); nfs_clear_inode(inode); } int nfs_sync_inode(struct inode *inode) { inode_dio_wait(inode); return nfs_wb_all(inode); } EXPORT_SYMBOL_GPL(nfs_sync_inode); /** * nfs_sync_mapping - helper to flush all mmapped dirty data to disk * @mapping: pointer to struct address_space */ int nfs_sync_mapping(struct address_space *mapping) { int ret = 0; if (mapping->nrpages != 0) { unmap_mapping_range(mapping, 0, 0, 0); ret = nfs_wb_all(mapping->host); } return ret; } static int nfs_attribute_timeout(struct inode *inode) { struct nfs_inode *nfsi = NFS_I(inode); return !time_in_range_open(jiffies, nfsi->read_cache_jiffies, nfsi->read_cache_jiffies + nfsi->attrtimeo); } static bool nfs_check_cache_flags_invalid(struct inode *inode, unsigned long flags) { unsigned long cache_validity = READ_ONCE(NFS_I(inode)->cache_validity); return (cache_validity & flags) != 0; } bool nfs_check_cache_invalid(struct inode *inode, unsigned long flags) { if (nfs_check_cache_flags_invalid(inode, flags)) return true; return nfs_attribute_cache_expired(inode); } EXPORT_SYMBOL_GPL(nfs_check_cache_invalid); #ifdef CONFIG_NFS_V4_2 static bool nfs_has_xattr_cache(const struct nfs_inode *nfsi) { return nfsi->xattr_cache != NULL; } #else static bool nfs_has_xattr_cache(const struct nfs_inode *nfsi) { return false; } #endif void nfs_set_cache_invalid(struct inode *inode, unsigned long flags) { struct nfs_inode *nfsi = NFS_I(inode); if (nfs_have_delegated_attributes(inode)) { if (!(flags & NFS_INO_REVAL_FORCED)) flags &= ~(NFS_INO_INVALID_MODE | NFS_INO_INVALID_OTHER | NFS_INO_INVALID_XATTR); flags &= ~(NFS_INO_INVALID_CHANGE | NFS_INO_INVALID_SIZE); } if (!nfs_has_xattr_cache(nfsi)) flags &= ~NFS_INO_INVALID_XATTR; if (flags & NFS_INO_INVALID_DATA) nfs_fscache_invalidate(inode, 0); flags &= ~NFS_INO_REVAL_FORCED; flags |= nfsi->cache_validity; if (inode->i_mapping->nrpages == 0) flags &= ~NFS_INO_INVALID_DATA; /* pairs with nfs_clear_invalid_mapping()'s smp_load_acquire() */ smp_store_release(&nfsi->cache_validity, flags); if (inode->i_mapping->nrpages == 0 || nfsi->cache_validity & NFS_INO_INVALID_DATA) { nfs_ooo_clear(nfsi); } trace_nfs_set_cache_invalid(inode, 0); } EXPORT_SYMBOL_GPL(nfs_set_cache_invalid); /* * Invalidate the local caches */ static void nfs_zap_caches_locked(struct inode *inode) { struct nfs_inode *nfsi = NFS_I(inode); int mode = inode->i_mode; nfs_inc_stats(inode, NFSIOS_ATTRINVALIDATE); nfsi->attrtimeo = NFS_MINATTRTIMEO(inode); nfsi->attrtimeo_timestamp = jiffies; if (S_ISREG(mode) || S_ISDIR(mode) || S_ISLNK(mode)) nfs_set_cache_invalid(inode, NFS_INO_INVALID_ATTR | NFS_INO_INVALID_DATA | NFS_INO_INVALID_ACCESS | NFS_INO_INVALID_ACL | NFS_INO_INVALID_XATTR); else nfs_set_cache_invalid(inode, NFS_INO_INVALID_ATTR | NFS_INO_INVALID_ACCESS | NFS_INO_INVALID_ACL | NFS_INO_INVALID_XATTR); nfs_zap_label_cache_locked(nfsi); } void nfs_zap_caches(struct inode *inode) { spin_lock(&inode->i_lock); nfs_zap_caches_locked(inode); spin_unlock(&inode->i_lock); } void nfs_zap_mapping(struct inode *inode, struct address_space *mapping) { if (mapping->nrpages != 0) { spin_lock(&inode->i_lock); nfs_set_cache_invalid(inode, NFS_INO_INVALID_DATA); spin_unlock(&inode->i_lock); } } void nfs_zap_acl_cache(struct inode *inode) { void (*clear_acl_cache)(struct inode *); clear_acl_cache = NFS_PROTO(inode)->clear_acl_cache; if (clear_acl_cache != NULL) clear_acl_cache(inode); spin_lock(&inode->i_lock); NFS_I(inode)->cache_validity &= ~NFS_INO_INVALID_ACL; spin_unlock(&inode->i_lock); } EXPORT_SYMBOL_GPL(nfs_zap_acl_cache); void nfs_invalidate_atime(struct inode *inode) { if (nfs_have_delegated_atime(inode)) return; spin_lock(&inode->i_lock); nfs_set_cache_invalid(inode, NFS_INO_INVALID_ATIME); spin_unlock(&inode->i_lock); } EXPORT_SYMBOL_GPL(nfs_invalidate_atime); /* * Invalidate, but do not unhash, the inode. * NB: must be called with inode->i_lock held! */ static void nfs_set_inode_stale_locked(struct inode *inode) { set_bit(NFS_INO_STALE, &NFS_I(inode)->flags); nfs_zap_caches_locked(inode); trace_nfs_set_inode_stale(inode); } void nfs_set_inode_stale(struct inode *inode) { spin_lock(&inode->i_lock); nfs_set_inode_stale_locked(inode); spin_unlock(&inode->i_lock); } struct nfs_find_desc { struct nfs_fh *fh; struct nfs_fattr *fattr; }; /* * In NFSv3 we can have 64bit inode numbers. In order to support * this, and re-exported directories (also seen in NFSv2) * we are forced to allow 2 different inodes to have the same * i_ino. */ static int nfs_find_actor(struct inode *inode, void *opaque) { struct nfs_find_desc *desc = opaque; struct nfs_fh *fh = desc->fh; struct nfs_fattr *fattr = desc->fattr; if (NFS_FILEID(inode) != fattr->fileid) return 0; if (inode_wrong_type(inode, fattr->mode)) return 0; if (nfs_compare_fh(NFS_FH(inode), fh)) return 0; if (is_bad_inode(inode) || NFS_STALE(inode)) return 0; return 1; } static int nfs_init_locked(struct inode *inode, void *opaque) { struct nfs_find_desc *desc = opaque; struct nfs_fattr *fattr = desc->fattr; set_nfs_fileid(inode, fattr->fileid); inode->i_mode = fattr->mode; nfs_copy_fh(NFS_FH(inode), desc->fh); return 0; } #ifdef CONFIG_NFS_V4_SECURITY_LABEL static void nfs_clear_label_invalid(struct inode *inode) { spin_lock(&inode->i_lock); NFS_I(inode)->cache_validity &= ~NFS_INO_INVALID_LABEL; spin_unlock(&inode->i_lock); } void nfs_setsecurity(struct inode *inode, struct nfs_fattr *fattr) { int error; if (fattr->label == NULL) return; if ((fattr->valid & NFS_ATTR_FATTR_V4_SECURITY_LABEL) && inode->i_security) { error = security_inode_notifysecctx(inode, fattr->label->label, fattr->label->len); if (error) printk(KERN_ERR "%s() %s %d " "security_inode_notifysecctx() %d\n", __func__, (char *)fattr->label->label, fattr->label->len, error); nfs_clear_label_invalid(inode); } } struct nfs4_label *nfs4_label_alloc(struct nfs_server *server, gfp_t flags) { struct nfs4_label *label; if (!(server->caps & NFS_CAP_SECURITY_LABEL)) return NULL; label = kzalloc(sizeof(struct nfs4_label), flags); if (label == NULL) return ERR_PTR(-ENOMEM); label->label = kzalloc(NFS4_MAXLABELLEN, flags); if (label->label == NULL) { kfree(label); return ERR_PTR(-ENOMEM); } label->len = NFS4_MAXLABELLEN; return label; } EXPORT_SYMBOL_GPL(nfs4_label_alloc); #else void nfs_setsecurity(struct inode *inode, struct nfs_fattr *fattr) { } #endif EXPORT_SYMBOL_GPL(nfs_setsecurity); /* Search for inode identified by fh, fileid and i_mode in inode cache. */ struct inode * nfs_ilookup(struct super_block *sb, struct nfs_fattr *fattr, struct nfs_fh *fh) { struct nfs_find_desc desc = { .fh = fh, .fattr = fattr, }; struct inode *inode; unsigned long hash; if (!(fattr->valid & NFS_ATTR_FATTR_FILEID) || !(fattr->valid & NFS_ATTR_FATTR_TYPE)) return NULL; hash = nfs_fattr_to_ino_t(fattr); inode = ilookup5(sb, hash, nfs_find_actor, &desc); dprintk("%s: returning %p\n", __func__, inode); return inode; } static void nfs_inode_init_regular(struct nfs_inode *nfsi) { atomic_long_set(&nfsi->nrequests, 0); atomic_long_set(&nfsi->redirtied_pages, 0); INIT_LIST_HEAD(&nfsi->commit_info.list); atomic_long_set(&nfsi->commit_info.ncommit, 0); atomic_set(&nfsi->commit_info.rpcs_out, 0); mutex_init(&nfsi->commit_mutex); } static void nfs_inode_init_dir(struct nfs_inode *nfsi) { nfsi->cache_change_attribute = 0; memset(nfsi->cookieverf, 0, sizeof(nfsi->cookieverf)); init_rwsem(&nfsi->rmdir_sem); } /* * This is our front-end to iget that looks up inodes by file handle * instead of inode number. */ struct inode * nfs_fhget(struct super_block *sb, struct nfs_fh *fh, struct nfs_fattr *fattr) { struct nfs_find_desc desc = { .fh = fh, .fattr = fattr }; struct inode *inode = ERR_PTR(-ENOENT); u64 fattr_supported = NFS_SB(sb)->fattr_valid; unsigned long hash; nfs_attr_check_mountpoint(sb, fattr); if (nfs_attr_use_mounted_on_fileid(fattr)) fattr->fileid = fattr->mounted_on_fileid; else if ((fattr->valid & NFS_ATTR_FATTR_FILEID) == 0) goto out_no_inode; if ((fattr->valid & NFS_ATTR_FATTR_TYPE) == 0) goto out_no_inode; hash = nfs_fattr_to_ino_t(fattr); inode = iget5_locked(sb, hash, nfs_find_actor, nfs_init_locked, &desc); if (inode == NULL) { inode = ERR_PTR(-ENOMEM); goto out_no_inode; } if (inode->i_state & I_NEW) { struct nfs_inode *nfsi = NFS_I(inode); unsigned long now = jiffies; /* We set i_ino for the few things that still rely on it, * such as stat(2) */ inode->i_ino = hash; /* We can't support update_atime(), since the server will reset it */ inode->i_flags |= S_NOATIME|S_NOCMTIME; inode->i_mode = fattr->mode; nfsi->cache_validity = 0; if ((fattr->valid & NFS_ATTR_FATTR_MODE) == 0 && (fattr_supported & NFS_ATTR_FATTR_MODE)) nfs_set_cache_invalid(inode, NFS_INO_INVALID_MODE); /* Why so? Because we want revalidate for devices/FIFOs, and * that's precisely what we have in nfs_file_inode_operations. */ inode->i_op = NFS_SB(sb)->nfs_client->rpc_ops->file_inode_ops; if (S_ISREG(inode->i_mode)) { inode->i_fop = NFS_SB(sb)->nfs_client->rpc_ops->file_ops; inode->i_data.a_ops = &nfs_file_aops; nfs_inode_init_regular(nfsi); mapping_set_large_folios(inode->i_mapping); } else if (S_ISDIR(inode->i_mode)) { inode->i_op = NFS_SB(sb)->nfs_client->rpc_ops->dir_inode_ops; inode->i_fop = &nfs_dir_operations; inode->i_data.a_ops = &nfs_dir_aops; nfs_inode_init_dir(nfsi); /* Deal with crossing mountpoints */ if (fattr->valid & NFS_ATTR_FATTR_MOUNTPOINT || fattr->valid & NFS_ATTR_FATTR_V4_REFERRAL) { if (fattr->valid & NFS_ATTR_FATTR_V4_REFERRAL) inode->i_op = &nfs_referral_inode_operations; else inode->i_op = &nfs_mountpoint_inode_operations; inode->i_fop = NULL; inode->i_flags |= S_AUTOMOUNT; } } else if (S_ISLNK(inode->i_mode)) { inode->i_op = &nfs_symlink_inode_operations; inode_nohighmem(inode); } else init_special_inode(inode, inode->i_mode, fattr->rdev); inode_set_atime(inode, 0, 0); inode_set_mtime(inode, 0, 0); inode_set_ctime(inode, 0, 0); inode_set_iversion_raw(inode, 0); inode->i_size = 0; clear_nlink(inode); inode->i_uid = make_kuid(&init_user_ns, -2); inode->i_gid = make_kgid(&init_user_ns, -2); inode->i_blocks = 0; nfsi->write_io = 0; nfsi->read_io = 0; nfsi->read_cache_jiffies = fattr->time_start; nfsi->attr_gencount = fattr->gencount; if (fattr->valid & NFS_ATTR_FATTR_ATIME) inode_set_atime_to_ts(inode, fattr->atime); else if (fattr_supported & NFS_ATTR_FATTR_ATIME) nfs_set_cache_invalid(inode, NFS_INO_INVALID_ATIME); if (fattr->valid & NFS_ATTR_FATTR_MTIME) inode_set_mtime_to_ts(inode, fattr->mtime); else if (fattr_supported & NFS_ATTR_FATTR_MTIME) nfs_set_cache_invalid(inode, NFS_INO_INVALID_MTIME); if (fattr->valid & NFS_ATTR_FATTR_CTIME) inode_set_ctime_to_ts(inode, fattr->ctime); else if (fattr_supported & NFS_ATTR_FATTR_CTIME) nfs_set_cache_invalid(inode, NFS_INO_INVALID_CTIME); if (fattr->valid & NFS_ATTR_FATTR_CHANGE) inode_set_iversion_raw(inode, fattr->change_attr); else nfs_set_cache_invalid(inode, NFS_INO_INVALID_CHANGE); if (fattr->valid & NFS_ATTR_FATTR_SIZE) inode->i_size = nfs_size_to_loff_t(fattr->size); else nfs_set_cache_invalid(inode, NFS_INO_INVALID_SIZE); if (fattr->valid & NFS_ATTR_FATTR_NLINK) set_nlink(inode, fattr->nlink); else if (fattr_supported & NFS_ATTR_FATTR_NLINK) nfs_set_cache_invalid(inode, NFS_INO_INVALID_NLINK); if (fattr->valid & NFS_ATTR_FATTR_OWNER) inode->i_uid = fattr->uid; else if (fattr_supported & NFS_ATTR_FATTR_OWNER) nfs_set_cache_invalid(inode, NFS_INO_INVALID_OTHER); if (fattr->valid & NFS_ATTR_FATTR_GROUP) inode->i_gid = fattr->gid; else if (fattr_supported & NFS_ATTR_FATTR_GROUP) nfs_set_cache_invalid(inode, NFS_INO_INVALID_OTHER); if (fattr->valid & NFS_ATTR_FATTR_BLOCKS_USED) inode->i_blocks = fattr->du.nfs2.blocks; else if (fattr_supported & NFS_ATTR_FATTR_BLOCKS_USED && fattr->size != 0) nfs_set_cache_invalid(inode, NFS_INO_INVALID_BLOCKS); if (fattr->valid & NFS_ATTR_FATTR_SPACE_USED) { /* * report the blocks in 512byte units */ inode->i_blocks = nfs_calc_block_size(fattr->du.nfs3.used); } else if (fattr_supported & NFS_ATTR_FATTR_SPACE_USED && fattr->size != 0) nfs_set_cache_invalid(inode, NFS_INO_INVALID_BLOCKS); nfs_setsecurity(inode, fattr); nfsi->attrtimeo = NFS_MINATTRTIMEO(inode); nfsi->attrtimeo_timestamp = now; nfsi->access_cache = RB_ROOT; nfs_fscache_init_inode(inode); unlock_new_inode(inode); } else { int err = nfs_refresh_inode(inode, fattr); if (err < 0) { iput(inode); inode = ERR_PTR(err); goto out_no_inode; } } dprintk("NFS: nfs_fhget(%s/%Lu fh_crc=0x%08x ct=%d)\n", inode->i_sb->s_id, (unsigned long long)NFS_FILEID(inode), nfs_display_fhandle_hash(fh), atomic_read(&inode->i_count)); out: return inode; out_no_inode: dprintk("nfs_fhget: iget failed with error %ld\n", PTR_ERR(inode)); goto out; } EXPORT_SYMBOL_GPL(nfs_fhget); static void nfs_fattr_fixup_delegated(struct inode *inode, struct nfs_fattr *fattr) { unsigned long cache_validity = NFS_I(inode)->cache_validity; if (nfs_have_delegated_mtime(inode)) { if (!(cache_validity & NFS_INO_INVALID_CTIME)) fattr->valid &= ~(NFS_ATTR_FATTR_PRECTIME | NFS_ATTR_FATTR_CTIME); if (!(cache_validity & NFS_INO_INVALID_MTIME)) fattr->valid &= ~(NFS_ATTR_FATTR_PREMTIME | NFS_ATTR_FATTR_MTIME); if (!(cache_validity & NFS_INO_INVALID_ATIME)) fattr->valid &= ~NFS_ATTR_FATTR_ATIME; } else if (nfs_have_delegated_atime(inode)) { if (!(cache_validity & NFS_INO_INVALID_ATIME)) fattr->valid &= ~NFS_ATTR_FATTR_ATIME; } } static void nfs_update_timestamps(struct inode *inode, unsigned int ia_valid) { enum file_time_flags time_flags = 0; unsigned int cache_flags = 0; if (ia_valid & ATTR_MTIME) { time_flags |= S_MTIME | S_CTIME; cache_flags |= NFS_INO_INVALID_CTIME | NFS_INO_INVALID_MTIME; } if (ia_valid & ATTR_ATIME) { time_flags |= S_ATIME; cache_flags |= NFS_INO_INVALID_ATIME; } inode_update_timestamps(inode, time_flags); NFS_I(inode)->cache_validity &= ~cache_flags; } void nfs_update_delegated_atime(struct inode *inode) { spin_lock(&inode->i_lock); if (nfs_have_delegated_atime(inode)) nfs_update_timestamps(inode, ATTR_ATIME); spin_unlock(&inode->i_lock); } void nfs_update_delegated_mtime_locked(struct inode *inode) { if (nfs_have_delegated_mtime(inode)) nfs_update_timestamps(inode, ATTR_MTIME); } void nfs_update_delegated_mtime(struct inode *inode) { spin_lock(&inode->i_lock); nfs_update_delegated_mtime_locked(inode); spin_unlock(&inode->i_lock); } EXPORT_SYMBOL_GPL(nfs_update_delegated_mtime); #define NFS_VALID_ATTRS (ATTR_MODE|ATTR_UID|ATTR_GID|ATTR_SIZE|ATTR_ATIME|ATTR_ATIME_SET|ATTR_MTIME|ATTR_MTIME_SET|ATTR_FILE|ATTR_OPEN) int nfs_setattr(struct mnt_idmap *idmap, struct dentry *dentry, struct iattr *attr) { struct inode *inode = d_inode(dentry); struct nfs_fattr *fattr; int error = 0; nfs_inc_stats(inode, NFSIOS_VFSSETATTR); /* skip mode change if it's just for clearing setuid/setgid */ if (attr->ia_valid & (ATTR_KILL_SUID | ATTR_KILL_SGID)) attr->ia_valid &= ~ATTR_MODE; if (attr->ia_valid & ATTR_SIZE) { BUG_ON(!S_ISREG(inode->i_mode)); error = inode_newsize_ok(inode, attr->ia_size); if (error) return error; if (attr->ia_size == i_size_read(inode)) attr->ia_valid &= ~ATTR_SIZE; } if (nfs_have_delegated_mtime(inode) && attr->ia_valid & ATTR_MTIME) { spin_lock(&inode->i_lock); nfs_update_timestamps(inode, attr->ia_valid); spin_unlock(&inode->i_lock); attr->ia_valid &= ~(ATTR_MTIME | ATTR_ATIME); } else if (nfs_have_delegated_atime(inode) && attr->ia_valid & ATTR_ATIME && !(attr->ia_valid & ATTR_MTIME)) { nfs_update_delegated_atime(inode); attr->ia_valid &= ~ATTR_ATIME; } /* Optimization: if the end result is no change, don't RPC */ if (((attr->ia_valid & NFS_VALID_ATTRS) & ~(ATTR_FILE|ATTR_OPEN)) == 0) return 0; trace_nfs_setattr_enter(inode); /* Write all dirty data */ if (S_ISREG(inode->i_mode)) nfs_sync_inode(inode); fattr = nfs_alloc_fattr_with_label(NFS_SERVER(inode)); if (fattr == NULL) { error = -ENOMEM; goto out; } error = NFS_PROTO(inode)->setattr(dentry, fattr, attr); if (error == 0) error = nfs_refresh_inode(inode, fattr); nfs_free_fattr(fattr); out: trace_nfs_setattr_exit(inode, error); return error; } EXPORT_SYMBOL_GPL(nfs_setattr); /** * nfs_vmtruncate - unmap mappings "freed" by truncate() syscall * @inode: inode of the file used * @offset: file offset to start truncating * * This is a copy of the common vmtruncate, but with the locking * corrected to take into account the fact that NFS requires * inode->i_size to be updated under the inode->i_lock. * Note: must be called with inode->i_lock held! */ static int nfs_vmtruncate(struct inode * inode, loff_t offset) { int err; err = inode_newsize_ok(inode, offset); if (err) goto out; trace_nfs_size_truncate(inode, offset); i_size_write(inode, offset); /* Optimisation */ if (offset == 0) { NFS_I(inode)->cache_validity &= ~NFS_INO_INVALID_DATA; nfs_ooo_clear(NFS_I(inode)); } NFS_I(inode)->cache_validity &= ~NFS_INO_INVALID_SIZE; spin_unlock(&inode->i_lock); truncate_pagecache(inode, offset); nfs_update_delegated_mtime_locked(inode); spin_lock(&inode->i_lock); out: return err; } /** * nfs_setattr_update_inode - Update inode metadata after a setattr call. * @inode: pointer to struct inode * @attr: pointer to struct iattr * @fattr: pointer to struct nfs_fattr * * Note: we do this in the *proc.c in order to ensure that * it works for things like exclusive creates too. */ void nfs_setattr_update_inode(struct inode *inode, struct iattr *attr, struct nfs_fattr *fattr) { /* Barrier: bump the attribute generation count. */ nfs_fattr_set_barrier(fattr); spin_lock(&inode->i_lock); NFS_I(inode)->attr_gencount = fattr->gencount; if ((attr->ia_valid & ATTR_SIZE) != 0) { if (!nfs_have_delegated_mtime(inode)) nfs_set_cache_invalid(inode, NFS_INO_INVALID_MTIME); nfs_set_cache_invalid(inode, NFS_INO_INVALID_BLOCKS); nfs_inc_stats(inode, NFSIOS_SETATTRTRUNC); nfs_vmtruncate(inode, attr->ia_size); } if ((attr->ia_valid & (ATTR_MODE|ATTR_UID|ATTR_GID)) != 0) { NFS_I(inode)->cache_validity &= ~NFS_INO_INVALID_CTIME; if ((attr->ia_valid & ATTR_KILL_SUID) != 0 && inode->i_mode & S_ISUID) inode->i_mode &= ~S_ISUID; if (setattr_should_drop_sgid(&nop_mnt_idmap, inode)) inode->i_mode &= ~S_ISGID; if ((attr->ia_valid & ATTR_MODE) != 0) { int mode = attr->ia_mode & S_IALLUGO; mode |= inode->i_mode & ~S_IALLUGO; inode->i_mode = mode; } if ((attr->ia_valid & ATTR_UID) != 0) inode->i_uid = attr->ia_uid; if ((attr->ia_valid & ATTR_GID) != 0) inode->i_gid = attr->ia_gid; if (fattr->valid & NFS_ATTR_FATTR_CTIME) inode_set_ctime_to_ts(inode, fattr->ctime); else nfs_set_cache_invalid(inode, NFS_INO_INVALID_CHANGE | NFS_INO_INVALID_CTIME); nfs_set_cache_invalid(inode, NFS_INO_INVALID_ACCESS | NFS_INO_INVALID_ACL); } if (attr->ia_valid & (ATTR_ATIME_SET|ATTR_ATIME)) { NFS_I(inode)->cache_validity &= ~(NFS_INO_INVALID_ATIME | NFS_INO_INVALID_CTIME); if (fattr->valid & NFS_ATTR_FATTR_ATIME) inode_set_atime_to_ts(inode, fattr->atime); else if (attr->ia_valid & ATTR_ATIME_SET) inode_set_atime_to_ts(inode, attr->ia_atime); else nfs_set_cache_invalid(inode, NFS_INO_INVALID_ATIME); if (fattr->valid & NFS_ATTR_FATTR_CTIME) inode_set_ctime_to_ts(inode, fattr->ctime); else nfs_set_cache_invalid(inode, NFS_INO_INVALID_CHANGE | NFS_INO_INVALID_CTIME); } if (attr->ia_valid & (ATTR_MTIME_SET|ATTR_MTIME)) { NFS_I(inode)->cache_validity &= ~(NFS_INO_INVALID_MTIME | NFS_INO_INVALID_CTIME); if (fattr->valid & NFS_ATTR_FATTR_MTIME) inode_set_mtime_to_ts(inode, fattr->mtime); else if (attr->ia_valid & ATTR_MTIME_SET) inode_set_mtime_to_ts(inode, attr->ia_mtime); else nfs_set_cache_invalid(inode, NFS_INO_INVALID_MTIME); if (fattr->valid & NFS_ATTR_FATTR_CTIME) inode_set_ctime_to_ts(inode, fattr->ctime); else nfs_set_cache_invalid(inode, NFS_INO_INVALID_CHANGE | NFS_INO_INVALID_CTIME); } if (fattr->valid) nfs_update_inode(inode, fattr); spin_unlock(&inode->i_lock); } EXPORT_SYMBOL_GPL(nfs_setattr_update_inode); /* * Don't request help from readdirplus if the file is being written to, * or if attribute caching is turned off */ static bool nfs_getattr_readdirplus_enable(const struct inode *inode) { return nfs_server_capable(inode, NFS_CAP_READDIRPLUS) && !nfs_have_writebacks(inode) && NFS_MAXATTRTIMEO(inode) > 5 * HZ; } static void nfs_readdirplus_parent_cache_miss(struct dentry *dentry) { if (!IS_ROOT(dentry)) { struct dentry *parent = dget_parent(dentry); nfs_readdir_record_entry_cache_miss(d_inode(parent)); dput(parent); } } static void nfs_readdirplus_parent_cache_hit(struct dentry *dentry) { if (!IS_ROOT(dentry)) { struct dentry *parent = dget_parent(dentry); nfs_readdir_record_entry_cache_hit(d_inode(parent)); dput(parent); } } static u32 nfs_get_valid_attrmask(struct inode *inode) { unsigned long cache_validity = READ_ONCE(NFS_I(inode)->cache_validity); u32 reply_mask = STATX_INO | STATX_TYPE; if (!(cache_validity & NFS_INO_INVALID_ATIME)) reply_mask |= STATX_ATIME; if (!(cache_validity & NFS_INO_INVALID_CTIME)) reply_mask |= STATX_CTIME; if (!(cache_validity & NFS_INO_INVALID_MTIME)) reply_mask |= STATX_MTIME; if (!(cache_validity & NFS_INO_INVALID_SIZE)) reply_mask |= STATX_SIZE; if (!(cache_validity & NFS_INO_INVALID_NLINK)) reply_mask |= STATX_NLINK; if (!(cache_validity & NFS_INO_INVALID_MODE)) reply_mask |= STATX_MODE; if (!(cache_validity & NFS_INO_INVALID_OTHER)) reply_mask |= STATX_UID | STATX_GID; if (!(cache_validity & NFS_INO_INVALID_BLOCKS)) reply_mask |= STATX_BLOCKS; if (!(cache_validity & NFS_INO_INVALID_CHANGE)) reply_mask |= STATX_CHANGE_COOKIE; return reply_mask; } int nfs_getattr(struct mnt_idmap *idmap, const struct path *path, struct kstat *stat, u32 request_mask, unsigned int query_flags) { struct inode *inode = d_inode(path->dentry); struct nfs_server *server = NFS_SERVER(inode); unsigned long cache_validity; int err = 0; bool force_sync = query_flags & AT_STATX_FORCE_SYNC; bool do_update = false; bool readdirplus_enabled = nfs_getattr_readdirplus_enable(inode); trace_nfs_getattr_enter(inode); request_mask &= STATX_TYPE | STATX_MODE | STATX_NLINK | STATX_UID | STATX_GID | STATX_ATIME | STATX_MTIME | STATX_CTIME | STATX_INO | STATX_SIZE | STATX_BLOCKS | STATX_CHANGE_COOKIE; if ((query_flags & AT_STATX_DONT_SYNC) && !force_sync) { if (readdirplus_enabled) nfs_readdirplus_parent_cache_hit(path->dentry); goto out_no_revalidate; } /* Flush out writes to the server in order to update c/mtime/version. */ if ((request_mask & (STATX_CTIME | STATX_MTIME | STATX_CHANGE_COOKIE)) && S_ISREG(inode->i_mode)) { if (nfs_have_delegated_mtime(inode)) filemap_fdatawrite(inode->i_mapping); else filemap_write_and_wait(inode->i_mapping); } /* * We may force a getattr if the user cares about atime. * * Note that we only have to check the vfsmount flags here: * - NFS always sets S_NOATIME by so checking it would give a * bogus result * - NFS never sets SB_NOATIME or SB_NODIRATIME so there is * no point in checking those. */ if ((path->mnt->mnt_flags & MNT_NOATIME) || ((path->mnt->mnt_flags & MNT_NODIRATIME) && S_ISDIR(inode->i_mode))) request_mask &= ~STATX_ATIME; /* Is the user requesting attributes that might need revalidation? */ if (!(request_mask & (STATX_MODE|STATX_NLINK|STATX_ATIME|STATX_CTIME| STATX_MTIME|STATX_UID|STATX_GID| STATX_SIZE|STATX_BLOCKS| STATX_CHANGE_COOKIE))) goto out_no_revalidate; /* Check whether the cached attributes are stale */ do_update |= force_sync || nfs_attribute_cache_expired(inode); cache_validity = READ_ONCE(NFS_I(inode)->cache_validity); do_update |= cache_validity & NFS_INO_INVALID_CHANGE; if (request_mask & STATX_ATIME) do_update |= cache_validity & NFS_INO_INVALID_ATIME; if (request_mask & STATX_CTIME) do_update |= cache_validity & NFS_INO_INVALID_CTIME; if (request_mask & STATX_MTIME) do_update |= cache_validity & NFS_INO_INVALID_MTIME; if (request_mask & STATX_SIZE) do_update |= cache_validity & NFS_INO_INVALID_SIZE; if (request_mask & STATX_NLINK) do_update |= cache_validity & NFS_INO_INVALID_NLINK; if (request_mask & STATX_MODE) do_update |= cache_validity & NFS_INO_INVALID_MODE; if (request_mask & (STATX_UID | STATX_GID)) do_update |= cache_validity & NFS_INO_INVALID_OTHER; if (request_mask & STATX_BLOCKS) do_update |= cache_validity & NFS_INO_INVALID_BLOCKS; if (do_update) { if (readdirplus_enabled) nfs_readdirplus_parent_cache_miss(path->dentry); err = __nfs_revalidate_inode(server, inode); if (err) goto out; } else if (readdirplus_enabled) nfs_readdirplus_parent_cache_hit(path->dentry); out_no_revalidate: /* Only return attributes that were revalidated. */ stat->result_mask = nfs_get_valid_attrmask(inode) | request_mask; generic_fillattr(&nop_mnt_idmap, request_mask, inode, stat); stat->ino = nfs_compat_user_ino64(NFS_FILEID(inode)); stat->change_cookie = inode_peek_iversion_raw(inode); stat->attributes_mask |= STATX_ATTR_CHANGE_MONOTONIC; if (server->change_attr_type != NFS4_CHANGE_TYPE_IS_UNDEFINED) stat->attributes |= STATX_ATTR_CHANGE_MONOTONIC; if (S_ISDIR(inode->i_mode)) stat->blksize = NFS_SERVER(inode)->dtsize; out: trace_nfs_getattr_exit(inode, err); return err; } EXPORT_SYMBOL_GPL(nfs_getattr); static void nfs_init_lock_context(struct nfs_lock_context *l_ctx) { refcount_set(&l_ctx->count, 1); l_ctx->lockowner = current->files; INIT_LIST_HEAD(&l_ctx->list); atomic_set(&l_ctx->io_count, 0); } static struct nfs_lock_context *__nfs_find_lock_context(struct nfs_open_context *ctx) { struct nfs_lock_context *pos; list_for_each_entry_rcu(pos, &ctx->lock_context.list, list) { if (pos->lockowner != current->files) continue; if (refcount_inc_not_zero(&pos->count)) return pos; } return NULL; } struct nfs_lock_context *nfs_get_lock_context(struct nfs_open_context *ctx) { struct nfs_lock_context *res, *new = NULL; struct inode *inode = d_inode(ctx->dentry); rcu_read_lock(); res = __nfs_find_lock_context(ctx); rcu_read_unlock(); if (res == NULL) { new = kmalloc(sizeof(*new), GFP_KERNEL_ACCOUNT); if (new == NULL) return ERR_PTR(-ENOMEM); nfs_init_lock_context(new); spin_lock(&inode->i_lock); res = __nfs_find_lock_context(ctx); if (res == NULL) { new->open_context = get_nfs_open_context(ctx); if (new->open_context) { list_add_tail_rcu(&new->list, &ctx->lock_context.list); res = new; new = NULL; } else res = ERR_PTR(-EBADF); } spin_unlock(&inode->i_lock); kfree(new); } return res; } EXPORT_SYMBOL_GPL(nfs_get_lock_context); void nfs_put_lock_context(struct nfs_lock_context *l_ctx) { struct nfs_open_context *ctx = l_ctx->open_context; struct inode *inode = d_inode(ctx->dentry); if (!refcount_dec_and_lock(&l_ctx->count, &inode->i_lock)) return; list_del_rcu(&l_ctx->list); spin_unlock(&inode->i_lock); put_nfs_open_context(ctx); kfree_rcu(l_ctx, rcu_head); } EXPORT_SYMBOL_GPL(nfs_put_lock_context); /** * nfs_close_context - Common close_context() routine NFSv2/v3 * @ctx: pointer to context * @is_sync: is this a synchronous close * * Ensure that the attributes are up to date if we're mounted * with close-to-open semantics and we have cached data that will * need to be revalidated on open. */ void nfs_close_context(struct nfs_open_context *ctx, int is_sync) { struct nfs_inode *nfsi; struct inode *inode; if (!(ctx->mode & FMODE_WRITE)) return; if (!is_sync) return; inode = d_inode(ctx->dentry); if (nfs_have_read_or_write_delegation(inode)) return; nfsi = NFS_I(inode); if (inode->i_mapping->nrpages == 0) return; if (nfsi->cache_validity & NFS_INO_INVALID_DATA) return; if (!list_empty(&nfsi->open_files)) return; if (NFS_SERVER(inode)->flags & NFS_MOUNT_NOCTO) return; nfs_revalidate_inode(inode, NFS_INO_INVALID_CHANGE | NFS_INO_INVALID_SIZE); } EXPORT_SYMBOL_GPL(nfs_close_context); struct nfs_open_context *alloc_nfs_open_context(struct dentry *dentry, fmode_t f_mode, struct file *filp) { struct nfs_open_context *ctx; ctx = kmalloc(sizeof(*ctx), GFP_KERNEL_ACCOUNT); if (!ctx) return ERR_PTR(-ENOMEM); nfs_sb_active(dentry->d_sb); ctx->dentry = dget(dentry); if (filp) ctx->cred = get_cred(filp->f_cred); else ctx->cred = get_current_cred(); rcu_assign_pointer(ctx->ll_cred, NULL); ctx->state = NULL; ctx->mode = f_mode; ctx->flags = 0; ctx->error = 0; ctx->flock_owner = (fl_owner_t)filp; nfs_init_lock_context(&ctx->lock_context); ctx->lock_context.open_context = ctx; INIT_LIST_HEAD(&ctx->list); ctx->mdsthreshold = NULL; nfs_localio_file_init(&ctx->nfl); return ctx; } EXPORT_SYMBOL_GPL(alloc_nfs_open_context); struct nfs_open_context *get_nfs_open_context(struct nfs_open_context *ctx) { if (ctx != NULL && refcount_inc_not_zero(&ctx->lock_context.count)) return ctx; return NULL; } EXPORT_SYMBOL_GPL(get_nfs_open_context); static void __put_nfs_open_context(struct nfs_open_context *ctx, int is_sync) { struct inode *inode = d_inode(ctx->dentry); struct super_block *sb = ctx->dentry->d_sb; if (!refcount_dec_and_test(&ctx->lock_context.count)) return; if (!list_empty(&ctx->list)) { spin_lock(&inode->i_lock); list_del_rcu(&ctx->list); spin_unlock(&inode->i_lock); } if (inode != NULL) NFS_PROTO(inode)->close_context(ctx, is_sync); put_cred(ctx->cred); dput(ctx->dentry); nfs_sb_deactive(sb); put_rpccred(rcu_dereference_protected(ctx->ll_cred, 1)); kfree(ctx->mdsthreshold); nfs_close_local_fh(&ctx->nfl); kfree_rcu(ctx, rcu_head); } void put_nfs_open_context(struct nfs_open_context *ctx) { __put_nfs_open_context(ctx, 0); } EXPORT_SYMBOL_GPL(put_nfs_open_context); static void put_nfs_open_context_sync(struct nfs_open_context *ctx) { __put_nfs_open_context(ctx, 1); } /* * Ensure that mmap has a recent RPC credential for use when writing out * shared pages */ void nfs_inode_attach_open_context(struct nfs_open_context *ctx) { struct inode *inode = d_inode(ctx->dentry); struct nfs_inode *nfsi = NFS_I(inode); spin_lock(&inode->i_lock); if (list_empty(&nfsi->open_files) && nfs_ooo_test(nfsi)) nfs_set_cache_invalid(inode, NFS_INO_INVALID_DATA | NFS_INO_REVAL_FORCED); list_add_tail_rcu(&ctx->list, &nfsi->open_files); spin_unlock(&inode->i_lock); } EXPORT_SYMBOL_GPL(nfs_inode_attach_open_context); void nfs_file_set_open_context(struct file *filp, struct nfs_open_context *ctx) { filp->private_data = get_nfs_open_context(ctx); set_bit(NFS_CONTEXT_FILE_OPEN, &ctx->flags); if (list_empty(&ctx->list)) nfs_inode_attach_open_context(ctx); } EXPORT_SYMBOL_GPL(nfs_file_set_open_context); /* * Given an inode, search for an open context with the desired characteristics */ struct nfs_open_context *nfs_find_open_context(struct inode *inode, const struct cred *cred, fmode_t mode) { struct nfs_inode *nfsi = NFS_I(inode); struct nfs_open_context *pos, *ctx = NULL; rcu_read_lock(); list_for_each_entry_rcu(pos, &nfsi->open_files, list) { if (cred != NULL && cred_fscmp(pos->cred, cred) != 0) continue; if ((pos->mode & (FMODE_READ|FMODE_WRITE)) != mode) continue; if (!test_bit(NFS_CONTEXT_FILE_OPEN, &pos->flags)) continue; ctx = get_nfs_open_context(pos); if (ctx) break; } rcu_read_unlock(); return ctx; } void nfs_file_clear_open_context(struct file *filp) { struct nfs_open_context *ctx = nfs_file_open_context(filp); if (ctx) { struct inode *inode = d_inode(ctx->dentry); clear_bit(NFS_CONTEXT_FILE_OPEN, &ctx->flags); /* * We fatal error on write before. Try to writeback * every page again. */ if (ctx->error < 0) invalidate_inode_pages2(inode->i_mapping); filp->private_data = NULL; put_nfs_open_context_sync(ctx); } } /* * These allocate and release file read/write context information. */ int nfs_open(struct inode *inode, struct file *filp) { struct nfs_open_context *ctx; ctx = alloc_nfs_open_context(file_dentry(filp), flags_to_mode(filp->f_flags), filp); if (IS_ERR(ctx)) return PTR_ERR(ctx); nfs_file_set_open_context(filp, ctx); put_nfs_open_context(ctx); nfs_fscache_open_file(inode, filp); return 0; } /* * This function is called whenever some part of NFS notices that * the cached attributes have to be refreshed. */ int __nfs_revalidate_inode(struct nfs_server *server, struct inode *inode) { int status = -ESTALE; struct nfs_fattr *fattr = NULL; struct nfs_inode *nfsi = NFS_I(inode); dfprintk(PAGECACHE, "NFS: revalidating (%s/%Lu)\n", inode->i_sb->s_id, (unsigned long long)NFS_FILEID(inode)); trace_nfs_revalidate_inode_enter(inode); if (is_bad_inode(inode)) goto out; if (NFS_STALE(inode)) goto out; /* pNFS: Attributes aren't updated until we layoutcommit */ if (S_ISREG(inode->i_mode)) { status = pnfs_sync_inode(inode, false); if (status) goto out; } status = -ENOMEM; fattr = nfs_alloc_fattr_with_label(NFS_SERVER(inode)); if (fattr == NULL) goto out; nfs_inc_stats(inode, NFSIOS_INODEREVALIDATE); status = NFS_PROTO(inode)->getattr(server, NFS_FH(inode), fattr, inode); if (status != 0) { dfprintk(PAGECACHE, "nfs_revalidate_inode: (%s/%Lu) getattr failed, error=%d\n", inode->i_sb->s_id, (unsigned long long)NFS_FILEID(inode), status); switch (status) { case -ETIMEDOUT: /* A soft timeout occurred. Use cached information? */ if (server->flags & NFS_MOUNT_SOFTREVAL) status = 0; break; case -ESTALE: if (!S_ISDIR(inode->i_mode)) nfs_set_inode_stale(inode); else nfs_zap_caches(inode); } goto out; } status = nfs_refresh_inode(inode, fattr); if (status) { dfprintk(PAGECACHE, "nfs_revalidate_inode: (%s/%Lu) refresh failed, error=%d\n", inode->i_sb->s_id, (unsigned long long)NFS_FILEID(inode), status); goto out; } if (nfsi->cache_validity & NFS_INO_INVALID_ACL) nfs_zap_acl_cache(inode); nfs_setsecurity(inode, fattr); dfprintk(PAGECACHE, "NFS: (%s/%Lu) revalidation complete\n", inode->i_sb->s_id, (unsigned long long)NFS_FILEID(inode)); out: nfs_free_fattr(fattr); trace_nfs_revalidate_inode_exit(inode, status); return status; } int nfs_attribute_cache_expired(struct inode *inode) { if (nfs_have_delegated_attributes(inode)) return 0; return nfs_attribute_timeout(inode); } /** * nfs_revalidate_inode - Revalidate the inode attributes * @inode: pointer to inode struct * @flags: cache flags to check * * Updates inode attribute information by retrieving the data from the server. */ int nfs_revalidate_inode(struct inode *inode, unsigned long flags) { if (!nfs_check_cache_invalid(inode, flags)) return NFS_STALE(inode) ? -ESTALE : 0; return __nfs_revalidate_inode(NFS_SERVER(inode), inode); } EXPORT_SYMBOL_GPL(nfs_revalidate_inode); static int nfs_invalidate_mapping(struct inode *inode, struct address_space *mapping) { int ret; nfs_fscache_invalidate(inode, 0); if (mapping->nrpages != 0) { if (S_ISREG(inode->i_mode)) { ret = nfs_sync_mapping(mapping); if (ret < 0) return ret; } ret = invalidate_inode_pages2(mapping); if (ret < 0) return ret; } nfs_inc_stats(inode, NFSIOS_DATAINVALIDATE); dfprintk(PAGECACHE, "NFS: (%s/%Lu) data cache invalidated\n", inode->i_sb->s_id, (unsigned long long)NFS_FILEID(inode)); return 0; } /** * nfs_clear_invalid_mapping - Conditionally clear a mapping * @mapping: pointer to mapping * * If the NFS_INO_INVALID_DATA inode flag is set, clear the mapping. */ int nfs_clear_invalid_mapping(struct address_space *mapping) { struct inode *inode = mapping->host; struct nfs_inode *nfsi = NFS_I(inode); unsigned long *bitlock = &nfsi->flags; int ret = 0; /* * We must clear NFS_INO_INVALID_DATA first to ensure that * invalidations that come in while we're shooting down the mappings * are respected. But, that leaves a race window where one revalidator * can clear the flag, and then another checks it before the mapping * gets invalidated. Fix that by serializing access to this part of * the function. * * At the same time, we need to allow other tasks to see whether we * might be in the middle of invalidating the pages, so we only set * the bit lock here if it looks like we're going to be doing that. */ for (;;) { ret = wait_on_bit_action(bitlock, NFS_INO_INVALIDATING, nfs_wait_bit_killable, TASK_KILLABLE|TASK_FREEZABLE_UNSAFE); if (ret) goto out; smp_rmb(); /* pairs with smp_wmb() below */ if (test_bit(NFS_INO_INVALIDATING, bitlock)) continue; /* pairs with nfs_set_cache_invalid()'s smp_store_release() */ if (!(smp_load_acquire(&nfsi->cache_validity) & NFS_INO_INVALID_DATA)) goto out; /* Slow-path that double-checks with spinlock held */ spin_lock(&inode->i_lock); if (test_bit(NFS_INO_INVALIDATING, bitlock)) { spin_unlock(&inode->i_lock); continue; } if (nfsi->cache_validity & NFS_INO_INVALID_DATA) break; spin_unlock(&inode->i_lock); goto out; } set_bit(NFS_INO_INVALIDATING, bitlock); smp_wmb(); nfsi->cache_validity &= ~NFS_INO_INVALID_DATA; nfs_ooo_clear(nfsi); spin_unlock(&inode->i_lock); trace_nfs_invalidate_mapping_enter(inode); ret = nfs_invalidate_mapping(inode, mapping); trace_nfs_invalidate_mapping_exit(inode, ret); clear_bit_unlock(NFS_INO_INVALIDATING, bitlock); smp_mb__after_atomic(); wake_up_bit(bitlock, NFS_INO_INVALIDATING); out: return ret; } bool nfs_mapping_need_revalidate_inode(struct inode *inode) { return nfs_check_cache_invalid(inode, NFS_INO_INVALID_CHANGE) || NFS_STALE(inode); } int nfs_revalidate_mapping_rcu(struct inode *inode) { struct nfs_inode *nfsi = NFS_I(inode); unsigned long *bitlock = &nfsi->flags; int ret = 0; if (IS_SWAPFILE(inode)) goto out; if (nfs_mapping_need_revalidate_inode(inode)) { ret = -ECHILD; goto out; } spin_lock(&inode->i_lock); if (test_bit(NFS_INO_INVALIDATING, bitlock) || (nfsi->cache_validity & NFS_INO_INVALID_DATA)) ret = -ECHILD; spin_unlock(&inode->i_lock); out: return ret; } /** * nfs_revalidate_mapping - Revalidate the pagecache * @inode: pointer to host inode * @mapping: pointer to mapping */ int nfs_revalidate_mapping(struct inode *inode, struct address_space *mapping) { /* swapfiles are not supposed to be shared. */ if (IS_SWAPFILE(inode)) return 0; if (nfs_mapping_need_revalidate_inode(inode)) { int ret = __nfs_revalidate_inode(NFS_SERVER(inode), inode); if (ret < 0) return ret; } return nfs_clear_invalid_mapping(mapping); } static bool nfs_file_has_writers(struct nfs_inode *nfsi) { struct inode *inode = &nfsi->vfs_inode; if (!S_ISREG(inode->i_mode)) return false; if (list_empty(&nfsi->open_files)) return false; return inode_is_open_for_write(inode); } static bool nfs_file_has_buffered_writers(struct nfs_inode *nfsi) { return nfs_file_has_writers(nfsi) && nfs_file_io_is_buffered(nfsi); } static void nfs_wcc_update_inode(struct inode *inode, struct nfs_fattr *fattr) { struct timespec64 ts; if ((fattr->valid & NFS_ATTR_FATTR_PRECHANGE) && (fattr->valid & NFS_ATTR_FATTR_CHANGE) && inode_eq_iversion_raw(inode, fattr->pre_change_attr)) { inode_set_iversion_raw(inode, fattr->change_attr); if (S_ISDIR(inode->i_mode)) nfs_set_cache_invalid(inode, NFS_INO_INVALID_DATA); else if (nfs_server_capable(inode, NFS_CAP_XATTR)) nfs_set_cache_invalid(inode, NFS_INO_INVALID_XATTR); } /* If we have atomic WCC data, we may update some attributes */ ts = inode_get_ctime(inode); if ((fattr->valid & NFS_ATTR_FATTR_PRECTIME) && (fattr->valid & NFS_ATTR_FATTR_CTIME) && timespec64_equal(&ts, &fattr->pre_ctime)) { inode_set_ctime_to_ts(inode, fattr->ctime); } ts = inode_get_mtime(inode); if ((fattr->valid & NFS_ATTR_FATTR_PREMTIME) && (fattr->valid & NFS_ATTR_FATTR_MTIME) && timespec64_equal(&ts, &fattr->pre_mtime)) { inode_set_mtime_to_ts(inode, fattr->mtime); } if ((fattr->valid & NFS_ATTR_FATTR_PRESIZE) && (fattr->valid & NFS_ATTR_FATTR_SIZE) && i_size_read(inode) == nfs_size_to_loff_t(fattr->pre_size) && !nfs_have_writebacks(inode)) { trace_nfs_size_wcc(inode, fattr->size); i_size_write(inode, nfs_size_to_loff_t(fattr->size)); } } /** * nfs_check_inode_attributes - verify consistency of the inode attribute cache * @inode: pointer to inode * @fattr: updated attributes * * Verifies the attribute cache. If we have just changed the attributes, * so that fattr carries weak cache consistency data, then it may * also update the ctime/mtime/change_attribute. */ static int nfs_check_inode_attributes(struct inode *inode, struct nfs_fattr *fattr) { struct nfs_inode *nfsi = NFS_I(inode); loff_t cur_size, new_isize; unsigned long invalid = 0; struct timespec64 ts; if (nfs_have_delegated_attributes(inode)) return 0; if (!(fattr->valid & NFS_ATTR_FATTR_FILEID)) { /* Only a mounted-on-fileid? Just exit */ if (fattr->valid & NFS_ATTR_FATTR_MOUNTED_ON_FILEID) return 0; /* Has the inode gone and changed behind our back? */ } else if (nfsi->fileid != fattr->fileid) { /* Is this perhaps the mounted-on fileid? */ if ((fattr->valid & NFS_ATTR_FATTR_MOUNTED_ON_FILEID) && nfsi->fileid == fattr->mounted_on_fileid) return 0; return -ESTALE; } if ((fattr->valid & NFS_ATTR_FATTR_TYPE) && inode_wrong_type(inode, fattr->mode)) return -ESTALE; if (!nfs_file_has_buffered_writers(nfsi)) { /* Verify a few of the more important attributes */ if ((fattr->valid & NFS_ATTR_FATTR_CHANGE) != 0 && !inode_eq_iversion_raw(inode, fattr->change_attr)) invalid |= NFS_INO_INVALID_CHANGE; ts = inode_get_mtime(inode); if ((fattr->valid & NFS_ATTR_FATTR_MTIME) && !timespec64_equal(&ts, &fattr->mtime)) invalid |= NFS_INO_INVALID_MTIME; ts = inode_get_ctime(inode); if ((fattr->valid & NFS_ATTR_FATTR_CTIME) && !timespec64_equal(&ts, &fattr->ctime)) invalid |= NFS_INO_INVALID_CTIME; if (fattr->valid & NFS_ATTR_FATTR_SIZE) { cur_size = i_size_read(inode); new_isize = nfs_size_to_loff_t(fattr->size); if (cur_size != new_isize) invalid |= NFS_INO_INVALID_SIZE; } } /* Have any file permissions changed? */ if ((fattr->valid & NFS_ATTR_FATTR_MODE) && (inode->i_mode & S_IALLUGO) != (fattr->mode & S_IALLUGO)) invalid |= NFS_INO_INVALID_MODE; if ((fattr->valid & NFS_ATTR_FATTR_OWNER) && !uid_eq(inode->i_uid, fattr->uid)) invalid |= NFS_INO_INVALID_OTHER; if ((fattr->valid & NFS_ATTR_FATTR_GROUP) && !gid_eq(inode->i_gid, fattr->gid)) invalid |= NFS_INO_INVALID_OTHER; /* Has the link count changed? */ if ((fattr->valid & NFS_ATTR_FATTR_NLINK) && inode->i_nlink != fattr->nlink) invalid |= NFS_INO_INVALID_NLINK; ts = inode_get_atime(inode); if ((fattr->valid & NFS_ATTR_FATTR_ATIME) && !timespec64_equal(&ts, &fattr->atime)) invalid |= NFS_INO_INVALID_ATIME; if (invalid != 0) nfs_set_cache_invalid(inode, invalid); nfsi->read_cache_jiffies = fattr->time_start; return 0; } static atomic_long_t nfs_attr_generation_counter; static unsigned long nfs_read_attr_generation_counter(void) { return atomic_long_read(&nfs_attr_generation_counter); } unsigned long nfs_inc_attr_generation_counter(void) { return atomic_long_inc_return(&nfs_attr_generation_counter); } EXPORT_SYMBOL_GPL(nfs_inc_attr_generation_counter); void nfs_fattr_init(struct nfs_fattr *fattr) { fattr->valid = 0; fattr->time_start = jiffies; fattr->gencount = nfs_inc_attr_generation_counter(); fattr->owner_name = NULL; fattr->group_name = NULL; fattr->mdsthreshold = NULL; } EXPORT_SYMBOL_GPL(nfs_fattr_init); /** * nfs_fattr_set_barrier * @fattr: attributes * * Used to set a barrier after an attribute was updated. This * barrier ensures that older attributes from RPC calls that may * have raced with our update cannot clobber these new values. * Note that you are still responsible for ensuring that other * operations which change the attribute on the server do not * collide. */ void nfs_fattr_set_barrier(struct nfs_fattr *fattr) { fattr->gencount = nfs_inc_attr_generation_counter(); } struct nfs_fattr *nfs_alloc_fattr(void) { struct nfs_fattr *fattr; fattr = kmalloc(sizeof(*fattr), GFP_KERNEL); if (fattr != NULL) { nfs_fattr_init(fattr); fattr->label = NULL; } return fattr; } EXPORT_SYMBOL_GPL(nfs_alloc_fattr); struct nfs_fattr *nfs_alloc_fattr_with_label(struct nfs_server *server) { struct nfs_fattr *fattr = nfs_alloc_fattr(); if (!fattr) return NULL; fattr->label = nfs4_label_alloc(server, GFP_KERNEL); if (IS_ERR(fattr->label)) { kfree(fattr); return NULL; } return fattr; } EXPORT_SYMBOL_GPL(nfs_alloc_fattr_with_label); struct nfs_fh *nfs_alloc_fhandle(void) { struct nfs_fh *fh; fh = kmalloc(sizeof(struct nfs_fh), GFP_KERNEL); if (fh != NULL) fh->size = 0; return fh; } EXPORT_SYMBOL_GPL(nfs_alloc_fhandle); #ifdef NFS_DEBUG /* * _nfs_display_fhandle_hash - calculate the crc32 hash for the filehandle * in the same way that wireshark does * * @fh: file handle * * For debugging only. */ u32 _nfs_display_fhandle_hash(const struct nfs_fh *fh) { /* wireshark uses 32-bit AUTODIN crc and does a bitwise * not on the result */ return nfs_fhandle_hash(fh); } EXPORT_SYMBOL_GPL(_nfs_display_fhandle_hash); /* * _nfs_display_fhandle - display an NFS file handle on the console * * @fh: file handle to display * @caption: display caption * * For debugging only. */ void _nfs_display_fhandle(const struct nfs_fh *fh, const char *caption) { unsigned short i; if (fh == NULL || fh->size == 0) { printk(KERN_DEFAULT "%s at %p is empty\n", caption, fh); return; } printk(KERN_DEFAULT "%s at %p is %u bytes, crc: 0x%08x:\n", caption, fh, fh->size, _nfs_display_fhandle_hash(fh)); for (i = 0; i < fh->size; i += 16) { __be32 *pos = (__be32 *)&fh->data[i]; switch ((fh->size - i - 1) >> 2) { case 0: printk(KERN_DEFAULT " %08x\n", be32_to_cpup(pos)); break; case 1: printk(KERN_DEFAULT " %08x %08x\n", be32_to_cpup(pos), be32_to_cpup(pos + 1)); break; case 2: printk(KERN_DEFAULT " %08x %08x %08x\n", be32_to_cpup(pos), be32_to_cpup(pos + 1), be32_to_cpup(pos + 2)); break; default: printk(KERN_DEFAULT " %08x %08x %08x %08x\n", be32_to_cpup(pos), be32_to_cpup(pos + 1), be32_to_cpup(pos + 2), be32_to_cpup(pos + 3)); } } } EXPORT_SYMBOL_GPL(_nfs_display_fhandle); #endif /** * nfs_inode_attrs_cmp_generic - compare attributes * @fattr: attributes * @inode: pointer to inode * * Attempt to divine whether or not an RPC call reply carrying stale * attributes got scheduled after another call carrying updated ones. * Note also the check for wraparound of 'attr_gencount' * * The function returns '1' if it thinks the attributes in @fattr are * more recent than the ones cached in @inode. Otherwise it returns * the value '0'. */ static int nfs_inode_attrs_cmp_generic(const struct nfs_fattr *fattr, const struct inode *inode) { unsigned long attr_gencount = NFS_I(inode)->attr_gencount; return (long)(fattr->gencount - attr_gencount) > 0 || (long)(attr_gencount - nfs_read_attr_generation_counter()) > 0; } /** * nfs_inode_attrs_cmp_monotonic - compare attributes * @fattr: attributes * @inode: pointer to inode * * Attempt to divine whether or not an RPC call reply carrying stale * attributes got scheduled after another call carrying updated ones. * * We assume that the server observes monotonic semantics for * the change attribute, so a larger value means that the attributes in * @fattr are more recent, in which case the function returns the * value '1'. * A return value of '0' indicates no measurable change * A return value of '-1' means that the attributes in @inode are * more recent. */ static int nfs_inode_attrs_cmp_monotonic(const struct nfs_fattr *fattr, const struct inode *inode) { s64 diff = fattr->change_attr - inode_peek_iversion_raw(inode); if (diff > 0) return 1; return diff == 0 ? 0 : -1; } /** * nfs_inode_attrs_cmp_strict_monotonic - compare attributes * @fattr: attributes * @inode: pointer to inode * * Attempt to divine whether or not an RPC call reply carrying stale * attributes got scheduled after another call carrying updated ones. * * We assume that the server observes strictly monotonic semantics for * the change attribute, so a larger value means that the attributes in * @fattr are more recent, in which case the function returns the * value '1'. * A return value of '-1' means that the attributes in @inode are * more recent or unchanged. */ static int nfs_inode_attrs_cmp_strict_monotonic(const struct nfs_fattr *fattr, const struct inode *inode) { return nfs_inode_attrs_cmp_monotonic(fattr, inode) > 0 ? 1 : -1; } /** * nfs_inode_attrs_cmp - compare attributes * @fattr: attributes * @inode: pointer to inode * * This function returns '1' if it thinks the attributes in @fattr are * more recent than the ones cached in @inode. It returns '-1' if * the attributes in @inode are more recent than the ones in @fattr, * and it returns 0 if not sure. */ static int nfs_inode_attrs_cmp(const struct nfs_fattr *fattr, const struct inode *inode) { if (nfs_inode_attrs_cmp_generic(fattr, inode) > 0) return 1; switch (NFS_SERVER(inode)->change_attr_type) { case NFS4_CHANGE_TYPE_IS_UNDEFINED: break; case NFS4_CHANGE_TYPE_IS_TIME_METADATA: if (!(fattr->valid & NFS_ATTR_FATTR_CHANGE)) break; return nfs_inode_attrs_cmp_monotonic(fattr, inode); default: if (!(fattr->valid & NFS_ATTR_FATTR_CHANGE)) break; return nfs_inode_attrs_cmp_strict_monotonic(fattr, inode); } return 0; } /** * nfs_inode_finish_partial_attr_update - complete a previous inode update * @fattr: attributes * @inode: pointer to inode * * Returns '1' if the last attribute update left the inode cached * attributes in a partially unrevalidated state, and @fattr * matches the change attribute of that partial update. * Otherwise returns '0'. */ static int nfs_inode_finish_partial_attr_update(const struct nfs_fattr *fattr, const struct inode *inode) { const unsigned long check_valid = NFS_INO_INVALID_ATIME | NFS_INO_INVALID_CTIME | NFS_INO_INVALID_MTIME | NFS_INO_INVALID_SIZE | NFS_INO_INVALID_BLOCKS | NFS_INO_INVALID_OTHER | NFS_INO_INVALID_NLINK; unsigned long cache_validity = NFS_I(inode)->cache_validity; enum nfs4_change_attr_type ctype = NFS_SERVER(inode)->change_attr_type; if (ctype != NFS4_CHANGE_TYPE_IS_UNDEFINED && !(cache_validity & NFS_INO_INVALID_CHANGE) && (cache_validity & check_valid) != 0 && (fattr->valid & NFS_ATTR_FATTR_CHANGE) != 0 && nfs_inode_attrs_cmp_monotonic(fattr, inode) == 0) return 1; return 0; } static void nfs_ooo_merge(struct nfs_inode *nfsi, u64 start, u64 end) { int i, cnt; if (nfsi->cache_validity & NFS_INO_DATA_INVAL_DEFER) /* No point merging anything */ return; if (!nfsi->ooo) { nfsi->ooo = kmalloc(sizeof(*nfsi->ooo), GFP_ATOMIC); if (!nfsi->ooo) { nfsi->cache_validity |= NFS_INO_DATA_INVAL_DEFER; return; } nfsi->ooo->cnt = 0; } /* add this range, merging if possible */ cnt = nfsi->ooo->cnt; for (i = 0; i < cnt; i++) { if (end == nfsi->ooo->gap[i].start) end = nfsi->ooo->gap[i].end; else if (start == nfsi->ooo->gap[i].end) start = nfsi->ooo->gap[i].start; else continue; /* Remove 'i' from table and loop to insert the new range */ cnt -= 1; nfsi->ooo->gap[i] = nfsi->ooo->gap[cnt]; i = -1; } if (start != end) { if (cnt >= ARRAY_SIZE(nfsi->ooo->gap)) { nfsi->cache_validity |= NFS_INO_DATA_INVAL_DEFER; kfree(nfsi->ooo); nfsi->ooo = NULL; return; } nfsi->ooo->gap[cnt].start = start; nfsi->ooo->gap[cnt].end = end; cnt += 1; } nfsi->ooo->cnt = cnt; } static void nfs_ooo_record(struct nfs_inode *nfsi, struct nfs_fattr *fattr) { /* This reply was out-of-order, so record in the * pre/post change id, possibly cancelling * gaps created when iversion was jumpped forward. */ if ((fattr->valid & NFS_ATTR_FATTR_CHANGE) && (fattr->valid & NFS_ATTR_FATTR_PRECHANGE)) nfs_ooo_merge(nfsi, fattr->change_attr, fattr->pre_change_attr); } static int nfs_refresh_inode_locked(struct inode *inode, struct nfs_fattr *fattr) { int attr_cmp = nfs_inode_attrs_cmp(fattr, inode); int ret = 0; trace_nfs_refresh_inode_enter(inode); if (attr_cmp > 0 || nfs_inode_finish_partial_attr_update(fattr, inode)) ret = nfs_update_inode(inode, fattr); else { nfs_ooo_record(NFS_I(inode), fattr); if (attr_cmp == 0) ret = nfs_check_inode_attributes(inode, fattr); } trace_nfs_refresh_inode_exit(inode, ret); return ret; } /** * nfs_refresh_inode - try to update the inode attribute cache * @inode: pointer to inode * @fattr: updated attributes * * Check that an RPC call that returned attributes has not overlapped with * other recent updates of the inode metadata, then decide whether it is * safe to do a full update of the inode attributes, or whether just to * call nfs_check_inode_attributes. */ int nfs_refresh_inode(struct inode *inode, struct nfs_fattr *fattr) { int status; if ((fattr->valid & NFS_ATTR_FATTR) == 0) return 0; spin_lock(&inode->i_lock); status = nfs_refresh_inode_locked(inode, fattr); spin_unlock(&inode->i_lock); return status; } EXPORT_SYMBOL_GPL(nfs_refresh_inode); static int nfs_post_op_update_inode_locked(struct inode *inode, struct nfs_fattr *fattr, unsigned int invalid) { if (S_ISDIR(inode->i_mode)) invalid |= NFS_INO_INVALID_DATA; nfs_set_cache_invalid(inode, invalid); if ((fattr->valid & NFS_ATTR_FATTR) == 0) return 0; return nfs_refresh_inode_locked(inode, fattr); } /** * nfs_post_op_update_inode - try to update the inode attribute cache * @inode: pointer to inode * @fattr: updated attributes * * After an operation that has changed the inode metadata, mark the * attribute cache as being invalid, then try to update it. * * NB: if the server didn't return any post op attributes, this * function will force the retrieval of attributes before the next * NFS request. Thus it should be used only for operations that * are expected to change one or more attributes, to avoid * unnecessary NFS requests and trips through nfs_update_inode(). */ int nfs_post_op_update_inode(struct inode *inode, struct nfs_fattr *fattr) { int status; spin_lock(&inode->i_lock); nfs_fattr_set_barrier(fattr); status = nfs_post_op_update_inode_locked(inode, fattr, NFS_INO_INVALID_CHANGE | NFS_INO_INVALID_CTIME | NFS_INO_REVAL_FORCED); spin_unlock(&inode->i_lock); return status; } EXPORT_SYMBOL_GPL(nfs_post_op_update_inode); /** * nfs_post_op_update_inode_force_wcc_locked - update the inode attribute cache * @inode: pointer to inode * @fattr: updated attributes * * After an operation that has changed the inode metadata, mark the * attribute cache as being invalid, then try to update it. Fake up * weak cache consistency data, if none exist. * * This function is mainly designed to be used by the ->write_done() functions. */ int nfs_post_op_update_inode_force_wcc_locked(struct inode *inode, struct nfs_fattr *fattr) { int attr_cmp = nfs_inode_attrs_cmp(fattr, inode); int status; /* Don't do a WCC update if these attributes are already stale */ if (attr_cmp < 0) return 0; if ((fattr->valid & NFS_ATTR_FATTR) == 0 || !attr_cmp) { /* Record the pre/post change info before clearing PRECHANGE */ nfs_ooo_record(NFS_I(inode), fattr); fattr->valid &= ~(NFS_ATTR_FATTR_PRECHANGE | NFS_ATTR_FATTR_PRESIZE | NFS_ATTR_FATTR_PREMTIME | NFS_ATTR_FATTR_PRECTIME); goto out_noforce; } if ((fattr->valid & NFS_ATTR_FATTR_CHANGE) != 0 && (fattr->valid & NFS_ATTR_FATTR_PRECHANGE) == 0) { fattr->pre_change_attr = inode_peek_iversion_raw(inode); fattr->valid |= NFS_ATTR_FATTR_PRECHANGE; } if ((fattr->valid & NFS_ATTR_FATTR_CTIME) != 0 && (fattr->valid & NFS_ATTR_FATTR_PRECTIME) == 0) { fattr->pre_ctime = inode_get_ctime(inode); fattr->valid |= NFS_ATTR_FATTR_PRECTIME; } if ((fattr->valid & NFS_ATTR_FATTR_MTIME) != 0 && (fattr->valid & NFS_ATTR_FATTR_PREMTIME) == 0) { fattr->pre_mtime = inode_get_mtime(inode); fattr->valid |= NFS_ATTR_FATTR_PREMTIME; } if ((fattr->valid & NFS_ATTR_FATTR_SIZE) != 0 && (fattr->valid & NFS_ATTR_FATTR_PRESIZE) == 0) { fattr->pre_size = i_size_read(inode); fattr->valid |= NFS_ATTR_FATTR_PRESIZE; } out_noforce: status = nfs_post_op_update_inode_locked(inode, fattr, NFS_INO_INVALID_CHANGE | NFS_INO_INVALID_CTIME | NFS_INO_INVALID_MTIME | NFS_INO_INVALID_BLOCKS); return status; } /** * nfs_post_op_update_inode_force_wcc - try to update the inode attribute cache * @inode: pointer to inode * @fattr: updated attributes * * After an operation that has changed the inode metadata, mark the * attribute cache as being invalid, then try to update it. Fake up * weak cache consistency data, if none exist. * * This function is mainly designed to be used by the ->write_done() functions. */ int nfs_post_op_update_inode_force_wcc(struct inode *inode, struct nfs_fattr *fattr) { int status; spin_lock(&inode->i_lock); nfs_fattr_set_barrier(fattr); status = nfs_post_op_update_inode_force_wcc_locked(inode, fattr); spin_unlock(&inode->i_lock); return status; } EXPORT_SYMBOL_GPL(nfs_post_op_update_inode_force_wcc); /* * Many nfs protocol calls return the new file attributes after * an operation. Here we update the inode to reflect the state * of the server's inode. * * This is a bit tricky because we have to make sure all dirty pages * have been sent off to the server before calling invalidate_inode_pages. * To make sure no other process adds more write requests while we try * our best to flush them, we make them sleep during the attribute refresh. * * A very similar scenario holds for the dir cache. */ static int nfs_update_inode(struct inode *inode, struct nfs_fattr *fattr) { struct nfs_server *server = NFS_SERVER(inode); struct nfs_inode *nfsi = NFS_I(inode); loff_t cur_isize, new_isize; u64 fattr_supported = server->fattr_valid; unsigned long invalid = 0; unsigned long now = jiffies; unsigned long save_cache_validity; bool have_writers = nfs_file_has_buffered_writers(nfsi); bool cache_revalidated = true; bool attr_changed = false; bool have_delegation; dfprintk(VFS, "NFS: %s(%s/%lu fh_crc=0x%08x ct=%d info=0x%x)\n", __func__, inode->i_sb->s_id, inode->i_ino, nfs_display_fhandle_hash(NFS_FH(inode)), atomic_read(&inode->i_count), fattr->valid); if (!(fattr->valid & NFS_ATTR_FATTR_FILEID)) { /* Only a mounted-on-fileid? Just exit */ if (fattr->valid & NFS_ATTR_FATTR_MOUNTED_ON_FILEID) return 0; /* Has the inode gone and changed behind our back? */ } else if (nfsi->fileid != fattr->fileid) { /* Is this perhaps the mounted-on fileid? */ if ((fattr->valid & NFS_ATTR_FATTR_MOUNTED_ON_FILEID) && nfsi->fileid == fattr->mounted_on_fileid) return 0; printk(KERN_ERR "NFS: server %s error: fileid changed\n" "fsid %s: expected fileid 0x%Lx, got 0x%Lx\n", NFS_SERVER(inode)->nfs_client->cl_hostname, inode->i_sb->s_id, (long long)nfsi->fileid, (long long)fattr->fileid); goto out_err; } /* * Make sure the inode's type hasn't changed. */ if ((fattr->valid & NFS_ATTR_FATTR_TYPE) && inode_wrong_type(inode, fattr->mode)) { /* * Big trouble! The inode has become a different object. */ printk(KERN_DEBUG "NFS: %s: inode %lu mode changed, %07o to %07o\n", __func__, inode->i_ino, inode->i_mode, fattr->mode); goto out_err; } /* Update the fsid? */ if (S_ISDIR(inode->i_mode) && (fattr->valid & NFS_ATTR_FATTR_FSID) && !nfs_fsid_equal(&server->fsid, &fattr->fsid) && !IS_AUTOMOUNT(inode)) server->fsid = fattr->fsid; /* Save the delegation state before clearing cache_validity */ have_delegation = nfs_have_delegated_attributes(inode); /* * Update the read time so we don't revalidate too often. */ nfsi->read_cache_jiffies = fattr->time_start; /* Fix up any delegated attributes in the struct nfs_fattr */ nfs_fattr_fixup_delegated(inode, fattr); save_cache_validity = nfsi->cache_validity; nfsi->cache_validity &= ~(NFS_INO_INVALID_ATTR | NFS_INO_INVALID_ATIME | NFS_INO_REVAL_FORCED | NFS_INO_INVALID_BLOCKS); /* Do atomic weak cache consistency updates */ nfs_wcc_update_inode(inode, fattr); if (pnfs_layoutcommit_outstanding(inode)) { nfsi->cache_validity |= save_cache_validity & (NFS_INO_INVALID_CHANGE | NFS_INO_INVALID_CTIME | NFS_INO_INVALID_MTIME | NFS_INO_INVALID_SIZE | NFS_INO_INVALID_BLOCKS); cache_revalidated = false; } /* More cache consistency checks */ if (fattr->valid & NFS_ATTR_FATTR_CHANGE) { if (!have_writers && nfsi->ooo && nfsi->ooo->cnt == 1 && nfsi->ooo->gap[0].end == inode_peek_iversion_raw(inode)) { /* There is one remaining gap that hasn't been * merged into iversion - do that now. */ inode_set_iversion_raw(inode, nfsi->ooo->gap[0].start); kfree(nfsi->ooo); nfsi->ooo = NULL; } if (!inode_eq_iversion_raw(inode, fattr->change_attr)) { /* Could it be a race with writeback? */ if (!(have_writers || have_delegation)) { invalid |= NFS_INO_INVALID_DATA | NFS_INO_INVALID_ACCESS | NFS_INO_INVALID_ACL | NFS_INO_INVALID_XATTR; /* Force revalidate of all attributes */ save_cache_validity |= NFS_INO_INVALID_CTIME | NFS_INO_INVALID_MTIME | NFS_INO_INVALID_SIZE | NFS_INO_INVALID_BLOCKS | NFS_INO_INVALID_NLINK | NFS_INO_INVALID_MODE | NFS_INO_INVALID_OTHER; if (S_ISDIR(inode->i_mode)) nfs_force_lookup_revalidate(inode); attr_changed = true; dprintk("NFS: change_attr change on server for file %s/%ld\n", inode->i_sb->s_id, inode->i_ino); } else if (!have_delegation) { nfs_ooo_record(nfsi, fattr); nfs_ooo_merge(nfsi, inode_peek_iversion_raw(inode), fattr->change_attr); } inode_set_iversion_raw(inode, fattr->change_attr); } } else { nfsi->cache_validity |= save_cache_validity & NFS_INO_INVALID_CHANGE; if (!have_delegation || (nfsi->cache_validity & NFS_INO_INVALID_CHANGE) != 0) cache_revalidated = false; } if (fattr->valid & NFS_ATTR_FATTR_MTIME) inode_set_mtime_to_ts(inode, fattr->mtime); else if (fattr_supported & NFS_ATTR_FATTR_MTIME) nfsi->cache_validity |= save_cache_validity & NFS_INO_INVALID_MTIME; if (fattr->valid & NFS_ATTR_FATTR_CTIME) inode_set_ctime_to_ts(inode, fattr->ctime); else if (fattr_supported & NFS_ATTR_FATTR_CTIME) nfsi->cache_validity |= save_cache_validity & NFS_INO_INVALID_CTIME; /* Check if our cached file size is stale */ if (fattr->valid & NFS_ATTR_FATTR_SIZE) { new_isize = nfs_size_to_loff_t(fattr->size); cur_isize = i_size_read(inode); if (new_isize != cur_isize && !have_delegation) { /* Do we perhaps have any outstanding writes, or has * the file grown beyond our last write? */ if (!nfs_have_writebacks(inode) || new_isize > cur_isize) { trace_nfs_size_update(inode, new_isize); i_size_write(inode, new_isize); if (!have_writers) invalid |= NFS_INO_INVALID_DATA; } } if (new_isize == 0 && !(fattr->valid & (NFS_ATTR_FATTR_SPACE_USED | NFS_ATTR_FATTR_BLOCKS_USED))) { fattr->du.nfs3.used = 0; fattr->valid |= NFS_ATTR_FATTR_SPACE_USED; } } else nfsi->cache_validity |= save_cache_validity & NFS_INO_INVALID_SIZE; if (fattr->valid & NFS_ATTR_FATTR_ATIME) inode_set_atime_to_ts(inode, fattr->atime); else if (fattr_supported & NFS_ATTR_FATTR_ATIME) nfsi->cache_validity |= save_cache_validity & NFS_INO_INVALID_ATIME; if (fattr->valid & NFS_ATTR_FATTR_MODE) { if ((inode->i_mode & S_IALLUGO) != (fattr->mode & S_IALLUGO)) { umode_t newmode = inode->i_mode & S_IFMT; newmode |= fattr->mode & S_IALLUGO; inode->i_mode = newmode; invalid |= NFS_INO_INVALID_ACCESS | NFS_INO_INVALID_ACL; } } else if (fattr_supported & NFS_ATTR_FATTR_MODE) nfsi->cache_validity |= save_cache_validity & NFS_INO_INVALID_MODE; if (fattr->valid & NFS_ATTR_FATTR_OWNER) { if (!uid_eq(inode->i_uid, fattr->uid)) { invalid |= NFS_INO_INVALID_ACCESS | NFS_INO_INVALID_ACL; inode->i_uid = fattr->uid; } } else if (fattr_supported & NFS_ATTR_FATTR_OWNER) nfsi->cache_validity |= save_cache_validity & NFS_INO_INVALID_OTHER; if (fattr->valid & NFS_ATTR_FATTR_GROUP) { if (!gid_eq(inode->i_gid, fattr->gid)) { invalid |= NFS_INO_INVALID_ACCESS | NFS_INO_INVALID_ACL; inode->i_gid = fattr->gid; } } else if (fattr_supported & NFS_ATTR_FATTR_GROUP) nfsi->cache_validity |= save_cache_validity & NFS_INO_INVALID_OTHER; if (fattr->valid & NFS_ATTR_FATTR_NLINK) { if (inode->i_nlink != fattr->nlink) set_nlink(inode, fattr->nlink); } else if (fattr_supported & NFS_ATTR_FATTR_NLINK) nfsi->cache_validity |= save_cache_validity & NFS_INO_INVALID_NLINK; if (fattr->valid & NFS_ATTR_FATTR_SPACE_USED) { /* * report the blocks in 512byte units */ inode->i_blocks = nfs_calc_block_size(fattr->du.nfs3.used); } else if (fattr_supported & NFS_ATTR_FATTR_SPACE_USED) nfsi->cache_validity |= save_cache_validity & NFS_INO_INVALID_BLOCKS; if (fattr->valid & NFS_ATTR_FATTR_BLOCKS_USED) inode->i_blocks = fattr->du.nfs2.blocks; else if (fattr_supported & NFS_ATTR_FATTR_BLOCKS_USED) nfsi->cache_validity |= save_cache_validity & NFS_INO_INVALID_BLOCKS; /* Update attrtimeo value if we're out of the unstable period */ if (attr_changed) { nfs_inc_stats(inode, NFSIOS_ATTRINVALIDATE); nfsi->attrtimeo = NFS_MINATTRTIMEO(inode); nfsi->attrtimeo_timestamp = now; /* Set barrier to be more recent than all outstanding updates */ nfsi->attr_gencount = nfs_inc_attr_generation_counter(); } else { if (cache_revalidated) { if (!time_in_range_open(now, nfsi->attrtimeo_timestamp, nfsi->attrtimeo_timestamp + nfsi->attrtimeo)) { nfsi->attrtimeo <<= 1; if (nfsi->attrtimeo > NFS_MAXATTRTIMEO(inode)) nfsi->attrtimeo = NFS_MAXATTRTIMEO(inode); } nfsi->attrtimeo_timestamp = now; } /* Set the barrier to be more recent than this fattr */ if ((long)(fattr->gencount - nfsi->attr_gencount) > 0) nfsi->attr_gencount = fattr->gencount; } /* Don't invalidate the data if we were to blame */ if (!(S_ISREG(inode->i_mode) || S_ISDIR(inode->i_mode) || S_ISLNK(inode->i_mode))) invalid &= ~NFS_INO_INVALID_DATA; nfs_set_cache_invalid(inode, invalid); return 0; out_err: /* * No need to worry about unhashing the dentry, as the * lookup validation will know that the inode is bad. * (But we fall through to invalidate the caches.) */ nfs_set_inode_stale_locked(inode); return -ESTALE; } struct inode *nfs_alloc_inode(struct super_block *sb) { struct nfs_inode *nfsi; nfsi = alloc_inode_sb(sb, nfs_inode_cachep, GFP_KERNEL); if (!nfsi) return NULL; nfsi->flags = 0UL; nfsi->cache_validity = 0UL; nfsi->ooo = NULL; #if IS_ENABLED(CONFIG_NFS_V4) nfsi->nfs4_acl = NULL; #endif /* CONFIG_NFS_V4 */ #ifdef CONFIG_NFS_V4_2 nfsi->xattr_cache = NULL; #endif nfs_netfs_inode_init(nfsi); return &nfsi->vfs_inode; } EXPORT_SYMBOL_GPL(nfs_alloc_inode); void nfs_free_inode(struct inode *inode) { kfree(NFS_I(inode)->ooo); kmem_cache_free(nfs_inode_cachep, NFS_I(inode)); } EXPORT_SYMBOL_GPL(nfs_free_inode); static inline void nfs4_init_once(struct nfs_inode *nfsi) { #if IS_ENABLED(CONFIG_NFS_V4) INIT_LIST_HEAD(&nfsi->open_states); nfsi->delegation = NULL; init_rwsem(&nfsi->rwsem); nfsi->layout = NULL; #endif } static void init_once(void *foo) { struct nfs_inode *nfsi = foo; inode_init_once(&nfsi->vfs_inode); INIT_LIST_HEAD(&nfsi->open_files); INIT_LIST_HEAD(&nfsi->access_cache_entry_lru); INIT_LIST_HEAD(&nfsi->access_cache_inode_lru); nfs4_init_once(nfsi); } static int __init nfs_init_inodecache(void) { nfs_inode_cachep = kmem_cache_create("nfs_inode_cache", sizeof(struct nfs_inode), 0, (SLAB_RECLAIM_ACCOUNT| SLAB_ACCOUNT), init_once); if (nfs_inode_cachep == NULL) return -ENOMEM; return 0; } static void nfs_destroy_inodecache(void) { /* * Make sure all delayed rcu free inodes are flushed before we * destroy cache. */ rcu_barrier(); kmem_cache_destroy(nfs_inode_cachep); } struct workqueue_struct *nfslocaliod_workqueue; struct workqueue_struct *nfsiod_workqueue; EXPORT_SYMBOL_GPL(nfsiod_workqueue); /* * Destroy the nfsiod workqueues */ static void nfsiod_stop(void) { struct workqueue_struct *wq; wq = nfsiod_workqueue; if (wq != NULL) { nfsiod_workqueue = NULL; destroy_workqueue(wq); } #if IS_ENABLED(CONFIG_NFS_LOCALIO) wq = nfslocaliod_workqueue; if (wq != NULL) { nfslocaliod_workqueue = NULL; destroy_workqueue(wq); } #endif /* CONFIG_NFS_LOCALIO */ } /* * Start the nfsiod workqueues */ static int nfsiod_start(void) { dprintk("RPC: creating workqueue nfsiod\n"); nfsiod_workqueue = alloc_workqueue("nfsiod", WQ_MEM_RECLAIM | WQ_UNBOUND, 0); if (nfsiod_workqueue == NULL) return -ENOMEM; #if IS_ENABLED(CONFIG_NFS_LOCALIO) /* * localio writes need to use a normal (non-memreclaim) workqueue. * When we start getting low on space, XFS goes and calls flush_work() on * a non-memreclaim work queue, which causes a priority inversion problem. */ dprintk("RPC: creating workqueue nfslocaliod\n"); nfslocaliod_workqueue = alloc_workqueue("nfslocaliod", WQ_UNBOUND, 0); if (unlikely(nfslocaliod_workqueue == NULL)) { nfsiod_stop(); return -ENOMEM; } #endif /* CONFIG_NFS_LOCALIO */ return 0; } unsigned int nfs_net_id; EXPORT_SYMBOL_GPL(nfs_net_id); static int nfs_net_init(struct net *net) { struct nfs_net *nn = net_generic(net, nfs_net_id); nfs_clients_init(net); if (!rpc_proc_register(net, &nn->rpcstats)) { nfs_clients_exit(net); return -ENOMEM; } return nfs_fs_proc_net_init(net); } static void nfs_net_exit(struct net *net) { rpc_proc_unregister(net, "nfs"); nfs_fs_proc_net_exit(net); nfs_clients_exit(net); } static struct pernet_operations nfs_net_ops = { .init = nfs_net_init, .exit = nfs_net_exit, .id = &nfs_net_id, .size = sizeof(struct nfs_net), }; /* * Initialize NFS */ static int __init init_nfs_fs(void) { int err; err = nfs_sysfs_init(); if (err < 0) goto out10; err = register_pernet_subsys(&nfs_net_ops); if (err < 0) goto out9; err = nfsiod_start(); if (err) goto out7; err = nfs_fs_proc_init(); if (err) goto out6; err = nfs_init_nfspagecache(); if (err) goto out5; err = nfs_init_inodecache(); if (err) goto out4; err = nfs_init_readpagecache(); if (err) goto out3; err = nfs_init_writepagecache(); if (err) goto out2; err = nfs_init_directcache(); if (err) goto out1; err = register_nfs_fs(); if (err) goto out0; return 0; out0: nfs_destroy_directcache(); out1: nfs_destroy_writepagecache(); out2: nfs_destroy_readpagecache(); out3: nfs_destroy_inodecache(); out4: nfs_destroy_nfspagecache(); out5: nfs_fs_proc_exit(); out6: nfsiod_stop(); out7: unregister_pernet_subsys(&nfs_net_ops); out9: nfs_sysfs_exit(); out10: return err; } static void __exit exit_nfs_fs(void) { nfs_destroy_directcache(); nfs_destroy_writepagecache(); nfs_destroy_readpagecache(); nfs_destroy_inodecache(); nfs_destroy_nfspagecache(); unregister_pernet_subsys(&nfs_net_ops); unregister_nfs_fs(); nfs_fs_proc_exit(); nfsiod_stop(); nfs_sysfs_exit(); } /* Not quite true; I just maintain it */ MODULE_AUTHOR("Olaf Kirch <okir@monad.swb.de>"); MODULE_DESCRIPTION("NFS client support"); MODULE_LICENSE("GPL"); module_param(enable_ino64, bool, 0644); module_init(init_nfs_fs) module_exit(exit_nfs_fs) |
| 3 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 | // SPDX-License-Identifier: GPL-2.0 /* * Copyright (C) 2013 Seiji Aguchi <seiji.aguchi@hds.com> */ #include <linux/jump_label.h> #include <linux/atomic.h> #include <asm/trace/exceptions.h> DEFINE_STATIC_KEY_FALSE(trace_pagefault_key); int trace_pagefault_reg(void) { static_branch_inc(&trace_pagefault_key); return 0; } void trace_pagefault_unreg(void) { static_branch_dec(&trace_pagefault_key); } |
| 6405 6406 2479 6390 6625 6629 5560 6579 2240 2243 220 217 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 | // SPDX-License-Identifier: GPL-2.0-only /* * lib/bitmap.c * Helper functions for bitmap.h. */ #include <linux/bitmap.h> #include <linux/bitops.h> #include <linux/ctype.h> #include <linux/device.h> #include <linux/export.h> #include <linux/slab.h> /** * DOC: bitmap introduction * * bitmaps provide an array of bits, implemented using an * array of unsigned longs. The number of valid bits in a * given bitmap does _not_ need to be an exact multiple of * BITS_PER_LONG. * * The possible unused bits in the last, partially used word * of a bitmap are 'don't care'. The implementation makes * no particular effort to keep them zero. It ensures that * their value will not affect the results of any operation. * The bitmap operations that return Boolean (bitmap_empty, * for example) or scalar (bitmap_weight, for example) results * carefully filter out these unused bits from impacting their * results. * * The byte ordering of bitmaps is more natural on little * endian architectures. See the big-endian headers * include/asm-ppc64/bitops.h and include/asm-s390/bitops.h * for the best explanations of this ordering. */ bool __bitmap_equal(const unsigned long *bitmap1, const unsigned long *bitmap2, unsigned int bits) { unsigned int k, lim = bits/BITS_PER_LONG; for (k = 0; k < lim; ++k) if (bitmap1[k] != bitmap2[k]) return false; if (bits % BITS_PER_LONG) if ((bitmap1[k] ^ bitmap2[k]) & BITMAP_LAST_WORD_MASK(bits)) return false; return true; } EXPORT_SYMBOL(__bitmap_equal); bool __bitmap_or_equal(const unsigned long *bitmap1, const unsigned long *bitmap2, const unsigned long *bitmap3, unsigned int bits) { unsigned int k, lim = bits / BITS_PER_LONG; unsigned long tmp; for (k = 0; k < lim; ++k) { if ((bitmap1[k] | bitmap2[k]) != bitmap3[k]) return false; } if (!(bits % BITS_PER_LONG)) return true; tmp = (bitmap1[k] | bitmap2[k]) ^ bitmap3[k]; return (tmp & BITMAP_LAST_WORD_MASK(bits)) == 0; } void __bitmap_complement(unsigned long *dst, const unsigned long *src, unsigned int bits) { unsigned int k, lim = BITS_TO_LONGS(bits); for (k = 0; k < lim; ++k) dst[k] = ~src[k]; } EXPORT_SYMBOL(__bitmap_complement); /** * __bitmap_shift_right - logical right shift of the bits in a bitmap * @dst : destination bitmap * @src : source bitmap * @shift : shift by this many bits * @nbits : bitmap size, in bits * * Shifting right (dividing) means moving bits in the MS -> LS bit * direction. Zeros are fed into the vacated MS positions and the * LS bits shifted off the bottom are lost. */ void __bitmap_shift_right(unsigned long *dst, const unsigned long *src, unsigned shift, unsigned nbits) { unsigned k, lim = BITS_TO_LONGS(nbits); unsigned off = shift/BITS_PER_LONG, rem = shift % BITS_PER_LONG; unsigned long mask = BITMAP_LAST_WORD_MASK(nbits); for (k = 0; off + k < lim; ++k) { unsigned long upper, lower; /* * If shift is not word aligned, take lower rem bits of * word above and make them the top rem bits of result. */ if (!rem || off + k + 1 >= lim) upper = 0; else { upper = src[off + k + 1]; if (off + k + 1 == lim - 1) upper &= mask; upper <<= (BITS_PER_LONG - rem); } lower = src[off + k]; if (off + k == lim - 1) lower &= mask; lower >>= rem; dst[k] = lower | upper; } if (off) memset(&dst[lim - off], 0, off*sizeof(unsigned long)); } EXPORT_SYMBOL(__bitmap_shift_right); /** * __bitmap_shift_left - logical left shift of the bits in a bitmap * @dst : destination bitmap * @src : source bitmap * @shift : shift by this many bits * @nbits : bitmap size, in bits * * Shifting left (multiplying) means moving bits in the LS -> MS * direction. Zeros are fed into the vacated LS bit positions * and those MS bits shifted off the top are lost. */ void __bitmap_shift_left(unsigned long *dst, const unsigned long *src, unsigned int shift, unsigned int nbits) { int k; unsigned int lim = BITS_TO_LONGS(nbits); unsigned int off = shift/BITS_PER_LONG, rem = shift % BITS_PER_LONG; for (k = lim - off - 1; k >= 0; --k) { unsigned long upper, lower; /* * If shift is not word aligned, take upper rem bits of * word below and make them the bottom rem bits of result. */ if (rem && k > 0) lower = src[k - 1] >> (BITS_PER_LONG - rem); else lower = 0; upper = src[k] << rem; dst[k + off] = lower | upper; } if (off) memset(dst, 0, off*sizeof(unsigned long)); } EXPORT_SYMBOL(__bitmap_shift_left); /** * bitmap_cut() - remove bit region from bitmap and right shift remaining bits * @dst: destination bitmap, might overlap with src * @src: source bitmap * @first: start bit of region to be removed * @cut: number of bits to remove * @nbits: bitmap size, in bits * * Set the n-th bit of @dst iff the n-th bit of @src is set and * n is less than @first, or the m-th bit of @src is set for any * m such that @first <= n < nbits, and m = n + @cut. * * In pictures, example for a big-endian 32-bit architecture: * * The @src bitmap is:: * * 31 63 * | | * 10000000 11000001 11110010 00010101 10000000 11000001 01110010 00010101 * | | | | * 16 14 0 32 * * if @cut is 3, and @first is 14, bits 14-16 in @src are cut and @dst is:: * * 31 63 * | | * 10110000 00011000 00110010 00010101 00010000 00011000 00101110 01000010 * | | | * 14 (bit 17 0 32 * from @src) * * Note that @dst and @src might overlap partially or entirely. * * This is implemented in the obvious way, with a shift and carry * step for each moved bit. Optimisation is left as an exercise * for the compiler. */ void bitmap_cut(unsigned long *dst, const unsigned long *src, unsigned int first, unsigned int cut, unsigned int nbits) { unsigned int len = BITS_TO_LONGS(nbits); unsigned long keep = 0, carry; int i; if (first % BITS_PER_LONG) { keep = src[first / BITS_PER_LONG] & (~0UL >> (BITS_PER_LONG - first % BITS_PER_LONG)); } memmove(dst, src, len * sizeof(*dst)); while (cut--) { for (i = first / BITS_PER_LONG; i < len; i++) { if (i < len - 1) carry = dst[i + 1] & 1UL; else carry = 0; dst[i] = (dst[i] >> 1) | (carry << (BITS_PER_LONG - 1)); } } dst[first / BITS_PER_LONG] &= ~0UL << (first % BITS_PER_LONG); dst[first / BITS_PER_LONG] |= keep; } EXPORT_SYMBOL(bitmap_cut); bool __bitmap_and(unsigned long *dst, const unsigned long *bitmap1, const unsigned long *bitmap2, unsigned int bits) { unsigned int k; unsigned int lim = bits/BITS_PER_LONG; unsigned long result = 0; for (k = 0; k < lim; k++) result |= (dst[k] = bitmap1[k] & bitmap2[k]); if (bits % BITS_PER_LONG) result |= (dst[k] = bitmap1[k] & bitmap2[k] & BITMAP_LAST_WORD_MASK(bits)); return result != 0; } EXPORT_SYMBOL(__bitmap_and); void __bitmap_or(unsigned long *dst, const unsigned long *bitmap1, const unsigned long *bitmap2, unsigned int bits) { unsigned int k; unsigned int nr = BITS_TO_LONGS(bits); for (k = 0; k < nr; k++) dst[k] = bitmap1[k] | bitmap2[k]; } EXPORT_SYMBOL(__bitmap_or); void __bitmap_xor(unsigned long *dst, const unsigned long *bitmap1, const unsigned long *bitmap2, unsigned int bits) { unsigned int k; unsigned int nr = BITS_TO_LONGS(bits); for (k = 0; k < nr; k++) dst[k] = bitmap1[k] ^ bitmap2[k]; } EXPORT_SYMBOL(__bitmap_xor); bool __bitmap_andnot(unsigned long *dst, const unsigned long *bitmap1, const unsigned long *bitmap2, unsigned int bits) { unsigned int k; unsigned int lim = bits/BITS_PER_LONG; unsigned long result = 0; for (k = 0; k < lim; k++) result |= (dst[k] = bitmap1[k] & ~bitmap2[k]); if (bits % BITS_PER_LONG) result |= (dst[k] = bitmap1[k] & ~bitmap2[k] & BITMAP_LAST_WORD_MASK(bits)); return result != 0; } EXPORT_SYMBOL(__bitmap_andnot); void __bitmap_replace(unsigned long *dst, const unsigned long *old, const unsigned long *new, const unsigned long *mask, unsigned int nbits) { unsigned int k; unsigned int nr = BITS_TO_LONGS(nbits); for (k = 0; k < nr; k++) dst[k] = (old[k] & ~mask[k]) | (new[k] & mask[k]); } EXPORT_SYMBOL(__bitmap_replace); bool __bitmap_intersects(const unsigned long *bitmap1, const unsigned long *bitmap2, unsigned int bits) { unsigned int k, lim = bits/BITS_PER_LONG; for (k = 0; k < lim; ++k) if (bitmap1[k] & bitmap2[k]) return true; if (bits % BITS_PER_LONG) if ((bitmap1[k] & bitmap2[k]) & BITMAP_LAST_WORD_MASK(bits)) return true; return false; } EXPORT_SYMBOL(__bitmap_intersects); bool __bitmap_subset(const unsigned long *bitmap1, const unsigned long *bitmap2, unsigned int bits) { unsigned int k, lim = bits/BITS_PER_LONG; for (k = 0; k < lim; ++k) if (bitmap1[k] & ~bitmap2[k]) return false; if (bits % BITS_PER_LONG) if ((bitmap1[k] & ~bitmap2[k]) & BITMAP_LAST_WORD_MASK(bits)) return false; return true; } EXPORT_SYMBOL(__bitmap_subset); #define BITMAP_WEIGHT(FETCH, bits) \ ({ \ unsigned int __bits = (bits), idx, w = 0; \ \ for (idx = 0; idx < __bits / BITS_PER_LONG; idx++) \ w += hweight_long(FETCH); \ \ if (__bits % BITS_PER_LONG) \ w += hweight_long((FETCH) & BITMAP_LAST_WORD_MASK(__bits)); \ \ w; \ }) unsigned int __bitmap_weight(const unsigned long *bitmap, unsigned int bits) { return BITMAP_WEIGHT(bitmap[idx], bits); } EXPORT_SYMBOL(__bitmap_weight); unsigned int __bitmap_weight_and(const unsigned long *bitmap1, const unsigned long *bitmap2, unsigned int bits) { return BITMAP_WEIGHT(bitmap1[idx] & bitmap2[idx], bits); } EXPORT_SYMBOL(__bitmap_weight_and); unsigned int __bitmap_weight_andnot(const unsigned long *bitmap1, const unsigned long *bitmap2, unsigned int bits) { return BITMAP_WEIGHT(bitmap1[idx] & ~bitmap2[idx], bits); } EXPORT_SYMBOL(__bitmap_weight_andnot); void __bitmap_set(unsigned long *map, unsigned int start, int len) { unsigned long *p = map + BIT_WORD(start); const unsigned int size = start + len; int bits_to_set = BITS_PER_LONG - (start % BITS_PER_LONG); unsigned long mask_to_set = BITMAP_FIRST_WORD_MASK(start); while (len - bits_to_set >= 0) { *p |= mask_to_set; len -= bits_to_set; bits_to_set = BITS_PER_LONG; mask_to_set = ~0UL; p++; } if (len) { mask_to_set &= BITMAP_LAST_WORD_MASK(size); *p |= mask_to_set; } } EXPORT_SYMBOL(__bitmap_set); void __bitmap_clear(unsigned long *map, unsigned int start, int len) { unsigned long *p = map + BIT_WORD(start); const unsigned int size = start + len; int bits_to_clear = BITS_PER_LONG - (start % BITS_PER_LONG); unsigned long mask_to_clear = BITMAP_FIRST_WORD_MASK(start); while (len - bits_to_clear >= 0) { *p &= ~mask_to_clear; len -= bits_to_clear; bits_to_clear = BITS_PER_LONG; mask_to_clear = ~0UL; p++; } if (len) { mask_to_clear &= BITMAP_LAST_WORD_MASK(size); *p &= ~mask_to_clear; } } EXPORT_SYMBOL(__bitmap_clear); /** * bitmap_find_next_zero_area_off - find a contiguous aligned zero area * @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 * @align_offset: Alignment offset for zero area. * * The @align_mask should be one less than a power of 2; the effect is that * the bit offset of all zero areas this function finds plus @align_offset * is multiple of that power of 2. */ unsigned long bitmap_find_next_zero_area_off(unsigned long *map, unsigned long size, unsigned long start, unsigned int nr, unsigned long align_mask, unsigned long align_offset) { unsigned long index, end, i; again: index = find_next_zero_bit(map, size, start); /* Align allocation */ index = __ALIGN_MASK(index + align_offset, align_mask) - align_offset; end = index + nr; if (end > size) return end; i = find_next_bit(map, end, index); if (i < end) { start = i + 1; goto again; } return index; } EXPORT_SYMBOL(bitmap_find_next_zero_area_off); /** * bitmap_pos_to_ord - find ordinal of set bit at given position in bitmap * @buf: pointer to a bitmap * @pos: a bit position in @buf (0 <= @pos < @nbits) * @nbits: number of valid bit positions in @buf * * Map the bit at position @pos in @buf (of length @nbits) to the * ordinal of which set bit it is. If it is not set or if @pos * is not a valid bit position, map to -1. * * If for example, just bits 4 through 7 are set in @buf, then @pos * values 4 through 7 will get mapped to 0 through 3, respectively, * and other @pos values will get mapped to -1. When @pos value 7 * gets mapped to (returns) @ord value 3 in this example, that means * that bit 7 is the 3rd (starting with 0th) set bit in @buf. * * The bit positions 0 through @bits are valid positions in @buf. */ static int bitmap_pos_to_ord(const unsigned long *buf, unsigned int pos, unsigned int nbits) { if (pos >= nbits || !test_bit(pos, buf)) return -1; return bitmap_weight(buf, pos); } /** * bitmap_remap - Apply map defined by a pair of bitmaps to another bitmap * @dst: remapped result * @src: subset to be remapped * @old: defines domain of map * @new: defines range of map * @nbits: number of bits in each of these bitmaps * * Let @old and @new define a mapping of bit positions, such that * whatever position is held by the n-th set bit in @old is mapped * to the n-th set bit in @new. In the more general case, allowing * for the possibility that the weight 'w' of @new is less than the * weight of @old, map the position of the n-th set bit in @old to * the position of the m-th set bit in @new, where m == n % w. * * If either of the @old and @new bitmaps are empty, or if @src and * @dst point to the same location, then this routine copies @src * to @dst. * * The positions of unset bits in @old are mapped to themselves * (the identity map). * * Apply the above specified mapping to @src, placing the result in * @dst, clearing any bits previously set in @dst. * * For example, lets say that @old has bits 4 through 7 set, and * @new has bits 12 through 15 set. This defines the mapping of bit * position 4 to 12, 5 to 13, 6 to 14 and 7 to 15, and of all other * bit positions unchanged. So if say @src comes into this routine * with bits 1, 5 and 7 set, then @dst should leave with bits 1, * 13 and 15 set. */ void bitmap_remap(unsigned long *dst, const unsigned long *src, const unsigned long *old, const unsigned long *new, unsigned int nbits) { unsigned int oldbit, w; if (dst == src) /* following doesn't handle inplace remaps */ return; bitmap_zero(dst, nbits); w = bitmap_weight(new, nbits); for_each_set_bit(oldbit, src, nbits) { int n = bitmap_pos_to_ord(old, oldbit, nbits); if (n < 0 || w == 0) set_bit(oldbit, dst); /* identity map */ else set_bit(find_nth_bit(new, nbits, n % w), dst); } } EXPORT_SYMBOL(bitmap_remap); /** * bitmap_bitremap - Apply map defined by a pair of bitmaps to a single bit * @oldbit: bit position to be mapped * @old: defines domain of map * @new: defines range of map * @bits: number of bits in each of these bitmaps * * Let @old and @new define a mapping of bit positions, such that * whatever position is held by the n-th set bit in @old is mapped * to the n-th set bit in @new. In the more general case, allowing * for the possibility that the weight 'w' of @new is less than the * weight of @old, map the position of the n-th set bit in @old to * the position of the m-th set bit in @new, where m == n % w. * * The positions of unset bits in @old are mapped to themselves * (the identity map). * * Apply the above specified mapping to bit position @oldbit, returning * the new bit position. * * For example, lets say that @old has bits 4 through 7 set, and * @new has bits 12 through 15 set. This defines the mapping of bit * position 4 to 12, 5 to 13, 6 to 14 and 7 to 15, and of all other * bit positions unchanged. So if say @oldbit is 5, then this routine * returns 13. */ int bitmap_bitremap(int oldbit, const unsigned long *old, const unsigned long *new, int bits) { int w = bitmap_weight(new, bits); int n = bitmap_pos_to_ord(old, oldbit, bits); if (n < 0 || w == 0) return oldbit; else return find_nth_bit(new, bits, n % w); } EXPORT_SYMBOL(bitmap_bitremap); #ifdef CONFIG_NUMA /** * bitmap_onto - translate one bitmap relative to another * @dst: resulting translated bitmap * @orig: original untranslated bitmap * @relmap: bitmap relative to which translated * @bits: number of bits in each of these bitmaps * * Set the n-th bit of @dst iff there exists some m such that the * n-th bit of @relmap is set, the m-th bit of @orig is set, and * the n-th bit of @relmap is also the m-th _set_ bit of @relmap. * (If you understood the previous sentence the first time your * read it, you're overqualified for your current job.) * * In other words, @orig is mapped onto (surjectively) @dst, * using the map { <n, m> | the n-th bit of @relmap is the * m-th set bit of @relmap }. * * Any set bits in @orig above bit number W, where W is the * weight of (number of set bits in) @relmap are mapped nowhere. * In particular, if for all bits m set in @orig, m >= W, then * @dst will end up empty. In situations where the possibility * of such an empty result is not desired, one way to avoid it is * to use the bitmap_fold() operator, below, to first fold the * @orig bitmap over itself so that all its set bits x are in the * range 0 <= x < W. The bitmap_fold() operator does this by * setting the bit (m % W) in @dst, for each bit (m) set in @orig. * * Example [1] for bitmap_onto(): * Let's say @relmap has bits 30-39 set, and @orig has bits * 1, 3, 5, 7, 9 and 11 set. Then on return from this routine, * @dst will have bits 31, 33, 35, 37 and 39 set. * * When bit 0 is set in @orig, it means turn on the bit in * @dst corresponding to whatever is the first bit (if any) * that is turned on in @relmap. Since bit 0 was off in the * above example, we leave off that bit (bit 30) in @dst. * * When bit 1 is set in @orig (as in the above example), it * means turn on the bit in @dst corresponding to whatever * is the second bit that is turned on in @relmap. The second * bit in @relmap that was turned on in the above example was * bit 31, so we turned on bit 31 in @dst. * * Similarly, we turned on bits 33, 35, 37 and 39 in @dst, * because they were the 4th, 6th, 8th and 10th set bits * set in @relmap, and the 4th, 6th, 8th and 10th bits of * @orig (i.e. bits 3, 5, 7 and 9) were also set. * * When bit 11 is set in @orig, it means turn on the bit in * @dst corresponding to whatever is the twelfth bit that is * turned on in @relmap. In the above example, there were * only ten bits turned on in @relmap (30..39), so that bit * 11 was set in @orig had no affect on @dst. * * Example [2] for bitmap_fold() + bitmap_onto(): * Let's say @relmap has these ten bits set:: * * 40 41 42 43 45 48 53 61 74 95 * * (for the curious, that's 40 plus the first ten terms of the * Fibonacci sequence.) * * Further lets say we use the following code, invoking * bitmap_fold() then bitmap_onto, as suggested above to * avoid the possibility of an empty @dst result:: * * unsigned long *tmp; // a temporary bitmap's bits * * bitmap_fold(tmp, orig, bitmap_weight(relmap, bits), bits); * bitmap_onto(dst, tmp, relmap, bits); * * Then this table shows what various values of @dst would be, for * various @orig's. I list the zero-based positions of each set bit. * The tmp column shows the intermediate result, as computed by * using bitmap_fold() to fold the @orig bitmap modulo ten * (the weight of @relmap): * * =============== ============== ================= * @orig tmp @dst * 0 0 40 * 1 1 41 * 9 9 95 * 10 0 40 [#f1]_ * 1 3 5 7 1 3 5 7 41 43 48 61 * 0 1 2 3 4 0 1 2 3 4 40 41 42 43 45 * 0 9 18 27 0 9 8 7 40 61 74 95 * 0 10 20 30 0 40 * 0 11 22 33 0 1 2 3 40 41 42 43 * 0 12 24 36 0 2 4 6 40 42 45 53 * 78 102 211 1 2 8 41 42 74 [#f1]_ * =============== ============== ================= * * .. [#f1] * * For these marked lines, if we hadn't first done bitmap_fold() * into tmp, then the @dst result would have been empty. * * If either of @orig or @relmap is empty (no set bits), then @dst * will be returned empty. * * If (as explained above) the only set bits in @orig are in positions * m where m >= W, (where W is the weight of @relmap) then @dst will * once again be returned empty. * * All bits in @dst not set by the above rule are cleared. */ void bitmap_onto(unsigned long *dst, const unsigned long *orig, const unsigned long *relmap, unsigned int bits) { unsigned int n, m; /* same meaning as in above comment */ if (dst == orig) /* following doesn't handle inplace mappings */ return; bitmap_zero(dst, bits); /* * The following code is a more efficient, but less * obvious, equivalent to the loop: * for (m = 0; m < bitmap_weight(relmap, bits); m++) { * n = find_nth_bit(orig, bits, m); * if (test_bit(m, orig)) * set_bit(n, dst); * } */ m = 0; for_each_set_bit(n, relmap, bits) { /* m == bitmap_pos_to_ord(relmap, n, bits) */ if (test_bit(m, orig)) set_bit(n, dst); m++; } } /** * bitmap_fold - fold larger bitmap into smaller, modulo specified size * @dst: resulting smaller bitmap * @orig: original larger bitmap * @sz: specified size * @nbits: number of bits in each of these bitmaps * * For each bit oldbit in @orig, set bit oldbit mod @sz in @dst. * Clear all other bits in @dst. See further the comment and * Example [2] for bitmap_onto() for why and how to use this. */ void bitmap_fold(unsigned long *dst, const unsigned long *orig, unsigned int sz, unsigned int nbits) { unsigned int oldbit; if (dst == orig) /* following doesn't handle inplace mappings */ return; bitmap_zero(dst, nbits); for_each_set_bit(oldbit, orig, nbits) set_bit(oldbit % sz, dst); } #endif /* CONFIG_NUMA */ unsigned long *bitmap_alloc(unsigned int nbits, gfp_t flags) { return kmalloc_array(BITS_TO_LONGS(nbits), sizeof(unsigned long), flags); } EXPORT_SYMBOL(bitmap_alloc); unsigned long *bitmap_zalloc(unsigned int nbits, gfp_t flags) { return bitmap_alloc(nbits, flags | __GFP_ZERO); } EXPORT_SYMBOL(bitmap_zalloc); unsigned long *bitmap_alloc_node(unsigned int nbits, gfp_t flags, int node) { return kmalloc_array_node(BITS_TO_LONGS(nbits), sizeof(unsigned long), flags, node); } EXPORT_SYMBOL(bitmap_alloc_node); unsigned long *bitmap_zalloc_node(unsigned int nbits, gfp_t flags, int node) { return bitmap_alloc_node(nbits, flags | __GFP_ZERO, node); } EXPORT_SYMBOL(bitmap_zalloc_node); void bitmap_free(const unsigned long *bitmap) { kfree(bitmap); } EXPORT_SYMBOL(bitmap_free); static void devm_bitmap_free(void *data) { unsigned long *bitmap = data; bitmap_free(bitmap); } unsigned long *devm_bitmap_alloc(struct device *dev, unsigned int nbits, gfp_t flags) { unsigned long *bitmap; int ret; bitmap = bitmap_alloc(nbits, flags); if (!bitmap) return NULL; ret = devm_add_action_or_reset(dev, devm_bitmap_free, bitmap); if (ret) return NULL; return bitmap; } EXPORT_SYMBOL_GPL(devm_bitmap_alloc); unsigned long *devm_bitmap_zalloc(struct device *dev, unsigned int nbits, gfp_t flags) { return devm_bitmap_alloc(dev, nbits, flags | __GFP_ZERO); } EXPORT_SYMBOL_GPL(devm_bitmap_zalloc); #if BITS_PER_LONG == 64 /** * bitmap_from_arr32 - copy the contents of u32 array of bits to bitmap * @bitmap: array of unsigned longs, the destination bitmap * @buf: array of u32 (in host byte order), the source bitmap * @nbits: number of bits in @bitmap */ void bitmap_from_arr32(unsigned long *bitmap, const u32 *buf, unsigned int nbits) { unsigned int i, halfwords; halfwords = DIV_ROUND_UP(nbits, 32); for (i = 0; i < halfwords; i++) { bitmap[i/2] = (unsigned long) buf[i]; if (++i < halfwords) bitmap[i/2] |= ((unsigned long) buf[i]) << 32; } /* Clear tail bits in last word beyond nbits. */ if (nbits % BITS_PER_LONG) bitmap[(halfwords - 1) / 2] &= BITMAP_LAST_WORD_MASK(nbits); } EXPORT_SYMBOL(bitmap_from_arr32); /** * bitmap_to_arr32 - copy the contents of bitmap to a u32 array of bits * @buf: array of u32 (in host byte order), the dest bitmap * @bitmap: array of unsigned longs, the source bitmap * @nbits: number of bits in @bitmap */ void bitmap_to_arr32(u32 *buf, const unsigned long *bitmap, unsigned int nbits) { unsigned int i, halfwords; halfwords = DIV_ROUND_UP(nbits, 32); for (i = 0; i < halfwords; i++) { buf[i] = (u32) (bitmap[i/2] & UINT_MAX); if (++i < halfwords) buf[i] = (u32) (bitmap[i/2] >> 32); } /* Clear tail bits in last element of array beyond nbits. */ if (nbits % BITS_PER_LONG) buf[halfwords - 1] &= (u32) (UINT_MAX >> ((-nbits) & 31)); } EXPORT_SYMBOL(bitmap_to_arr32); #endif #if BITS_PER_LONG == 32 /** * bitmap_from_arr64 - copy the contents of u64 array of bits to bitmap * @bitmap: array of unsigned longs, the destination bitmap * @buf: array of u64 (in host byte order), the source bitmap * @nbits: number of bits in @bitmap */ void bitmap_from_arr64(unsigned long *bitmap, const u64 *buf, unsigned int nbits) { int n; for (n = nbits; n > 0; n -= 64) { u64 val = *buf++; *bitmap++ = val; if (n > 32) *bitmap++ = val >> 32; } /* * Clear tail bits in the last word beyond nbits. * * Negative index is OK because here we point to the word next * to the last word of the bitmap, except for nbits == 0, which * is tested implicitly. */ if (nbits % BITS_PER_LONG) bitmap[-1] &= BITMAP_LAST_WORD_MASK(nbits); } EXPORT_SYMBOL(bitmap_from_arr64); /** * bitmap_to_arr64 - copy the contents of bitmap to a u64 array of bits * @buf: array of u64 (in host byte order), the dest bitmap * @bitmap: array of unsigned longs, the source bitmap * @nbits: number of bits in @bitmap */ void bitmap_to_arr64(u64 *buf, const unsigned long *bitmap, unsigned int nbits) { const unsigned long *end = bitmap + BITS_TO_LONGS(nbits); while (bitmap < end) { *buf = *bitmap++; if (bitmap < end) *buf |= (u64)(*bitmap++) << 32; buf++; } /* Clear tail bits in the last element of array beyond nbits. */ if (nbits % 64) buf[-1] &= GENMASK_ULL((nbits - 1) % 64, 0); } EXPORT_SYMBOL(bitmap_to_arr64); #endif |
| 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 | /* SPDX-License-Identifier: GPL-2.0-or-later */ /* Queue of folios definitions * * Copyright (C) 2024 Red Hat, Inc. All Rights Reserved. * Written by David Howells (dhowells@redhat.com) * * See: * * Documentation/core-api/folio_queue.rst * * for a description of the API. */ #ifndef _LINUX_FOLIO_QUEUE_H #define _LINUX_FOLIO_QUEUE_H #include <linux/pagevec.h> /* * Segment in a queue of running buffers. Each segment can hold a number of * folios and a portion of the queue can be referenced with the ITER_FOLIOQ * iterator. The possibility exists of inserting non-folio elements into the * queue (such as gaps). * * Explicit prev and next pointers are used instead of a list_head to make it * easier to add segments to tail and remove them from the head without the * need for a lock. */ struct folio_queue { struct folio_batch vec; /* Folios in the queue segment */ u8 orders[PAGEVEC_SIZE]; /* Order of each folio */ struct folio_queue *next; /* Next queue segment or NULL */ struct folio_queue *prev; /* Previous queue segment of NULL */ unsigned long marks; /* 1-bit mark per folio */ unsigned long marks2; /* Second 1-bit mark per folio */ unsigned long marks3; /* Third 1-bit mark per folio */ #if PAGEVEC_SIZE > BITS_PER_LONG #error marks is not big enough #endif unsigned int rreq_id; unsigned int debug_id; }; /** * folioq_init - Initialise a folio queue segment * @folioq: The segment to initialise * @rreq_id: The request identifier to use in tracelines. * * Initialise a folio queue segment and set an identifier to be used in traces. * * Note that the folio pointers are left uninitialised. */ static inline void folioq_init(struct folio_queue *folioq, unsigned int rreq_id) { folio_batch_init(&folioq->vec); folioq->next = NULL; folioq->prev = NULL; folioq->marks = 0; folioq->marks2 = 0; folioq->marks3 = 0; folioq->rreq_id = rreq_id; folioq->debug_id = 0; } /** * folioq_nr_slots: Query the capacity of a folio queue segment * @folioq: The segment to query * * Query the number of folios that a particular folio queue segment might hold. * [!] NOTE: This must not be assumed to be the same for every segment! */ static inline unsigned int folioq_nr_slots(const struct folio_queue *folioq) { return PAGEVEC_SIZE; } /** * folioq_count: Query the occupancy of a folio queue segment * @folioq: The segment to query * * Query the number of folios that have been added to a folio queue segment. * Note that this is not decreased as folios are removed from a segment. */ static inline unsigned int folioq_count(struct folio_queue *folioq) { return folio_batch_count(&folioq->vec); } /** * folioq_full: Query if a folio queue segment is full * @folioq: The segment to query * * Query if a folio queue segment is fully occupied. Note that this does not * change if folios are removed from a segment. */ static inline bool folioq_full(struct folio_queue *folioq) { //return !folio_batch_space(&folioq->vec); return folioq_count(folioq) >= folioq_nr_slots(folioq); } /** * folioq_is_marked: Check first folio mark in a folio queue segment * @folioq: The segment to query * @slot: The slot number of the folio to query * * Determine if the first mark is set for the folio in the specified slot in a * folio queue segment. */ static inline bool folioq_is_marked(const struct folio_queue *folioq, unsigned int slot) { return test_bit(slot, &folioq->marks); } /** * folioq_mark: Set the first mark on a folio in a folio queue segment * @folioq: The segment to modify * @slot: The slot number of the folio to modify * * Set the first mark for the folio in the specified slot in a folio queue * segment. */ static inline void folioq_mark(struct folio_queue *folioq, unsigned int slot) { set_bit(slot, &folioq->marks); } /** * folioq_unmark: Clear the first mark on a folio in a folio queue segment * @folioq: The segment to modify * @slot: The slot number of the folio to modify * * Clear the first mark for the folio in the specified slot in a folio queue * segment. */ static inline void folioq_unmark(struct folio_queue *folioq, unsigned int slot) { clear_bit(slot, &folioq->marks); } /** * folioq_is_marked2: Check second folio mark in a folio queue segment * @folioq: The segment to query * @slot: The slot number of the folio to query * * Determine if the second mark is set for the folio in the specified slot in a * folio queue segment. */ static inline bool folioq_is_marked2(const struct folio_queue *folioq, unsigned int slot) { return test_bit(slot, &folioq->marks2); } /** * folioq_mark2: Set the second mark on a folio in a folio queue segment * @folioq: The segment to modify * @slot: The slot number of the folio to modify * * Set the second mark for the folio in the specified slot in a folio queue * segment. */ static inline void folioq_mark2(struct folio_queue *folioq, unsigned int slot) { set_bit(slot, &folioq->marks2); } /** * folioq_unmark2: Clear the second mark on a folio in a folio queue segment * @folioq: The segment to modify * @slot: The slot number of the folio to modify * * Clear the second mark for the folio in the specified slot in a folio queue * segment. */ static inline void folioq_unmark2(struct folio_queue *folioq, unsigned int slot) { clear_bit(slot, &folioq->marks2); } /** * folioq_is_marked3: Check third folio mark in a folio queue segment * @folioq: The segment to query * @slot: The slot number of the folio to query * * Determine if the third mark is set for the folio in the specified slot in a * folio queue segment. */ static inline bool folioq_is_marked3(const struct folio_queue *folioq, unsigned int slot) { return test_bit(slot, &folioq->marks3); } /** * folioq_mark3: Set the third mark on a folio in a folio queue segment * @folioq: The segment to modify * @slot: The slot number of the folio to modify * * Set the third mark for the folio in the specified slot in a folio queue * segment. */ static inline void folioq_mark3(struct folio_queue *folioq, unsigned int slot) { set_bit(slot, &folioq->marks3); } /** * folioq_unmark3: Clear the third mark on a folio in a folio queue segment * @folioq: The segment to modify * @slot: The slot number of the folio to modify * * Clear the third mark for the folio in the specified slot in a folio queue * segment. */ static inline void folioq_unmark3(struct folio_queue *folioq, unsigned int slot) { clear_bit(slot, &folioq->marks3); } static inline unsigned int __folio_order(struct folio *folio) { if (!folio_test_large(folio)) return 0; return folio->_flags_1 & 0xff; } /** * folioq_append: Add a folio to a folio queue segment * @folioq: The segment to add to * @folio: The folio to add * * Add a folio to the tail of the sequence in a folio queue segment, increasing * the occupancy count and returning the slot number for the folio just added. * The folio size is extracted and stored in the queue and the marks are left * unmodified. * * Note that it's left up to the caller to check that the segment capacity will * not be exceeded and to extend the queue. */ static inline unsigned int folioq_append(struct folio_queue *folioq, struct folio *folio) { unsigned int slot = folioq->vec.nr++; folioq->vec.folios[slot] = folio; folioq->orders[slot] = __folio_order(folio); return slot; } /** * folioq_append_mark: Add a folio to a folio queue segment * @folioq: The segment to add to * @folio: The folio to add * * Add a folio to the tail of the sequence in a folio queue segment, increasing * the occupancy count and returning the slot number for the folio just added. * The folio size is extracted and stored in the queue, the first mark is set * and and the second and third marks are left unmodified. * * Note that it's left up to the caller to check that the segment capacity will * not be exceeded and to extend the queue. */ static inline unsigned int folioq_append_mark(struct folio_queue *folioq, struct folio *folio) { unsigned int slot = folioq->vec.nr++; folioq->vec.folios[slot] = folio; folioq->orders[slot] = __folio_order(folio); folioq_mark(folioq, slot); return slot; } /** * folioq_folio: Get a folio from a folio queue segment * @folioq: The segment to access * @slot: The folio slot to access * * Retrieve the folio in the specified slot from a folio queue segment. Note * that no bounds check is made and if the slot hasn't been added into yet, the * pointer will be undefined. If the slot has been cleared, NULL will be * returned. */ static inline struct folio *folioq_folio(const struct folio_queue *folioq, unsigned int slot) { return folioq->vec.folios[slot]; } /** * folioq_folio_order: Get the order of a folio from a folio queue segment * @folioq: The segment to access * @slot: The folio slot to access * * Retrieve the order of the folio in the specified slot from a folio queue * segment. Note that no bounds check is made and if the slot hasn't been * added into yet, the order returned will be 0. */ static inline unsigned int folioq_folio_order(const struct folio_queue *folioq, unsigned int slot) { return folioq->orders[slot]; } /** * folioq_folio_size: Get the size of a folio from a folio queue segment * @folioq: The segment to access * @slot: The folio slot to access * * Retrieve the size of the folio in the specified slot from a folio queue * segment. Note that no bounds check is made and if the slot hasn't been * added into yet, the size returned will be PAGE_SIZE. */ static inline size_t folioq_folio_size(const struct folio_queue *folioq, unsigned int slot) { return PAGE_SIZE << folioq_folio_order(folioq, slot); } /** * folioq_clear: Clear a folio from a folio queue segment * @folioq: The segment to clear * @slot: The folio slot to clear * * Clear a folio from a sequence in a folio queue segment and clear its marks. * The occupancy count is left unchanged. */ static inline void folioq_clear(struct folio_queue *folioq, unsigned int slot) { folioq->vec.folios[slot] = NULL; folioq_unmark(folioq, slot); folioq_unmark2(folioq, slot); folioq_unmark3(folioq, slot); } #endif /* _LINUX_FOLIO_QUEUE_H */ |
| 725 726 726 721 726 721 555 521 522 555 553 238 555 554 555 555 555 13 13 13 13 236 238 238 13 13 13 8 13 11 6 9 11 9 9 9 9 8 7 7 7 13 13 13 13 9 8 8 9 13 13 13 11 11 4 4 10 2 2 2 2 555 681 553 555 486 553 554 553 554 486 553 720 720 645 721 8 8 8 8 552 485 553 484 58 485 58 485 553 522 555 523 551 553 555 552 127 53 128 128 128 523 126 555 521 555 555 553 555 555 555 554 237 237 712 711 238 238 237 237 238 127 | 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 | // SPDX-License-Identifier: GPL-2.0 /* * /proc/sys support */ #include <linux/init.h> #include <linux/sysctl.h> #include <linux/poll.h> #include <linux/proc_fs.h> #include <linux/printk.h> #include <linux/security.h> #include <linux/sched.h> #include <linux/cred.h> #include <linux/namei.h> #include <linux/mm.h> #include <linux/uio.h> #include <linux/module.h> #include <linux/bpf-cgroup.h> #include <linux/mount.h> #include <linux/kmemleak.h> #include <linux/lockdep.h> #include "internal.h" #define list_for_each_table_entry(entry, header) \ entry = header->ctl_table; \ for (size_t i = 0 ; i < header->ctl_table_size; ++i, entry++) static const struct dentry_operations proc_sys_dentry_operations; static const struct file_operations proc_sys_file_operations; static const struct inode_operations proc_sys_inode_operations; static const struct file_operations proc_sys_dir_file_operations; static const struct inode_operations proc_sys_dir_operations; /* * Support for permanently empty directories. * Must be non-empty to avoid sharing an address with other tables. */ static const struct ctl_table sysctl_mount_point[] = { { } }; /** * register_sysctl_mount_point() - registers a sysctl mount point * @path: path for the mount point * * Used to create a permanently empty directory to serve as mount point. * There are some subtle but important permission checks this allows in the * case of unprivileged mounts. */ struct ctl_table_header *register_sysctl_mount_point(const char *path) { return register_sysctl_sz(path, sysctl_mount_point, 0); } EXPORT_SYMBOL(register_sysctl_mount_point); #define sysctl_is_perm_empty_ctl_header(hptr) \ (hptr->type == SYSCTL_TABLE_TYPE_PERMANENTLY_EMPTY) #define sysctl_set_perm_empty_ctl_header(hptr) \ (hptr->type = SYSCTL_TABLE_TYPE_PERMANENTLY_EMPTY) #define sysctl_clear_perm_empty_ctl_header(hptr) \ (hptr->type = SYSCTL_TABLE_TYPE_DEFAULT) void proc_sys_poll_notify(struct ctl_table_poll *poll) { if (!poll) return; atomic_inc(&poll->event); wake_up_interruptible(&poll->wait); } static const struct ctl_table root_table[] = { { .procname = "", .mode = S_IFDIR|S_IRUGO|S_IXUGO, }, }; static struct ctl_table_root sysctl_table_root = { .default_set.dir.header = { {{.count = 1, .nreg = 1, .ctl_table = root_table }}, .ctl_table_arg = root_table, .root = &sysctl_table_root, .set = &sysctl_table_root.default_set, }, }; static DEFINE_SPINLOCK(sysctl_lock); static void drop_sysctl_table(struct ctl_table_header *header); static int sysctl_follow_link(struct ctl_table_header **phead, const struct ctl_table **pentry); static int insert_links(struct ctl_table_header *head); static void put_links(struct ctl_table_header *header); static void sysctl_print_dir(struct ctl_dir *dir) { if (dir->header.parent) sysctl_print_dir(dir->header.parent); pr_cont("%s/", dir->header.ctl_table[0].procname); } static int namecmp(const char *name1, int len1, const char *name2, int len2) { int cmp; cmp = memcmp(name1, name2, min(len1, len2)); if (cmp == 0) cmp = len1 - len2; return cmp; } static const struct ctl_table *find_entry(struct ctl_table_header **phead, struct ctl_dir *dir, const char *name, int namelen) { struct ctl_table_header *head; const struct ctl_table *entry; struct rb_node *node = dir->root.rb_node; lockdep_assert_held(&sysctl_lock); while (node) { struct ctl_node *ctl_node; const char *procname; int cmp; ctl_node = rb_entry(node, struct ctl_node, node); head = ctl_node->header; entry = &head->ctl_table[ctl_node - head->node]; procname = entry->procname; cmp = namecmp(name, namelen, procname, strlen(procname)); if (cmp < 0) node = node->rb_left; else if (cmp > 0) node = node->rb_right; else { *phead = head; return entry; } } return NULL; } static int insert_entry(struct ctl_table_header *head, const struct ctl_table *entry) { struct rb_node *node = &head->node[entry - head->ctl_table].node; struct rb_node **p = &head->parent->root.rb_node; struct rb_node *parent = NULL; const char *name = entry->procname; int namelen = strlen(name); while (*p) { struct ctl_table_header *parent_head; const struct ctl_table *parent_entry; struct ctl_node *parent_node; const char *parent_name; int cmp; parent = *p; parent_node = rb_entry(parent, struct ctl_node, node); parent_head = parent_node->header; parent_entry = &parent_head->ctl_table[parent_node - parent_head->node]; parent_name = parent_entry->procname; cmp = namecmp(name, namelen, parent_name, strlen(parent_name)); if (cmp < 0) p = &(*p)->rb_left; else if (cmp > 0) p = &(*p)->rb_right; else { pr_err("sysctl duplicate entry: "); sysctl_print_dir(head->parent); pr_cont("%s\n", entry->procname); return -EEXIST; } } rb_link_node(node, parent, p); rb_insert_color(node, &head->parent->root); return 0; } static void erase_entry(struct ctl_table_header *head, const struct ctl_table *entry) { struct rb_node *node = &head->node[entry - head->ctl_table].node; rb_erase(node, &head->parent->root); } static void init_header(struct ctl_table_header *head, struct ctl_table_root *root, struct ctl_table_set *set, struct ctl_node *node, const struct ctl_table *table, size_t table_size) { head->ctl_table = table; head->ctl_table_size = table_size; head->ctl_table_arg = table; head->used = 0; head->count = 1; head->nreg = 1; head->unregistering = NULL; head->root = root; head->set = set; head->parent = NULL; head->node = node; INIT_HLIST_HEAD(&head->inodes); if (node) { const struct ctl_table *entry; list_for_each_table_entry(entry, head) { node->header = head; node++; } } if (table == sysctl_mount_point) sysctl_set_perm_empty_ctl_header(head); } static void erase_header(struct ctl_table_header *head) { const struct ctl_table *entry; list_for_each_table_entry(entry, head) erase_entry(head, entry); } static int insert_header(struct ctl_dir *dir, struct ctl_table_header *header) { const struct ctl_table *entry; struct ctl_table_header *dir_h = &dir->header; int err; /* Is this a permanently empty directory? */ if (sysctl_is_perm_empty_ctl_header(dir_h)) return -EROFS; /* Am I creating a permanently empty directory? */ if (sysctl_is_perm_empty_ctl_header(header)) { if (!RB_EMPTY_ROOT(&dir->root)) return -EINVAL; sysctl_set_perm_empty_ctl_header(dir_h); } dir_h->nreg++; header->parent = dir; err = insert_links(header); if (err) goto fail_links; list_for_each_table_entry(entry, header) { err = insert_entry(header, entry); if (err) goto fail; } return 0; fail: erase_header(header); put_links(header); fail_links: if (header->ctl_table == sysctl_mount_point) sysctl_clear_perm_empty_ctl_header(dir_h); header->parent = NULL; drop_sysctl_table(dir_h); return err; } static int use_table(struct ctl_table_header *p) { lockdep_assert_held(&sysctl_lock); if (unlikely(p->unregistering)) return 0; p->used++; return 1; } static void unuse_table(struct ctl_table_header *p) { lockdep_assert_held(&sysctl_lock); if (!--p->used) if (unlikely(p->unregistering)) complete(p->unregistering); } static void proc_sys_invalidate_dcache(struct ctl_table_header *head) { proc_invalidate_siblings_dcache(&head->inodes, &sysctl_lock); } static void start_unregistering(struct ctl_table_header *p) { /* will reacquire if has to wait */ lockdep_assert_held(&sysctl_lock); /* * if p->used is 0, nobody will ever touch that entry again; * we'll eliminate all paths to it before dropping sysctl_lock */ if (unlikely(p->used)) { struct completion wait; init_completion(&wait); p->unregistering = &wait; spin_unlock(&sysctl_lock); wait_for_completion(&wait); } else { /* anything non-NULL; we'll never dereference it */ p->unregistering = ERR_PTR(-EINVAL); spin_unlock(&sysctl_lock); } /* * Invalidate dentries for unregistered sysctls: namespaced sysctls * can have duplicate names and contaminate dcache very badly. */ proc_sys_invalidate_dcache(p); /* * do not remove from the list until nobody holds it; walking the * list in do_sysctl() relies on that. */ spin_lock(&sysctl_lock); erase_header(p); } static struct ctl_table_header *sysctl_head_grab(struct ctl_table_header *head) { BUG_ON(!head); spin_lock(&sysctl_lock); if (!use_table(head)) head = ERR_PTR(-ENOENT); spin_unlock(&sysctl_lock); return head; } static void sysctl_head_finish(struct ctl_table_header *head) { if (!head) return; spin_lock(&sysctl_lock); unuse_table(head); spin_unlock(&sysctl_lock); } static struct ctl_table_set * lookup_header_set(struct ctl_table_root *root) { struct ctl_table_set *set = &root->default_set; if (root->lookup) set = root->lookup(root); return set; } static const struct ctl_table *lookup_entry(struct ctl_table_header **phead, struct ctl_dir *dir, const char *name, int namelen) { struct ctl_table_header *head; const struct ctl_table *entry; spin_lock(&sysctl_lock); entry = find_entry(&head, dir, name, namelen); if (entry && use_table(head)) *phead = head; else entry = NULL; spin_unlock(&sysctl_lock); return entry; } static struct ctl_node *first_usable_entry(struct rb_node *node) { struct ctl_node *ctl_node; for (;node; node = rb_next(node)) { ctl_node = rb_entry(node, struct ctl_node, node); if (use_table(ctl_node->header)) return ctl_node; } return NULL; } static void first_entry(struct ctl_dir *dir, struct ctl_table_header **phead, const struct ctl_table **pentry) { struct ctl_table_header *head = NULL; const struct ctl_table *entry = NULL; struct ctl_node *ctl_node; spin_lock(&sysctl_lock); ctl_node = first_usable_entry(rb_first(&dir->root)); spin_unlock(&sysctl_lock); if (ctl_node) { head = ctl_node->header; entry = &head->ctl_table[ctl_node - head->node]; } *phead = head; *pentry = entry; } static void next_entry(struct ctl_table_header **phead, const struct ctl_table **pentry) { struct ctl_table_header *head = *phead; const struct ctl_table *entry = *pentry; struct ctl_node *ctl_node = &head->node[entry - head->ctl_table]; spin_lock(&sysctl_lock); unuse_table(head); ctl_node = first_usable_entry(rb_next(&ctl_node->node)); spin_unlock(&sysctl_lock); head = NULL; if (ctl_node) { head = ctl_node->header; entry = &head->ctl_table[ctl_node - head->node]; } *phead = head; *pentry = entry; } /* * sysctl_perm does NOT grant the superuser all rights automatically, because * some sysctl variables are readonly even to root. */ static int test_perm(int mode, int op) { if (uid_eq(current_euid(), GLOBAL_ROOT_UID)) mode >>= 6; else if (in_egroup_p(GLOBAL_ROOT_GID)) mode >>= 3; if ((op & ~mode & (MAY_READ|MAY_WRITE|MAY_EXEC)) == 0) return 0; return -EACCES; } static int sysctl_perm(struct ctl_table_header *head, const struct ctl_table *table, int op) { struct ctl_table_root *root = head->root; int mode; if (root->permissions) mode = root->permissions(head, table); else mode = table->mode; return test_perm(mode, op); } static struct inode *proc_sys_make_inode(struct super_block *sb, struct ctl_table_header *head, const struct ctl_table *table) { struct ctl_table_root *root = head->root; struct inode *inode; struct proc_inode *ei; inode = new_inode(sb); if (!inode) return ERR_PTR(-ENOMEM); inode->i_ino = get_next_ino(); ei = PROC_I(inode); spin_lock(&sysctl_lock); if (unlikely(head->unregistering)) { spin_unlock(&sysctl_lock); iput(inode); return ERR_PTR(-ENOENT); } ei->sysctl = head; ei->sysctl_entry = table; hlist_add_head_rcu(&ei->sibling_inodes, &head->inodes); head->count++; spin_unlock(&sysctl_lock); simple_inode_init_ts(inode); inode->i_mode = table->mode; if (!S_ISDIR(table->mode)) { inode->i_mode |= S_IFREG; inode->i_op = &proc_sys_inode_operations; inode->i_fop = &proc_sys_file_operations; } else { inode->i_mode |= S_IFDIR; inode->i_op = &proc_sys_dir_operations; inode->i_fop = &proc_sys_dir_file_operations; if (sysctl_is_perm_empty_ctl_header(head)) make_empty_dir_inode(inode); } inode->i_uid = GLOBAL_ROOT_UID; inode->i_gid = GLOBAL_ROOT_GID; if (root->set_ownership) root->set_ownership(head, &inode->i_uid, &inode->i_gid); return inode; } void proc_sys_evict_inode(struct inode *inode, struct ctl_table_header *head) { spin_lock(&sysctl_lock); hlist_del_init_rcu(&PROC_I(inode)->sibling_inodes); if (!--head->count) kfree_rcu(head, rcu); spin_unlock(&sysctl_lock); } static struct ctl_table_header *grab_header(struct inode *inode) { struct ctl_table_header *head = PROC_I(inode)->sysctl; if (!head) head = &sysctl_table_root.default_set.dir.header; return sysctl_head_grab(head); } static struct dentry *proc_sys_lookup(struct inode *dir, struct dentry *dentry, unsigned int flags) { struct ctl_table_header *head = grab_header(dir); struct ctl_table_header *h = NULL; const struct qstr *name = &dentry->d_name; const struct ctl_table *p; struct inode *inode; struct dentry *err = ERR_PTR(-ENOENT); struct ctl_dir *ctl_dir; int ret; if (IS_ERR(head)) return ERR_CAST(head); ctl_dir = container_of(head, struct ctl_dir, header); p = lookup_entry(&h, ctl_dir, name->name, name->len); if (!p) goto out; if (S_ISLNK(p->mode)) { ret = sysctl_follow_link(&h, &p); err = ERR_PTR(ret); if (ret) goto out; } d_set_d_op(dentry, &proc_sys_dentry_operations); inode = proc_sys_make_inode(dir->i_sb, h ? h : head, p); err = d_splice_alias(inode, dentry); out: if (h) sysctl_head_finish(h); sysctl_head_finish(head); return err; } static ssize_t proc_sys_call_handler(struct kiocb *iocb, struct iov_iter *iter, int write) { struct inode *inode = file_inode(iocb->ki_filp); struct ctl_table_header *head = grab_header(inode); const struct ctl_table *table = PROC_I(inode)->sysctl_entry; size_t count = iov_iter_count(iter); char *kbuf; ssize_t error; if (IS_ERR(head)) return PTR_ERR(head); /* * At this point we know that the sysctl was not unregistered * and won't be until we finish. */ error = -EPERM; if (sysctl_perm(head, table, write ? MAY_WRITE : MAY_READ)) goto out; /* if that can happen at all, it should be -EINVAL, not -EISDIR */ error = -EINVAL; if (!table->proc_handler) goto out; /* don't even try if the size is too large */ error = -ENOMEM; if (count >= KMALLOC_MAX_SIZE) goto out; kbuf = kvzalloc(count + 1, GFP_KERNEL); if (!kbuf) goto out; if (write) { error = -EFAULT; if (!copy_from_iter_full(kbuf, count, iter)) goto out_free_buf; kbuf[count] = '\0'; } error = BPF_CGROUP_RUN_PROG_SYSCTL(head, table, write, &kbuf, &count, &iocb->ki_pos); if (error) goto out_free_buf; /* careful: calling conventions are nasty here */ error = table->proc_handler(table, write, kbuf, &count, &iocb->ki_pos); if (error) goto out_free_buf; if (!write) { error = -EFAULT; if (copy_to_iter(kbuf, count, iter) < count) goto out_free_buf; } error = count; out_free_buf: kvfree(kbuf); out: sysctl_head_finish(head); return error; } static ssize_t proc_sys_read(struct kiocb *iocb, struct iov_iter *iter) { return proc_sys_call_handler(iocb, iter, 0); } static ssize_t proc_sys_write(struct kiocb *iocb, struct iov_iter *iter) { return proc_sys_call_handler(iocb, iter, 1); } static int proc_sys_open(struct inode *inode, struct file *filp) { struct ctl_table_header *head = grab_header(inode); const struct ctl_table *table = PROC_I(inode)->sysctl_entry; /* sysctl was unregistered */ if (IS_ERR(head)) return PTR_ERR(head); if (table->poll) filp->private_data = proc_sys_poll_event(table->poll); sysctl_head_finish(head); return 0; } static __poll_t proc_sys_poll(struct file *filp, poll_table *wait) { struct inode *inode = file_inode(filp); struct ctl_table_header *head = grab_header(inode); const struct ctl_table *table = PROC_I(inode)->sysctl_entry; __poll_t ret = DEFAULT_POLLMASK; unsigned long event; /* sysctl was unregistered */ if (IS_ERR(head)) return EPOLLERR | EPOLLHUP; if (!table->proc_handler) goto out; if (!table->poll) goto out; event = (unsigned long)filp->private_data; poll_wait(filp, &table->poll->wait, wait); if (event != atomic_read(&table->poll->event)) { filp->private_data = proc_sys_poll_event(table->poll); ret = EPOLLIN | EPOLLRDNORM | EPOLLERR | EPOLLPRI; } out: sysctl_head_finish(head); return ret; } static bool proc_sys_fill_cache(struct file *file, struct dir_context *ctx, struct ctl_table_header *head, const struct ctl_table *table) { struct dentry *child, *dir = file->f_path.dentry; struct inode *inode; struct qstr qname; ino_t ino = 0; unsigned type = DT_UNKNOWN; qname.name = table->procname; qname.len = strlen(table->procname); qname.hash = full_name_hash(dir, qname.name, qname.len); child = d_lookup(dir, &qname); if (!child) { DECLARE_WAIT_QUEUE_HEAD_ONSTACK(wq); child = d_alloc_parallel(dir, &qname, &wq); if (IS_ERR(child)) return false; if (d_in_lookup(child)) { struct dentry *res; d_set_d_op(child, &proc_sys_dentry_operations); inode = proc_sys_make_inode(dir->d_sb, head, table); res = d_splice_alias(inode, child); d_lookup_done(child); if (unlikely(res)) { dput(child); if (IS_ERR(res)) return false; child = res; } } } inode = d_inode(child); ino = inode->i_ino; type = inode->i_mode >> 12; dput(child); return dir_emit(ctx, qname.name, qname.len, ino, type); } static bool proc_sys_link_fill_cache(struct file *file, struct dir_context *ctx, struct ctl_table_header *head, const struct ctl_table *table) { bool ret = true; head = sysctl_head_grab(head); if (IS_ERR(head)) return false; /* It is not an error if we can not follow the link ignore it */ if (sysctl_follow_link(&head, &table)) goto out; ret = proc_sys_fill_cache(file, ctx, head, table); out: sysctl_head_finish(head); return ret; } static int scan(struct ctl_table_header *head, const struct ctl_table *table, unsigned long *pos, struct file *file, struct dir_context *ctx) { bool res; if ((*pos)++ < ctx->pos) return true; if (unlikely(S_ISLNK(table->mode))) res = proc_sys_link_fill_cache(file, ctx, head, table); else res = proc_sys_fill_cache(file, ctx, head, table); if (res) ctx->pos = *pos; return res; } static int proc_sys_readdir(struct file *file, struct dir_context *ctx) { struct ctl_table_header *head = grab_header(file_inode(file)); struct ctl_table_header *h = NULL; const struct ctl_table *entry; struct ctl_dir *ctl_dir; unsigned long pos; if (IS_ERR(head)) return PTR_ERR(head); ctl_dir = container_of(head, struct ctl_dir, header); if (!dir_emit_dots(file, ctx)) goto out; pos = 2; for (first_entry(ctl_dir, &h, &entry); h; next_entry(&h, &entry)) { if (!scan(h, entry, &pos, file, ctx)) { sysctl_head_finish(h); break; } } out: sysctl_head_finish(head); return 0; } static int proc_sys_permission(struct mnt_idmap *idmap, struct inode *inode, int mask) { /* * sysctl entries that are not writeable, * are _NOT_ writeable, capabilities or not. */ struct ctl_table_header *head; const struct ctl_table *table; int error; /* Executable files are not allowed under /proc/sys/ */ if ((mask & MAY_EXEC) && S_ISREG(inode->i_mode)) return -EACCES; head = grab_header(inode); if (IS_ERR(head)) return PTR_ERR(head); table = PROC_I(inode)->sysctl_entry; if (!table) /* global root - r-xr-xr-x */ error = mask & MAY_WRITE ? -EACCES : 0; else /* Use the permissions on the sysctl table entry */ error = sysctl_perm(head, table, mask & ~MAY_NOT_BLOCK); sysctl_head_finish(head); return error; } static int proc_sys_setattr(struct mnt_idmap *idmap, struct dentry *dentry, struct iattr *attr) { struct inode *inode = d_inode(dentry); int error; if (attr->ia_valid & (ATTR_MODE | ATTR_UID | ATTR_GID)) return -EPERM; error = setattr_prepare(&nop_mnt_idmap, dentry, attr); if (error) return error; setattr_copy(&nop_mnt_idmap, inode, attr); return 0; } static int proc_sys_getattr(struct mnt_idmap *idmap, const struct path *path, struct kstat *stat, u32 request_mask, unsigned int query_flags) { struct inode *inode = d_inode(path->dentry); struct ctl_table_header *head = grab_header(inode); const struct ctl_table *table = PROC_I(inode)->sysctl_entry; if (IS_ERR(head)) return PTR_ERR(head); generic_fillattr(&nop_mnt_idmap, request_mask, inode, stat); if (table) stat->mode = (stat->mode & S_IFMT) | table->mode; sysctl_head_finish(head); return 0; } static const struct file_operations proc_sys_file_operations = { .open = proc_sys_open, .poll = proc_sys_poll, .read_iter = proc_sys_read, .write_iter = proc_sys_write, .splice_read = copy_splice_read, .splice_write = iter_file_splice_write, .llseek = default_llseek, }; static const struct file_operations proc_sys_dir_file_operations = { .read = generic_read_dir, .iterate_shared = proc_sys_readdir, .llseek = generic_file_llseek, }; static const struct inode_operations proc_sys_inode_operations = { .permission = proc_sys_permission, .setattr = proc_sys_setattr, .getattr = proc_sys_getattr, }; static const struct inode_operations proc_sys_dir_operations = { .lookup = proc_sys_lookup, .permission = proc_sys_permission, .setattr = proc_sys_setattr, .getattr = proc_sys_getattr, }; static int proc_sys_revalidate(struct inode *dir, const struct qstr *name, struct dentry *dentry, unsigned int flags) { if (flags & LOOKUP_RCU) return -ECHILD; return !PROC_I(d_inode(dentry))->sysctl->unregistering; } static int proc_sys_delete(const struct dentry *dentry) { return !!PROC_I(d_inode(dentry))->sysctl->unregistering; } static int sysctl_is_seen(struct ctl_table_header *p) { struct ctl_table_set *set = p->set; int res; spin_lock(&sysctl_lock); if (p->unregistering) res = 0; else if (!set->is_seen) res = 1; else res = set->is_seen(set); spin_unlock(&sysctl_lock); return res; } static int proc_sys_compare(const struct dentry *dentry, unsigned int len, const char *str, const struct qstr *name) { struct ctl_table_header *head; struct inode *inode; /* Although proc doesn't have negative dentries, rcu-walk means * that inode here can be NULL */ /* AV: can it, indeed? */ inode = d_inode_rcu(dentry); if (!inode) return 1; if (name->len != len) return 1; if (memcmp(name->name, str, len)) return 1; head = rcu_dereference(PROC_I(inode)->sysctl); return !head || !sysctl_is_seen(head); } static const struct dentry_operations proc_sys_dentry_operations = { .d_revalidate = proc_sys_revalidate, .d_delete = proc_sys_delete, .d_compare = proc_sys_compare, }; static struct ctl_dir *find_subdir(struct ctl_dir *dir, const char *name, int namelen) { struct ctl_table_header *head; const struct ctl_table *entry; entry = find_entry(&head, dir, name, namelen); if (!entry) return ERR_PTR(-ENOENT); if (!S_ISDIR(entry->mode)) return ERR_PTR(-ENOTDIR); return container_of(head, struct ctl_dir, header); } static struct ctl_dir *new_dir(struct ctl_table_set *set, const char *name, int namelen) { struct ctl_table *table; struct ctl_dir *new; struct ctl_node *node; char *new_name; new = kzalloc(sizeof(*new) + sizeof(struct ctl_node) + sizeof(struct ctl_table) + namelen + 1, GFP_KERNEL); if (!new) return NULL; node = (struct ctl_node *)(new + 1); table = (struct ctl_table *)(node + 1); new_name = (char *)(table + 1); memcpy(new_name, name, namelen); table[0].procname = new_name; table[0].mode = S_IFDIR|S_IRUGO|S_IXUGO; init_header(&new->header, set->dir.header.root, set, node, table, 1); return new; } /** * get_subdir - find or create a subdir with the specified name. * @dir: Directory to create the subdirectory in * @name: The name of the subdirectory to find or create * @namelen: The length of name * * Takes a directory with an elevated reference count so we know that * if we drop the lock the directory will not go away. Upon success * the reference is moved from @dir to the returned subdirectory. * Upon error an error code is returned and the reference on @dir is * simply dropped. */ static struct ctl_dir *get_subdir(struct ctl_dir *dir, const char *name, int namelen) { struct ctl_table_set *set = dir->header.set; struct ctl_dir *subdir, *new = NULL; int err; spin_lock(&sysctl_lock); subdir = find_subdir(dir, name, namelen); if (!IS_ERR(subdir)) goto found; if (PTR_ERR(subdir) != -ENOENT) goto failed; spin_unlock(&sysctl_lock); new = new_dir(set, name, namelen); spin_lock(&sysctl_lock); subdir = ERR_PTR(-ENOMEM); if (!new) goto failed; /* Was the subdir added while we dropped the lock? */ subdir = find_subdir(dir, name, namelen); if (!IS_ERR(subdir)) goto found; if (PTR_ERR(subdir) != -ENOENT) goto failed; /* Nope. Use the our freshly made directory entry. */ err = insert_header(dir, &new->header); subdir = ERR_PTR(err); if (err) goto failed; subdir = new; found: subdir->header.nreg++; failed: if (IS_ERR(subdir)) { pr_err("sysctl could not get directory: "); sysctl_print_dir(dir); pr_cont("%*.*s %ld\n", namelen, namelen, name, PTR_ERR(subdir)); } drop_sysctl_table(&dir->header); if (new) drop_sysctl_table(&new->header); spin_unlock(&sysctl_lock); return subdir; } static struct ctl_dir *xlate_dir(struct ctl_table_set *set, struct ctl_dir *dir) { struct ctl_dir *parent; const char *procname; if (!dir->header.parent) return &set->dir; parent = xlate_dir(set, dir->header.parent); if (IS_ERR(parent)) return parent; procname = dir->header.ctl_table[0].procname; return find_subdir(parent, procname, strlen(procname)); } static int sysctl_follow_link(struct ctl_table_header **phead, const struct ctl_table **pentry) { struct ctl_table_header *head; const struct ctl_table *entry; struct ctl_table_root *root; struct ctl_table_set *set; struct ctl_dir *dir; int ret; spin_lock(&sysctl_lock); root = (*pentry)->data; set = lookup_header_set(root); dir = xlate_dir(set, (*phead)->parent); if (IS_ERR(dir)) ret = PTR_ERR(dir); else { const char *procname = (*pentry)->procname; head = NULL; entry = find_entry(&head, dir, procname, strlen(procname)); ret = -ENOENT; if (entry && use_table(head)) { unuse_table(*phead); *phead = head; *pentry = entry; ret = 0; } } spin_unlock(&sysctl_lock); return ret; } static int sysctl_err(const char *path, const struct ctl_table *table, char *fmt, ...) { struct va_format vaf; va_list args; va_start(args, fmt); vaf.fmt = fmt; vaf.va = &args; pr_err("sysctl table check failed: %s/%s %pV\n", path, table->procname, &vaf); va_end(args); return -EINVAL; } static int sysctl_check_table_array(const char *path, const struct ctl_table *table) { unsigned int extra; int err = 0; if ((table->proc_handler == proc_douintvec) || (table->proc_handler == proc_douintvec_minmax)) { if (table->maxlen != sizeof(unsigned int)) err |= sysctl_err(path, table, "array not allowed"); } if (table->proc_handler == proc_dou8vec_minmax) { if (table->maxlen != sizeof(u8)) err |= sysctl_err(path, table, "array not allowed"); if (table->extra1) { extra = *(unsigned int *) table->extra1; if (extra > 255U) err |= sysctl_err(path, table, "range value too large for proc_dou8vec_minmax"); } if (table->extra2) { extra = *(unsigned int *) table->extra2; if (extra > 255U) err |= sysctl_err(path, table, "range value too large for proc_dou8vec_minmax"); } } if (table->proc_handler == proc_dobool) { if (table->maxlen != sizeof(bool)) err |= sysctl_err(path, table, "array not allowed"); } return err; } static int sysctl_check_table(const char *path, struct ctl_table_header *header) { const struct ctl_table *entry; int err = 0; list_for_each_table_entry(entry, header) { if (!entry->procname) err |= sysctl_err(path, entry, "procname is null"); if ((entry->proc_handler == proc_dostring) || (entry->proc_handler == proc_dobool) || (entry->proc_handler == proc_dointvec) || (entry->proc_handler == proc_douintvec) || (entry->proc_handler == proc_douintvec_minmax) || (entry->proc_handler == proc_dointvec_minmax) || (entry->proc_handler == proc_dou8vec_minmax) || (entry->proc_handler == proc_dointvec_jiffies) || (entry->proc_handler == proc_dointvec_userhz_jiffies) || (entry->proc_handler == proc_dointvec_ms_jiffies) || (entry->proc_handler == proc_doulongvec_minmax) || (entry->proc_handler == proc_doulongvec_ms_jiffies_minmax)) { if (!entry->data) err |= sysctl_err(path, entry, "No data"); if (!entry->maxlen) err |= sysctl_err(path, entry, "No maxlen"); else err |= sysctl_check_table_array(path, entry); } if (!entry->proc_handler) err |= sysctl_err(path, entry, "No proc_handler"); if ((entry->mode & (S_IRUGO|S_IWUGO)) != entry->mode) err |= sysctl_err(path, entry, "bogus .mode 0%o", entry->mode); } return err; } static struct ctl_table_header *new_links(struct ctl_dir *dir, struct ctl_table_header *head) { struct ctl_table *link_table, *link; struct ctl_table_header *links; const struct ctl_table *entry; struct ctl_node *node; char *link_name; int name_bytes; name_bytes = 0; list_for_each_table_entry(entry, head) { name_bytes += strlen(entry->procname) + 1; } links = kzalloc(sizeof(struct ctl_table_header) + sizeof(struct ctl_node)*head->ctl_table_size + sizeof(struct ctl_table)*head->ctl_table_size + name_bytes, GFP_KERNEL); if (!links) return NULL; node = (struct ctl_node *)(links + 1); link_table = (struct ctl_table *)(node + head->ctl_table_size); link_name = (char *)(link_table + head->ctl_table_size); link = link_table; list_for_each_table_entry(entry, head) { int len = strlen(entry->procname) + 1; memcpy(link_name, entry->procname, len); link->procname = link_name; link->mode = S_IFLNK|S_IRWXUGO; link->data = head->root; link_name += len; link++; } init_header(links, dir->header.root, dir->header.set, node, link_table, head->ctl_table_size); links->nreg = head->ctl_table_size; return links; } static bool get_links(struct ctl_dir *dir, struct ctl_table_header *header, struct ctl_table_root *link_root) { struct ctl_table_header *tmp_head; const struct ctl_table *entry, *link; if (header->ctl_table_size == 0 || sysctl_is_perm_empty_ctl_header(header)) return true; /* Are there links available for every entry in table? */ list_for_each_table_entry(entry, header) { const char *procname = entry->procname; link = find_entry(&tmp_head, dir, procname, strlen(procname)); if (!link) return false; if (S_ISDIR(link->mode) && S_ISDIR(entry->mode)) continue; if (S_ISLNK(link->mode) && (link->data == link_root)) continue; return false; } /* The checks passed. Increase the registration count on the links */ list_for_each_table_entry(entry, header) { const char *procname = entry->procname; link = find_entry(&tmp_head, dir, procname, strlen(procname)); tmp_head->nreg++; } return true; } static int insert_links(struct ctl_table_header *head) { struct ctl_table_set *root_set = &sysctl_table_root.default_set; struct ctl_dir *core_parent; struct ctl_table_header *links; int err; if (head->set == root_set) return 0; core_parent = xlate_dir(root_set, head->parent); if (IS_ERR(core_parent)) return 0; if (get_links(core_parent, head, head->root)) return 0; core_parent->header.nreg++; spin_unlock(&sysctl_lock); links = new_links(core_parent, head); spin_lock(&sysctl_lock); err = -ENOMEM; if (!links) goto out; err = 0; if (get_links(core_parent, head, head->root)) { kfree(links); goto out; } err = insert_header(core_parent, links); if (err) kfree(links); out: drop_sysctl_table(&core_parent->header); return err; } /* Find the directory for the ctl_table. If one is not found create it. */ static struct ctl_dir *sysctl_mkdir_p(struct ctl_dir *dir, const char *path) { const char *name, *nextname; for (name = path; name; name = nextname) { int namelen; nextname = strchr(name, '/'); if (nextname) { namelen = nextname - name; nextname++; } else { namelen = strlen(name); } if (namelen == 0) continue; /* * namelen ensures if name is "foo/bar/yay" only foo is * registered first. We traverse as if using mkdir -p and * return a ctl_dir for the last directory entry. */ dir = get_subdir(dir, name, namelen); if (IS_ERR(dir)) break; } return dir; } /** * __register_sysctl_table - register a leaf sysctl table * @set: Sysctl tree to register on * @path: The path to the directory the sysctl table is in. * * @table: the top-level table structure. This table should not be free'd * after registration. So it should not be used on stack. It can either * be a global or dynamically allocated by the caller and free'd later * after sysctl unregistration. * @table_size : The number of elements in table * * Register a sysctl table hierarchy. @table should be a filled in ctl_table * array. * * The members of the &struct ctl_table structure are used as follows: * procname - the name of the sysctl file under /proc/sys. Set to %NULL to not * enter a sysctl file * data - a pointer to data for use by proc_handler * maxlen - the maximum size in bytes of the data * mode - the file permissions for the /proc/sys file * type - Defines the target type (described in struct definition) * proc_handler - the text handler routine (described below) * * extra1, extra2 - extra pointers usable by the proc handler routines * XXX: we should eventually modify these to use long min / max [0] * [0] https://lkml.kernel.org/87zgpte9o4.fsf@email.froward.int.ebiederm.org * * Leaf nodes in the sysctl tree will be represented by a single file * under /proc; non-leaf nodes are not allowed. * * There must be a proc_handler routine for any terminal nodes. * Several default handlers are available to cover common cases - * * proc_dostring(), proc_dointvec(), proc_dointvec_jiffies(), * proc_dointvec_userhz_jiffies(), proc_dointvec_minmax(), * proc_doulongvec_ms_jiffies_minmax(), proc_doulongvec_minmax() * * It is the handler's job to read the input buffer from user memory * and process it. The handler should return 0 on success. * * This routine returns %NULL on a failure to register, and a pointer * to the table header on success. */ struct ctl_table_header *__register_sysctl_table( struct ctl_table_set *set, const char *path, const struct ctl_table *table, size_t table_size) { struct ctl_table_root *root = set->dir.header.root; struct ctl_table_header *header; struct ctl_dir *dir; struct ctl_node *node; header = kzalloc(sizeof(struct ctl_table_header) + sizeof(struct ctl_node)*table_size, GFP_KERNEL_ACCOUNT); if (!header) return NULL; node = (struct ctl_node *)(header + 1); init_header(header, root, set, node, table, table_size); if (sysctl_check_table(path, header)) goto fail; spin_lock(&sysctl_lock); dir = &set->dir; /* Reference moved down the directory tree get_subdir */ dir->header.nreg++; spin_unlock(&sysctl_lock); dir = sysctl_mkdir_p(dir, path); if (IS_ERR(dir)) goto fail; spin_lock(&sysctl_lock); if (insert_header(dir, header)) goto fail_put_dir_locked; drop_sysctl_table(&dir->header); spin_unlock(&sysctl_lock); return header; fail_put_dir_locked: drop_sysctl_table(&dir->header); spin_unlock(&sysctl_lock); fail: kfree(header); return NULL; } /** * register_sysctl_sz - register a sysctl table * @path: The path to the directory the sysctl table is in. If the path * doesn't exist we will create it for you. * @table: the table structure. The calller must ensure the life of the @table * will be kept during the lifetime use of the syctl. It must not be freed * until unregister_sysctl_table() is called with the given returned table * with this registration. If your code is non modular then you don't need * to call unregister_sysctl_table() and can instead use something like * register_sysctl_init() which does not care for the result of the syctl * registration. * @table_size: The number of elements in table. * * Register a sysctl table. @table should be a filled in ctl_table * array. A completely 0 filled entry terminates the table. * * See __register_sysctl_table for more details. */ struct ctl_table_header *register_sysctl_sz(const char *path, const struct ctl_table *table, size_t table_size) { return __register_sysctl_table(&sysctl_table_root.default_set, path, table, table_size); } EXPORT_SYMBOL(register_sysctl_sz); /** * __register_sysctl_init() - register sysctl table to path * @path: path name for sysctl base. If that path doesn't exist we will create * it for you. * @table: This is the sysctl table that needs to be registered to the path. * The caller must ensure the life of the @table will be kept during the * lifetime use of the sysctl. * @table_name: The name of sysctl table, only used for log printing when * registration fails * @table_size: The number of elements in table * * The sysctl interface is used by userspace to query or modify at runtime * a predefined value set on a variable. These variables however have default * values pre-set. Code which depends on these variables will always work even * if register_sysctl() fails. If register_sysctl() fails you'd just loose the * ability to query or modify the sysctls dynamically at run time. Chances of * register_sysctl() failing on init are extremely low, and so for both reasons * this function does not return any error as it is used by initialization code. * * Context: if your base directory does not exist it will be created for you. */ void __init __register_sysctl_init(const char *path, const struct ctl_table *table, const char *table_name, size_t table_size) { struct ctl_table_header *hdr = register_sysctl_sz(path, table, table_size); if (unlikely(!hdr)) { pr_err("failed when register_sysctl_sz %s to %s\n", table_name, path); return; } kmemleak_not_leak(hdr); } static void put_links(struct ctl_table_header *header) { struct ctl_table_set *root_set = &sysctl_table_root.default_set; struct ctl_table_root *root = header->root; struct ctl_dir *parent = header->parent; struct ctl_dir *core_parent; const struct ctl_table *entry; if (header->set == root_set) return; core_parent = xlate_dir(root_set, parent); if (IS_ERR(core_parent)) return; list_for_each_table_entry(entry, header) { struct ctl_table_header *link_head; const struct ctl_table *link; const char *name = entry->procname; link = find_entry(&link_head, core_parent, name, strlen(name)); if (link && ((S_ISDIR(link->mode) && S_ISDIR(entry->mode)) || (S_ISLNK(link->mode) && (link->data == root)))) { drop_sysctl_table(link_head); } else { pr_err("sysctl link missing during unregister: "); sysctl_print_dir(parent); pr_cont("%s\n", name); } } } static void drop_sysctl_table(struct ctl_table_header *header) { struct ctl_dir *parent = header->parent; if (--header->nreg) return; if (parent) { put_links(header); start_unregistering(header); } if (!--header->count) kfree_rcu(header, rcu); if (parent) drop_sysctl_table(&parent->header); } /** * unregister_sysctl_table - unregister a sysctl table hierarchy * @header: the header returned from register_sysctl or __register_sysctl_table * * Unregisters the sysctl table and all children. proc entries may not * actually be removed until they are no longer used by anyone. */ void unregister_sysctl_table(struct ctl_table_header * header) { might_sleep(); if (header == NULL) return; spin_lock(&sysctl_lock); drop_sysctl_table(header); spin_unlock(&sysctl_lock); } EXPORT_SYMBOL(unregister_sysctl_table); void setup_sysctl_set(struct ctl_table_set *set, struct ctl_table_root *root, int (*is_seen)(struct ctl_table_set *)) { memset(set, 0, sizeof(*set)); set->is_seen = is_seen; init_header(&set->dir.header, root, set, NULL, root_table, 1); } void retire_sysctl_set(struct ctl_table_set *set) { WARN_ON(!RB_EMPTY_ROOT(&set->dir.root)); } int __init proc_sys_init(void) { struct proc_dir_entry *proc_sys_root; proc_sys_root = proc_mkdir("sys", NULL); proc_sys_root->proc_iops = &proc_sys_dir_operations; proc_sys_root->proc_dir_ops = &proc_sys_dir_file_operations; proc_sys_root->nlink = 0; return sysctl_init_bases(); } struct sysctl_alias { const char *kernel_param; const char *sysctl_param; }; /* * Historically some settings had both sysctl and a command line parameter. * With the generic sysctl. parameter support, we can handle them at a single * place and only keep the historical name for compatibility. This is not meant * to add brand new aliases. When adding existing aliases, consider whether * the possibly different moment of changing the value (e.g. from early_param * to the moment do_sysctl_args() is called) is an issue for the specific * parameter. */ static const struct sysctl_alias sysctl_aliases[] = { {"hardlockup_all_cpu_backtrace", "kernel.hardlockup_all_cpu_backtrace" }, {"hung_task_panic", "kernel.hung_task_panic" }, {"numa_zonelist_order", "vm.numa_zonelist_order" }, {"softlockup_all_cpu_backtrace", "kernel.softlockup_all_cpu_backtrace" }, { } }; static const char *sysctl_find_alias(char *param) { const struct sysctl_alias *alias; for (alias = &sysctl_aliases[0]; alias->kernel_param != NULL; alias++) { if (strcmp(alias->kernel_param, param) == 0) return alias->sysctl_param; } return NULL; } bool sysctl_is_alias(char *param) { const char *alias = sysctl_find_alias(param); return alias != NULL; } /* Set sysctl value passed on kernel command line. */ static int process_sysctl_arg(char *param, char *val, const char *unused, void *arg) { char *path; struct vfsmount **proc_mnt = arg; struct file_system_type *proc_fs_type; struct file *file; int len; int err; loff_t pos = 0; ssize_t wret; if (strncmp(param, "sysctl", sizeof("sysctl") - 1) == 0) { param += sizeof("sysctl") - 1; if (param[0] != '/' && param[0] != '.') return 0; param++; } else { param = (char *) sysctl_find_alias(param); if (!param) return 0; } if (!val) return -EINVAL; len = strlen(val); if (len == 0) return -EINVAL; /* * To set sysctl options, we use a temporary mount of proc, look up the * respective sys/ file and write to it. To avoid mounting it when no * options were given, we mount it only when the first sysctl option is * found. Why not a persistent mount? There are problems with a * persistent mount of proc in that it forces userspace not to use any * proc mount options. */ if (!*proc_mnt) { proc_fs_type = get_fs_type("proc"); if (!proc_fs_type) { pr_err("Failed to find procfs to set sysctl from command line\n"); return 0; } *proc_mnt = kern_mount(proc_fs_type); put_filesystem(proc_fs_type); if (IS_ERR(*proc_mnt)) { pr_err("Failed to mount procfs to set sysctl from command line\n"); return 0; } } path = kasprintf(GFP_KERNEL, "sys/%s", param); if (!path) panic("%s: Failed to allocate path for %s\n", __func__, param); strreplace(path, '.', '/'); file = file_open_root_mnt(*proc_mnt, path, O_WRONLY, 0); if (IS_ERR(file)) { err = PTR_ERR(file); if (err == -ENOENT) pr_err("Failed to set sysctl parameter '%s=%s': parameter not found\n", param, val); else if (err == -EACCES) pr_err("Failed to set sysctl parameter '%s=%s': permission denied (read-only?)\n", param, val); else pr_err("Error %pe opening proc file to set sysctl parameter '%s=%s'\n", file, param, val); goto out; } wret = kernel_write(file, val, len, &pos); if (wret < 0) { err = wret; if (err == -EINVAL) pr_err("Failed to set sysctl parameter '%s=%s': invalid value\n", param, val); else pr_err("Error %pe writing to proc file to set sysctl parameter '%s=%s'\n", ERR_PTR(err), param, val); } else if (wret != len) { pr_err("Wrote only %zd bytes of %d writing to proc file %s to set sysctl parameter '%s=%s\n", wret, len, path, param, val); } err = filp_close(file, NULL); if (err) pr_err("Error %pe closing proc file to set sysctl parameter '%s=%s\n", ERR_PTR(err), param, val); out: kfree(path); return 0; } void do_sysctl_args(void) { char *command_line; struct vfsmount *proc_mnt = NULL; command_line = kstrdup(saved_command_line, GFP_KERNEL); if (!command_line) panic("%s: Failed to allocate copy of command line\n", __func__); parse_args("Setting sysctl args", command_line, NULL, 0, -1, -1, &proc_mnt, process_sysctl_arg); if (proc_mnt) kern_unmount(proc_mnt); kfree(command_line); } |
| 1063 1066 | 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-only #include <linux/etherdevice.h> #include "ipvlan.h" #include <linux/if_vlan.h> #include <linux/if_tap.h> #include <linux/interrupt.h> #include <linux/nsproxy.h> #include <linux/compat.h> #include <linux/if_tun.h> #include <linux/module.h> #include <linux/skbuff.h> #include <linux/cache.h> #include <linux/sched.h> #include <linux/types.h> #include <linux/slab.h> #include <linux/wait.h> #include <linux/cdev.h> #include <linux/idr.h> #include <linux/fs.h> #include <linux/uio.h> #include <net/net_namespace.h> #include <net/rtnetlink.h> #include <net/sock.h> #include <linux/virtio_net.h> #define TUN_OFFLOADS (NETIF_F_HW_CSUM | NETIF_F_TSO_ECN | NETIF_F_TSO | \ NETIF_F_TSO6) static dev_t ipvtap_major; static struct cdev ipvtap_cdev; static const void *ipvtap_net_namespace(const struct device *d) { const struct net_device *dev = to_net_dev(d->parent); return dev_net(dev); } static struct class ipvtap_class = { .name = "ipvtap", .ns_type = &net_ns_type_operations, .namespace = ipvtap_net_namespace, }; struct ipvtap_dev { struct ipvl_dev vlan; struct tap_dev tap; }; static void ipvtap_count_tx_dropped(struct tap_dev *tap) { struct ipvtap_dev *vlantap = container_of(tap, struct ipvtap_dev, tap); struct ipvl_dev *vlan = &vlantap->vlan; this_cpu_inc(vlan->pcpu_stats->tx_drps); } static void ipvtap_count_rx_dropped(struct tap_dev *tap) { struct ipvtap_dev *vlantap = container_of(tap, struct ipvtap_dev, tap); struct ipvl_dev *vlan = &vlantap->vlan; ipvlan_count_rx(vlan, 0, 0, 0); } static void ipvtap_update_features(struct tap_dev *tap, netdev_features_t features) { struct ipvtap_dev *vlantap = container_of(tap, struct ipvtap_dev, tap); struct ipvl_dev *vlan = &vlantap->vlan; vlan->sfeatures = features; netdev_update_features(vlan->dev); } static int ipvtap_newlink(struct net *src_net, struct net_device *dev, struct nlattr *tb[], struct nlattr *data[], struct netlink_ext_ack *extack) { struct ipvtap_dev *vlantap = netdev_priv(dev); int err; INIT_LIST_HEAD(&vlantap->tap.queue_list); /* Since macvlan supports all offloads by default, make * tap support all offloads also. */ vlantap->tap.tap_features = TUN_OFFLOADS; vlantap->tap.count_tx_dropped = ipvtap_count_tx_dropped; vlantap->tap.update_features = ipvtap_update_features; vlantap->tap.count_rx_dropped = ipvtap_count_rx_dropped; err = netdev_rx_handler_register(dev, tap_handle_frame, &vlantap->tap); if (err) return err; /* Don't put anything that may fail after macvlan_common_newlink * because we can't undo what it does. */ err = ipvlan_link_new(src_net, dev, tb, data, extack); if (err) { netdev_rx_handler_unregister(dev); return err; } vlantap->tap.dev = vlantap->vlan.dev; return err; } static void ipvtap_dellink(struct net_device *dev, struct list_head *head) { struct ipvtap_dev *vlan = netdev_priv(dev); netdev_rx_handler_unregister(dev); tap_del_queues(&vlan->tap); ipvlan_link_delete(dev, head); } static void ipvtap_setup(struct net_device *dev) { ipvlan_link_setup(dev); dev->tx_queue_len = TUN_READQ_SIZE; dev->priv_flags &= ~IFF_NO_QUEUE; } static struct rtnl_link_ops ipvtap_link_ops __read_mostly = { .kind = "ipvtap", .setup = ipvtap_setup, .newlink = ipvtap_newlink, .dellink = ipvtap_dellink, .priv_size = sizeof(struct ipvtap_dev), }; static int ipvtap_device_event(struct notifier_block *unused, unsigned long event, void *ptr) { struct net_device *dev = netdev_notifier_info_to_dev(ptr); struct ipvtap_dev *vlantap; struct device *classdev; dev_t devt; int err; char tap_name[IFNAMSIZ]; if (dev->rtnl_link_ops != &ipvtap_link_ops) return NOTIFY_DONE; snprintf(tap_name, IFNAMSIZ, "tap%d", dev->ifindex); vlantap = netdev_priv(dev); switch (event) { case NETDEV_REGISTER: /* Create the device node here after the network device has * been registered but before register_netdevice has * finished running. */ err = tap_get_minor(ipvtap_major, &vlantap->tap); if (err) return notifier_from_errno(err); devt = MKDEV(MAJOR(ipvtap_major), vlantap->tap.minor); classdev = device_create(&ipvtap_class, &dev->dev, devt, dev, "%s", tap_name); if (IS_ERR(classdev)) { tap_free_minor(ipvtap_major, &vlantap->tap); return notifier_from_errno(PTR_ERR(classdev)); } err = sysfs_create_link(&dev->dev.kobj, &classdev->kobj, tap_name); if (err) return notifier_from_errno(err); break; case NETDEV_UNREGISTER: /* vlan->minor == 0 if NETDEV_REGISTER above failed */ if (vlantap->tap.minor == 0) break; sysfs_remove_link(&dev->dev.kobj, tap_name); devt = MKDEV(MAJOR(ipvtap_major), vlantap->tap.minor); device_destroy(&ipvtap_class, devt); tap_free_minor(ipvtap_major, &vlantap->tap); break; case NETDEV_CHANGE_TX_QUEUE_LEN: if (tap_queue_resize(&vlantap->tap)) return NOTIFY_BAD; break; } return NOTIFY_DONE; } static struct notifier_block ipvtap_notifier_block __read_mostly = { .notifier_call = ipvtap_device_event, }; static int __init ipvtap_init(void) { int err; err = tap_create_cdev(&ipvtap_cdev, &ipvtap_major, "ipvtap", THIS_MODULE); if (err) goto out1; err = class_register(&ipvtap_class); if (err) goto out2; err = register_netdevice_notifier(&ipvtap_notifier_block); if (err) goto out3; err = ipvlan_link_register(&ipvtap_link_ops); if (err) goto out4; return 0; out4: unregister_netdevice_notifier(&ipvtap_notifier_block); out3: class_unregister(&ipvtap_class); out2: tap_destroy_cdev(ipvtap_major, &ipvtap_cdev); out1: return err; } module_init(ipvtap_init); static void __exit ipvtap_exit(void) { rtnl_link_unregister(&ipvtap_link_ops); unregister_netdevice_notifier(&ipvtap_notifier_block); class_unregister(&ipvtap_class); tap_destroy_cdev(ipvtap_major, &ipvtap_cdev); } module_exit(ipvtap_exit); MODULE_ALIAS_RTNL_LINK("ipvtap"); MODULE_AUTHOR("Sainath Grandhi <sainath.grandhi@intel.com>"); MODULE_DESCRIPTION("IP-VLAN based tap driver"); MODULE_LICENSE("GPL"); |
| 141 6 280 102 79 | 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 | #undef TRACE_SYSTEM #define TRACE_SYSTEM qdisc #if !defined(_TRACE_QDISC_H) || defined(TRACE_HEADER_MULTI_READ) #define _TRACE_QDISC_H #include <linux/skbuff.h> #include <linux/netdevice.h> #include <linux/tracepoint.h> #include <linux/ftrace.h> #include <linux/pkt_sched.h> #include <net/sch_generic.h> TRACE_EVENT(qdisc_dequeue, TP_PROTO(struct Qdisc *qdisc, const struct netdev_queue *txq, int packets, struct sk_buff *skb), TP_ARGS(qdisc, txq, packets, skb), TP_STRUCT__entry( __field( struct Qdisc *, qdisc ) __field(const struct netdev_queue *, txq ) __field( int, packets ) __field( void *, skbaddr ) __field( int, ifindex ) __field( u32, handle ) __field( u32, parent ) __field( unsigned long, txq_state) ), /* skb==NULL indicate packets dequeued was 0, even when packets==1 */ TP_fast_assign( __entry->qdisc = qdisc; __entry->txq = txq; __entry->packets = skb ? packets : 0; __entry->skbaddr = skb; __entry->ifindex = txq->dev ? txq->dev->ifindex : 0; __entry->handle = qdisc->handle; __entry->parent = qdisc->parent; __entry->txq_state = txq->state; ), TP_printk("dequeue ifindex=%d qdisc handle=0x%X parent=0x%X txq_state=0x%lX packets=%d skbaddr=%p", __entry->ifindex, __entry->handle, __entry->parent, __entry->txq_state, __entry->packets, __entry->skbaddr ) ); TRACE_EVENT(qdisc_enqueue, TP_PROTO(struct Qdisc *qdisc, const struct netdev_queue *txq, struct sk_buff *skb), TP_ARGS(qdisc, txq, skb), TP_STRUCT__entry( __field(struct Qdisc *, qdisc) __field(const struct netdev_queue *, txq) __field(void *, skbaddr) __field(int, ifindex) __field(u32, handle) __field(u32, parent) ), TP_fast_assign( __entry->qdisc = qdisc; __entry->txq = txq; __entry->skbaddr = skb; __entry->ifindex = txq->dev ? txq->dev->ifindex : 0; __entry->handle = qdisc->handle; __entry->parent = qdisc->parent; ), TP_printk("enqueue ifindex=%d qdisc handle=0x%X parent=0x%X skbaddr=%p", __entry->ifindex, __entry->handle, __entry->parent, __entry->skbaddr) ); TRACE_EVENT(qdisc_reset, TP_PROTO(struct Qdisc *q), TP_ARGS(q), TP_STRUCT__entry( __string( dev, qdisc_dev(q) ? qdisc_dev(q)->name : "(null)" ) __string( kind, q->ops->id ) __field( u32, parent ) __field( u32, handle ) ), TP_fast_assign( __assign_str(dev); __assign_str(kind); __entry->parent = q->parent; __entry->handle = q->handle; ), TP_printk("dev=%s kind=%s parent=%x:%x handle=%x:%x", __get_str(dev), __get_str(kind), TC_H_MAJ(__entry->parent) >> 16, TC_H_MIN(__entry->parent), TC_H_MAJ(__entry->handle) >> 16, TC_H_MIN(__entry->handle)) ); TRACE_EVENT(qdisc_destroy, TP_PROTO(struct Qdisc *q), TP_ARGS(q), TP_STRUCT__entry( __string( dev, qdisc_dev(q)->name ) __string( kind, q->ops->id ) __field( u32, parent ) __field( u32, handle ) ), TP_fast_assign( __assign_str(dev); __assign_str(kind); __entry->parent = q->parent; __entry->handle = q->handle; ), TP_printk("dev=%s kind=%s parent=%x:%x handle=%x:%x", __get_str(dev), __get_str(kind), TC_H_MAJ(__entry->parent) >> 16, TC_H_MIN(__entry->parent), TC_H_MAJ(__entry->handle) >> 16, TC_H_MIN(__entry->handle)) ); TRACE_EVENT(qdisc_create, TP_PROTO(const struct Qdisc_ops *ops, struct net_device *dev, u32 parent), TP_ARGS(ops, dev, parent), TP_STRUCT__entry( __string( dev, dev->name ) __string( kind, ops->id ) __field( u32, parent ) ), TP_fast_assign( __assign_str(dev); __assign_str(kind); __entry->parent = parent; ), TP_printk("dev=%s kind=%s parent=%x:%x", __get_str(dev), __get_str(kind), TC_H_MAJ(__entry->parent) >> 16, TC_H_MIN(__entry->parent)) ); #endif /* _TRACE_QDISC_H */ /* This part must be outside protection */ #include <trace/define_trace.h> |
| 707 707 | 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 | // SPDX-License-Identifier: GPL-2.0-only /* * rcuref - A scalable reference count implementation for RCU managed objects * * rcuref is provided to replace open coded reference count implementations * based on atomic_t. It protects explicitely RCU managed objects which can * be visible even after the last reference has been dropped and the object * is heading towards destruction. * * A common usage pattern is: * * get() * rcu_read_lock(); * p = get_ptr(); * if (p && !atomic_inc_not_zero(&p->refcnt)) * p = NULL; * rcu_read_unlock(); * return p; * * put() * if (!atomic_dec_return(&->refcnt)) { * remove_ptr(p); * kfree_rcu((p, rcu); * } * * atomic_inc_not_zero() is implemented with a try_cmpxchg() loop which has * O(N^2) behaviour under contention with N concurrent operations. * * rcuref uses atomic_add_negative_relaxed() for the fast path, which scales * better under contention. * * Why not refcount? * ================= * * In principle it should be possible to make refcount use the rcuref * scheme, but the destruction race described below cannot be prevented * unless the protected object is RCU managed. * * Theory of operation * =================== * * rcuref uses an unsigned integer reference counter. As long as the * counter value is greater than or equal to RCUREF_ONEREF and not larger * than RCUREF_MAXREF the reference is alive: * * ONEREF MAXREF SATURATED RELEASED DEAD NOREF * 0 0x7FFFFFFF 0x8000000 0xA0000000 0xBFFFFFFF 0xC0000000 0xE0000000 0xFFFFFFFF * <---valid --------> <-------saturation zone-------> <-----dead zone-----> * * The get() and put() operations do unconditional increments and * decrements. The result is checked after the operation. This optimizes * for the fast path. * * If the reference count is saturated or dead, then the increments and * decrements are not harmful as the reference count still stays in the * respective zones and is always set back to STATURATED resp. DEAD. The * zones have room for 2^28 racing operations in each direction, which * makes it practically impossible to escape the zones. * * Once the last reference is dropped the reference count becomes * RCUREF_NOREF which forces rcuref_put() into the slowpath operation. The * slowpath then tries to set the reference count from RCUREF_NOREF to * RCUREF_DEAD via a cmpxchg(). This opens a small window where a * concurrent rcuref_get() can acquire the reference count and bring it * back to RCUREF_ONEREF or even drop the reference again and mark it DEAD. * * If the cmpxchg() succeeds then a concurrent rcuref_get() will result in * DEAD + 1, which is inside the dead zone. If that happens the reference * count is put back to DEAD. * * The actual race is possible due to the unconditional increment and * decrements in rcuref_get() and rcuref_put(): * * T1 T2 * get() put() * if (atomic_add_negative(-1, &ref->refcnt)) * succeeds-> atomic_cmpxchg(&ref->refcnt, NOREF, DEAD); * * atomic_add_negative(1, &ref->refcnt); <- Elevates refcount to DEAD + 1 * * As the result of T1's add is negative, the get() goes into the slow path * and observes refcnt being in the dead zone which makes the operation fail. * * Possible critical states: * * Context Counter References Operation * T1 0 1 init() * T2 1 2 get() * T1 0 1 put() * T2 -1 0 put() tries to mark dead * T1 0 1 get() * T2 0 1 put() mark dead fails * T1 -1 0 put() tries to mark dead * T1 DEAD 0 put() mark dead succeeds * T2 DEAD+1 0 get() fails and puts it back to DEAD * * Of course there are more complex scenarios, but the above illustrates * the working principle. The rest is left to the imagination of the * reader. * * Deconstruction race * =================== * * The release operation must be protected by prohibiting a grace period in * order to prevent a possible use after free: * * T1 T2 * put() get() * // ref->refcnt = ONEREF * if (!atomic_add_negative(-1, &ref->refcnt)) * return false; <- Not taken * * // ref->refcnt == NOREF * --> preemption * // Elevates ref->refcnt to ONEREF * if (!atomic_add_negative(1, &ref->refcnt)) * return true; <- taken * * if (put(&p->ref)) { <-- Succeeds * remove_pointer(p); * kfree_rcu(p, rcu); * } * * RCU grace period ends, object is freed * * atomic_cmpxchg(&ref->refcnt, NOREF, DEAD); <- UAF * * This is prevented by disabling preemption around the put() operation as * that's in most kernel configurations cheaper than a rcu_read_lock() / * rcu_read_unlock() pair and in many cases even a NOOP. In any case it * prevents the grace period which keeps the object alive until all put() * operations complete. * * Saturation protection * ===================== * * The reference count has a saturation limit RCUREF_MAXREF (INT_MAX). * Once this is exceedded the reference count becomes stale by setting it * to RCUREF_SATURATED, which will cause a memory leak, but it prevents * wrap arounds which obviously cause worse problems than a memory * leak. When saturation is reached a warning is emitted. * * Race conditions * =============== * * All reference count increment/decrement operations are unconditional and * only verified after the fact. This optimizes for the good case and takes * the occasional race vs. a dead or already saturated refcount into * account. The saturation and dead zones are large enough to accomodate * for that. * * Memory ordering * =============== * * Memory ordering rules are slightly relaxed wrt regular atomic_t functions * and provide only what is strictly required for refcounts. * * The increments are fully relaxed; these will not provide ordering. The * rationale is that whatever is used to obtain the object to increase the * reference count on will provide the ordering. For locked data * structures, its the lock acquire, for RCU/lockless data structures its * the dependent load. * * rcuref_get() provides a control dependency ordering future stores which * ensures that the object is not modified when acquiring a reference * fails. * * rcuref_put() provides release order, i.e. all prior loads and stores * will be issued before. It also provides a control dependency ordering * against the subsequent destruction of the object. * * If rcuref_put() successfully dropped the last reference and marked the * object DEAD it also provides acquire ordering. */ #include <linux/export.h> #include <linux/rcuref.h> /** * rcuref_get_slowpath - Slowpath of rcuref_get() * @ref: Pointer to the reference count * * Invoked when the reference count is outside of the valid zone. * * Return: * False if the reference count was already marked dead * * True if the reference count is saturated, which prevents the * object from being deconstructed ever. */ bool rcuref_get_slowpath(rcuref_t *ref) { unsigned int cnt = atomic_read(&ref->refcnt); /* * If the reference count was already marked dead, undo the * increment so it stays in the middle of the dead zone and return * fail. */ if (cnt >= RCUREF_RELEASED) { atomic_set(&ref->refcnt, RCUREF_DEAD); return false; } /* * If it was saturated, warn and mark it so. In case the increment * was already on a saturated value restore the saturation * marker. This keeps it in the middle of the saturation zone and * prevents the reference count from overflowing. This leaks the * object memory, but prevents the obvious reference count overflow * damage. */ if (WARN_ONCE(cnt > RCUREF_MAXREF, "rcuref saturated - leaking memory")) atomic_set(&ref->refcnt, RCUREF_SATURATED); return true; } EXPORT_SYMBOL_GPL(rcuref_get_slowpath); /** * rcuref_put_slowpath - Slowpath of __rcuref_put() * @ref: Pointer to the 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 rcuref_put_slowpath(rcuref_t *ref) { unsigned int cnt = atomic_read(&ref->refcnt); /* Did this drop the last reference? */ if (likely(cnt == RCUREF_NOREF)) { /* * Carefully try to set the reference count to RCUREF_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_try_cmpxchg_release(&ref->refcnt, &cnt, RCUREF_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 >= RCUREF_RELEASED, "rcuref - imbalanced put()")) { atomic_set(&ref->refcnt, RCUREF_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 > RCUREF_MAXREF) atomic_set(&ref->refcnt, RCUREF_SATURATED); return false; } EXPORT_SYMBOL_GPL(rcuref_put_slowpath); |
| 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 | // SPDX-License-Identifier: GPL-2.0-only #include "netlink.h" #include "common.h" #include "bitset.h" struct fec_req_info { struct ethnl_req_info base; }; struct fec_reply_data { struct ethnl_reply_data base; __ETHTOOL_DECLARE_LINK_MODE_MASK(fec_link_modes); u32 active_fec; u8 fec_auto; struct fec_stat_grp { u64 stats[1 + ETHTOOL_MAX_LANES]; u8 cnt; } corr, uncorr, corr_bits; }; #define FEC_REPDATA(__reply_base) \ container_of(__reply_base, struct fec_reply_data, base) #define ETHTOOL_FEC_MASK ((ETHTOOL_FEC_LLRS << 1) - 1) const struct nla_policy ethnl_fec_get_policy[ETHTOOL_A_FEC_HEADER + 1] = { [ETHTOOL_A_FEC_HEADER] = NLA_POLICY_NESTED(ethnl_header_policy_stats), }; static void ethtool_fec_to_link_modes(u32 fec, unsigned long *link_modes, u8 *fec_auto) { if (fec_auto) *fec_auto = !!(fec & ETHTOOL_FEC_AUTO); if (fec & ETHTOOL_FEC_OFF) __set_bit(ETHTOOL_LINK_MODE_FEC_NONE_BIT, link_modes); if (fec & ETHTOOL_FEC_RS) __set_bit(ETHTOOL_LINK_MODE_FEC_RS_BIT, link_modes); if (fec & ETHTOOL_FEC_BASER) __set_bit(ETHTOOL_LINK_MODE_FEC_BASER_BIT, link_modes); if (fec & ETHTOOL_FEC_LLRS) __set_bit(ETHTOOL_LINK_MODE_FEC_LLRS_BIT, link_modes); } static int ethtool_link_modes_to_fecparam(struct ethtool_fecparam *fec, unsigned long *link_modes, u8 fec_auto) { memset(fec, 0, sizeof(*fec)); if (fec_auto) fec->fec |= ETHTOOL_FEC_AUTO; if (__test_and_clear_bit(ETHTOOL_LINK_MODE_FEC_NONE_BIT, link_modes)) fec->fec |= ETHTOOL_FEC_OFF; if (__test_and_clear_bit(ETHTOOL_LINK_MODE_FEC_RS_BIT, link_modes)) fec->fec |= ETHTOOL_FEC_RS; if (__test_and_clear_bit(ETHTOOL_LINK_MODE_FEC_BASER_BIT, link_modes)) fec->fec |= ETHTOOL_FEC_BASER; if (__test_and_clear_bit(ETHTOOL_LINK_MODE_FEC_LLRS_BIT, link_modes)) fec->fec |= ETHTOOL_FEC_LLRS; if (!bitmap_empty(link_modes, __ETHTOOL_LINK_MODE_MASK_NBITS)) return -EINVAL; return 0; } static void fec_stats_recalc(struct fec_stat_grp *grp, struct ethtool_fec_stat *stats) { int i; if (stats->lanes[0] == ETHTOOL_STAT_NOT_SET) { grp->stats[0] = stats->total; grp->cnt = stats->total != ETHTOOL_STAT_NOT_SET; return; } grp->cnt = 1; grp->stats[0] = 0; for (i = 0; i < ETHTOOL_MAX_LANES; i++) { if (stats->lanes[i] == ETHTOOL_STAT_NOT_SET) break; grp->stats[0] += stats->lanes[i]; grp->stats[grp->cnt++] = stats->lanes[i]; } } static int fec_prepare_data(const struct ethnl_req_info *req_base, struct ethnl_reply_data *reply_base, const struct genl_info *info) { __ETHTOOL_DECLARE_LINK_MODE_MASK(active_fec_modes) = {}; struct fec_reply_data *data = FEC_REPDATA(reply_base); struct net_device *dev = reply_base->dev; struct ethtool_fecparam fec = {}; int ret; if (!dev->ethtool_ops->get_fecparam) return -EOPNOTSUPP; ret = ethnl_ops_begin(dev); if (ret < 0) return ret; ret = dev->ethtool_ops->get_fecparam(dev, &fec); if (ret) goto out_complete; if (req_base->flags & ETHTOOL_FLAG_STATS && dev->ethtool_ops->get_fec_stats) { struct ethtool_fec_stats stats; ethtool_stats_init((u64 *)&stats, sizeof(stats) / 8); dev->ethtool_ops->get_fec_stats(dev, &stats); fec_stats_recalc(&data->corr, &stats.corrected_blocks); fec_stats_recalc(&data->uncorr, &stats.uncorrectable_blocks); fec_stats_recalc(&data->corr_bits, &stats.corrected_bits); } WARN_ON_ONCE(fec.reserved); ethtool_fec_to_link_modes(fec.fec, data->fec_link_modes, &data->fec_auto); ethtool_fec_to_link_modes(fec.active_fec, active_fec_modes, NULL); data->active_fec = find_first_bit(active_fec_modes, __ETHTOOL_LINK_MODE_MASK_NBITS); /* Don't report attr if no FEC mode set. Note that * ethtool_fecparam_to_link_modes() ignores NONE and AUTO. */ if (data->active_fec == __ETHTOOL_LINK_MODE_MASK_NBITS) data->active_fec = 0; out_complete: ethnl_ops_complete(dev); return ret; } static int fec_reply_size(const struct ethnl_req_info *req_base, const struct ethnl_reply_data *reply_base) { bool compact = req_base->flags & ETHTOOL_FLAG_COMPACT_BITSETS; const struct fec_reply_data *data = FEC_REPDATA(reply_base); int len = 0; int ret; ret = ethnl_bitset_size(data->fec_link_modes, NULL, __ETHTOOL_LINK_MODE_MASK_NBITS, link_mode_names, compact); if (ret < 0) return ret; len += ret; len += nla_total_size(sizeof(u8)) + /* _FEC_AUTO */ nla_total_size(sizeof(u32)); /* _FEC_ACTIVE */ if (req_base->flags & ETHTOOL_FLAG_STATS) len += 3 * nla_total_size_64bit(sizeof(u64) * (1 + ETHTOOL_MAX_LANES)); return len; } static int fec_put_stats(struct sk_buff *skb, const struct fec_reply_data *data) { struct nlattr *nest; nest = nla_nest_start(skb, ETHTOOL_A_FEC_STATS); if (!nest) return -EMSGSIZE; if (nla_put_64bit(skb, ETHTOOL_A_FEC_STAT_CORRECTED, sizeof(u64) * data->corr.cnt, data->corr.stats, ETHTOOL_A_FEC_STAT_PAD) || nla_put_64bit(skb, ETHTOOL_A_FEC_STAT_UNCORR, sizeof(u64) * data->uncorr.cnt, data->uncorr.stats, ETHTOOL_A_FEC_STAT_PAD) || nla_put_64bit(skb, ETHTOOL_A_FEC_STAT_CORR_BITS, sizeof(u64) * data->corr_bits.cnt, data->corr_bits.stats, ETHTOOL_A_FEC_STAT_PAD)) goto err_cancel; nla_nest_end(skb, nest); return 0; err_cancel: nla_nest_cancel(skb, nest); return -EMSGSIZE; } static int fec_fill_reply(struct sk_buff *skb, const struct ethnl_req_info *req_base, const struct ethnl_reply_data *reply_base) { bool compact = req_base->flags & ETHTOOL_FLAG_COMPACT_BITSETS; const struct fec_reply_data *data = FEC_REPDATA(reply_base); int ret; ret = ethnl_put_bitset(skb, ETHTOOL_A_FEC_MODES, data->fec_link_modes, NULL, __ETHTOOL_LINK_MODE_MASK_NBITS, link_mode_names, compact); if (ret < 0) return ret; if (nla_put_u8(skb, ETHTOOL_A_FEC_AUTO, data->fec_auto) || (data->active_fec && nla_put_u32(skb, ETHTOOL_A_FEC_ACTIVE, data->active_fec))) return -EMSGSIZE; if (req_base->flags & ETHTOOL_FLAG_STATS && fec_put_stats(skb, data)) return -EMSGSIZE; return 0; } /* FEC_SET */ const struct nla_policy ethnl_fec_set_policy[ETHTOOL_A_FEC_AUTO + 1] = { [ETHTOOL_A_FEC_HEADER] = NLA_POLICY_NESTED(ethnl_header_policy), [ETHTOOL_A_FEC_MODES] = { .type = NLA_NESTED }, [ETHTOOL_A_FEC_AUTO] = NLA_POLICY_MAX(NLA_U8, 1), }; static int ethnl_set_fec_validate(struct ethnl_req_info *req_info, struct genl_info *info) { const struct ethtool_ops *ops = req_info->dev->ethtool_ops; return ops->get_fecparam && ops->set_fecparam ? 1 : -EOPNOTSUPP; } static int ethnl_set_fec(struct ethnl_req_info *req_info, struct genl_info *info) { __ETHTOOL_DECLARE_LINK_MODE_MASK(fec_link_modes) = {}; struct net_device *dev = req_info->dev; struct nlattr **tb = info->attrs; struct ethtool_fecparam fec = {}; bool mod = false; u8 fec_auto; int ret; ret = dev->ethtool_ops->get_fecparam(dev, &fec); if (ret < 0) return ret; ethtool_fec_to_link_modes(fec.fec, fec_link_modes, &fec_auto); ret = ethnl_update_bitset(fec_link_modes, __ETHTOOL_LINK_MODE_MASK_NBITS, tb[ETHTOOL_A_FEC_MODES], link_mode_names, info->extack, &mod); if (ret < 0) return ret; ethnl_update_u8(&fec_auto, tb[ETHTOOL_A_FEC_AUTO], &mod); if (!mod) return 0; ret = ethtool_link_modes_to_fecparam(&fec, fec_link_modes, fec_auto); if (ret) { NL_SET_ERR_MSG_ATTR(info->extack, tb[ETHTOOL_A_FEC_MODES], "invalid FEC modes requested"); return ret; } if (!fec.fec) { NL_SET_ERR_MSG_ATTR(info->extack, tb[ETHTOOL_A_FEC_MODES], "no FEC modes set"); return -EINVAL; } ret = dev->ethtool_ops->set_fecparam(dev, &fec); return ret < 0 ? ret : 1; } const struct ethnl_request_ops ethnl_fec_request_ops = { .request_cmd = ETHTOOL_MSG_FEC_GET, .reply_cmd = ETHTOOL_MSG_FEC_GET_REPLY, .hdr_attr = ETHTOOL_A_FEC_HEADER, .req_info_size = sizeof(struct fec_req_info), .reply_data_size = sizeof(struct fec_reply_data), .prepare_data = fec_prepare_data, .reply_size = fec_reply_size, .fill_reply = fec_fill_reply, .set_validate = ethnl_set_fec_validate, .set = ethnl_set_fec, .set_ntf_cmd = ETHTOOL_MSG_FEC_NTF, }; |
| 6 6 4 2 6 6 | 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 | // SPDX-License-Identifier: GPL-2.0-only #include "netlink.h" #include "common.h" struct linkinfo_req_info { struct ethnl_req_info base; }; struct linkinfo_reply_data { struct ethnl_reply_data base; struct ethtool_link_ksettings ksettings; struct ethtool_link_settings *lsettings; }; #define LINKINFO_REPDATA(__reply_base) \ container_of(__reply_base, struct linkinfo_reply_data, base) const struct nla_policy ethnl_linkinfo_get_policy[] = { [ETHTOOL_A_LINKINFO_HEADER] = NLA_POLICY_NESTED(ethnl_header_policy), }; static int linkinfo_prepare_data(const struct ethnl_req_info *req_base, struct ethnl_reply_data *reply_base, const struct genl_info *info) { struct linkinfo_reply_data *data = LINKINFO_REPDATA(reply_base); struct net_device *dev = reply_base->dev; int ret; data->lsettings = &data->ksettings.base; ret = ethnl_ops_begin(dev); if (ret < 0) return ret; ret = __ethtool_get_link_ksettings(dev, &data->ksettings); if (ret < 0) GENL_SET_ERR_MSG(info, "failed to retrieve link settings"); ethnl_ops_complete(dev); return ret; } static int linkinfo_reply_size(const struct ethnl_req_info *req_base, const struct ethnl_reply_data *reply_base) { return nla_total_size(sizeof(u8)) /* LINKINFO_PORT */ + nla_total_size(sizeof(u8)) /* LINKINFO_PHYADDR */ + nla_total_size(sizeof(u8)) /* LINKINFO_TP_MDIX */ + nla_total_size(sizeof(u8)) /* LINKINFO_TP_MDIX_CTRL */ + nla_total_size(sizeof(u8)) /* LINKINFO_TRANSCEIVER */ + 0; } static int linkinfo_fill_reply(struct sk_buff *skb, const struct ethnl_req_info *req_base, const struct ethnl_reply_data *reply_base) { const struct linkinfo_reply_data *data = LINKINFO_REPDATA(reply_base); if (nla_put_u8(skb, ETHTOOL_A_LINKINFO_PORT, data->lsettings->port) || nla_put_u8(skb, ETHTOOL_A_LINKINFO_PHYADDR, data->lsettings->phy_address) || nla_put_u8(skb, ETHTOOL_A_LINKINFO_TP_MDIX, data->lsettings->eth_tp_mdix) || nla_put_u8(skb, ETHTOOL_A_LINKINFO_TP_MDIX_CTRL, data->lsettings->eth_tp_mdix_ctrl) || nla_put_u8(skb, ETHTOOL_A_LINKINFO_TRANSCEIVER, data->lsettings->transceiver)) return -EMSGSIZE; return 0; } /* LINKINFO_SET */ const struct nla_policy ethnl_linkinfo_set_policy[] = { [ETHTOOL_A_LINKINFO_HEADER] = NLA_POLICY_NESTED(ethnl_header_policy), [ETHTOOL_A_LINKINFO_PORT] = { .type = NLA_U8 }, [ETHTOOL_A_LINKINFO_PHYADDR] = { .type = NLA_U8 }, [ETHTOOL_A_LINKINFO_TP_MDIX_CTRL] = { .type = NLA_U8 }, }; static int ethnl_set_linkinfo_validate(struct ethnl_req_info *req_info, struct genl_info *info) { const struct ethtool_ops *ops = req_info->dev->ethtool_ops; if (!ops->get_link_ksettings || !ops->set_link_ksettings) return -EOPNOTSUPP; return 1; } static int ethnl_set_linkinfo(struct ethnl_req_info *req_info, struct genl_info *info) { struct ethtool_link_ksettings ksettings = {}; struct ethtool_link_settings *lsettings; struct net_device *dev = req_info->dev; struct nlattr **tb = info->attrs; bool mod = false; int ret; ret = __ethtool_get_link_ksettings(dev, &ksettings); if (ret < 0) { GENL_SET_ERR_MSG(info, "failed to retrieve link settings"); return ret; } lsettings = &ksettings.base; ethnl_update_u8(&lsettings->port, tb[ETHTOOL_A_LINKINFO_PORT], &mod); ethnl_update_u8(&lsettings->phy_address, tb[ETHTOOL_A_LINKINFO_PHYADDR], &mod); ethnl_update_u8(&lsettings->eth_tp_mdix_ctrl, tb[ETHTOOL_A_LINKINFO_TP_MDIX_CTRL], &mod); if (!mod) return 0; ret = dev->ethtool_ops->set_link_ksettings(dev, &ksettings); if (ret < 0) { GENL_SET_ERR_MSG(info, "link settings update failed"); return ret; } return 1; } const struct ethnl_request_ops ethnl_linkinfo_request_ops = { .request_cmd = ETHTOOL_MSG_LINKINFO_GET, .reply_cmd = ETHTOOL_MSG_LINKINFO_GET_REPLY, .hdr_attr = ETHTOOL_A_LINKINFO_HEADER, .req_info_size = sizeof(struct linkinfo_req_info), .reply_data_size = sizeof(struct linkinfo_reply_data), .prepare_data = linkinfo_prepare_data, .reply_size = linkinfo_reply_size, .fill_reply = linkinfo_fill_reply, .set_validate = ethnl_set_linkinfo_validate, .set = ethnl_set_linkinfo, .set_ntf_cmd = ETHTOOL_MSG_LINKINFO_NTF, }; |
| 93 93 3 44 23 17 48 16 40 44 5 3 47 2 37 16 37 39 6 45 31 25 37 2 35 31 31 25 12 16 37 45 45 16 37 37 33 4 37 37 2 14 2 45 45 45 45 16 37 31 17 25 31 25 25 17 31 17 25 25 26 26 12 20 1 20 20 32 32 43 44 32 32 16 16 16 16 16 2 14 16 20 20 20 7 17 12 12 12 12 49 48 115 10 10 31 31 31 40 40 40 37 3 37 9 9 9 6 5 20 20 20 20 17 17 3 3 62 50 50 10 12 3 11 13 18 109 109 78 34 48 32 50 78 31 51 75 75 65 22 31 75 4 4 3 3 3 3 3 3 11 1 4 6 6 2 1 3 3 3 3 7 1 3 2 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 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 | // SPDX-License-Identifier: GPL-2.0-only #include <linux/kernel.h> #include <linux/netdevice.h> #include <linux/rtnetlink.h> #include <linux/slab.h> #include <net/switchdev.h> #include "br_private.h" #include "br_private_tunnel.h" static void nbp_vlan_set_vlan_dev_state(struct net_bridge_port *p, u16 vid); static inline int br_vlan_cmp(struct rhashtable_compare_arg *arg, const void *ptr) { const struct net_bridge_vlan *vle = ptr; u16 vid = *(u16 *)arg->key; return vle->vid != vid; } static const struct rhashtable_params br_vlan_rht_params = { .head_offset = offsetof(struct net_bridge_vlan, vnode), .key_offset = offsetof(struct net_bridge_vlan, vid), .key_len = sizeof(u16), .nelem_hint = 3, .max_size = VLAN_N_VID, .obj_cmpfn = br_vlan_cmp, .automatic_shrinking = true, }; static struct net_bridge_vlan *br_vlan_lookup(struct rhashtable *tbl, u16 vid) { return rhashtable_lookup_fast(tbl, &vid, br_vlan_rht_params); } static void __vlan_add_pvid(struct net_bridge_vlan_group *vg, const struct net_bridge_vlan *v) { if (vg->pvid == v->vid) return; smp_wmb(); br_vlan_set_pvid_state(vg, v->state); vg->pvid = v->vid; } static void __vlan_delete_pvid(struct net_bridge_vlan_group *vg, u16 vid) { if (vg->pvid != vid) return; smp_wmb(); vg->pvid = 0; } /* Update the BRIDGE_VLAN_INFO_PVID and BRIDGE_VLAN_INFO_UNTAGGED flags of @v. * If @commit is false, return just whether the BRIDGE_VLAN_INFO_PVID and * BRIDGE_VLAN_INFO_UNTAGGED bits of @flags would produce any change onto @v. */ static bool __vlan_flags_update(struct net_bridge_vlan *v, u16 flags, bool commit) { struct net_bridge_vlan_group *vg; bool change; if (br_vlan_is_master(v)) vg = br_vlan_group(v->br); else vg = nbp_vlan_group(v->port); /* check if anything would be changed on commit */ change = !!(flags & BRIDGE_VLAN_INFO_PVID) == !!(vg->pvid != v->vid) || ((flags ^ v->flags) & BRIDGE_VLAN_INFO_UNTAGGED); if (!commit) goto out; if (flags & BRIDGE_VLAN_INFO_PVID) __vlan_add_pvid(vg, v); else __vlan_delete_pvid(vg, v->vid); if (flags & BRIDGE_VLAN_INFO_UNTAGGED) v->flags |= BRIDGE_VLAN_INFO_UNTAGGED; else v->flags &= ~BRIDGE_VLAN_INFO_UNTAGGED; out: return change; } static bool __vlan_flags_would_change(struct net_bridge_vlan *v, u16 flags) { return __vlan_flags_update(v, flags, false); } static void __vlan_flags_commit(struct net_bridge_vlan *v, u16 flags) { __vlan_flags_update(v, flags, true); } static int __vlan_vid_add(struct net_device *dev, struct net_bridge *br, struct net_bridge_vlan *v, u16 flags, struct netlink_ext_ack *extack) { int err; /* Try switchdev op first. In case it is not supported, fallback to * 8021q add. */ err = br_switchdev_port_vlan_add(dev, v->vid, flags, false, extack); if (err == -EOPNOTSUPP) return vlan_vid_add(dev, br->vlan_proto, v->vid); v->priv_flags |= BR_VLFLAG_ADDED_BY_SWITCHDEV; return err; } static void __vlan_add_list(struct net_bridge_vlan *v) { struct net_bridge_vlan_group *vg; struct list_head *headp, *hpos; struct net_bridge_vlan *vent; if (br_vlan_is_master(v)) vg = br_vlan_group(v->br); else vg = nbp_vlan_group(v->port); headp = &vg->vlan_list; list_for_each_prev(hpos, headp) { vent = list_entry(hpos, struct net_bridge_vlan, vlist); if (v->vid >= vent->vid) break; } list_add_rcu(&v->vlist, hpos); } static void __vlan_del_list(struct net_bridge_vlan *v) { list_del_rcu(&v->vlist); } static int __vlan_vid_del(struct net_device *dev, struct net_bridge *br, const struct net_bridge_vlan *v) { int err; /* Try switchdev op first. In case it is not supported, fallback to * 8021q del. */ err = br_switchdev_port_vlan_del(dev, v->vid); if (!(v->priv_flags & BR_VLFLAG_ADDED_BY_SWITCHDEV)) vlan_vid_del(dev, br->vlan_proto, v->vid); return err == -EOPNOTSUPP ? 0 : err; } /* Returns a master vlan, if it didn't exist it gets created. In all cases * a reference is taken to the master vlan before returning. */ static struct net_bridge_vlan * br_vlan_get_master(struct net_bridge *br, u16 vid, struct netlink_ext_ack *extack) { struct net_bridge_vlan_group *vg; struct net_bridge_vlan *masterv; vg = br_vlan_group(br); masterv = br_vlan_find(vg, vid); if (!masterv) { bool changed; /* missing global ctx, create it now */ if (br_vlan_add(br, vid, 0, &changed, extack)) return NULL; masterv = br_vlan_find(vg, vid); if (WARN_ON(!masterv)) return NULL; refcount_set(&masterv->refcnt, 1); return masterv; } refcount_inc(&masterv->refcnt); return masterv; } static void br_master_vlan_rcu_free(struct rcu_head *rcu) { struct net_bridge_vlan *v; v = container_of(rcu, struct net_bridge_vlan, rcu); WARN_ON(!br_vlan_is_master(v)); free_percpu(v->stats); v->stats = NULL; kfree(v); } static void br_vlan_put_master(struct net_bridge_vlan *masterv) { struct net_bridge_vlan_group *vg; if (!br_vlan_is_master(masterv)) return; vg = br_vlan_group(masterv->br); if (refcount_dec_and_test(&masterv->refcnt)) { rhashtable_remove_fast(&vg->vlan_hash, &masterv->vnode, br_vlan_rht_params); __vlan_del_list(masterv); br_multicast_toggle_one_vlan(masterv, false); br_multicast_ctx_deinit(&masterv->br_mcast_ctx); call_rcu(&masterv->rcu, br_master_vlan_rcu_free); } } static void nbp_vlan_rcu_free(struct rcu_head *rcu) { struct net_bridge_vlan *v; v = container_of(rcu, struct net_bridge_vlan, rcu); WARN_ON(br_vlan_is_master(v)); /* if we had per-port stats configured then free them here */ if (v->priv_flags & BR_VLFLAG_PER_PORT_STATS) free_percpu(v->stats); v->stats = NULL; kfree(v); } static void br_vlan_init_state(struct net_bridge_vlan *v) { struct net_bridge *br; if (br_vlan_is_master(v)) br = v->br; else br = v->port->br; if (br_opt_get(br, BROPT_MST_ENABLED)) { br_mst_vlan_init_state(v); return; } v->state = BR_STATE_FORWARDING; v->msti = 0; } /* This is the shared VLAN add function which works for both ports and bridge * devices. There are four possible calls to this function in terms of the * vlan entry type: * 1. vlan is being added on a port (no master flags, global entry exists) * 2. vlan is being added on a bridge (both master and brentry flags) * 3. vlan is being added on a port, but a global entry didn't exist which * is being created right now (master flag set, brentry flag unset), the * global entry is used for global per-vlan features, but not for filtering * 4. same as 3 but with both master and brentry flags set so the entry * will be used for filtering in both the port and the bridge */ static int __vlan_add(struct net_bridge_vlan *v, u16 flags, struct netlink_ext_ack *extack) { struct net_bridge_vlan *masterv = NULL; struct net_bridge_port *p = NULL; struct net_bridge_vlan_group *vg; struct net_device *dev; struct net_bridge *br; int err; if (br_vlan_is_master(v)) { br = v->br; dev = br->dev; vg = br_vlan_group(br); } else { p = v->port; br = p->br; dev = p->dev; vg = nbp_vlan_group(p); } if (p) { /* Add VLAN to the device filter if it is supported. * This ensures tagged traffic enters the bridge when * promiscuous mode is disabled by br_manage_promisc(). */ err = __vlan_vid_add(dev, br, v, flags, extack); if (err) goto out; /* need to work on the master vlan too */ if (flags & BRIDGE_VLAN_INFO_MASTER) { bool changed; err = br_vlan_add(br, v->vid, flags | BRIDGE_VLAN_INFO_BRENTRY, &changed, extack); if (err) goto out_filt; if (changed) br_vlan_notify(br, NULL, v->vid, 0, RTM_NEWVLAN); } masterv = br_vlan_get_master(br, v->vid, extack); if (!masterv) { err = -ENOMEM; goto out_filt; } v->brvlan = masterv; if (br_opt_get(br, BROPT_VLAN_STATS_PER_PORT)) { v->stats = netdev_alloc_pcpu_stats(struct pcpu_sw_netstats); if (!v->stats) { err = -ENOMEM; goto out_filt; } v->priv_flags |= BR_VLFLAG_PER_PORT_STATS; } else { v->stats = masterv->stats; } br_multicast_port_ctx_init(p, v, &v->port_mcast_ctx); } else { if (br_vlan_should_use(v)) { err = br_switchdev_port_vlan_add(dev, v->vid, flags, false, extack); if (err && err != -EOPNOTSUPP) goto out; } br_multicast_ctx_init(br, v, &v->br_mcast_ctx); v->priv_flags |= BR_VLFLAG_GLOBAL_MCAST_ENABLED; } /* Add the dev mac and count the vlan only if it's usable */ if (br_vlan_should_use(v)) { err = br_fdb_add_local(br, p, dev->dev_addr, v->vid); if (err) { br_err(br, "failed insert local address into bridge forwarding table\n"); goto out_filt; } vg->num_vlans++; } /* set the state before publishing */ br_vlan_init_state(v); err = rhashtable_lookup_insert_fast(&vg->vlan_hash, &v->vnode, br_vlan_rht_params); if (err) goto out_fdb_insert; __vlan_add_list(v); __vlan_flags_commit(v, flags); br_multicast_toggle_one_vlan(v, true); if (p) nbp_vlan_set_vlan_dev_state(p, v->vid); out: return err; out_fdb_insert: if (br_vlan_should_use(v)) { br_fdb_find_delete_local(br, p, dev->dev_addr, v->vid); vg->num_vlans--; } out_filt: if (p) { __vlan_vid_del(dev, br, v); if (masterv) { if (v->stats && masterv->stats != v->stats) free_percpu(v->stats); v->stats = NULL; br_vlan_put_master(masterv); v->brvlan = NULL; } } else { br_switchdev_port_vlan_del(dev, v->vid); } goto out; } static int __vlan_del(struct net_bridge_vlan *v) { struct net_bridge_vlan *masterv = v; struct net_bridge_vlan_group *vg; struct net_bridge_port *p = NULL; int err = 0; if (br_vlan_is_master(v)) { vg = br_vlan_group(v->br); } else { p = v->port; vg = nbp_vlan_group(v->port); masterv = v->brvlan; } __vlan_delete_pvid(vg, v->vid); if (p) { err = __vlan_vid_del(p->dev, p->br, v); if (err) goto out; } else { err = br_switchdev_port_vlan_del(v->br->dev, v->vid); if (err && err != -EOPNOTSUPP) goto out; err = 0; } if (br_vlan_should_use(v)) { v->flags &= ~BRIDGE_VLAN_INFO_BRENTRY; vg->num_vlans--; } if (masterv != v) { vlan_tunnel_info_del(vg, v); rhashtable_remove_fast(&vg->vlan_hash, &v->vnode, br_vlan_rht_params); __vlan_del_list(v); nbp_vlan_set_vlan_dev_state(p, v->vid); br_multicast_toggle_one_vlan(v, false); br_multicast_port_ctx_deinit(&v->port_mcast_ctx); call_rcu(&v->rcu, nbp_vlan_rcu_free); } br_vlan_put_master(masterv); out: return err; } static void __vlan_group_free(struct net_bridge_vlan_group *vg) { WARN_ON(!list_empty(&vg->vlan_list)); rhashtable_destroy(&vg->vlan_hash); vlan_tunnel_deinit(vg); kfree(vg); } static void __vlan_flush(const struct net_bridge *br, const struct net_bridge_port *p, struct net_bridge_vlan_group *vg) { struct net_bridge_vlan *vlan, *tmp; u16 v_start = 0, v_end = 0; int err; __vlan_delete_pvid(vg, vg->pvid); list_for_each_entry_safe(vlan, tmp, &vg->vlan_list, vlist) { /* take care of disjoint ranges */ if (!v_start) { v_start = vlan->vid; } else if (vlan->vid - v_end != 1) { /* found range end, notify and start next one */ br_vlan_notify(br, p, v_start, v_end, RTM_DELVLAN); v_start = vlan->vid; } v_end = vlan->vid; err = __vlan_del(vlan); if (err) { br_err(br, "port %u(%s) failed to delete vlan %d: %pe\n", (unsigned int) p->port_no, p->dev->name, vlan->vid, ERR_PTR(err)); } } /* notify about the last/whole vlan range */ if (v_start) br_vlan_notify(br, p, v_start, v_end, RTM_DELVLAN); } struct sk_buff *br_handle_vlan(struct net_bridge *br, const struct net_bridge_port *p, struct net_bridge_vlan_group *vg, struct sk_buff *skb) { struct pcpu_sw_netstats *stats; struct net_bridge_vlan *v; u16 vid; /* If this packet was not filtered at input, let it pass */ if (!BR_INPUT_SKB_CB(skb)->vlan_filtered) goto out; /* At this point, we know that the frame was filtered and contains * a valid vlan id. If the vlan id has untagged flag set, * send untagged; otherwise, send tagged. */ br_vlan_get_tag(skb, &vid); v = br_vlan_find(vg, vid); /* Vlan entry must be configured at this point. The * only exception is the bridge is set in promisc mode and the * packet is destined for the bridge device. In this case * pass the packet as is. */ if (!v || !br_vlan_should_use(v)) { if ((br->dev->flags & IFF_PROMISC) && skb->dev == br->dev) { goto out; } else { kfree_skb(skb); return NULL; } } if (br_opt_get(br, BROPT_VLAN_STATS_ENABLED)) { stats = this_cpu_ptr(v->stats); u64_stats_update_begin(&stats->syncp); u64_stats_add(&stats->tx_bytes, skb->len); u64_stats_inc(&stats->tx_packets); u64_stats_update_end(&stats->syncp); } /* If the skb will be sent using forwarding offload, the assumption is * that the switchdev will inject the packet into hardware together * with the bridge VLAN, so that it can be forwarded according to that * VLAN. The switchdev should deal with popping the VLAN header in * hardware on each egress port as appropriate. So only strip the VLAN * header if forwarding offload is not being used. */ if (v->flags & BRIDGE_VLAN_INFO_UNTAGGED && !br_switchdev_frame_uses_tx_fwd_offload(skb)) __vlan_hwaccel_clear_tag(skb); if (p && (p->flags & BR_VLAN_TUNNEL) && br_handle_egress_vlan_tunnel(skb, v)) { kfree_skb(skb); return NULL; } out: return skb; } /* Called under RCU */ static bool __allowed_ingress(const struct net_bridge *br, struct net_bridge_vlan_group *vg, struct sk_buff *skb, u16 *vid, u8 *state, struct net_bridge_vlan **vlan) { struct pcpu_sw_netstats *stats; struct net_bridge_vlan *v; bool tagged; BR_INPUT_SKB_CB(skb)->vlan_filtered = true; /* If vlan tx offload is disabled on bridge device and frame was * sent from vlan device on the bridge device, it does not have * HW accelerated vlan tag. */ if (unlikely(!skb_vlan_tag_present(skb) && skb->protocol == br->vlan_proto)) { skb = skb_vlan_untag(skb); if (unlikely(!skb)) return false; } if (!br_vlan_get_tag(skb, vid)) { /* Tagged frame */ if (skb->vlan_proto != br->vlan_proto) { /* Protocol-mismatch, empty out vlan_tci for new tag */ skb_push(skb, ETH_HLEN); skb = vlan_insert_tag_set_proto(skb, skb->vlan_proto, skb_vlan_tag_get(skb)); if (unlikely(!skb)) return false; skb_pull(skb, ETH_HLEN); skb_reset_mac_len(skb); *vid = 0; tagged = false; } else { tagged = true; } } else { /* Untagged frame */ tagged = false; } if (!*vid) { u16 pvid = br_get_pvid(vg); /* Frame had a tag with VID 0 or did not have a tag. * See if pvid is set on this port. That tells us which * vlan untagged or priority-tagged traffic belongs to. */ if (!pvid) goto drop; /* PVID is set on this port. Any untagged or priority-tagged * ingress frame is considered to belong to this vlan. */ *vid = pvid; if (likely(!tagged)) /* Untagged Frame. */ __vlan_hwaccel_put_tag(skb, br->vlan_proto, pvid); else /* Priority-tagged Frame. * At this point, we know that skb->vlan_tci VID * field was 0. * We update only VID field and preserve PCP field. */ skb->vlan_tci |= pvid; /* if snooping and stats are disabled we can avoid the lookup */ if (!br_opt_get(br, BROPT_MCAST_VLAN_SNOOPING_ENABLED) && !br_opt_get(br, BROPT_VLAN_STATS_ENABLED)) { if (*state == BR_STATE_FORWARDING) { *state = br_vlan_get_pvid_state(vg); if (!br_vlan_state_allowed(*state, true)) goto drop; } return true; } } v = br_vlan_find(vg, *vid); if (!v || !br_vlan_should_use(v)) goto drop; if (*state == BR_STATE_FORWARDING) { *state = br_vlan_get_state(v); if (!br_vlan_state_allowed(*state, true)) goto drop; } if (br_opt_get(br, BROPT_VLAN_STATS_ENABLED)) { stats = this_cpu_ptr(v->stats); u64_stats_update_begin(&stats->syncp); u64_stats_add(&stats->rx_bytes, skb->len); u64_stats_inc(&stats->rx_packets); u64_stats_update_end(&stats->syncp); } *vlan = v; return true; drop: kfree_skb(skb); return false; } bool br_allowed_ingress(const struct net_bridge *br, struct net_bridge_vlan_group *vg, struct sk_buff *skb, u16 *vid, u8 *state, struct net_bridge_vlan **vlan) { /* If VLAN filtering is disabled on the bridge, all packets are * permitted. */ *vlan = NULL; if (!br_opt_get(br, BROPT_VLAN_ENABLED)) { BR_INPUT_SKB_CB(skb)->vlan_filtered = false; return true; } return __allowed_ingress(br, vg, skb, vid, state, vlan); } /* Called under RCU. */ bool br_allowed_egress(struct net_bridge_vlan_group *vg, const struct sk_buff *skb) { const struct net_bridge_vlan *v; u16 vid; /* If this packet was not filtered at input, let it pass */ if (!BR_INPUT_SKB_CB(skb)->vlan_filtered) return true; br_vlan_get_tag(skb, &vid); v = br_vlan_find(vg, vid); if (v && br_vlan_should_use(v) && br_vlan_state_allowed(br_vlan_get_state(v), false)) return true; return false; } /* Called under RCU */ bool br_should_learn(struct net_bridge_port *p, struct sk_buff *skb, u16 *vid) { struct net_bridge_vlan_group *vg; struct net_bridge *br = p->br; struct net_bridge_vlan *v; /* If filtering was disabled at input, let it pass. */ if (!br_opt_get(br, BROPT_VLAN_ENABLED)) return true; vg = nbp_vlan_group_rcu(p); if (!vg || !vg->num_vlans) return false; if (!br_vlan_get_tag(skb, vid) && skb->vlan_proto != br->vlan_proto) *vid = 0; if (!*vid) { *vid = br_get_pvid(vg); if (!*vid || !br_vlan_state_allowed(br_vlan_get_pvid_state(vg), true)) return false; return true; } v = br_vlan_find(vg, *vid); if (v && br_vlan_state_allowed(br_vlan_get_state(v), true)) return true; return false; } static int br_vlan_add_existing(struct net_bridge *br, struct net_bridge_vlan_group *vg, struct net_bridge_vlan *vlan, u16 flags, bool *changed, struct netlink_ext_ack *extack) { bool would_change = __vlan_flags_would_change(vlan, flags); bool becomes_brentry = false; int err; if (!br_vlan_is_brentry(vlan)) { /* Trying to change flags of non-existent bridge vlan */ if (!(flags & BRIDGE_VLAN_INFO_BRENTRY)) return -EINVAL; becomes_brentry = true; } /* Master VLANs that aren't brentries weren't notified before, * time to notify them now. */ if (becomes_brentry || would_change) { err = br_switchdev_port_vlan_add(br->dev, vlan->vid, flags, would_change, extack); if (err && err != -EOPNOTSUPP) return err; } if (becomes_brentry) { /* It was only kept for port vlans, now make it real */ err = br_fdb_add_local(br, NULL, br->dev->dev_addr, vlan->vid); if (err) { br_err(br, "failed to insert local address into bridge forwarding table\n"); goto err_fdb_insert; } refcount_inc(&vlan->refcnt); vlan->flags |= BRIDGE_VLAN_INFO_BRENTRY; vg->num_vlans++; *changed = true; br_multicast_toggle_one_vlan(vlan, true); } __vlan_flags_commit(vlan, flags); if (would_change) *changed = true; return 0; err_fdb_insert: br_switchdev_port_vlan_del(br->dev, vlan->vid); return err; } /* Must be protected by RTNL. * Must be called with vid in range from 1 to 4094 inclusive. * changed must be true only if the vlan was created or updated */ int br_vlan_add(struct net_bridge *br, u16 vid, u16 flags, bool *changed, struct netlink_ext_ack *extack) { struct net_bridge_vlan_group *vg; struct net_bridge_vlan *vlan; int ret; ASSERT_RTNL(); *changed = false; vg = br_vlan_group(br); vlan = br_vlan_find(vg, vid); if (vlan) return br_vlan_add_existing(br, vg, vlan, flags, changed, extack); vlan = kzalloc(sizeof(*vlan), GFP_KERNEL); if (!vlan) return -ENOMEM; vlan->stats = netdev_alloc_pcpu_stats(struct pcpu_sw_netstats); if (!vlan->stats) { kfree(vlan); return -ENOMEM; } vlan->vid = vid; vlan->flags = flags | BRIDGE_VLAN_INFO_MASTER; vlan->flags &= ~BRIDGE_VLAN_INFO_PVID; vlan->br = br; if (flags & BRIDGE_VLAN_INFO_BRENTRY) refcount_set(&vlan->refcnt, 1); ret = __vlan_add(vlan, flags, extack); if (ret) { free_percpu(vlan->stats); kfree(vlan); } else { *changed = true; } return ret; } /* Must be protected by RTNL. * Must be called with vid in range from 1 to 4094 inclusive. */ int br_vlan_delete(struct net_bridge *br, u16 vid) { struct net_bridge_vlan_group *vg; struct net_bridge_vlan *v; ASSERT_RTNL(); vg = br_vlan_group(br); v = br_vlan_find(vg, vid); if (!v || !br_vlan_is_brentry(v)) return -ENOENT; br_fdb_find_delete_local(br, NULL, br->dev->dev_addr, vid); br_fdb_delete_by_port(br, NULL, vid, 0); vlan_tunnel_info_del(vg, v); return __vlan_del(v); } void br_vlan_flush(struct net_bridge *br) { struct net_bridge_vlan_group *vg; ASSERT_RTNL(); vg = br_vlan_group(br); __vlan_flush(br, NULL, vg); RCU_INIT_POINTER(br->vlgrp, NULL); synchronize_net(); __vlan_group_free(vg); } struct net_bridge_vlan *br_vlan_find(struct net_bridge_vlan_group *vg, u16 vid) { if (!vg) return NULL; return br_vlan_lookup(&vg->vlan_hash, vid); } /* Must be protected by RTNL. */ static void recalculate_group_addr(struct net_bridge *br) { if (br_opt_get(br, BROPT_GROUP_ADDR_SET)) return; spin_lock_bh(&br->lock); if (!br_opt_get(br, BROPT_VLAN_ENABLED) || br->vlan_proto == htons(ETH_P_8021Q)) { /* Bridge Group Address */ br->group_addr[5] = 0x00; } else { /* vlan_enabled && ETH_P_8021AD */ /* Provider Bridge Group Address */ br->group_addr[5] = 0x08; } spin_unlock_bh(&br->lock); } /* Must be protected by RTNL. */ void br_recalculate_fwd_mask(struct net_bridge *br) { if (!br_opt_get(br, BROPT_VLAN_ENABLED) || br->vlan_proto == htons(ETH_P_8021Q)) br->group_fwd_mask_required = BR_GROUPFWD_DEFAULT; else /* vlan_enabled && ETH_P_8021AD */ br->group_fwd_mask_required = BR_GROUPFWD_8021AD & ~(1u << br->group_addr[5]); } int br_vlan_filter_toggle(struct net_bridge *br, unsigned long val, struct netlink_ext_ack *extack) { struct switchdev_attr attr = { .orig_dev = br->dev, .id = SWITCHDEV_ATTR_ID_BRIDGE_VLAN_FILTERING, .flags = SWITCHDEV_F_SKIP_EOPNOTSUPP, .u.vlan_filtering = val, }; int err; if (br_opt_get(br, BROPT_VLAN_ENABLED) == !!val) return 0; br_opt_toggle(br, BROPT_VLAN_ENABLED, !!val); err = switchdev_port_attr_set(br->dev, &attr, extack); if (err && err != -EOPNOTSUPP) { br_opt_toggle(br, BROPT_VLAN_ENABLED, !val); return err; } br_manage_promisc(br); recalculate_group_addr(br); br_recalculate_fwd_mask(br); if (!val && br_opt_get(br, BROPT_MCAST_VLAN_SNOOPING_ENABLED)) { br_info(br, "vlan filtering disabled, automatically disabling multicast vlan snooping\n"); br_multicast_toggle_vlan_snooping(br, false, NULL); } return 0; } bool br_vlan_enabled(const struct net_device *dev) { struct net_bridge *br = netdev_priv(dev); return br_opt_get(br, BROPT_VLAN_ENABLED); } EXPORT_SYMBOL_GPL(br_vlan_enabled); int br_vlan_get_proto(const struct net_device *dev, u16 *p_proto) { struct net_bridge *br = netdev_priv(dev); *p_proto = ntohs(br->vlan_proto); return 0; } EXPORT_SYMBOL_GPL(br_vlan_get_proto); int __br_vlan_set_proto(struct net_bridge *br, __be16 proto, struct netlink_ext_ack *extack) { struct switchdev_attr attr = { .orig_dev = br->dev, .id = SWITCHDEV_ATTR_ID_BRIDGE_VLAN_PROTOCOL, .flags = SWITCHDEV_F_SKIP_EOPNOTSUPP, .u.vlan_protocol = ntohs(proto), }; int err = 0; struct net_bridge_port *p; struct net_bridge_vlan *vlan; struct net_bridge_vlan_group *vg; __be16 oldproto = br->vlan_proto; if (br->vlan_proto == proto) return 0; err = switchdev_port_attr_set(br->dev, &attr, extack); if (err && err != -EOPNOTSUPP) return err; /* Add VLANs for the new proto to the device filter. */ list_for_each_entry(p, &br->port_list, list) { vg = nbp_vlan_group(p); list_for_each_entry(vlan, &vg->vlan_list, vlist) { if (vlan->priv_flags & BR_VLFLAG_ADDED_BY_SWITCHDEV) continue; err = vlan_vid_add(p->dev, proto, vlan->vid); if (err) goto err_filt; } } br->vlan_proto = proto; recalculate_group_addr(br); br_recalculate_fwd_mask(br); /* Delete VLANs for the old proto from the device filter. */ list_for_each_entry(p, &br->port_list, list) { vg = nbp_vlan_group(p); list_for_each_entry(vlan, &vg->vlan_list, vlist) { if (vlan->priv_flags & BR_VLFLAG_ADDED_BY_SWITCHDEV) continue; vlan_vid_del(p->dev, oldproto, vlan->vid); } } return 0; err_filt: attr.u.vlan_protocol = ntohs(oldproto); switchdev_port_attr_set(br->dev, &attr, NULL); list_for_each_entry_continue_reverse(vlan, &vg->vlan_list, vlist) { if (vlan->priv_flags & BR_VLFLAG_ADDED_BY_SWITCHDEV) continue; vlan_vid_del(p->dev, proto, vlan->vid); } list_for_each_entry_continue_reverse(p, &br->port_list, list) { vg = nbp_vlan_group(p); list_for_each_entry(vlan, &vg->vlan_list, vlist) { if (vlan->priv_flags & BR_VLFLAG_ADDED_BY_SWITCHDEV) continue; vlan_vid_del(p->dev, proto, vlan->vid); } } return err; } int br_vlan_set_proto(struct net_bridge *br, unsigned long val, struct netlink_ext_ack *extack) { if (!eth_type_vlan(htons(val))) return -EPROTONOSUPPORT; return __br_vlan_set_proto(br, htons(val), extack); } int br_vlan_set_stats(struct net_bridge *br, unsigned long val) { switch (val) { case 0: case 1: br_opt_toggle(br, BROPT_VLAN_STATS_ENABLED, !!val); break; default: return -EINVAL; } return 0; } int br_vlan_set_stats_per_port(struct net_bridge *br, unsigned long val) { struct net_bridge_port *p; /* allow to change the option if there are no port vlans configured */ list_for_each_entry(p, &br->port_list, list) { struct net_bridge_vlan_group *vg = nbp_vlan_group(p); if (vg->num_vlans) return -EBUSY; } switch (val) { case 0: case 1: br_opt_toggle(br, BROPT_VLAN_STATS_PER_PORT, !!val); break; default: return -EINVAL; } return 0; } static bool vlan_default_pvid(struct net_bridge_vlan_group *vg, u16 vid) { struct net_bridge_vlan *v; if (vid != vg->pvid) return false; v = br_vlan_lookup(&vg->vlan_hash, vid); if (v && br_vlan_should_use(v) && (v->flags & BRIDGE_VLAN_INFO_UNTAGGED)) return true; return false; } static void br_vlan_disable_default_pvid(struct net_bridge *br) { struct net_bridge_port *p; u16 pvid = br->default_pvid; /* Disable default_pvid on all ports where it is still * configured. */ if (vlan_default_pvid(br_vlan_group(br), pvid)) { if (!br_vlan_delete(br, pvid)) br_vlan_notify(br, NULL, pvid, 0, RTM_DELVLAN); } list_for_each_entry(p, &br->port_list, list) { if (vlan_default_pvid(nbp_vlan_group(p), pvid) && !nbp_vlan_delete(p, pvid)) br_vlan_notify(br, p, pvid, 0, RTM_DELVLAN); } br->default_pvid = 0; } int __br_vlan_set_default_pvid(struct net_bridge *br, u16 pvid, struct netlink_ext_ack *extack) { const struct net_bridge_vlan *pvent; struct net_bridge_vlan_group *vg; struct net_bridge_port *p; unsigned long *changed; bool vlchange; u16 old_pvid; int err = 0; if (!pvid) { br_vlan_disable_default_pvid(br); return 0; } changed = bitmap_zalloc(BR_MAX_PORTS, GFP_KERNEL); if (!changed) return -ENOMEM; old_pvid = br->default_pvid; /* Update default_pvid config only if we do not conflict with * user configuration. */ vg = br_vlan_group(br); pvent = br_vlan_find(vg, pvid); if ((!old_pvid || vlan_default_pvid(vg, old_pvid)) && (!pvent || !br_vlan_should_use(pvent))) { err = br_vlan_add(br, pvid, BRIDGE_VLAN_INFO_PVID | BRIDGE_VLAN_INFO_UNTAGGED | BRIDGE_VLAN_INFO_BRENTRY, &vlchange, extack); if (err) goto out; if (br_vlan_delete(br, old_pvid)) br_vlan_notify(br, NULL, old_pvid, 0, RTM_DELVLAN); br_vlan_notify(br, NULL, pvid, 0, RTM_NEWVLAN); __set_bit(0, changed); } list_for_each_entry(p, &br->port_list, list) { /* Update default_pvid config only if we do not conflict with * user configuration. */ vg = nbp_vlan_group(p); if ((old_pvid && !vlan_default_pvid(vg, old_pvid)) || br_vlan_find(vg, pvid)) continue; err = nbp_vlan_add(p, pvid, BRIDGE_VLAN_INFO_PVID | BRIDGE_VLAN_INFO_UNTAGGED, &vlchange, extack); if (err) goto err_port; if (nbp_vlan_delete(p, old_pvid)) br_vlan_notify(br, p, old_pvid, 0, RTM_DELVLAN); br_vlan_notify(p->br, p, pvid, 0, RTM_NEWVLAN); __set_bit(p->port_no, changed); } br->default_pvid = pvid; out: bitmap_free(changed); return err; err_port: list_for_each_entry_continue_reverse(p, &br->port_list, list) { if (!test_bit(p->port_no, changed)) continue; if (old_pvid) { nbp_vlan_add(p, old_pvid, BRIDGE_VLAN_INFO_PVID | BRIDGE_VLAN_INFO_UNTAGGED, &vlchange, NULL); br_vlan_notify(p->br, p, old_pvid, 0, RTM_NEWVLAN); } nbp_vlan_delete(p, pvid); br_vlan_notify(br, p, pvid, 0, RTM_DELVLAN); } if (test_bit(0, changed)) { if (old_pvid) { br_vlan_add(br, old_pvid, BRIDGE_VLAN_INFO_PVID | BRIDGE_VLAN_INFO_UNTAGGED | BRIDGE_VLAN_INFO_BRENTRY, &vlchange, NULL); br_vlan_notify(br, NULL, old_pvid, 0, RTM_NEWVLAN); } br_vlan_delete(br, pvid); br_vlan_notify(br, NULL, pvid, 0, RTM_DELVLAN); } goto out; } int br_vlan_set_default_pvid(struct net_bridge *br, unsigned long val, struct netlink_ext_ack *extack) { u16 pvid = val; int err = 0; if (val >= VLAN_VID_MASK) return -EINVAL; if (pvid == br->default_pvid) goto out; /* Only allow default pvid change when filtering is disabled */ if (br_opt_get(br, BROPT_VLAN_ENABLED)) { pr_info_once("Please disable vlan filtering to change default_pvid\n"); err = -EPERM; goto out; } err = __br_vlan_set_default_pvid(br, pvid, extack); out: return err; } int br_vlan_init(struct net_bridge *br) { struct net_bridge_vlan_group *vg; int ret = -ENOMEM; vg = kzalloc(sizeof(*vg), GFP_KERNEL); if (!vg) goto out; ret = rhashtable_init(&vg->vlan_hash, &br_vlan_rht_params); if (ret) goto err_rhtbl; ret = vlan_tunnel_init(vg); if (ret) goto err_tunnel_init; INIT_LIST_HEAD(&vg->vlan_list); br->vlan_proto = htons(ETH_P_8021Q); br->default_pvid = 1; rcu_assign_pointer(br->vlgrp, vg); out: return ret; err_tunnel_init: rhashtable_destroy(&vg->vlan_hash); err_rhtbl: kfree(vg); goto out; } int nbp_vlan_init(struct net_bridge_port *p, struct netlink_ext_ack *extack) { struct switchdev_attr attr = { .orig_dev = p->br->dev, .id = SWITCHDEV_ATTR_ID_BRIDGE_VLAN_FILTERING, .flags = SWITCHDEV_F_SKIP_EOPNOTSUPP, .u.vlan_filtering = br_opt_get(p->br, BROPT_VLAN_ENABLED), }; struct net_bridge_vlan_group *vg; int ret = -ENOMEM; vg = kzalloc(sizeof(struct net_bridge_vlan_group), GFP_KERNEL); if (!vg) goto out; ret = switchdev_port_attr_set(p->dev, &attr, extack); if (ret && ret != -EOPNOTSUPP) goto err_vlan_enabled; ret = rhashtable_init(&vg->vlan_hash, &br_vlan_rht_params); if (ret) goto err_rhtbl; ret = vlan_tunnel_init(vg); if (ret) goto err_tunnel_init; INIT_LIST_HEAD(&vg->vlan_list); rcu_assign_pointer(p->vlgrp, vg); if (p->br->default_pvid) { bool changed; ret = nbp_vlan_add(p, p->br->default_pvid, BRIDGE_VLAN_INFO_PVID | BRIDGE_VLAN_INFO_UNTAGGED, &changed, extack); if (ret) goto err_vlan_add; br_vlan_notify(p->br, p, p->br->default_pvid, 0, RTM_NEWVLAN); } out: return ret; err_vlan_add: RCU_INIT_POINTER(p->vlgrp, NULL); synchronize_rcu(); vlan_tunnel_deinit(vg); err_tunnel_init: rhashtable_destroy(&vg->vlan_hash); err_rhtbl: err_vlan_enabled: kfree(vg); goto out; } /* Must be protected by RTNL. * Must be called with vid in range from 1 to 4094 inclusive. * changed must be true only if the vlan was created or updated */ int nbp_vlan_add(struct net_bridge_port *port, u16 vid, u16 flags, bool *changed, struct netlink_ext_ack *extack) { struct net_bridge_vlan *vlan; int ret; ASSERT_RTNL(); *changed = false; vlan = br_vlan_find(nbp_vlan_group(port), vid); if (vlan) { bool would_change = __vlan_flags_would_change(vlan, flags); if (would_change) { /* Pass the flags to the hardware bridge */ ret = br_switchdev_port_vlan_add(port->dev, vid, flags, true, extack); if (ret && ret != -EOPNOTSUPP) return ret; } __vlan_flags_commit(vlan, flags); *changed = would_change; return 0; } vlan = kzalloc(sizeof(*vlan), GFP_KERNEL); if (!vlan) return -ENOMEM; vlan->vid = vid; vlan->port = port; ret = __vlan_add(vlan, flags, extack); if (ret) kfree(vlan); else *changed = true; return ret; } /* Must be protected by RTNL. * Must be called with vid in range from 1 to 4094 inclusive. */ int nbp_vlan_delete(struct net_bridge_port *port, u16 vid) { struct net_bridge_vlan *v; ASSERT_RTNL(); v = br_vlan_find(nbp_vlan_group(port), vid); if (!v) return -ENOENT; br_fdb_find_delete_local(port->br, port, port->dev->dev_addr, vid); br_fdb_delete_by_port(port->br, port, vid, 0); return __vlan_del(v); } void nbp_vlan_flush(struct net_bridge_port *port) { struct net_bridge_vlan_group *vg; ASSERT_RTNL(); vg = nbp_vlan_group(port); __vlan_flush(port->br, port, vg); RCU_INIT_POINTER(port->vlgrp, NULL); synchronize_net(); __vlan_group_free(vg); } void br_vlan_get_stats(const struct net_bridge_vlan *v, struct pcpu_sw_netstats *stats) { int i; memset(stats, 0, sizeof(*stats)); for_each_possible_cpu(i) { u64 rxpackets, rxbytes, txpackets, txbytes; struct pcpu_sw_netstats *cpu_stats; unsigned int start; cpu_stats = per_cpu_ptr(v->stats, i); do { start = u64_stats_fetch_begin(&cpu_stats->syncp); rxpackets = u64_stats_read(&cpu_stats->rx_packets); rxbytes = u64_stats_read(&cpu_stats->rx_bytes); txbytes = u64_stats_read(&cpu_stats->tx_bytes); txpackets = u64_stats_read(&cpu_stats->tx_packets); } while (u64_stats_fetch_retry(&cpu_stats->syncp, start)); u64_stats_add(&stats->rx_packets, rxpackets); u64_stats_add(&stats->rx_bytes, rxbytes); u64_stats_add(&stats->tx_bytes, txbytes); u64_stats_add(&stats->tx_packets, txpackets); } } int br_vlan_get_pvid(const struct net_device *dev, u16 *p_pvid) { struct net_bridge_vlan_group *vg; struct net_bridge_port *p; ASSERT_RTNL(); p = br_port_get_check_rtnl(dev); if (p) vg = nbp_vlan_group(p); else if (netif_is_bridge_master(dev)) vg = br_vlan_group(netdev_priv(dev)); else return -EINVAL; *p_pvid = br_get_pvid(vg); return 0; } EXPORT_SYMBOL_GPL(br_vlan_get_pvid); int br_vlan_get_pvid_rcu(const struct net_device *dev, u16 *p_pvid) { struct net_bridge_vlan_group *vg; struct net_bridge_port *p; p = br_port_get_check_rcu(dev); if (p) vg = nbp_vlan_group_rcu(p); else if (netif_is_bridge_master(dev)) vg = br_vlan_group_rcu(netdev_priv(dev)); else return -EINVAL; *p_pvid = br_get_pvid(vg); return 0; } EXPORT_SYMBOL_GPL(br_vlan_get_pvid_rcu); void br_vlan_fill_forward_path_pvid(struct net_bridge *br, struct net_device_path_ctx *ctx, struct net_device_path *path) { struct net_bridge_vlan_group *vg; int idx = ctx->num_vlans - 1; u16 vid; path->bridge.vlan_mode = DEV_PATH_BR_VLAN_KEEP; if (!br_opt_get(br, BROPT_VLAN_ENABLED)) return; vg = br_vlan_group(br); if (idx >= 0 && ctx->vlan[idx].proto == br->vlan_proto) { vid = ctx->vlan[idx].id; } else { path->bridge.vlan_mode = DEV_PATH_BR_VLAN_TAG; vid = br_get_pvid(vg); } path->bridge.vlan_id = vid; path->bridge.vlan_proto = br->vlan_proto; } int br_vlan_fill_forward_path_mode(struct net_bridge *br, struct net_bridge_port *dst, struct net_device_path *path) { struct net_bridge_vlan_group *vg; struct net_bridge_vlan *v; if (!br_opt_get(br, BROPT_VLAN_ENABLED)) return 0; vg = nbp_vlan_group_rcu(dst); v = br_vlan_find(vg, path->bridge.vlan_id); if (!v || !br_vlan_should_use(v)) return -EINVAL; if (!(v->flags & BRIDGE_VLAN_INFO_UNTAGGED)) return 0; if (path->bridge.vlan_mode == DEV_PATH_BR_VLAN_TAG) path->bridge.vlan_mode = DEV_PATH_BR_VLAN_KEEP; else if (v->priv_flags & BR_VLFLAG_ADDED_BY_SWITCHDEV) path->bridge.vlan_mode = DEV_PATH_BR_VLAN_UNTAG_HW; else path->bridge.vlan_mode = DEV_PATH_BR_VLAN_UNTAG; return 0; } int br_vlan_get_info(const struct net_device *dev, u16 vid, struct bridge_vlan_info *p_vinfo) { struct net_bridge_vlan_group *vg; struct net_bridge_vlan *v; struct net_bridge_port *p; ASSERT_RTNL(); p = br_port_get_check_rtnl(dev); if (p) vg = nbp_vlan_group(p); else if (netif_is_bridge_master(dev)) vg = br_vlan_group(netdev_priv(dev)); else return -EINVAL; v = br_vlan_find(vg, vid); if (!v) return -ENOENT; p_vinfo->vid = vid; p_vinfo->flags = v->flags; if (vid == br_get_pvid(vg)) p_vinfo->flags |= BRIDGE_VLAN_INFO_PVID; return 0; } EXPORT_SYMBOL_GPL(br_vlan_get_info); int br_vlan_get_info_rcu(const struct net_device *dev, u16 vid, struct bridge_vlan_info *p_vinfo) { struct net_bridge_vlan_group *vg; struct net_bridge_vlan *v; struct net_bridge_port *p; p = br_port_get_check_rcu(dev); if (p) vg = nbp_vlan_group_rcu(p); else if (netif_is_bridge_master(dev)) vg = br_vlan_group_rcu(netdev_priv(dev)); else return -EINVAL; v = br_vlan_find(vg, vid); if (!v) return -ENOENT; p_vinfo->vid = vid; p_vinfo->flags = v->flags; if (vid == br_get_pvid(vg)) p_vinfo->flags |= BRIDGE_VLAN_INFO_PVID; return 0; } EXPORT_SYMBOL_GPL(br_vlan_get_info_rcu); static int br_vlan_is_bind_vlan_dev(const struct net_device *dev) { return is_vlan_dev(dev) && !!(vlan_dev_priv(dev)->flags & VLAN_FLAG_BRIDGE_BINDING); } static int br_vlan_is_bind_vlan_dev_fn(struct net_device *dev, __always_unused struct netdev_nested_priv *priv) { return br_vlan_is_bind_vlan_dev(dev); } static bool br_vlan_has_upper_bind_vlan_dev(struct net_device *dev) { int found; rcu_read_lock(); found = netdev_walk_all_upper_dev_rcu(dev, br_vlan_is_bind_vlan_dev_fn, NULL); rcu_read_unlock(); return !!found; } struct br_vlan_bind_walk_data { u16 vid; struct net_device *result; }; static int br_vlan_match_bind_vlan_dev_fn(struct net_device *dev, struct netdev_nested_priv *priv) { struct br_vlan_bind_walk_data *data = priv->data; int found = 0; if (br_vlan_is_bind_vlan_dev(dev) && vlan_dev_priv(dev)->vlan_id == data->vid) { data->result = dev; found = 1; } return found; } static struct net_device * br_vlan_get_upper_bind_vlan_dev(struct net_device *dev, u16 vid) { struct br_vlan_bind_walk_data data = { .vid = vid, }; struct netdev_nested_priv priv = { .data = (void *)&data, }; rcu_read_lock(); netdev_walk_all_upper_dev_rcu(dev, br_vlan_match_bind_vlan_dev_fn, &priv); rcu_read_unlock(); return data.result; } static bool br_vlan_is_dev_up(const struct net_device *dev) { return !!(dev->flags & IFF_UP) && netif_oper_up(dev); } static void br_vlan_set_vlan_dev_state(const struct net_bridge *br, struct net_device *vlan_dev) { u16 vid = vlan_dev_priv(vlan_dev)->vlan_id; struct net_bridge_vlan_group *vg; struct net_bridge_port *p; bool has_carrier = false; if (!netif_carrier_ok(br->dev)) { netif_carrier_off(vlan_dev); return; } list_for_each_entry(p, &br->port_list, list) { vg = nbp_vlan_group(p); if (br_vlan_find(vg, vid) && br_vlan_is_dev_up(p->dev)) { has_carrier = true; break; } } if (has_carrier) netif_carrier_on(vlan_dev); else netif_carrier_off(vlan_dev); } static void br_vlan_set_all_vlan_dev_state(struct net_bridge_port *p) { struct net_bridge_vlan_group *vg = nbp_vlan_group(p); struct net_bridge_vlan *vlan; struct net_device *vlan_dev; list_for_each_entry(vlan, &vg->vlan_list, vlist) { vlan_dev = br_vlan_get_upper_bind_vlan_dev(p->br->dev, vlan->vid); if (vlan_dev) { if (br_vlan_is_dev_up(p->dev)) { if (netif_carrier_ok(p->br->dev)) netif_carrier_on(vlan_dev); } else { br_vlan_set_vlan_dev_state(p->br, vlan_dev); } } } } static void br_vlan_toggle_bridge_binding(struct net_device *br_dev, bool enable) { struct net_bridge *br = netdev_priv(br_dev); if (enable) br_opt_toggle(br, BROPT_VLAN_BRIDGE_BINDING, true); else br_opt_toggle(br, BROPT_VLAN_BRIDGE_BINDING, br_vlan_has_upper_bind_vlan_dev(br_dev)); } static void br_vlan_upper_change(struct net_device *dev, struct net_device *upper_dev, bool linking) { struct net_bridge *br = netdev_priv(dev); if (!br_vlan_is_bind_vlan_dev(upper_dev)) return; br_vlan_toggle_bridge_binding(dev, linking); if (linking) br_vlan_set_vlan_dev_state(br, upper_dev); } struct br_vlan_link_state_walk_data { struct net_bridge *br; }; static int br_vlan_link_state_change_fn(struct net_device *vlan_dev, struct netdev_nested_priv *priv) { struct br_vlan_link_state_walk_data *data = priv->data; if (br_vlan_is_bind_vlan_dev(vlan_dev)) br_vlan_set_vlan_dev_state(data->br, vlan_dev); return 0; } static void br_vlan_link_state_change(struct net_device *dev, struct net_bridge *br) { struct br_vlan_link_state_walk_data data = { .br = br }; struct netdev_nested_priv priv = { .data = (void *)&data, }; rcu_read_lock(); netdev_walk_all_upper_dev_rcu(dev, br_vlan_link_state_change_fn, &priv); rcu_read_unlock(); } /* Must be protected by RTNL. */ static void nbp_vlan_set_vlan_dev_state(struct net_bridge_port *p, u16 vid) { struct net_device *vlan_dev; if (!br_opt_get(p->br, BROPT_VLAN_BRIDGE_BINDING)) return; vlan_dev = br_vlan_get_upper_bind_vlan_dev(p->br->dev, vid); if (vlan_dev) br_vlan_set_vlan_dev_state(p->br, vlan_dev); } /* Must be protected by RTNL. */ int br_vlan_bridge_event(struct net_device *dev, unsigned long event, void *ptr) { struct netdev_notifier_changeupper_info *info; struct net_bridge *br = netdev_priv(dev); int vlcmd = 0, ret = 0; bool changed = false; switch (event) { case NETDEV_REGISTER: ret = br_vlan_add(br, br->default_pvid, BRIDGE_VLAN_INFO_PVID | BRIDGE_VLAN_INFO_UNTAGGED | BRIDGE_VLAN_INFO_BRENTRY, &changed, NULL); vlcmd = RTM_NEWVLAN; break; case NETDEV_UNREGISTER: changed = !br_vlan_delete(br, br->default_pvid); vlcmd = RTM_DELVLAN; break; case NETDEV_CHANGEUPPER: info = ptr; br_vlan_upper_change(dev, info->upper_dev, info->linking); break; case NETDEV_CHANGE: case NETDEV_UP: if (!br_opt_get(br, BROPT_VLAN_BRIDGE_BINDING)) break; br_vlan_link_state_change(dev, br); break; } if (changed) br_vlan_notify(br, NULL, br->default_pvid, 0, vlcmd); return ret; } void br_vlan_vlan_upper_event(struct net_device *br_dev, struct net_device *vlan_dev, unsigned long event) { struct vlan_dev_priv *vlan = vlan_dev_priv(vlan_dev); struct net_bridge *br = netdev_priv(br_dev); bool bridge_binding; switch (event) { case NETDEV_CHANGE: case NETDEV_UP: break; default: return; } bridge_binding = vlan->flags & VLAN_FLAG_BRIDGE_BINDING; br_vlan_toggle_bridge_binding(br_dev, bridge_binding); if (bridge_binding) br_vlan_set_vlan_dev_state(br, vlan_dev); else if (!bridge_binding && netif_carrier_ok(br_dev)) netif_carrier_on(vlan_dev); } /* Must be protected by RTNL. */ void br_vlan_port_event(struct net_bridge_port *p, unsigned long event) { if (!br_opt_get(p->br, BROPT_VLAN_BRIDGE_BINDING)) return; switch (event) { case NETDEV_CHANGE: case NETDEV_DOWN: case NETDEV_UP: br_vlan_set_all_vlan_dev_state(p); break; } } static bool br_vlan_stats_fill(struct sk_buff *skb, const struct net_bridge_vlan *v) { struct pcpu_sw_netstats stats; struct nlattr *nest; nest = nla_nest_start(skb, BRIDGE_VLANDB_ENTRY_STATS); if (!nest) return false; br_vlan_get_stats(v, &stats); if (nla_put_u64_64bit(skb, BRIDGE_VLANDB_STATS_RX_BYTES, u64_stats_read(&stats.rx_bytes), BRIDGE_VLANDB_STATS_PAD) || nla_put_u64_64bit(skb, BRIDGE_VLANDB_STATS_RX_PACKETS, u64_stats_read(&stats.rx_packets), BRIDGE_VLANDB_STATS_PAD) || nla_put_u64_64bit(skb, BRIDGE_VLANDB_STATS_TX_BYTES, u64_stats_read(&stats.tx_bytes), BRIDGE_VLANDB_STATS_PAD) || nla_put_u64_64bit(skb, BRIDGE_VLANDB_STATS_TX_PACKETS, u64_stats_read(&stats.tx_packets), BRIDGE_VLANDB_STATS_PAD)) goto out_err; nla_nest_end(skb, nest); return true; out_err: nla_nest_cancel(skb, nest); return false; } /* v_opts is used to dump the options which must be equal in the whole range */ static bool br_vlan_fill_vids(struct sk_buff *skb, u16 vid, u16 vid_range, const struct net_bridge_vlan *v_opts, const struct net_bridge_port *p, u16 flags, bool dump_stats) { struct bridge_vlan_info info; struct nlattr *nest; nest = nla_nest_start(skb, BRIDGE_VLANDB_ENTRY); if (!nest) return false; memset(&info, 0, sizeof(info)); info.vid = vid; if (flags & BRIDGE_VLAN_INFO_UNTAGGED) info.flags |= BRIDGE_VLAN_INFO_UNTAGGED; if (flags & BRIDGE_VLAN_INFO_PVID) info.flags |= BRIDGE_VLAN_INFO_PVID; if (nla_put(skb, BRIDGE_VLANDB_ENTRY_INFO, sizeof(info), &info)) goto out_err; if (vid_range && vid < vid_range && !(flags & BRIDGE_VLAN_INFO_PVID) && nla_put_u16(skb, BRIDGE_VLANDB_ENTRY_RANGE, vid_range)) goto out_err; if (v_opts) { if (!br_vlan_opts_fill(skb, v_opts, p)) goto out_err; if (dump_stats && !br_vlan_stats_fill(skb, v_opts)) goto out_err; } nla_nest_end(skb, nest); return true; out_err: nla_nest_cancel(skb, nest); return false; } static size_t rtnl_vlan_nlmsg_size(void) { return NLMSG_ALIGN(sizeof(struct br_vlan_msg)) + nla_total_size(0) /* BRIDGE_VLANDB_ENTRY */ + nla_total_size(sizeof(u16)) /* BRIDGE_VLANDB_ENTRY_RANGE */ + nla_total_size(sizeof(struct bridge_vlan_info)) /* BRIDGE_VLANDB_ENTRY_INFO */ + br_vlan_opts_nl_size(); /* bridge vlan options */ } void br_vlan_notify(const struct net_bridge *br, const struct net_bridge_port *p, u16 vid, u16 vid_range, int cmd) { struct net_bridge_vlan_group *vg; struct net_bridge_vlan *v = NULL; struct br_vlan_msg *bvm; struct nlmsghdr *nlh; struct sk_buff *skb; int err = -ENOBUFS; struct net *net; u16 flags = 0; int ifindex; /* right now notifications are done only with rtnl held */ ASSERT_RTNL(); if (p) { ifindex = p->dev->ifindex; vg = nbp_vlan_group(p); net = dev_net(p->dev); } else { ifindex = br->dev->ifindex; vg = br_vlan_group(br); net = dev_net(br->dev); } skb = nlmsg_new(rtnl_vlan_nlmsg_size(), GFP_KERNEL); if (!skb) goto out_err; err = -EMSGSIZE; nlh = nlmsg_put(skb, 0, 0, cmd, sizeof(*bvm), 0); if (!nlh) goto out_err; bvm = nlmsg_data(nlh); memset(bvm, 0, sizeof(*bvm)); bvm->family = AF_BRIDGE; bvm->ifindex = ifindex; switch (cmd) { case RTM_NEWVLAN: /* need to find the vlan due to flags/options */ v = br_vlan_find(vg, vid); if (!v || !br_vlan_should_use(v)) goto out_kfree; flags = v->flags; if (br_get_pvid(vg) == v->vid) flags |= BRIDGE_VLAN_INFO_PVID; break; case RTM_DELVLAN: break; default: goto out_kfree; } if (!br_vlan_fill_vids(skb, vid, vid_range, v, p, flags, false)) goto out_err; nlmsg_end(skb, nlh); rtnl_notify(skb, net, 0, RTNLGRP_BRVLAN, NULL, GFP_KERNEL); return; out_err: rtnl_set_sk_err(net, RTNLGRP_BRVLAN, err); out_kfree: kfree_skb(skb); } /* check if v_curr can enter a range ending in range_end */ bool br_vlan_can_enter_range(const struct net_bridge_vlan *v_curr, const struct net_bridge_vlan *range_end) { return v_curr->vid - range_end->vid == 1 && range_end->flags == v_curr->flags && br_vlan_opts_eq_range(v_curr, range_end); } static int br_vlan_dump_dev(const struct net_device *dev, struct sk_buff *skb, struct netlink_callback *cb, u32 dump_flags) { struct net_bridge_vlan *v, *range_start = NULL, *range_end = NULL; bool dump_global = !!(dump_flags & BRIDGE_VLANDB_DUMPF_GLOBAL); bool dump_stats = !!(dump_flags & BRIDGE_VLANDB_DUMPF_STATS); struct net_bridge_vlan_group *vg; int idx = 0, s_idx = cb->args[1]; struct nlmsghdr *nlh = NULL; struct net_bridge_port *p; struct br_vlan_msg *bvm; struct net_bridge *br; int err = 0; u16 pvid; if (!netif_is_bridge_master(dev) && !netif_is_bridge_port(dev)) return -EINVAL; if (netif_is_bridge_master(dev)) { br = netdev_priv(dev); vg = br_vlan_group_rcu(br); p = NULL; } else { /* global options are dumped only for bridge devices */ if (dump_global) return 0; p = br_port_get_rcu(dev); if (WARN_ON(!p)) return -EINVAL; vg = nbp_vlan_group_rcu(p); br = p->br; } if (!vg) return 0; nlh = nlmsg_put(skb, NETLINK_CB(cb->skb).portid, cb->nlh->nlmsg_seq, RTM_NEWVLAN, sizeof(*bvm), NLM_F_MULTI); if (!nlh) return -EMSGSIZE; bvm = nlmsg_data(nlh); memset(bvm, 0, sizeof(*bvm)); bvm->family = PF_BRIDGE; bvm->ifindex = dev->ifindex; pvid = br_get_pvid(vg); /* idx must stay at range's beginning until it is filled in */ list_for_each_entry_rcu(v, &vg->vlan_list, vlist) { if (!dump_global && !br_vlan_should_use(v)) continue; if (idx < s_idx) { idx++; continue; } if (!range_start) { range_start = v; range_end = v; continue; } if (dump_global) { if (br_vlan_global_opts_can_enter_range(v, range_end)) goto update_end; if (!br_vlan_global_opts_fill(skb, range_start->vid, range_end->vid, range_start)) { err = -EMSGSIZE; break; } /* advance number of filled vlans */ idx += range_end->vid - range_start->vid + 1; range_start = v; } else if (dump_stats || v->vid == pvid || !br_vlan_can_enter_range(v, range_end)) { u16 vlan_flags = br_vlan_flags(range_start, pvid); if (!br_vlan_fill_vids(skb, range_start->vid, range_end->vid, range_start, p, vlan_flags, dump_stats)) { err = -EMSGSIZE; break; } /* advance number of filled vlans */ idx += range_end->vid - range_start->vid + 1; range_start = v; } update_end: range_end = v; } /* err will be 0 and range_start will be set in 3 cases here: * - first vlan (range_start == range_end) * - last vlan (range_start == range_end, not in range) * - last vlan range (range_start != range_end, in range) */ if (!err && range_start) { if (dump_global && !br_vlan_global_opts_fill(skb, range_start->vid, range_end->vid, range_start)) err = -EMSGSIZE; else if (!dump_global && !br_vlan_fill_vids(skb, range_start->vid, range_end->vid, range_start, p, br_vlan_flags(range_start, pvid), dump_stats)) err = -EMSGSIZE; } cb->args[1] = err ? idx : 0; nlmsg_end(skb, nlh); return err; } static const struct nla_policy br_vlan_db_dump_pol[BRIDGE_VLANDB_DUMP_MAX + 1] = { [BRIDGE_VLANDB_DUMP_FLAGS] = { .type = NLA_U32 }, }; static int br_vlan_rtm_dump(struct sk_buff *skb, struct netlink_callback *cb) { struct nlattr *dtb[BRIDGE_VLANDB_DUMP_MAX + 1]; int idx = 0, err = 0, s_idx = cb->args[0]; struct net *net = sock_net(skb->sk); struct br_vlan_msg *bvm; struct net_device *dev; u32 dump_flags = 0; err = nlmsg_parse(cb->nlh, sizeof(*bvm), dtb, BRIDGE_VLANDB_DUMP_MAX, br_vlan_db_dump_pol, cb->extack); if (err < 0) return err; bvm = nlmsg_data(cb->nlh); if (dtb[BRIDGE_VLANDB_DUMP_FLAGS]) dump_flags = nla_get_u32(dtb[BRIDGE_VLANDB_DUMP_FLAGS]); rcu_read_lock(); if (bvm->ifindex) { dev = dev_get_by_index_rcu(net, bvm->ifindex); if (!dev) { err = -ENODEV; goto out_err; } err = br_vlan_dump_dev(dev, skb, cb, dump_flags); /* if the dump completed without an error we return 0 here */ if (err != -EMSGSIZE) goto out_err; } else { for_each_netdev_rcu(net, dev) { if (idx < s_idx) goto skip; err = br_vlan_dump_dev(dev, skb, cb, dump_flags); if (err == -EMSGSIZE) break; skip: idx++; } } cb->args[0] = idx; rcu_read_unlock(); return skb->len; out_err: rcu_read_unlock(); return err; } static const struct nla_policy br_vlan_db_policy[BRIDGE_VLANDB_ENTRY_MAX + 1] = { [BRIDGE_VLANDB_ENTRY_INFO] = NLA_POLICY_EXACT_LEN(sizeof(struct bridge_vlan_info)), [BRIDGE_VLANDB_ENTRY_RANGE] = { .type = NLA_U16 }, [BRIDGE_VLANDB_ENTRY_STATE] = { .type = NLA_U8 }, [BRIDGE_VLANDB_ENTRY_TUNNEL_INFO] = { .type = NLA_NESTED }, [BRIDGE_VLANDB_ENTRY_MCAST_ROUTER] = { .type = NLA_U8 }, [BRIDGE_VLANDB_ENTRY_MCAST_N_GROUPS] = { .type = NLA_REJECT }, [BRIDGE_VLANDB_ENTRY_MCAST_MAX_GROUPS] = { .type = NLA_U32 }, [BRIDGE_VLANDB_ENTRY_NEIGH_SUPPRESS] = NLA_POLICY_MAX(NLA_U8, 1), }; static int br_vlan_rtm_process_one(struct net_device *dev, const struct nlattr *attr, int cmd, struct netlink_ext_ack *extack) { struct bridge_vlan_info *vinfo, vrange_end, *vinfo_last = NULL; struct nlattr *tb[BRIDGE_VLANDB_ENTRY_MAX + 1]; bool changed = false, skip_processing = false; struct net_bridge_vlan_group *vg; struct net_bridge_port *p = NULL; int err = 0, cmdmap = 0; struct net_bridge *br; if (netif_is_bridge_master(dev)) { br = netdev_priv(dev); vg = br_vlan_group(br); } else { p = br_port_get_rtnl(dev); if (WARN_ON(!p)) return -ENODEV; br = p->br; vg = nbp_vlan_group(p); } if (WARN_ON(!vg)) return -ENODEV; err = nla_parse_nested(tb, BRIDGE_VLANDB_ENTRY_MAX, attr, br_vlan_db_policy, extack); if (err) return err; if (!tb[BRIDGE_VLANDB_ENTRY_INFO]) { NL_SET_ERR_MSG_MOD(extack, "Missing vlan entry info"); return -EINVAL; } memset(&vrange_end, 0, sizeof(vrange_end)); vinfo = nla_data(tb[BRIDGE_VLANDB_ENTRY_INFO]); if (vinfo->flags & (BRIDGE_VLAN_INFO_RANGE_BEGIN | BRIDGE_VLAN_INFO_RANGE_END)) { NL_SET_ERR_MSG_MOD(extack, "Old-style vlan ranges are not allowed when using RTM vlan calls"); return -EINVAL; } if (!br_vlan_valid_id(vinfo->vid, extack)) return -EINVAL; if (tb[BRIDGE_VLANDB_ENTRY_RANGE]) { vrange_end.vid = nla_get_u16(tb[BRIDGE_VLANDB_ENTRY_RANGE]); /* validate user-provided flags without RANGE_BEGIN */ vrange_end.flags = BRIDGE_VLAN_INFO_RANGE_END | vinfo->flags; vinfo->flags |= BRIDGE_VLAN_INFO_RANGE_BEGIN; /* vinfo_last is the range start, vinfo the range end */ vinfo_last = vinfo; vinfo = &vrange_end; if (!br_vlan_valid_id(vinfo->vid, extack) || !br_vlan_valid_range(vinfo, vinfo_last, extack)) return -EINVAL; } switch (cmd) { case RTM_NEWVLAN: cmdmap = RTM_SETLINK; skip_processing = !!(vinfo->flags & BRIDGE_VLAN_INFO_ONLY_OPTS); break; case RTM_DELVLAN: cmdmap = RTM_DELLINK; break; } if (!skip_processing) { struct bridge_vlan_info *tmp_last = vinfo_last; /* br_process_vlan_info may overwrite vinfo_last */ err = br_process_vlan_info(br, p, cmdmap, vinfo, &tmp_last, &changed, extack); /* notify first if anything changed */ if (changed) br_ifinfo_notify(cmdmap, br, p); if (err) return err; } /* deal with options */ if (cmd == RTM_NEWVLAN) { struct net_bridge_vlan *range_start, *range_end; if (vinfo_last) { range_start = br_vlan_find(vg, vinfo_last->vid); range_end = br_vlan_find(vg, vinfo->vid); } else { range_start = br_vlan_find(vg, vinfo->vid); range_end = range_start; } err = br_vlan_process_options(br, p, range_start, range_end, tb, extack); } return err; } static int br_vlan_rtm_process(struct sk_buff *skb, struct nlmsghdr *nlh, struct netlink_ext_ack *extack) { struct net *net = sock_net(skb->sk); struct br_vlan_msg *bvm; struct net_device *dev; struct nlattr *attr; int err, vlans = 0; int rem; /* this should validate the header and check for remaining bytes */ err = nlmsg_parse(nlh, sizeof(*bvm), NULL, BRIDGE_VLANDB_MAX, NULL, extack); if (err < 0) return err; bvm = nlmsg_data(nlh); dev = __dev_get_by_index(net, bvm->ifindex); if (!dev) return -ENODEV; if (!netif_is_bridge_master(dev) && !netif_is_bridge_port(dev)) { NL_SET_ERR_MSG_MOD(extack, "The device is not a valid bridge or bridge port"); return -EINVAL; } nlmsg_for_each_attr(attr, nlh, sizeof(*bvm), rem) { switch (nla_type(attr)) { case BRIDGE_VLANDB_ENTRY: err = br_vlan_rtm_process_one(dev, attr, nlh->nlmsg_type, extack); break; case BRIDGE_VLANDB_GLOBAL_OPTIONS: err = br_vlan_rtm_process_global_options(dev, attr, nlh->nlmsg_type, extack); break; default: continue; } vlans++; if (err) break; } if (!vlans) { NL_SET_ERR_MSG_MOD(extack, "No vlans found to process"); err = -EINVAL; } return err; } static const struct rtnl_msg_handler br_vlan_rtnl_msg_handlers[] = { {THIS_MODULE, PF_BRIDGE, RTM_NEWVLAN, br_vlan_rtm_process, NULL, 0}, {THIS_MODULE, PF_BRIDGE, RTM_DELVLAN, br_vlan_rtm_process, NULL, 0}, {THIS_MODULE, PF_BRIDGE, RTM_GETVLAN, NULL, br_vlan_rtm_dump, 0}, }; int br_vlan_rtnl_init(void) { return rtnl_register_many(br_vlan_rtnl_msg_handlers); } void br_vlan_rtnl_uninit(void) { rtnl_unregister_many(br_vlan_rtnl_msg_handlers); } |
| 58 58 385 1065 1060 385 359 104 385 58 | 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 | // SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB /* * Copyright (c) 2005 Voltaire Inc. All rights reserved. * Copyright (c) 2002-2005, Network Appliance, Inc. All rights reserved. * Copyright (c) 1999-2019, Mellanox Technologies, Inc. All rights reserved. * Copyright (c) 2005-2006 Intel Corporation. All rights reserved. */ #include <linux/completion.h> #include <linux/in.h> #include <linux/in6.h> #include <linux/mutex.h> #include <linux/random.h> #include <linux/rbtree.h> #include <linux/igmp.h> #include <linux/xarray.h> #include <linux/inetdevice.h> #include <linux/slab.h> #include <linux/module.h> #include <net/route.h> #include <net/net_namespace.h> #include <net/netns/generic.h> #include <net/netevent.h> #include <net/tcp.h> #include <net/ipv6.h> #include <net/ip_fib.h> #include <net/ip6_route.h> #include <rdma/rdma_cm.h> #include <rdma/rdma_cm_ib.h> #include <rdma/rdma_netlink.h> #include <rdma/ib.h> #include <rdma/ib_cache.h> #include <rdma/ib_cm.h> #include <rdma/ib_sa.h> #include <rdma/iw_cm.h> #include "core_priv.h" #include "cma_priv.h" #include "cma_trace.h" MODULE_AUTHOR("Sean Hefty"); MODULE_DESCRIPTION("Generic RDMA CM Agent"); MODULE_LICENSE("Dual BSD/GPL"); #define CMA_CM_RESPONSE_TIMEOUT 20 #define CMA_MAX_CM_RETRIES 15 #define CMA_CM_MRA_SETTING (IB_CM_MRA_FLAG_DELAY | 24) #define CMA_IBOE_PACKET_LIFETIME 16 #define CMA_PREFERRED_ROCE_GID_TYPE IB_GID_TYPE_ROCE_UDP_ENCAP static const char * const cma_events[] = { [RDMA_CM_EVENT_ADDR_RESOLVED] = "address resolved", [RDMA_CM_EVENT_ADDR_ERROR] = "address error", [RDMA_CM_EVENT_ROUTE_RESOLVED] = "route resolved ", [RDMA_CM_EVENT_ROUTE_ERROR] = "route error", [RDMA_CM_EVENT_CONNECT_REQUEST] = "connect request", [RDMA_CM_EVENT_CONNECT_RESPONSE] = "connect response", [RDMA_CM_EVENT_CONNECT_ERROR] = "connect error", [RDMA_CM_EVENT_UNREACHABLE] = "unreachable", [RDMA_CM_EVENT_REJECTED] = "rejected", [RDMA_CM_EVENT_ESTABLISHED] = "established", [RDMA_CM_EVENT_DISCONNECTED] = "disconnected", [RDMA_CM_EVENT_DEVICE_REMOVAL] = "device removal", [RDMA_CM_EVENT_MULTICAST_JOIN] = "multicast join", [RDMA_CM_EVENT_MULTICAST_ERROR] = "multicast error", [RDMA_CM_EVENT_ADDR_CHANGE] = "address change", [RDMA_CM_EVENT_TIMEWAIT_EXIT] = "timewait exit", }; static void cma_iboe_set_mgid(struct sockaddr *addr, union ib_gid *mgid, enum ib_gid_type gid_type); const char *__attribute_const__ rdma_event_msg(enum rdma_cm_event_type event) { size_t index = event; return (index < ARRAY_SIZE(cma_events) && cma_events[index]) ? cma_events[index] : "unrecognized event"; } EXPORT_SYMBOL(rdma_event_msg); const char *__attribute_const__ rdma_reject_msg(struct rdma_cm_id *id, int reason) { if (rdma_ib_or_roce(id->device, id->port_num)) return ibcm_reject_msg(reason); if (rdma_protocol_iwarp(id->device, id->port_num)) return iwcm_reject_msg(reason); WARN_ON_ONCE(1); return "unrecognized transport"; } EXPORT_SYMBOL(rdma_reject_msg); /** * rdma_is_consumer_reject - return true if the consumer rejected the connect * request. * @id: Communication identifier that received the REJECT event. * @reason: Value returned in the REJECT event status field. */ static bool rdma_is_consumer_reject(struct rdma_cm_id *id, int reason) { if (rdma_ib_or_roce(id->device, id->port_num)) return reason == IB_CM_REJ_CONSUMER_DEFINED; if (rdma_protocol_iwarp(id->device, id->port_num)) return reason == -ECONNREFUSED; WARN_ON_ONCE(1); return false; } const void *rdma_consumer_reject_data(struct rdma_cm_id *id, struct rdma_cm_event *ev, u8 *data_len) { const void *p; if (rdma_is_consumer_reject(id, ev->status)) { *data_len = ev->param.conn.private_data_len; p = ev->param.conn.private_data; } else { *data_len = 0; p = NULL; } return p; } EXPORT_SYMBOL(rdma_consumer_reject_data); /** * rdma_iw_cm_id() - return the iw_cm_id pointer for this cm_id. * @id: Communication Identifier */ struct iw_cm_id *rdma_iw_cm_id(struct rdma_cm_id *id) { struct rdma_id_private *id_priv; id_priv = container_of(id, struct rdma_id_private, id); if (id->device->node_type == RDMA_NODE_RNIC) return id_priv->cm_id.iw; return NULL; } EXPORT_SYMBOL(rdma_iw_cm_id); /** * rdma_res_to_id() - return the rdma_cm_id pointer for this restrack. * @res: rdma resource tracking entry pointer */ struct rdma_cm_id *rdma_res_to_id(struct rdma_restrack_entry *res) { struct rdma_id_private *id_priv = container_of(res, struct rdma_id_private, res); return &id_priv->id; } EXPORT_SYMBOL(rdma_res_to_id); static int cma_add_one(struct ib_device *device); static void cma_remove_one(struct ib_device *device, void *client_data); static struct ib_client cma_client = { .name = "cma", .add = cma_add_one, .remove = cma_remove_one }; static struct ib_sa_client sa_client; static LIST_HEAD(dev_list); static LIST_HEAD(listen_any_list); static DEFINE_MUTEX(lock); static struct rb_root id_table = RB_ROOT; /* Serialize operations of id_table tree */ static DEFINE_SPINLOCK(id_table_lock); static struct workqueue_struct *cma_wq; static unsigned int cma_pernet_id; struct cma_pernet { struct xarray tcp_ps; struct xarray udp_ps; struct xarray ipoib_ps; struct xarray ib_ps; }; static struct cma_pernet *cma_pernet(struct net *net) { return net_generic(net, cma_pernet_id); } static struct xarray *cma_pernet_xa(struct net *net, enum rdma_ucm_port_space ps) { struct cma_pernet *pernet = cma_pernet(net); switch (ps) { case RDMA_PS_TCP: return &pernet->tcp_ps; case RDMA_PS_UDP: return &pernet->udp_ps; case RDMA_PS_IPOIB: return &pernet->ipoib_ps; case RDMA_PS_IB: return &pernet->ib_ps; default: return NULL; } } struct id_table_entry { struct list_head id_list; struct rb_node rb_node; }; struct cma_device { struct list_head list; struct ib_device *device; struct completion comp; refcount_t refcount; struct list_head id_list; enum ib_gid_type *default_gid_type; u8 *default_roce_tos; }; struct rdma_bind_list { enum rdma_ucm_port_space ps; struct hlist_head owners; unsigned short port; }; static int cma_ps_alloc(struct net *net, enum rdma_ucm_port_space ps, struct rdma_bind_list *bind_list, int snum) { struct xarray *xa = cma_pernet_xa(net, ps); return xa_insert(xa, snum, bind_list, GFP_KERNEL); } static struct rdma_bind_list *cma_ps_find(struct net *net, enum rdma_ucm_port_space ps, int snum) { struct xarray *xa = cma_pernet_xa(net, ps); return xa_load(xa, snum); } static void cma_ps_remove(struct net *net, enum rdma_ucm_port_space ps, int snum) { struct xarray *xa = cma_pernet_xa(net, ps); xa_erase(xa, snum); } enum { CMA_OPTION_AFONLY, }; void cma_dev_get(struct cma_device *cma_dev) { refcount_inc(&cma_dev->refcount); } void cma_dev_put(struct cma_device *cma_dev) { if (refcount_dec_and_test(&cma_dev->refcount)) complete(&cma_dev->comp); } struct cma_device *cma_enum_devices_by_ibdev(cma_device_filter filter, void *cookie) { struct cma_device *cma_dev; struct cma_device *found_cma_dev = NULL; mutex_lock(&lock); list_for_each_entry(cma_dev, &dev_list, list) if (filter(cma_dev->device, cookie)) { found_cma_dev = cma_dev; break; } if (found_cma_dev) cma_dev_get(found_cma_dev); mutex_unlock(&lock); return found_cma_dev; } int cma_get_default_gid_type(struct cma_device *cma_dev, u32 port) { if (!rdma_is_port_valid(cma_dev->device, port)) return -EINVAL; return cma_dev->default_gid_type[port - rdma_start_port(cma_dev->device)]; } int cma_set_default_gid_type(struct cma_device *cma_dev, u32 port, enum ib_gid_type default_gid_type) { unsigned long supported_gids; if (!rdma_is_port_valid(cma_dev->device, port)) return -EINVAL; if (default_gid_type == IB_GID_TYPE_IB && rdma_protocol_roce_eth_encap(cma_dev->device, port)) default_gid_type = IB_GID_TYPE_ROCE; supported_gids = roce_gid_type_mask_support(cma_dev->device, port); if (!(supported_gids & 1 << default_gid_type)) return -EINVAL; cma_dev->default_gid_type[port - rdma_start_port(cma_dev->device)] = default_gid_type; return 0; } int cma_get_default_roce_tos(struct cma_device *cma_dev, u32 port) { if (!rdma_is_port_valid(cma_dev->device, port)) return -EINVAL; return cma_dev->default_roce_tos[port - rdma_start_port(cma_dev->device)]; } int cma_set_default_roce_tos(struct cma_device *cma_dev, u32 port, u8 default_roce_tos) { if (!rdma_is_port_valid(cma_dev->device, port)) return -EINVAL; cma_dev->default_roce_tos[port - rdma_start_port(cma_dev->device)] = default_roce_tos; return 0; } struct ib_device *cma_get_ib_dev(struct cma_device *cma_dev) { return cma_dev->device; } /* * Device removal can occur at anytime, so we need extra handling to * serialize notifying the user of device removal with other callbacks. * We do this by disabling removal notification while a callback is in process, * and reporting it after the callback completes. */ struct cma_multicast { struct rdma_id_private *id_priv; union { struct ib_sa_multicast *sa_mc; struct { struct work_struct work; struct rdma_cm_event event; } iboe_join; }; struct list_head list; void *context; struct sockaddr_storage addr; u8 join_state; }; struct cma_work { struct work_struct work; struct rdma_id_private *id; enum rdma_cm_state old_state; enum rdma_cm_state new_state; struct rdma_cm_event event; }; union cma_ip_addr { struct in6_addr ip6; struct { __be32 pad[3]; __be32 addr; } ip4; }; struct cma_hdr { u8 cma_version; u8 ip_version; /* IP version: 7:4 */ __be16 port; union cma_ip_addr src_addr; union cma_ip_addr dst_addr; }; #define CMA_VERSION 0x00 struct cma_req_info { struct sockaddr_storage listen_addr_storage; struct sockaddr_storage src_addr_storage; struct ib_device *device; union ib_gid local_gid; __be64 service_id; int port; bool has_gid; u16 pkey; }; static int cma_comp_exch(struct rdma_id_private *id_priv, enum rdma_cm_state comp, enum rdma_cm_state exch) { unsigned long flags; int ret; /* * The FSM uses a funny double locking where state is protected by both * the handler_mutex and the spinlock. State is not allowed to change * to/from a handler_mutex protected value without also holding * handler_mutex. */ if (comp == RDMA_CM_CONNECT || exch == RDMA_CM_CONNECT) lockdep_assert_held(&id_priv->handler_mutex); spin_lock_irqsave(&id_priv->lock, flags); if ((ret = (id_priv->state == comp))) id_priv->state = exch; spin_unlock_irqrestore(&id_priv->lock, flags); return ret; } static inline u8 cma_get_ip_ver(const struct cma_hdr *hdr) { return hdr->ip_version >> 4; } static void cma_set_ip_ver(struct cma_hdr *hdr, u8 ip_ver) { hdr->ip_version = (ip_ver << 4) | (hdr->ip_version & 0xF); } static struct sockaddr *cma_src_addr(struct rdma_id_private *id_priv) { return (struct sockaddr *)&id_priv->id.route.addr.src_addr; } static inline struct sockaddr *cma_dst_addr(struct rdma_id_private *id_priv) { return (struct sockaddr *)&id_priv->id.route.addr.dst_addr; } static int cma_igmp_send(struct net_device *ndev, union ib_gid *mgid, bool join) { struct in_device *in_dev = NULL; if (ndev) { rtnl_lock(); in_dev = __in_dev_get_rtnl(ndev); if (in_dev) { if (join) ip_mc_inc_group(in_dev, *(__be32 *)(mgid->raw + 12)); else ip_mc_dec_group(in_dev, *(__be32 *)(mgid->raw + 12)); } rtnl_unlock(); } return (in_dev) ? 0 : -ENODEV; } static int compare_netdev_and_ip(int ifindex_a, struct sockaddr *sa, struct id_table_entry *entry_b) { struct rdma_id_private *id_priv = list_first_entry( &entry_b->id_list, struct rdma_id_private, id_list_entry); int ifindex_b = id_priv->id.route.addr.dev_addr.bound_dev_if; struct sockaddr *sb = cma_dst_addr(id_priv); if (ifindex_a != ifindex_b) return (ifindex_a > ifindex_b) ? 1 : -1; if (sa->sa_family != sb->sa_family) return sa->sa_family - sb->sa_family; if (sa->sa_family == AF_INET && __builtin_object_size(sa, 0) >= sizeof(struct sockaddr_in)) { return memcmp(&((struct sockaddr_in *)sa)->sin_addr, &((struct sockaddr_in *)sb)->sin_addr, sizeof(((struct sockaddr_in *)sa)->sin_addr)); } if (sa->sa_family == AF_INET6 && __builtin_object_size(sa, 0) >= sizeof(struct sockaddr_in6)) { return ipv6_addr_cmp(&((struct sockaddr_in6 *)sa)->sin6_addr, &((struct sockaddr_in6 *)sb)->sin6_addr); } return -1; } static int cma_add_id_to_tree(struct rdma_id_private *node_id_priv) { struct rb_node **new, *parent = NULL; struct id_table_entry *this, *node; unsigned long flags; int result; node = kzalloc(sizeof(*node), GFP_KERNEL); if (!node) return -ENOMEM; spin_lock_irqsave(&id_table_lock, flags); new = &id_table.rb_node; while (*new) { this = container_of(*new, struct id_table_entry, rb_node); result = compare_netdev_and_ip( node_id_priv->id.route.addr.dev_addr.bound_dev_if, cma_dst_addr(node_id_priv), this); parent = *new; if (result < 0) new = &((*new)->rb_left); else if (result > 0) new = &((*new)->rb_right); else { list_add_tail(&node_id_priv->id_list_entry, &this->id_list); kfree(node); goto unlock; } } INIT_LIST_HEAD(&node->id_list); list_add_tail(&node_id_priv->id_list_entry, &node->id_list); rb_link_node(&node->rb_node, parent, new); rb_insert_color(&node->rb_node, &id_table); unlock: spin_unlock_irqrestore(&id_table_lock, flags); return 0; } static struct id_table_entry * node_from_ndev_ip(struct rb_root *root, int ifindex, struct sockaddr *sa) { struct rb_node *node = root->rb_node; struct id_table_entry *data; int result; while (node) { data = container_of(node, struct id_table_entry, rb_node); result = compare_netdev_and_ip(ifindex, sa, data); if (result < 0) node = node->rb_left; |